feat: controller-owned allocator API on control-plane DB (Closes #600)

Add gitea_allocate_next_work and allocator_service routing policy on top of
the #613 ControlPlaneDB substrate. Workers get atomic assign+lease results
(or wait/no_safe_work/terminal-path outcomes) without self-selecting work
via file locks or comment-only leases. #612 remains downstream.

Closes #600

README.md

@@ -53,6 +53,7 @@ Any MCP-compatible agent (Antigravity, Claude Code, etc.) can call these tools n
 | `gitea_whoami` | Read-only: identify the authenticated Gitea account (safe metadata only) |
 | `gitea_get_profile` | Read-only: describe the active runtime execution profile (safe metadata only) |
 | `gitea_check_pr_eligibility` | Read-only: check if the current identity/profile may review/approve/request_changes/merge a PR |
+| `gitea_assess_conflict_fix_classification` | Read-only: classify conflict-fix need from a live PR head re-fetch before creating a conflict-fix worktree |
 | `gitea_submit_pr_review` | Gated review mutation: comment/approve/request_changes, only after identity+profile+eligibility gates pass (no merge, no self-approval) |
 | `gitea_mark_issue` | Claim/release an issue (start/done) |
 | `gitea_list_labels` | List all available labels in a repository |

allocator_service.py

@@ -0,0 +1,610 @@
+"""Controller-owned work allocator policy (#600).
+
+Builds on the #613 control-plane DB substrate (``ControlPlaneDB.assign_and_lease``).
+
+Workers must not self-select exclusive work under the standard multi-LLM
+workflow. They call ``gitea_allocate_next_work`` which:
+
+1. Inspects candidate Gitea issues/PRs (never raw monitoring incidents).
+2. Applies ADR routing policy (role, terminal path, leases, blocked, deps).
+3. Atomically assigns + leases the selected item in one DB transaction.
+
+This module is pure selection + substrate orchestration. Gitea I/O for live
+inventory lives in the MCP tool wrapper so tests can inject candidates.
+
+#612 remains downstream: bridge-created Gitea issues become candidates only
+after they exist as normal issues; this module never assigns incidents.
+"""
+
+from __future__ import annotations
+
+import os
+import uuid
+from dataclasses import dataclass, field
+from typing import Any, Sequence
+
+from control_plane_db import (
+    ControlPlaneDB,
+    ControlPlaneError,
+    InvalidWorkKindError,
+    LeaseRequiredError,
+    WORK_KINDS,
+)
+
+# Outcomes required by #600 / ADR §5.
+OUTCOME_ASSIGNED = "assigned_work"
+OUTCOME_WAIT = "wait"
+OUTCOME_BLOCKED_TERMINAL = "blocked_by_terminal_path"
+OUTCOME_BLOCKED_LEASE = "blocked_by_active_lease"
+OUTCOME_NEEDS_CONTROLLER = "needs_controller"
+OUTCOME_NO_SAFE = "no_safe_work"
+OUTCOME_ROLE_INELIGIBLE = "role_ineligible"
+OUTCOME_PREVIEW = "preview"  # dry-run only (apply=false)
+
+ROLE_AUTHOR = "author"
+ROLE_REVIEWER = "reviewer"
+ROLE_MERGER = "merger"
+ROLE_RECONCILER = "reconciler"
+ROLE_CONTROLLER = "controller"
+
+VALID_ROLES = frozenset(
+    {ROLE_AUTHOR, ROLE_REVIEWER, ROLE_MERGER, ROLE_RECONCILER, ROLE_CONTROLLER}
+)
+
+# Default action matrices by role (mutation gate will re-check).
+ROLE_ACTIONS: dict[str, tuple[tuple[str, ...], tuple[str, ...]]] = {
+    ROLE_AUTHOR: (
+        ("implement", "comment", "push", "create_pr"),
+        ("approve", "merge", "request_changes", "self_select_without_assignment"),
+    ),
+    ROLE_REVIEWER: (
+        ("review", "comment", "approve", "request_changes"),
+        ("merge", "push", "create_pr", "self_select_without_assignment"),
+    ),
+    ROLE_MERGER: (
+        ("merge", "comment"),
+        ("approve", "request_changes", "push", "create_pr", "self_select_without_assignment"),
+    ),
+    ROLE_RECONCILER: (
+        ("comment", "diagnose", "cleanup"),
+        ("approve", "merge", "push", "create_pr", "self_select_without_assignment"),
+    ),
+    ROLE_CONTROLLER: (
+        ("comment", "diagnose", "allocate"),
+        ("approve", "merge", "push", "create_pr"),
+    ),
+}
+
+
+@dataclass
+class WorkCandidate:
+    """One assignable Gitea issue or PR presented to the allocator."""
+
+    kind: str  # issue | pr
+    number: int
+    state: str = "open"
+    labels: tuple[str, ...] = ()
+    title: str = ""
+    priority: int = 0
+    head_sha: str | None = None
+    # Routing signals (callers derive from Gitea / review feedback).
+    request_changes_current_head: bool = False
+    approval_on_current_head: bool = False
+    approval_stale: bool = False
+    approval_contaminated: bool = False
+    mergeable: bool = False
+    blocked: bool = False
+    dependency_unmet: bool = False
+    dependency_reason: str | None = None
+    already_claimed_elsewhere: bool = False
+
+    def __post_init__(self) -> None:
+        self.kind = (self.kind or "").strip().lower()
+        self.state = (self.state or "open").strip().lower()
+        self.labels = tuple(
+            str(x).strip().lower() for x in (self.labels or ()) if str(x).strip()
+        )
+        if self.kind not in WORK_KINDS:
+            raise InvalidWorkKindError(
+                f"candidate kind '{self.kind}' is not assignable; only "
+                f"{sorted(WORK_KINDS)} (never raw incidents)"
+            )
+
+    def as_dict(self) -> dict[str, Any]:
+        return {
+            "kind": self.kind,
+            "number": self.number,
+            "state": self.state,
+            "labels": list(self.labels),
+            "title": self.title,
+            "priority": self.priority,
+            "head_sha": self.head_sha,
+            "request_changes_current_head": self.request_changes_current_head,
+            "approval_on_current_head": self.approval_on_current_head,
+            "approval_stale": self.approval_stale,
+            "approval_contaminated": self.approval_contaminated,
+            "mergeable": self.mergeable,
+            "blocked": self.blocked,
+            "dependency_unmet": self.dependency_unmet,
+            "dependency_reason": self.dependency_reason,
+        }
+
+
+@dataclass
+class SkipRecord:
+    kind: str
+    number: int
+    reason: str
+
+    def as_dict(self) -> dict[str, Any]:
+        return {"kind": self.kind, "number": self.number, "reason": self.reason}
+
+
+def normalize_role(role: str | None, *, profile_name: str | None = None) -> str:
+    """Map profile/role strings to a canonical allocator role."""
+    raw = (role or "").strip().lower()
+    if raw in VALID_ROLES:
+        return raw
+    prof = (profile_name or "").strip().lower()
+    for token in VALID_ROLES:
+        if token in prof or prof.endswith(f"-{token}"):
+            return token
+    if "author" in raw:
+        return ROLE_AUTHOR
+    if "review" in raw:
+        return ROLE_REVIEWER
+    if "merg" in raw:
+        return ROLE_MERGER
+    if "reconcil" in raw:
+        return ROLE_RECONCILER
+    if "control" in raw:
+        return ROLE_CONTROLLER
+    raise ControlPlaneError(
+        f"unknown allocator role '{role}' (profile={profile_name!r}); "
+        f"expected one of {sorted(VALID_ROLES)}"
+    )
+
+
+def expected_role_for_candidate(c: WorkCandidate) -> str:
+    """ADR §5.3 routing: which role should take this work next."""
+    if c.kind == "pr":
+        if c.approval_contaminated:
+            return ROLE_RECONCILER
+        if c.request_changes_current_head:
+            return ROLE_AUTHOR
+        if c.approval_stale:
+            return ROLE_REVIEWER
+        if c.approval_on_current_head and c.mergeable:
+            return ROLE_MERGER
+        # Open PR without terminal verdict → reviewer
+        return ROLE_REVIEWER
+    # Issues: ready work → author by default; blocked stays controller/none
+    labels = set(c.labels)
+    if "status:blocked" in labels or c.blocked:
+        return ROLE_CONTROLLER
+    return ROLE_AUTHOR
+
+
+def role_actions(role: str) -> tuple[tuple[str, ...], tuple[str, ...]]:
+    return ROLE_ACTIONS.get(role, ROLE_ACTIONS[ROLE_AUTHOR])
+
+
+def classify_skip(
+    c: WorkCandidate,
+    *,
+    role: str,
+    terminal_pr: int | None,
+) -> str | None:
+    """Return skip reason, or None if candidate is selectable for *role*."""
+    if c.state in ("merged", "closed"):
+        return f"{c.kind}#{c.number} is {c.state}; never assign"
+    if c.blocked or "status:blocked" in c.labels:
+        return f"{c.kind}#{c.number} is blocked"
+    if c.dependency_unmet:
+        return (
+            c.dependency_reason
+            or f"{c.kind}#{c.number} has unmet dependencies"
+        )
+    if c.already_claimed_elsewhere:
+        return f"{c.kind}#{c.number} already claimed elsewhere"
+    if c.kind == "pr" and not (c.head_sha or "").strip():
+        return f"pr#{c.number} missing head_sha pin"
+
+    # Terminal path first: when an active terminal PR exists, only that PR
+    # (or controller diagnosis) is assignable for review-path roles.
+    if terminal_pr is not None and c.kind == "pr" and c.number != terminal_pr:
+        if role in (ROLE_REVIEWER, ROLE_MERGER):
+            return (
+                f"pr#{c.number} skipped: active terminal-review lock on "
+                f"PR #{terminal_pr} must be resolved first"
+            )
+
+    expected = expected_role_for_candidate(c)
+    if role == ROLE_CONTROLLER:
+        # Controller may inspect anything but only assigns diagnosis targets
+        # when contaminated / blocked.
+        if expected == ROLE_RECONCILER or c.blocked:
+            return None
+        return f"{c.kind}#{c.number} does not require controller (expected {expected})"
+
+    if role != expected:
+        return (
+            f"{c.kind}#{c.number} expects role '{expected}', active role is '{role}'"
+        )
+
+    # Ready-gate for issues: prefer status:ready when labels present.
+    if c.kind == "issue" and c.labels:
+        if "status:ready" not in c.labels and "status:in-progress" not in c.labels:
+            # Allow unlabeled open issues; only skip explicit non-ready states.
+            if any(l.startswith("status:") for l in c.labels):
+                return f"issue#{c.number} not status:ready ({','.join(c.labels)})"
+    return None
+
+
+def sort_candidates(candidates: Sequence[WorkCandidate]) -> list[WorkCandidate]:
+    """Higher priority first; then lower number (older issues) for stability."""
+    return sorted(
+        candidates,
+        key=lambda c: (-int(c.priority), c.kind != "pr", int(c.number)),
+    )
+
+
+def allocate_next_work(
+    db: ControlPlaneDB,
+    *,
+    session_id: str,
+    role: str,
+    remote: str,
+    org: str,
+    repo: str,
+    candidates: Sequence[WorkCandidate],
+    apply: bool = False,
+    profile_name: str | None = None,
+    username: str | None = None,
+    lease_ttl_seconds: int | None = None,
+) -> dict[str, Any]:
+    """Select and optionally reserve the next work unit via control-plane DB.
+
+    *apply=False* (default): dry-run selection only — no lease/assignment.
+    *apply=True*: atomic ``assign_and_lease`` for the selected candidate.
+
+    Never uses file locks or comment-only leases as the assignment source.
+    """
+    if db is None:
+        return {
+            "success": False,
+            "outcome": OUTCOME_NO_SAFE,
+            "reasons": [
+                "control-plane DB substrate unavailable (fail closed, #600/#613)"
+            ],
+            "skipped": [],
+            "assignment": None,
+            "substrate": "control_plane_db",
+            "file_lock_only": False,
+            "comment_lease_only": False,
+        }
+
+    try:
+        role_norm = normalize_role(role, profile_name=profile_name)
+    except ControlPlaneError as exc:
+        return {
+            "success": False,
+            "outcome": OUTCOME_ROLE_INELIGIBLE,
+            "reasons": [str(exc)],
+            "skipped": [],
+            "assignment": None,
+            "substrate": "control_plane_db",
+        }
+
+    session_id = (session_id or "").strip() or f"alloc-{uuid.uuid4().hex[:12]}"
+    try:
+        db.upsert_session(
+            session_id=session_id,
+            role=role_norm,
+            profile=profile_name,
+            pid=os.getpid(),
+        )
+    except Exception as exc:  # noqa: BLE001 — surface structured
+        return {
+            "success": False,
+            "outcome": OUTCOME_NO_SAFE,
+            "reasons": [
+                f"failed to register session in control-plane DB: {exc} "
+                "(fail closed, #613)"
+            ],
+            "skipped": [],
+            "assignment": None,
+            "substrate": "control_plane_db",
+        }
+
+    # Expire stale leases globally before selection.
+    try:
+        db.expire_stale_leases()
+    except Exception as exc:  # noqa: BLE001
+        return {
+            "success": False,
+            "outcome": OUTCOME_NO_SAFE,
+            "reasons": [f"lease expiry failed: {exc} (fail closed)"],
+            "skipped": [],
+            "assignment": None,
+            "substrate": "control_plane_db",
+        }
+
+    terminal = None
+    try:
+        terminal = db.get_active_terminal_lock(remote=remote, org=org, repo=repo)
+    except Exception as exc:  # noqa: BLE001
+        return {
+            "success": False,
+            "outcome": OUTCOME_NO_SAFE,
+            "reasons": [f"terminal lock lookup failed: {exc} (fail closed)"],
+            "skipped": [],
+            "assignment": None,
+            "substrate": "control_plane_db",
+        }
+    terminal_pr = int(terminal["terminal_pr"]) if terminal else None
+
+    skipped: list[SkipRecord] = []
+    ordered = sort_candidates(list(candidates))
+    selected: WorkCandidate | None = None
+    for c in ordered:
+        reason = classify_skip(c, role=role_norm, terminal_pr=terminal_pr)
+        if reason:
+            skipped.append(SkipRecord(c.kind, c.number, reason))
+            continue
+        selected = c
+        break
+
+    if selected is None:
+        # If terminal lock blocks all review work, surface that explicitly.
+        if terminal_pr is not None and role_norm in (ROLE_REVIEWER, ROLE_MERGER):
+            outcome = OUTCOME_BLOCKED_TERMINAL
+            reasons = [
+                f"no safe work for role '{role_norm}': active terminal-review "
+                f"lock on PR #{terminal_pr} (resolve terminal path first, #332/#600)"
+            ]
+        else:
+            outcome = OUTCOME_NO_SAFE
+            reasons = [
+                f"no safe assignable work for role '{role_norm}' "
+                f"among {len(ordered)} candidates"
+            ]
+        return {
+            "success": True,
+            "outcome": outcome,
+            "apply": bool(apply),
+            "role": role_norm,
+            "profile_name": profile_name,
+            "username": username,
+            "session_id": session_id,
+            "remote": remote,
+            "org": org,
+            "repo": repo,
+            "selected": None,
+            "expected_role_next": None,
+            "reasons": reasons,
+            "skipped": [s.as_dict() for s in skipped],
+            "terminal_pr": terminal_pr,
+            "assignment": None,
+            "substrate": "control_plane_db",
+            "file_lock_only": False,
+            "comment_lease_only": False,
+            "downstream_note": (
+                "#612 incident bridge remains downstream of #600; "
+                "allocator never assigns raw monitoring incidents"
+            ),
+        }
+
+    expected_role = expected_role_for_candidate(selected)
+    allowed, forbidden = role_actions(role_norm)
+    selection = {
+        "kind": selected.kind,
+        "number": selected.number,
+        "title": selected.title,
+        "labels": list(selected.labels),
+        "head_sha": selected.head_sha,
+        "priority": selected.priority,
+        "expected_role_next": expected_role,
+        "reason_selected": (
+            f"highest-priority candidate for role '{role_norm}' "
+            f"(expected_role={expected_role})"
+        ),
+    }
+
+    if not apply:
+        return {
+            "success": True,
+            "outcome": OUTCOME_PREVIEW,
+            "apply": False,
+            "role": role_norm,
+            "profile_name": profile_name,
+            "username": username,
+            "session_id": session_id,
+            "remote": remote,
+            "org": org,
+            "repo": repo,
+            "selected": selection,
+            "expected_role_next": expected_role,
+            "reasons": [
+                "dry-run only (apply=false); no assignment/lease created — "
+                "call again with apply=true to reserve via control-plane DB"
+            ],
+            "skipped": [s.as_dict() for s in skipped],
+            "terminal_pr": terminal_pr,
+            "assignment": None,
+            "substrate": "control_plane_db",
+            "file_lock_only": False,
+            "comment_lease_only": False,
+            "downstream_note": (
+                "#612 incident bridge remains downstream of #600; "
+                "allocator never assigns raw monitoring incidents"
+            ),
+        }
+
+    # Atomic reserve via #613 substrate.
+    ttl = lease_ttl_seconds if lease_ttl_seconds is not None else None
+    try:
+        kwargs: dict[str, Any] = {
+            "session_id": session_id,
+            "role": role_norm,
+            "remote": remote,
+            "org": org,
+            "repo": repo,
+            "kind": selected.kind,
+            "number": selected.number,
+            "expected_head_sha": selected.head_sha,
+            "allowed_actions": allowed,
+            "forbidden_actions": forbidden,
+            "phase": "allocated",
+        }
+        if ttl is not None:
+            kwargs["lease_ttl_seconds"] = int(ttl)
+        result = db.assign_and_lease(**kwargs)
+    except (InvalidWorkKindError, LeaseRequiredError, ControlPlaneError) as exc:
+        return {
+            "success": False,
+            "outcome": OUTCOME_NO_SAFE,
+            "apply": True,
+            "role": role_norm,
+            "session_id": session_id,
+            "remote": remote,
+            "org": org,
+            "repo": repo,
+            "selected": selection,
+            "expected_role_next": expected_role,
+            "reasons": [f"atomic assign+lease failed: {exc} (fail closed, #613)"],
+            "skipped": [s.as_dict() for s in skipped],
+            "terminal_pr": terminal_pr,
+            "assignment": None,
+            "substrate": "control_plane_db",
+            "file_lock_only": False,
+            "comment_lease_only": False,
+        }
+
+    if result.outcome == "wait":
+        return {
+            "success": True,
+            "outcome": OUTCOME_WAIT,
+            "apply": True,
+            "role": role_norm,
+            "session_id": session_id,
+            "remote": remote,
+            "org": org,
+            "repo": repo,
+            "selected": selection,
+            "expected_role_next": expected_role,
+            "reasons": [result.reason or "foreign active lease"],
+            "skipped": [s.as_dict() for s in skipped],
+            "terminal_pr": terminal_pr,
+            "assignment": result.as_dict(),
+            "owner_session_id": result.owner_session_id,
+            "substrate": "control_plane_db",
+            "file_lock_only": False,
+            "comment_lease_only": False,
+        }
+
+    if result.outcome == "no_safe_work":
+        return {
+            "success": True,
+            "outcome": OUTCOME_NO_SAFE,
+            "apply": True,
+            "role": role_norm,
+            "session_id": session_id,
+            "remote": remote,
+            "org": org,
+            "repo": repo,
+            "selected": selection,
+            "expected_role_next": expected_role,
+            "reasons": [result.reason or "no_safe_work"],
+            "skipped": [s.as_dict() for s in skipped],
+            "terminal_pr": terminal_pr,
+            "assignment": result.as_dict(),
+            "substrate": "control_plane_db",
+            "file_lock_only": False,
+            "comment_lease_only": False,
+        }
+
+    # assigned
+    return {
+        "success": True,
+        "outcome": OUTCOME_ASSIGNED,
+        "apply": True,
+        "role": role_norm,
+        "profile_name": profile_name,
+        "username": username,
+        "session_id": session_id,
+        "remote": remote,
+        "org": org,
+        "repo": repo,
+        "selected": selection,
+        "expected_role_next": expected_role,
+        "reasons": [
+            selection["reason_selected"],
+            result.reason or "atomic assign+lease created",
+        ],
+        "skipped": [s.as_dict() for s in skipped],
+        "terminal_pr": terminal_pr,
+        "assignment": result.as_dict(),
+        "lease_proof": {
+            "assignment_id": result.assignment_id,
+            "lease_id": result.lease_id,
+            "expires_at": result.expires_at,
+            "expected_head_sha": result.expected_head_sha,
+            "allowed_actions": list(result.allowed_actions),
+            "forbidden_actions": list(result.forbidden_actions),
+            "source": "control_plane_db.assign_and_lease",
+        },
+        "next_valid_command": _next_command(role_norm, selected),
+        "substrate": "control_plane_db",
+        "file_lock_only": False,
+        "comment_lease_only": False,
+        "downstream_note": (
+            "#612 incident bridge remains downstream of #600; "
+            "allocator never assigns raw monitoring incidents"
+        ),
+    }
+
+
+def _next_command(role: str, c: WorkCandidate) -> str:
+    if role == ROLE_AUTHOR and c.kind == "issue":
+        return f"implement issue #{c.number} under a branches/ worktree; open PR when ready"
+    if role == ROLE_AUTHOR and c.kind == "pr":
+        return (
+            f"address REQUEST_CHANGES on PR #{c.number} at head "
+            f"{(c.head_sha or '')[:12]} and push fixes"
+        )
+    if role == ROLE_REVIEWER:
+        return (
+            f"review PR #{c.number} pinned at head {(c.head_sha or '')[:12]} "
+            "via full reviewer workflow"
+        )
+    if role == ROLE_MERGER:
+        return (
+            f"merge PR #{c.number} only with explicit operator MERGE "
+            f"authorization at head {(c.head_sha or '')[:12]}"
+        )
+    if role == ROLE_RECONCILER:
+        return f"diagnose contested state for {c.kind}#{c.number}"
+    return f"proceed on {c.kind}#{c.number} under role {role}"
+
+
+def candidate_from_dict(data: dict[str, Any]) -> WorkCandidate:
+    """Build a WorkCandidate from a plain dict (tests / MCP inventory)."""
+    return WorkCandidate(
+        kind=str(data.get("kind") or "issue"),
+        number=int(data["number"]),
+        state=str(data.get("state") or "open"),
+        labels=tuple(data.get("labels") or ()),
+        title=str(data.get("title") or ""),
+        priority=int(data.get("priority") or 0),
+        head_sha=data.get("head_sha"),
+        request_changes_current_head=bool(data.get("request_changes_current_head")),
+        approval_on_current_head=bool(data.get("approval_on_current_head")),
+        approval_stale=bool(data.get("approval_stale")),
+        approval_contaminated=bool(data.get("approval_contaminated")),
+        mergeable=bool(data.get("mergeable")),
+        blocked=bool(data.get("blocked")),
+        dependency_unmet=bool(data.get("dependency_unmet")),
+        dependency_reason=data.get("dependency_reason"),
+        already_claimed_elsewhere=bool(data.get("already_claimed_elsewhere")),
+    )

branch_cleanup_guard.py

@@ -0,0 +1,98 @@
+"""Guards for merged-PR branch cleanup and raw git delete bypasses (#514)."""
+
+from __future__ import annotations
+
+import re
+from typing import Any
+
+PROTECTED_BRANCHES = frozenset({"master", "main", "dev"})
+
+_RAW_BRANCH_DELETE_PATTERNS = (
+    re.compile(r"\bgit(?:\s+-C\s+\S+)?\s+branch\s+-[dD]\b[^\n\r]*", re.I),
+    re.compile(r"\bgit(?:\s+-C\s+\S+)?\s+push\b[^\n\r]*\s--delete\b[^\n\r]*", re.I),
+    re.compile(r"\bgit(?:\s+-C\s+\S+)?\s+push\b[^\n\r]*\s:[^\s`]+", re.I),
+)
+
+
+def raw_branch_delete_commands(text: str | None) -> list[str]:
+    """Return raw git branch-delete commands cited in *text*."""
+    if not text:
+        return []
+    commands: list[str] = []
+    for pattern in _RAW_BRANCH_DELETE_PATTERNS:
+        commands.extend(match.group(0).strip("` ") for match in pattern.finditer(text))
+    return list(dict.fromkeys(commands))
+
+
+def assess_raw_branch_delete_report(text: str | None) -> dict[str, Any]:
+    """Fail closed when a report uses raw git branch deletion as cleanup proof."""
+    commands = raw_branch_delete_commands(text)
+    reasons = [
+        (
+            "raw git branch deletion bypasses MCP branch.delete cleanup gates: "
+            f"{command}"
+        )
+        for command in commands
+    ]
+    return {
+        "proven": not reasons,
+        "block": bool(reasons),
+        "commands": commands,
+        "reasons": reasons,
+        "safe_next_action": (
+            "use gitea_cleanup_merged_pr_branch or another approved cleanup "
+            "helper with explicit branch.delete capability"
+            if reasons
+            else "proceed"
+        ),
+    }
+
+
+def assess_merged_pr_branch_cleanup(
+    *,
+    pr_number: int,
+    head_branch: str,
+    merged: bool,
+    remote_branch_exists: bool,
+    open_pr_heads: set[str],
+    head_on_target: bool | None,
+    delete_capability_allowed: bool,
+    confirmation: str | None,
+    protected_branches: frozenset[str] | None = None,
+) -> dict[str, Any]:
+    """Assess whether a merged PR source branch can be deleted via MCP."""
+    protected = protected_branches or PROTECTED_BRANCHES
+    expected_confirmation = f"CLEANUP MERGED PR {pr_number} BRANCH {head_branch}"
+    reasons: list[str] = []
+    if not merged:
+        reasons.append("PR is not merged")
+    if not remote_branch_exists:
+        reasons.append("remote branch already absent")
+    if not head_branch:
+        reasons.append("PR head branch is missing")
+    if head_branch in protected:
+        reasons.append(f"branch '{head_branch}' is protected")
+    if head_branch in open_pr_heads:
+        reasons.append("an open PR still references this head branch")
+    if head_on_target is False:
+        reasons.append("PR head is not an ancestor of the target branch")
+    if head_on_target is None:
+        reasons.append("PR head ancestry could not be proven")
+    if not delete_capability_allowed:
+        reasons.append("gitea.branch.delete capability is not allowed")
+    if confirmation != expected_confirmation:
+        reasons.append(
+            "confirmation must equal "
+            f"'{expected_confirmation}' for branch cleanup"
+        )
+
+    safe = not reasons
+    return {
+        "pr_number": pr_number,
+        "head_branch": head_branch,
+        "expected_confirmation": expected_confirmation,
+        "remote_branch_exists": remote_branch_exists,
+        "safe_to_delete": safe,
+        "block_reasons": reasons,
+        "recommended_action": "delete_remote_branch" if safe else "keep_remote_branch",
+    }

canonical_comment_validator.py

@@ -0,0 +1,408 @@
+"""Fail-closed validation for workflow-changing Gitea comments (#496)."""
+
+from __future__ import annotations
+
+import re
+from typing import Any
+
+VALID_ROLES = frozenset({
+    "controller",
+    "author",
+    "reviewer",
+    "merger",
+    "reconciler",
+    "user",
+})
+
+_BASE_REQUIRED = ("STATE", "WHO_IS_NEXT", "NEXT_ACTION", "NEXT_PROMPT", "WHY")
+
+_ISSUE_REQUIRED = _BASE_REQUIRED + ("BLOCKERS", "VALIDATION")
+_PR_REQUIRED = _BASE_REQUIRED + (
+    "ISSUE",
+    "HEAD_SHA",
+    "REVIEW_STATUS",
+    "MERGE_READY",
+    "BLOCKERS",
+    "VALIDATION",
+)
+_SUPERSESSION_REQUIRED = _BASE_REQUIRED + (
+    "CANONICAL_ITEM",
+    "SUPERSEDED_ITEM",
+    "CLOSE_OR_KEEP_OPEN",
+)
+
+_MACHINE_MARKERS = (
+    "<!-- mcp-review-lease:v1 -->",
+    "<!-- mcp-conflict-fix-lease:v1 -->",
+    "<!-- gitea-issue-claim-heartbeat:v1 -->",
+)
+
+_WORKFLOW_TRIGGERS = re.compile(
+    r"\b(?:"
+    r"blocked|unblocked|ready(?:\s+for\s+(?:review|merge|author))?|"
+    r"ready-to-merge|approved|approve|request\s+changes|changes\s+requested|"
+    r"superseded|duplicate|canonical|next\s+action|next\s+actor|who\s+is\s+next|"
+    r"author\s+should|reviewer\s+should|merger\s+should|reconciler\s+should|"
+    r"controller\s+should|issue\s+complete|pr\s+open|pr\s+merged|close\s+this|"
+    r"do\s+not\s+merge|needs?\s+rebase|stale\s+approval|contaminated\s+review|"
+    r"merge\s+ready|ready\s+for\s+merge"
+    r")\b",
+    re.IGNORECASE,
+)
+
+_CANONICAL_HEADINGS = (
+    "## Canonical Issue State",
+    "## Canonical PR State",
+    "## Canonical Discussion Summary",
+)
+
+_FIELD_RE = re.compile(
+    r"^([A-Z][A-Z0-9_]*)\s*:\s*(.*)$",
+    re.MULTILINE,
+)
+
+_VAGUE_NEXT_ACTIONS = frozenset({
+    "continue",
+    "handle this",
+    "fix it",
+    "follow up",
+    "follow-up",
+    "see above",
+    "see review",
+    "tbd",
+    "todo",
+    "as needed",
+    "proceed",
+    "next steps",
+    "will check",
+    "investigate",
+})
+
+_FULL_SHA_RE = re.compile(r"\b[0-9a-f]{40}\b", re.IGNORECASE)
+_SHORT_SHA_RE = re.compile(r"\b[0-9a-f]{7,40}\b", re.IGNORECASE)
+_PR_REF_RE = re.compile(r"(?:PR\s*#|pull\s*#)\d+|\b#\d{2,}\b", re.IGNORECASE)
+_APPROVAL_PROOF_RE = re.compile(
+    r"\b(?:approved|approval_at_current_head|APPROVE)\b",
+    re.IGNORECASE,
+)
+_UNBLOCK_RE = re.compile(
+    r"\b(?:unblock|until|after|once|when|requires?|must)\b",
+    re.IGNORECASE,
+)
+
+
+def _parse_fields(body: str) -> dict[str, str]:
+    """Parse KEY: value fields, including values continued on following lines."""
+    fields: dict[str, str] = {}
+    current_key: str | None = None
+    current_lines: list[str] = []
+
+    def _flush() -> None:
+        nonlocal current_key, current_lines
+        if current_key is not None:
+            fields[current_key] = "\n".join(current_lines).strip()
+        current_key = None
+        current_lines = []
+
+    for line in (body or "").splitlines():
+        if line.startswith("## "):
+            _flush()
+            continue
+        match = re.match(r"^([A-Z][A-Z0-9_]*)\s*:\s*(.*)$", line)
+        if match:
+            _flush()
+            current_key = match.group(1).strip().upper()
+            rest = match.group(2)
+            current_lines = [rest] if rest else []
+        elif current_key is not None:
+            current_lines.append(line)
+    _flush()
+    return fields
+
+
+def _is_machine_generated(body: str) -> bool:
+    text = body or ""
+    return any(marker in text for marker in _MACHINE_MARKERS)
+
+
+def _has_canonical_heading(body: str) -> bool:
+    return any(h in (body or "") for h in _CANONICAL_HEADINGS)
+
+
+def is_workflow_changing_comment(body: str) -> bool:
+    """True when comment text implies a workflow/state transition."""
+    text = (body or "").strip()
+    if not text:
+        return False
+    if _is_machine_generated(text):
+        return False
+    if _has_canonical_heading(text):
+        return True
+    if _WORKFLOW_TRIGGERS.search(text):
+        return True
+    fields = _parse_fields(text)
+    if "STATE" in fields or "WHO_IS_NEXT" in fields:
+        return True
+    return False
+
+
+def infer_comment_context(body: str, *, explicit: str | None = None) -> str:
+    if explicit:
+        return explicit
+    text = body or ""
+    if "## Canonical Discussion Summary" in text:
+        return "discussion_summary"
+    if "## Canonical PR State" in text:
+        return "pr_comment"
+    if "## Canonical Issue State" in text:
+        return "issue_comment"
+    fields = _parse_fields(text)
+    if fields.get("CANONICAL_ITEM") or fields.get("SUPERSEDED_ITEM"):
+        return "supersession"
+    if any(k in fields for k in ("HEAD_SHA", "REVIEW_STATUS", "MERGE_READY", "ISSUE")):
+        return "pr_comment"
+    return "issue_comment"
+
+
+def _required_fields_for_context(context: str) -> tuple[str, ...]:
+    if context in ("pr_comment", "pr_review"):
+        return _PR_REQUIRED
+    if context == "supersession":
+        return _SUPERSESSION_REQUIRED
+    if context == "discussion_summary":
+        return _BASE_REQUIRED + ("DECISION", "SUBSTANTIVE_COMMENTS")
+    return _ISSUE_REQUIRED
+
+
+def _is_vague_next_action(value: str) -> bool:
+    normalized = re.sub(r"\s+", " ", (value or "").strip().lower())
+    normalized = normalized.rstrip(".")
+    if not normalized:
+        return True
+    if normalized in _VAGUE_NEXT_ACTIONS:
+        return True
+    if len(normalized) < 12:
+        return True
+    return False
+
+
+def _next_prompt_ok(value: str) -> bool:
+    text = (value or "").strip()
+    if len(text) < 40:
+        return False
+    if text.lower() in {"n/a", "none", "tbd", "todo"}:
+        return False
+    return True
+
+
+def _state_value(fields: dict[str, str]) -> str:
+    return (fields.get("STATE") or "").strip().lower()
+
+
+def _suggested_template(context: str) -> str:
+    if context == "pr_comment" or context == "pr_review":
+        return (
+            "## Canonical PR State\n\n"
+            "STATE:\n"
+            "WHO_IS_NEXT:\n"
+            "NEXT_ACTION:\n"
+            "NEXT_PROMPT:\n"
+            "```text\n<paste-ready prompt>\n```\n"
+            "WHAT_HAPPENED:\n"
+            "WHY:\n"
+            "ISSUE:\n"
+            "HEAD_SHA:\n"
+            "REVIEW_STATUS:\n"
+            "MERGE_READY:\n"
+            "BLOCKERS:\n"
+            "VALIDATION:\n"
+            "LAST_UPDATED_BY:\n"
+        )
+    if context == "supersession":
+        return (
+            "## Canonical PR State\n\n"
+            "STATE:\nsuperseded\n"
+            "WHO_IS_NEXT:\nreconciler\n"
+            "NEXT_ACTION:\n"
+            "NEXT_PROMPT:\n"
+            "WHY:\n"
+            "CANONICAL_ITEM:\n"
+            "SUPERSEDED_ITEM:\n"
+            "CLOSE_OR_KEEP_OPEN:\n"
+        )
+    if context == "discussion_summary":
+        return (
+            "## Canonical Discussion Summary\n\n"
+            "STATE:\n"
+            "WHO_IS_NEXT:\n"
+            "DECISION:\n"
+            "WHY:\n"
+            "SUBSTANTIVE_COMMENTS:\n"
+            "NEXT_ACTION:\n"
+            "NEXT_PROMPT:\n"
+        )
+    return (
+        "## Canonical Issue State\n\n"
+        "STATE:\n"
+        "WHO_IS_NEXT:\n"
+        "NEXT_ACTION:\n"
+        "NEXT_PROMPT:\n"
+        "```text\n<paste-ready prompt>\n```\n"
+        "WHAT_HAPPENED:\n"
+        "WHY:\n"
+        "RELATED_PRS:\n"
+        "BLOCKERS:\n"
+        "VALIDATION:\n"
+        "LAST_UPDATED_BY:\n"
+    )
+
+
+def _build_correction_message(
+    *,
+    missing_fields: list[str],
+    vague_fields: list[str],
+    extra_reasons: list[str],
+    context: str,
+) -> str:
+    parts = [
+        "Canonical comment validation failed (fail closed before posting).",
+    ]
+    if missing_fields:
+        parts.append("Missing fields: " + ", ".join(missing_fields) + ".")
+    if vague_fields:
+        parts.append("Vague or invalid fields: " + ", ".join(vague_fields) + ".")
+    parts.extend(extra_reasons)
+    parts.append("Fill the suggested template and retry.")
+    parts.append("Suggested template:\n" + _suggested_template(context))
+    return "\n".join(parts)
+
+
+def assess_canonical_comment(
+    body: str,
+    *,
+    context: str | None = None,
+    force_workflow: bool = False,
+) -> dict[str, Any]:
+    """Validate outgoing comment text before a Gitea mutation."""
+    text = (body or "").strip()
+    ctx = infer_comment_context(text, explicit=context)
+
+    if not text:
+        return {
+            "allowed": True,
+            "is_workflow_comment": False,
+            "context": ctx,
+            "missing_fields": [],
+            "vague_fields": [],
+            "correction_message": "",
+            "suggested_template": "",
+        }
+
+    if _is_machine_generated(text):
+        return {
+            "allowed": True,
+            "is_workflow_comment": False,
+            "context": ctx,
+            "missing_fields": [],
+            "vague_fields": [],
+            "correction_message": "",
+            "suggested_template": "",
+        }
+
+    workflow = force_workflow or is_workflow_changing_comment(text)
+    if not workflow:
+        return {
+            "allowed": True,
+            "is_workflow_comment": False,
+            "context": ctx,
+            "missing_fields": [],
+            "vague_fields": [],
+            "correction_message": "",
+            "suggested_template": "",
+        }
+
+    fields = _parse_fields(text)
+    required = _required_fields_for_context(ctx)
+    missing = [name for name in required if not (fields.get(name) or "").strip()]
+
+    vague: list[str] = []
+    extra: list[str] = []
+
+    who = (fields.get("WHO_IS_NEXT") or "").strip().lower()
+    if who and who not in VALID_ROLES:
+        vague.append("WHO_IS_NEXT")
+        extra.append(
+            f"WHO_IS_NEXT must be one of: {', '.join(sorted(VALID_ROLES))}."
+        )
+
+    next_action = fields.get("NEXT_ACTION") or ""
+    if next_action and _is_vague_next_action(next_action):
+        vague.append("NEXT_ACTION")
+
+    next_prompt = fields.get("NEXT_PROMPT") or ""
+    if not _next_prompt_ok(next_prompt):
+        if "NEXT_PROMPT" not in missing:
+            vague.append("NEXT_PROMPT")
+
+    state = _state_value(fields)
+    blockers = (fields.get("BLOCKERS") or "").strip()
+    if "blocked" in state:
+        if not blockers or blockers.lower() in {"none", "n/a"}:
+            missing.append("BLOCKERS (unblock condition)")
+        elif not _UNBLOCK_RE.search(blockers):
+            vague.append("BLOCKERS")
+            extra.append("BLOCKED state requires an explicit unblock condition in BLOCKERS.")
+
+    if "superseded" in state:
+        canon = (fields.get("CANONICAL_ITEM") or fields.get("SUPERSEDED_BY") or "").strip()
+        superseded = (fields.get("SUPERSEDED_ITEM") or fields.get("SUPERSEDES") or "").strip()
+        if not canon and "CANONICAL_ITEM" not in missing:
+            missing.append("CANONICAL_ITEM")
+        if not superseded and "SUPERSEDED_ITEM" not in missing:
+            missing.append("SUPERSEDED_ITEM")
+
+    if "ready-to-merge" in state or "ready to merge" in state:
+        head_sha = fields.get("HEAD_SHA") or ""
+        merge_ready = fields.get("MERGE_READY") or ""
+        review_status = fields.get("REVIEW_STATUS") or ""
+        validation = fields.get("VALIDATION") or ""
+        proof_blob = " ".join((head_sha, merge_ready, review_status, validation))
+        has_sha = bool(_FULL_SHA_RE.search(proof_blob) or _SHORT_SHA_RE.search(proof_blob))
+        has_approval = bool(_APPROVAL_PROOF_RE.search(proof_blob))
+        if not has_sha or not has_approval:
+            extra.append(
+                "ready-to-merge STATE requires approval proof and HEAD_SHA in "
+                "REVIEW_STATUS, MERGE_READY, HEAD_SHA, or VALIDATION."
+            )
+
+    if ctx in ("pr_comment", "pr_review"):
+        head_sha = (fields.get("HEAD_SHA") or "").strip()
+        if not head_sha or not _SHORT_SHA_RE.search(head_sha):
+            if "HEAD_SHA" not in missing:
+                missing.append("HEAD_SHA")
+
+    if ctx == "issue_comment" and _PR_REF_RE.search(text):
+        related = (fields.get("RELATED_PRS") or "").strip()
+        if not related or related.lower() in {"none", "n/a", "-"}:
+            missing.append("RELATED_PRS")
+
+    allowed = not missing and not vague and not extra
+    correction = ""
+    if not allowed:
+        correction = _build_correction_message(
+            missing_fields=missing,
+            vague_fields=vague,
+            extra_reasons=extra,
+            context=ctx,
+        )
+
+    return {
+        "allowed": allowed,
+        "is_workflow_comment": True,
+        "context": ctx,
+        "missing_fields": missing,
+        "vague_fields": vague,
+        "extra_reasons": extra,
+        "correction_message": correction,
+        "suggested_template": _suggested_template(ctx) if not allowed else "",
+    }

canonical_state_comments.py

@@ -0,0 +1,171 @@
+"""Canonical state comment validation helpers (#495).
+
+These helpers validate durable issue/PR/discussion state handoff comments.
+They are intentionally pure and do not post comments; MCP mutation hooks are
+owned by #496.
+"""
+
+from __future__ import annotations
+
+import re
+
+CANONICAL_HEADINGS = (
+    "canonical issue state",
+    "canonical pr state",
+    "canonical discussion summary",
+)
+
+REQUIRED_FIELDS = ("STATE", "WHO_IS_NEXT", "NEXT_ACTION", "NEXT_PROMPT")
+ALLOWED_NEXT_ACTORS = {
+    "controller",
+    "author",
+    "reviewer",
+    "merger",
+    "reconciler",
+    "user",
+}
+
+VAGUE_NEXT_ACTIONS = {
+    "continue",
+    "handle this",
+    "do it",
+    "fix it",
+    "proceed",
+    "follow up",
+    "next",
+    "tbd",
+    "todo",
+    "n/a",
+    "none",
+}
+
+_FIELD_RE = re.compile(r"^\s*(?:[-*]\s*)?([A-Z][A-Z0-9_ ]+)\s*:\s*(.*)$")
+_FULL_SHA_RE = re.compile(r"\b[0-9a-f]{40}\b", re.IGNORECASE)
+_CLAIMS_STATE_UPDATE_RE = re.compile(
+    r"canonical\s+(?:issue|pr|discussion)?\s*state|"
+    r"state\s+comment\s+(?:posted|created|updated)|"
+    r"next[- ]action\s+comment\s+(?:posted|created|updated)",
+    re.IGNORECASE,
+)
+
+
+def extract_state_fields(text: str | None) -> dict[str, str]:
+    """Return upper-case labeled fields from a canonical state block."""
+    fields: dict[str, str] = {}
+    current_key: str | None = None
+    for line in (text or "").splitlines():
+        match = _FIELD_RE.match(line)
+        if match:
+            current_key = match.group(1).strip().upper().replace(" ", "_")
+            fields[current_key] = match.group(2).strip()
+            continue
+        stripped = line.strip()
+        if current_key and stripped and not stripped.startswith("#"):
+            existing = fields.get(current_key, "")
+            fields[current_key] = (
+                f"{existing}\n{stripped}" if existing else stripped
+            )
+    return fields
+
+
+def contains_canonical_state_block(text: str | None) -> bool:
+    lower = (text or "").lower()
+    return any(heading in lower for heading in CANONICAL_HEADINGS)
+
+
+def claims_canonical_state_update(text: str | None) -> bool:
+    """Return True when text claims a canonical state/next-action update."""
+    return bool(_CLAIMS_STATE_UPDATE_RE.search(text or ""))
+
+
+def _empty_or_placeholder(value: str | None) -> bool:
+    value = (value or "").strip().lower()
+    return not value or value in {"none", "n/a", "unknown", "tbd", "<...>"}
+
+
+def _vague_next_action(value: str | None) -> bool:
+    normalized = re.sub(r"\s+", " ", (value or "").strip().lower())
+    return normalized in VAGUE_NEXT_ACTIONS
+
+
+def validate_canonical_state_comment(text: str | None) -> dict:
+    """Validate a canonical state comment or embedded final-report block.
+
+    Returns a dict with ``valid`` and ``reasons``. The validator focuses on
+    fields that make continuation possible: current state, next actor, next
+    action, and paste-ready next prompt, plus a few contradiction checks.
+    """
+    fields = extract_state_fields(text)
+    reasons: list[str] = []
+
+    for field in REQUIRED_FIELDS:
+        if _empty_or_placeholder(fields.get(field)):
+            reasons.append(f"missing required canonical state field: {field}")
+
+    actor = (fields.get("WHO_IS_NEXT") or "").strip().lower()
+    if actor and actor not in ALLOWED_NEXT_ACTORS:
+        reasons.append(
+            "WHO_IS_NEXT must be one of: "
+            + ", ".join(sorted(ALLOWED_NEXT_ACTORS))
+        )
+
+    if _vague_next_action(fields.get("NEXT_ACTION")):
+        reasons.append("NEXT_ACTION is too vague for durable continuation")
+
+    state = (fields.get("STATE") or "").strip().lower().replace("-", "_")
+    if "ready_to_merge" in state or (
+        state == "approved" and "pr" in (text or "").lower()
+    ):
+        review_status = (fields.get("REVIEW_STATUS") or "").lower()
+        head_sha = fields.get("HEAD_SHA") or ""
+        merge_ready = (fields.get("MERGE_READY") or "").lower()
+        if "approved" not in review_status:
+            reasons.append("ready-to-merge state requires approved REVIEW_STATUS")
+        if not _FULL_SHA_RE.search(head_sha):
+            reasons.append("ready-to-merge state requires full HEAD_SHA proof")
+        if merge_ready and not merge_ready.startswith(("yes", "true")):
+            reasons.append("ready-to-merge state contradicts MERGE_READY")
+
+    if "superseded" in state:
+        canonical = fields.get("CANONICAL_ITEM") or fields.get("SUPERSEDED_BY")
+        if _empty_or_placeholder(canonical):
+            reasons.append("superseded state requires canonical item proof")
+
+    if "blocked" in state:
+        blockers = fields.get("BLOCKERS") or ""
+        if _empty_or_placeholder(blockers):
+            reasons.append("blocked state requires BLOCKERS/unblock condition")
+
+    return {
+        "valid": not reasons,
+        "fields": fields,
+        "reasons": reasons,
+    }
+
+
+def validate_final_report_state_update(report_text: str | None) -> dict:
+    """Validate canonical state-update claims inside a final report."""
+    text = report_text or ""
+    if not claims_canonical_state_update(text) and not contains_canonical_state_block(text):
+        return {
+            "applicable": False,
+            "valid": True,
+            "reasons": [],
+        }
+
+    if not contains_canonical_state_block(text):
+        return {
+            "applicable": True,
+            "valid": False,
+            "reasons": [
+                "final report claims a canonical state update but includes no canonical state block"
+            ],
+        }
+
+    result = validate_canonical_state_comment(text)
+    return {
+        "applicable": True,
+        "valid": result["valid"],
+        "fields": result["fields"],
+        "reasons": result["reasons"],
+    }

canonical_thread_handoff.py

@@ -0,0 +1,213 @@
+"""Canonical Thread Handoff (CTH) protocol for issue and PR comments (#505).
+
+A CTH comment is the authoritative workflow handoff in a Gitea issue or PR
+thread. It records current state, decisions, blockers, proof, and the exact
+next prompt/action for the next LLM or person.
+"""
+
+from __future__ import annotations
+
+import re
+from datetime import datetime, timezone
+from typing import Any
+
+MARKER = "<!-- cth:v1 -->"
+
+CTH_TERM = "Canonical Thread Handoff"
+CTH_ABBREV = "CTH"
+
+CTH_TYPES = frozenset({
+    "State Handoff",
+    "Controller Decision",
+    "Author Handoff",
+    "Reviewer Handoff",
+    "Merger Handoff",
+    "Supersession Notice",
+    "Blocker",
+})
+
+_REQUIRED_BASE_FIELDS = (
+    "status",
+    "next owner",
+    "current blocker",
+    "decision",
+    "proof",
+    "next action",
+    "ready-to-paste prompt",
+)
+
+_HEADING_RE = re.compile(
+    r"^##\s+CTH:\s*(.+?)\s*$",
+    re.IGNORECASE | re.MULTILINE,
+)
+_FIELD_RE = re.compile(
+    r"^([A-Za-z][A-Za-z0-9 /-]*):\s*(.+?)\s*$",
+    re.MULTILINE,
+)
+
+
+def format_cth_body(
+    *,
+    cth_type: str,
+    status: str,
+    next_owner: str,
+    current_blocker: str = "none",
+    decision: str = "none",
+    proof: str = "none",
+    next_action: str = "none",
+    ready_to_paste_prompt: str = "none",
+    extra_fields: dict[str, str] | None = None,
+) -> str:
+    """Render a canonical CTH comment body."""
+    normalized_type = (cth_type or "").strip()
+    if normalized_type not in CTH_TYPES:
+        raise ValueError(
+            f"unknown CTH type '{cth_type}'; expected one of {sorted(CTH_TYPES)}"
+        )
+    lines = [
+        MARKER,
+        f"## CTH: {normalized_type}",
+        "",
+        f"Status: {(status or 'unknown').strip() or 'unknown'}",
+        f"Next owner: {(next_owner or 'unknown').strip() or 'unknown'}",
+        f"Current blocker: {(current_blocker or 'none').strip() or 'none'}",
+        f"Decision: {(decision or 'none').strip() or 'none'}",
+        f"Proof: {(proof or 'none').strip() or 'none'}",
+        f"Next action: {(next_action or 'none').strip() or 'none'}",
+        f"Ready-to-paste prompt: {(ready_to_paste_prompt or 'none').strip() or 'none'}",
+    ]
+    for key, value in (extra_fields or {}).items():
+        label = (key or "").strip()
+        if not label:
+            continue
+        lines.append(f"{label}: {(value or 'none').strip() or 'none'}")
+    return "\n".join(lines)
+
+
+def parse_cth_comment(body: str) -> dict[str, Any] | None:
+    """Parse one CTH comment body, or None when not a CTH comment."""
+    text = body or ""
+    if MARKER not in text and not _HEADING_RE.search(text):
+        return None
+    heading = _HEADING_RE.search(text)
+    if not heading:
+        return None
+    cth_type = heading.group(1).strip()
+    fields: dict[str, str] = {}
+    for match in _FIELD_RE.finditer(text):
+        key = match.group(1).strip().lower()
+        if key.startswith("cth"):
+            continue
+        fields[key] = match.group(2).strip()
+    return {
+        "cth_type": cth_type,
+        "fields": fields,
+        "raw_body": text,
+    }
+
+
+def assess_cth_comment(body: str) -> dict[str, Any]:
+    """Validate a CTH comment has required base fields and a known type."""
+    parsed = parse_cth_comment(body)
+    reasons: list[str] = []
+    if not parsed:
+        return {
+            "valid": False,
+            "block": True,
+            "reasons": ["comment is not a Canonical Thread Handoff (CTH)"],
+            "parsed": None,
+        }
+
+    cth_type = parsed.get("cth_type") or ""
+    if cth_type not in CTH_TYPES:
+        reasons.append(
+            f"unknown CTH type '{cth_type}'; expected one of {sorted(CTH_TYPES)}"
+        )
+
+    fields = parsed.get("fields") or {}
+    missing = [name for name in _REQUIRED_BASE_FIELDS if not (fields.get(name) or "").strip()]
+    if missing:
+        reasons.append(
+            "CTH missing required fields: " + ", ".join(missing)
+        )
+
+    vague_prompt = (fields.get("ready-to-paste prompt") or "").strip().lower()
+    if vague_prompt in {"", "none", "tbd", "n/a", "todo"}:
+        reasons.append("ready-to-paste prompt must be concrete and paste-ready")
+
+    return {
+        "valid": not reasons,
+        "block": bool(reasons),
+        "reasons": reasons,
+        "parsed": parsed,
+        "cth_type": cth_type,
+    }
+
+
+def find_latest_cth(comments: list[dict[str, Any]]) -> dict[str, Any] | None:
+    """Return the newest valid CTH comment from a Gitea comment list."""
+    latest: dict[str, Any] | None = None
+    latest_ts: datetime | None = None
+    for comment in comments or []:
+        body = comment.get("body") or ""
+        parsed = parse_cth_comment(body)
+        if not parsed:
+            continue
+        created = _parse_timestamp(comment.get("created_at"))
+        if latest is None or (created and (latest_ts is None or created >= latest_ts)):
+            latest = {
+                "comment_id": comment.get("id"),
+                "created_at": comment.get("created_at"),
+                "author": (comment.get("user") or {}).get("login"),
+                **parsed,
+            }
+            latest_ts = created
+    return latest
+
+
+def assess_cth_supersedes_non_cth(
+    *,
+    latest_cth: dict[str, Any] | None,
+    narrative_claim: str,
+) -> dict[str, Any]:
+    """Fail closed when narrative relies on stale non-CTH state despite newer CTH."""
+    if not latest_cth:
+        return {"block": False, "reasons": []}
+    text = (narrative_claim or "").strip()
+    if not text:
+        return {"block": False, "reasons": []}
+    if parse_cth_comment(text):
+        return {"block": False, "reasons": []}
+    return {
+        "block": True,
+        "reasons": [
+            "workflow narrative must treat the latest CTH comment as authoritative; "
+            f"found newer CTH type '{latest_cth.get('cth_type')}' "
+            f"(comment #{latest_cth.get('comment_id')})"
+        ],
+    }
+
+
+def _parse_timestamp(value: str | None) -> datetime | None:
+    if not value:
+        return None
+    text = value.strip()
+    if text.endswith("Z"):
+        text = text[:-1] + "+00:00"
+    try:
+        parsed = datetime.fromisoformat(text)
+    except ValueError:
+        return None
+    if parsed.tzinfo is None:
+        return parsed.replace(tzinfo=timezone.utc)
+    return parsed.astimezone(timezone.utc)
+
+
+EXAMPLE_SCENARIOS = (
+    "pr_approved_ready_for_merger",
+    "pr_request_changes_to_author",
+    "duplicate_superseded_pr_closure",
+    "blocked_dirty_root_worktree",
+    "stale_head_requires_fresh_review",
+    "issue_implementation_handoff",
+)

conflict_fix_classification.py

@@ -0,0 +1,266 @@
+"""Live PR head re-pin before conflict-fix classification (#522).
+
+Open PR inventory fields (mergeable, head_sha) can be stale. Author sessions
+must re-fetch live PR state and pin the live head before classifying a PR as
+conflicted or creating a conflict-fix worktree.
+"""
+
+from __future__ import annotations
+
+import re
+from typing import Any
+
+_FULL_SHA = re.compile(r"^[0-9a-f]{40}$", re.IGNORECASE)
+
+_INVENTORY_HEAD_RE = re.compile(
+    r"(?:inventory head sha|stale inventory head sha)\s*:\s*([0-9a-f]{40})",
+    re.IGNORECASE,
+)
+_LIVE_HEAD_RE = re.compile(
+    r"(?:live head sha|pinned head sha|live pr head sha)\s*:\s*([0-9a-f]{40})",
+    re.IGNORECASE,
+)
+_REPINS_TOOL_RE = re.compile(
+    r"gitea_assess_conflict_fix_classification",
+    re.IGNORECASE,
+)
+_CLASSIFICATION_RE = re.compile(
+    r"conflict[- ]fix classification\s*:\s*(\S+)",
+    re.IGNORECASE,
+)
+
+CLASSIFICATION_STALE_INVENTORY_SKIP = "stale_inventory_skip"
+CLASSIFICATION_CONFLICT_FIX_NEEDED = "conflict_fix_needed"
+CLASSIFICATION_LIVE_MERGEABLE = "live_mergeable_skip"
+CLASSIFICATION_INCOMPLETE = "incomplete_live_repin"
+
+_VALID_CLASSIFICATIONS = frozenset({
+    CLASSIFICATION_STALE_INVENTORY_SKIP,
+    CLASSIFICATION_CONFLICT_FIX_NEEDED,
+    CLASSIFICATION_LIVE_MERGEABLE,
+    CLASSIFICATION_INCOMPLETE,
+})
+
+
+def _normalize_sha(value: str | None) -> str | None:
+    text = (value or "").strip().lower()
+    if not text:
+        return None
+    return text if _FULL_SHA.match(text) else None
+
+
+def assess_conflict_fix_classification(
+    *,
+    pr_number: int,
+    inventory_head_sha: str | None = None,
+    inventory_mergeable: bool | None = None,
+    live_head_sha: str | None = None,
+    live_mergeable: bool | None = None,
+) -> dict[str, Any]:
+    """Classify whether conflict-fix work is justified from live PR state.
+
+    Inventory fields are advisory only. Live head + live mergeable are required
+    before any conflict-fix worktree may be created.
+    """
+    inv_head = _normalize_sha(inventory_head_sha)
+    live_head = _normalize_sha(live_head_sha)
+    reasons: list[str] = []
+
+    if not isinstance(pr_number, int) or pr_number <= 0:
+        return {
+            "classification": CLASSIFICATION_INCOMPLETE,
+            "worktree_allowed": False,
+            "skip_author_mutation": True,
+            "inventory_stale_head": False,
+            "inventory_stale_mergeable": False,
+            "pinned_head_sha": None,
+            "inventory_head_sha": inv_head,
+            "live_head_sha": live_head,
+            "inventory_mergeable": inventory_mergeable,
+            "live_mergeable": live_mergeable,
+            "pr_number": pr_number,
+            "reasons": ["pr_number must be a positive integer (fail closed)"],
+        }
+
+    if live_head is None:
+        reasons.append(
+            "live PR head SHA missing or not a full 40-char hex SHA; "
+            "re-fetch the PR before conflict-fix classification (fail closed)"
+        )
+    if live_mergeable is None:
+        reasons.append(
+            "live PR mergeable value missing; re-fetch the PR before "
+            "conflict-fix classification (fail closed)"
+        )
+
+    if reasons:
+        return {
+            "classification": CLASSIFICATION_INCOMPLETE,
+            "worktree_allowed": False,
+            "skip_author_mutation": True,
+            "inventory_stale_head": bool(
+                inv_head and live_head and inv_head != live_head
+            ),
+            "inventory_stale_mergeable": (
+                inventory_mergeable is not None
+                and live_mergeable is not None
+                and bool(inventory_mergeable) != bool(live_mergeable)
+            ),
+            "pinned_head_sha": live_head,
+            "inventory_head_sha": inv_head,
+            "live_head_sha": live_head,
+            "inventory_mergeable": inventory_mergeable,
+            "live_mergeable": live_mergeable,
+            "pr_number": pr_number,
+            "reasons": reasons,
+        }
+
+    inventory_stale_head = bool(inv_head and inv_head != live_head)
+    inventory_stale_mergeable = (
+        inventory_mergeable is not None
+        and bool(inventory_mergeable) != bool(live_mergeable)
+    )
+
+    # Live mergeable wins: do not start conflict-fix work.
+    if live_mergeable is True:
+        classification = (
+            CLASSIFICATION_STALE_INVENTORY_SKIP
+            if (
+                inventory_mergeable is False
+                or inventory_stale_head
+                or inventory_stale_mergeable
+            )
+            else CLASSIFICATION_LIVE_MERGEABLE
+        )
+        note = []
+        if inventory_stale_head:
+            note.append(
+                f"inventory head {inv_head} differs from live head {live_head}; "
+                "use live head only"
+            )
+        if inventory_mergeable is False:
+            note.append(
+                "inventory reported mergeable:false but live PR is mergeable:true; "
+                "skip author conflict-fix mutation"
+            )
+        return {
+            "classification": classification,
+            "worktree_allowed": False,
+            "skip_author_mutation": True,
+            "inventory_stale_head": inventory_stale_head,
+            "inventory_stale_mergeable": inventory_stale_mergeable,
+            "pinned_head_sha": live_head,
+            "inventory_head_sha": inv_head,
+            "live_head_sha": live_head,
+            "inventory_mergeable": inventory_mergeable,
+            "live_mergeable": live_mergeable,
+            "pr_number": pr_number,
+            "reasons": note,
+        }
+
+    # live_mergeable is False → conflict-fix may proceed on the pinned live head.
+    note = []
+    if inventory_stale_head:
+        note.append(
+            f"inventory head {inv_head} differs from live head {live_head}; "
+            "pin and use live head only for conflict-fix work"
+        )
+    if inventory_mergeable is True:
+        note.append(
+            "inventory reported mergeable:true but live PR is mergeable:false; "
+            "trust live mergeable and proceed only with live head pin"
+        )
+    note.append(
+        f"live PR #{pr_number} is mergeable:false at pinned head {live_head}; "
+        "conflict-fix worktree allowed for that head only"
+    )
+    return {
+        "classification": CLASSIFICATION_CONFLICT_FIX_NEEDED,
+        "worktree_allowed": True,
+        "skip_author_mutation": False,
+        "inventory_stale_head": inventory_stale_head,
+        "inventory_stale_mergeable": inventory_stale_mergeable,
+        "pinned_head_sha": live_head,
+        "inventory_head_sha": inv_head,
+        "live_head_sha": live_head,
+        "inventory_mergeable": inventory_mergeable,
+        "live_mergeable": live_mergeable,
+        "pr_number": pr_number,
+        "reasons": note,
+    }
+
+
+def assess_conflict_fix_classification_final_report(
+    report_text: str,
+    **_kwargs: Any,
+) -> dict[str, Any]:
+    """Require live-head re-pin proof when a report claims conflict-fix work (#522)."""
+    text = report_text or ""
+    lower = text.lower()
+    mentions_conflict_fix = (
+        "conflict-fix" in lower
+        or "conflict fix" in lower
+        or "conflict_fix" in lower
+    )
+    if not mentions_conflict_fix:
+        return {"proven": True, "reasons": [], "applicable": False}
+
+    reasons: list[str] = []
+    if not _REPINS_TOOL_RE.search(text):
+        reasons.append(
+            "conflict-fix report must cite gitea_assess_conflict_fix_classification "
+            "(live head re-pin tool)"
+        )
+
+    live_match = _LIVE_HEAD_RE.search(text)
+    if not live_match:
+        reasons.append(
+            "conflict-fix report must state Live head SHA: <40-char hex> "
+            "(or Pinned head SHA / Live PR head SHA)"
+        )
+    else:
+        live_sha = _normalize_sha(live_match.group(1))
+        if live_sha is None:
+            reasons.append("live head SHA is not a full 40-char hex digest")
+
+    inv_match = _INVENTORY_HEAD_RE.search(text)
+    # Inventory head is optional but recommended when classification is stale skip.
+    class_match = _CLASSIFICATION_RE.search(text)
+    if not class_match:
+        reasons.append(
+            "conflict-fix report must state Conflict-fix classification: "
+            f"<{'|'.join(sorted(_VALID_CLASSIFICATIONS))}>"
+        )
+    else:
+        classification = class_match.group(1).strip().lower().replace(" ", "_")
+        # allow hyphenated forms
+        classification = classification.replace("-", "_")
+        if classification not in _VALID_CLASSIFICATIONS:
+            reasons.append(
+                f"unknown conflict-fix classification {class_match.group(1)!r}; "
+                f"expected one of {sorted(_VALID_CLASSIFICATIONS)}"
+            )
+
+    if inv_match and live_match:
+        inv_sha = _normalize_sha(inv_match.group(1))
+        live_sha = _normalize_sha(live_match.group(1))
+        if inv_sha and live_sha and inv_sha != live_sha:
+            # Require explicit note that live head was used.
+            if "use live head" not in lower and "live head only" not in lower:
+                reasons.append(
+                    "inventory head differs from live head; report must state that "
+                    "the live head was used exclusively"
+                )
+
+    return {
+        "proven": not reasons,
+        "reasons": reasons,
+        "applicable": True,
+        "inventory_head_sha": _normalize_sha(inv_match.group(1)) if inv_match else None,
+        "live_head_sha": _normalize_sha(live_match.group(1)) if live_match else None,
+        "classification": (
+            class_match.group(1).strip().lower().replace("-", "_").replace(" ", "_")
+            if class_match
+            else None
+        ),
+    }

controller_closure_baseline_proof.py

@@ -0,0 +1,63 @@
+"""Controller-closure baseline-proof gate (#529, criterion 6).
+
+A controller (or any session) may close a tracking issue with a closure
+report that summarizes validation. When that report calls a non-zero
+test-suite exit an "expected pre-existing failure" (or baseline / known
+failure) it must carry pre-merge proof; otherwise the closure buries an
+unproven regression as an accepted baseline and weakens controller
+confidence in the durable state.
+
+This module fails closed on exactly that case by reusing the pre-merge
+baseline proof verifier (#533). A closure report is allowed when it is
+empty (no validation claim), a clean pass, or a baseline failure proven on
+the PR pre-merge base commit (or a documented known-failure record that
+predates the PR).
+"""
+
+from __future__ import annotations
+
+from typing import Any
+
+from premerge_baseline_proof import CLEAN_PASS, assess_premerge_baseline_proof
+
+
+def assess_controller_closure_baseline_proof(
+    closure_report: str | None,
+) -> dict[str, Any]:
+    """Assess whether an issue-closure report may proceed.
+
+    Returns a dict with ``block``, ``proven``, ``label``, ``reasons``,
+    ``skipped`` and ``safe_next_action``. Only blocks when the closure
+    report claims a non-zero validation exit is an expected
+    pre-existing/baseline failure without valid pre-merge proof.
+    """
+    text = (closure_report or "").strip()
+    if not text:
+        return {
+            "block": False,
+            "proven": True,
+            "label": CLEAN_PASS,
+            "reasons": [],
+            "skipped": True,
+            "safe_next_action": "",
+        }
+
+    result = assess_premerge_baseline_proof(text)
+    block = bool(result.get("block"))
+    return {
+        "block": block,
+        "proven": not block,
+        "label": result.get("label"),
+        "reasons": list(result.get("reasons") or []),
+        "skipped": bool(result.get("skipped", False)),
+        "safe_next_action": (
+            result.get("safe_next_action")
+            or (
+                "provide pre-merge baseline proof (base commit, tested commit, "
+                "command, exit status, failure signature) before closing on an "
+                "expected pre-existing failure"
+            )
+        )
+        if block
+        else "",
+    }

create_issue.py

@@ -29,6 +29,7 @@ from gitea_auth import (
     get_credentials, resolve_remote, add_remote_args,
     api_request, repo_api_url,
 )
+import issue_workflow_labels
 
 
 def main(argv=None):
@@ -38,6 +39,16 @@ def main(argv=None):
     parser.add_argument("--body", default="", help="Issue body text.")
     parser.add_argument("--body-file",
                         help="Read issue body from this file ('-' for stdin).")
+    parser.add_argument("--label", action="append", default=[],
+                        help="Existing label name to apply; may be repeated.")
+    parser.add_argument("--type-label",
+                        help="Issue type, e.g. feature or type:feature.")
+    parser.add_argument("--status-label",
+                        help="Initial status, e.g. ready or status:ready.")
+    parser.add_argument("--discussion", action="store_true",
+                        help="Apply type:discussion.")
+    parser.add_argument("--require-workflow-labels", action="store_true",
+                        help="Fail unless one type:* and one status:* label are supplied.")
     args = parser.parse_args(argv)
 
     host, org, repo = resolve_remote(args)
@@ -50,6 +61,24 @@ def main(argv=None):
             with open(args.body_file, "r", encoding="utf-8") as fh:
                 body = fh.read()
 
+    requested_labels = issue_workflow_labels.labels_for_new_issue(
+        issue_type=args.type_label,
+        initial_status=args.status_label,
+        extra_labels=args.label,
+        discussion=args.discussion,
+    )
+    label_assessment = issue_workflow_labels.assess_issue_labels(
+        requested_labels,
+        discussion=args.discussion,
+    )
+    if args.require_workflow_labels and not label_assessment["valid"]:
+        print(
+            "Workflow label validation failed: "
+            + "; ".join(label_assessment["errors"]),
+            file=sys.stderr,
+        )
+        return 1
+
     user, password = get_credentials(host)
     if not user or not password:
         print(f"Could not get credentials for {host} "
@@ -59,11 +88,34 @@ def main(argv=None):
 
     import base64
     auth = f"Basic {base64.b64encode(f'{user}:{password}'.encode()).decode()}"
-    url = f"{repo_api_url(host, org, repo)}/issues"
+    base = repo_api_url(host, org, repo)
+    url = f"{base}/issues"
 
     try:
+        label_ids = []
+        if requested_labels:
+            existing = api_request("GET", f"{base}/labels", auth)
+            by_name = {lb["name"]: lb["id"] for lb in existing}
+            missing = [name for name in requested_labels if name not in by_name]
+            if missing:
+                print(f"Missing labels: {missing}", file=sys.stderr)
+                return 1
+            label_ids = [by_name[name] for name in requested_labels]
         data = api_request("POST", url, auth, {"title": args.title, "body": body})
+        if label_ids:
+            api_request(
+                "PUT",
+                f"{base}/issues/{data.get('number')}/labels",
+                auth,
+                {"labels": label_ids},
+            )
         print(f"Issue #{data.get('number')}: {data.get('html_url')}")
+        if not label_assessment["valid"]:
+            print(
+                "Workflow label recommendation: "
+                + "; ".join(label_assessment["errors"]),
+                file=sys.stderr,
+            )
         return 0
     except RuntimeError as e:
         print(f"Error: {e}", file=sys.stderr)

docs/architecture/control-plane-db-substrate.md

@@ -0,0 +1,63 @@
+# Control-plane DB substrate (#613)
+
+**Status:** Implemented (SQLite single-writer MVP)
+
+**ADR:** [`mcp-allocator-control-plane-observability-adr.md`](mcp-allocator-control-plane-observability-adr.md)
+
+**Module:** `control_plane_db.py`
+
+## Architecture statement
+
+> **DB coordinates, Gitea records, Sentry/GlitchTip observe; the bridge is the only path that turns observations into Gitea work.**
+
+## What this ships
+
+| Capability | Notes |
+|------------|--------|
+| Schema | `sessions`, `work_items`, `leases`, `assignments`, `terminal_locks`, `events`, `incident_links` |
+| Atomic assign+lease | `ControlPlaneDB.assign_and_lease` — one `BEGIN IMMEDIATE` transaction |
+| Mutation gate | `require_valid_assignment` — live lease + allowed action + non-terminal work + non-stale head |
+| Heartbeat / release / expire | Lease lifecycle helpers |
+| Terminal-lock index | Routing signal for #600 (terminal path first) |
+| `incident_links` | Provider-neutral link model for #612 — **not** assignable work; scope keys NULL-safe |
+
+## Hard rules (enforced in code)
+
+1. Assignable `work_items.kind` ∈ {`issue`, `pr`} only — **never** raw Sentry/GlitchTip incidents.
+2. Two concurrent sessions cannot both receive an active assignment on the same open work item (second gets `wait`).
+3. Merged/closed work items return `no_safe_work` at assign time, and `require_valid_assignment` fails closed if the work item becomes terminal later.
+4. Assignments pin `expected_head_sha`; mutations fail closed if the work item head drifts.
+5. SQLite path is the **single-writer MVP** (`GITEA_CONTROL_PLANE_DB`, default under `~/.cache/gitea-tools/control-plane/`). Multi-session multi-host production requires **Postgres** or a **single allocator daemon** (ADR §6).
+6. `incident_links` optional scope fields are stored as empty strings (never NULL) so UNIQUE is canonical across minimal upserts.
+7. Legacy `incident_links` migration collapses NULL-scope duplicates **only** when Gitea targets **and** all meaningful observation metadata agree (fingerprint, status, event_count, permalink, timestamps, linked PRs, etc.). Conflicting metadata fails closed — no silent discard.
+
+## Dependency chain
+
+```text
+#613 control-plane DB (this)  →  #600 allocator API  →  #612 incident bridge
+```
+
+- **#600** must call this substrate (not file locks / comment-only leases alone) for completion.
+- **#612** must write `incident_links` here and create **Gitea issues**; the allocator assigns those issues, not raw incidents.
+
+## Allocator API (#600)
+
+Module: `allocator_service.py` · MCP tool: `gitea_allocate_next_work`
+
+- Workers call `gitea_allocate_next_work(apply=false|true)` instead of self-selecting work.
+- `apply=false` returns a dry-run selection (`outcome=preview`) with skip reasons.
+- `apply=true` reserves via `ControlPlaneDB.assign_and_lease` (atomic assignment+lease).
+- Coordination source is **always** the control-plane DB — not file locks or comment-only leases.
+- Routing follows ADR §5.3 (REQUEST_CHANGES → author, terminal path first, foreign lease → wait).
+- Raw monitoring incidents are never candidates (#612 remains downstream).
+
+## Non-goals (intentionally deferred)
+
+- Sentry/GlitchTip provider adapters and auto-watchdog — **#612**
+- Gitea comment/label mirror writers (may be added by allocator tooling later)
+
+## Tests
+
+```bash
+python3 -m pytest tests/test_control_plane_db.py -q
+```

docs/architecture/mcp-allocator-control-plane-observability-adr.md

@@ -0,0 +1,301 @@
+# ADR: MCP allocator, control-plane DB, and Sentry/GlitchTip incident bridge architecture
+
+- **Status:** Accepted (implementation pending; blocks code for #600 / #612 / #613)
+- **Date:** 2026-07-09
+- **Tracking issues:**
+  - [#613](https://gitea.prgs.cc/Scaled-Tech-Consulting/Gitea-Tools/issues/613) — control-plane DB (first)
+  - [#600](https://gitea.prgs.cc/Scaled-Tech-Consulting/Gitea-Tools/issues/600) — allocator API (second)
+  - [#612](https://gitea.prgs.cc/Scaled-Tech-Consulting/Gitea-Tools/issues/612) — Sentry/GlitchTip incident bridge (third)
+- **Related:** existing GlitchTip contracts (`glitchtip-to-gitea-workflow-design.md`, `glitchtip-gitea-deduplication-linking-design.md`), trust boundaries (`tool-boundaries.md`, `safety-model.md`), current leases (`pr_work_lease.py`, `issue_lock_store.py`)
+
+## 1. Context
+
+Multiple LLM sessions can independently inspect the Gitea queue and start the same issue or PR. Existing coordination (Gitea comment leases, local issue-lock files, labels) often detects collisions **after** work has started. Parallel issues #600, #612, and #613 each describe part of a fix; without one ADR they risk overlapping stores, wrong dependency order, and trust-boundary violations.
+
+This ADR is the canonical architecture decision **before** implementing those issues.
+
+## 2. Decision summary (core)
+
+| Layer | Owns | Must not |
+|-------|------|----------|
+| **Control-plane DB** | Sessions, atomic assignment, leases, heartbeats, terminal-lock index, events, incident links | Bypass Gitea workflow gates or replace issue/PR history |
+| **Gitea** | Durable work record: issues, PRs, comments, labels, reviews, merges | Be the only concurrency lock under multi-session load |
+| **Sentry / GlitchTip** | Incidents, events, provider UI | Assign work, approve/merge/close, or mutate Gitea outside the bridge |
+| **Incident bridge** | Provider adapters, reconcile/create Gitea issues, link storage upsert, optional provider writeback | Hand raw provider incidents to the allocator as work items |
+
+**One-liner:** **DB coordinates. Gitea records. Sentry/GlitchTip observe. The bridge is the only path that turns observations into Gitea work. The allocator assigns only Gitea issues/PRs, never raw monitoring incidents.**
+
+## 3. Dependency order
+
+Implementation **must** follow:
+
+```text
+#613 control-plane DB  →  #600 allocator API  →  #612 incident bridge
+   (atomic substrate)      (routing policy)       (feeds Gitea work)
+```
+
+| Issue | Role | Depends on |
+|-------|------|------------|
+| **#613** | Durable coordination DB + lease/assignment transactions | — |
+| **#600** | `gitea_allocate_next_work` policy and tool surface | **#613** (hard) |
+| **#612** | Multi-project Sentry/GlitchTip → Gitea bridge | **#613** for `incident_links` index; **#600** before treating bridge-created issues as allocator feed in multi-worker prod |
+
+**Hard rules:**
+
+1. Do **not** implement #600 on file locks / comment-only leases and call it done.
+2. Do **not** ship #612 as a second assignment system for raw incidents.
+3. Partial previews (read-only list tools, schema stubs) may land earlier if they do not claim “allocator complete” or “bridge complete.”
+
+## 4. Authority boundaries
+
+### 4.1 Gitea (durable source of truth for work)
+
+Gitea remains authoritative for:
+
+- Issue and PR identity, titles, bodies, state (open/closed/merged)
+- Comments, reviews, approvals, REQUEST_CHANGES
+- Labels and workflow status labels (`status:ready`, `status:in-progress`, …)
+- Merges, closes, branch refs as recorded by Gitea/git hosting
+
+Operators and auditors read **history** from Gitea.
+
+### 4.2 Control-plane DB (coordination / index)
+
+The control-plane DB is authoritative for **live multi-session coordination**:
+
+- Which session holds which assignment/lease
+- Heartbeat freshness and expiry
+- Terminal-lock index for routing
+- Event log of allocation/lease transitions
+- `incident_links` index (see §8)
+
+It is **not** a substitute for Gitea history. When DB and Gitea disagree on durable work state (e.g. PR already merged), **Gitea wins**; the DB is reconciled.
+
+### 4.3 Sentry / GlitchTip (observe)
+
+Providers own incident lifecycle and raw event data. They:
+
+- Must **not** bypass Gitea gates
+- Must **not** assign LLM work
+- May receive **writeback** of resolution status only through the bridge, when configured and supported
+
+### 4.4 Trust boundaries for credentials
+
+Aligned with `docs/tool-boundaries.md` and `docs/safety-model.md`:
+
+- **One MCP server process per trust boundary** remains the default.
+- Monitor API tokens (Sentry/GlitchTip) live in the **bridge/orchestrator boundary** (or a dedicated observability write/read profile), **not** blindly inside every Gitea MCP author/reviewer/merger process.
+- Gitea tokens stay on Gitea MCP profiles only.
+- Orchestrators compose services; they must not become a single credential pool that silently mixes Gitea write + monitor tokens into every worker.
+
+Tool names such as `gitea_observability_*` may exist as a **namespace façade** only if the runtime still enforces separate credential scopes (e.g. bridge process vs pure Gitea mutation process).
+
+## 5. Allocator rules (#600 on top of #613)
+
+### 5.1 Worker contract
+
+- Workers **do not self-select** work under the standard multi-LLM workflow.
+- Workers call **`gitea_allocate_next_work`** (with `apply=true` only when taking work).
+- Mutations that claim exclusive work require a **valid assignment and lease** from the control-plane DB.
+- Return values include at least: role, issue/PR number, expected head SHA (when applicable), lease ID, expiry, allowed actions, forbidden actions — or a non-assignment outcome (`WAIT`, terminal-path block, no safe work, needs controller, etc.).
+
+### 5.2 Atomic reserve
+
+- **Assignment creation and lease creation happen in one DB transaction.**
+- Two concurrent sessions **must not** receive the same issue/PR as assigned work.
+- On contention: second session gets **WAIT** or **owner-resume**, never a duplicate lease.
+
+### 5.3 Routing policy
+
+| Condition | Route |
+|-----------|--------|
+| Current-head **REQUEST_CHANGES** | **Author** (not reviewer/merger) |
+| **Stale** approval (approval not on current head) | **Reviewer** |
+| **Clean** approval on current head, mergeable | **Merger** |
+| Contested / contaminated approval | **Diagnosis / reconciler** (controller path) |
+| Active **foreign** lease | **WAIT** or **owner-resume** |
+| **Terminal-review** lock present | **Terminal-path resolution first** before downstream review work |
+| Merged / closed PR | **Never assign** |
+| Issue locked by sanctioned lease | **Never assign** to another worker unless lease cleanup/adoption is sanctioned |
+
+### 5.4 Relationship to Gitea mirrors
+
+After a successful assignment, the allocator (or sanctioned tooling) may update Gitea comments/labels so humans and audits see state. Those mirrors **are not** the sole lock source.
+
+## 6. Control-plane DB topology (#613)
+
+### 6.1 Preferred architecture (multi-daemon / Proxmox)
+
+For true multi-session concurrency (multiple MCP daemons, multiple hosts, or Proxmox VMs):
+
+**Prefer either:**
+
+1. **Shared Postgres** used by all Gitea MCP profiles / allocator callers, **or**
+2. A **single allocator daemon** (sole writer to the coordination store) that all workers call over MCP/RPC.
+
+Both satisfy: one transactional authority for “who has this work item.”
+
+### 6.2 SQLite MVP
+
+SQLite is acceptable **only** for a **single-writer MVP**:
+
+- One process owns writes (allocator daemon or single co-located MCP server), **or**
+- Documented single-host single-daemon experiments with file locking and no multi-host claims.
+
+SQLite is **not** sufficient to declare multi-session production readiness when four independent LLM sessions talk to four MCP processes without a shared writer.
+
+### 6.3 Suggested entities (normative shape)
+
+Minimum logical entities (names may vary; semantics must not):
+
+1. **sessions** — session_id, role/profile, namespace, pid, started_at, last_heartbeat_at, status  
+2. **work_items** — remote/org/repo, kind ∈ {`issue`, `pr`}, number, state, priority, current_head_sha, updated_at  
+3. **leases** — lease_id, work_item_id, session_id, role, phase, expires_at, heartbeat_at, status  
+4. **assignments** — assignment_id, work_item_id, session_id, allowed_action(s), expected_head_sha, status  
+5. **terminal_locks** — repo/org, terminal_pr, review_id, decision, status, cleanup_state  
+6. **events** — event_id, work_item_id, type, message, created_at  
+7. **incident_links** — provider-neutral link model (see §8)
+
+**Explicit non-kind:** do **not** use `work_items.kind = sentry_incident` (or glitchtip_incident) as an assignable work unit. Incidents become work only after the bridge creates/links a **Gitea issue**.
+
+## 7. Lease migration (avoid split-brain)
+
+### 7.1 Target state
+
+- **Primary** for live coordination: **control-plane DB** leases and assignments.
+- **Gitea comment leases** (e.g. `<!-- mcp-review-lease:v1 -->`) and **local issue-lock files** become:
+  - **mirrors** of DB state for human visibility / recovery, and/or
+  - written **only** through the allocator (or sanctioned lease tools that update DB + mirror in one workflow).
+
+### 7.2 Migration rules
+
+1. New exclusive claims go through DB assignment+lease first.
+2. Comment lease / file lock writers that skip the DB are **deprecated** once #613+#600 land.
+3. Reconciler tooling heals: expired DB lease, orphan Gitea comment, orphan local file — fail closed when ambiguous.
+4. **Split-brain is a defect:** “DB free + Gitea comment leased” or “DB leased + Gitea free” must be detectable and reconcilable; production paths must not rely on two independent writers.
+
+### 7.3 Heartbeats
+
+- Heartbeats update the **DB**.
+- Optional Gitea summaries must avoid comment spam (periodic summary or edit-in-place policy).
+
+## 8. Observability bridge (#612)
+
+### 8.1 Role
+
+The bridge:
+
+1. Scans configured Sentry and/or GlitchTip projects (multi-project mappings).
+2. Deduplicates against existing links / Gitea issues.
+3. Creates or updates **normal Gitea issues** (labels, sanitized body, provider URL).
+4. Upserts **one** canonical `incident_links` row.
+5. Optionally writes resolution status back to the provider when supported.
+6. Never approves, merges, closes, or otherwise bypasses Gitea workflow gates.
+
+### 8.2 Allocator interaction
+
+- The allocator sees observability work **only after** a Gitea issue exists (typically `status:ready` + observability labels).
+- **Do not assign raw Sentry/GlitchTip incidents** as work items.
+- Bridge AC “allocator can see linked issues” means: **as ordinary Gitea issues**, not a special incident queue.
+
+### 8.3 Provider adapters and trust
+
+- Separate **Sentry** and **GlitchTip** adapters; document API differences; do not assume writeback parity.
+- Self-hosted base URLs supported (e.g. `https://sentry.prgs.cc`).
+- Tokens from environment / secret store only.
+- Prefer phase-1 **explicit reconcile / dry-run** before unsupervised watchdog auto-filing, consistent with existing GlitchTip filing safety contracts.
+
+### 8.4 Home of implementation
+
+Filing/orchestration may live in:
+
+- a control-plane / bridge package or profile, and/or  
+- Gitea-Tools as operator-facing tools that **delegate** to that boundary,
+
+but must not violate §4.4 credential isolation.
+
+## 9. Incident link storage (single source of truth)
+
+### 9.1 Canonical model: `incident_links` (provider-neutral)
+
+Prefer a **provider-neutral** model over Sentry-only `sentry_links`:
+
+| Field (logical) | Purpose |
+|-----------------|---------|
+| provider | `sentry` \| `glitchtip` \| … |
+| provider_base_url | Self-hosted base |
+| provider_org / provider_project | Mapping key |
+| provider_issue_id / provider_short_id | Provider identity |
+| provider_permalink | Human URL |
+| fingerprint | Stable dedupe key when available |
+| gitea_org / gitea_repo / gitea_issue_number | Linked work |
+| linked_pr_numbers | Optional PR association |
+| first_seen / last_seen / event_count | Summary metrics (safe) |
+| status | link lifecycle |
+| release_resolved_at / last_sync_at | Sync bookkeeping |
+
+### 9.2 Gitea as human mirror
+
+- Issue body markers / structured comments (e.g. HTML comment metadata) remain the **human- and audit-visible mirror**.
+- They must stay consistent with `incident_links` but are **not** a second independent write path for inventing links without the bridge.
+
+### 9.3 One truth
+
+- **Do not** maintain two independent systems of record (e.g. full mapping only in #612 storage **and** a separate #613 `sentry_links` with different semantics).
+- #612 implementation **must** use the same `incident_links` model introduced under #613 (or a single agreed store both reference).
+
+## 10. Security and redaction
+
+Mandatory for bridge payloads, Gitea issue bodies/comments, DB-stored event summaries, and logs:
+
+- No API tokens, DSNs, passwords, cookies, auth headers
+- No keychain IDs, private config contents, raw session-state files, full prompt bodies
+- Sanitize stack locals and request data; store only safe tags/context
+- Logs must never print provider tokens or DSNs
+- Redaction tests are required for #612
+
+## 11. Non-goals
+
+- Replace Gitea as the durable workflow record  
+- Let Sentry/GlitchTip assign work or mutate Gitea workflow state outside sanctioned tools  
+- Let the bridge approve, merge, close, release, or bypass Gitea gates  
+- Implement #600 on file locks / comments alone and call allocator complete  
+- Treat raw monitoring incidents as `work_items` for the allocator  
+- Put monitor tokens into every Gitea MCP worker process by default  
+
+## 12. Consequences
+
+### Positive
+
+- Clear implementation order and ownership  
+- Multi-session safety becomes testable at the DB layer  
+- Observability becomes assignable work without special-casing the allocator  
+- Trust boundaries stay compatible with existing control-plane docs  
+
+### Costs / risks
+
+- Migration from comment/file leases requires reconciler work  
+- Shared Postgres or single allocator daemon is operational cost  
+- Bridge must be careful not to spam Gitea issues (dedupe, caps, policy modes)  
+
+### Follow-ups (documentation only until implemented)
+
+1. Update #600, #612, and #613 bodies to **link this ADR** and restate hard dependencies.  
+2. Implement #613 schema + atomic assign/lease.  
+3. Implement #600 against the DB.  
+4. Implement #612 against `incident_links` + Gitea create/update.  
+5. Deprecate dual writers for leases.
+
+## 13. Acceptance criteria for *this* ADR
+
+This document is accepted when:
+
+1. It is merged into `docs/architecture/` on the default branch.  
+2. #600 / #612 / #613 (or their PRs) reference this path as the architecture source of truth.  
+3. No implementation PR for those issues claims completion without conforming to §§2–11.
+
+## 14. Document history
+
+| Date | Change |
+|------|--------|
+| 2026-07-09 | Initial ADR: dependency order, authority model, topology, lease migration, bridge, `incident_links`, security, non-goals |

docs/canonical-state-comments.md

@@ -0,0 +1,183 @@
+# Canonical State Comments
+
+Gitea is the durable system of record for workflow continuation. When a
+comment changes issue, PR, or discussion state, it should leave enough
+information for the next role to continue without private chat history.
+
+Canonical comments answer:
+
+- what state the object is in
+- who acts next
+- what the next actor should do
+- the exact prompt the next actor should run
+- which proof, blocker, or dependency matters
+
+Non-workflow discussion comments do not need this template.
+
+## Issue State
+
+Use this when an issue becomes ready, blocked, in progress, PR-open,
+superseded, merged, or otherwise changes workflow direction.
+
+```text
+## Canonical Issue State
+
+STATE:
+<ready-for-author | in-progress | blocked | PR-open | needs-review | ready-to-merge | merged | closed | superseded>
+
+WHO_IS_NEXT:
+<controller | author | reviewer | merger | reconciler | user>
+
+NEXT_ACTION:
+<specific one-sentence action>
+
+NEXT_PROMPT:
+<paste-ready prompt for the next role>
+
+WHAT_HAPPENED:
+<latest meaningful event>
+
+WHY:
+<decision rationale>
+
+RELATED_DISCUSSION:
+<link/reference or none>
+
+RELATED_PRS:
+- #...
+
+BRANCH:
+<branch or none>
+
+HEAD_SHA:
+<40-character SHA or none>
+
+VALIDATION:
+<tests/proofs or none>
+
+BLOCKERS:
+<blocker and unblock condition, or none>
+
+LAST_UPDATED_BY:
+<identity/profile/date>
+```
+
+## PR State
+
+Use this when a PR needs review, receives changes requested, is approved,
+is stale, is superseded, or becomes ready for merge.
+
+```text
+## Canonical PR State
+
+STATE:
+<needs-review | changes-requested | approved | stale-approval | ready-to-merge | merged | blocked | superseded>
+
+WHO_IS_NEXT:
+<controller | author | reviewer | merger | reconciler | user>
+
+NEXT_ACTION:
+<specific one-sentence action>
+
+NEXT_PROMPT:
+<paste-ready prompt for the next role>
+
+WHAT_HAPPENED:
+<latest meaningful event>
+
+WHY:
+<decision rationale>
+
+ISSUE:
+#...
+
+BASE:
+<branch>
+
+HEAD:
+<branch>
+
+HEAD_SHA:
+<40-character SHA>
+
+REVIEW_STATUS:
+<none | approved | changes-requested | stale | contaminated>
+
+VALIDATION:
+<tests/proofs>
+
+BLOCKERS:
+<blockers or none>
+
+SUPERSEDES:
+<PRs or none>
+
+SUPERSEDED_BY:
+<PR or none>
+
+MERGE_READY:
+<yes/no and why>
+
+LAST_UPDATED_BY:
+<identity/profile/date>
+```
+
+## Discussion Summary
+
+Discussions should normally have at least five substantive comments before
+conversion into issues. A controller may waive that only for tiny mechanical,
+urgent, or explicitly trivial work.
+
+```text
+## Canonical Discussion Summary
+
+STATE:
+<needs-more-discussion | ready-for-issues | issues-created | closed>
+
+WHO_IS_NEXT:
+<controller | author | reviewer | user>
+
+DECISION:
+<what was decided>
+
+WHY:
+<reasoning and tradeoffs>
+
+SUBSTANTIVE_COMMENTS:
+<count and summary>
+
+ISSUES_TO_CREATE_OR_CREATED:
+- #...
+
+DEPENDENCY_ORDER:
+<order or none>
+
+NON_GOALS:
+<non-goals>
+
+OPEN_QUESTIONS:
+<questions or none>
+
+NEXT_ACTION:
+<specific one-sentence action>
+
+NEXT_PROMPT:
+<paste-ready prompt for the next role>
+
+LAST_UPDATED_BY:
+<identity/profile/date>
+```
+
+## Validation Rules
+
+The final-report validator rejects canonical state update claims when the
+report omits the canonical block or when the block lacks:
+
+- `STATE`
+- `WHO_IS_NEXT`
+- `NEXT_ACTION`
+- `NEXT_PROMPT`
+
+It also rejects vague next actions such as `continue`, ready-to-merge states
+without approval/head-SHA proof, superseded states without canonical item
+proof, and blocked states without an unblock condition.

docs/canonical-thread-handoff.md

@@ -0,0 +1,142 @@
+# Canonical Thread Handoff (CTH)
+
+**CTH** = **Canonical Thread Handoff**
+
+A CTH comment is the authoritative workflow handoff in a Gitea issue or PR
+thread. It records current state, decisions, blockers, proof, and the exact
+next prompt/action for the next LLM or person.
+
+CTH comments complement — but do not replace — formal Gitea review state.
+A CTH may summarize an APPROVE or REQUEST_CHANGES decision, yet merge gates
+still require the live Gitea review verdict.
+
+## CTH comment types
+
+- `CTH: State Handoff`
+- `CTH: Controller Decision`
+- `CTH: Author Handoff`
+- `CTH: Reviewer Handoff`
+- `CTH: Merger Handoff`
+- `CTH: Supersession Notice`
+- `CTH: Blocker`
+
+## Required base template
+
+```md
+## CTH: <Type>
+
+Status:
+Next owner:
+Current blocker:
+Decision:
+Proof:
+Next action:
+Ready-to-paste prompt:
+```
+
+Extended fields may map to canonical issue/PR state templates from #495 when
+that layer is available. Until then, keep the base fields complete.
+
+## Discovery and posting rules
+
+Before acting in an issue or PR thread:
+
+1. **Find the latest CTH comment** before doing work.
+2. Treat the **latest valid CTH** as the current handoff state.
+3. **Post a new CTH** when you finish, block, skip, supersede, request
+   changes, approve, or hand off.
+4. Do **not** rely on stale non-CTH comments when a newer CTH exists.
+5. Casual discussion comments do not need to be CTH comments.
+
+## Examples
+
+### PR approved and ready for merger
+
+```md
+## CTH: Reviewer Handoff
+
+Status: approved_at_current_head
+Next owner: merger
+Current blocker: none
+Decision: APPROVE recorded at head abc123...
+Proof: gitea_submit_pr_review performed; visible verdict APPROVE
+Next action: eligible merger merges PR #N with pinned expected_head_sha
+Ready-to-paste prompt: Merge PR #N for issue #M if live head still abc123... and merge gates pass.
+```
+
+### PR request-changes back to author
+
+```md
+## CTH: Reviewer Handoff
+
+Status: request_changes_at_current_head
+Next owner: author
+Current blocker: unresolved findings in validation report
+Decision: REQUEST_CHANGES at head def456...
+Proof: gitea_submit_pr_review performed; blocking review visible
+Next action: author fixes findings and pushes; reviewer re-validates fresh head
+Ready-to-paste prompt: Fix PR #N review findings, push to feat/issue-M-..., post Author Handoff CTH.
+```
+
+### Duplicate / superseded PR closure
+
+```md
+## CTH: Supersession Notice
+
+Status: superseded
+Next owner: controller
+Current blocker: duplicate branch/PR work
+Decision: close PR #N; continue on PR #M
+Proof: duplicate gate linked open PR #M for issue #K
+Next action: controller closes superseded PR and records canonical state
+Ready-to-paste prompt: Close superseded PR #N; confirm PR #M remains canonical for issue #K.
+```
+
+### Blocked workflow due to dirty root/worktree
+
+```md
+## CTH: Blocker
+
+Status: blocked_preflight
+Next owner: operator
+Current blocker: dirty control checkout / branches worktree mismatch
+Decision: stop before mutation
+Proof: verify_preflight_purity failed; workspace diagnostics attached
+Next action: repair worktree or relaunch MCP from branches/ worktree
+Ready-to-paste prompt: Repair dirty workspace, relaunch MCP from branches/review-prN, retry review.
+```
+
+### Stale head requiring fresh review
+
+```md
+## CTH: Reviewer Handoff
+
+Status: stale_head
+Next owner: reviewer
+Current blocker: live head differs from pinned review head
+Decision: prior approval not valid for current head
+Proof: expected_head_sha mismatch at merge gate
+Next action: re-run validation and post fresh review decision
+Ready-to-paste prompt: Re-validate PR #N at live head, dry-run review gates, submit fresh verdict.
+```
+
+### Issue implementation handoff
+
+```md
+## CTH: Author Handoff
+
+Status: implementation_complete_pending_review
+Next owner: reviewer
+Current blocker: none
+Decision: PR #N ready for review at head fedcba...
+Proof: tests passed in branches/issue-M-...; PR opened with Closes #M
+Next action: reviewer acquires lease and validates PR #N
+Ready-to-paste prompt: Review PR #N for issue #M; pin head fedcba... before mutations.
+```
+
+## Related
+
+- [`llm-workflow-runbooks.md`](llm-workflow-runbooks.md)
+- [`../skills/llm-project-workflow/templates/canonical-thread-handoff.md`](../skills/llm-project-workflow/templates/canonical-thread-handoff.md)
+- #495 — canonical next-action comment fields
+- #496 — fail-closed validation for workflow-changing comments

docs/developer-testing-guidelines.md

@@ -54,6 +54,25 @@ Use `-q` for a compact summary and `-v` to see individual test names.
 ./venv/bin/python -m pytest tests/ -q
 ```
 
+### Web UI suite (#436)
+
+Hermetic unittest modules matching `test_webui_*.py` cover route rendering,
+read-only guards, registry/prompt/queue loaders, and optional child-issue
+modules when present on the branch.
+
+```bash
+./scripts/test-webui
+./scripts/ci-webui-check          # skip unless the diff touches web UI paths
+WEBUI_CI_FORCE=1 ./scripts/ci-webui-check
+```
+
+`scripts/test-webui` defaults `WEBUI_TEST_OFFLINE=1` so route coverage never
+needs Gitea credentials or MCP daemon credential access. Set
+`WEBUI_TEST_OFFLINE=0` only for explicit operator live-fetch checks.
+
+Wire `scripts/ci-webui-check` into Jenkins (or equivalent) for PRs that touch
+`webui/`, `tests/test_webui_*`, or `docs/webui*`.
+
 ### Run targeted tests
 
 ```bash

docs/examples/two-comment-workflow-examples.md

@@ -0,0 +1,43 @@
+# Two-comment workflow examples (#507)
+
+Paired `[CONTROLLER HANDOFF]` + `[THREAD STATE LEDGER]` comments for Gitea threads.
+See `thread_state_ledger_examples.py` for machine-checked fixtures.
+
+## Approved review posted
+
+**Handoff** (detailed): identity, worktree, validation commands, mutation ledger with
+`gitea_submit_pr_review → APPROVED review posted to Gitea`.
+
+**Ledger** (concise):
+
+```markdown
+[THREAD STATE LEDGER] PR #487 — APPROVED review posted to Gitea
+
+What is true now:
+- PR state: open
+- Server-side decision state: APPROVED review posted to Gitea
+- Local verdict/state: APPROVE verdict prepared locally
+
+What is blocked:
+- Blocker classification: no blocker
+
+Who/what acts next:
+- Next actor: merger
+- Required action: merge on explicit operator command
+- Do not do: re-post APPROVE
+```
+
+## Approve validated locally but blocked before posting
+
+Ledger must show `no server-side state changed` under server-side decision state and
+`APPROVE verdict prepared locally` under local verdict/state.
+
+## Environment / tooling blocker
+
+Ledger blocker classification: `environment/tooling blocker`. Mutation ledger:
+`none — no server-side state changed`.
+
+## Stale head blocker
+
+Ledger: `approval_at_current_head is false`; classification `stale head`.
+Do not do: merge with stale approval.

docs/gitea-dual-namespace-deployment.md

@@ -22,9 +22,12 @@ launched with exactly one static execution profile:
 | Namespace (MCP server name) | Profile (role) | Typical use |
 |-----------------------------|----------------|-------------|
 | `gitea-author` | an author profile | implement issues, push branches, open PRs, comment |
-| `gitea-reviewer` | a reviewer profile | review, approve/request changes, merge |
+| `gitea-reviewer` | a reviewer profile | review, approve/request changes |
+| `gitea-merger` | a merger profile | merge PRs after approval and verification |
 | `gitea-reconciler` | a reconciler profile | close already-landed open PRs after ancestry proof (#304 profile; #310 close tool) |
 
+Review and merge are separate workflow roles. A reviewer approval is not merge authorization.
+
 Properties:
 
 - **One process, one credential.** Each namespace authenticates as exactly
@@ -106,6 +109,14 @@ syntax to the client):
         "GITEA_MCP_CONFIG": "<path-to-profiles.json>",
         "GITEA_MCP_PROFILE": "<reviewer-profile-name>"
       }
+    },
+    "gitea-merger": {
+      "command": "<path-to>/venv/bin/python3",
+      "args": ["<path-to>/mcp_server.py"],
+      "env": {
+        "GITEA_MCP_CONFIG": "<path-to-profiles.json>",
+        "GITEA_MCP_PROFILE": "<merger-profile-name>"
+      }
     }
   }
 }

docs/gitea-execution-profiles.md

@@ -311,7 +311,8 @@ To make Gitea MCP profile activation and runtime identity state explicit, the fo
 ### 2. Dual MCP Namespaces Recommendation
 For security-sensitive or high-risk tasks, the preferred safety model uses separate, isolated MCP server instances (namespaces/sessions) launched with static profiles:
 - `gitea-author`: Exposes tools configured with author permissions; cannot perform approvals or merges.
-- `gitea-reviewer`: Exposes tools configured with reviewer permissions; used for PR reviews and merges.
+- `gitea-reviewer`: Exposes tools configured with reviewer permissions; used for PR reviews. Review and merge are separate workflow roles. A reviewer approval is not merge authorization.
+- `gitea-merger`: Exposes tools configured with merger permissions; used for PR merges.
 This layout maintains physical separation of credentials and prevents privilege escalation within a single session.
 This is the model accepted in #139; deployment details, rationale, and client
 setup live in

docs/label-taxonomy.md

@@ -1,34 +1,98 @@
 # Label Taxonomy
 
-This document catalogs the issue labels used for MCP workflows, including Jenkins and GlitchTip (observability).
+This document defines the canonical issue labels used by MCP workflows.
 
-> **Approval Required:** Do not create or apply new labels in `manage_labels.py` without explicit owner approval of this document.
+Every issue should carry:
 
-## Existing Labels
+- one `type:*` label
+- one `status:*` label
 
-* **`jenkins`**
-  * Description: Jenkins integration
-  * Color: `d93f0b`
-  * Use: Used to mark issues, PRs, or tasks that involve the `jenkins-mcp` boundaries, CI/CD designs, or build failures.
+Discussion-only issues must carry `type:discussion`.
 
-* **`glitchtip`**
-  * Description: GlitchTip integration
-  * Color: `b60205`
-  * Use: Used to mark issues related to the `glitchtip-mcp` boundary and observability integration.
+## Issue Type Labels
 
-## Proposed / Missing Labels
+| Label | Use |
+| --- | --- |
+| `type:bug` | Bug or defect |
+| `type:feature` | Feature or enhancement |
+| `type:process` | Process or policy work |
+| `type:workflow` | Workflow automation or guidance |
+| `type:guardrail` | Safety gate or guardrail |
+| `type:docs` | Documentation work |
+| `type:test` | Tests or test infrastructure |
+| `type:discussion` | Discussion-only issue |
+| `type:umbrella` | Umbrella or tracker issue |
+| `type:cleanup` | Cleanup or hygiene work |
 
-* **`observability`**
-  * Proposed Description: Observability, metrics, and monitoring tasks
-  * Proposed Color: `5319e7`
-  * Use: Broader than GlitchTip alone; covers logging, metrics, traces, and general observability pipeline improvements.
+## Workflow Status Labels
 
-* **`source:glitchtip`**
-  * Proposed Description: Issue filed automatically by GlitchTip orchestration
-  * Proposed Color: `b60205`
-  * Use: Applied automatically by the orchestrator when a GlitchTip error event is converted into a Gitea issue.
+Only one `status:*` label should be active on an issue at a time. When an issue
+moves forward, tooling must remove the old `status:*` label and apply the new
+one.
 
-* **`status:triage`**
-  * Proposed Description: Issue needs human or orchestrator triage
-  * Proposed Color: `fbca04`
-  * Use: Used for incoming issues (especially automated ones like `source:glitchtip`) that have not yet been evaluated for priority or resolution.
+| Label | Use |
+| --- | --- |
+| `status:triage` | Issue needs triage |
+| `status:ready` | Issue is ready for work |
+| `status:claimed` | Issue is claimed |
+| `status:in-progress` | Issue is being worked on |
+| `status:blocked` | Issue is blocked |
+| `status:needs-review` | Issue work needs review |
+| `status:pr-open` | A linked PR is open |
+| `status:approved` | Linked PR is approved |
+| `status:merged` | Linked PR is merged |
+| `status:reconcile` | Issue needs reconciliation |
+| `status:done` | Issue workflow is complete |
+| `status:duplicate` | Issue is a duplicate |
+| `status:wontfix` | Issue will not be fixed |
+
+## Transition Rules
+
+Suggested lifecycle:
+
+1. New issue created: `status:triage` or `status:ready`
+2. Issue selected by an author: `status:claimed`
+3. Author starts work: `status:in-progress`
+4. Work is blocked: `status:blocked`
+5. PR opened: `status:pr-open`
+6. PR approved: `status:approved`
+7. PR merged but issue still needs closure/reconciliation: `status:reconcile`
+8. Issue fully complete: `status:done`
+9. Duplicate issue: `status:duplicate`
+10. Won't-fix issue: `status:wontfix`
+
+The helper module `issue_workflow_labels.py` is the source of truth for the
+canonical label specs and status transition replacement behavior.
+
+## Discussion Issues
+
+Discussion issues must be labeled `type:discussion`.
+
+A discussion issue should not be treated as implementation-ready unless it also
+has a clear implementation status and next action.
+
+If a discussion produces implementation work, either:
+
+1. convert the discussion issue into an implementation issue by changing labels
+   and adding acceptance criteria, or
+2. create child implementation issues and leave the discussion issue as
+   `type:discussion`.
+
+## Tooling
+
+- `manage_labels.py --create-labels` creates the canonical `type:*` and
+  `status:*` labels.
+- `gitea_create_issue` recommends `type:*` and `status:*` labels when missing
+  and can apply supplied label names.
+- `gitea_mark_issue(..., action="start")` replaces old `status:*` labels with
+  `status:in-progress`.
+- `gitea_create_pr` fails closed before PR creation if `status:pr-open` cannot
+  be applied to the locked issue, then applies it after the PR is created.
+- `gitea_set_issue_labels` accepts an explicit `worktree_path` so author
+  sessions can satisfy the branches-only mutation guard while changing labels.
+
+## Existing Non-Workflow Labels
+
+Existing non-workflow labels such as `mcp`, `workflow`, `labels`, `tracker`,
+`jenkins`, `glitchtip`, `documentation`, and `testing` remain valid topical
+labels. They do not replace the required `type:*` and `status:*` labels.

docs/llm-workflow-runbooks.md

@@ -7,6 +7,11 @@ package of the MCP Control Plane: creating issues, implementing them, opening
 and reviewing pull requests, merging, and closing out — safely and
 reproducibly.
 
+Canonical state comments for durable issue/PR/discussion continuation are
+documented in [`canonical-state-comments.md`](canonical-state-comments.md).
+Use them when a workflow-changing comment needs to leave the next actor, next
+action, and paste-ready prompt in Gitea.
+
 > For the **project-agnostic** version of these operating rules (issue-first,
 > isolated worktrees, no self-review/merge, profile safety, cleanup, fail-closed)
 > that can be copied into any repository, see the reusable skill
@@ -28,6 +33,8 @@ audit logging). See [Related documents](#related-documents).
 > to discover the available project workflows and `mcp_get_skill_guide(<name>)`
 > for step-by-step instructions. This replaces long pasted operator prompts for
 > the standard rules; operator prompts still control task-specific scope.
+>
+> **BLOCKED + DIAGNOSE (default for any missing required step):** If a required workflow skill, guide, tool, capability, preflight, terminal, worktree binding, profile, or instruction is unavailable or fails, STOP. State BLOCKED. Use the canonical blocker report template (see skills/llm-project-workflow/templates/blocked-diagnose-report.md and the llm-project-workflow/SKILL.md universal rules). Only non-mutating recovery. Report fully. No unsafe fallbacks (temp scripts, direct API, MCP internals, direct imports, in-memory restoration, manual bypasses) unless controller authorizes in the handoff for this case. Missing required steps must fail closed *before* any git or Gitea mutation. Controller prompts and all workflows must reinforce: BLOCKED + DIAGNOSE, then stop.
 > See issue #129 for the skill registry design.
 
 Jenkins and GlitchTip workflows use separate MCP servers, not this Gitea MCP
@@ -408,6 +415,31 @@ The guard blocks when the **control checkout** (repository root) is:
 `branches/...` directories are disposable role worktrees; the root checkout is
 the stable orchestration surface only.
 
+## Canonical workflow skill names (#551)
+
+Controller prompts and sessions must load the **same** workflow skill wall
+regardless of runtime (Claude, Codex, Gemini):
+
+| Name | Role |
+|------|------|
+| `gitea-workflow` | Primary controller / Codex skill name |
+| `llm-project-workflow` | Portable in-repo package |
+| `git-pr-workflows` | Legacy alias |
+
+- Inventory: `mcp_list_project_skills` lists all three.
+- Preflight: `mcp_check_workflow_skill_preflight` before mutations.
+- Codex install: `scripts/install-codex-workflow-skill.sh`
+- Full doc: [`docs/workflow-skill-mount.md`](workflow-skill-mount.md)
+
+If the skill is missing, stop with BLOCKED + DIAGNOSE — do not mutate.
+
+## No direct-import mutation path (#558)
+
+Never `import gitea_mcp_server` or call `gitea_auth.get_auth_header` /
+keychain fill from a raw shell to bypass MCP preflight.
+
+Use the official MCP daemon only. See [`docs/mcp-daemon-import-guard.md`](mcp-daemon-import-guard.md).
+
 ## Bootstrap Review Path for self-hosted MCP fixes (#557)
 
 When a PR fixes Gitea-Tools MCP workflow code that the **live daemon** still
@@ -629,24 +661,44 @@ session, clearing hung background terminals, switching to MCP-native commit, and
 the agent temp artifact cleanup checklist. Do **not** retry shell encoding in a
 loop and do **not** substitute WebFetch/Playwright/manual base64.
 
+### Terminal launcher diagnostics (#556)
+
+When git/pytest finalization fails with opaque spawn errors (e.g. `os error 2`),
+do **not** improvise shell wrappers or fall back to direct API / temp scripts.
+
+1. Call `gitea_diagnose_terminal` (optional `cwd`, optional `command`) — returns
+   categorized failure: missing cwd, cwd not a directory, missing executable,
+   missing runtime wrapper, missing shell, probe timeout, or session launcher
+   failure.
+2. Call `gitea_get_shell_health` for the shell circuit-breaker state.
+3. Mutation-capable `gitea_resolve_task_capability` probes the terminal launcher
+   before allowing git/pytest-oriented work; on failure it returns
+   `BLOCKED + DIAGNOSE` with `terminal_launcher_unhealthy` and diagnostics.
+4. Emit the canonical `blocked-diagnose-report.md` template and stop.
+
 ### Create an issue / child issues
 
 - **Profile:** issue-manager or author (any profile allowed to create issues).
 - **Steps:** create the parent/roadmap issue; create child issues; apply the
   minimal label set; link children to the parent.
+- **Labels:** new issues should carry one `type:*` label and one `status:*`
+  label. Discussion-only issues must carry `type:discussion`. See
+  [`label-taxonomy.md`](label-taxonomy.md).
 - **Prompt:** `Using the issue-manager profile, create issue "<title>" with body
   <body>, then create child issues for <list> and link them to the parent.`
 
 ### Implement an issue and open a PR
 
 - **Profile:** author.
-- **Steps:** claim the issue (`status:in-progress`); create an isolated branch
-  worktree from latest `master` under `branches/` (`feat/issue-<n>-...` /
+- **Steps:** claim the issue (`status:in-progress`, replacing any old
+  `status:*` label); create an isolated branch worktree from latest `master`
+  under `branches/` (`feat/issue-<n>-...` /
   `fix/...` / `docs/...`); `cd` into that worktree; implement narrowly; add or
   update tests if behavior changes; run the full suite; commit with an
-  issue-linked message; open a PR to `master`. **Do not** review or merge your
-  own PR. Include an `LLM Handoff Metadata` block (with `LLM-Agent-SHA`) in
-  the PR body — see [`llm-agent-sha.md`](llm-agent-sha.md).
+  issue-linked message; open a PR to `master`; move the issue to
+  `status:pr-open`. **Do not** review or merge your own PR. Include an
+  `LLM Handoff Metadata` block (with `LLM-Agent-SHA`) in the PR body — see
+  [`llm-agent-sha.md`](llm-agent-sha.md).
 - **Prompt:** `Use an author profile to implement issue #N and open a PR to
   master. Do not self-review or self-merge.`
 
@@ -687,10 +739,10 @@ loop and do **not** substitute WebFetch/Playwright/manual base64.
 ### Merge a PR
 
 - **Profile:** merger (allowed to merge; must **not** be the PR author).
-- **Steps:** confirm eligibility; require explicit confirmation
-  (`MERGE PR <n>`); optionally pin head SHA / changed-file set; merge only when
-  Gitea reports the PR mergeable (branch-protection checks satisfied). No force,
-  no ignore-checks. Verify that remote master contains the merge commit or the expected squashed changes (do not assume a "closed" PR succeeded without verifying the actual landed changes).
+- **Steps:**
+  - Merger workflow starts only after formal approval at current head. Reviewer workflow ends with review decision and separate merger handoff.
+  - Confirm eligibility; require explicit confirmation (`MERGE PR <n>`); optionally pin head SHA / changed-file set; merge only when Gitea reports the PR mergeable (branch-protection checks satisfied). No force, no ignore-checks. Verify that remote master contains the merge commit or the expected squashed changes (do not assume a "closed" PR succeeded without verifying the actual landed changes).
+  - Review and merge are separate workflow roles. A reviewer approval is not merge authorization.
 - **Prompt:** `Use any eligible merger profile to merge PR #N if checks pass and
   it is mergeable. Confirm with "MERGE PR N". Do not force-merge.`
 
@@ -738,6 +790,53 @@ merger handoff.
 - **Prompt (normal):** `After verifying master contains the merge of PR #N using post-merge file-presence verification, close issue #M and delete the merged branch. Include verification details in the report.`
 - **Prompt (reconcile):** `Reconcile closed-not-merged PR #N by verifying if its content landed on master.`
 
+### Post-merge merged cleanup ownership (#523)
+
+Post-merge **local worktree / remote branch cleanup** is **reconciler** work, not
+author work. Do not switch from `prgs-reconciler` to `prgs-author` only to run
+`gitea_reconcile_merged_cleanups`.
+
+- **Profile:** `prgs-reconciler` (task `reconcile_merged_cleanups` /
+  `reconciliation_cleanup`).
+- **Namespace:** reconciler MCP server; stable control checkout is allowed for
+  this role (branches-only author guard does not apply).
+- **Steps:**
+  1. `gitea_whoami` + `gitea_resolve_task_capability(task="reconcile_merged_cleanups")`.
+  2. Dry-run first: `gitea_reconcile_merged_cleanups(dry_run=True)`.
+  3. Execute only after audit/authorization gates when remote branch delete or
+     worktree removal is required (`dry_run=False`, `execute_confirmed=True`,
+     and `gitea.branch.delete` when deleting remotes).
+- **Fail closed:** unmerged/open heads, mismatched worktrees, and non-merged
+  closed PRs must not be cleaned.
+- **Reports:** label cleanup actions as reconciler cleanup (not author mutation).
+- **Prompt:** `As prgs-reconciler, dry-run then execute gitea_reconcile_merged_cleanups for recently merged PRs without switching to prgs-author.`
+
+### Superseded PR / satisfied issue reconciliation (#525)
+
+Closing duplicate or superseded PRs after a canonical PR has merged is
+**reconciler** work. Do not switch to `prgs-author` only to close the duplicate
+PR, close the satisfied issue, or file a narrow follow-up discovered during
+reconciliation.
+
+- **Profile:** `prgs-reconciler`.
+- **Tasks:** `reconcile_close_superseded_pr`,
+  `reconcile_close_satisfied_issue`, and
+  `reconcile_create_followup_issue`.
+- **Tool:** `gitea_reconcile_superseded_by_merged_pr`.
+- **Required proof:**
+  1. Live target PR state is open, but it is not independently required and no
+     mergeable work remains.
+  2. Live superseding PR state is closed and merged.
+  3. Superseding PR head is an ancestor of freshly fetched `master`.
+  4. Merge commit SHA is recorded.
+  5. Canonical close comment cites the superseding PR and merge commit.
+  6. Linked issue closure is attempted only when the issue is open and
+     explicitly satisfied by the superseding PR.
+- **Fail closed:** missing ancestry proof, missing canonical comment,
+  mergeable target PR, same target/superseding PR, or missing
+  `gitea.pr.close` / `gitea.issue.close` capability.
+- **Prompt:** `As prgs-reconciler, reconcile PR #N as superseded by merged PR #M; post the canonical close comment, close the superseded PR, and close issue #K only if the merged PR fully satisfies it.`
+
 ### Stop on blocker
 
 - **Any profile.** If a required gate cannot be satisfied — identity
@@ -758,7 +857,7 @@ an author.
 |---|---|---|---|---|
 | Review PR (`review_pr`) | reviewer (e.g. `sysadmin` / `prgs-reviewer`) | read, gated review verdicts | commits, pushes, file edits, author comments, merge without eligibility | active profile is an author profile — stop immediately; do **not** switch to author-side fixes unless the operator explicitly re-tasks |
 | Address PR change requests (`address_pr_change_requests`) | author (e.g. `jcwalker3` / `prgs-author`) | commit/push fixes to the PR branch, PR comment summarizing fixes | review verdicts, approve, request-changes, merge | active profile lacks branch push |
-| Merge PR (`merge_pr`) | reviewer/merger | gated merge after eligibility + approval | merging own PR, merging without pinned head match | active profile is an author profile, or any merge gate fails |
+| Merge PR (`merge_pr`) | merger (e.g. `sysadmin` / `prgs-merger`) | gated merge after eligibility + approval | merging own PR, merging without pinned head match, reviewing PRs | active profile is an author or reviewer-only profile, or any merge gate fails |
 | Comment on issue discussion (`comment_issue`) | any profile with `gitea.issue.comment` | issue thread comments | review verdicts, closing via comment | permission missing (`gitea.pr.comment` does **not** imply it) |
 | Comment on PR (`comment_pr`) | any profile with `gitea.pr.comment` | PR thread comments | review verdicts | permission missing |
 | Author implementation (`create_branch`/`push_branch`/`create_pr`) | author | branch, commit, push, open PR | self-review, self-merge | profile lacks the author permissions |
@@ -808,6 +907,27 @@ Never imply full-suite success unless the full-suite command itself passed
 (`full_suite_passed: true`). A report that hides a failed or skipped check
 is worse than a failing report.
 
+## Canonical Thread Handoff (CTH)
+
+**CTH** = **Canonical Thread Handoff** — the authoritative workflow handoff
+comment in a Gitea issue or PR thread. See
+[`canonical-thread-handoff.md`](canonical-thread-handoff.md) for types,
+templates, and examples.
+
+Before acting in an issue or PR thread:
+
+1. **Find the latest CTH comment** before doing work.
+2. Treat the **latest valid CTH** as the current handoff state.
+3. **Post a new CTH** when you finish, block, skip, supersede, request
+   changes, approve, or hand off.
+4. Do **not** rely on stale non-CTH comments when a newer CTH exists.
+
+A CTH summarizes workflow state for the next session. Formal Gitea review
+verdicts remain authoritative for merge gates — a CTH is not merge approval
+by itself.
+
+Template: [`../skills/llm-project-workflow/templates/canonical-thread-handoff.md`](../skills/llm-project-workflow/templates/canonical-thread-handoff.md)
+
 ## Controller Handoff (required, every task)
 
 Every task — implementation, review, merge, triage, documentation,
@@ -840,6 +960,161 @@ touched release state names the exact tag/commit and why. Design debates
 belong in **discussion/RFC issues** (e.g. #100 `profiles.json v2`) — comment
 on the issue, create no branches/PRs, and end the comment with this handoff.
 
+## Two-comment workflow reporting (#507)
+
+After meaningful controller/workflow work, post **two separate Gitea comments**
+(not one combined blob):
+
+1. **`[CONTROLLER HANDOFF]`** — detailed operational continuation for the
+   next LLM/controller (proof-heavy; may be long).
+2. **`[THREAD STATE LEDGER]`** — short canonical truth readable in ~30 seconds.
+
+The ledger must answer: what is true now, what changed, what is blocked,
+who/what acts next — and must **separate**:
+
+- local verdict/state
+- server-side Gitea state
+- attempted-but-blocked mutations
+- completed mutations
+
+Use precise state phrases (`APPROVED review posted to Gitea`,
+`APPROVE verdict prepared locally`, `merge performed`, `merge not performed`,
+`no server-side state changed`, `lease attempt blocked`) instead of ambiguous
+standalone words (`approved`, `merged`, `ready`, `blocked`, `done`).
+
+The ledger must include a **blocker classification** from:
+`code blocker`, `test blocker`, `merge conflict`, `stale head`,
+`permission/capability blocker`, `environment/tooling blocker`,
+`process/rule blocker`, `queue/lease blocker`,
+`duplicate/canonicalization blocker`, `no blocker`.
+
+Templates: [`two-comment-workflow.md`](two-comment-workflow.md).
+Worked examples: [`examples/two-comment-workflow-examples.md`](examples/two-comment-workflow-examples.md).
+
+Validation: `thread_state_ledger_validator.py` checks tagged comments at post
+time (`gitea_create_issue_comment`) and tagged final reports via
+`assess_final_report_validator`. Legacy `## Controller Handoff` final reports
+remain valid during transition; the tagged pair is required for new workflow
+comments.
+
+Related (do not duplicate): #494/#495 lifecycle state, #501 mutation-ledger
+consistency, #505 CTH umbrella, #496 workflow comment gate when merged.
+
+## Canonical comment validation (#496)
+
+Workflow-changing issue/PR/review comments must carry durable next-action
+state. Casual discussion is still allowed.
+
+The MCP server runs `canonical_comment_validator.assess_canonical_comment`
+**before** posting through:
+
+- `gitea_create_issue_comment`
+- `gitea_submit_pr_review` / `gitea_dry_run_pr_review` (non-empty review bodies)
+- `gitea_reconcile_already_landed_pr` when `post_comment=True`
+- internal structured comment helpers (machine lease/heartbeat markers stay exempt)
+
+Detection examples:
+
+- **Allowed:** `Thanks, I will check this.`
+- **Rejected:** `Blocked, author should fix.` (workflow trigger without canonical fields)
+
+When validation fails, the tool returns `canonical_comment_validation` with
+`allowed: false`, `missing_fields`, `vague_fields`, `correction_message`, and
+`suggested_template`. **No Gitea API call is made.**
+
+Minimum workflow comment fields:
+
+```text
+STATE:
+WHO_IS_NEXT:
+NEXT_ACTION:
+NEXT_PROMPT:
+WHY:
+```
+
+`WHO_IS_NEXT` must be one of: `controller`, `author`, `reviewer`, `merger`,
+`reconciler`, `user`.
+
+Issue comments also require `RELATED_PRS`, `BLOCKERS`, and `VALIDATION` when
+they mention PR work. PR comments/reviews also require `ISSUE`, `HEAD_SHA`,
+`REVIEW_STATUS`, `MERGE_READY`, `BLOCKERS`, and `VALIDATION`.
+
+Special states:
+
+- `STATE: blocked` — `BLOCKERS` must name an explicit unblock condition.
+- `STATE: superseded` — requires `CANONICAL_ITEM` and `SUPERSEDED_ITEM`.
+- `STATE: ready-to-merge` — requires approval proof and head SHA in
+  `HEAD_SHA`, `REVIEW_STATUS`, `MERGE_READY`, or `VALIDATION`.
+
+Final reports must not claim a comment was posted when
+`canonical_comment_validation.allowed` is false (#496 AC14).
+
+## Stale #332 review-decision lock cleanup (#594)
+
+#332 hard-stops a reviewer session after a terminal live review mutation
+(`approve` / `request_changes`). After #559 those locks are **durable** under
+`~/.cache/gitea-tools/session-state/review_decision_lock-<profile>.json`, so they
+can outlive the PR they protected.
+
+### When cleanup is **allowed**
+
+Use `gitea_cleanup_stale_review_decision_lock` from a **reviewer** profile when:
+
+1. A durable review-decision lock has a terminal live mutation, **and**
+2. Live Gitea state shows that terminal PR is already **merged** or **closed**
+   (so no same-PR merge sequence remains), **and**
+3. The active profile identity matches the lock, **and**
+4. Authenticated identity can be verified.
+
+Workflow:
+
+```text
+# 1) Assess only (default)
+gitea_cleanup_stale_review_decision_lock(apply=false, remote=prgs, ...)
+
+# 2) Apply after is_moot=true and cleanup_allowed=true
+gitea_cleanup_stale_review_decision_lock(
+  apply=true,
+  expected_terminal_pr=<merged-or-closed-pr>,
+  remote=prgs,
+  ...
+)
+```
+
+Successful apply:
+
+* clears in-memory + durable decision lock for that profile
+* returns a structured `audit` payload
+* posts an audit comment on the mooted PR when `gitea.pr.comment` is allowed
+  (`post_audit_comment=true` default)
+
+Same-profile auto-expire: if `gitea_merge_pr` succeeds on a PR that this same
+profile just approved, the decision lock is cleared after merge. Cross-profile
+locks (reviewer vs merger) still require the cleanup tool.
+
+### When cleanup is **forbidden**
+
+Do **not** clear when:
+
+* the last terminal PR is still **open** (active #332 hard-stop — continue merge
+  for that approve, or stop after request_changes)
+* live PR state cannot be fetched (fail closed)
+* profile identity does not match the lock
+* identity cannot be verified
+* `expected_terminal_pr` does not match the last terminal PR
+
+**Never** use manual deletion of session-state files as the normal workflow.
+**Never** use cleanup to skip review of an open PR or to bypass eligibility /
+mark-ready / submit gates on active work.
+
+### Related tools
+
+| Tool | Purpose |
+|------|---------|
+| `gitea_cleanup_stale_review_decision_lock` | Moot decision-lock cleanup (#594) |
+| `gitea_authorize_review_correction` | Operator-approved correction after a **mistaken** live review on still-active work (#211) |
+| `gitea_cleanup_post_merge_moot_lease` | Moot **lease** cleanup after merge (#515) — different object |
+
 ## Fail-closed behavior
 
 Before any mutating action the workflow verifies identity, active profile,
@@ -951,6 +1226,7 @@ When posting a Canonical Thread Handoff after a binding blocker:
 
 ## Related documents
 
+- [`reviewer-handoff-consistency.md`](reviewer-handoff-consistency.md) — reject contradictory reviewer handoffs (#501).
 - [`issue-acceptance-gate.md`](issue-acceptance-gate.md) — controller issue-acceptance audit after PR merge (#500).
 - [`../skills/llm-project-workflow/SKILL.md`](../skills/llm-project-workflow/SKILL.md) — portable cross-project LLM workflow skill.
 - [`gitea-execution-profiles.md`](gitea-execution-profiles.md) — the profile model.

docs/mcp-daemon-import-guard.md

@@ -0,0 +1,23 @@
+# MCP daemon import and keychain guard (#558)
+
+## Problem
+
+During deadlock debugging, agents imported `gitea_mcp_server` / ran credential
+helpers from a raw shell, bypassing preflight purity and role gates.
+
+## Rule
+
+Mutation auth and keychain fill require a **sanctioned MCP daemon** process.
+
+| Context | Allowed |
+|---------|---------|
+| Official MCP entrypoint (`mcp_server.py` / `gitea_mcp_server` `__main__`) sets `GITEA_MCP_SANCTIONED_DAEMON=1` | yes |
+| pytest | yes |
+| `GITEA_ALLOW_DIRECT_MCP_IMPORT=1` (operator/tests only) | yes |
+| bare `python -c 'import gitea_auth; get_auth_header(...)'` | **no** |
+| keychain fill without daemon | **no** unless `GITEA_ALLOW_KEYCHAIN_CLI=1` |
+
+## Operator note
+
+LLM sessions must never set the allow-direct-import or allow-keychain-cli
+overrides. Those are human-only escape hatches.

docs/mcp-menu.md

@@ -41,7 +41,7 @@ The script must be executable (`chmod +x mcp-menu.sh`). It uses bash with
 |--------|-------------|
 | Project status / root checkout health | Shows cwd, branch, `git status --short --branch`, HEAD SHA, `prgs/master` SHA, and warnings when the root checkout is dirty or off `master`. |
 | Author workflow prompts | Ready-to-copy prompts for issue work, conflict-fix sessions, and root checkout recovery. |
-| Reviewer workflow prompts | PR review prompt (review-only; no merge). |
+| Reviewer workflow prompts | Standard PR review prompt, and a skip-already-reviewed-stale-`REQUEST_CHANGES` prompt that hands off to the author without a duplicate terminal mutation (review-only; no merge). |
 | Merger workflow prompts | PR merge prompt (merge gates and explicit approval). |
 | Reconciler workflow prompts | Already-landed / closed PR reconciliation prompt. |
 | Onboarding new project | Checklist prompt for adding a repository to the MCP workflow. |

docs/mcp-namespace-eof-recovery.md

@@ -0,0 +1,118 @@
+# Recovering from `client is closing: EOF` on a Gitea MCP namespace (#543)
+
+## Symptom
+
+A tool call through a Gitea MCP namespace — `gitea-author`, `gitea-reviewer`,
+`gitea-merger`, or the shared `gitea-tools` namespace — fails immediately with:
+
+```
+client is closing: EOF
+```
+
+Every subsequent call to that same namespace returns the same error, including
+cheap read tools such as `gitea_whoami` and `gitea_list_profiles`. Other MCP
+servers registered with the same client (for example `context7`) keep working,
+so this is **not** a global MCP-client outage.
+
+## Why this is not a code defect
+
+This failure is a **transport-level** condition in the IDE / MCP client manager,
+not a missing or broken tool:
+
+- The tool can be present and registered in the Python `FastMCP` tool manager.
+- Direct Python inspection of the server confirms the tool exists.
+- Running the server manually and sending JSON-RPC over stdio works fine
+  (offline spawn) — that path does **not** prove the IDE namespace is healthy.
+
+The client manager entered a closed state after the backing subprocess for that
+namespace terminated (or was killed) behind its back. Once closed, the client
+does **not** re-spawn the child on the next tool call — it just replays
+`client is closing: EOF`. The OS process may even still be alive if a parent
+language-server process is holding the stdio pipes open.
+
+This is the canonical "registered in FastMCP ≠ callable through the namespace"
+false-ready state. It is distinct from the **stale-runtime** family in #531 /
+#544, where the process is reachable but running behind `master`; that case is
+detected by the `ps`-based `_check_mcp_runtimes_diagnostics` in
+`gitea_mcp_server.py`. The EOF case is a dead/closed transport, not a stale one,
+so the `ps` check alone will not surface it.
+
+## Recovery path (canonical — client reconnect only)
+
+Do the steps in order. Stop as soon as a live **client-namespace** call succeeds.
+
+1. **Confirm the blast radius.** Call a cheap read tool on the failing namespace
+   (`gitea_whoami` or `gitea_list_profiles`). Then call the same tool on a
+   different MCP server (e.g. `context7`).
+   - Only the Gitea namespace fails → single-namespace transport close. Continue.
+   - Every server fails → restart the whole MCP client, not just one namespace.
+
+2. **Reconnect the namespace through the client, not the shell.** Use the IDE /
+   client MCP-reconnect action for that server entry (in Claude Code:
+   `/mcp` → reconnect the affected `gitea-*` server). Reconnecting forces the
+   client to spawn a fresh subprocess and re-open the pipe. This clears the
+   closed-client state that a bare `kill`/respawn from a terminal does **not**.
+
+3. **Do not "fix" it by importing the server or poking the process.** Reaching
+   for `python -c 'import gitea_mcp_server ...'`, raw JSON-RPC from a shell,
+   killing PIDs to force a respawn, or touching MCP config mtimes does **not**
+   restore the *client's* view of the namespace and violates the daemon-import
+   guard (#558, `docs/mcp-daemon-import-guard.md`). The only sanctioned repair
+   is a **client reconnect / relaunch**.
+
+4. **Verify through the same path the workflow will use.** After reconnect, call
+   the specific tool the blocked workflow needs — not just any tool — through
+   the target namespace. For a merge that means calling the merger-authorized
+   adoption/merge tool through `gitea-merger`. A green `gitea_whoami` on one
+   namespace does **not** prove another namespace or another tool is callable.
+   Record success with:
+
+   ```text
+   gitea_assess_mcp_namespace_health(..., probe_source="client_namespace")
+   ```
+
+5. **If reconnect does not clear it,** relaunch the client entirely, then repeat
+   step 4. If EOF persists after a full relaunch, the backing subprocess is
+   failing to start — inspect its stderr / launch config (command path, venv,
+   `*_MCP_CONFIG`, `*_MCP_PROFILE` env) rather than retrying the call. Still
+   do not use PID kill or config-touch as the primary recovery.
+
+## Diagnostics to capture when reporting EOF
+
+Include all of these so the failure is actionable and reproducible:
+
+- **Namespace name** that returned EOF (`gitea-author` / `gitea-reviewer` /
+  `gitea-merger` / `gitea-tools`).
+- **Tool** that was called and the **exact** error string.
+- **PID** of the backing process (if any) and whether it was still alive
+  (informational only — not a recovery action).
+- **Profile / env** for that namespace (execution profile, `*_MCP_PROFILE`,
+  worktree binding such as `GITEA_AUTHOR_WORKTREE`).
+- **Config path** the client launched the server from.
+- Result of the **cross-server control** call (did `context7` succeed?).
+
+## Offline spawn probe (non-authoritative)
+
+`test_mcp_conn.py` performs a full JSON-RPC handshake against a **fresh
+subprocess** (`initialize` → `initialized` → `tools/list` → `tools/call`) and
+classifies with `probe_source=offline_spawn`. That is useful for offline
+launch/registration debugging. It is **not** proof the IDE-managed namespace is
+healthy. See `docs/mcp-namespace-health.md`.
+
+## Do-not list during EOF recovery
+
+- Do **not** retry a blocked merge/adoption until the required tool is confirmed
+  callable through the merger-authorized **client** namespace (see #543).
+- Do **not** clean, reset, or rebind a **foreign** worktree to work around the
+  error.
+- Do **not** bypass the namespace with direct imports, raw API/curl, or
+  in-memory state restoration.
+- Do **not** kill MCP PIDs or touch config mtimes as a substitute for client
+  reconnect.
+
+## Related
+
+- #531 / #544 — stale-runtime detection (`ps`-based); sibling failure mode.
+- #558 / `docs/mcp-daemon-import-guard.md` — why shell imports are not a repair.
+- `docs/mcp-client-registration.md` — per-server registration contract.
+- `docs/mcp-namespace-health.md` — probe sources and mutation enforcement.

docs/mcp-namespace-health.md

@@ -0,0 +1,88 @@
+# MCP namespace health diagnostics (#543)
+
+Gitea MCP tools can be registered in the Python FastMCP server while the IDE's
+live MCP namespace is still unusable. The failure usually appears as
+`client is closing: EOF`, `transport closed`, or an empty response when calling
+a tool such as `gitea_whoami`.
+
+Do not treat static tool registration as proof that review or merge workflows
+can proceed. A reviewer or merger flow must have **client-namespace** evidence
+that the required tool is callable through the configured IDE MCP namespace.
+
+## Probe sources (do not confuse them)
+
+| Source | How obtained | Proves IDE namespace? |
+| --- | --- | --- |
+| `client_namespace` | Tool call through the IDE-managed MCP client | **Yes** |
+| `offline_spawn` | `test_mcp_conn.py` subprocess JSON-RPC handshake | **No** (offline only) |
+
+`gitea_assess_mcp_namespace_health` accepts `probe_source` and only sets
+`ide_namespace_proven=true` for `client_namespace` success. Offline spawn
+success never clears review/merge mutation gates.
+
+## Client-namespace health check (canonical)
+
+1. Through the IDE client, call a cheap tool on the target namespace
+   (`gitea_whoami` or `gitea_list_profiles`).
+2. Feed the live result into:
+
+```text
+gitea_assess_mcp_namespace_health(
+    namespace="gitea-merger",          # or reviewer / author / tools
+    registered_tools=[...],            # optional static list
+    probe_result={"success": true, "result": {...}},
+    probe_source="client_namespace",
+)
+```
+
+3. A healthy client-namespace assessment is recorded in the MCP session and
+   consulted by **live** `gitea_submit_pr_review` / `gitea_merge_pr` gates.
+4. If the probe fails with EOF, recover via **client reconnect only** — see
+   `docs/mcp-namespace-eof-recovery.md`. Do **not** kill PIDs or touch MCP
+   config mtimes as a recovery procedure.
+
+## Offline spawn probe (non-authoritative)
+
+```bash
+python3 test_mcp_conn.py --config ~/.gemini/config/mcp_config.json
+```
+
+This script spawns a **separate** server process from config, performs
+JSON-RPC `initialize` → `tools/list` → `tools/call`, and classifies the
+result with `probe_source=offline_spawn`. Use it for offline debugging of
+launch command / registration. It does **not** prove the IDE-managed
+namespace is healthy.
+
+By default the script checks:
+
+| Namespace | Required tool |
+| --- | --- |
+| `gitea-author` | `gitea_whoami` |
+| `gitea-reviewer` | `gitea_whoami` |
+| `gitea-merger` | `gitea_whoami` |
+| `gitea-tools` | `gitea_list_profiles` |
+
+## Recovery (canonical)
+
+When a namespace returns EOF, follow
+`docs/mcp-namespace-eof-recovery.md` in order:
+
+1. Confirm blast radius (Gitea namespace vs all MCP servers).
+2. **Reconnect the namespace through the client** (IDE reconnect / relaunch).
+3. Do not repair via shell imports, raw JSON-RPC, PID kills, or config mtime
+   touches — those do not restore the client's closed transport.
+4. Re-verify the **specific** required tool through the target namespace.
+5. Resume review/merge only after a successful `client_namespace` assessment.
+
+## Enforcement
+
+1. **State machine (read-only):** feed `blocks_merge_workflow` from a
+   `client_namespace` assessment into
+   `gitea_assess_review_merge_state_machine(live_namespace_broken=...)`.
+2. **Live mutations:** `gitea_submit_pr_review` and `gitea_merge_pr` call
+   `_live_namespace_health_gate` and fail closed when the session has a
+   recorded unhealthy or non-client probe for the required namespace
+   (`gitea-reviewer` for review, `gitea-merger` for merge).
+
+When blocked, repair the IDE namespace and re-record a healthy
+`client_namespace` assessment before retrying the mutation.

docs/reviewer-handoff-consistency.md

@@ -0,0 +1,35 @@
+# Reviewer Handoff Consistency
+
+Reviewer and final-review controller handoffs must not contradict themselves.
+A narrative that says a merge happened, a review was blocked, or a terminal
+mutation budget was consumed must match the mutation ledger fields in the same
+handoff.
+
+## What gets validated
+
+`reviewer_handoff_consistency.assess_reviewer_handoff_consistency()` checks:
+
+- merge claims appear under `Merge mutations` or `MCP/Gitea mutations`
+- terminal-mutation-budget claims name the exact prior mutation in the ledger
+- blocked review submission is not paired with "final decision marked"
+- reviewer lease acquisition includes a `Review decision`
+- blocked/rejected mutations include proof fields:
+  - tool called
+  - mutation attempted
+  - mutation rejected
+  - no server-side state changed
+
+`final_report_validator` applies this as `reviewer.handoff_consistency` on
+`review_pr` reports and fails closed.
+
+## Blocked review template
+
+When `gitea_submit_pr_review` fails closed, use
+`reviewer_handoff_consistency.render_blocked_review_handoff_template()` or the
+copy in
+[`skills/llm-project-workflow/templates/blocked-review-handoff.md`](../skills/llm-project-workflow/templates/blocked-review-handoff.md).
+
+## Related
+
+- #331 — file-mutation ledger alignment
+- #501 — contradictory narrative vs ledger detection

docs/two-comment-workflow.md

@@ -0,0 +1,123 @@
+# Two-comment workflow: Controller Handoff + Thread State Ledger
+
+After meaningful controller/workflow work, post **two separate Gitea comments**:
+
+1. **`[CONTROLLER HANDOFF]`** — detailed operational handoff for the next
+   LLM/controller session (proof-heavy; may be long).
+2. **`[THREAD STATE LEDGER]`** — short canonical truth readable in ~30 seconds.
+
+The ledger is the concise source of truth. The handoff is the detailed
+continuation artifact. This complements CTH (#505) and lifecycle state
+comments (#494/#495) without replacing them.
+
+## Controller Handoff template
+
+```markdown
+[CONTROLLER HANDOFF] PR #___ / Issue #___ — <short title>
+
+Purpose:
+This comment is the operational handoff for the next controller/LLM session.
+
+Identity/profile:
+- Active profile:
+- Authenticated identity:
+- Role:
+- Self-review / role-conflict proof:
+
+Target:
+- Repo:
+- Issue:
+- PR:
+- Branch:
+- Pinned head SHA:
+- Worktree:
+
+Work performed:
+- <step 1>
+- <step 2>
+
+Files touched or reviewed:
+- `<file>` — <why it matters>
+
+Validation:
+- `<command>` → <result>
+- Full suite: <result or not run + reason>
+
+Server-side mutation ledger:
+- <mutation 1, including tool/action/comment id if available>
+- Or: none — no server-side state changed
+
+Local-only changes:
+- <worktree created, files edited locally, etc.>
+- Or: none
+
+Blockers:
+- <none>
+- Or: <exact blocker, exact gate, exact reason>
+
+Controller prompt for next session:
+```markdown
+<ready-to-paste prompt>
+```
+```
+
+## Thread State Ledger template
+
+```markdown
+[THREAD STATE LEDGER] PR #___ / Issue #___ — <current state in one line>
+
+What is true now:
+- PR state:
+- Issue state:
+- Current head SHA:
+- Server-side decision state:
+- Local verdict/state:
+- Latest known validation:
+
+What changed:
+- <short summary since prior ledger>
+
+What is blocked:
+- Blocker classification: <see list below>
+
+Who/what acts next:
+- Next actor:
+- Required action:
+- Do not do:
+- Resume from:
+```
+
+### Blocker classifications
+
+- code blocker
+- test blocker
+- merge conflict
+- stale head
+- permission/capability blocker
+- environment/tooling blocker
+- process/rule blocker
+- queue/lease blocker
+- duplicate/canonicalization blocker
+- no blocker
+
+### Precise state language
+
+Prefer:
+
+- `APPROVE verdict prepared locally`
+- `APPROVED review posted to Gitea`
+- `REQUEST_CHANGES posted to Gitea`
+- `merge performed` / `merge not performed`
+- `lease acquired` / `lease attempt blocked`
+- `server-side state changed` / `no server-side state changed`
+
+Avoid ambiguous standalone claims (`approved`, `ready`, `merged`, `blocked`,
+`done`) without proof and server-side state separation.
+
+## Validation
+
+- `thread_state_ledger_validator.py` — comment and final-report checks
+- `gitea_create_issue_comment` — fail-closed gate on tagged comments
+- `assess_final_report_validator` — `shared.two_comment_workflow` rule
+
+Examples: [`examples/two-comment-workflow-examples.md`](examples/two-comment-workflow-examples.md)

docs/webui-deployment.md

@@ -0,0 +1,59 @@
+# Web UI deployment boundary (#435)
+
+The MCP Control Plane web UI is an **internal operator console**, not a
+customer-facing application. The MVP assumes local or trusted-network access
+only.
+
+## MVP deployment model
+
+- **Default bind:** `127.0.0.1:8765` (`WEBUI_HOST` / `WEBUI_PORT`)
+- **Authentication:** none in MVP — protection comes from network placement
+- **Mutations:** read-only routes; gated write actions remain disabled (#434)
+- **Secrets:** resolved server-side via `gitea_auth` / `GITEA_MCP_CONFIG`; never
+  embedded in HTML, JavaScript, or browser storage
+
+Do **not** expose the UI on the public internet without an access layer.
+
+## Beyond localhost
+
+If the UI must be reachable outside the operator laptop:
+
+1. Prefer **Cloudflare Access**, **Cloudflare WARP**, or an org **VPN** so only
+   authenticated staff reach the service.
+2. Bind to a specific interface only when necessary — never `0.0.0.0` / `::`
+   without understanding the exposure.
+3. Set explicit override env vars only after access controls are in place:
+   - `WEBUI_ALLOW_PUBLIC_BIND=1` — acknowledges all-interface bind (`0.0.0.0`, `::`)
+   - `WEBUI_ALLOW_REMOTE_BIND=1` — acknowledges a non-loopback host
+
+Startup **refuses** all-interface binds unless `WEBUI_ALLOW_PUBLIC_BIND=1`.
+Non-loopback binds log a warning unless `WEBUI_ALLOW_REMOTE_BIND=1`.
+
+## Environment variables
+
+| Variable | Default | Purpose |
+|----------|---------|---------|
+| `WEBUI_HOST` | `127.0.0.1` | Bind address |
+| `WEBUI_PORT` | `8765` | Listen port |
+| `WEBUI_REPO_ROOT` | repository root | Workflow/schema hash root for prompt library |
+| `WEBUI_PROJECT_REGISTRY` | packaged JSON | Project registry file path |
+| `GITEA_MCP_CONFIG` | unset | Server-side MCP profile config path (optional) |
+| `GITEA_MCP_PROFILE` | unset | Active MCP profile name (optional) |
+| `WEBUI_ALLOW_PUBLIC_BIND` | unset | Acknowledge `0.0.0.0` / `::` bind |
+| `WEBUI_ALLOW_REMOTE_BIND` | unset | Acknowledge non-loopback bind |
+
+Gitea credentials (`GITEA_TOKEN_*`, `.env.*`, keychain refs) are read only on
+the server when a page needs live Gitea data (e.g. `/queue`). They are not
+shipped to the browser.
+
+## Health / deployment metadata
+
+`GET /health` includes a `deployment` object with bind disposition, runtime
+assumption paths, and the client-secret policy. Use it to verify an instance is
+configured for internal-only operation.
+
+## Non-goals (MVP)
+
+- Full SSO or session login in the UI
+- Hosting on the public internet without Access/VPN/WARP
+- Embedding Gitea tokens in the frontend bundle

docs/webui-local-dev.md

@@ -29,6 +29,13 @@ Optional environment variables:
 |----------|---------|---------|
 | `WEBUI_HOST` | `127.0.0.1` | Bind address (keep local for MVP) |
 | `WEBUI_PORT` | `8765` | Listen port |
+| `WEBUI_REPO_ROOT` | repository root | Prompt library workflow hash root |
+| `WEBUI_PROJECT_REGISTRY` | packaged JSON | Project registry path |
+| `GITEA_MCP_CONFIG` | unset | Server-side MCP profile config (never sent to browser) |
+| `GITEA_MCP_PROFILE` | unset | Active MCP profile name (server-side only) |
+
+See [webui-deployment.md](webui-deployment.md) for internal-only serving,
+Cloudflare Access/WARP/VPN guidance, and unsafe bind overrides (#435).
 
 ## Routes (MVP)
 
@@ -45,13 +52,27 @@ Optional environment variables:
 | `/api/prompts` | JSON prompt export with workflow hashes |
 | `/runtime` | MCP runtime health and stale detection (#430) |
 | `/api/runtime` | JSON runtime health export |
-| `/audit` | Stub — report audit paste (#431) |
-| `/worktrees` | Stub — hygiene dashboard (#432) |
+| `/audit` | Report audit paste + validator preview (#431) |
+| `/api/audit` | JSON validator preview (POST `report_text`, optional `task_kind`) |
+| `/worktrees` | Worktree hygiene dashboard (#432) |
+| `/api/worktrees` | JSON worktree scan with classifications and anomalies |
+| `/actions` | Gated write-action registry — all disabled in MVP (#434) |
+| `/api/actions` | JSON action registry with capability metadata |
+| `/api/actions/{id}/preview` | Mutation ledger preview (GET, read-only) |
 | `/leases` | Lease and collision visibility (#433) |
 | `/api/leases` | JSON lease/collision export |
 
-All routes are GET-only. POST/PUT/PATCH/DELETE return `405` with
-`read-only-mvp`.
+Most routes are GET-only. POST/PUT/PATCH/DELETE return `405` with
+`read-only-mvp`, except `/audit` and `/api/audit` which accept POST for
+local validator preview only (no Gitea mutations, no server-side storage).
+
+## Report audit (#431)
+
+Paste an LLM final report at `/audit` or POST JSON to `/api/audit`. The UI
+reuses `final_report_validator` and review schema checks to surface missing
+proof fields, wrong validation vocabulary, mutation contradictions, and a
+suggested next prompt or issue-comment draft. Task kind can be auto-detected
+or selected explicitly.
 
 ## Project registry (#427)
 
@@ -84,6 +105,84 @@ credentials. The UI surfaces pagination proof (returned count, pages fetched,
 If credentials are missing or the fetch fails, the page shows an explicit error
 instead of an empty queue (fail closed).
 
+## Gated actions (#434)
+
+`/actions` registers future write actions (claim, comment, review, merge,
+delete branch, create PR/issue). Each entry declares the MCP tool, required
+permission, and profile role from `task_capability_map.py` — aligned with
+`gitea_resolve_task_capability`. Buttons are disabled; previews always render
+a mutation ledger. Direct `attempt_action` calls fail closed without invoking
+MCP tools.
+
+## Worktree hygiene (#432)
+
+`/worktrees` scans local `branches/` directories and registered git worktrees.
+Each entry is classified (`active-pr`, `active-issue`, `dirty`, `stale-clean`,
+`detached-review`, `unsafe-unknown`, `orphan`). Missing preserved worktrees
+referenced by the issue lock file are flagged as anomalies (#404). The page
+includes a copy/paste canonical cleanup prompt only — no deletion actions.
+
+Override scan root with `WEBUI_REPO_ROOT` (defaults to repository root).
+
+## Lease visibility (#433)
+
+`/leases` surfaces read-only lease and collision state: local issue lock file,
+in-progress claim inventory (#268), reviewer PR lease comments when present
+(`<!-- mcp-review-lease:v1 -->`, #407), duplicate open PRs per issue (#400),
+and duplicate local branches per issue. Links to collision-history backend
+issues (#267, #268, #400, #407) are included. No lease acquire/release from UI.
+
+## Runtime health (#430)
+
+`/runtime` surfaces read-only MCP/runtime diagnostics for the default registry
+project: active profile and role kind, authenticated identity (when credentials
+are available), config model/mode, local vs remote `master` SHA sync, shell
+health, workflow/schema SHA-256 hashes, and stale-runtime warnings when the
+checkout is behind merged safety-gate changes. Restart guidance links to #420;
+no tokens or MCP restart actions are exposed.
+
+## Deployment boundary (#435)
+
+MVP serves on loopback by default. Binding `0.0.0.0` or `::` is **refused**
+unless `WEBUI_ALLOW_PUBLIC_BIND=1`. Non-loopback hosts log a warning unless
+`WEBUI_ALLOW_REMOTE_BIND=1`. `GET /health` exposes `deployment` metadata.
+
+## Tests
+
+```bash
+pytest tests/test_webui_skeleton.py tests/test_webui_project_registry.py tests/test_webui_prompt_library.py tests/test_webui_queue_dashboard.py tests/test_webui_gated_actions.py -q
+pytest tests/test_webui_skeleton.py tests/test_webui_project_registry.py tests/test_webui_prompt_library.py tests/test_webui_queue_dashboard.py tests/test_webui_audit.py tests/test_webui_worktree_hygiene.py -q
+pytest tests/test_webui_skeleton.py tests/test_webui_project_registry.py tests/test_webui_prompt_library.py tests/test_webui_queue_dashboard.py tests/test_webui_lease_visibility.py tests/test_webui_runtime_health.py -q
+
+pytest tests/test_webui_skeleton.py tests/test_webui_project_registry.py tests/test_webui_prompt_library.py tests/test_webui_queue_dashboard.py tests/test_webui_deployment_boundary.py -q
+
+## Tests (#436)
+
+Run the full hermetic web UI suite (all `test_webui_*.py` modules):
+
+```bash
+./scripts/test-webui
+```
+
+CI / Jenkins multibranch can call the path-filtered gate (runs only when the
+diff touches `webui/`, `tests/test_webui_*`, or web UI docs/scripts):
+
+```bash
+./scripts/ci-webui-check
+WEBUI_CI_FORCE=1 ./scripts/ci-webui-check   # always run
+```
+
+`scripts/test-webui` sets `WEBUI_TEST_OFFLINE=1` by default. In that mode the
+queue, lease, and runtime routes use empty offline snapshots instead of Gitea
+credentials, so CI can run without MCP daemon credential access. Set
+`WEBUI_TEST_OFFLINE=0` only when deliberately validating live fetch behavior.
+
+Or invoke unittest directly:
+
+```bash
+python3 -m unittest discover -s tests -p 'test_webui_*.py' -q
+```
+
 ## Lease visibility (#433)
 
 `/leases` surfaces read-only lease and collision state: local issue lock file,
@@ -104,5 +203,6 @@ no tokens or MCP restart actions are exposed.
 ## Tests
 
 ```bash
+pytest tests/test_webui_skeleton.py tests/test_webui_project_registry.py tests/test_webui_prompt_library.py tests/test_webui_queue_dashboard.py tests/test_webui_audit.py tests/test_webui_worktree_hygiene.py -q
 pytest tests/test_webui_skeleton.py tests/test_webui_project_registry.py tests/test_webui_prompt_library.py tests/test_webui_queue_dashboard.py tests/test_webui_lease_visibility.py tests/test_webui_runtime_health.py -q
-```
+```

docs/wiki/Identity-and-Profiles.md

@@ -16,12 +16,21 @@ bind an authenticated Gitea identity to an allowed operation set.
 - **Allowed:** branch create/push, PR create, issue comment/create/close, repo commit, read.
 - **Forbidden:** PR approve, merge, request_changes.
 
-### Reviewer / merger
+### Reviewer
 
 - **Profile:** `prgs-reviewer`
 - **Typical identity:** `sysadmin`
-- **Allowed:** PR review/approve/merge/request_changes, issue comment, read.
-- **Forbidden:** branch push, PR create, repo commit.
+- **Allowed:** PR review/approve/request_changes, issue comment, read.
+- **Forbidden:** branch push, PR create, repo commit, PR merge.
+
+Review and merge are separate workflow roles. A reviewer approval is not merge authorization.
+
+### Merger
+
+- **Profile:** `prgs-merger`
+- **Typical identity:** `sysadmin`
+- **Allowed:** PR merge, issue comment, read.
+- **Forbidden:** branch push, PR create, repo commit, PR approve, PR review, PR request_changes.
 
 ## Configuration
 

docs/wiki/Safety-and-Gates.md

@@ -15,5 +15,7 @@
 5. **Explicit merge confirmation** — `gitea_merge_pr` requires `confirmation="MERGE PR <n>"`.
 6. **No self-review / self-merge** — Authenticated user must differ from PR author for approve/merge.
 7. **Review decision lock** — Live review mutations require validation-phase dry-run and `gitea_mark_final_review_decision`.
-8. **Redaction** — Tokens, passwords, and keychain material never appear in tool output.
-9. **Wiki publication (#224)** — `docs/wiki/` and the sync helper are prerequisites only. Closing a wiki issue requires live Gitea Wiki proof on the repo Wiki tab. See [Runbooks](Runbooks.md#wiki-publication-readiness-gate-224).
+8. **Terminal review hard-stop (#332)** — After a terminal live review mutation, only same-PR merge after `approve` may continue. Durable locks (#559) must not be deleted by hand.
+9. **Stale decision-lock cleanup (#594)** — `gitea_cleanup_stale_review_decision_lock` may clear a durable #332 lock **only** when the last terminal mutation's PR is live-state **merged or closed**, identity/profile gates pass, and apply uses a reviewer-capable profile. Open/ambiguous locks stay fail-closed. Successful cleanup records a durable audit trail.
+10. **Redaction** — Tokens, passwords, and keychain material never appear in tool output.
+11. **Wiki publication (#224)** — `docs/wiki/` and the sync helper are prerequisites only. Closing a wiki issue requires live Gitea Wiki proof on the repo Wiki tab. See [Runbooks](Runbooks.md#wiki-publication-readiness-gate-224).

docs/workflow-skill-mount.md

@@ -0,0 +1,68 @@
+# Workflow skill mount across runtimes (#551)
+
+## Problem
+
+Controller prompts require **`gitea-workflow`**, but:
+
+- Claude may load `~/.claude/skills/gitea-workflow`
+- Codex often has **no** `~/.codex/skills/gitea-workflow`
+- The portable package in-repo is `skills/llm-project-workflow`
+- `mcp_list_project_skills` historically listed operational guides only, not
+  the workflow router
+
+Sessions then either **block** incorrectly or **proceed without** the workflow
+wall.
+
+## Canonical names (must resolve to the same skill)
+
+| Name | Use |
+|------|-----|
+| `gitea-workflow` | **Primary** controller / Codex skill name |
+| `llm-project-workflow` | Portable in-repo package name |
+| `git-pr-workflows` | Legacy alias |
+
+Source of truth: `skills/llm-project-workflow/SKILL.md`  
+In-repo alias stub: `skills/gitea-workflow/SKILL.md`
+
+## Codex install
+
+From a `branches/` worktree (or any clone of the repo):
+
+```bash
+./scripts/install-codex-workflow-skill.sh
+# optional:
+./scripts/install-codex-workflow-skill.sh --dry-run
+./scripts/install-codex-workflow-skill.sh --skills-dir "$HOME/.codex/skills"
+```
+
+This symlinks the portable package under all three names. **Restart Codex**
+after install.
+
+## MCP discovery
+
+- `mcp_list_project_skills` includes `gitea-workflow`, `llm-project-workflow`,
+  and `git-pr-workflows`.
+- `mcp_get_skill_guide("<name>")` returns the same router steps for each.
+- `mcp_check_workflow_skill_preflight` proves the in-repo skill file exists and
+  reports Codex mount status.
+
+## Preflight rule
+
+Before any git or Gitea mutation:
+
+1. Call `mcp_check_workflow_skill_preflight`.
+2. If `blocked` / `workflow_skill_ready` is false → **BLOCKED + DIAGNOSE**; do
+   not mutate.
+3. Load the skill by **any** canonical name and follow the router.
+
+Missing Codex mount alone does not block if the in-repo skill is present and
+loaded via MCP/docs; operators should still install the Codex symlink so
+prompt names resolve natively.
+
+## Controller prompts
+
+Prefer:
+
+> Invoke skill `gitea-workflow` (alias of `llm-project-workflow`).
+
+Do not require a name that is only available on one runtime.

final_report_validator.py

@@ -11,8 +11,12 @@ import inspect
 import re
 from typing import Any, Callable
 
+import branch_cleanup_guard
 import issue_acceptance_gate
 import issue_lock_provenance
+import merger_lease_adoption
+import reviewer_handoff_consistency
+import thread_state_ledger_validator
 from mcp_native_cleanup_proof import assess_mcp_native_cleanup_proof
 from post_merge_cleanup_proof import assess_post_merge_cleanup_proof
 from review_proofs import (
@@ -29,31 +33,40 @@ from validation_status_vocabulary import assess_validation_status_vocabulary
 
 FINAL_REPORT_TASK_KINDS = frozenset({
     "review_pr",
+    "merge_pr",
     "reconcile_already_landed",
     "author_issue",
     "work_issue",
     "issue_filing",
     "issue_selection",
     "inventory",
+    "controller_close",
 })
 
 _TASK_KIND_ALIASES = {
     "review": "review_pr",
     "review-merge-pr": "review_pr",
+    "merge": "merge_pr",
+    "merge_pr": "merge_pr",
     "reconcile-landed-pr": "reconcile_already_landed",
     "reconcile_already_landed": "reconcile_already_landed",
     "work-issue": "work_issue",
     "create_issue": "issue_filing",
+    "close_issue": "controller_close",
+    "close-issue": "controller_close",
+    "controller-close": "controller_close",
 }
 
 _HANDOFF_ROLE_BY_TASK = {
     "review_pr": "review",
+    "merge_pr": "merger",
     "reconcile_already_landed": None,
     "author_issue": "author",
     "work_issue": "author",
     "issue_filing": "issue_filing",
     "issue_selection": None,
     "inventory": "inventory",
+    "controller_close": None,
 }
 
 _LEGACY_WORKSPACE_MUTATIONS_RE = re.compile(
@@ -195,6 +208,23 @@ _PAGINATION_PROOF_RE = re.compile(
     re.IGNORECASE,
 )
 _GIT_FETCH_RE = re.compile(r"\bgit\s+fetch\b", re.IGNORECASE)
+_CANONICAL_VALIDATION_REJECTED_RE = re.compile(
+    r"canonical comment validation failed|"
+    r"canonical_comment_validation|"
+    r'"allowed"\s*:\s*false',
+    re.IGNORECASE,
+)
+_COMMENT_POSTED_CLAIM_RE = re.compile(
+    r"(?:issue comments posted\s*:\s+(?!none\b)\S|"
+    r"pr comments posted\s*:\s+(?!none\b)\S|"
+    r"comment_id\s*[:=]\s*\d+|"
+    r"gitea comment (?:was )?posted|"
+    r"posted (?:issue|pr|canonical) (?:state )?comment|"
+    r"comment posted successfully|"
+    r"mcp/gitea mutations\s*:\s*[^;\n]*comment posted|"
+    r"reconciliation mutations\s*:\s*[^;\n]*comment posted)",
+    re.IGNORECASE,
+)
 _READONLY_DIAG_RE = re.compile(
     r"read[- ]only diagnostics\s*:\s*(.+)$",
     re.IGNORECASE | re.MULTILINE,
@@ -381,6 +411,43 @@ def _rule_shared_email_disclosure(report_text: str) -> list[dict[str, str]]:
     )
 
 
+def _rule_shared_canonical_comment_post_claim(
+    report_text: str,
+    *,
+    action_log: list[dict] | None = None,
+) -> list[dict[str, str]]:
+    """#496: reports must not claim comment posted when validator rejected."""
+    text = report_text or ""
+    rejected_in_report = bool(_CANONICAL_VALIDATION_REJECTED_RE.search(text))
+    rejected_in_log = False
+    if action_log:
+        for entry in action_log:
+            validation = entry.get("canonical_comment_validation") or {}
+            if validation.get("allowed") is False:
+                rejected_in_log = True
+                break
+            result = entry.get("result") or {}
+            nested = result.get("canonical_comment_validation") or {}
+            if nested.get("allowed") is False:
+                rejected_in_log = True
+                break
+    if not (rejected_in_report or rejected_in_log):
+        return []
+    if not _COMMENT_POSTED_CLAIM_RE.search(text):
+        return []
+    return [
+        validator_finding(
+            "shared.canonical_comment_post_claim",
+            "block",
+            "MCP/Gitea mutations",
+            "report claims a Gitea comment was posted while canonical comment "
+            "validation rejected the workflow comment",
+            "do not claim comment posted when validator fail-closed; repair "
+            "the canonical comment body and retry posting",
+        )
+    ]
+
+
 def _rule_reviewer_legacy_workspace_mutations(
     report_text: str,
     *,
@@ -598,6 +665,27 @@ def _rule_reviewer_stale_head_proof(report_text: str) -> list[dict[str, str]]:
     )
 
 
+def _rule_conflict_fix_classification_proof(report_text: str) -> list[dict[str, str]]:
+    from conflict_fix_classification import (
+        assess_conflict_fix_classification_final_report,
+    )
+
+    text = report_text or ""
+    result = assess_conflict_fix_classification_final_report(text)
+    if result.get("proven"):
+        return []
+    return _findings_from_reasons(
+        "author.conflict_fix_classification_proof",
+        result.get("reasons") or [],
+        field="Conflict-fix classification",
+        severity="block",
+        safe_next_action=(
+            "call gitea_assess_conflict_fix_classification, state the live head "
+            "SHA, and state the classification before creating a conflict-fix worktree"
+        ),
+    )
+
+
 def _rule_conflict_fix_push_proof(report_text: str) -> list[dict[str, str]]:
     from pr_work_lease import assess_conflict_fix_final_report
 
@@ -767,6 +855,27 @@ def _rule_reviewer_premerge_baseline_proof(report_text: str) -> list[dict[str, s
     )
 
 
+def _rule_reviewer_post_merge_validation(report_text: str) -> list[dict[str, str]]:
+    """Block active approval on an already-merged/closed PR, and post-merge moot
+    validation claimed without merged-state + merge-commit proof (#529)."""
+    from post_merge_validation import assess_post_merge_validation
+
+    result = assess_post_merge_validation(report_text)
+    if not result.get("block"):
+        return []
+    return _findings_from_reasons(
+        "reviewer.post_merge_validation",
+        result.get("reasons") or [],
+        field="Validation status",
+        severity="block",
+        safe_next_action=result.get("safe_next_action")
+        or (
+            "record post-merge moot validation instead of an active approval; "
+            "cite PR state merged/closed and the merge commit SHA"
+        ),
+    )
+
+
 def _rule_reviewer_validation_status_vocabulary(
     report_text: str,
     *,
@@ -1111,6 +1220,25 @@ def _rule_reviewer_validation_structured(
     )
 
 
+def _rule_reviewer_handoff_consistency(report_text: str) -> list[dict[str, str]]:
+    result = reviewer_handoff_consistency.assess_reviewer_handoff_consistency(
+        report_text
+    )
+    if result.get("proven"):
+        return []
+    return _findings_from_reasons(
+        "reviewer.handoff_consistency",
+        result.get("reasons") or [],
+        field="Review mutations",
+        severity="block",
+        safe_next_action=(
+            "rewrite reviewer handoff so narrative claims match the mutation "
+            "ledger; use the blocked-review handoff template when submission "
+            "was rejected"
+        ),
+    )
+
+
 def _rule_reviewer_mutation_ledger(
     report_text: str,
     *,
@@ -1162,6 +1290,24 @@ def _rule_shared_manual_lock_pr_override(report_text: str) -> list[dict[str, str
     )
 
 
+def _rule_shared_manual_lease_proof_handoff(report_text: str) -> list[dict[str, str]]:
+    """Block merge/review handoffs that claim unsafe lease seeding (#535)."""
+    result = merger_lease_adoption.assess_manual_lease_proof_handoff(report_text)
+    if result.get("proven"):
+        return []
+    return _findings_from_reasons(
+        "shared.manual_lease_proof_handoff",
+        result.get("reasons") or [],
+        field="Merge mutations",
+        severity="block",
+        safe_next_action=(
+            "use gitea_adopt_merger_pr_lease or gitea_acquire_reviewer_pr_lease; "
+            "cite lease_proof_source / adoption_comment_id; never claim manual "
+            "seeded/injected lease proof"
+        ),
+    )
+
+
 def _rule_shared_issue_acceptance_gate(report_text: str) -> list[dict[str, str]]:
     result = issue_acceptance_gate.validate_final_report_issue_acceptance(report_text)
     if not result.get("applicable") or result.get("valid"):
@@ -1194,6 +1340,17 @@ def _rule_shared_author_reviewer_same_run(report_text: str) -> list[dict[str, st
     )
 
 
+def _rule_shared_raw_branch_delete_bypass(report_text: str) -> list[dict[str, str]]:
+    result = branch_cleanup_guard.assess_raw_branch_delete_report(report_text)
+    if not result["block"]:
+        return []
+    return _findings_from_reasons(
+        "shared.raw_branch_delete_bypass",
+        result["reasons"],
+        field="Cleanup mutations",
+        severity="block",
+        safe_next_action=result["safe_next_action"],
+    )
 def _rule_reviewer_workflow_load_boundary(report_text: str) -> list[dict[str, str]]:
     """#403: require structured workflow-load helper result, not file-view narrative."""
     if not report_text.strip():
@@ -1277,6 +1434,29 @@ def _rule_reviewer_review_mutation(
     )
 
 
+def _rule_shared_two_comment_workflow(report_text: str) -> list[dict[str, str]]:
+    """#507: tagged Controller Handoff must pair with Thread State Ledger."""
+    return thread_state_ledger_validator.findings_for_final_report(report_text)
+
+
+def _rule_shared_canonical_state_update(report_text: str) -> list[dict[str, str]]:
+    from canonical_state_comments import validate_final_report_state_update
+
+    result = validate_final_report_state_update(report_text)
+    if not result.get("applicable") or result.get("valid"):
+        return []
+    return [
+        validator_finding(
+            "shared.canonical_state_update",
+            "block",
+            "Canonical state update",
+            reason,
+            "include a canonical state block with STATE, WHO_IS_NEXT, NEXT_ACTION, and NEXT_PROMPT",
+        )
+        for reason in (result.get("reasons") or ["invalid canonical state update"])
+    ]
+
+
 def _rule_reviewer_mutation_capability_proof(report_text: str) -> list[dict[str, str]]:
     from reviewer_mutation_capability_proof import assess_mutation_capability_proof
 
@@ -1324,18 +1504,30 @@ def _rule_shared_mcp_native_cleanup_proof(report_text: str) -> list[dict[str, st
 _SHARED_ISSUE_LOCK_RULES = (
     _rule_shared_issue_lock_external_state,
     _rule_shared_manual_lock_pr_override,
+    _rule_shared_manual_lease_proof_handoff,
     _rule_shared_author_reviewer_same_run,
+    _rule_shared_raw_branch_delete_bypass,
+    _rule_shared_canonical_state_update,
 )
 
+_SHARED_TWO_COMMENT_RULES = (
+    _rule_shared_two_comment_workflow,
+)
 _SHARED_CLEANUP_PROOF_RULES = (
     _rule_shared_mcp_native_cleanup_proof,
 )
 
+_SHARED_CANONICAL_COMMENT_RULES = (
+    _rule_shared_canonical_comment_post_claim,
+)
+
 _RULES_BY_TASK: dict[str, list[Callable[..., list[dict[str, str]]]]] = {
     "review_pr": [
         _rule_shared_controller_handoff,
         _rule_shared_state_handoff_next_action,
         _rule_shared_email_disclosure,
+        *_SHARED_TWO_COMMENT_RULES,
+        *_SHARED_CANONICAL_COMMENT_RULES,
         *_SHARED_ISSUE_LOCK_RULES,
         _rule_reviewer_legacy_workspace_mutations,
         _rule_reviewer_vague_mutations_none,
@@ -1348,12 +1540,14 @@ _RULES_BY_TASK: dict[str, list[Callable[..., list[dict[str, str]]]]] = {
         _rule_reviewer_linked_issue,
         _rule_reviewer_baseline_on_failure,
         _rule_reviewer_premerge_baseline_proof,
+        _rule_reviewer_post_merge_validation,
         _rule_reviewer_validation_status_vocabulary,
         _rule_reviewer_main_checkout_baseline,
         _rule_reviewer_main_checkout_path,
         _rule_reviewer_already_landed_eligible,
         _rule_reviewer_already_landed_state,
         _rule_reviewer_target_branch_freshness,
+        _rule_reviewer_handoff_consistency,
         _rule_reviewer_workflow_load_boundary,
         _rule_reviewer_mutation_ledger,
         _rule_reviewer_review_mutation,
@@ -1362,10 +1556,23 @@ _RULES_BY_TASK: dict[str, list[Callable[..., list[dict[str, str]]]]] = {
         *_SHARED_CLEANUP_PROOF_RULES,
         _rule_reviewer_stale_head_proof,
     ],
+    "merge_pr": [
+        _rule_shared_controller_handoff,
+        _rule_shared_email_disclosure,
+        *_SHARED_ISSUE_LOCK_RULES,
+        _rule_reviewer_legacy_workspace_mutations,
+        _rule_reviewer_vague_mutations_none,
+        _rule_reviewer_mutation_categories,
+        _rule_reviewer_git_fetch_readonly,
+        _rule_reviewer_linked_issue,
+        _rule_reviewer_stale_head_proof,
+    ],
     "reconcile_already_landed": [
         _rule_reconcile_controller_handoff,
         _rule_shared_state_handoff_next_action,
         _rule_shared_email_disclosure,
+        *_SHARED_TWO_COMMENT_RULES,
+        *_SHARED_CANONICAL_COMMENT_RULES,
         *_SHARED_ISSUE_LOCK_RULES,
         *_SHARED_CLEANUP_PROOF_RULES,
         _rule_reconcile_stale_author_fields,
@@ -1383,6 +1590,8 @@ _RULES_BY_TASK: dict[str, list[Callable[..., list[dict[str, str]]]]] = {
         _rule_shared_controller_handoff,
         _rule_shared_state_handoff_next_action,
         _rule_shared_email_disclosure,
+        *_SHARED_TWO_COMMENT_RULES,
+        *_SHARED_CANONICAL_COMMENT_RULES,
         *_SHARED_ISSUE_LOCK_RULES,
         _rule_reviewer_vague_mutations_none,
     ],
@@ -1390,9 +1599,12 @@ _RULES_BY_TASK: dict[str, list[Callable[..., list[dict[str, str]]]]] = {
         _rule_shared_controller_handoff,
         _rule_shared_state_handoff_next_action,
         _rule_shared_email_disclosure,
+        *_SHARED_TWO_COMMENT_RULES,
+        *_SHARED_CANONICAL_COMMENT_RULES,
         *_SHARED_ISSUE_LOCK_RULES,
         _rule_shared_issue_acceptance_gate,
         _rule_reviewer_vague_mutations_none,
+        _rule_conflict_fix_classification_proof,
         _rule_conflict_fix_push_proof,
         _rule_worktree_cleanup_audit_proof,
     ],
@@ -1400,12 +1612,16 @@ _RULES_BY_TASK: dict[str, list[Callable[..., list[dict[str, str]]]]] = {
         _rule_shared_controller_handoff,
         _rule_shared_state_handoff_next_action,
         _rule_shared_email_disclosure,
+        *_SHARED_TWO_COMMENT_RULES,
+        *_SHARED_CANONICAL_COMMENT_RULES,
         *_SHARED_ISSUE_LOCK_RULES,
     ],
     "inventory": [
         _rule_shared_controller_handoff,
         _rule_shared_state_handoff_next_action,
         _rule_shared_email_disclosure,
+        *_SHARED_TWO_COMMENT_RULES,
+        *_SHARED_CANONICAL_COMMENT_RULES,
         *_SHARED_ISSUE_LOCK_RULES,
         _rule_reconcile_pagination_proof,
     ],
@@ -1413,8 +1629,17 @@ _RULES_BY_TASK: dict[str, list[Callable[..., list[dict[str, str]]]]] = {
         _rule_shared_controller_handoff,
         _rule_shared_state_handoff_next_action,
         _rule_shared_email_disclosure,
+        *_SHARED_TWO_COMMENT_RULES,
+        *_SHARED_CANONICAL_COMMENT_RULES,
         *_SHARED_ISSUE_LOCK_RULES,
     ],
+    # Controller issue closure (#529): a closure report must not bury an
+    # unproven non-zero suite exit as an "expected pre-existing failure".
+    # Kept intentionally narrow so a closure pre-check does not demand the
+    # full reviewer/author handoff schema.
+    "controller_close": [
+        _rule_reviewer_premerge_baseline_proof,
+    ],
 }
 
 

gitea-mcp.v2-contexts.example.json

@@ -52,8 +52,19 @@
       "execution_profile": "example-reviewer",
       "audit_label": "example-reviewer",
       "auth": { "type": "keychain", "id": "example-gitea-reviewer-token" },
-      "allowed_operations": ["read", "review", "comment", "issue.comment", "approve", "request_changes", "merge"],
-      "forbidden_operations": ["branch", "commit", "push", "open_pr"]
+      "allowed_operations": ["read", "review", "comment", "issue.comment", "approve", "request_changes"],
+      "forbidden_operations": ["branch", "commit", "push", "open_pr", "merge"]
+    },
+    "example-merger": {
+      "enabled": true,
+      "context": "example-context",
+      "role": "merger",
+      "username": "reviewer-user",
+      "execution_profile": "example-merger",
+      "audit_label": "example-merger",
+      "auth": { "type": "keychain", "id": "example-gitea-reviewer-token" },
+      "allowed_operations": ["read", "comment", "issue.comment", "merge"],
+      "forbidden_operations": ["branch", "commit", "push", "open_pr", "approve", "review", "request_changes"]
     }
   },
   "projects": {
@@ -63,7 +74,8 @@
       "default_owner": "Example-Org",
       "default_repo": "Example-Repo",
       "default_author_profile": "example-author",
-      "default_reviewer_profile": "example-reviewer"
+      "default_reviewer_profile": "example-reviewer",
+      "default_merger_profile": "example-merger"
     }
   },
   "rules": {

gitea_auth.py

@@ -104,6 +104,10 @@ def get_credentials(host):
 
     # 3. Optional fallback to macOS Keychain via git credential fill
     if not user and not password and os.environ.get("GITEA_USE_KEYCHAIN") == "1":
+        # #558: block raw keychain dumps outside the sanctioned MCP daemon.
+        import mcp_daemon_guard
+
+        mcp_daemon_guard.assert_keychain_access_allowed()
         cmd_parts = ["git", "creden" + "tial", "fi" + "ll"]
         try:
             p = subprocess.Popen(
@@ -116,6 +120,8 @@ def get_credentials(host):
                     user = line.split("=", 1)[1]
                 elif line.startswith("password="):
                     password = line.split("=", 1)[1]
+        except mcp_daemon_guard.UnsanctionedRuntimeError:
+            raise
         except Exception:
             pass
 
@@ -124,6 +130,11 @@ def get_credentials(host):
 
 def get_auth_header(host):
     """Return an ``Authorization`` header value for *host*."""
+    # #558: resolving credentials for API mutation must not happen via ad-hoc
+    # direct imports that bypass the MCP daemon preflight wall.
+    import mcp_daemon_guard
+
+    mcp_daemon_guard.assert_sanctioned_mutation_runtime("get_auth_header")
     host_key = host.lower().strip()
 
     # 1. Try Token-based auth from dynamic configs

issue_content_gate.py

@@ -0,0 +1,180 @@
+"""Pre-create issue content gate (#582).
+
+Blocks issue creation when the title/body is a *vague reference* to
+out-of-band content the LLM cannot prove it has ("the drafted issue",
+"the prepared issue", "the issue we discussed", "the previous draft")
+with no durable source pointer.
+
+The rule from #582: an LLM must not fabricate an issue from stale chat
+memory. When the requested issue content is a vague reference and no
+durable source pointer (existing issue/PR/comment, checked-in file, URL,
+or scratchpad path) is present, the gate fails closed and the caller must
+return BLOCKED + DIAGNOSE naming the exact vague/missing fields.
+
+This gate intentionally does NOT require a non-empty body: title-only
+issue creation remains allowed for callers that explicitly want it. It
+only blocks content that is a placeholder reference to something the
+current context does not contain.
+"""
+
+from __future__ import annotations
+
+import re
+import unicodedata
+
+# Vague reference phrases that point at out-of-band draft content. Stored
+# normalized (lowercase, punctuation-stripped, whitespace-collapsed) so they
+# can be matched against normalized field text.
+VAGUE_REFERENCE_PHRASES: tuple[str, ...] = (
+    "the drafted issue",
+    "drafted issue",
+    "the prepared issue",
+    "prepared issue",
+    "the issue we discussed",
+    "the issue we talked about",
+    "the one we discussed",
+    "the previous draft",
+    "previous draft",
+    "the draft above",
+    "the issue above",
+    "as discussed",
+    "as we discussed",
+    "as previously discussed",
+    "per our discussion",
+    "per our conversation",
+    "per our chat",
+    "see above",
+    "same as before",
+    "the issue from earlier",
+    "the issue i drafted",
+    "the issue you drafted",
+)
+
+# A field that only restates a vague phrase (optionally with a leading verb
+# such as "create"/"add"/"open"/"file") is still a vague reference.
+_LEADING_VERBS = ("create", "add", "open", "file", "make", "please", "the")
+
+# Durable source pointers: if any of these appears, the content points at a
+# retrievable source of truth and is NOT treated as a fabricated reference.
+_DURABLE_SOURCE_REGEXES: tuple[re.Pattern[str], ...] = (
+    re.compile(r"#\d+"),                                   # #402
+    re.compile(r"\b(?:issue|pull|pr)\s+#?\d+", re.I),      # issue 402 / PR #17
+    re.compile(r"\bcomment\s+#?\d+", re.I),                # comment 8155
+    re.compile(r"https?://\S+", re.I),                     # URL
+    re.compile(                                            # checked-in file
+        r"[\w./-]+\.(?:py|md|json|txt|sh|ya?ml|toml|cfg|ini|rst)\b", re.I
+    ),
+    re.compile(r"\bscratchpad\b", re.I),                   # scratchpad path
+    re.compile(r"(?:^|\s)/[\w./-]+"),                      # absolute path
+)
+
+
+def normalize_text(text: str) -> str:
+    """Lowercase, punctuation-stripped, whitespace-collapsed text."""
+    norm = unicodedata.normalize("NFKC", (text or "").strip().lower())
+    norm = re.sub(r"[^\w\s]", " ", norm)
+    norm = re.sub(r"\s+", " ", norm).strip()
+    return norm
+
+
+def has_durable_source_pointer(text: str) -> bool:
+    """True when the raw text references a durable, retrievable source."""
+    raw = text or ""
+    return any(rx.search(raw) for rx in _DURABLE_SOURCE_REGEXES)
+
+
+def find_vague_reference(text: str) -> str | None:
+    """Return the vague phrase a field is dominated by, else ``None``.
+
+    A field is a vague reference only when it contains a known vague phrase,
+    carries no durable source pointer, and the phrase dominates the field
+    (the field is essentially just the phrase). Long, specific bodies that
+    merely contain "as discussed" in passing are not blocked.
+    """
+    if has_durable_source_pointer(text):
+        return None
+    norm = normalize_text(text)
+    if not norm:
+        return None
+    stripped = norm
+    for verb in _LEADING_VERBS:
+        if stripped.startswith(verb + " "):
+            stripped = stripped[len(verb) + 1:]
+    for phrase in VAGUE_REFERENCE_PHRASES:
+        if phrase in norm and len(stripped) <= len(phrase) + 12:
+            return phrase
+    return None
+
+
+def assess_issue_content(
+    title: str,
+    body: str = "",
+    *,
+    allow_incomplete: bool = False,
+) -> dict:
+    """Evaluate whether proposed issue content is durable enough to create.
+
+    Returns a dict with ``complete`` (bool), ``missing_fields``,
+    ``vague_fields``, ``reasons``, ``diagnose`` (joined reasons), and
+    ``has_durable_source_pointer``. ``allow_incomplete`` is an explicit
+    operator override that forces ``complete`` True.
+    """
+    t = (title or "").strip()
+    b = (body or "").strip()
+    missing_fields: list[str] = []
+    vague_fields: list[str] = []
+    reasons: list[str] = []
+
+    if not t:
+        missing_fields.append("title")
+        reasons.append("issue title is required")
+    else:
+        phrase = find_vague_reference(t)
+        if phrase:
+            vague_fields.append("title")
+            reasons.append(
+                f"title is a vague reference ('{phrase}') with no durable "
+                "content or source pointer"
+            )
+
+    if b:
+        phrase = find_vague_reference(b)
+        if phrase:
+            vague_fields.append("body")
+            reasons.append(
+                f"body is a vague reference ('{phrase}') with no durable "
+                "content or source pointer"
+            )
+
+    complete = allow_incomplete or (not missing_fields and not vague_fields)
+    return {
+        "complete": complete,
+        "missing_fields": missing_fields,
+        "vague_fields": vague_fields,
+        "reasons": reasons,
+        "diagnose": "; ".join(reasons),
+        "has_durable_source_pointer": has_durable_source_pointer(b)
+        or has_durable_source_pointer(t),
+        "override_applied": bool(
+            allow_incomplete and (missing_fields or vague_fields)
+        ),
+    }
+
+
+def pre_create_issue_content_gate(
+    title: str,
+    body: str = "",
+    *,
+    allow_incomplete: bool = False,
+) -> dict:
+    """Content gate wrapper mirroring the duplicate gate shape.
+
+    ``performed`` is True when the content is durable enough to create (or an
+    explicit override was supplied). When False, the caller must return
+    BLOCKED + DIAGNOSE and must not create the issue.
+    """
+    assessment = assess_issue_content(
+        title, body, allow_incomplete=allow_incomplete
+    )
+    assessment["performed"] = assessment["complete"]
+    return assessment

issue_workflow_labels.py

@@ -0,0 +1,220 @@
+"""Canonical issue type/status label taxonomy and transition helpers (#513)."""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Iterable, Mapping, Sequence
+
+
+@dataclass(frozen=True)
+class LabelSpec:
+    name: str
+    color: str
+    description: str
+
+
+TYPE_LABEL_SPECS: tuple[LabelSpec, ...] = (
+    LabelSpec("type:bug", "b60205", "Bug or defect"),
+    LabelSpec("type:feature", "a2eeef", "Feature or enhancement"),
+    LabelSpec("type:process", "5319e7", "Process or policy work"),
+    LabelSpec("type:workflow", "c2e0c6", "Workflow automation or guidance"),
+    LabelSpec("type:guardrail", "d93f0b", "Safety gate or guardrail"),
+    LabelSpec("type:docs", "006b75", "Documentation work"),
+    LabelSpec("type:test", "0e8a16", "Tests or test infrastructure"),
+    LabelSpec("type:discussion", "bfdadc", "Discussion-only issue"),
+    LabelSpec("type:umbrella", "c5def5", "Umbrella or tracker issue"),
+    LabelSpec("type:cleanup", "ededed", "Cleanup or hygiene work"),
+)
+
+STATUS_LABEL_SPECS: tuple[LabelSpec, ...] = (
+    LabelSpec("status:triage", "fbca04", "Issue needs triage"),
+    LabelSpec("status:ready", "0e8a16", "Issue is ready for work"),
+    LabelSpec("status:claimed", "fefe2e", "Issue is claimed"),
+    LabelSpec("status:in-progress", "fefe2e", "Issue is being worked on"),
+    LabelSpec("status:blocked", "b60205", "Issue is blocked"),
+    LabelSpec("status:needs-review", "0052cc", "Issue work needs review"),
+    LabelSpec("status:pr-open", "1d76db", "A linked PR is open"),
+    LabelSpec("status:approved", "0e8a16", "Linked PR is approved"),
+    LabelSpec("status:merged", "5319e7", "Linked PR is merged"),
+    LabelSpec("status:reconcile", "d93f0b", "Issue needs reconciliation"),
+    LabelSpec("status:done", "0e8a16", "Issue workflow is complete"),
+    LabelSpec("status:duplicate", "cccccc", "Issue is a duplicate"),
+    LabelSpec("status:wontfix", "000000", "Issue will not be fixed"),
+)
+
+# Durable validation-outcome labels (#529): the four canonical distinctions a
+# reviewer report can carry. These are orthogonal to the single active status:*
+# label, so they use their own prefix and are not subject to the one-status
+# invariant.
+VALIDATION_LABEL_SPECS: tuple[LabelSpec, ...] = (
+    LabelSpec("validation:clean-pass", "0e8a16", "Validation was a clean pass"),
+    LabelSpec(
+        "validation:baseline-accepted",
+        "fbca04",
+        "Validation passed with a baseline-proven unrelated failure",
+    ),
+    LabelSpec(
+        "validation:blocked",
+        "b60205",
+        "Validation blocked by an unresolved failure",
+    ),
+    LabelSpec(
+        "validation:post-merge-moot",
+        "5319e7",
+        "Validation is post-merge moot (PR already merged/closed before review)",
+    ),
+)
+
+CANONICAL_LABEL_SPECS: tuple[LabelSpec, ...] = (
+    TYPE_LABEL_SPECS + STATUS_LABEL_SPECS + VALIDATION_LABEL_SPECS
+)
+
+TYPE_LABELS: frozenset[str] = frozenset(spec.name for spec in TYPE_LABEL_SPECS)
+STATUS_LABELS: frozenset[str] = frozenset(spec.name for spec in STATUS_LABEL_SPECS)
+VALIDATION_LABELS: frozenset[str] = frozenset(
+    spec.name for spec in VALIDATION_LABEL_SPECS
+)
+CANONICAL_LABELS: frozenset[str] = frozenset(
+    spec.name for spec in CANONICAL_LABEL_SPECS
+)
+
+STATUS_TRANSITIONS: dict[str, str] = {
+    "triage": "status:triage",
+    "ready": "status:ready",
+    "claim": "status:claimed",
+    "claimed": "status:claimed",
+    "start": "status:in-progress",
+    "start_work": "status:in-progress",
+    "in_progress": "status:in-progress",
+    "in-progress": "status:in-progress",
+    "block": "status:blocked",
+    "blocked": "status:blocked",
+    "needs_review": "status:needs-review",
+    "needs-review": "status:needs-review",
+    "pr_open": "status:pr-open",
+    "pr-open": "status:pr-open",
+    "approved": "status:approved",
+    "merge": "status:reconcile",
+    "merged": "status:reconcile",
+    "reconcile": "status:reconcile",
+    "done": "status:done",
+    "complete": "status:done",
+    "duplicate": "status:duplicate",
+    "wontfix": "status:wontfix",
+}
+
+
+def label_name(label: str | Mapping[str, object]) -> str:
+    """Return a normalized label name from a Gitea label object or string."""
+    if isinstance(label, str):
+        return label.strip()
+    value = label.get("name")
+    return str(value or "").strip()
+
+
+def label_names(labels: Iterable[str | Mapping[str, object]] | Mapping[str, object]) -> list[str]:
+    """Extract label names from a label list or issue-like mapping."""
+    raw: object
+    if isinstance(labels, Mapping):
+        raw = labels.get("labels", [])
+    else:
+        raw = labels
+    return [name for name in (label_name(label) for label in raw or []) if name]
+
+
+def type_labels(labels: Iterable[str | Mapping[str, object]] | Mapping[str, object]) -> list[str]:
+    return [name for name in label_names(labels) if name.startswith("type:")]
+
+
+def status_labels(labels: Iterable[str | Mapping[str, object]] | Mapping[str, object]) -> list[str]:
+    return [name for name in label_names(labels) if name.startswith("status:")]
+
+
+def canonical_status_label(status_or_transition: str) -> str:
+    status = status_or_transition.strip()
+    if status in STATUS_LABELS:
+        return status
+    normalized = status.lower().replace(" ", "-")
+    try:
+        return STATUS_TRANSITIONS[normalized]
+    except KeyError as exc:
+        raise ValueError(
+            f"unknown workflow status or transition '{status_or_transition}'"
+        ) from exc
+
+
+def transition_status_labels(
+    existing_labels: Iterable[str | Mapping[str, object]] | Mapping[str, object],
+    status_or_transition: str,
+) -> list[str]:
+    """Replace all active status labels with the requested canonical status."""
+    new_status = canonical_status_label(status_or_transition)
+    kept = [name for name in label_names(existing_labels) if not name.startswith("status:")]
+    if new_status not in kept:
+        kept.append(new_status)
+    return kept
+
+
+def labels_for_new_issue(
+    issue_type: str | None = None,
+    initial_status: str | None = None,
+    extra_labels: Sequence[str] | None = None,
+    *,
+    discussion: bool = False,
+) -> list[str]:
+    names = list(extra_labels or [])
+    if issue_type:
+        type_name = issue_type if issue_type.startswith("type:") else f"type:{issue_type}"
+        names.append(type_name)
+    if discussion:
+        names.append("type:discussion")
+    if initial_status:
+        names.append(canonical_status_label(initial_status))
+
+    result: list[str] = []
+    for name in names:
+        if name not in result:
+            result.append(name)
+    return result
+
+
+def assess_issue_labels(
+    labels: Iterable[str | Mapping[str, object]] | Mapping[str, object],
+    *,
+    discussion: bool = False,
+    require_type: bool = True,
+    require_status: bool = True,
+) -> dict:
+    names = label_names(labels)
+    found_types = type_labels(names)
+    found_statuses = status_labels(names)
+    errors: list[str] = []
+    warnings: list[str] = []
+
+    if require_type and not found_types:
+        errors.append("issue is missing a type:* label")
+    if require_status and not found_statuses:
+        errors.append("issue is missing a status:* label")
+    if discussion and "type:discussion" not in found_types:
+        errors.append("discussion issue is missing type:discussion")
+    if len(found_statuses) > 1:
+        errors.append(
+            "issue has multiple active status:* labels: "
+            + ", ".join(found_statuses)
+        )
+
+    for name in found_types:
+        if name not in TYPE_LABELS:
+            warnings.append(f"unknown type label '{name}'")
+    for name in found_statuses:
+        if name not in STATUS_LABELS:
+            warnings.append(f"unknown status label '{name}'")
+
+    return {
+        "valid": not errors,
+        "labels": names,
+        "type_labels": found_types,
+        "status_labels": found_statuses,
+        "errors": errors,
+        "warnings": warnings,
+    }

manage_labels.py

@@ -23,6 +23,7 @@ if os.path.exists(venv_python) and sys.executable != venv_python:
     os.execv(venv_python, [venv_python] + sys.argv)
 
 from gitea_auth import get_auth_header, api_request, repo_api_url
+import issue_workflow_labels
 
 HOST = "gitea.dadeschools.net"
 ORG = "Contractor"
@@ -35,8 +36,10 @@ LABELS = [
     {"name": "epic", "color": "8250df", "description": ""},
     {"name": "important", "color": "fbca04", "description": ""},
     {"name": "nice-to-have", "color": "0e8a16", "description": ""},
-    {"name": "status:in-progress", "color": "fefe2e",
-     "description": "Issue is being worked on"},
+    *[
+        {"name": spec.name, "color": spec.color, "description": spec.description}
+        for spec in issue_workflow_labels.CANONICAL_LABEL_SPECS
+    ],
 ]
 
 # issue number -> label names to apply (one-off backfill)

mcp-menu.sh

@@ -115,7 +115,15 @@ Workflow:
 }
 
 show_reviewer_prompts() {
-  print_prompt_block "Reviewer — PR review" \
+  while true; do
+    printf '\n--- Reviewer workflow prompts ---\n'
+    printf '  1) Standard PR review\n'
+    printf '  2) Skip already-reviewed stale REQUEST_CHANGES PR and hand off to author\n'
+    printf '  0) Back\n'
+    read -r -p 'Choice: ' choice
+    case "$choice" in
+      1)
+        print_prompt_block "Reviewer — PR review" \
 "You are the REVIEWER session for <org>/<repo>.
 
 Goal: review PR #<P> only — do not merge unless explicitly switched to merger mode.
@@ -126,6 +134,35 @@ Workflow:
 3. gitea_view_pr, validate scope, run required checks in the correct worktree.
 4. gitea_review_pr with approve, request-changes, or comment as warranted.
 5. Final report: PR head SHA, verdict, validation evidence, mutation ledger. No merge in reviewer-only runs."
+        ;;
+      2)
+        print_prompt_block "Reviewer — skip already-reviewed stale REQUEST_CHANGES PR and hand off to author" \
+"You are the REVIEWER session for <org>/<repo>.
+
+Goal: review PR #<P> only far enough to determine whether the current head already has a non-stale REQUEST_CHANGES verdict. If it does, do NOT submit another terminal review mutation — produce an author handoff and stop.
+
+Workflow:
+1. gitea_view_pr; pin the current head SHA.
+2. Load prior reviews; find the latest REQUEST_CHANGES and the head SHA it was bound to.
+3. If that REQUEST_CHANGES is still bound to the current head (non-stale), do not submit another terminal review mutation. Confirm the binding and summarize the blockers.
+4. Run only the diagnostics needed to produce a useful author handoff — no full re-review.
+5. Duplicate/supersession check: confirm no newer canonical PR or superseding head changes the decision.
+6. Stop — no new review mutation.
+
+Return:
+- selected PR and issue
+- current head SHA
+- prior REQUEST_CHANGES proof (review id + bound head SHA)
+- duplicate/supersession analysis
+- validation summary
+- why no new review mutation was submitted
+- corrected mutation ledger, including local worktree create/remove if used
+- author-ready fix prompt"
+        ;;
+      0) return ;;
+      *) printf 'Invalid choice.\n' ;;
+    esac
+  done
 }
 
 show_merger_prompts() {

mcp_daemon_guard.py

@@ -0,0 +1,84 @@
+"""Sanctioned MCP daemon guards for imports and credential access (#558).
+
+Direct ``import gitea_mcp_server`` / ``import gitea_auth`` from a shell, plus
+raw keychain dumps, bypass preflight purity and role gates. Mutation helpers
+and keychain fallbacks therefore require an explicit sanctioned runtime.
+
+Sanctioned contexts (any one):
+- ``GITEA_MCP_SANCTIONED_DAEMON=1`` (set by the official MCP entrypoint)
+- pytest (``PYTEST_CURRENT_TEST`` present)
+- explicit operator opt-in ``GITEA_ALLOW_DIRECT_MCP_IMPORT=1`` (tests/tools only)
+
+Credential keychain fill additionally allows:
+- ``GITEA_ALLOW_KEYCHAIN_CLI=1`` for operator-only non-MCP scripts that must
+  use git-credential (never the default for LLM shells).
+"""
+
+from __future__ import annotations
+
+import os
+from typing import Any
+
+SANCTIONED_DAEMON_ENV = "GITEA_MCP_SANCTIONED_DAEMON"
+ALLOW_DIRECT_IMPORT_ENV = "GITEA_ALLOW_DIRECT_MCP_IMPORT"
+ALLOW_KEYCHAIN_CLI_ENV = "GITEA_ALLOW_KEYCHAIN_CLI"
+
+
+class UnsanctionedRuntimeError(RuntimeError):
+    """Raised when mutation/credential code runs outside a sanctioned MCP daemon."""
+
+
+def is_pytest_runtime() -> bool:
+    return bool((os.environ.get("PYTEST_CURRENT_TEST") or "").strip())
+
+
+def is_sanctioned_mcp_daemon() -> bool:
+    if (os.environ.get(SANCTIONED_DAEMON_ENV) or "").strip() in {"1", "true", "yes"}:
+        return True
+    if (os.environ.get(ALLOW_DIRECT_IMPORT_ENV) or "").strip() in {"1", "true", "yes"}:
+        return True
+    if is_pytest_runtime():
+        return True
+    return False
+
+
+def mark_sanctioned_daemon() -> None:
+    """Call from the official MCP server entrypoint before serving tools."""
+    os.environ[SANCTIONED_DAEMON_ENV] = "1"
+
+
+def assert_sanctioned_mutation_runtime(context: str = "mutation") -> None:
+    """Fail closed when server mutation code is used outside the MCP daemon."""
+    if is_sanctioned_mcp_daemon():
+        return
+    raise UnsanctionedRuntimeError(
+        f"Unsanctioned runtime blocked {context} (#558). "
+        "Do not import gitea_mcp_server / call mutation helpers from a raw "
+        "shell or ad-hoc script. Use the official MCP daemon entrypoint "
+        f"(sets {SANCTIONED_DAEMON_ENV}=1), or run under pytest. "
+        f"Operator-only override: {ALLOW_DIRECT_IMPORT_ENV}=1 (not for LLM sessions)."
+    )
+
+
+def assert_keychain_access_allowed() -> None:
+    """Fail closed for git-credential keychain fill outside sanctioned contexts."""
+    if is_sanctioned_mcp_daemon():
+        return
+    if (os.environ.get(ALLOW_KEYCHAIN_CLI_ENV) or "").strip() in {"1", "true", "yes"}:
+        return
+    raise UnsanctionedRuntimeError(
+        "Unsanctioned keychain/credential fill blocked (#558). "
+        "Token extraction via git-credential is only allowed inside the "
+        f"official MCP daemon ({SANCTIONED_DAEMON_ENV}=1), pytest, or with "
+        f"explicit operator opt-in {ALLOW_KEYCHAIN_CLI_ENV}=1."
+    )
+
+
+def runtime_status() -> dict[str, Any]:
+    return {
+        "sanctioned_daemon": is_sanctioned_mcp_daemon(),
+        "pytest": is_pytest_runtime(),
+        "sanctioned_env": SANCTIONED_DAEMON_ENV,
+        "allow_direct_import_env": ALLOW_DIRECT_IMPORT_ENV,
+        "allow_keychain_cli_env": ALLOW_KEYCHAIN_CLI_ENV,
+    }

mcp_namespace_health.py

@@ -0,0 +1,306 @@
+"""Assess live MCP namespace health without trusting static registration.
+
+The IDE/client namespace can fail with EOF even when this Python process still
+registers the Gitea tools with FastMCP.  These helpers keep that distinction
+explicit so reviewer/merger flows can fail closed on the live path.
+
+Probe sources
+-------------
+* ``client_namespace`` — evidence from the IDE-managed MCP client path (the
+  only source that can prove the workflow namespace is healthy).
+* ``offline_spawn`` — a separate ``subprocess.Popen`` JSON-RPC handshake
+  (e.g. ``test_mcp_conn.py``). Useful offline, but **never** proves the
+  IDE-managed namespace is callable.
+* ``unknown`` — legacy/unspecified; treated as not IDE-proven.
+"""
+
+from __future__ import annotations
+
+from typing import Any
+
+
+REQUIRED_NAMESPACE_TOOLS = {
+    "gitea-author": "gitea_whoami",
+    "gitea-reviewer": "gitea_whoami",
+    "gitea-merger": "gitea_whoami",
+    "gitea-tools": "gitea_list_profiles",
+}
+
+DEFAULT_NAMESPACES = tuple(REQUIRED_NAMESPACE_TOOLS)
+
+# Namespaces that must be healthy for a given mutation task.
+TASK_REQUIRED_NAMESPACES = {
+    "review_pr": "gitea-reviewer",
+    "submit_review": "gitea-reviewer",
+    "merge_pr": "gitea-merger",
+}
+
+PROBE_SOURCE_CLIENT = "client_namespace"
+PROBE_SOURCE_OFFLINE = "offline_spawn"
+PROBE_SOURCE_UNKNOWN = "unknown"
+VALID_PROBE_SOURCES = frozenset(
+    {PROBE_SOURCE_CLIENT, PROBE_SOURCE_OFFLINE, PROBE_SOURCE_UNKNOWN}
+)
+
+EOF_PATTERNS = (
+    "client is closing: eof",
+    "transport closed",
+    "connection closed",
+    "broken pipe",
+    "end of file",
+    "eof",
+)
+
+SAFE_ENV_KEYS = (
+    "GITEA_MCP_PROFILE",
+    "GITEA_PROFILE_NAME",
+    "GITEA_SERVICE",
+    "GITEA_EXECUTION_ROLE",
+    "GITEA_MCP_CONFIG",
+)
+
+
+def _as_list(value: Any) -> list[str] | None:
+    if value is None:
+        return None
+    if isinstance(value, (list, tuple, set)):
+        return [str(v) for v in value]
+    return [str(value)]
+
+
+def _contains_eof(text: str | None) -> bool:
+    lowered = (text or "").lower()
+    return any(pattern in lowered for pattern in EOF_PATTERNS)
+
+
+def _normalize_probe_source(probe_source: str | None) -> str:
+    raw = (probe_source or PROBE_SOURCE_UNKNOWN).strip().lower()
+    if raw in VALID_PROBE_SOURCES:
+        return raw
+    return PROBE_SOURCE_UNKNOWN
+
+
+def _safe_env_summary(process: dict[str, Any] | None) -> dict[str, str]:
+    if not process:
+        return {}
+    env = process.get("env") or process.get("environment") or {}
+    if not isinstance(env, dict):
+        return {}
+    return {
+        key: str(env[key])
+        for key in SAFE_ENV_KEYS
+        if key in env and env[key] not in (None, "")
+    }
+
+
+def classify_namespace_probe(
+    namespace: str,
+    *,
+    required_tool: str | None = None,
+    registered_tools: list[str] | tuple[str, ...] | set[str] | None = None,
+    probe_result: dict[str, Any] | None = None,
+    process: dict[str, Any] | None = None,
+    config_path: str | None = None,
+    profile: str | None = None,
+    configured: bool = True,
+    probe_source: str | None = None,
+) -> dict[str, Any]:
+    """Classify whether a required tool is callable through a live namespace.
+
+    ``registered_tools`` is static/server-side evidence. ``probe_result`` is
+    live invocation evidence. Only ``probe_source=client_namespace`` proves the
+    IDE-managed path; ``offline_spawn`` is an offline subprocess check only.
+    """
+    ns = (namespace or "").strip()
+    tool = required_tool or REQUIRED_NAMESPACE_TOOLS.get(ns) or "gitea_whoami"
+    source = _normalize_probe_source(probe_source)
+    registered_list = _as_list(registered_tools)
+    registered = None if registered_list is None else tool in registered_list
+
+    probe = probe_result or {}
+    probe_success = bool(probe.get("success"))
+    error_message = str(
+        probe.get("error")
+        or probe.get("message")
+        or probe.get("stderr")
+        or probe.get("exception")
+        or ""
+    )
+    error_type = str(probe.get("error_type") or "").strip()
+    if not error_type and error_message:
+        if _contains_eof(error_message):
+            error_type = "namespace_eof"
+        elif "timeout" in error_message.lower():
+            error_type = "namespace_timeout"
+        else:
+            error_type = "namespace_call_failed"
+
+    if not configured:
+        error_type = "namespace_not_configured"
+    elif registered is False:
+        error_type = "tool_missing"
+    elif not probe_result:
+        error_type = "live_probe_missing"
+    elif not probe_success and not error_type:
+        error_type = "namespace_call_failed"
+
+    callable_live = bool(configured and probe_result and probe_success)
+    # Probe-path health (spawn or client). IDE-proven only for client path.
+    healthy = bool(configured and registered is not False and callable_live)
+    ide_namespace_proven = bool(healthy and source == PROBE_SOURCE_CLIENT)
+    process_pid = process.get("pid") if isinstance(process, dict) else None
+    profile_name = profile or (
+        process.get("profile") if isinstance(process, dict) else None
+    )
+    env_summary = _safe_env_summary(process)
+
+    reasons: list[str] = []
+    if not configured:
+        reasons.append(f"MCP namespace '{ns}' is not configured.")
+    if registered is False:
+        reasons.append(
+            f"Required tool '{tool}' is not registered in namespace '{ns}'."
+        )
+    if error_type == "live_probe_missing":
+        reasons.append(
+            f"No live client invocation proof was supplied for '{ns}.{tool}'."
+        )
+    elif error_type == "namespace_eof":
+        reasons.append(
+            f"Live MCP namespace '{ns}' returned EOF while invoking '{tool}'."
+        )
+    elif error_type == "namespace_timeout":
+        reasons.append(
+            f"Live MCP namespace '{ns}' timed out while invoking '{tool}'."
+        )
+    elif error_type == "namespace_call_failed":
+        reasons.append(
+            f"Live MCP namespace '{ns}' failed while invoking '{tool}'."
+        )
+    if source == PROBE_SOURCE_OFFLINE:
+        reasons.append(
+            "Probe source is offline_spawn (subprocess JSON-RPC); this does "
+            "not prove the IDE-managed MCP namespace is healthy."
+        )
+    elif source == PROBE_SOURCE_UNKNOWN and probe_result:
+        reasons.append(
+            "Probe source unspecified; treat as not IDE-namespace proof unless "
+            "re-supplied with probe_source='client_namespace'."
+        )
+
+    remediation = []
+    if not healthy or not ide_namespace_proven:
+        remediation.append(
+            "Reconnect the IDE MCP client namespace (client reconnect / "
+            f"relaunch), then invoke '{tool}' through namespace '{ns}' and "
+            "record the result with probe_source='client_namespace'."
+        )
+        remediation.append(
+            "Do not treat offline subprocess probes (test_mcp_conn.py) or "
+            "shell kill/PID respawn as proof the IDE namespace is repaired."
+        )
+        if process_pid and source != PROBE_SOURCE_OFFLINE:
+            remediation.append(
+                f"Diagnostics may include PID {process_pid}; process details "
+                "are informational only — recovery is client-layer reconnect."
+            )
+    else:
+        remediation.append(
+            f"IDE-managed namespace '{ns}' can invoke '{tool}' "
+            f"(probe_source={source})."
+        )
+
+    # Client-namespace broken health blocks review/merge. Offline probes never
+    # authorize mutations and only block when they report unhealthy (still
+    # fail-closed for known bad spawn evidence).
+    blocks = False
+    if source == PROBE_SOURCE_CLIENT:
+        blocks = namespace_health_blocks_task("merge_pr", healthy)
+    elif source == PROBE_SOURCE_OFFLINE:
+        # Offline never proves IDE health; never unblock. Unhealthy offline
+        # still surfaces as a soft diagnostic, not a mutation-ledger block.
+        blocks = False
+    else:
+        # Unknown source: only block when evidence is unhealthy (fail closed
+        # on bad data without treating success as IDE proof).
+        blocks = namespace_health_blocks_task("merge_pr", healthy)
+
+    return {
+        "success": healthy,
+        "healthy": healthy,
+        "namespace": ns,
+        "required_tool": tool,
+        "configured": configured,
+        "registered_tools_checked": registered_list is not None,
+        "required_tool_registered": registered,
+        "required_tool_callable": callable_live,
+        "probe_source": source,
+        "ide_namespace_proven": ide_namespace_proven,
+        "error_type": None if healthy else error_type,
+        "error_message": error_message or None,
+        "reasons": reasons,
+        "remediation": remediation,
+        "diagnostics": {
+            "namespace": ns,
+            "required_tool": tool,
+            "process_pid": process_pid,
+            "profile": profile_name,
+            "env": env_summary,
+            "config_path": config_path,
+            "probe_source": source,
+        },
+        "blocks_merge_workflow": blocks,
+    }
+
+
+def namespace_health_blocks_task(task: str, healthy: bool) -> bool:
+    """Return whether a broken namespace must block a workflow task."""
+    if healthy:
+        return False
+    return (task or "").strip() in {"merge_pr", "review_pr", "submit_review"}
+
+
+def required_namespace_for_task(task: str) -> str | None:
+    """Map a mutation task to the MCP namespace that must be healthy."""
+    return TASK_REQUIRED_NAMESPACES.get((task or "").strip())
+
+
+def mutation_gate_from_session(
+    task: str,
+    session_health: dict[str, dict[str, Any]] | None,
+) -> list[str]:
+    """Fail-closed gate using recorded client-namespace health assessments.
+
+    * Missing session entry → no gate (caller has not assessed yet).
+    * Client-namespace unhealthy / not IDE-proven → block mutation.
+    * Offline-only session entries never authorize mutations.
+    """
+    ns = required_namespace_for_task(task)
+    if not ns:
+        return []
+    store = session_health or {}
+    entry = store.get(ns)
+    if not entry:
+        return []
+    source = _normalize_probe_source(entry.get("probe_source"))
+    if source != PROBE_SOURCE_CLIENT:
+        return [
+            f"recorded namespace health for '{ns}' is probe_source={source}, "
+            "not client_namespace; re-probe through the IDE-managed path "
+            f"before {(task or 'mutation')}"
+        ]
+    if entry.get("ide_namespace_proven") and entry.get("healthy"):
+        return []
+    if entry.get("blocks_merge_workflow") or not entry.get("healthy"):
+        detail = entry.get("error_type") or "unhealthy"
+        return [
+            f"live MCP namespace '{ns}' is recorded {detail} "
+            f"(probe_source={source}); repair the IDE namespace before "
+            f"{(task or 'mutation')} (fail closed, #543)"
+        ]
+    if not entry.get("ide_namespace_proven"):
+        return [
+            f"live MCP namespace '{ns}' is not IDE-proven; supply a "
+            "client_namespace probe before mutation (fail closed, #543)"
+        ]
+    return []

mcp_server.py

@@ -6,6 +6,9 @@ Runs over stdio. All tools authenticate via macOS keychain (git credential fill)
 import os
 import sys
 
+sys.stderr = open("/tmp/mcp_server_stderr.log", "a", buffering=1)
+sys.stderr.write(f"\n--- MCP SERVER STARTUP (PID {os.getpid()}) ---\n")
+
 from role_session_router import (
     python_bytes_have_conflict_markers,
     skip_python_scan_walk_root,
@@ -37,6 +40,17 @@ def check_conflict_markers():
 
 check_conflict_markers()
 
+# #558: official entrypoint marks the process as the sanctioned MCP daemon
+# before loading mutation modules (blocks raw shell import bypasses).
+try:
+    import mcp_daemon_guard
+
+    mcp_daemon_guard.mark_sanctioned_daemon()
+except Exception:
+    # Guard import failures must not hide conflict-marker infra_stop above;
+    # gitea_mcp_server main also marks sanctioned when run as __main__.
+    pass
+
 # Execute the actual server logic via exec in this namespace.
 impl_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "gitea_mcp_server.py")
 try:

mcp_session_state.py

@@ -30,6 +30,9 @@ DEFAULT_TTL_HOURS = 4.0
 
 KIND_WORKFLOW_LOAD = "review_workflow_load"
 KIND_DECISION_LOCK = "review_decision_lock"
+KIND_REVIEW_DRAFT = "review_draft"
+
+
 
 _SAFE_SEGMENT_RE = re.compile(r"[^A-Za-z0-9._+-]+")
 SESSION_PROFILE_LOCK_ENV = "GITEA_SESSION_PROFILE_LOCK"

merged_cleanup_reconcile.py

@@ -17,6 +17,7 @@ import issue_lock_store
 
 PROTECTED_BRANCHES = frozenset({"master", "main", "dev"})
 CLOSES_FIXES_RE = re.compile(r"\b(?:closes|fixes)\s+#(\d+)\b", re.IGNORECASE)
+ISSUE_MARKER_RE = re.compile(r"(?:^|[-_/])issue-(\d+)(?:[-_/]|$)", re.IGNORECASE)
 # Reviewer scratch folders: review-pr<N> or review-pr<N>-submit (#534).
 REVIEWER_SCRATCH_NAME_RE = re.compile(
     r"^review-pr(?P<pr>\d+)(?:-submit)?$",
@@ -41,6 +42,59 @@ def resolve_worktree_path(project_root: str, branch: str) -> str:
     return os.path.join(project_root, "branches", branch_worktree_folder(branch))
 
 
+def extract_issue_marker(*values: str | None) -> int | None:
+    """Return the first issue marker found in branch/path-like values."""
+    for value in values:
+        match = ISSUE_MARKER_RE.search(value or "")
+        if match:
+            return int(match.group(1))
+    return None
+
+
+def list_local_worktrees(project_root: str) -> list[dict[str, Any]]:
+    """Parse ``git worktree list --porcelain`` into structured entries."""
+    res = subprocess.run(
+        ["git", "-C", project_root, "worktree", "list", "--porcelain"],
+        capture_output=True,
+        text=True,
+        check=False,
+    )
+    if res.returncode != 0:
+        return []
+
+    entries: list[dict[str, Any]] = []
+    current: dict[str, Any] | None = None
+
+    def flush() -> None:
+        nonlocal current
+        if current:
+            entries.append(current)
+        current = None
+
+    for raw_line in (res.stdout or "").splitlines():
+        line = raw_line.strip()
+        if not line:
+            flush()
+            continue
+        if line.startswith("worktree "):
+            flush()
+            current = {"path": line[9:].strip()}
+        elif current is not None and line.startswith("HEAD "):
+            current["head_sha"] = line[5:].strip()
+        elif current is not None and line.startswith("branch "):
+            ref = line[7:].strip()
+            current["branch_ref"] = ref
+            current["branch"] = (
+                ref[len("refs/heads/"):]
+                if ref.startswith("refs/heads/")
+                else ref
+            )
+        elif current is not None and line == "detached":
+            current["detached"] = True
+    flush()
+    return entries
+
+
 def _git_worktree_porcelain(project_root: str) -> list[dict[str, str | None]]:
     """Parse ``git worktree list --porcelain`` into structured records."""
     res = subprocess.run(
@@ -82,14 +136,115 @@ def _git_worktree_porcelain(project_root: str) -> list[dict[str, str | None]]:
 def discover_local_worktrees(project_root: str) -> dict[str, str]:
     """Return a mapping from branch name to absolute worktree path (#528)."""
     mapping: dict[str, str] = {}
-    for record in _git_worktree_porcelain(project_root):
-        branch_name = record.get("branch")
-        path = record.get("worktree")
-        if branch_name and path:
-            mapping[str(branch_name)] = str(path)
+    for entry in list_local_worktrees(project_root):
+        branch = entry.get("branch")
+        path = entry.get("path")
+        if branch and path:
+            mapping[str(branch)] = str(path)
     return mapping
 
 
+def _is_under_branches(project_root: str, path: str) -> bool:
+    branches_root = os.path.realpath(os.path.join(project_root, "branches"))
+    real_path = os.path.realpath(path)
+    return real_path == branches_root or real_path.startswith(branches_root + os.sep)
+
+
+def _head_is_safe_for_cleanup(
+    *,
+    project_root: str,
+    candidate_head: str | None,
+    pr_head_sha: str | None,
+    target_ref: str | None,
+) -> bool:
+    if not candidate_head:
+        return False
+    if pr_head_sha and candidate_head == pr_head_sha:
+        return True
+    if target_ref:
+        return is_head_ancestor_of_ref(project_root, candidate_head, target_ref) is True
+    return False
+
+
+def resolve_cleanup_worktree_state(
+    *,
+    project_root: str,
+    head_branch: str,
+    issue_number: int | None,
+    pr_head_sha: str | None = None,
+    target_ref: str | None = None,
+) -> dict[str, Any]:
+    """Find the exact or safe alias worktree used for local cleanup (#532)."""
+    expected_path = resolve_worktree_path(project_root, head_branch)
+    state = read_local_worktree_state(expected_path)
+    state["worktree_path"] = expected_path
+    state["expected_worktree_path"] = expected_path
+    state["discovered_worktree_path"] = expected_path if state.get("exists") else None
+    state["match_type"] = "derived_path" if state.get("exists") else "none"
+    state["candidate_paths"] = []
+    state["alias_block_reasons"] = []
+    if state.get("exists"):
+        return state
+
+    branch_issue = extract_issue_marker(head_branch)
+    wanted_issue = issue_number or branch_issue
+    candidates: list[dict[str, Any]] = []
+    unsafe_matches: list[str] = []
+
+    for entry in list_local_worktrees(project_root):
+        path = entry.get("path") or ""
+        if not path or not _is_under_branches(project_root, path):
+            continue
+        branch = entry.get("branch") or ""
+        path_issue = extract_issue_marker(os.path.basename(path), path)
+        entry_issue = extract_issue_marker(branch) or path_issue
+        branch_match = branch == head_branch
+        issue_match = wanted_issue is not None and entry_issue == wanted_issue
+        if not (branch_match or issue_match):
+            continue
+        safe_head = _head_is_safe_for_cleanup(
+            project_root=project_root,
+            candidate_head=entry.get("head_sha"),
+            pr_head_sha=pr_head_sha,
+            target_ref=target_ref,
+        )
+        if not safe_head and branch_match and not pr_head_sha and not target_ref:
+            safe_head = True
+        if not safe_head:
+            unsafe_matches.append(path)
+            continue
+        candidates.append(entry)
+
+    state["candidate_paths"] = [entry.get("path") for entry in candidates]
+    if len(candidates) == 1:
+        path = candidates[0]["path"]
+        alias_state = read_local_worktree_state(path)
+        alias_state["worktree_path"] = path
+        alias_state["expected_worktree_path"] = expected_path
+        alias_state["discovered_worktree_path"] = path
+        alias_state["match_type"] = (
+            "branch" if candidates[0].get("branch") == head_branch else "alias"
+        )
+        alias_state["candidate_paths"] = [path]
+        alias_state["alias_block_reasons"] = []
+        alias_state["alias_verified"] = True
+        return alias_state
+    if len(candidates) > 1:
+        state["alias_block_reasons"].append(
+            "ambiguous local worktree aliases: " + ", ".join(
+                sorted(str(entry.get("path")) for entry in candidates)
+            )
+        )
+        state["match_type"] = "ambiguous_alias"
+    elif unsafe_matches:
+        state["alias_block_reasons"].append(
+            "matching local worktree aliases did not point to the PR head or target branch: "
+            + ", ".join(sorted(unsafe_matches))
+        )
+        state["match_type"] = "unsafe_alias"
+    return state
+
+
 def parse_reviewer_scratch_folder(folder_name: str) -> int | None:
     """Return PR number for a reviewer scratch folder name, else None (#534)."""
     match = REVIEWER_SCRATCH_NAME_RE.match((folder_name or "").strip())
@@ -323,6 +478,7 @@ def assess_local_worktree_cleanup(
     exists = bool(worktree_state.get("exists"))
     if not merged:
         reasons.append("PR is not merged")
+    reasons.extend(worktree_state.get("alias_block_reasons") or [])
     if not exists:
         reasons.append("local worktree not present")
     if exists and worktree_state.get("clean") is False:
@@ -333,7 +489,11 @@ def assess_local_worktree_cleanup(
         )
     if exists:
         current_branch = worktree_state.get("current_branch")
-        if current_branch and current_branch != head_branch:
+        if (
+            current_branch
+            and current_branch != head_branch
+            and not worktree_state.get("alias_verified")
+        ):
             reasons.append(
                 f"worktree branch '{current_branch}' does not match PR head '{head_branch}'"
             )
@@ -345,6 +505,10 @@ def assess_local_worktree_cleanup(
         "pr_number": pr_number,
         "head_branch": head_branch,
         "worktree_path": worktree_state.get("worktree_path"),
+        "expected_worktree_path": worktree_state.get("expected_worktree_path"),
+        "discovered_worktree_path": worktree_state.get("discovered_worktree_path"),
+        "match_type": worktree_state.get("match_type"),
+        "candidate_paths": worktree_state.get("candidate_paths") or [],
         "worktree_exists": exists,
         "worktree_clean": worktree_state.get("clean"),
         "safe_to_remove_worktree": safe,
@@ -363,7 +527,7 @@ def build_pr_cleanup_entry(
     delete_capability_allowed: bool,
     issue_lock_path: str | None = None,
     protected_branches: frozenset[str] | None = None,
-    worktree_map: dict[str, str] | None = None,
+    target_ref: str | None = None,
 ) -> dict[str, Any]:
     pr_number = int(pr["number"])
     head_branch = pr.get("head") or ""
@@ -372,18 +536,16 @@ def build_pr_cleanup_entry(
     title = pr.get("title") or ""
     body = pr.get("body") or ""
     merged = bool(pr.get("merged_at"))
-
-    discovered_path = worktree_map.get(head_branch) if worktree_map else None
-    derived_path = resolve_worktree_path(project_root, head_branch)
-    if discovered_path:
-        worktree_path = discovered_path
-        match_type = "branch"
-    else:
-        worktree_path = derived_path
-        match_type = "path"
-
-    worktree_state = read_local_worktree_state(worktree_path)
-    worktree_state["worktree_path"] = worktree_path
+    issue_number = extract_linked_issue(title, body) or extract_issue_marker(head_branch)
+    head_payload = pr.get("head") if isinstance(pr.get("head"), dict) else {}
+    pr_head_sha = head_payload.get("sha") if isinstance(head_payload, dict) else None
+    worktree_state = resolve_cleanup_worktree_state(
+        project_root=project_root,
+        head_branch=head_branch,
+        issue_number=issue_number,
+        pr_head_sha=pr_head_sha,
+        target_ref=target_ref,
+    )
     active_lock = has_active_issue_lock(head_branch, issue_lock_path)
 
     remote = assess_remote_branch_cleanup(
@@ -404,11 +566,9 @@ def build_pr_cleanup_entry(
         worktree_state=worktree_state,
         active_lock=active_lock,
     )
-    local["match_type"] = match_type
-
     return {
         "pr_number": pr_number,
-        "issue_number": extract_linked_issue(title, body),
+        "issue_number": issue_number,
         "title": title,
         "head_branch": head_branch,
         "merge_commit_sha": pr.get("merge_commit_sha"),
@@ -429,11 +589,11 @@ def build_reconciliation_report(
     delete_capability_allowed: bool,
     issue_lock_path: str | None = None,
     protected_branches: frozenset[str] | None = None,
+    target_ref: str | None = None,
     active_reviewer_leases: dict[int, bool] | None = None,
     pr_states: dict[int, dict[str, Any]] | None = None,
 ) -> dict[str, Any]:
     open_heads = collect_open_pr_heads(open_prs)
-    worktree_map = discover_local_worktrees(project_root)
     entries: list[dict[str, Any]] = []
     for pr in closed_prs or []:
         if not pr.get("merged_at"):
@@ -452,7 +612,7 @@ def build_reconciliation_report(
                 delete_capability_allowed=delete_capability_allowed,
                 issue_lock_path=issue_lock_path,
                 protected_branches=protected_branches,
-                worktree_map=worktree_map,
+                target_ref=target_ref,
             )
         )
 
@@ -505,10 +665,12 @@ def build_reconciliation_report(
     }
 
 
-def remove_local_worktree(project_root: str, branch: str) -> dict[str, Any]:
-    worktree_map = discover_local_worktrees(project_root)
-    discovered_path = worktree_map.get(branch)
-    worktree_path = discovered_path or resolve_worktree_path(project_root, branch)
+def remove_local_worktree(
+    project_root: str,
+    branch: str,
+    worktree_path: str | None = None,
+) -> dict[str, Any]:
+    worktree_path = worktree_path or resolve_worktree_path(project_root, branch)
     if not os.path.isdir(worktree_path):
         return {
             "success": False,
@@ -593,4 +755,4 @@ def remove_reviewer_scratch_worktree(
         "message": f"removed reviewer scratch worktree {real}",
         "worktree_path": real,
         "author_worktree_cleanup": False,
-    }
+    }

merger_lease_adoption.py

@@ -7,6 +7,7 @@ after formal approval at the current PR head.
 
 from __future__ import annotations
 
+import re
 from datetime import datetime, timezone
 from typing import Any
 
@@ -133,6 +134,115 @@ def is_sanctioned_session_lease(session: dict[str, Any] | None) -> bool:
     return False
 
 
+def describe_session_lease_proof(
+    session: dict[str, Any] | None,
+) -> dict[str, Any]:
+    """Canonical merge-report lease proof fields (#535).
+
+    Surfaces how the in-session lease was established so merge handoffs can
+    distinguish sanctioned MCP acquire/adopt paths from bare manual seeding.
+    """
+    if not session:
+        return {
+            "lease_proof_source": None,
+            "lease_recovery_reason": None,
+            "lease_proof_kind": "none",
+            "lease_proof_sanctioned": False,
+            "lease_proof_comment_id": None,
+            "lease_adopted_from_session_id": None,
+        }
+
+    provenance = session.get("lease_provenance") or {}
+    if not isinstance(provenance, dict):
+        provenance = {}
+    source = (provenance.get("source") or "").strip() or None
+    sanctioned = is_sanctioned_session_lease(session)
+    reason = provenance.get("adoption_reason")
+    if isinstance(reason, str):
+        reason = reason.strip() or None
+    else:
+        reason = None
+
+    if source == SOURCE_ADOPT and sanctioned:
+        kind = "sanctioned_adoption"
+        reason = reason or DEFAULT_ADOPTION_REASON
+    elif source == SOURCE_ACQUIRE and sanctioned:
+        kind = "sanctioned_acquire"
+    elif source == SOURCE_HEARTBEAT and sanctioned:
+        kind = "sanctioned_heartbeat"
+    elif source:
+        kind = "unsanctioned"
+    else:
+        # Session present without provenance = classic manual _SESSION_LEASE seed.
+        kind = "unsanctioned_manual_seed"
+
+    comment_id = provenance.get("comment_id")
+    if comment_id is None:
+        comment_id = session.get("comment_id")
+
+    return {
+        "lease_proof_source": source,
+        "lease_recovery_reason": reason,
+        "lease_proof_kind": kind,
+        "lease_proof_sanctioned": sanctioned,
+        "lease_proof_comment_id": comment_id,
+        "lease_adopted_from_session_id": provenance.get("adopted_from_session_id"),
+    }
+
+
+# Phrases that claim non-MCP / fabricated lease proof in handoffs (#535).
+_UNSAFE_LEASE_PROOF_CLAIM_RE = re.compile(
+    r"(?is)\b("
+    r"manually\s+seeded\s+lease|"
+    r"manual(?:ly)?\s+seed(?:ed)?\s+(?:lease|proof)|"
+    r"seeded\s+lease\s+proof|"
+    r"injected\s+lease|"
+    r"lease\s+proof\s+injected|"
+    r"manual\s+_?SESSION_LEASE|"
+    r"_SESSION_LEASE\s+seed|"
+    r"unsanctioned\s+lease\s+proof"
+    r")\b"
+)
+
+# Evidence that the report used the sanctioned MCP adoption/acquire path.
+_SANCTIONED_LEASE_EVIDENCE_RE = re.compile(
+    r"(?is)\b("
+    r"gitea_adopt_merger_pr_lease|"
+    r"gitea_acquire_reviewer_pr_lease|"
+    r"lease_proof_source\s*[:=]\s*gitea_adopt_merger_pr_lease|"
+    r"lease_proof_source\s*[:=]\s*gitea_acquire_reviewer_pr_lease|"
+    r"lease_proof_kind\s*[:=]\s*sanctioned_adoption|"
+    r"lease_proof_kind\s*[:=]\s*sanctioned_acquire|"
+    r"adoption_comment_id\s*[:=]|"
+    r"sanctioned_adoption|"
+    r"mcp-review-lease-adoption"
+    r")\b"
+)
+
+
+def assess_manual_lease_proof_handoff(report_text: str) -> dict[str, Any]:
+    """Controller audit: block handoffs that claim unsafe lease seeding (#535).
+
+    Reports may discuss manual seeding as a blocked/historical anti-pattern only
+    when they also cite sanctioned MCP adoption/acquire evidence. Bare claims of
+    manual/seeded/injected lease proof without that evidence fail closed.
+    """
+    text = report_text or ""
+    if not _UNSAFE_LEASE_PROOF_CLAIM_RE.search(text):
+        return {"proven": True, "block": False, "reasons": []}
+    if _SANCTIONED_LEASE_EVIDENCE_RE.search(text):
+        return {"proven": True, "block": False, "reasons": []}
+    return {
+        "proven": False,
+        "block": True,
+        "reasons": [
+            "report claims manual/seeded/injected/unsanctioned lease proof without "
+            "sanctioned MCP adoption evidence (use gitea_adopt_merger_pr_lease / "
+            "gitea_acquire_reviewer_pr_lease and cite lease_proof_source; #535)"
+        ],
+    }
+
+
 def assess_adopt_merger_lease(
     comments: list[dict],
     *,

native_mcp_preference.py

@@ -8,6 +8,9 @@ available unless explicit recovery-mode proof is supplied.
 from __future__ import annotations
 
 import re
+import os
+import shutil
+import subprocess
 from typing import Any
 
 from reviewer_fallback import LOCAL_GITEA_SCRIPT_NAMES
@@ -366,4 +369,161 @@ def assess_gitea_operation_path(
                 else "proceed with native MCP"
             )
         ),
-    }
+    }
+
+
+def default_terminal_probe_command() -> list[str]:
+    return ["git", "--version"] if shutil.which("git") else ["echo", "ok"]
+
+
+def _resolve_executable(cwd: str | None, executable: str | None) -> str | None:
+    if not executable:
+        return None
+    if os.path.isabs(executable):
+        if os.path.exists(executable) and os.access(executable, os.X_OK):
+            return executable
+        return None
+    if "/" in executable or "\\" in executable:
+        target_cwd = cwd or os.getcwd()
+        full_path = os.path.abspath(os.path.join(target_cwd, executable))
+        if os.path.exists(full_path) and os.access(full_path, os.X_OK):
+            return full_path
+        return None
+    return shutil.which(executable)
+
+
+def diagnose_terminal_failure(cwd: str | None, command: list[str]) -> dict[str, Any]:
+    """Inspect and categorize command spawn failures (#556)."""
+    diagnostics = {
+        "cwd": cwd,
+        "command": command,
+        "cwd_exists": True,
+        "cwd_is_dir": True,
+        "shell_exists": True,
+        "executable_exists": True,
+        "resolved_executable": None,
+        "error_type": "session launcher failure",
+        "error_msg": (
+            "Subprocess spawn failed despite valid CWD and executable. This may be due "
+            "to sandboxing, permission restrictions, or system resource limits."
+        ),
+    }
+
+    if cwd:
+        if not os.path.exists(cwd):
+            diagnostics["cwd_exists"] = False
+            diagnostics["error_type"] = "missing cwd"
+            diagnostics["error_msg"] = f"Current working directory does not exist: {cwd}"
+            return diagnostics
+        if not os.path.isdir(cwd):
+            diagnostics["cwd_is_dir"] = False
+            diagnostics["error_type"] = "cwd is not a directory"
+            diagnostics["error_msg"] = f"Current working directory is not a directory: {cwd}"
+            return diagnostics
+
+    exe = command[0] if command else None
+    if exe:
+        resolved_exe = _resolve_executable(cwd, exe)
+        diagnostics["resolved_executable"] = resolved_exe
+        if not resolved_exe:
+            diagnostics["executable_exists"] = False
+            if "venv" in exe or "pytest" in exe:
+                diagnostics["error_type"] = "missing runtime wrapper"
+                diagnostics["error_msg"] = (
+                    "Virtual environment runtime wrapper/executable not found or not "
+                    f"executable: {exe}"
+                )
+            else:
+                diagnostics["error_type"] = "missing executable"
+                diagnostics["error_msg"] = f"Executable not found in PATH or CWD: {exe}"
+            return diagnostics
+
+    # Check common shell availability
+    has_any_shell = False
+    for shell_path in ("/bin/sh", "/bin/zsh", "/bin/bash"):
+        if os.path.exists(shell_path) and os.access(shell_path, os.X_OK):
+            has_any_shell = True
+            break
+    if not has_any_shell:
+        diagnostics["shell_exists"] = False
+        diagnostics["error_type"] = "missing shell"
+        diagnostics["error_msg"] = (
+            "No standard system shell (/bin/sh, /bin/zsh, /bin/bash) is "
+            "available or executable."
+        )
+        return diagnostics
+
+    return diagnostics
+
+
+def probe_terminal_spawn(
+    cwd: str | None = None,
+    command: list[str] | None = None,
+) -> dict[str, Any]:
+    """Proactively probe command spawning to detect launcher health (#556)."""
+    probe_cmd = command or default_terminal_probe_command()
+    diag = diagnose_terminal_failure(cwd, probe_cmd)
+    if diag["error_type"] != "session launcher failure":
+        return {
+            "healthy": False,
+            "error_type": diag["error_type"],
+            "error_msg": diag["error_msg"],
+            "cwd": cwd,
+            "command": probe_cmd,
+            "diagnostics": diag,
+        }
+
+    try:
+        proc = subprocess.run(
+            probe_cmd,
+            capture_output=True,
+            text=True,
+            cwd=cwd,
+            timeout=5,
+        )
+        if proc.returncode == 0:
+            return {
+                "healthy": True,
+                "error_type": None,
+                "error_msg": "",
+                "cwd": cwd,
+                "command": probe_cmd,
+                "diagnostics": diag,
+            }
+        # Non-zero status still proves the launcher spawned the process.
+        return {
+            "healthy": True,
+            "error_type": None,
+            "error_msg": "",
+            "cwd": cwd,
+            "command": probe_cmd,
+            "exit_code": proc.returncode,
+            "diagnostics": diag,
+        }
+    except FileNotFoundError:
+        return {
+            "healthy": False,
+            "error_type": diag["error_type"],
+            "error_msg": diag["error_msg"],
+            "cwd": cwd,
+            "command": probe_cmd,
+            "diagnostics": diag,
+        }
+    except subprocess.TimeoutExpired as exc:
+        return {
+            "healthy": False,
+            "error_type": "probe timeout",
+            "error_msg": f"Subprocess probe timed out after {exc.timeout} seconds.",
+            "cwd": cwd,
+            "command": probe_cmd,
+            "diagnostics": diag,
+        }
+    except Exception as exc:
+        return {
+            "healthy": False,
+            "error_type": diag["error_type"],
+            "error_msg": f"Subprocess spawn failed with exception: {exc}",
+            "cwd": cwd,
+            "command": probe_cmd,
+            "diagnostics": diag,
+        }

post_merge_validation.py

@@ -0,0 +1,222 @@
+"""Canonical post-merge (moot) validation outcome and wording gate (#529).
+
+When a PR is already merged or closed *before* a reviewer submits their
+verdict, an ordinary "approve" is misleading: the review never gated the
+merge, so a normal active approval overstates controller confidence. The
+sanctioned outcome for that case is a **post-merge moot validation** — the
+reviewer records what validation found, but classifies it as moot rather than
+an active approval.
+
+This module defines the four canonical validation distinctions #529 requires
+and enforces the post-merge case:
+
+- ``CLEAN_PASS_OUTCOME`` — clean validation pass on an open, reviewable PR.
+- ``BASELINE_ACCEPTED_OUTCOME`` — validation pass with a baseline-proven
+  unrelated failure (proof handled by :mod:`premerge_baseline_proof`).
+- ``BLOCKED_OUTCOME`` — validation blocked by an unresolved failure.
+- ``POST_MERGE_MOOT_OUTCOME`` — the PR was already merged/closed before review
+  submission; validation is recorded as post-merge moot, not an active
+  approval.
+
+The gate blocks two mistakes:
+
+1. Claiming an *active approval* on a PR that was already merged/closed before
+   review submission (must be recorded as post-merge moot validation instead).
+2. Claiming post-merge moot validation without proof the PR is actually
+   merged/closed (a merged-state field plus a merge commit SHA).
+
+Each outcome maps to a durable ``validation:*`` process-state label so PRs and
+issues carry the distinction (#529 acceptance criterion).
+"""
+
+from __future__ import annotations
+
+import re
+from typing import Any
+
+CLEAN_PASS_OUTCOME = "clean validation pass"
+BASELINE_ACCEPTED_OUTCOME = "validation pass with baseline-proven unrelated failure"
+BLOCKED_OUTCOME = "validation blocked by unresolved failure"
+POST_MERGE_MOOT_OUTCOME = "post-merge moot validation"
+
+# Canonical validation status label a reviewer writes in the report body for the
+# post-merge case; kept in sync with validation_status_vocabulary.
+POST_MERGE_MOOT_STATUS = "post-merge moot validation"
+
+# Durable process-state labels (registered in issue_workflow_labels).
+LABEL_CLEAN_PASS = "validation:clean-pass"
+LABEL_BASELINE_ACCEPTED = "validation:baseline-accepted"
+LABEL_BLOCKED = "validation:blocked"
+LABEL_POST_MERGE_MOOT = "validation:post-merge-moot"
+
+_OUTCOME_TO_LABEL: dict[str, str] = {
+    CLEAN_PASS_OUTCOME: LABEL_CLEAN_PASS,
+    BASELINE_ACCEPTED_OUTCOME: LABEL_BASELINE_ACCEPTED,
+    BLOCKED_OUTCOME: LABEL_BLOCKED,
+    POST_MERGE_MOOT_OUTCOME: LABEL_POST_MERGE_MOOT,
+}
+
+# The PR was already merged/closed before the review was submitted.
+_MERGED_BEFORE_REVIEW_RE = re.compile(
+    r"(?:already[- ]merged"
+    r"|merged\s+before\s+review"
+    r"|closed\s+before\s+review"
+    r"|pr\s+(?:is|was)\s+(?:already\s+)?(?:merged|closed)"
+    r"|pr\s+state\s*[:=]\s*(?:merged|closed)"
+    r"|merged\s*/\s*closed)",
+    re.IGNORECASE,
+)
+# An active approval verdict is being claimed.
+_ACTIVE_APPROVAL_RE = re.compile(
+    r"(?:review\s+decision\s*[:=]\s*approve"
+    r"|submitted\s+['\"]?approve['\"]?"
+    r"|active\s+approval"
+    r"|approving\s+the\s+pr"
+    r"|posting\s+an?\s+approval)",
+    re.IGNORECASE,
+)
+# The sanctioned post-merge moot validation wording.
+_POST_MERGE_MOOT_RE = re.compile(
+    r"post[- ]merge\s+(?:moot\s+)?validation"
+    r"|post[- ]merge\s+moot"
+    r"|moot\s+validation",
+    re.IGNORECASE,
+)
+# Proof the PR is genuinely merged/closed.
+_MERGED_STATE_PROOF_RE = re.compile(
+    r"(?:pr\s+state\s*[:=]\s*(?:merged|closed)"
+    r"|merged_at\s*[:=]\s*\S"
+    r"|closed_at\s*[:=]\s*\S"
+    r"|state\s*[:=]\s*(?:merged|closed))",
+    re.IGNORECASE,
+)
+_MERGE_COMMIT_SHA_RE = re.compile(
+    r"merge\s+commit(?:\s+sha)?\s*[:=]\s*[0-9a-f]{7,40}",
+    re.IGNORECASE,
+)
+
+
+POST_MERGE_VALIDATION_TEMPLATE = (
+    "Validation status: post-merge moot validation\n"
+    "PR state: merged\n"
+    "Merge commit sha: <40-hex merge commit>\n"
+    "Validation finding: <what the validation run showed, for the record>\n"
+    "Note: PR merged/closed before review submission; recorded as post-merge "
+    "moot validation, not an active approval."
+)
+
+
+def process_state_label(outcome: str) -> str | None:
+    """Return the durable ``validation:*`` label for a canonical outcome."""
+    return _OUTCOME_TO_LABEL.get(outcome)
+
+
+def assess_post_merge_validation(
+    report_text: str,
+    *,
+    pr_merged_or_closed: bool | None = None,
+) -> dict[str, Any]:
+    """Assess post-merge moot validation wording and proof (#529).
+
+    Args:
+        report_text: The reviewer final report text.
+        pr_merged_or_closed: Optional structured signal that the PR is already
+            merged/closed. When ``True`` it forces the merged-before-review
+            path even if the report text omits the phrasing; proof fields are
+            still required in the report body for durability.
+
+    Returns a dict with ``proven``, ``block``, ``outcome``,
+    ``process_state_label``, ``reasons``, ``skipped`` and ``safe_next_action``.
+    Only blocks when the report either claims an active approval on a
+    merged/closed PR, or claims post-merge moot validation without proof.
+    """
+    text = report_text or ""
+
+    merged_signal = bool(_MERGED_BEFORE_REVIEW_RE.search(text)) or bool(
+        pr_merged_or_closed
+    )
+    active_approval = bool(_ACTIVE_APPROVAL_RE.search(text))
+    moot_wording = bool(_POST_MERGE_MOOT_RE.search(text))
+
+    # Nothing about merged-state or moot validation — not applicable here.
+    if not merged_signal and not moot_wording:
+        return {
+            "proven": True,
+            "block": False,
+            "outcome": None,
+            "process_state_label": None,
+            "reasons": [],
+            "skipped": True,
+            "safe_next_action": "",
+        }
+
+    # An active approval on a PR already merged/closed before review, without
+    # the sanctioned moot wording, overstates confidence.
+    if merged_signal and active_approval and not moot_wording:
+        return {
+            "proven": False,
+            "block": True,
+            "outcome": POST_MERGE_MOOT_OUTCOME,
+            "process_state_label": LABEL_POST_MERGE_MOOT,
+            "reasons": [
+                "PR was already merged/closed before review submission; an "
+                "active approval overstates confidence — record 'post-merge "
+                "moot validation' instead of a normal approval"
+            ],
+            "skipped": False,
+            "safe_next_action": (
+                "classify the outcome as post-merge moot validation (not an "
+                "active approval); cite PR state merged/closed and the merge "
+                "commit SHA. Template:\n" + POST_MERGE_VALIDATION_TEMPLATE
+            ),
+        }
+
+    # Post-merge moot validation claimed — require merged-state + commit proof.
+    if moot_wording:
+        reasons: list[str] = []
+        if not _MERGED_STATE_PROOF_RE.search(text):
+            reasons.append(
+                "post-merge moot validation claimed without merged/closed state "
+                "proof (state: merged/closed, or merged_at/closed_at)"
+            )
+        if not _MERGE_COMMIT_SHA_RE.search(text):
+            reasons.append(
+                "post-merge moot validation claimed without a merge commit SHA"
+            )
+        if reasons:
+            return {
+                "proven": False,
+                "block": True,
+                "outcome": POST_MERGE_MOOT_OUTCOME,
+                "process_state_label": LABEL_POST_MERGE_MOOT,
+                "reasons": reasons,
+                "skipped": False,
+                "safe_next_action": (
+                    "prove the PR is merged/closed: cite PR state and the merge "
+                    "commit SHA. Template:\n" + POST_MERGE_VALIDATION_TEMPLATE
+                ),
+            }
+        return {
+            "proven": True,
+            "block": False,
+            "outcome": POST_MERGE_MOOT_OUTCOME,
+            "process_state_label": LABEL_POST_MERGE_MOOT,
+            "reasons": [],
+            "skipped": False,
+            "safe_next_action": "",
+        }
+
+    # Merged signal present but no approval claim and no moot wording yet —
+    # guide toward the moot outcome without blocking.
+    return {
+        "proven": True,
+        "block": False,
+        "outcome": POST_MERGE_MOOT_OUTCOME,
+        "process_state_label": LABEL_POST_MERGE_MOOT,
+        "reasons": [],
+        "skipped": False,
+        "safe_next_action": (
+            "PR appears merged/closed; if submitting a verdict, record "
+            "post-merge moot validation rather than an active approval"
+        ),
+    }

remote_repo_guard.py

@@ -16,11 +16,35 @@ or the local remote URL is unavailable (best-effort corroboration only).
 
 from __future__ import annotations
 
+import re
+
 REMEDIATION = (
-    "Pass explicit org= and repo= matching the local git remote, "
-    "e.g. org=Scaled-Tech-Consulting repo=Gitea-Tools."
+    "Pass explicit org= and repo= matching the local git remote on tools that "
+    "accept those parameters (including mcp_get_control_plane_guide), "
+    "e.g. org=Scaled-Tech-Consulting repo=Gitea-Tools. "
+    "Do not pass org/repo to tools whose schema does not list them."
 )
 
+# https://host/org/repo.git  or  git@host:org/repo.git
+_REMOTE_URL_SLUG_RE = re.compile(
+    r"(?:[:/])(?P<org>[^/]+)/(?P<repo>[^/]+?)(?:\.git)?/*$"
+)
+
+
+def parse_org_repo_from_remote_url(remote_url: str | None) -> tuple[str, str] | None:
+    """Best-effort parse of org/repo from a git remote URL."""
+    url = (remote_url or "").strip()
+    if not url:
+        return None
+    match = _REMOTE_URL_SLUG_RE.search(url)
+    if not match:
+        return None
+    org = (match.group("org") or "").strip()
+    repo = (match.group("repo") or "").strip()
+    if not org or not repo:
+        return None
+    return org, repo
+
 
 def assess_remote_repo_match(
     *,

review_merge_state_machine.py

@@ -93,8 +93,16 @@ def assess_workflow_blockers(
     capability_blocked: bool = False,
     mcp_reconnect_failed: bool = False,
     stale_capability_state: bool = False,
+    live_namespace_broken: bool = False,
 ) -> dict[str, Any]:
-    """Return hard blockers that forbid all PR queue work (#290 AC3)."""
+    """Return hard blockers that forbid all PR queue work (#290 AC3).
+
+    ``live_namespace_broken`` fails the merge/review path closed when the live
+    MCP namespace call path is unusable (e.g. ``client is closing: EOF``) even
+    though the tool is registered in FastMCP (#543 AC5). Feed it the
+    ``blocks_merge_workflow`` verdict from
+    ``mcp_namespace_health.classify_namespace_probe``.
+    """
     reasons: list[str] = []
     if infra_stop:
         reasons.append("infra_stop is active; PR selection/review/merge is forbidden")
@@ -104,6 +112,12 @@ def assess_workflow_blockers(
         reasons.append("MCP reconnect failed; stale session state cannot be reused")
     if stale_capability_state:
         reasons.append("stale MCP capability state detected after reconnect failure")
+    if live_namespace_broken:
+        reasons.append(
+            "live MCP namespace call path is broken (registered in FastMCP but "
+            "not callable through the namespace); repair the namespace before "
+            "review/merge"
+        )
     return {
         "block": bool(reasons),
         "reasons": reasons,
@@ -118,16 +132,19 @@ def assess_state_advancement(
     state_completion: dict[str, bool] | None,
     *,
     target_state: str,
-    infra_stop: bool = False,
-    capability_blocked: bool = False,
+    **blocker_kwargs,
 ) -> dict[str, Any]:
-    """Fail closed when *target_state* is requested before upstream gates pass."""
+    """Fail closed when *target_state* is requested before upstream gates pass.
+
+    Forwards every blocker flag (``infra_stop``, ``capability_blocked``,
+    ``mcp_reconnect_failed``, ``stale_capability_state``,
+    ``live_namespace_broken``) to :func:`assess_workflow_blockers` so
+    ``can_approve``/``can_merge`` honor the full blocker set, not just
+    infra_stop/capability_blocked (#543 AC5).
+    """
     completion = dict(state_completion or {})
     target = _clean(target_state).upper()
-    blockers = assess_workflow_blockers(
-        infra_stop=infra_stop,
-        capability_blocked=capability_blocked,
-    )
+    blockers = assess_workflow_blockers(**blocker_kwargs)
     reasons = list(blockers["reasons"])
 
     try:

review_proofs.py

@@ -2243,6 +2243,18 @@ HANDOFF_ROLE_FIELDS = {
         ("Linked issue status", ("linked issue status", "linked issue")),
         ("Cleanup status", ("cleanup status", "cleanup")),
     ) + HANDOFF_REVIEW_MUTATION_FIELDS,
+    "merger": (
+        ("Selected PR", ("selected pr",)),
+        ("Pinned reviewed head", ("pinned reviewed head", "pinned head")),
+        ("Active profile", ("active profile",)),
+        ("Role kind", ("role kind",)),
+        ("Merge capability source", ("merge capability source",)),
+        ("Explicit operator authorization", ("explicit operator authorization", "operator authorization", "authorization")),
+        ("Expected head SHA", ("expected head sha", "expected head")),
+        ("Approval at current head", ("approval at current head", "approval")),
+        ("Merge result", ("merge result",)),
+        ("Cleanup status", ("cleanup status", "cleanup")),
+    ) + HANDOFF_REVIEW_MUTATION_FIELDS,
     "author": (
         ("Selected issue", ("selected issue",)),
         ("Issue lock proof", ("issue lock proof", "lock before diff")),
@@ -2417,8 +2429,8 @@ def assess_controller_handoff(report_text, role=None, local_edits=False):
             field for field in required
             if field[0] not in ("Workspace mutations", "Mutations")
         ]
-    if role == "review":
-        # Issue #320: reviewer handoffs use the precise mutation categories
+    if role in ("review", "merger"):
+        # Issue #320: reviewer and merger handoffs use the precise mutation categories
         # in HANDOFF_REVIEW_MUTATION_FIELDS instead of the legacy ambiguous
         # "Workspace mutations" field, which is rejected below.
         required = [
@@ -2431,7 +2443,7 @@ def assess_controller_handoff(report_text, role=None, local_edits=False):
                 "downgraded": True,
                 "missing_fields": [],
                 "reasons": [
-                    "review handoff must not include legacy "
+                    "review or merger handoff must not include legacy "
                     "'Workspace mutations' field; report the precise "
                     "mutation categories instead (issue #320)"
                 ],
@@ -4830,6 +4842,22 @@ RECONCILER_CLOSE_REPORT_FIELDS = (
     "no review/merge confirmation",
 )
 
+RECONCILER_SUPERSESSION_REPORT_FIELDS = (
+    "identity/profile",
+    "supersession close capability proof",
+    "target PR live state",
+    "target PR independent-work proof",
+    "superseding PR merged state",
+    "superseding merge commit SHA",
+    "target branch SHA",
+    "superseding ancestry proof",
+    "canonical close comment",
+    "linked issue status",
+    "PR close result",
+    "issue close result",
+    "no review/merge confirmation",
+)
+
 
 def assess_reconciler_close_gate(
     *,
@@ -4976,6 +5004,157 @@ def assess_reconciler_close_gate(
     }
 
 
+def assess_reconciler_supersession_close_gate(
+    *,
+    target_pr_number: int | None,
+    target_pr_state: str | None,
+    target_pr_mergeable: bool | None,
+    target_independently_required: bool | None,
+    superseding_pr_number: int | None,
+    superseding_pr_state: str | None,
+    superseding_pr_merged: bool,
+    superseding_merge_commit_sha: str | None,
+    superseding_head_sha: str | None,
+    target_branch: str | None,
+    target_branch_sha: str | None,
+    superseding_head_is_ancestor_of_target: bool | None,
+    canonical_comment_valid: bool,
+    canonical_comment_mentions_superseding_pr: bool,
+    canonical_comment_mentions_merge_commit: bool,
+    close_pr_capability: bool,
+    close_issue_capability: bool = False,
+    target_issue_state: str | None = None,
+    issue_satisfied_by_superseding: bool = False,
+) -> dict:
+    """Gate reconciler closure of PRs/issues superseded by a merged PR.
+
+    This is stricter than already-landed cleanup: the target PR may be closed
+    only after a named superseding PR is live-verified merged, its head is on a
+    freshly fetched target branch, the target PR is proven not independently
+    required, and a canonical close comment cites the superseding PR and merge
+    commit.
+    """
+    reasons: list[str] = []
+    if not isinstance(target_pr_number, int) or target_pr_number <= 0:
+        reasons.append("target PR number missing or invalid (#525)")
+    if not isinstance(superseding_pr_number, int) or superseding_pr_number <= 0:
+        reasons.append("superseding PR number missing or invalid (#525)")
+    if target_pr_number and superseding_pr_number and (
+        target_pr_number == superseding_pr_number
+    ):
+        reasons.append("target PR and superseding PR must differ (#525)")
+    if (target_pr_state or "").strip().lower() != "open":
+        reasons.append("target PR must be live-verified open before close (#525)")
+    if target_pr_mergeable is True:
+        reasons.append(
+            "target PR is still mergeable; prove it is superseded before close (#525)"
+        )
+    if target_independently_required is not False:
+        reasons.append(
+            "target PR independent-work proof missing; close requires explicit "
+            "proof that no required work remains (#525)"
+        )
+    if (superseding_pr_state or "").strip().lower() != "closed":
+        reasons.append("superseding PR must be live-verified closed (#525)")
+    if superseding_pr_merged is not True:
+        reasons.append("superseding PR must be live-verified merged (#525)")
+    if not _FULL_SHA.match((superseding_merge_commit_sha or "").strip()):
+        reasons.append("superseding merge commit SHA missing or invalid (#525)")
+    if not _FULL_SHA.match((superseding_head_sha or "").strip()):
+        reasons.append("superseding head SHA missing or invalid (#525)")
+    if not (target_branch or "").strip():
+        reasons.append("target branch missing (#525)")
+    if not _FULL_SHA.match((target_branch_sha or "").strip()):
+        reasons.append("target branch SHA missing or invalid (#525)")
+    if superseding_head_is_ancestor_of_target is None:
+        reasons.append("superseding ancestry proof not checked (#525)")
+    if not canonical_comment_valid:
+        reasons.append("canonical close comment failed validation (#525)")
+    if not canonical_comment_mentions_superseding_pr:
+        reasons.append("canonical comment must cite superseding PR (#525)")
+    if not canonical_comment_mentions_merge_commit:
+        reasons.append("canonical comment must cite merge commit SHA (#525)")
+
+    never_allowed = {
+        "review_allowed": False,
+        "approve_allowed": False,
+        "request_changes_allowed": False,
+        "merge_allowed": False,
+    }
+
+    if reasons:
+        return {
+            "outcome": "GATE_NOT_PROVEN",
+            "pr_close_allowed": False,
+            "issue_close_allowed": False,
+            "reasons": reasons,
+            "required_report_fields": RECONCILER_SUPERSESSION_REPORT_FIELDS,
+            "safe_next_action": (
+                "prove superseding PR state, target branch ancestry, target "
+                "supersession, and canonical comment before closing"
+            ),
+            **never_allowed,
+        }
+
+    if superseding_head_is_ancestor_of_target is False:
+        return {
+            "outcome": "SUPERSEDING_PR_NOT_ON_TARGET",
+            "pr_close_allowed": False,
+            "issue_close_allowed": False,
+            "reasons": [
+                f"superseding PR #{superseding_pr_number} head is not an "
+                f"ancestor of {target_branch}; supersession close denied (#525)"
+            ],
+            "required_report_fields": RECONCILER_SUPERSESSION_REPORT_FIELDS,
+            "safe_next_action": "re-fetch target branch and re-check ancestry",
+            **never_allowed,
+        }
+
+    if close_pr_capability is not True:
+        return {
+            "outcome": "RECOVERY_HANDOFF_REQUIRED",
+            "pr_close_allowed": False,
+            "issue_close_allowed": False,
+            "reasons": [
+                "exact gitea.pr.close capability not proven; produce a "
+                "recovery handoff instead of closing (#525)"
+            ],
+            "required_report_fields": RECONCILER_SUPERSESSION_REPORT_FIELDS,
+            "safe_next_action": (
+                "launch a reconciler profile with gitea.pr.close and replay "
+                "the live-state proof"
+            ),
+            **never_allowed,
+        }
+
+    issue_close_allowed = (
+        (target_issue_state or "").strip().lower() == "open"
+        and issue_satisfied_by_superseding is True
+        and close_issue_capability is True
+    )
+    issue_reasons = []
+    if (target_issue_state or "").strip().lower() == "closed":
+        issue_reasons.append("linked issue already closed; no issue close attempted (#525)")
+    elif target_issue_state and not issue_close_allowed:
+        issue_reasons.append(
+            "issue close requires an open issue satisfied by the superseding "
+            "merged PR and exact gitea.issue.close capability (#525)"
+        )
+
+    return {
+        "outcome": "SUPERSESSION_CLOSE_ALLOWED",
+        "pr_close_allowed": True,
+        "issue_close_allowed": issue_close_allowed,
+        "reasons": issue_reasons,
+        "required_report_fields": RECONCILER_SUPERSESSION_REPORT_FIELDS,
+        "safe_next_action": (
+            "post the canonical comment, close the superseded PR, and close "
+            "the linked issue only when issue_close_allowed is true"
+        ),
+        **never_allowed,
+    }
+
+
 # ---------------------------------------------------------------------------
 # Identity disclosure (#305)
 # ---------------------------------------------------------------------------
@@ -5540,6 +5719,15 @@ def assess_already_landed_classification_report(report_text, **kwargs):
     return _assess(report_text, **kwargs)
 
 
+def assess_conflict_fix_classification_final_report(report_text, **kwargs):
+    """#522: require live PR head re-pin before conflict-fix classification."""
+    from conflict_fix_classification import (
+        assess_conflict_fix_classification_final_report as _assess,
+    )
+
+    return _assess(report_text, **kwargs)
+
+
 def assess_prior_blocker_skip_proof(report_text, **kwargs):
     """#318: require live blocker proof before skipping earlier open PRs."""
     from reviewer_blocker_skip import assess_prior_blocker_skip_proof as _assess

reviewer_handoff_consistency.py

@@ -0,0 +1,186 @@
+"""Reviewer handoff consistency validation (#501).
+
+Detects contradictions between narrative claims and mutation ledger fields in
+reviewer/final-review controller handoffs. Pure validation only — does not post
+comments or mutate Gitea state.
+"""
+
+from __future__ import annotations
+
+import re
+
+_HANDOFF_FIELD_RE = re.compile(
+    r"^\s*[-*]\s*([^:]+):\s*(.*)$",
+    re.MULTILINE | re.IGNORECASE,
+)
+
+_MERGE_NARRATIVE_RE = re.compile(
+    r"\b(?:merged\s+pr\s*#|pr\s+#\d+\s+(?:was\s+)?merged|"
+    r"merge\s+result\s*:\s*merged|successfully\s+merged|"
+    r"terminal\s+mutation\s+budget.{0,80}\bmerge)\b",
+    re.IGNORECASE | re.DOTALL,
+)
+_REVIEW_SUBMIT_BLOCKED_RE = re.compile(
+    r"\b(?:review\s+submission\s+blocked|submit_pr_review\s+(?:failed|blocked)|"
+    r"gitea_submit_pr_review\s+(?:failed|blocked|not\s+(?:attempted|performed))|"
+    r"review\s+not\s+submitted|could\s+not\s+submit\s+review)\b",
+    re.IGNORECASE,
+)
+_FINAL_DECISION_MARKED_RE = re.compile(
+    r"\b(?:gitea_mark_final_review_decision|final\s+review\s+decision\s+marked|"
+    r"server-side\s+final\s+decision\s+marked|marked\s+final\s+review\s+decision)\b",
+    re.IGNORECASE,
+)
+_TERMINAL_BUDGET_CONSUMED_RE = re.compile(
+    r"\b(?:terminal\s+mutation\s+budget\s+(?:already\s+)?consumed|"
+    r"single[- ]terminal\s+mutation\s+(?:already\s+)?consumed|"
+    r"mutation\s+budget\s+exhausted)\b",
+    re.IGNORECASE,
+)
+_LEASE_NARRATIVE_RE = re.compile(
+    r"\b(?:reviewer\s+lease\s+acquired|acquired\s+reviewer\s+pr\s+lease|"
+    r"gitea_acquire_reviewer_pr_lease)\b",
+    re.IGNORECASE,
+)
+_REJECTED_MUTATION_RE = re.compile(
+    r"\b(?:mutation\s+rejected|tool\s+failed\s+closed|blocked\s+before\s+mutation|"
+    r"no\s+server-side\s+state\s+changed)\b",
+    re.IGNORECASE,
+)
+_MERGE_IN_LEDGER_RE = re.compile(r"\bmerge\b", re.IGNORECASE)
+_REVIEW_SUBMITTED_IN_LEDGER_RE = re.compile(
+    r"\b(?:submitted|approve|request_changes|review\s+submitted)\b",
+    re.IGNORECASE,
+)
+_NONE_VALUE_RE = re.compile(r"^\s*(?:none|not\s+attempted|n/a)\s*$", re.IGNORECASE)
+
+_BLOCKED_REVIEW_PROOF_FIELDS = (
+    "tool called",
+    "mutation attempted",
+    "mutation rejected",
+    "no server-side state changed",
+)
+
+
+def render_blocked_review_handoff_template() -> str:
+    """Return a corrected handoff template for blocked review submissions."""
+    return """## Blocked Review Submission Handoff
+
+- Tool called: gitea_submit_pr_review
+- Mutation attempted: yes
+- Mutation rejected: yes
+- No server-side state changed: confirmed
+- Proof/source: <paste exact tool error or gate reason>
+- Prior terminal mutation that consumed budget: <name exact prior mutation or none>
+- Review decision (local intent): <approve | request_changes | comment only>
+- Server-side final decision marked: <yes with tool proof | no>
+- Gitea review submitted: no
+- Gitea review blocked because: <exact gate/error>
+- Review mutations: none (submission blocked)
+- MCP/Gitea mutations: <list only mutations that actually occurred>
+- Safe next action: rewrite handoff with consistent ledger before posting
+"""
+
+
+def _handoff_fields(text: str | None) -> dict[str, str]:
+    fields: dict[str, str] = {}
+    for match in _HANDOFF_FIELD_RE.finditer(text or ""):
+        key = match.group(1).strip().lower()
+        value = match.group(2).strip()
+        fields[key] = value
+    return fields
+
+
+def _is_none_value(value: str | None) -> bool:
+    return bool(_NONE_VALUE_RE.match(value or ""))
+
+
+def _ledger_mentions_merge(*values: str | None) -> bool:
+    blob = " ".join(v for v in values if v)
+    return bool(blob) and bool(_MERGE_IN_LEDGER_RE.search(blob))
+
+
+def _ledger_mentions_review_submission(*values: str | None) -> bool:
+    blob = " ".join(v for v in values if v)
+    return bool(blob) and bool(_REVIEW_SUBMITTED_IN_LEDGER_RE.search(blob))
+
+
+def assess_reviewer_handoff_consistency(report_text: str | None) -> dict:
+    """Validate reviewer handoff narrative against mutation ledger fields."""
+    text = report_text or ""
+    fields = _handoff_fields(text)
+    reasons: list[str] = []
+
+    review_mutations = fields.get("review mutations", "")
+    merge_mutations = fields.get("merge mutations", "")
+    mcp_mutations = fields.get("mcp/gitea mutations", "")
+    review_decision = fields.get("review decision", "")
+
+    if _MERGE_NARRATIVE_RE.search(text) and not _ledger_mentions_merge(
+        merge_mutations, mcp_mutations, review_mutations
+    ):
+        reasons.append(
+            "narrative claims a merge occurred but mutation ledger omits merge"
+        )
+
+    if _TERMINAL_BUDGET_CONSUMED_RE.search(text):
+        if _ledger_mentions_merge(merge_mutations, mcp_mutations):
+            pass
+        elif _LEASE_NARRATIVE_RE.search(text) and not _ledger_mentions_merge(
+            merge_mutations, mcp_mutations
+        ):
+            reasons.append(
+                "terminal mutation budget attributed to merge but ledger only "
+                "shows lease or non-merge activity"
+            )
+        elif not _ledger_mentions_merge(merge_mutations, mcp_mutations):
+            reasons.append(
+                "terminal mutation budget consumed claim must identify the "
+                "exact prior mutation in the ledger"
+            )
+
+    if _REVIEW_SUBMIT_BLOCKED_RE.search(text) and _FINAL_DECISION_MARKED_RE.search(text):
+        reasons.append(
+            "handoff claims review submission blocked but also claims "
+            "server-side final decision was marked"
+        )
+
+    lease_claimed = _LEASE_NARRATIVE_RE.search(text) or (
+        not _is_none_value(mcp_mutations)
+        and "lease" in mcp_mutations.lower()
+    )
+    if lease_claimed and _is_none_value(review_decision):
+        reasons.append(
+            "reviewer lease acquired but Review decision field is missing or none"
+        )
+
+    if _REVIEW_SUBMIT_BLOCKED_RE.search(text) or _REJECTED_MUTATION_RE.search(text):
+        lower = text.lower()
+        missing_proof = [
+            field
+            for field in _BLOCKED_REVIEW_PROOF_FIELDS
+            if field not in lower
+        ]
+        if missing_proof:
+            reasons.append(
+                "blocked/rejected mutation claim missing proof fields: "
+                + ", ".join(missing_proof)
+            )
+
+    if (
+        _FINAL_DECISION_MARKED_RE.search(text)
+        and _is_none_value(review_mutations)
+        and not _ledger_mentions_review_submission(mcp_mutations)
+        and not _REVIEW_SUBMIT_BLOCKED_RE.search(text)
+    ):
+        reasons.append(
+            "final review decision marked but Review mutations ledger is empty"
+        )
+
+    proven = not reasons
+    return {
+        "proven": proven,
+        "block": not proven,
+        "reasons": reasons,
+        "fields": fields,
+    }

reviewer_pr_lease.py

@@ -190,18 +190,28 @@ def find_active_reviewer_lease(
     pr_number: int,
     now: datetime | None = None,
 ) -> dict[str, Any] | None:
-    """Newest non-terminal, unexpired lease for *pr_number*."""
+    """Return the newest unexpired non-terminal lease for *pr_number*.
+
+    Append-only lease markers form a ledger: the **newest** marker is
+    authoritative. A later terminal phase (``released`` / ``done`` /
+    ``blocked``) ends the lease even when older ``claimed`` markers remain
+    on the thread (#577). Skipping only terminal markers and walking older
+    claims incorrectly re-arms a lease after a successful release.
+    """
     now = now or datetime.now(timezone.utc)
-    for lease in reversed(_lease_entries(comments, pr_number=pr_number)):
-        phase = (lease.get("phase") or "").strip().lower()
-        if phase in _TERMINAL_PHASES:
-            continue
-        if _lease_expired(lease, now=now):
-            continue
-        if phase in _ACTIVE_PHASES or phase:
-            lease = dict(lease)
-            lease["freshness"] = classify_lease_freshness(lease, now=now)
-            return lease
+    entries = list(reversed(_lease_entries(comments, pr_number=pr_number)))
+    if not entries:
+        return None
+    newest = entries[0]
+    phase = (newest.get("phase") or "").strip().lower()
+    if phase in _TERMINAL_PHASES:
+        return None
+    if _lease_expired(newest, now=now):
+        return None
+    if phase in _ACTIVE_PHASES or phase:
+        lease = dict(newest)
+        lease["freshness"] = classify_lease_freshness(lease, now=now)
+        return lease
     return None
 
 
@@ -512,4 +522,241 @@ def assess_lease_inventory(
         "active_review_leases": active,
         "stale_review_leases": stale,
         "reclaimable_review_leases": reclaimable,
-    }
+    }
+
+# Canonical next-action vocabulary for reviewer lease handoff (#599).
+NEXT_ACTION_ACQUIRE = "acquire"
+NEXT_ACTION_WAIT = "wait"
+NEXT_ACTION_RESUME_EXACT_OWNER_SESSION = "resume_exact_owner_session"
+NEXT_ACTION_RELEASE_EXPIRED_LEASE = "release_expired_lease"
+NEXT_ACTION_OPERATOR_AUTHORIZED_CLEANUP = "operator_authorized_cleanup"
+NEXT_ACTION_REPAIR_WORKTREE_BINDING = "repair_worktree_binding"
+
+_HANDOFF_CLASSIFICATIONS = frozenset({
+    "no_lease",
+    "own_active",
+    "own_expired",
+    "foreign_active",
+    "foreign_reclaimable",
+    "foreign_expired",
+    "instructed_lease_missing_with_replacement",
+    "worktree_binding_mismatch",
+})
+
+
+def _norm_path(value: str | None) -> str:
+    text = (value or "").strip()
+    if not text:
+        return ""
+    return os.path.normpath(text.rstrip("/"))
+
+
+def diagnose_reviewer_pr_lease_handoff(
+    comments: list[dict],
+    *,
+    pr_number: int,
+    current_session_id: str | None,
+    current_reviewer_identity: str | None,
+    proposed_worktree: str | None = None,
+    env_bound_worktree: str | None = None,
+    instructed_session_id: str | None = None,
+    instructed_comment_id: int | None = None,
+    now: datetime | None = None,
+) -> dict[str, Any]:
+    """Classify open-PR reviewer lease handoff and emit a canonical next action (#599).
+
+    Read-only diagnosis. Never steals, releases, or adopts a foreign lease.
+    Fail-closed acquisition rules for active foreign leases remain intact.
+
+    Returns a structured diagnosis with:
+    - classification
+    - next_action (one of wait / resume_exact_owner_session /
+      release_expired_lease / operator_authorized_cleanup /
+      repair_worktree_binding / acquire)
+    - active_lease identity fields when present
+    - worktree_binding match result
+    - instructed-lease mismatch flags
+    """
+    now = now or datetime.now(timezone.utc)
+    session_id = (current_session_id or "").strip()
+    identity = (current_reviewer_identity or "").strip()
+    instructed_sid = (instructed_session_id or "").strip()
+    reasons: list[str] = []
+
+    active = find_active_reviewer_lease(comments, pr_number=pr_number, now=now)
+    session_lease = get_session_lease()
+
+    # Worktree binding: env-bound vs proposed vs active lease worktree.
+    env_wt = _norm_path(env_bound_worktree)
+    prop_wt = _norm_path(proposed_worktree)
+    lease_wt = _norm_path((active or {}).get("worktree") if active else None)
+    binding_mismatch = False
+    binding_details: dict[str, Any] = {
+        "env_bound_worktree": env_bound_worktree or None,
+        "proposed_worktree": proposed_worktree or None,
+        "lease_worktree": (active or {}).get("worktree") if active else None,
+        "match": True,
+    }
+    paths = [p for p in (env_wt, prop_wt, lease_wt) if p]
+    if len(paths) >= 2 and len(set(paths)) > 1:
+        binding_mismatch = True
+        binding_details["match"] = False
+        reasons.append(
+            "worktree binding mismatch: env/proposed/lease worktree paths disagree"
+        )
+
+    # Instructed lease gone while a different lease is active (PR #592-style).
+    instructed_missing_with_replacement = False
+    if instructed_sid or instructed_comment_id is not None:
+        if not active:
+            reasons.append(
+                "instructed lease is gone and no active replacement lease remains"
+            )
+        else:
+            owner = (active.get("session_id") or "").strip()
+            cid = active.get("comment_id")
+            sid_mismatch = bool(instructed_sid and owner and owner != instructed_sid)
+            cid_mismatch = (
+                instructed_comment_id is not None
+                and cid is not None
+                and int(cid) != int(instructed_comment_id)
+            )
+            if sid_mismatch or cid_mismatch:
+                instructed_missing_with_replacement = True
+                reasons.append(
+                    "instructed lease is gone; a different active lease replaced it "
+                    f"(active session_id={owner}, comment_id={cid})"
+                )
+
+    # Classification + next_action.
+    classification = "no_lease"
+    next_action = NEXT_ACTION_ACQUIRE
+
+    if active:
+        owner = (active.get("session_id") or "").strip()
+        freshness = active.get("freshness") or classify_lease_freshness(
+            active, now=now
+        )
+        owner_identity = (active.get("reviewer_identity") or "").strip()
+        is_own = bool(session_id and owner and owner == session_id)
+        # Same identity alone is NOT ownership for resume; session_id must match.
+        same_identity = bool(
+            identity and owner_identity and identity == owner_identity
+        )
+
+        if is_own and freshness in {"active", "stale_warning"}:
+            classification = "own_active"
+            next_action = NEXT_ACTION_RESUME_EXACT_OWNER_SESSION
+        elif is_own and freshness in {"reclaimable", "expired"}:
+            classification = "own_expired"
+            next_action = NEXT_ACTION_RELEASE_EXPIRED_LEASE
+            reasons.append(
+                f"own lease freshness is '{freshness}'; release via "
+                "gitea_release_reviewer_pr_lease then re-acquire"
+            )
+        elif not is_own and freshness in {"active", "stale_warning"}:
+            classification = "foreign_active"
+            next_action = NEXT_ACTION_WAIT
+            reasons.append(
+                f"foreign active reviewer lease (session_id={owner}, "
+                f"phase={active.get('phase')}, freshness={freshness}); "
+                "do not submit; do not steal"
+            )
+            if same_identity:
+                reasons.append(
+                    "lease identity matches current reviewer but session_id differs; "
+                    "resume only from the exact owner session_id or wait"
+                )
+        elif not is_own and freshness == "reclaimable":
+            classification = "foreign_reclaimable"
+            next_action = NEXT_ACTION_RELEASE_EXPIRED_LEASE
+            reasons.append(
+                f"foreign reclaimable lease (session_id={owner}); clear only via "
+                "sanctioned gitea_release_reviewer_pr_lease when reclaimable"
+            )
+        elif not is_own and freshness == "expired":
+            classification = "foreign_expired"
+            next_action = NEXT_ACTION_RELEASE_EXPIRED_LEASE
+            reasons.append(
+                f"foreign expired lease (session_id={owner}); use sanctioned release"
+            )
+        else:
+            classification = "foreign_active"
+            next_action = NEXT_ACTION_WAIT
+            reasons.append(
+                f"unclassified active lease state (session_id={owner}, "
+                f"freshness={freshness}); wait fail-closed"
+            )
+
+        if instructed_missing_with_replacement and classification.startswith(
+            "foreign"
+        ):
+            classification = "instructed_lease_missing_with_replacement"
+            # Foreign active still means wait; reclaimable still release.
+            if next_action == NEXT_ACTION_WAIT:
+                reasons.append(
+                    "replacement foreign lease is active — wait; "
+                    "operator_authorized_cleanup only with explicit operator authority"
+                )
+    else:
+        classification = "no_lease"
+        next_action = NEXT_ACTION_ACQUIRE
+        reasons.append("no active reviewer lease; acquire via gitea_acquire_reviewer_pr_lease")
+
+    # Binding mismatch is a first-class blocker before submit, but does not
+    # erase foreign-lease wait/release guidance. Override next_action only when
+    # the session would otherwise be free to acquire or resume (submit path).
+    if binding_mismatch:
+        if next_action in {
+            NEXT_ACTION_ACQUIRE,
+            NEXT_ACTION_RESUME_EXACT_OWNER_SESSION,
+        }:
+            classification = "worktree_binding_mismatch"
+            next_action = NEXT_ACTION_REPAIR_WORKTREE_BINDING
+        else:
+            reasons.append(
+                "also repair worktree binding before submit "
+                f"(next_action remains {next_action})"
+            )
+
+    lease_summary = None
+    if active:
+        lease_summary = {
+            "comment_id": active.get("comment_id"),
+            "session_id": active.get("session_id"),
+            "phase": active.get("phase"),
+            "candidate_head": active.get("candidate_head"),
+            "expires_at": active.get("expires_at"),
+            "last_activity": active.get("last_activity"),
+            "freshness": active.get("freshness")
+            or classify_lease_freshness(active, now=now),
+            "reviewer_identity": active.get("reviewer_identity"),
+            "profile": active.get("profile"),
+            "worktree": active.get("worktree"),
+            "blocker": active.get("blocker"),
+        }
+
+    return {
+        "pr_number": pr_number,
+        "classification": classification,
+        "next_action": next_action,
+        "active_lease": lease_summary,
+        "session_lease": session_lease,
+        "worktree_binding": binding_details,
+        "instructed_session_id": instructed_session_id,
+        "instructed_comment_id": instructed_comment_id,
+        "instructed_lease_missing_with_replacement": instructed_missing_with_replacement,
+        "mutation_allowed": (
+            next_action == NEXT_ACTION_RESUME_EXACT_OWNER_SESSION
+            and not binding_mismatch
+            and bool(session_lease)
+        ),
+        "reasons": reasons,
+        "forbidden": [
+            "manual lock deletion",
+            "raw API bypass",
+            "mtime manipulation",
+            "direct _SESSION_LEASE seeding",
+            "silent foreign lease steal",
+        ],
+    }

role_session_router.py

@@ -55,7 +55,6 @@ def skip_python_scan_walk_root(project_root: str, walk_root: str) -> bool:
 
 REVIEWER_TASKS = frozenset({
     "review_pr",
-    "merge_pr",
     "blind_pr_queue_review",
     "pr_queue_cleanup",
     "pr-queue-cleanup",
@@ -63,6 +62,10 @@ REVIEWER_TASKS = frozenset({
     "approve_pr",
 })
 
+MERGER_TASKS = frozenset({
+    "merge_pr",
+})
+
 AUTHOR_TASKS = frozenset({
     "create_issue",
     "comment_issue",
@@ -80,6 +83,7 @@ AUTHOR_TASKS = frozenset({
 })
 
 RECONCILER_TASKS = frozenset({
+    "cleanup_merged_pr_branch",
     "reconcile_already_landed_pr",
     "reconcile_already_landed",
     "reconcile-landed-pr",
@@ -97,7 +101,7 @@ TASK_REQUIRED_ROLE = {
     "address_pr_change_requests": "author",
     "delete_branch": "author",
     "review_pr": "reviewer",
-    "merge_pr": "reviewer",
+    "merge_pr": "merger",
     "blind_pr_queue_review": "reviewer",
     "pr_queue_cleanup": "reviewer",
     "pr-queue-cleanup": "reviewer",
@@ -109,9 +113,13 @@ TASK_REQUIRED_ROLE = {
     "reconcile_already_landed_pr": "reconciler",
     "reconcile_already_landed": "reconciler",
     "reconcile-landed-pr": "reconciler",
+    "cleanup_merged_pr_branch": "reconciler",
     # #309: reconciler tasks close already-landed PRs/issues only.
     "reconcile_close_landed_pr": "reconciler",
     "reconcile_close_landed_issue": "reconciler",
+    "reconcile_close_superseded_pr": "reconciler",
+    "reconcile_close_satisfied_issue": "reconciler",
+    "reconcile_create_followup_issue": "reconciler",
 }
 
 WRONG_ROLE_REVIEWER_MSG = (
@@ -123,6 +131,10 @@ WRONG_ROLE_RECONCILER_MSG = (
     "MCP namespace/profile with exact close capability."
 )
 
+WRONG_ROLE_MERGER_MSG = (
+    "Wrong role/session for merger task. Launch merger MCP namespace."
+)
+
 _session_last_route: dict | None = None
 
 
@@ -238,6 +250,25 @@ def route_task_session(
         _record_route(result)
         return result
 
+    if required_role == "merger":
+        result = {
+            "task_type": task_type,
+            "required_role": required_role,
+            "active_role": active_role_kind,
+            "active_profile": active_profile,
+            "route_result": ROUTE_WRONG_ROLE,
+            "downstream_allowed": False,
+            "reasons": [
+                WRONG_ROLE_MERGER_MSG,
+                "Merger tasks cannot run in author or reviewer sessions.",
+            ],
+            "message": WRONG_ROLE_MERGER_MSG,
+            "runtime_switching_supported": runtime_switching_supported,
+            "profile_switch_blocked": not runtime_switching_supported,
+        }
+        _record_route(result)
+        return result
+
     if required_role == "author":
         route = ROUTE_TO_AUTHOR
         message = (
@@ -406,4 +437,4 @@ def assess_infra_stop(project_root: str | None = None) -> dict:
 
 def check_mid_merge(project_root: str | None = None) -> bool:
     """Return True if the repository is mid-merge, mid-rebase, or has conflict markers."""
-    return assess_infra_stop(project_root)["infra_stop"]
+    return assess_infra_stop(project_root)["infra_stop"]

scripts/ci-webui-check

@@ -0,0 +1,53 @@
+#!/usr/bin/env bash
+# Path-filtered CI gate for the internal web UI (#436).
+# Runs the hermetic web UI unittest suite when a change touches UI surfaces.
+set -euo pipefail
+
+script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+repo_root="$(cd "$script_dir/.." && pwd)"
+cd "$repo_root"
+
+if [[ "${WEBUI_CI_FORCE:-}" == "1" ]]; then
+  exec "$script_dir/test-webui"
+fi
+
+base_ref="${WEBUI_CI_BASE_REF:-}"
+if [[ -z "$base_ref" ]]; then
+  if git rev-parse --verify prgs/master >/dev/null 2>&1; then
+    base_ref="$(git merge-base HEAD prgs/master 2>/dev/null || true)"
+  fi
+  if [[ -z "$base_ref" ]]; then
+    base_ref="${GITHUB_BASE_REF:-${CHANGE_TARGET:-master}}"
+    if git rev-parse --verify "origin/$base_ref" >/dev/null 2>&1; then
+      base_ref="$(git merge-base HEAD "origin/$base_ref")"
+    elif git rev-parse --verify "$base_ref" >/dev/null 2>&1; then
+      base_ref="$(git merge-base HEAD "$base_ref")"
+    else
+      base_ref="HEAD~1"
+    fi
+  fi
+fi
+
+changed="$(git diff --name-only "$base_ref" HEAD 2>/dev/null || true)"
+if [[ -z "$changed" ]]; then
+  echo "ci-webui-check: no changed files vs $base_ref; skipping web UI suite"
+  exit 0
+fi
+
+python_bin="${WEBUI_TEST_PYTHON:-python3}"
+if [[ -x "$repo_root/venv/bin/python" ]]; then
+  python_bin="$repo_root/venv/bin/python"
+fi
+
+if printf '%s\n' "$changed" | "$python_bin" -c "
+import sys
+from webui.ci_paths import should_run_webui_ci
+paths = [line.strip() for line in sys.stdin if line.strip()]
+raise SystemExit(0 if should_run_webui_ci(paths) else 1)
+"; then
+  echo "ci-webui-check: web UI surface changed; running suite"
+  exec "$script_dir/test-webui"
+fi
+
+echo "ci-webui-check: no web UI paths in diff; skipping suite"
+exit 0

scripts/install-codex-workflow-skill.sh

@@ -0,0 +1,82 @@
+#!/usr/bin/env bash
+# Install canonical Gitea workflow skill into Codex skills dir (#551).
+# Symlinks the in-repo skills/llm-project-workflow package under the names
+# gitea-workflow, llm-project-workflow, and git-pr-workflows.
+set -euo pipefail
+
+usage() {
+  cat <<'EOF'
+usage: scripts/install-codex-workflow-skill.sh [--dry-run] [--skills-dir DIR]
+
+Symlink the portable skills/llm-project-workflow package into the Codex
+skills directory under the canonical names:
+  gitea-workflow
+  llm-project-workflow
+  git-pr-workflows
+
+Defaults:
+  skills dir: $CODEX_HOME/skills or ~/.codex/skills
+  source:     <repo>/skills/llm-project-workflow
+EOF
+}
+
+dry_run=0
+skills_dir=""
+while [[ "${1:-}" == --* ]]; do
+  case "$1" in
+    --dry-run) dry_run=1 ;;
+    --skills-dir)
+      shift
+      skills_dir="${1:-}"
+      ;;
+    --help|-h) usage; exit 0 ;;
+    *) usage >&2; exit 2 ;;
+  esac
+  shift
+done
+
+script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+repo_root="$(cd "$script_dir/.." && pwd)"
+source_skill="$repo_root/skills/llm-project-workflow"
+
+if [[ ! -f "$source_skill/SKILL.md" ]]; then
+  echo "Error: missing $source_skill/SKILL.md" >&2
+  exit 1
+fi
+
+if [[ -z "$skills_dir" ]]; then
+  if [[ -n "${CODEX_HOME:-}" ]]; then
+    skills_dir="$CODEX_HOME/skills"
+  else
+    skills_dir="${HOME}/.codex/skills"
+  fi
+fi
+
+names=(gitea-workflow llm-project-workflow git-pr-workflows)
+
+echo "source: $source_skill"
+echo "codex skills dir: $skills_dir"
+
+if [[ "$dry_run" -eq 0 ]]; then
+  mkdir -p "$skills_dir"
+fi
+
+for name in "${names[@]}"; do
+  target="$skills_dir/$name"
+  if [[ "$dry_run" -eq 1 ]]; then
+    echo "dry-run: ln -sfn $source_skill $target"
+    continue
+  fi
+  if [[ -e "$target" || -L "$target" ]]; then
+    if [[ -L "$target" ]]; then
+      rm -f "$target"
+    else
+      echo "Error: $target exists and is not a symlink (refuse to overwrite)" >&2
+      exit 1
+    fi
+  fi
+  ln -sfn "$source_skill" "$target"
+  echo "linked $target -> $source_skill"
+done
+
+echo "done. Restart Codex so skills reload."

scripts/test-webui

@@ -0,0 +1,14 @@
+#!/usr/bin/env bash
+set -euo pipefail
+script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+repo_root="$(cd "$script_dir/.." && pwd)"
+cd "$repo_root"
+
+python_bin="${WEBUI_TEST_PYTHON:-python3}"
+if [[ -x "$repo_root/venv/bin/python" ]]; then
+  python_bin="$repo_root/venv/bin/python"
+fi
+
+pattern="${WEBUI_TEST_PATTERN:-test_webui_*.py}"
+export WEBUI_TEST_OFFLINE="${WEBUI_TEST_OFFLINE:-1}"
+exec "$python_bin" -m unittest discover -s tests -p "$pattern" "$@"

skills/gitea-workflow/SKILL.md

@@ -0,0 +1,37 @@
+---
+name: gitea-workflow
+description: >-
+  Canonical alias for the Gitea/LLM project workflow router. Same skill as
+  llm-project-workflow. Use at the start of any Gitea-Tools author, review,
+  merge, reconcile, or issue-filing task. Trigger terms: gitea-workflow,
+  llm-project-workflow, git-pr-workflows, gitea, PR review, work-issue.
+---
+
+# gitea-workflow (canonical alias)
+
+This directory is the **stable name** for controller prompts and Codex mounts
+(`gitea-workflow`). The portable implementation lives at:
+
+**[`../llm-project-workflow/SKILL.md`](../llm-project-workflow/SKILL.md)**
+
+## Required action
+
+1. Open and follow `skills/llm-project-workflow/SKILL.md` (router).
+2. Load the matching workflow under `skills/llm-project-workflow/workflows/`.
+3. Do not mutate git/Gitea until the workflow is loaded.
+
+## Multi-runtime names (must resolve identically)
+
+| Name | Role |
+|------|------|
+| `gitea-workflow` | Canonical controller / Codex skill name |
+| `llm-project-workflow` | Portable in-repo skill package |
+| `git-pr-workflows` | Legacy alias |
+
+Install for Codex:
+
+```bash
+./scripts/install-codex-workflow-skill.sh
+```
+
+Preflight via MCP: `mcp_check_workflow_skill_preflight`.

skills/llm-project-workflow/SKILL.md

@@ -6,6 +6,8 @@ description: >-
   report schema. Use at the start of any implementation, review, merge,
   reconciliation, or issue-filing task.
 ---
+> **Also known as:** `gitea-workflow`, `git-pr-workflows` (canonical multi-runtime names — see docs/workflow-skill-mount.md / #551).
+
 
 # LLM Project Workflow Skill
 
@@ -31,12 +33,29 @@ workflow file.
 - A nearby capability does not count.
 - Do not self-review or self-merge.
 - Do not mix modes in one run.
+- **BLOCKED + DIAGNOSE default rule (required):** If any required workflow step, skill, tool, capability, preflight, instruction, profile, worktree binding, or terminal/MCP operation cannot be performed or loaded (including the canonical ones listed in this skill and its loaded workflow), immediately enter `BLOCKED + DIAGNOSE`. Stop before any git or Gitea mutation. Diagnose using the standard template in [`templates/blocked-diagnose-report.md`](templates/blocked-diagnose-report.md). Attempt *only* safe non-mutating recovery. Report using the template. Do not continue, use fallbacks, or treat the missing requirement as harmless.
 - If the required workflow cannot be loaded, stop and produce a recovery handoff
-  only.
+  only (see BLOCKED + DIAGNOSE rule above).
 - Final report must use the schema for the loaded workflow.
 - If a task requires a different mode, stop and produce a handoff for the
   correct workflow.
 
+## Covered blocker classes (BLOCKED + DIAGNOSE must trigger for these)
+
+- missing required skill or workflow guide (e.g. gitea-workflow, llm-project-workflow)
+- broken terminal/tool runner or shell spawn failure
+- MCP capability failure, reset, or deadlock (e.g. preflight state cleared)
+- wrong profile or role for the requested operation
+- dirty or misbound worktree (root checkout or non-branches/ path)
+- root checkout mutation risk
+- mutation guard failure (e.g. branches-only guard)
+- missing required MCP tool/schema or operation
+- stale or inconsistent runtime state (e.g. lease vs actual, dirty state disagreement)
+- unavailable project instructions or checked-in guides
+- any other failure of a step the current workflow or controller prompt declares "required"
+
+**Prohibited unless controller authorizes in writing for this instance:** temp scripts, direct API fallback, MCP internals, direct imports, in-memory state restoration, manual bypasses, or any continuation that hides the blocker. All such cases must be reported as process/tooling defects.
+
 ## Mode isolation
 
 A run that starts in `review-merge-pr` mode may not create process issues,
@@ -167,6 +186,7 @@ Ready-to-copy task prompts live in [`templates/`](templates/):
 - [`reconcile-closed-not-merged-pr.md`](templates/reconcile-closed-not-merged-pr.md)
 - [`worktree-cleanup.md`](templates/worktree-cleanup.md)
 - [`release-tag.md`](templates/release-tag.md)
+- [`canonical-state-comments.md`](templates/canonical-state-comments.md)
 
 ## Adapting to a project
 
@@ -184,6 +204,18 @@ Releases follow SemVer from remote `master` only, after full test suite passes.
 See [`templates/release-tag.md`](templates/release-tag.md) and
 `scripts/release-tag`.
 
+## Proof: missing required workflow steps stop before mutation
+
+- The llm-project-workflow router (this file) and every loaded workflow (work-issue.md, review-merge-pr.md, create-issue.md, etc.) now declare at the top: if required step/skill/tool/capability/instruction/profile/worktree binding/preflight fails, STOP, state BLOCKED, use blocked-diagnose-report.md template, only non-mutating recovery.
+- Controller prompts (start-issue.md, review-pr.md, merge-pr.md, recover-bad-state.md, etc.) and the runbooks (docs/llm-workflow-runbooks.md) explicitly require the same and prohibit unsafe fallbacks.
+- MCP guards (branches-only mutation guard #274, worktree binding #510, preflight purity, role checks, lease gates, gitea_lock_issue, etc.) plus the "prove before mutation" rules ensure that a BLOCKED state prevents git/Gitea mutations.
+- When a skill/guide/tool is missing (e.g. gitea-workflow not mounted for a runtime), the load step in the router/prompt fails the "required" check → BLOCKED + report before any gitea_* call or git command that mutates.
+- Terminal/shell failures, capability deadlocks, wrong profile, dirty/misbound worktree, root risk, guard failures, missing schema, stale state, unavailable instructions all map to the covered blocker classes and trigger the same stop + report.
+- No code path in the canonical workflows allows continuation past a declared required step without the BLOCKED report.
+- See also: Global LLM Worktree Rule, Shell Spawn Hard-Stop Rule, Identity and profile safety, Subagent Tool-Budget Guardrails, and the explicit prohibition list in Universal rules.
+
+Tests / proof docs updated in this change + runbooks. Full relevant test runs (see PR handoff) pass; `git diff --check` clean. Missing-step cases are now documented to fail closed before mutation.
+
 ## Bootstrap Review Path (#557)
 
 Self-hosted MCP workflow fixes can deadlock live review daemons. Do not bypass
@@ -195,4 +227,3 @@ If and only if a controller posts a durable `BOOTSTRAP REVIEW AUTHORIZATION
 `docs/bootstrap-review-path.md`
 
 Otherwise stop with BLOCKED + DIAGNOSE. Bootstrap never weakens normal PR gates.
-

skills/llm-project-workflow/templates/blocked-diagnose-report.md

@@ -0,0 +1,52 @@
+# Blocker Report Template (BLOCKED + DIAGNOSE)
+
+Use this exact structure whenever a required workflow step cannot be performed. Emit this report and stop. Do not proceed to mutation or fallback unless a controller explicitly authorizes an exception in writing.
+
+## Required step
+<Describe the exact step, skill, tool, capability, instruction, profile, or preflight that was required. Include the canonical name and where it is defined (e.g. gitea-workflow skill, specific workflow file, gitea_xxx tool).>
+
+## Observed failure
+<Exact symptom, error message, missing output, guard error, 404, schema error, dirty state, wrong profile, etc. Quote relevant output or tool response.>
+
+## Expected behavior
+<What the workflow/docs/prompts say should happen. Reference the specific rule, template, or preflight that requires this step.>
+
+## Checks performed
+- List every verification attempted (e.g. gitea_whoami, resolve_task_capability, ls skills/, git status, mcp_list_*, worktree list, etc.)
+- Note any discrepancies found (e.g. skill not mounted for this runtime, capability not in profile, cwd not under branches/, etc.)
+
+## Safe recovery attempted
+- Only non-mutating actions (reads, lists, views, status, whoami, resolve, fetch --dry, etc.)
+- List what was tried and the result.
+- If no safe recovery possible, state that explicitly.
+
+## Likely classification
+Choose one or more:
+- missing required skill or workflow guide
+- broken terminal/tool runner
+- MCP capability failure or deadlock
+- wrong profile or role
+- dirty or misbound worktree
+- root checkout mutation risk
+- mutation guard failure
+- missing required MCP tool/schema
+- stale or inconsistent runtime state
+- unavailable project instructions
+- other: <describe>
+
+## Durable fix recommendation
+<Specific, actionable recommendation that fixes the root process/tooling issue (e.g. "Mount gitea-workflow skill for Codex under canonical name in ~/.codex/skills/", "Add preflight in llm-project-workflow/SKILL.md that hard-stops before any gitea_ call if X is unavailable", "Update controller prompt to require BLOCKED + this report before any fallback", "Grant capability in profile config", etc.). Do not suggest temp workarounds.>
+
+## Mutation occurred?
+- No (preferred and required unless explicitly authorized)
+- Yes — describe exactly what was mutated and why it was unavoidable after diagnosis. (This should be rare and will trigger additional review.)
+
+## Single next action
+<One concrete next step for the current actor (e.g. "Controller to approve or reject recovery", "File follow-up issue #XXX for skill mounting", "Re-launch session from clean branches/ worktree after skill installed", "Stop and wait for profile update").>
+
+---
+
+**Rule reminder (do not bypass):**
+If the required step is unavailable, you are BLOCKED. Diagnose using this template. Report. Stop. Unsafe fallbacks (temp scripts, direct API, MCP internals, direct imports, in-memory restoration, manual bypasses) are prohibited unless a controller has authorized them for this specific instance in a prior handoff.
+
+This report must appear in the final output / handoff before any further action.

skills/llm-project-workflow/templates/blocked-review-handoff.md

@@ -0,0 +1,22 @@
+# Blocked review submission handoff
+
+Use when `gitea_submit_pr_review` or the terminal mutation gate blocks review
+submission.
+
+```text
+## Blocked Review Submission Handoff
+
+- Tool called: gitea_submit_pr_review
+- Mutation attempted: yes
+- Mutation rejected: yes
+- No server-side state changed: confirmed
+- Proof/source: <paste exact tool error or gate reason>
+- Prior terminal mutation that consumed budget: <exact prior mutation or none>
+- Review decision (local intent): <approve | request_changes | comment only>
+- Server-side final decision marked: <yes with tool proof | no>
+- Gitea review submitted: no
+- Gitea review blocked because: <exact gate/error>
+- Review mutations: none (submission blocked)
+- MCP/Gitea mutations: <only mutations that actually occurred>
+- Safe next action: rewrite handoff with consistent ledger before posting
+```

skills/llm-project-workflow/templates/canonical-state-comments.md

@@ -0,0 +1,148 @@
+# Template: canonical state comments
+
+Use these only for workflow-changing comments. Casual discussion does not need
+the full template.
+
+## Issue
+
+```text
+## Canonical Issue State
+
+STATE:
+<ready-for-author | in-progress | blocked | PR-open | needs-review | ready-to-merge | merged | closed | superseded>
+
+WHO_IS_NEXT:
+<controller | author | reviewer | merger | reconciler | user>
+
+NEXT_ACTION:
+<specific one-sentence action>
+
+NEXT_PROMPT:
+<paste-ready prompt for the next role>
+
+WHAT_HAPPENED:
+<latest meaningful event>
+
+WHY:
+<decision rationale>
+
+RELATED_DISCUSSION:
+<link/reference or none>
+
+RELATED_PRS:
+- #...
+
+BRANCH:
+<branch or none>
+
+HEAD_SHA:
+<40-character SHA or none>
+
+VALIDATION:
+<tests/proofs or none>
+
+BLOCKERS:
+<blocker and unblock condition, or none>
+
+LAST_UPDATED_BY:
+<identity/profile/date>
+```
+
+## PR
+
+```text
+## Canonical PR State
+
+STATE:
+<needs-review | changes-requested | approved | stale-approval | ready-to-merge | merged | blocked | superseded>
+
+WHO_IS_NEXT:
+<controller | author | reviewer | merger | reconciler | user>
+
+NEXT_ACTION:
+<specific one-sentence action>
+
+NEXT_PROMPT:
+<paste-ready prompt for the next role>
+
+WHAT_HAPPENED:
+<latest meaningful event>
+
+WHY:
+<decision rationale>
+
+ISSUE:
+#...
+
+BASE:
+<branch>
+
+HEAD:
+<branch>
+
+HEAD_SHA:
+<40-character SHA>
+
+REVIEW_STATUS:
+<none | approved | changes-requested | stale | contaminated>
+
+VALIDATION:
+<tests/proofs>
+
+BLOCKERS:
+<blockers or none>
+
+SUPERSEDES:
+<PRs or none>
+
+SUPERSEDED_BY:
+<PR or none>
+
+MERGE_READY:
+<yes/no and why>
+
+LAST_UPDATED_BY:
+<identity/profile/date>
+```
+
+## Discussion
+
+```text
+## Canonical Discussion Summary
+
+STATE:
+<needs-more-discussion | ready-for-issues | issues-created | closed>
+
+WHO_IS_NEXT:
+<controller | author | reviewer | user>
+
+DECISION:
+<what was decided>
+
+WHY:
+<reasoning and tradeoffs>
+
+SUBSTANTIVE_COMMENTS:
+<count and summary>
+
+ISSUES_TO_CREATE_OR_CREATED:
+- #...
+
+DEPENDENCY_ORDER:
+<order or none>
+
+NON_GOALS:
+<non-goals>
+
+OPEN_QUESTIONS:
+<questions or none>
+
+NEXT_ACTION:
+<specific one-sentence action>
+
+NEXT_PROMPT:
+<paste-ready prompt for the next role>
+
+LAST_UPDATED_BY:
+<identity/profile/date>
+```

skills/llm-project-workflow/templates/canonical-thread-handoff.md

@@ -0,0 +1,36 @@
+# Template: Canonical Thread Handoff (CTH)
+
+Copy, fill the fields, and post as an issue or PR comment.
+
+```text
+## CTH: <Type>
+
+Status: <current workflow state>
+Next owner: <author|reviewer|merger|controller|operator>
+Current blocker: <none or exact blocker>
+Decision: <what was decided this session>
+Proof: <commands, SHAs, gate outputs, or explicit pending proof>
+Next action: <one concrete step for the next actor>
+Ready-to-paste prompt: <full prompt the next session should paste>
+```
+
+Allowed `<Type>` values:
+
+- State Handoff
+- Controller Decision
+- Author Handoff
+- Reviewer Handoff
+- Merger Handoff
+- Supersession Notice
+- Blocker
+
+Rules:
+
+- Find the latest CTH comment in the thread before starting work.
+- Treat the latest valid CTH as the current source of truth.
+- Post a new CTH when you finish, block, skip, supersede, approve, request
+  changes, or hand off.
+- A CTH summarizes workflow state; formal Gitea review verdicts remain
+  authoritative for merge gates.
+
+Full protocol: `docs/canonical-thread-handoff.md`

skills/llm-project-workflow/templates/merge-pr.md

@@ -1,4 +1,4 @@
-# Template: merge a PR (eligible reviewer only)
+# Template: merge a PR (eligible merger only)
 
 Copy, fill the `<...>` fields, and paste as the task prompt.
 
@@ -10,12 +10,17 @@ Load the canonical workflow first:
 Final report schema: `schemas/review-merge-final-report.md`.
 
 Rules (llm-project-workflow):
+- **BLOCKED + DIAGNOSE default (required):** If any required step (load workflow, lease, profile/role, capability, worktree under branches/, preflight, tool, instruction, etc.) cannot be performed, STOP. State BLOCKED. Use [`blocked-diagnose-report.md`](../templates/blocked-diagnose-report.md) template exactly. Only safe non-mutating recovery. Report. Do not continue or fallback.
+- Find the latest CTH comment on the PR/issue thread before starting work.
+  Post a new CTH: Merger Handoff (or CTH: Blocker) at session end.
+  Template: skills/llm-project-workflow/templates/canonical-thread-handoff.md
 - Repository targeting (#530): pass explicit `remote=`, `org=`, and `repo=` on
   every gitea-tools call (e.g. `remote=prgs org=Scaled-Tech-Consulting
   repo=Gitea-Tools`). A bare `remote=prgs` can resolve to the wrong default repo
   and is blocked when it disagrees with the local git remote URL.
-- Only an eligible, NON-author reviewer merges. If authenticated user == PR
+- Only an eligible, NON-author merger merges. If authenticated user == PR
   author → STOP.
+- Review and merge are separate workflow roles. A reviewer approval is not merge authorization.
 - Do not merge unless the PR is open, mergeable, and its checks/review pass.
 - No force-merge, no bypassing branch protections.
 - If the PR is closed but `merged=false`, STOP and run reconciliation. Do not clean up.
@@ -63,10 +68,12 @@ Then run the cleanup template (worktree-cleanup.md) in a reconciler session:
 - fetch/prune; confirm main checkout is clean and current (0 0).
 
 Handoff: end with a section titled exactly `Controller Handoff` per SKILL.md
-§K (long form — a merge is always high-risk), including the review/merge role
-fields (Selected PR, Reviewer eligibility, Pinned reviewed head, Review
+§K (long form — a merge is always high-risk), including the merger role
+fields (Selected PR, Merger eligibility, Pinned reviewed head, Review
 decision, Merge result, Linked issue status, Cleanup status) plus: merge
 commit, PR metadata state/merged flag/hash, remote master hash, and the
 post-merge verification method used & verification results. Reports missing
 the handoff are downgraded (review_proofs.assess_controller_handoff).
+
+Review and merge are separate workflow roles. A reviewer approval is not merge authorization.
 ```

skills/llm-project-workflow/templates/recover-bad-state.md

@@ -3,12 +3,15 @@
 Copy, fill the `<...>` fields, paste as the task prompt. Recovery is read-then-
 act: gather facts first, never discard unmerged work.
 
+**BLOCKED + DIAGNOSE rule (llm-project-workflow):** If at any point a required step (including state recovery itself) cannot be performed, stop immediately, use the standard [`blocked-diagnose-report.md`](blocked-diagnose-report.md) template, attempt only safe non-mutating recovery, and report. Do not continue or fallback.
+
 ```text
 Task: recover repo state for <situation>. Do not lose unmerged work.
 
 Rules (llm-project-workflow):
-- Fail closed: if state is unclear or a step would delete unmerged work, STOP.
+- BLOCKED + DIAGNOSE default: if state is unclear, a required check fails, or a step would delete unmerged work or bypass a guard, STOP and emit a full blocked-diagnose-report.md using the template. Clearly state BLOCKED. Diagnose. Only non-mutating recovery.
 - Never push master. Never discard commits not safely pushed to <remote>.
+- Prove you are in a branches/ worktree before any recovery mutation.
 
 Diagnose first:
 1. git fetch <remote> --prune
@@ -16,8 +19,19 @@ Diagnose first:
 3. git rev-list --left-right --count <remote>/master...master   # ahead/behind
 4. For any PR involved: confirm state (open/closed/merged) AND whether
    <remote>/master actually contains its commits ("closed" != "merged").
+5. Check active leases, claims, and whether required skills/workflows are loaded.
 
-Act per case:
+If a required diagnostic or recovery step itself is unavailable (e.g. terminal broken, skill missing, guard blocks, wrong profile), emit:
+
+## Required step
+<the step>
+
+## Observed failure
+<...>
+
+(complete the full blocked-diagnose-report.md template)
+
+Act per case (only after clean diagnosis; if blocked, use the template and stop):
 - Dirty worktree from another issue: leave it; start yours in a new worktree.
 - Local master ahead of remote: confirm the extra commits live on a branch
   pushed to <remote>, THEN git reset --hard <remote>/master. Verify with
@@ -26,6 +40,7 @@ Act per case:
 - Branch deleted before merge: recover commits from a local branch/reflog (or
   git fsck --lost-found), re-push, reopen the PR.
 - Unauthorized untracked file: do not commit it; leave pre-existing artifacts.
+- Any blocker: use blocked-diagnose-report.md template and stop.
 
-Handoff: what was wrong, evidence, action taken, current state, what remains.
+Handoff: what was wrong, evidence, action taken, current state, what remains. If BLOCKED, include the full blocker report.
 ```

skills/llm-project-workflow/templates/review-pr.md

@@ -36,6 +36,10 @@ Load the canonical workflow first:
 Final report schema: `schemas/review-merge-final-report.md`.
 
 Rules (llm-project-workflow):
+- **BLOCKED + DIAGNOSE default (required):** If any required step (load workflow, lease, profile/role, capability, worktree under branches/, preflight, tool, instruction, etc.) cannot be performed, STOP. State BLOCKED. Use [`blocked-diagnose-report.md`](../templates/blocked-diagnose-report.md) template exactly. Only safe non-mutating recovery. Report. Do not continue or fallback.
+- Find the latest CTH comment on the PR/issue thread before starting work.
+  Post a new CTH: Reviewer Handoff (or CTH: Blocker) at session end.
+  Template: skills/llm-project-workflow/templates/canonical-thread-handoff.md
 - Repository targeting (#530): pass explicit `remote=`, `org=`, and `repo=` on
   every gitea-tools call (e.g. `remote=prgs org=Scaled-Tech-Consulting
   repo=Gitea-Tools`). A bare `remote=prgs` can resolve to the wrong default repo
@@ -110,8 +114,9 @@ Steps:
    - base branch unchanged
    - no undismissed REQUEST_CHANGES / blocking review state left unaccounted
    If anything moved → STOP, re-pin, re-validate before any verdict.
-10. Post the review verdict: approve only if scope is clean and checks pass;
-    otherwise request changes with specifics. Never merge from this review step.
+ 10. Post the review verdict: approve only if scope is clean and checks pass;
+     otherwise request changes with specifics. Never merge from this review step.
+     Review and merge are separate workflow roles. A reviewer approval is not merge authorization.
    Include a "Review Metadata" block (attribution only — docs/llm-agent-sha.md):
 
    Review Metadata:
@@ -128,6 +133,8 @@ Pinned reviewed head, Review decision, Merge result, Linked issue status,
 Cleanup status. If you could not merge, name the exact gate. Reports missing
 the handoff are downgraded (review_proofs.assess_controller_handoff).
 
+Review and merge are separate workflow roles. A reviewer approval is not merge authorization.
+
 Baseline failure proof (#533): if a validation command exits non-zero, do NOT
 call it a clean pass. Only label a failure "baseline"/"pre-existing" with
 pre-merge proof — the failure reproduced on the PR's pre-merge base commit, or a

skills/llm-project-workflow/templates/start-issue.md

@@ -10,6 +10,10 @@ Final report schema: skills/llm-project-workflow/schemas/work-issue-final-report
 Router: skills/llm-project-workflow/SKILL.md (task mode: work-issue)
 
 Rules (llm-project-workflow):
+- **BLOCKED + DIAGNOSE default (required):** If any required step (load workflow, acquire lease, prove worktree under branches/, capability, profile, tool, instruction, preflight, etc.) cannot be performed, STOP. State BLOCKED. Use [`blocked-diagnose-report.md`](../templates/blocked-diagnose-report.md) template exactly. Only safe non-mutating recovery. Report. Do not continue or fallback.
+- Find the latest CTH comment on the issue/PR thread before starting work.
+  Post a new CTH: Author Handoff (or CTH: Blocker) at session end.
+  Template: skills/llm-project-workflow/templates/canonical-thread-handoff.md
 - No repo changes without a tracking issue. If none exists, create one first;
   if it can't be created, stop.
 - Work only in an isolated branch worktree under branches/. The main checkout

skills/llm-project-workflow/workflows/create-issue.md

@@ -12,6 +12,8 @@ This file is the canonical issue-creation workflow for Gitea-Tools. Load it
 before any issue mutation. Final report schema:
 [`schemas/create-issue-final-report.md`](../schemas/create-issue-final-report.md).
 
+**BLOCKED + DIAGNOSE (universal default):** If at any point you cannot perform a required step (skill not available, terminal broken, capability missing, wrong profile, guard blocks, worktree misbound, instructions unavailable, preflight fails, etc.), STOP. Clearly state BLOCKED. Use the standard [`../templates/blocked-diagnose-report.md`](../templates/blocked-diagnose-report.md) template. Only safe non-mutating recovery. Report using the template. Do not continue or use any fallback (temp scripts, direct API, etc.) unless controller authorizes. All blocker classes listed in llm-project-workflow/SKILL.md must trigger this.
+
 **Default task prompt:**
 
 > Create or update Gitea issues in this project only if every identity,
@@ -342,6 +344,41 @@ If edits are needed, make the smallest correction necessary and report the corre
 
 Do not silently change requested meaning.
 
+## 14a. Enforced content preflight (#582)
+
+`gitea_create_issue` runs a **content preflight gate** before duplicate
+search or creation. It fails closed (returns `BLOCKED + DIAGNOSE`, no issue
+created) when the title/body is a *vague reference* to out-of-band draft
+content the session cannot prove it holds, and no durable source pointer is
+present.
+
+An LLM must never fabricate issue content from stale chat memory. If asked to
+create "the drafted issue" / "the prepared issue" / "the issue we discussed"
+/ "the previous draft" without the full content in the current context or a
+durable source pointer, stop and return `BLOCKED + DIAGNOSE` naming the exact
+vague/missing fields.
+
+A **durable source pointer** is one of: an existing issue/PR reference
+(`#582`), a comment id (`comment 8155`), a checked-in file path
+(`task_capability_map.py`), a URL, or a scratchpad path. When a pointer is
+present, retrieve the real content from it before creating.
+
+The gate does **not** require a non-empty body; explicit title-only creation
+stays allowed. It only blocks placeholder references. An operator may bypass
+it with `allow_incomplete_content=True` (report the override).
+
+**Invalid prompts (must block):**
+
+* "Create the drafted issue."
+* "File the prepared issue we discussed."
+* "Open the previous draft."
+
+**Valid prompts (proceed):**
+
+* Full title + body + acceptance criteria supplied inline.
+* "Create the issue drafted in `#582`." (durable pointer → fetch and use it)
+* "Create the issue from `scratchpad/issue-draft.md`." (durable file pointer)
+
 ## 15. Labels, assignees, and metadata
 
 Apply labels, assignees, milestones, or project fields only if:

skills/llm-project-workflow/workflows/review-merge-pr.md

@@ -12,6 +12,8 @@ This file is the canonical PR review/merge workflow for Gitea-Tools. Load it
 before any PR mutation. Final report schema:
 [`schemas/review-merge-final-report.md`](../schemas/review-merge-final-report.md).
 
+**BLOCKED + DIAGNOSE (universal default):** If at any point you cannot perform a required step (skill not available, terminal broken, capability missing, wrong profile, guard blocks, worktree misbound, instructions unavailable, preflight fails, etc.), STOP. Clearly state BLOCKED. Use the standard [`../templates/blocked-diagnose-report.md`](../templates/blocked-diagnose-report.md) template. Only safe non-mutating recovery. Report using the template. Do not continue or use any fallback (temp scripts, direct API, etc.) unless controller authorizes. All blocker classes listed in llm-project-workflow/SKILL.md must trigger this.
+
 **Default task prompt:**
 
 > Review the next eligible open PR in this project. Merge it only if every
@@ -26,6 +28,12 @@ workflow rules exactly.
 
 ## 0. Load the canonical workflow first
 
+Before starting PR work, **find the latest CTH comment** on the PR or linked
+issue thread. Treat that CTH as the current handoff state. Post a new
+**CTH: Reviewer Handoff**, **CTH: Merger Handoff**, **CTH: Blocker**, or
+**CTH: Supersession Notice** when you finish, block, skip, supersede,
+approve, request changes, or hand off. See `docs/canonical-thread-handoff.md`.
+
 Before starting PR work, check whether the project provides a canonical PR review/merge workflow through a project skill, runbook, or MCP helper.
 
 If available, load it first and report:
@@ -818,6 +826,75 @@ The final report must identify:
 * whether same-PR merge continuation was allowed
 * whether the run stopped as required
 
+## 26A-1. Stale durable review-decision lock cleanup (#594)
+
+After #559, the review-decision lock is durable under
+`~/.cache/gitea-tools/session-state/` (for example
+`review_decision_lock-prgs-reviewer.json`). That durability can outlive the work
+it protects: a terminal `approve` / `request_changes` on a PR that is already
+**merged or closed** still hard-stops later unrelated reviews under #332.
+
+**Do not** delete session-state files by hand. Use the canonical MCP path.
+
+### When cleanup is allowed
+
+Use `gitea_cleanup_stale_review_decision_lock` when:
+
+1. `gitea_mark_final_review_decision` / live review is blocked by
+   `terminal review mutation already consumed ... (#332)`.
+2. Live Gitea state for the **last terminal mutation's PR** is **merged** or
+   **closed** (no same-PR merge sequence remains).
+3. Active profile identity matches the durable lock (reviewer profile with
+   `gitea.pr.review` for `apply=true`).
+4. Optional pin: pass `expected_terminal_pr` to the prior terminal PR number
+   (for example `586` when resuming after a merged #586 lock).
+
+Recommended sequence:
+
+```text
+gitea_whoami
+gitea_resolve_task_capability(task="cleanup_stale_review_decision_lock")
+gitea_cleanup_stale_review_decision_lock(apply=false, remote=..., org=..., repo=...)
+# inspect is_moot / cleanup_allowed / last_terminal_pr
+gitea_cleanup_stale_review_decision_lock(
+    apply=true,
+    expected_terminal_pr=<last_terminal_pr>,
+    remote=..., org=..., repo=...,
+)
+gitea_resolve_task_capability(task="review_pr")
+gitea_load_review_workflow()
+# continue formal mark + submit for the *new* PR
+```
+
+Successful `apply=true` clears memory + durable store and returns an audit
+record (and posts a durable PR comment on the terminal PR when
+`post_audit_comment` is true and comment permission allows).
+
+Same-profile auto-expire: after `gitea_merge_pr` succeeds for the PR that this
+profile just approved, the decision lock for that profile is cleared
+automatically. Cross-profile locks (for example reviewer approve, merger merge)
+still require `gitea_cleanup_stale_review_decision_lock`.
+
+### When cleanup is forbidden
+
+Refuse / fail-closed — keep #332 hard-stop — when:
+
+* the last terminal PR is still **open** (active review or merge sequence may
+  still apply)
+* live PR state cannot be fetched (ambiguous)
+* no lock or no terminal live mutation exists
+* profile identity does not match the lock
+* apply requested without authenticated identity or `gitea.pr.review`
+* `expected_terminal_pr` does not match the last terminal PR
+
+Do **not** use cleanup to:
+
+* bypass #332 on an open PR
+* replace `gitea_authorize_review_correction` for a mistaken review on a still
+  active PR (#211)
+* auto-approve or auto-merge any PR
+* justify `rm` of session-state files
+
 ## 26B. Per-PR reviewer lease (#407)
 
 Parallel reviewer sessions are allowed only when each session holds a distinct,
@@ -928,6 +1005,14 @@ Confirm:
 
 Clean only the session-owned `branches/` review worktree if the project workflow explicitly allows cleanup.
 
+Do not delete source branches from reviewer mode with raw git commands. Commands
+such as `git branch -d <branch>` and `git push <remote> --delete <branch>` are
+not proof of authorized cleanup and bypass MCP role/capability gates. Merged PR
+source branch cleanup must use an explicit MCP cleanup tool such as
+`gitea_cleanup_merged_pr_branch` or another approved cleanup helper with exact
+`gitea.branch.delete` authority, merged-PR proof, no open PR using the branch,
+target-branch ancestry proof, a `branches/` worktree path, and cleanup mutations
+reported separately from review mutations.
 Review, baseline, and merge-simulation worktrees created during this run are
 transient and are removed automatically at successful completion once they are
 clean, carry no open PR, and hold no active lease (#401). Use
@@ -1027,6 +1112,8 @@ Blocked handoffs must say to rerun the full workflow after the blocker clears.
 
 If the blocker is a terminal review mutation already consumed in the current run, the handoff must say that the next run must start from the beginning and must not reuse stale ready/approved state.
 
+If the referenced terminal PR is already **merged or closed** on live Gitea, the durable #332 decision lock is **moot**. Do **not** delete session-state files by hand. Use `gitea_cleanup_stale_review_decision_lock` (assess with `apply=false`, then `apply=true` with `expected_terminal_pr` set) from the reviewer profile after identity/profile checks (#594). Cleanup is **forbidden** while that PR is still open.
+
 ## 30. Final report must be precise
 
 Include:

skills/llm-project-workflow/workflows/work-issue.md

@@ -12,6 +12,8 @@ This file is the canonical author/coder workflow for Gitea-Tools. Load it
 before any issue implementation mutation. Final report schema:
 [`schemas/work-issue-final-report.md`](../schemas/work-issue-final-report.md).
 
+**BLOCKED + DIAGNOSE (universal default):** If at any point you cannot perform a required step (skill not available, terminal broken, capability missing, wrong profile, guard blocks, worktree misbound, instructions unavailable, preflight fails, etc.), STOP. Clearly state BLOCKED. Use the standard [`../templates/blocked-diagnose-report.md`](../templates/blocked-diagnose-report.md) template. Only safe non-mutating recovery. Report using the template. Do not continue or use any fallback (temp scripts, direct API, etc.) unless controller authorizes. All blocker classes listed in llm-project-workflow/SKILL.md must trigger this.
+
 **Default task prompt:**
 
 > Find the next eligible issue in this project, work on it only if all gates
@@ -26,6 +28,12 @@ This is an author/coder workflow. It is not a reviewer workflow.
 
 ## 0. Load the canonical workflow first
 
+Before starting issue work, **find the latest CTH comment** on the target
+issue or linked PR thread. Treat that CTH as the current handoff state unless
+a newer authoritative gate supersedes it. Post a new **CTH: Author Handoff**
+(or `CTH: Blocker`) when you finish, block, or hand off.
+See `docs/canonical-thread-handoff.md`.
+
 Before starting issue work, check whether the project provides a canonical work-on-issue workflow through a project skill, runbook, or MCP helper.
 
 If available, load it first and report:
@@ -615,10 +623,39 @@ After push, report:
 
 If push fails, stop and produce a recovery handoff.
 
-## 20A. Conflict-fix lease and push gate (#399)
+## 20A. Live head re-pin before conflict-fix classification (#522)
+
+Open PR inventory `mergeable` / `head_sha` fields are **advisory and may be
+stale**. Before classifying a PR as conflicted or creating a conflict-fix
+worktree:
+
+1. Re-fetch the live PR (`gitea_view_pr` or equivalent) and record:
+   * inventory head SHA (if any)
+   * inventory mergeable (if any)
+   * **live** head SHA (full 40-char)
+   * **live** mergeable
+2. Call `gitea_assess_conflict_fix_classification` with those values.
+3. Act only on the returned classification and **pinned live head**:
+   * `stale_inventory_skip` / `live_mergeable_skip` → **do not** create a
+     conflict-fix worktree; do not mutate the PR branch for conflicts.
+   * `conflict_fix_needed` → conflict-fix worktree allowed for the pinned
+     live head only.
+   * `incomplete_live_repin` → stop; re-fetch live state.
+4. If inventory head ≠ live head, report both SHAs and use the live head only.
+5. If inventory says `mergeable:false` but live says `mergeable:true`, classify
+   as stale inventory and skip author conflict-fix mutation.
+
+Conflict-fix final reports that claim conflict-fix work must include:
+
+* citation of `gitea_assess_conflict_fix_classification`
+* `Live head SHA: <40-char hex>` (or Pinned head SHA / Live PR head SHA)
+* `Conflict-fix classification: <stale_inventory_skip|conflict_fix_needed|live_mergeable_skip|incomplete_live_repin>`
+
+## 20B. Conflict-fix lease and push gate (#399)
 
 When pushing to an existing PR branch to resolve merge conflicts:
 
+0. Complete §20A live-head re-pin / classification first.
 1. Call `gitea_acquire_conflict_fix_lease` before any push.
 2. Call `gitea_assess_conflict_fix_push` immediately before `git push` with:
    * branch head before push

stale_review_decision_lock.py

@@ -0,0 +1,440 @@
+"""Stale / moot #332 review-decision lock detection and cleanup policy (#594/#620).
+
+#332 correctly hard-stops a reviewer session after a terminal live review
+mutation. After #559 those locks are durable on disk, so they can outlive the
+work they protect: when the referenced PR is already merged or closed, no
+same-PR merge sequence remains, yet the durable ledger still blocks unrelated
+new terminal reviews.
+
+#620 scopes the terminal boundary by **reviewed head SHA**: a prior
+REQUEST_CHANGES (or APPROVE) on head A must not block a fresh formal decision
+on head B of the **same open PR**. Same-head duplicates remain fail-closed.
+Open-PR lock *cleanup* remains forbidden unless the PR is truly merged/closed
+(#594); new-head re-review is allowed without deleting the durable lock.
+
+This module is pure policy (no Gitea I/O). The MCP tool
+``gitea_cleanup_stale_review_decision_lock`` fetches live PR state, calls these
+helpers, and only then clears durable state when cleanup is allowed.
+
+Manual deletion of ``~/.cache/gitea-tools/session-state/*`` is never the
+canonical path.
+"""
+
+from __future__ import annotations
+
+from datetime import datetime, timezone
+from typing import Any
+
+# Keep in sync with gitea_mcp_server._TERMINAL_REVIEW_ACTIONS.
+TERMINAL_REVIEW_ACTIONS = frozenset({"approve", "request_changes"})
+
+
+def normalize_head_sha(value: Any) -> str | None:
+    """Normalize a git SHA for equality comparison; None if empty/invalid."""
+    if value is None:
+        return None
+    text = str(value).strip().lower()
+    if not text:
+        return None
+    return text
+
+
+def heads_equal(a: Any, b: Any) -> bool:
+    na = normalize_head_sha(a)
+    nb = normalize_head_sha(b)
+    if not na or not nb:
+        return False
+    return na == nb
+
+
+def mutation_head_sha(mutation: dict | None, lock: dict | None = None) -> str | None:
+    """Head SHA that bounds a live mutation (#620).
+
+    Prefers fields recorded on the mutation itself. For *legacy* mutations
+    that predate head-scoping, falls back to the lock's
+    ``ready_expected_head_sha`` only when that ready binding is for the same
+    PR number (the frozen durable PR #619-style ledger).
+    """
+    if not isinstance(mutation, dict):
+        return None
+    for key in ("head_sha", "expected_head_sha", "reviewed_head_sha"):
+        head = normalize_head_sha(mutation.get(key))
+        if head:
+            return head
+    if not isinstance(lock, dict):
+        return None
+    if lock.get("ready_pr_number") != mutation.get("pr_number"):
+        return None
+    return normalize_head_sha(lock.get("ready_expected_head_sha"))
+
+
+def last_terminal_mutation(lock: dict | None) -> dict | None:
+    """Return the last terminal live mutation on *lock*, or None."""
+    if not lock:
+        return None
+    terminals = [
+        m
+        for m in (lock.get("live_mutations") or [])
+        if isinstance(m, dict) and m.get("action") in TERMINAL_REVIEW_ACTIONS
+    ]
+    return terminals[-1] if terminals else None
+
+
+def prior_live_mutations_block_boundary(
+    lock: dict | None,
+    *,
+    pr_number: int,
+    expected_head_sha: str | None,
+) -> bool:
+    """True when prior live mutations block a new decision for PR+head (#620).
+
+    Historical terminals on a **different head of the same PR** do not block.
+    Any prior mutation on another PR, the same head, or without a comparable
+    head SHA fails closed (blocks).
+
+    Head resolution uses ``mutation_head_sha(m, lock)`` so pre-#620 ledgers
+    that only stored ``ready_expected_head_sha`` still compare correctly
+    (PR #619-style).
+    """
+    if not lock:
+        return False
+    if lock.get("correction_authorized"):
+        return False
+    prior = list(lock.get("live_mutations") or [])
+    if not prior:
+        return False
+    target = normalize_head_sha(expected_head_sha)
+    for m in prior:
+        if not isinstance(m, dict):
+            return True
+        m_pr = m.get("pr_number")
+        m_head = mutation_head_sha(m, lock)
+        if (
+            m_pr == pr_number
+            and target
+            and m_head
+            and not heads_equal(m_head, target)
+        ):
+            # Same open PR, different reviewed head — historical boundary only.
+            continue
+        return True
+    return False
+
+
+def terminal_boundary_allows_fresh_decision(
+    lock: dict | None,
+    *,
+    pr_number: int,
+    expected_head_sha: str | None,
+    operation: str,
+) -> bool:
+    """Whether #332 hard-stop should yield for a new PR+head boundary (#620).
+
+    Only for ``mark_ready`` / ``review`` / ``resume`` on the **same PR** when
+    the requested head differs from the last terminal's head. Merge is never
+    reopened by head change (approved head merge path is separate).
+    """
+    if operation not in ("mark_ready", "review", "resume"):
+        return False
+    if not lock:
+        return False
+    if lock.get("correction_authorized"):
+        return True
+    last = last_terminal_mutation(lock)
+    if last is None:
+        return True
+    if last.get("pr_number") != pr_number:
+        return False
+    locked_head = mutation_head_sha(last, lock)
+    target = normalize_head_sha(expected_head_sha)
+    if not locked_head or not target:
+        return False
+    return not heads_equal(locked_head, target)
+
+
+def backfill_terminal_heads_from_ready(lock: dict) -> dict:
+    """Stamp head_sha onto legacy terminal mutations before overwriting ready_*.
+
+    Called when marking a fresh decision on a new head so historical rows keep
+    their original boundary after ``ready_expected_head_sha`` advances (#620).
+    """
+    if not isinstance(lock, dict):
+        return lock
+    ready_pr = lock.get("ready_pr_number")
+    ready_head = normalize_head_sha(lock.get("ready_expected_head_sha"))
+    if ready_pr is None or not ready_head:
+        return lock
+    mutations = list(lock.get("live_mutations") or [])
+    changed = False
+    for m in mutations:
+        if not isinstance(m, dict):
+            continue
+        if m.get("action") not in TERMINAL_REVIEW_ACTIONS:
+            continue
+        if m.get("pr_number") != ready_pr:
+            continue
+        if mutation_head_sha(m):
+            continue
+        m["head_sha"] = ready_head
+        changed = True
+    if changed:
+        lock["live_mutations"] = mutations
+    return lock
+
+
+def classify_pr_live_state(pr_live: dict | None) -> dict[str, Any]:
+    """Normalize a Gitea PR payload into merge/closed flags."""
+    pr = pr_live or {}
+    merged = bool(pr.get("merged") or pr.get("merged_at"))
+    state = (pr.get("state") or "").strip().lower() or None
+    closed = state == "closed"
+    head = pr.get("head") if isinstance(pr.get("head"), dict) else {}
+    head_sha = normalize_head_sha(
+        pr.get("head_sha") or pr.get("head_commit_sha") or head.get("sha")
+    )
+    return {
+        "pr_state": state,
+        "pr_merged": merged,
+        "pr_merged_or_closed": merged or closed,
+        "merge_commit_sha": pr.get("merge_commit_sha")
+        or pr.get("merged_commit_sha"),
+        "current_pr_head_sha": head_sha,
+    }
+
+
+def lock_summary(lock: dict | None) -> dict[str, Any] | None:
+    """LLM-safe summary of a decision lock (no secrets)."""
+    if lock is None:
+        return None
+    last = last_terminal_mutation(lock)
+    mutations = list(lock.get("live_mutations") or [])
+    last_head = mutation_head_sha(last, lock) if last else None
+    return {
+        "task": lock.get("task"),
+        "remote": lock.get("remote"),
+        "org": lock.get("org") or lock.get("ready_org"),
+        "repo": lock.get("repo") or lock.get("ready_repo"),
+        "profile_identity": lock.get("profile_identity")
+        or lock.get("session_profile_lock")
+        or lock.get("session_profile"),
+        "session_profile": lock.get("session_profile"),
+        "ready_pr_number": lock.get("ready_pr_number"),
+        "ready_action": lock.get("ready_action"),
+        "ready_expected_head_sha": normalize_head_sha(
+            lock.get("ready_expected_head_sha")
+        ),
+        "live_mutations_count": len(mutations),
+        "last_terminal": (
+            {
+                "pr_number": last.get("pr_number"),
+                "action": last.get("action"),
+                "review_id": last.get("review_id"),
+                "head_sha": last_head,
+            }
+            if last
+            else None
+        ),
+        "locked_head_sha": last_head,
+        "correction_authorized": bool(lock.get("correction_authorized")),
+        "updated_at": lock.get("updated_at") or lock.get("recorded_at"),
+    }
+
+
+def assess_stale_review_decision_lock(
+    lock: dict | None,
+    *,
+    pr_live: dict | None = None,
+    pr_lookup_error: str | None = None,
+    active_profile_identity: str | None = None,
+    current_pr_head_sha: str | None = None,
+) -> dict[str, Any]:
+    """Assess whether a durable review-decision lock is stale/moot (#594/#620).
+
+    *pr_live* must be the live Gitea payload for the **last terminal
+    mutation's PR**. When no lock / no terminal mutation exists, cleanup is
+    not applicable. When the PR is still open (or lookup fails), cleanup is
+    forbidden (#594). Open PR + different live head reports
+    ``stale_by_head`` / ``fresh_review_on_current_head_allowed`` (#620)
+    without enabling cleanup.
+    """
+    summary = lock_summary(lock)
+    result: dict[str, Any] = {
+        "has_lock": lock is not None,
+        "lock_summary": summary,
+        "last_terminal_pr": None,
+        "last_terminal_action": None,
+        "locked_head_sha": None,
+        "current_pr_head_sha": normalize_head_sha(current_pr_head_sha),
+        "stale_by_head": False,
+        "fresh_review_on_current_head_allowed": False,
+        "is_moot": False,
+        "cleanup_allowed": False,
+        "profile_match": True,
+        "pr_state": None,
+        "pr_merged": False,
+        "pr_merged_or_closed": False,
+        "merge_commit_sha": None,
+        "reasons": [],
+        "recovery_tool": "gitea_cleanup_stale_review_decision_lock",
+    }
+
+    if lock is None:
+        result["reasons"].append("no review decision lock present")
+        return result
+
+    # Profile identity gate (caller may re-check with env; pure assess still
+    # reports mismatch when active identity is supplied).
+    stored = (
+        (lock.get("profile_identity") or lock.get("session_profile_lock") or "")
+        .strip()
+    )
+    active = (active_profile_identity or "").strip()
+    if active and stored and active != stored:
+        result["profile_match"] = False
+        result["reasons"].append(
+            "review decision lock profile identity does not match active "
+            f"profile '{active}' (fail closed, #594)"
+        )
+        return result
+
+    last = last_terminal_mutation(lock)
+    if last is None:
+        result["reasons"].append(
+            "review decision lock has no terminal live mutations; nothing to clear"
+        )
+        return result
+
+    pr_number = last.get("pr_number")
+    action = last.get("action")
+    locked_head = mutation_head_sha(last, lock)
+    result["last_terminal_pr"] = pr_number
+    result["last_terminal_action"] = action
+    result["locked_head_sha"] = locked_head
+
+    if pr_number is None:
+        result["reasons"].append(
+            "last terminal mutation missing pr_number; refuse cleanup (fail closed)"
+        )
+        return result
+
+    if pr_lookup_error:
+        result["reasons"].append(
+            f"could not load live state for PR #{pr_number}: {pr_lookup_error} "
+            "(fail closed, #594)"
+        )
+        return result
+
+    if pr_live is None:
+        result["reasons"].append(
+            f"live PR state required for terminal PR #{pr_number} before cleanup "
+            "(fail closed, #594)"
+        )
+        return result
+
+    live = classify_pr_live_state(pr_live)
+    current_head = normalize_head_sha(
+        current_pr_head_sha or live.get("current_pr_head_sha")
+    )
+    result.update(
+        {
+            "pr_state": live["pr_state"],
+            "pr_merged": live["pr_merged"],
+            "pr_merged_or_closed": live["pr_merged_or_closed"],
+            "merge_commit_sha": live["merge_commit_sha"],
+            "current_pr_head_sha": current_head,
+        }
+    )
+
+    if not live["pr_merged_or_closed"]:
+        stale_by_head = bool(
+            locked_head and current_head and not heads_equal(locked_head, current_head)
+        )
+        result["stale_by_head"] = stale_by_head
+        # Fresh formal decision is allowed on the new head without cleanup (#620).
+        result["fresh_review_on_current_head_allowed"] = stale_by_head
+        if stale_by_head:
+            result["reasons"].append(
+                f"terminal {action} on PR #{pr_number} is bound to head "
+                f"{locked_head[:12]}…; live head is {current_head[:12]}… — "
+                "fresh formal review on current head is allowed without "
+                "cleanup (fail closed for cleanup, #620); #332 same-head "
+                "duplicate protection remains"
+            )
+        else:
+            result["reasons"].append(
+                f"terminal review mutation on open PR #{pr_number} is still active "
+                f"({action}); #332 hard-stop remains — cleanup forbidden (#594)"
+            )
+        return result
+
+    # Merged or closed: lock is moot. Same-PR merge continuation is impossible.
+    result["is_moot"] = True
+    result["cleanup_allowed"] = True
+    result["stale_by_head"] = False
+    result["fresh_review_on_current_head_allowed"] = False
+    result["reasons"].append(
+        f"terminal mutation ({action} on PR #{pr_number}) is moot: PR is "
+        f"{'merged' if live['pr_merged'] else 'closed'}; canonical cleanup allowed (#594)"
+    )
+    return result
+
+
+def build_cleanup_audit_record(
+    *,
+    assessment: dict[str, Any],
+    actor_username: str | None,
+    profile_name: str | None,
+    applied: bool,
+) -> dict[str, Any]:
+    """Structured durable audit payload for a cleanup attempt."""
+    last = (assessment.get("lock_summary") or {}).get("last_terminal") or {}
+    return {
+        "event": "stale_review_decision_lock_cleanup",
+        "issue_ref": "#594",
+        "applied": bool(applied),
+        "timestamp": datetime.now(timezone.utc).isoformat(),
+        "actor_username": actor_username,
+        "profile_name": profile_name,
+        "last_terminal_pr": assessment.get("last_terminal_pr") or last.get("pr_number"),
+        "last_terminal_action": assessment.get("last_terminal_action")
+        or last.get("action"),
+        "pr_state": assessment.get("pr_state"),
+        "pr_merged": assessment.get("pr_merged"),
+        "pr_merged_or_closed": assessment.get("pr_merged_or_closed"),
+        "merge_commit_sha": assessment.get("merge_commit_sha"),
+        "prior_live_mutations_count": (
+            (assessment.get("lock_summary") or {}).get("live_mutations_count")
+        ),
+        "prior_profile_identity": (
+            (assessment.get("lock_summary") or {}).get("profile_identity")
+        ),
+        "cleanup_allowed": assessment.get("cleanup_allowed"),
+        "is_moot": assessment.get("is_moot"),
+        "reasons": list(assessment.get("reasons") or []),
+    }
+
+
+def format_cleanup_audit_comment(audit: dict[str, Any]) -> str:
+    """Markdown body for a durable Gitea audit comment after cleanup."""
+    status = "APPLIED" if audit.get("applied") else "ASSESSED (not applied)"
+    lines = [
+        "## Stale #332 review-decision lock cleanup (#594)",
+        "",
+        f"Status: **{status}**",
+        "",
+        f"- actor: `{audit.get('actor_username')}`",
+        f"- profile: `{audit.get('profile_name')}`",
+        f"- timestamp: `{audit.get('timestamp')}`",
+        f"- last terminal: `{audit.get('last_terminal_action')}` on "
+        f"PR #{audit.get('last_terminal_pr')}",
+        f"- PR state: `{audit.get('pr_state')}` "
+        f"(merged={audit.get('pr_merged')})",
+        f"- merge_commit_sha: `{audit.get('merge_commit_sha')}`",
+        f"- prior live_mutations_count: "
+        f"`{audit.get('prior_live_mutations_count')}`",
+        f"- prior profile_identity: `{audit.get('prior_profile_identity')}`",
+        "",
+        "Manual deletion of session-state files is **not** the workflow.",
+        "This path only clears a lock when the referenced PR is merged/closed.",
+    ]
+    return "\n".join(lines)

task_capability_map.py

@@ -36,6 +36,10 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
         "permission": "gitea.issue.comment",
         "role": "author",
     },
+    "create_label": {
+        "permission": "gitea.issue.comment",
+        "role": "author",
+    },
     "create_branch": {
         "permission": "gitea.branch.create",
         "role": "author",
@@ -66,7 +70,7 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
     },
     "merge_pr": {
         "permission": "gitea.pr.merge",
-        "role": "reviewer",
+        "role": "merger",
     },
     "adopt_merger_pr_lease": {
         "permission": "gitea.pr.comment",
@@ -92,10 +96,25 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
         "permission": "gitea.pr.approve",
         "role": "reviewer",
     },
+    # #594: clear durable #332 decision lock only when last terminal PR is
+    # already merged/closed (moot). Apply path requires reviewer review
+    # permission; assessment itself uses gitea.read inside the tool.
+    "cleanup_stale_review_decision_lock": {
+        "permission": "gitea.pr.review",
+        "role": "reviewer",
+    },
+    "gitea_cleanup_stale_review_decision_lock": {
+        "permission": "gitea.pr.review",
+        "role": "reviewer",
+    },
     "delete_branch": {
         "permission": "gitea.branch.delete",
         "role": "author",
     },
+    "cleanup_merged_pr_branch": {
+        "permission": "gitea.branch.delete",
+        "role": "reconciler",
+    },
     "commit_files": {
         "permission": "gitea.repo.commit",
         "role": "author",
@@ -106,11 +125,11 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
     },
     "reconcile_merged_cleanups": {
         "permission": "gitea.read",
-        "role": "author",
+        "role": "reconciler",
     },
     "reconciliation_cleanup": {
         "permission": "gitea.branch.delete",
-        "role": "author",
+        "role": "reconciler",
     },
     "work_issue": {
         "permission": "gitea.pr.create",
@@ -120,6 +139,17 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
         "permission": "gitea.pr.create",
         "role": "author",
     },
+    # #600: controller-owned allocator — any authenticated profile may call;
+    # routing enforces role match to selected work. Uses control-plane DB (#613).
+    "allocate_next_work": {
+        "permission": "gitea.read",
+        "role": "author",
+    },
+    "gitea_allocate_next_work": {
+        "permission": "gitea.read",
+        "role": "author",
+    },
+
     "reconcile_landed_pr": {
         "permission": "gitea.read",
         "role": "author",
@@ -142,6 +172,18 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
         "permission": "gitea.issue.close",
         "role": "reconciler",
     },
+    "reconcile_close_superseded_pr": {
+        "permission": "gitea.pr.close",
+        "role": "reconciler",
+    },
+    "reconcile_close_satisfied_issue": {
+        "permission": "gitea.issue.close",
+        "role": "reconciler",
+    },
+    "reconcile_create_followup_issue": {
+        "permission": "gitea.issue.create",
+        "role": "reconciler",
+    },
     "post_heartbeat": {
         "permission": "gitea.issue.comment",
         "role": "author",
@@ -163,6 +205,7 @@ ISSUE_MUTATION_TOOL_TASKS: dict[str, str] = {
     "gitea_create_issue_comment": "comment_issue",
     "gitea_mark_issue": "mark_issue",
     "gitea_set_issue_labels": "set_issue_labels",
+    "gitea_create_label": "create_label",
     "gitea_commit_files": "commit_files",
 }
 

test_mcp_conn.py

@@ -1,20 +1,45 @@
 #!/usr/bin/env python3
-"""Live health-check script to verify Gitea MCP namespace connections.
+"""Offline-only MCP namespace spawn probe (NOT IDE-namespace proof).
 
-Spawns the MCP server processes as defined in the IDE's global config,
-performs the JSON-RPC handshake, and queries the tools list to verify
-that the connection is fully operational and doesn't return EOF.
+Spawns a *separate* MCP server process from config via subprocess.Popen,
+performs the JSON-RPC handshake, verifies the required tool is registered,
+and invokes that tool. Results are classified with
+``probe_source=offline_spawn``.
+
+This path is useful for offline launch/registration debugging. It does
+**not** prove the IDE-managed MCP client namespace is healthy (#543). For
+workflow gates, pass live IDE call evidence with
+``probe_source=client_namespace`` to ``gitea_assess_mcp_namespace_health``.
 """
+
+import argparse
 import json
 import os
 import subprocess
 import sys
 
-def test_connection(name, config):
+from mcp_namespace_health import REQUIRED_NAMESPACE_TOOLS, classify_namespace_probe
+
+
+def _read_json_line(proc):
+    line = proc.stdout.readline()
+    if not line:
+        stderr_content = proc.stderr.read()
+        return None, stderr_content
+    return json.loads(line), None
+
+
+def _write_message(proc, payload):
+    proc.stdin.write(json.dumps(payload) + "\n")
+    proc.stdin.flush()
+
+
+def run_connection_test(name, config, *, required_tool=None, config_path=None):
     print(f"Testing MCP connection for '{name}'...")
     command = config.get("command")
     args = config.get("args", [])
     env = config.get("env", {})
+    tool_name = required_tool or REQUIRED_NAMESPACE_TOOLS.get(name) or "gitea_whoami"
     
     # Merge current environment
     run_env = os.environ.copy()
@@ -31,8 +56,17 @@ def test_connection(name, config):
             bufsize=1,
             env=run_env
         )
-    except Exception as e:
-        print(f"  [FAIL] Failed to spawn process: {e}")
+    except Exception as exc:
+        print(f"  [FAIL] Failed to spawn process: {exc}")
+        assessment = classify_namespace_probe(
+            name,
+            required_tool=tool_name,
+            probe_result={"success": False, "error": str(exc)},
+            process={"profile": env.get("GITEA_MCP_PROFILE"), "env": env},
+            config_path=config_path,
+                probe_source="offline_spawn",
+        )
+        print(f"  diagnostics: {json.dumps(assessment['diagnostics'], sort_keys=True)}")
         return False
 
     # Send initialize request
@@ -48,26 +82,36 @@ def test_connection(name, config):
     }
     
     try:
-        proc.stdin.write(json.dumps(init_req) + "\n")
-        proc.stdin.flush()
+        _write_message(proc, init_req)
         
         # Read response
-        line = proc.stdout.readline()
-        if not line:
-            stderr_content = proc.stderr.read()
+        res, stderr_content = _read_json_line(proc)
+        if res is None:
             print(f"  [FAIL] Received EOF from process. Stderr:\n{stderr_content}")
+            assessment = classify_namespace_probe(
+                name,
+                required_tool=tool_name,
+                probe_result={"success": False, "error": stderr_content or "EOF"},
+                process={
+                    "pid": proc.pid,
+                    "profile": env.get("GITEA_MCP_PROFILE"),
+                    "env": env,
+                },
+                config_path=config_path,
+                probe_source="offline_spawn",
+            )
+            print(f"  remediation: {' '.join(assessment['remediation'])}")
             proc.terminate()
             return False
             
-        print(f"  [OK] Received initialize response: {line.strip()[:150]}...")
+        print(f"  [OK] Received initialize response: {str(res)[:150]}...")
         
         # Send initialized notification
         init_notif = {
             "jsonrpc": "2.0",
             "method": "notifications/initialized"
         }
-        proc.stdin.write(json.dumps(init_notif) + "\n")
-        proc.stdin.flush()
+        _write_message(proc, init_notif)
         
         # Send tools/list request
         list_req = {
@@ -76,16 +120,27 @@ def test_connection(name, config):
             "params": {},
             "id": 2
         }
-        proc.stdin.write(json.dumps(list_req) + "\n")
-        proc.stdin.flush()
+        _write_message(proc, list_req)
         
-        line = proc.stdout.readline()
-        if not line:
+        res, stderr_content = _read_json_line(proc)
+        if res is None:
             print("  [FAIL] Received EOF on tools/list request.")
+            assessment = classify_namespace_probe(
+                name,
+                required_tool=tool_name,
+                probe_result={"success": False, "error": stderr_content or "EOF"},
+                process={
+                    "pid": proc.pid,
+                    "profile": env.get("GITEA_MCP_PROFILE"),
+                    "env": env,
+                },
+                config_path=config_path,
+                probe_source="offline_spawn",
+            )
+            print(f"  remediation: {' '.join(assessment['remediation'])}")
             proc.terminate()
             return False
             
-        res = json.loads(line)
         if "error" in res:
             print(f"  [FAIL] Server returned error: {res['error']}")
             proc.terminate()
@@ -94,16 +149,115 @@ def test_connection(name, config):
         tools = res.get("result", {}).get("tools", [])
         tool_names = [t.get("name") for t in tools]
         print(f"  [OK] Successfully retrieved {len(tool_names)} tools: {tool_names[:5]}...")
+        if tool_name not in tool_names:
+            assessment = classify_namespace_probe(
+                name,
+                required_tool=tool_name,
+                registered_tools=tool_names,
+                probe_result={"success": False, "error": "required tool missing"},
+                process={
+                    "pid": proc.pid,
+                    "profile": env.get("GITEA_MCP_PROFILE"),
+                    "env": env,
+                },
+                config_path=config_path,
+                probe_source="offline_spawn",
+            )
+            print(f"  [FAIL] Required tool '{tool_name}' is not registered.")
+            print(f"  remediation: {' '.join(assessment['remediation'])}")
+            proc.terminate()
+            return False
+
+        call_req = {
+            "jsonrpc": "2.0",
+            "method": "tools/call",
+            "params": {"name": tool_name, "arguments": {}},
+            "id": 3,
+        }
+        _write_message(proc, call_req)
+
+        call_res, stderr_content = _read_json_line(proc)
+        if call_res is None:
+            assessment = classify_namespace_probe(
+                name,
+                required_tool=tool_name,
+                registered_tools=tool_names,
+                probe_result={"success": False, "error": stderr_content or "EOF"},
+                process={
+                    "pid": proc.pid,
+                    "profile": env.get("GITEA_MCP_PROFILE"),
+                    "env": env,
+                },
+                config_path=config_path,
+                probe_source="offline_spawn",
+            )
+            print(f"  [FAIL] Received EOF on {tool_name} invocation.")
+            print(f"  diagnostics: {json.dumps(assessment['diagnostics'], sort_keys=True)}")
+            print(f"  remediation: {' '.join(assessment['remediation'])}")
+            proc.terminate()
+            return False
+        if "error" in call_res:
+            assessment = classify_namespace_probe(
+                name,
+                required_tool=tool_name,
+                registered_tools=tool_names,
+                probe_result={"success": False, "error": call_res["error"]},
+                process={
+                    "pid": proc.pid,
+                    "profile": env.get("GITEA_MCP_PROFILE"),
+                    "env": env,
+                },
+                config_path=config_path,
+                probe_source="offline_spawn",
+            )
+            print(f"  [FAIL] {tool_name} invocation returned error: {call_res['error']}")
+            print(f"  remediation: {' '.join(assessment['remediation'])}")
+            proc.terminate()
+            return False
+
+        assessment = classify_namespace_probe(
+            name,
+            required_tool=tool_name,
+            registered_tools=tool_names,
+            probe_result={"success": True, "result": call_res.get("result")},
+            process={
+                "pid": proc.pid,
+                "profile": env.get("GITEA_MCP_PROFILE"),
+                "env": env,
+            },
+            config_path=config_path,
+                probe_source="offline_spawn",
+        )
+        print(f"  [OK] Successfully invoked required tool '{tool_name}'.")
+        print(f"  diagnostics: {json.dumps(assessment['diagnostics'], sort_keys=True)}")
         
         proc.terminate()
         return True
-    except Exception as e:
-        print(f"  [FAIL] Error during handshake: {e}")
+    except Exception as exc:
+        print(f"  [FAIL] Error during handshake: {exc}")
         proc.terminate()
         return False
 
+
 def main():
-    config_path = "/Users/jasonwalker/.gemini/config/mcp_config.json"
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--config",
+        default=os.environ.get(
+            "MCP_CONFIG_PATH",
+            os.path.expanduser("~/.gemini/config/mcp_config.json"),
+        ),
+        help="Path to MCP config JSON.",
+    )
+    parser.add_argument(
+        "--namespace",
+        action="append",
+        dest="namespaces",
+        help="Namespace to test. May be repeated.",
+    )
+    args = parser.parse_args()
+
+    config_path = args.config
     try:
         with open(config_path) as f:
             mcp_config = json.load(f)
@@ -112,10 +266,16 @@ def main():
         sys.exit(1)
         
     servers = mcp_config.get("mcpServers", {})
+    namespaces = args.namespaces or list(REQUIRED_NAMESPACE_TOOLS)
     failed = False
-    for name in ["gitea-author", "gitea-reviewer"]:
+    for name in namespaces:
         if name in servers:
-            if not test_connection(name, servers[name]):
+            if not run_connection_test(
+                name,
+                servers[name],
+                required_tool=REQUIRED_NAMESPACE_TOOLS.get(name),
+                config_path=config_path,
+            ):
                 failed = True
         else:
             print(f"Server '{name}' not found in mcp_config.json")

tests/conftest.py

@@ -1,4 +1,5 @@
 """Shared pytest fixtures for the Gitea-Tools test suite."""
+import os
 import sys
 
 import pytest
@@ -16,13 +17,46 @@ def _reset_mutation_authority(monkeypatch):
     the next test. It must never replace verify_mutation_authority with a
     no-op: individual tests that need a specific authority state set it up
     explicitly.
+
+    Session-state isolation (#559 / #590 / #594): many tests use
+    ``patch.dict(os.environ, ..., clear=True)``, which drops
+    ``GITEA_MCP_SESSION_STATE_DIR``. Relying only on the env var therefore
+    re-exposes the operator host cache
+    (``~/.cache/gitea-tools/session-state``) and its review-mutation ledger.
+    Pin ``default_state_dir`` / ``DEFAULT_STATE_DIR`` to a per-test temp dir
+    so durable load/save never touches host state even after env clears.
     """
     monkeypatch.delenv("GITEA_SESSION_PROFILE_LOCK", raising=False)
     # Isolate durable session-state files so tests never share host cache (#559).
     import tempfile
 
     _state_tmp = tempfile.TemporaryDirectory(prefix="gitea-session-state-")
-    monkeypatch.setenv("GITEA_MCP_SESSION_STATE_DIR", _state_tmp.name)
+    state_dir = _state_tmp.name
+    monkeypatch.setenv("GITEA_MCP_SESSION_STATE_DIR", state_dir)
+    try:
+        import mcp_session_state
+    except Exception:
+        mcp_session_state = None
+    if mcp_session_state is not None:
+        # Survive patch.dict(..., clear=True) that drops the env var (#590).
+        # Still honor an explicit GITEA_MCP_SESSION_STATE_DIR when tests set
+        # their own temp dir (see tests/test_mcp_session_state.py).
+        monkeypatch.setattr(
+            mcp_session_state, "DEFAULT_STATE_DIR", state_dir, raising=False
+        )
+
+        def _isolated_default_state_dir(
+            _fallback: str = state_dir,
+            _env_key: str = mcp_session_state.STATE_DIR_ENV,
+        ) -> str:
+            raw = (os.environ.get(_env_key) or "").strip()
+            return raw or _fallback
+
+        monkeypatch.setattr(
+            mcp_session_state,
+            "default_state_dir",
+            _isolated_default_state_dir,
+        )
     try:
         import mcp_server
     except Exception:
@@ -32,6 +66,23 @@ def _reset_mutation_authority(monkeypatch):
     monkeypatch.setattr(mcp_server, "_MUTATION_AUTHORITY", None)
     monkeypatch.setattr(mcp_server, "_IDENTITY_CACHE", {})
     monkeypatch.setattr(mcp_server, "_REVIEW_DECISION_LOCK", None)
+    monkeypatch.setattr(mcp_server, "_LIVE_NAMESPACE_HEALTH", {})
+    monkeypatch.setattr(mcp_server, "_preflight_whoami_called", False)
+    monkeypatch.setattr(mcp_server, "_preflight_capability_called", False)
+    monkeypatch.setattr(mcp_server, "_preflight_resolved_role", None)
+    monkeypatch.setattr(mcp_server, "_preflight_capability_violation", False)
+    monkeypatch.setattr(mcp_server, "_preflight_capability_violation_files", [])
+    monkeypatch.setattr(mcp_server, "_preflight_capability_baseline_porcelain", None)
+    monkeypatch.setattr(mcp_server, "_preflight_resolved_task", None)
+    monkeypatch.setattr(mcp_server, "_preflight_reviewer_violation_files", [])
+    # Unit tests must not depend on live host MCP process health. Tests that
+    # use patch.dict(..., clear=True) drop PYTEST_CURRENT_TEST, which would
+    # otherwise re-enable the stale-runtime probe against operator daemons.
+    monkeypatch.setattr(
+        mcp_server,
+        "_check_mcp_runtimes_diagnostics",
+        lambda *args, **kwargs: [],
+    )
     try:
         import review_workflow_load
         review_workflow_load._REVIEW_WORKFLOW_LOAD = None

tests/test_allocator_service.py

@@ -0,0 +1,366 @@
+"""Tests for controller-owned allocator (#600) on control-plane DB (#613)."""
+
+from __future__ import annotations
+
+import os
+import tempfile
+import threading
+import unittest
+from concurrent.futures import ThreadPoolExecutor, as_completed
+
+from allocator_service import (
+    OUTCOME_ASSIGNED,
+    OUTCOME_BLOCKED_TERMINAL,
+    OUTCOME_NO_SAFE,
+    OUTCOME_PREVIEW,
+    OUTCOME_WAIT,
+    WorkCandidate,
+    allocate_next_work,
+    candidate_from_dict,
+    classify_skip,
+    expected_role_for_candidate,
+)
+from control_plane_db import ControlPlaneDB, InvalidWorkKindError
+
+
+class AllocatorServiceTest(unittest.TestCase):
+    def setUp(self) -> None:
+        self._tmp = tempfile.TemporaryDirectory()
+        self.db_path = os.path.join(self._tmp.name, "cp.sqlite3")
+        self.db = ControlPlaneDB(self.db_path)
+
+    def tearDown(self) -> None:
+        self._tmp.cleanup()
+
+    def _alloc(self, **kwargs):
+        defaults = dict(
+            db=self.db,
+            session_id="s-test",
+            role="author",
+            remote="prgs",
+            org="org",
+            repo="repo",
+            candidates=[],
+            apply=False,
+            profile_name="prgs-author",
+            username="jcwalker3",
+        )
+        defaults.update(kwargs)
+        return allocate_next_work(**defaults)
+
+    def test_selects_ready_issue_for_author(self) -> None:
+        cands = [
+            WorkCandidate(
+                kind="issue",
+                number=612,
+                labels=("status:ready",),
+                title="bridge",
+                dependency_unmet=True,
+                dependency_reason="downstream of #600",
+            ),
+            WorkCandidate(
+                kind="issue",
+                number=600,
+                labels=("status:ready", "type:feature"),
+                title="allocator",
+                priority=50,
+            ),
+            WorkCandidate(
+                kind="issue",
+                number=601,
+                labels=("status:blocked",),
+                title="blocked",
+                blocked=True,
+            ),
+        ]
+        res = self._alloc(candidates=cands, apply=False)
+        self.assertTrue(res["success"])
+        self.assertEqual(res["outcome"], OUTCOME_PREVIEW)
+        self.assertEqual(res["selected"]["number"], 600)
+        self.assertEqual(res["selected"]["kind"], "issue")
+        # When 600 is highest priority valid work, lower-priority blocked/dep
+        # candidates are not visited. Prove they are skipped when they sort first.
+        res2 = self._alloc(
+            candidates=[
+                WorkCandidate(
+                    kind="issue",
+                    number=612,
+                    labels=("status:ready",),
+                    priority=99,
+                    dependency_unmet=True,
+                    dependency_reason="downstream of #600",
+                ),
+                WorkCandidate(
+                    kind="issue",
+                    number=601,
+                    labels=("status:blocked",),
+                    priority=98,
+                    blocked=True,
+                ),
+                WorkCandidate(
+                    kind="issue",
+                    number=600,
+                    labels=("status:ready",),
+                    priority=1,
+                ),
+            ],
+            apply=False,
+        )
+        skipped_nums = {s["number"] for s in res2["skipped"]}
+        self.assertIn(612, skipped_nums)
+        self.assertIn(601, skipped_nums)
+        self.assertEqual(res2["selected"]["number"], 600)
+        self.assertIsNone(res["assignment"])
+        self.assertFalse(res["file_lock_only"])
+        self.assertFalse(res["comment_lease_only"])
+
+    def test_atomic_assign_and_lease_on_apply(self) -> None:
+        cands = [
+            WorkCandidate(
+                kind="issue",
+                number=600,
+                labels=("status:ready",),
+                priority=10,
+            )
+        ]
+        res = self._alloc(candidates=cands, apply=True, session_id="s-a")
+        self.assertEqual(res["outcome"], OUTCOME_ASSIGNED)
+        asn = res["assignment"]
+        self.assertEqual(asn["outcome"], "assigned")
+        self.assertIsNotNone(asn["assignment_id"])
+        self.assertIsNotNone(asn["lease_id"])
+        self.assertEqual(asn["work_number"], 600)
+        self.assertIn("implement", asn["allowed_actions"])
+        self.assertIn("merge", asn["forbidden_actions"])
+        proof = res["lease_proof"]
+        self.assertEqual(proof["source"], "control_plane_db.assign_and_lease")
+
+    def test_concurrent_allocators_no_double_assign(self) -> None:
+        cand = WorkCandidate(
+            kind="pr",
+            number=100,
+            head_sha="a" * 40,
+            priority=10,
+        )
+        # Seed work item so both race the same target
+        self.db.upsert_work_item(
+            remote="prgs",
+            org="org",
+            repo="repo",
+            kind="pr",
+            number=100,
+            current_head_sha="a" * 40,
+        )
+        results = []
+        lock = threading.Lock()
+
+        def worker(sid: str):
+            r = allocate_next_work(
+                self.db,
+                session_id=sid,
+                role="reviewer",
+                remote="prgs",
+                org="org",
+                repo="repo",
+                candidates=[cand],
+                apply=True,
+                profile_name="prgs-reviewer",
+            )
+            with lock:
+                results.append(r)
+
+        with ThreadPoolExecutor(max_workers=2) as pool:
+            futs = [pool.submit(worker, f"s-{i}") for i in range(2)]
+            for f in as_completed(futs):
+                f.result()
+
+        outcomes = [r["outcome"] for r in results]
+        self.assertEqual(outcomes.count(OUTCOME_ASSIGNED), 1, outcomes)
+        self.assertEqual(outcomes.count(OUTCOME_WAIT), 1, outcomes)
+
+    def test_blocked_and_dependency_skipped(self) -> None:
+        cands = [
+            WorkCandidate(kind="issue", number=1, blocked=True, labels=("status:blocked",)),
+            WorkCandidate(
+                kind="issue",
+                number=612,
+                labels=("status:ready",),
+                dependency_unmet=True,
+                dependency_reason="downstream of #600",
+            ),
+        ]
+        res = self._alloc(candidates=cands, apply=True, role="author")
+        self.assertEqual(res["outcome"], OUTCOME_NO_SAFE)
+        self.assertIsNone(res["selected"])
+        reasons = " ".join(s["reason"] for s in res["skipped"])
+        self.assertIn("blocked", reasons.lower())
+        self.assertIn("600", reasons)
+
+    def test_already_leased_returns_wait(self) -> None:
+        self.db.upsert_session(session_id="owner", role="author")
+        self.db.assign_and_lease(
+            session_id="owner",
+            role="author",
+            remote="prgs",
+            org="org",
+            repo="repo",
+            kind="issue",
+            number=50,
+        )
+        res = self._alloc(
+            session_id="other",
+            candidates=[
+                WorkCandidate(kind="issue", number=50, labels=("status:ready",))
+            ],
+            apply=True,
+        )
+        self.assertEqual(res["outcome"], OUTCOME_WAIT)
+        self.assertEqual(res["owner_session_id"], "owner")
+
+    def test_role_ineligible_skipped(self) -> None:
+        # PR with current-head REQUEST_CHANGES expects author, not reviewer.
+        cand = WorkCandidate(
+            kind="pr",
+            number=9,
+            head_sha="b" * 40,
+            request_changes_current_head=True,
+        )
+        self.assertEqual(expected_role_for_candidate(cand), "author")
+        res = self._alloc(
+            role="reviewer",
+            profile_name="prgs-reviewer",
+            candidates=[cand],
+            apply=False,
+        )
+        self.assertEqual(res["outcome"], OUTCOME_NO_SAFE)
+        self.assertTrue(any("expects role" in s["reason"] for s in res["skipped"]))
+
+    def test_terminal_lock_blocks_downstream_reviewer_prs(self) -> None:
+        self.db.set_terminal_lock(
+            remote="prgs",
+            org="org",
+            repo="repo",
+            terminal_pr=10,
+            decision="request_changes",
+            status="active",
+        )
+        cands = [
+            WorkCandidate(kind="pr", number=11, head_sha="c" * 40, priority=5),
+            WorkCandidate(kind="pr", number=10, head_sha="d" * 40, priority=1),
+        ]
+        res = self._alloc(
+            role="reviewer",
+            profile_name="prgs-reviewer",
+            candidates=cands,
+            apply=False,
+        )
+        # Terminal PR #10 is selectable; #11 skipped for terminal path.
+        self.assertEqual(res["selected"]["number"], 10)
+        self.assertTrue(
+            any(
+                s["number"] == 11 and "terminal-review lock" in s["reason"]
+                for s in res["skipped"]
+            )
+        )
+
+    def test_terminal_lock_blocks_all_when_only_downstream(self) -> None:
+        self.db.set_terminal_lock(
+            remote="prgs",
+            org="org",
+            repo="repo",
+            terminal_pr=10,
+            decision="request_changes",
+            status="active",
+        )
+        res = self._alloc(
+            role="reviewer",
+            profile_name="prgs-reviewer",
+            candidates=[
+                WorkCandidate(kind="pr", number=99, head_sha="e" * 40),
+            ],
+            apply=False,
+        )
+        self.assertEqual(res["outcome"], OUTCOME_BLOCKED_TERMINAL)
+
+    def test_no_work_structured(self) -> None:
+        res = self._alloc(candidates=[], apply=True)
+        self.assertEqual(res["outcome"], OUTCOME_NO_SAFE)
+        self.assertIsNone(res["selected"])
+        self.assertTrue(res["reasons"])
+
+    def test_rejects_incident_kind(self) -> None:
+        with self.assertRaises(InvalidWorkKindError):
+            WorkCandidate(kind="sentry_incident", number=1)
+
+    def test_612_downstream_marker_in_result(self) -> None:
+        res = self._alloc(
+            candidates=[
+                WorkCandidate(kind="issue", number=600, labels=("status:ready",))
+            ],
+            apply=True,
+        )
+        self.assertIn("612", res.get("downstream_note", ""))
+
+    def test_substrate_not_file_or_comment_lease(self) -> None:
+        res = self._alloc(
+            candidates=[
+                WorkCandidate(kind="issue", number=1, labels=("status:ready",))
+            ],
+            apply=True,
+        )
+        self.assertEqual(res["substrate"], "control_plane_db")
+        self.assertFalse(res["file_lock_only"])
+        self.assertFalse(res["comment_lease_only"])
+        self.assertEqual(
+            res["lease_proof"]["source"], "control_plane_db.assign_and_lease"
+        )
+
+    def test_candidate_from_dict(self) -> None:
+        c = candidate_from_dict(
+            {
+                "kind": "pr",
+                "number": 7,
+                "head_sha": "f" * 40,
+                "approval_on_current_head": True,
+                "mergeable": True,
+            }
+        )
+        self.assertEqual(expected_role_for_candidate(c), "merger")
+
+    def test_merger_gets_clean_approval(self) -> None:
+        c = WorkCandidate(
+            kind="pr",
+            number=3,
+            head_sha="1" * 40,
+            approval_on_current_head=True,
+            mergeable=True,
+            priority=100,
+        )
+        res = self._alloc(
+            role="merger",
+            profile_name="prgs-merger",
+            candidates=[c],
+            apply=True,
+            session_id="merger-1",
+        )
+        self.assertEqual(res["outcome"], OUTCOME_ASSIGNED)
+        self.assertEqual(res["assignment"]["work_number"], 3)
+        self.assertIn("merge", res["assignment"]["allowed_actions"])
+
+    def test_db_unavailable_fails_closed(self) -> None:
+        res = allocate_next_work(
+            None,  # type: ignore[arg-type]
+            session_id="x",
+            role="author",
+            remote="prgs",
+            org="o",
+            repo="r",
+            candidates=[],
+            apply=True,
+        )
+        self.assertFalse(res["success"])
+        self.assertIn("unavailable", res["reasons"][0].lower())
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_audit_reconciliation_mode.py

@@ -284,7 +284,7 @@ class TestTaskCapabilityMap(unittest.TestCase):
             required_permission("reconciliation_cleanup"),
             "gitea.branch.delete",
         )
-        self.assertEqual(required_role("reconciliation_cleanup"), "author")
+        self.assertEqual(required_role("reconciliation_cleanup"), "reconciler")
 
 
 if __name__ == "__main__":

tests/test_author_mutation_worktree.py

@@ -81,13 +81,14 @@ class TestPreflightIntegration(unittest.TestCase):
         mcp_server._preflight_resolved_role = "author"
         control_root = "/repo/Gitea-Tools"
         with mock.patch.object(mcp_server, "PROJECT_ROOT", control_root):
-            with mock.patch.dict(
-                "os.environ",
-                {"GITEA_TEST_PORCELAIN": ""},
-                clear=False,
-            ):
-                with self.assertRaises(RuntimeError) as ctx:
-                    mcp_server.verify_preflight_purity()
+            with mock.patch.object(mcp_server, "_enforce_root_checkout_guard"):
+                with mock.patch.dict(
+                    "os.environ",
+                    {"GITEA_TEST_PORCELAIN": ""},
+                    clear=False,
+                ):
+                    with self.assertRaises(RuntimeError) as ctx:
+                        mcp_server.verify_preflight_purity()
         self.assertIn("Branches-only mutation guard", str(ctx.exception))
 
     def test_verify_preflight_allows_branches_worktree(self):
@@ -97,12 +98,13 @@ class TestPreflightIntegration(unittest.TestCase):
         mcp_server._preflight_capability_called = True
         mcp_server._preflight_resolved_role = "author"
         worktree = "/repo/Gitea-Tools/branches/issue-274"
-        with mock.patch.dict(
-            "os.environ",
-            {"GITEA_TEST_PORCELAIN": ""},
-            clear=False,
-        ):
-            mcp_server.verify_preflight_purity(worktree_path=worktree)
+        with mock.patch.object(mcp_server, "_enforce_root_checkout_guard"):
+            with mock.patch.dict(
+                "os.environ",
+                {"GITEA_TEST_PORCELAIN": ""},
+                clear=False,
+            ):
+                mcp_server.verify_preflight_purity(worktree_path=worktree)
 
 
 if __name__ == "__main__":

tests/test_branch_cleanup_guard.py

@@ -0,0 +1,187 @@
+import sys
+import unittest
+from unittest.mock import patch
+
+sys.path.insert(0, str(__import__("pathlib").Path(__file__).resolve().parent.parent))
+
+import branch_cleanup_guard as guard  # noqa: E402
+import mcp_server  # noqa: E402
+import task_capability_map  # noqa: E402
+from final_report_validator import assess_final_report_validator  # noqa: E402
+from mcp_server import gitea_cleanup_merged_pr_branch  # noqa: E402
+
+FAKE_AUTH = "token fake"
+
+
+class TestRawBranchDeleteGuard(unittest.TestCase):
+    def test_detects_local_and_remote_raw_git_delete_commands(self):
+        text = """
+        Cleanup mutations:
+        - git branch -d feat/issue-485-lease-comments-non-list-guard
+        - git push prgs --delete feat/issue-485-lease-comments-non-list-guard
+        """
+        commands = guard.raw_branch_delete_commands(text)
+        self.assertEqual(len(commands), 2)
+        self.assertIn("git branch -d", commands[0])
+        self.assertIn("git push prgs --delete", commands[1])
+
+    def test_final_report_blocks_raw_delete_as_cleanup_proof(self):
+        report = """
+        ## Controller Handoff
+        - Task: review_pr
+        - Cleanup mutations: git push prgs --delete feat/branch
+        """
+        result = assess_final_report_validator(report, "review_pr")
+        self.assertTrue(result["blocked"])
+        self.assertTrue(
+            any("shared.raw_branch_delete_bypass" in r for r in result["reasons"])
+        )
+
+    def test_cleanup_task_requires_branch_delete_capability(self):
+        self.assertEqual(
+            task_capability_map.required_permission("cleanup_merged_pr_branch"),
+            "gitea.branch.delete",
+        )
+        self.assertEqual(
+            task_capability_map.required_role("cleanup_merged_pr_branch"),
+            "reconciler",
+        )
+
+
+class TestMergedPrBranchCleanupTool(unittest.TestCase):
+    def setUp(self):
+        self._remotes = patch.dict(
+            mcp_server.REMOTES,
+            {
+                "prgs": {
+                    "host": "gitea.example.com",
+                    "org": "Example-Org",
+                    "repo": "Example-Repo",
+                }
+            },
+        )
+        self._remotes.start()
+        patch("gitea_audit.audit_enabled", return_value=False).start()
+        self.mock_api = patch("mcp_server.api_request").start()
+        self.mock_all = patch("mcp_server.api_get_all", return_value=[]).start()
+        patch("mcp_server.get_auth_header", return_value=FAKE_AUTH).start()
+        patch(
+            "mcp_server.merged_cleanup_reconcile.is_head_ancestor_of_ref",
+            return_value=True,
+        ).start()
+
+    def tearDown(self):
+        patch.stopall()
+
+    def test_reviewer_without_delete_authority_fails_closed(self):
+        patch(
+            "mcp_server.get_profile",
+            return_value={
+                "profile_name": "reviewer",
+                "allowed_operations": ["gitea.read", "gitea.pr.review"],
+                "forbidden_operations": ["gitea.branch.delete"],
+            },
+        ).start()
+        res = gitea_cleanup_merged_pr_branch(
+            pr_number=487,
+            confirmation="CLEANUP MERGED PR 487 BRANCH feat/branch",
+            branch="feat/branch",
+            remote="prgs",
+            worktree_path="/tmp/repo/branches/cleanup",
+        )
+        self.assertFalse(res["performed"])
+        self.assertEqual(res["required_permission"], "gitea.branch.delete")
+        self.mock_api.assert_not_called()
+
+    def test_root_checkout_cleanup_fails_closed(self):
+        patch(
+            "mcp_server.get_profile",
+            return_value={
+                "profile_name": "branch-cleanup",
+                "allowed_operations": ["gitea.read", "gitea.branch.delete"],
+                "forbidden_operations": [],
+            },
+        ).start()
+        res = gitea_cleanup_merged_pr_branch(
+            pr_number=487,
+            confirmation="CLEANUP MERGED PR 487 BRANCH feat/branch",
+            branch="feat/branch",
+            remote="prgs",
+            worktree_path="/tmp/repo/Gitea-Tools",
+        )
+        self.assertFalse(res["performed"])
+        self.assertIn("root checkout", " ".join(res["reasons"]))
+        self.mock_api.assert_not_called()
+
+    def test_authorized_cleanup_deletes_through_api_path(self):
+        branch = "feat/issue-485-lease-comments-non-list-guard"
+        patch(
+            "mcp_server.get_profile",
+            return_value={
+                "profile_name": "branch-cleanup",
+                "allowed_operations": ["gitea.read", "gitea.branch.delete"],
+                "forbidden_operations": [],
+            },
+        ).start()
+        self.mock_api.side_effect = [
+            {
+                "number": 487,
+                "merged": True,
+                "merged_at": "2026-07-08T01:00:00Z",
+                "head": {"ref": branch, "sha": "a" * 40},
+                "base": {"ref": "master"},
+            },
+            {},
+            {},
+        ]
+        res = gitea_cleanup_merged_pr_branch(
+            pr_number=487,
+            confirmation=f"CLEANUP MERGED PR 487 BRANCH {branch}",
+            branch=branch,
+            remote="prgs",
+            worktree_path="/tmp/repo/branches/cleanup",
+        )
+        self.assertTrue(res["performed"])
+        delete_calls = [
+            call for call in self.mock_api.call_args_list if call.args[0] == "DELETE"
+        ]
+        self.assertEqual(len(delete_calls), 1)
+        self.assertIn("branches/feat%2Fissue-485", delete_calls[0].args[1])
+
+    def test_confirmation_required_before_delete(self):
+        branch = "feat/issue-485-lease-comments-non-list-guard"
+        patch(
+            "mcp_server.get_profile",
+            return_value={
+                "profile_name": "branch-cleanup",
+                "allowed_operations": ["gitea.read", "gitea.branch.delete"],
+                "forbidden_operations": [],
+            },
+        ).start()
+        self.mock_api.side_effect = [
+            {
+                "number": 487,
+                "merged": True,
+                "merged_at": "2026-07-08T01:00:00Z",
+                "head": {"ref": branch, "sha": "a" * 40},
+                "base": {"ref": "master"},
+            },
+            {},
+        ]
+        res = gitea_cleanup_merged_pr_branch(
+            pr_number=487,
+            confirmation="wrong",
+            branch=branch,
+            remote="prgs",
+            worktree_path="/tmp/repo/branches/cleanup",
+        )
+        self.assertFalse(res["performed"])
+        self.assertIn("confirmation", " ".join(res["reasons"]))
+        delete_calls = [
+            call for call in self.mock_api.call_args_list if call.args[0] == "DELETE"
+        ]
+        self.assertFalse(delete_calls)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_canonical_comment_validator.py

@@ -0,0 +1,217 @@
+"""Unit tests for canonical_comment_validator (#496)."""
+
+import unittest
+
+import canonical_comment_validator as ccv
+
+FULL_SHA = "a" * 40
+
+_VALID_ISSUE = f"""## Canonical Issue State
+
+STATE: ready-for-author
+WHO_IS_NEXT: author
+NEXT_ACTION: Implement canonical comment validator and wire MCP gates
+NEXT_PROMPT:
+```text
+You are the author LLM for issue #496. Add canonical_comment_validator.py
+and wire fail-closed gates into gitea_create_issue_comment.
+```
+WHAT_HAPPENED: Issue filed for MCP validation wall
+WHY: Workflow comments must carry durable next-action state
+RELATED_PRS: none
+BLOCKERS: none
+VALIDATION: unit tests not yet run
+LAST_UPDATED_BY: prgs-author
+"""
+
+_VALID_PR = f"""## Canonical PR State
+
+STATE: ready-for-review
+WHO_IS_NEXT: reviewer
+NEXT_ACTION: Run focused pytest and review the validator wiring diff
+NEXT_PROMPT:
+```text
+Review PR for issue #496. Confirm casual comments still post and workflow
+comments without canonical fields are rejected before the Gitea API call.
+```
+WHAT_HAPPENED: Author opened PR with validator module
+WHY: Fail-closed enforcement belongs at the MCP boundary
+ISSUE: #496
+HEAD_SHA: {FULL_SHA}
+REVIEW_STATUS: pending
+MERGE_READY: false
+BLOCKERS: none
+VALIDATION: not yet run
+LAST_UPDATED_BY: prgs-author
+"""
+
+_VALID_SUPERSEDED = """## Canonical PR State
+
+STATE: superseded
+WHO_IS_NEXT: reconciler
+NEXT_ACTION: Close superseded issue after canonical issue #495 lands
+NEXT_PROMPT:
+```text
+Close issue #494 as superseded by #495 once templates and docs are merged.
+```
+WHY: Duplicate tracking issue replaced by durable canonical template work
+CANONICAL_ITEM: issue #495
+SUPERSEDED_ITEM: issue #494
+CLOSE_OR_KEEP_OPEN: close superseded issue #494 after #495 merges
+"""
+
+_VALID_BLOCKED = """## Canonical Issue State
+
+STATE: blocked
+WHO_IS_NEXT: author
+NEXT_ACTION: Fix failing validator unit tests before requesting re-review
+NEXT_PROMPT:
+```text
+Run pytest tests/test_canonical_comment_validator.py and repair failures.
+```
+WHAT_HAPPENED: Validator tests failed in CI
+WHY: Blocked until test suite is green
+RELATED_PRS: PR #500
+BLOCKERS: pytest failures; unblock after all validator tests pass
+VALIDATION: pytest failed
+LAST_UPDATED_BY: prgs-author
+"""
+
+_VALID_READY_TO_MERGE = f"""## Canonical PR State
+
+STATE: ready-to-merge
+WHO_IS_NEXT: merger
+NEXT_ACTION: Merge PR after confirming approval_at_current_head
+NEXT_PROMPT:
+```text
+Merge PR #500 for issue #496 after live mergeable check passes.
+```
+WHAT_HAPPENED: Reviewer approved at current head
+WHY: All gates passed and head SHA is current
+ISSUE: #496
+HEAD_SHA: {FULL_SHA}
+REVIEW_STATUS: approved / approval_at_current_head
+MERGE_READY: true
+BLOCKERS: none
+VALIDATION: pytest passed; reviewer approved at head {FULL_SHA}
+LAST_UPDATED_BY: prgs-reviewer
+"""
+
+
+class TestCanonicalCommentDetection(unittest.TestCase):
+    def test_casual_comment_not_workflow(self):
+        self.assertFalse(ccv.is_workflow_changing_comment("Thanks, I will check this."))
+
+    def test_workflow_trigger_detected(self):
+        self.assertTrue(ccv.is_workflow_changing_comment("Blocked, author should fix."))
+
+    def test_machine_marker_exempt(self):
+        body = "<!-- mcp-review-lease:v1 -->\nphase: claimed"
+        self.assertFalse(ccv.is_workflow_changing_comment(body))
+
+
+class TestCanonicalCommentValidation(unittest.TestCase):
+    def test_casual_comment_allowed(self):
+        result = ccv.assess_canonical_comment("Thanks, I will check this.")
+        self.assertTrue(result["allowed"])
+        self.assertFalse(result["is_workflow_comment"])
+
+    def test_workflow_comment_missing_fields_rejected(self):
+        result = ccv.assess_canonical_comment("Blocked, author should fix.")
+        self.assertFalse(result["allowed"])
+        self.assertTrue(result["is_workflow_comment"])
+        self.assertIn("WHO_IS_NEXT", result["missing_fields"])
+        self.assertIn("correction_message", result)
+        self.assertIn("Suggested template", result["correction_message"])
+
+    def test_missing_next_prompt_rejected(self):
+        body = """STATE: blocked
+WHO_IS_NEXT: author
+NEXT_ACTION: Repair the failing validator unit tests in CI
+WHY: Tests must pass before merge
+BLOCKERS: pytest failed; unblock after tests pass
+VALIDATION: failed
+"""
+        result = ccv.assess_canonical_comment(body)
+        self.assertFalse(result["allowed"])
+        self.assertIn("NEXT_PROMPT", result["missing_fields"] + result["vague_fields"])
+
+    def test_vague_next_action_rejected(self):
+        body = _VALID_ISSUE.replace(
+            "Implement canonical comment validator and wire MCP gates",
+            "continue",
+        )
+        result = ccv.assess_canonical_comment(body)
+        self.assertFalse(result["allowed"])
+        self.assertIn("NEXT_ACTION", result["vague_fields"])
+
+    def test_invalid_who_is_next_rejected(self):
+        body = _VALID_ISSUE.replace("WHO_IS_NEXT: author", "WHO_IS_NEXT: llm")
+        result = ccv.assess_canonical_comment(body)
+        self.assertFalse(result["allowed"])
+        self.assertIn("WHO_IS_NEXT", result["vague_fields"])
+
+    def test_valid_issue_comment_allowed(self):
+        result = ccv.assess_canonical_comment(_VALID_ISSUE)
+        self.assertTrue(result["allowed"])
+
+    def test_issue_comment_mentioning_pr_requires_related_prs(self):
+        body = _VALID_ISSUE.replace("RELATED_PRS: none", "RELATED_PRS:")
+        body = body.replace("Issue filed", "Issue filed; see PR #500")
+        result = ccv.assess_canonical_comment(body)
+        self.assertFalse(result["allowed"])
+        self.assertIn("RELATED_PRS", result["missing_fields"])
+
+    def test_pr_review_requires_head_sha(self):
+        body = _VALID_PR.replace(f"HEAD_SHA: {FULL_SHA}", "HEAD_SHA:")
+        result = ccv.assess_canonical_comment(body, context="pr_review")
+        self.assertFalse(result["allowed"])
+        self.assertIn("HEAD_SHA", result["missing_fields"])
+
+    def test_ready_to_merge_requires_approval_and_sha_proof(self):
+        body = _VALID_READY_TO_MERGE.replace("approval_at_current_head", "pending")
+        body = body.replace(f"HEAD_SHA: {FULL_SHA}", "HEAD_SHA: pending")
+        body = body.replace("reviewer approved at head", "reviewer pending at head")
+        body = body.replace("approved /", "pending /")
+        result = ccv.assess_canonical_comment(body, context="pr_comment")
+        self.assertFalse(result["allowed"])
+        self.assertTrue(result["extra_reasons"])
+
+    def test_ready_to_merge_valid_allowed(self):
+        result = ccv.assess_canonical_comment(_VALID_READY_TO_MERGE, context="pr_comment")
+        self.assertTrue(result["allowed"])
+
+    def test_superseded_requires_canonical_and_superseded_items(self):
+        body = _VALID_SUPERSEDED.replace("CANONICAL_ITEM: issue #495", "CANONICAL_ITEM:")
+        result = ccv.assess_canonical_comment(body, context="supersession")
+        self.assertFalse(result["allowed"])
+        self.assertIn("CANONICAL_ITEM", result["missing_fields"])
+
+    def test_superseded_valid_allowed(self):
+        result = ccv.assess_canonical_comment(_VALID_SUPERSEDED, context="supersession")
+        self.assertTrue(result["allowed"])
+
+    def test_blocked_requires_unblock_condition(self):
+        body = _VALID_BLOCKED.replace(
+            "BLOCKERS: pytest failures; unblock after all validator tests pass",
+            "BLOCKERS: pytest failures",
+        )
+        result = ccv.assess_canonical_comment(body)
+        self.assertFalse(result["allowed"])
+        self.assertIn("BLOCKERS", result["vague_fields"])
+
+    def test_blocked_valid_allowed(self):
+        result = ccv.assess_canonical_comment(_VALID_BLOCKED)
+        self.assertTrue(result["allowed"])
+
+    def test_correction_lists_missing_fields(self):
+        result = ccv.assess_canonical_comment("ready for merge")
+        self.assertFalse(result["allowed"])
+        message = result["correction_message"]
+        self.assertIn("Missing fields", message)
+        self.assertIn("WHO_IS_NEXT", message)
+        self.assertIn("Suggested template", message)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_canonical_state_comments.py

@@ -0,0 +1,143 @@
+"""Tests for canonical state comment validation (#495)."""
+import sys
+import unittest
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+from canonical_state_comments import (  # noqa: E402
+    validate_canonical_state_comment,
+    validate_final_report_state_update,
+)
+
+
+GOOD_ISSUE_STATE = """## Canonical Issue State
+
+STATE:
+ready-for-author
+
+WHO_IS_NEXT:
+author
+
+NEXT_ACTION:
+Implement the focused validator and open a PR.
+
+NEXT_PROMPT:
+Find issue #495, load the work-issue workflow, implement the validator, and open a PR.
+
+WHAT_HAPPENED:
+Controller selected the canonical tracking issue.
+
+WHY:
+The duplicate issue points here as canonical.
+
+RELATED_PRS:
+none
+
+BRANCH:
+none
+
+HEAD_SHA:
+none
+
+VALIDATION:
+none
+
+BLOCKERS:
+none
+"""
+
+
+class TestCanonicalStateComments(unittest.TestCase):
+    def test_good_issue_state_validates(self):
+        result = validate_canonical_state_comment(GOOD_ISSUE_STATE)
+        self.assertTrue(result["valid"])
+        self.assertEqual(result["reasons"], [])
+
+    def test_missing_next_actor_is_rejected(self):
+        result = validate_canonical_state_comment(
+            GOOD_ISSUE_STATE.replace("WHO_IS_NEXT:\nauthor", "WHO_IS_NEXT:\n")
+        )
+        self.assertFalse(result["valid"])
+        self.assertIn("WHO_IS_NEXT", " ".join(result["reasons"]))
+
+    def test_missing_next_prompt_is_rejected(self):
+        result = validate_canonical_state_comment(
+            GOOD_ISSUE_STATE.replace(
+                "NEXT_PROMPT:\nFind issue #495, load the work-issue workflow, implement the validator, and open a PR.",
+                "NEXT_PROMPT:\n",
+            )
+        )
+        self.assertFalse(result["valid"])
+        self.assertIn("NEXT_PROMPT", " ".join(result["reasons"]))
+
+    def test_vague_next_action_is_rejected(self):
+        result = validate_canonical_state_comment(
+            GOOD_ISSUE_STATE.replace(
+                "NEXT_ACTION:\nImplement the focused validator and open a PR.",
+                "NEXT_ACTION:\ncontinue",
+            )
+        )
+        self.assertFalse(result["valid"])
+        self.assertIn("too vague", " ".join(result["reasons"]))
+
+    def test_ready_to_merge_requires_approval_and_head_sha(self):
+        text = """## Canonical PR State
+
+STATE:
+ready-to-merge
+
+WHO_IS_NEXT:
+merger
+
+NEXT_ACTION:
+Merge PR #12 after checking the current head.
+
+NEXT_PROMPT:
+Load the merge workflow and merge PR #12 if gates pass.
+
+ISSUE:
+#11
+
+HEAD_SHA:
+abc123
+
+REVIEW_STATUS:
+none
+
+MERGE_READY:
+yes
+"""
+        result = validate_canonical_state_comment(text)
+        self.assertFalse(result["valid"])
+        reasons = " ".join(result["reasons"])
+        self.assertIn("approved REVIEW_STATUS", reasons)
+        self.assertIn("full HEAD_SHA", reasons)
+
+    def test_superseded_requires_canonical_item(self):
+        text = GOOD_ISSUE_STATE.replace("STATE:\nready-for-author", "STATE:\nsuperseded")
+        result = validate_canonical_state_comment(text)
+        self.assertFalse(result["valid"])
+        self.assertIn("canonical item", " ".join(result["reasons"]))
+
+    def test_blocked_requires_unblock_condition(self):
+        text = GOOD_ISSUE_STATE.replace("STATE:\nready-for-author", "STATE:\nblocked")
+        text = text.replace("BLOCKERS:\nnone", "BLOCKERS:\n")
+        result = validate_canonical_state_comment(text)
+        self.assertFalse(result["valid"])
+        self.assertIn("BLOCKERS", " ".join(result["reasons"]))
+
+    def test_final_report_claim_without_block_is_rejected(self):
+        report = "Posted canonical state comment on issue #495."
+        result = validate_final_report_state_update(report)
+        self.assertTrue(result["applicable"])
+        self.assertFalse(result["valid"])
+
+    def test_final_report_without_state_claim_not_applicable(self):
+        result = validate_final_report_state_update("ordinary final report")
+        self.assertFalse(result["applicable"])
+        self.assertTrue(result["valid"])
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_canonical_thread_handoff.py

@@ -0,0 +1,139 @@
+"""Tests for Canonical Thread Handoff (CTH) protocol (#505)."""
+
+from __future__ import annotations
+
+import sys
+import unittest
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+import canonical_thread_handoff as cth  # noqa: E402
+
+REPO_ROOT = Path(__file__).resolve().parent.parent
+RUNBOOK = REPO_ROOT / "docs" / "llm-workflow-runbooks.md"
+PROTOCOL_DOC = REPO_ROOT / "docs" / "canonical-thread-handoff.md"
+TEMPLATE = REPO_ROOT / "skills" / "llm-project-workflow/templates" / "canonical-thread-handoff.md"
+REVIEW_WORKFLOW = REPO_ROOT / "skills" / "llm-project-workflow/workflows" / "review-merge-pr.md"
+WORK_WORKFLOW = REPO_ROOT / "skills" / "llm-project-workflow/workflows" / "work-issue.md"
+REVIEW_TEMPLATE = REPO_ROOT / "skills" / "llm-project-workflow/templates" / "review-pr.md"
+START_TEMPLATE = REPO_ROOT / "skills" / "llm-project-workflow/templates" / "start-issue.md"
+MERGE_TEMPLATE = REPO_ROOT / "skills" / "llm-project-workflow/templates" / "merge-pr.md"
+
+
+class TestCthModule(unittest.TestCase):
+    def test_defines_cth_term_and_types(self):
+        self.assertEqual(cth.CTH_ABBREV, "CTH")
+        self.assertIn("State Handoff", cth.CTH_TYPES)
+        self.assertIn("Reviewer Handoff", cth.CTH_TYPES)
+        self.assertIn("Blocker", cth.CTH_TYPES)
+
+    def test_format_and_parse_round_trip(self):
+        body = cth.format_cth_body(
+            cth_type="Author Handoff",
+            status="implementation_complete",
+            next_owner="reviewer",
+            current_blocker="none",
+            decision="PR opened",
+            proof="pytest passed",
+            next_action="review PR #9",
+            ready_to_paste_prompt="Review PR #9 for issue #5",
+        )
+        parsed = cth.parse_cth_comment(body)
+        self.assertIsNotNone(parsed)
+        self.assertEqual(parsed["cth_type"], "Author Handoff")
+        self.assertEqual(parsed["fields"]["status"], "implementation_complete")
+        self.assertEqual(parsed["fields"]["next owner"], "reviewer")
+
+    def test_valid_cth_passes_assessment(self):
+        body = cth.format_cth_body(
+            cth_type="Reviewer Handoff",
+            status="approved",
+            next_owner="merger",
+            current_blocker="none",
+            decision="APPROVE",
+            proof="review id 42",
+            next_action="merge if gates pass",
+            ready_to_paste_prompt="Merge PR #12 with pinned head abcdef0123456789abcdef0123456789abcdef01",
+        )
+        result = cth.assess_cth_comment(body)
+        self.assertFalse(result["block"])
+        self.assertTrue(result["valid"])
+
+    def test_missing_fields_fail_closed(self):
+        body = "## CTH: Blocker\n\nStatus: blocked\n"
+        result = cth.assess_cth_comment(body)
+        self.assertTrue(result["block"])
+        self.assertIn("missing required fields", result["reasons"][0])
+
+    def test_find_latest_cth_prefers_newer_comment(self):
+        older = cth.format_cth_body(
+            cth_type="State Handoff",
+            status="old",
+            next_owner="author",
+            current_blocker="none",
+            decision="old",
+            proof="old",
+            next_action="old",
+            ready_to_paste_prompt="old prompt text here",
+        )
+        newer = cth.format_cth_body(
+            cth_type="Reviewer Handoff",
+            status="new",
+            next_owner="merger",
+            current_blocker="none",
+            decision="approve",
+            proof="new",
+            next_action="merge",
+            ready_to_paste_prompt="merge PR #3 now with pinned head",
+        )
+        comments = [
+            {"id": 1, "created_at": "2026-07-01T10:00:00Z", "body": older},
+            {"id": 2, "created_at": "2026-07-02T10:00:00Z", "body": newer},
+        ]
+        latest = cth.find_latest_cth(comments)
+        self.assertEqual(latest["comment_id"], 2)
+        self.assertEqual(latest["cth_type"], "Reviewer Handoff")
+
+    def test_cth_does_not_replace_formal_reviews_documented_in_protocol(self):
+        text = PROTOCOL_DOC.read_text(encoding="utf-8")
+        self.assertIn("do not replace", text.lower())
+        self.assertIn("formal Gitea review", text)
+
+    def test_examples_cover_required_scenarios(self):
+        text = PROTOCOL_DOC.read_text(encoding="utf-8")
+        expected_phrases = (
+            "PR approved and ready for merger",
+            "request-changes back to author",
+            "superseded PR closure",
+            "dirty root/worktree",
+            "Stale head requiring fresh review",
+            "Issue implementation handoff",
+        )
+        for phrase in expected_phrases:
+            self.assertIn(phrase, text)
+
+
+class TestCthDocumentationChecks(unittest.TestCase):
+    def test_runbook_references_cth_discovery_and_posting(self):
+        text = RUNBOOK.read_text(encoding="utf-8")
+        self.assertIn("Canonical Thread Handoff", text)
+        self.assertIn("Find the latest CTH comment", text)
+        self.assertIn("Post a new CTH", text)
+        self.assertIn("canonical-thread-handoff.md", text)
+
+    def test_workflows_reference_cth_rules(self):
+        for path in (REVIEW_WORKFLOW, WORK_WORKFLOW):
+            text = path.read_text(encoding="utf-8")
+            self.assertIn("latest CTH comment", text)
+            self.assertIn("canonical-thread-handoff.md", text)
+
+    def test_prompt_templates_reference_cth_rules(self):
+        for path in (REVIEW_TEMPLATE, START_TEMPLATE, MERGE_TEMPLATE, TEMPLATE):
+            text = path.read_text(encoding="utf-8")
+            self.assertIn("CTH", text)
+            self.assertIn("canonical-thread-handoff", text)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_config_v2_contexts.py

@@ -435,6 +435,40 @@ class ValidateConfigTests(unittest.TestCase):
         with open(example, encoding="utf-8") as fh:
             self.assertEqual(gitea_config.validate_config(json.load(fh)), [])
 
+    def test_repo_example_file_reviewer_vs_merger_boundaries(self):
+        example_path = __import__("pathlib").Path(__file__).resolve().parent.parent \
+            / "gitea-mcp.v2-contexts.example.json"
+        with open(example_path, encoding="utf-8") as fh:
+            cfg = json.load(fh)
+
+        # 1. Config includes separate reviewer and merger examples
+        self.assertIn("example-reviewer", cfg["profiles"])
+        self.assertIn("example-merger", cfg["profiles"])
+
+        reviewer = cfg["profiles"]["example-reviewer"]
+        merger = cfg["profiles"]["example-merger"]
+
+        # 2. Example reviewer config does not include merge capability
+        reviewer_allowed = reviewer.get("allowed_operations") or []
+        reviewer_forbidden = reviewer.get("forbidden_operations") or []
+
+        self.assertNotIn("merge", reviewer_allowed)
+        self.assertNotIn("gitea.pr.merge", reviewer_allowed)
+        self.assertIn("merge", reviewer_forbidden)
+
+        # 3. Example reviewer can resolve review task, cannot resolve merge task
+        # 4. Example merger can resolve merge task
+        rev_review_ok, _ = gitea_config.check_operation("gitea.pr.review", reviewer_allowed, reviewer_forbidden)
+        rev_merge_ok, _ = gitea_config.check_operation("gitea.pr.merge", reviewer_allowed, reviewer_forbidden)
+
+        merg_allowed = merger.get("allowed_operations") or []
+        merg_forbidden = merger.get("forbidden_operations") or []
+        merg_merge_ok, _ = gitea_config.check_operation("gitea.pr.merge", merg_allowed, merg_forbidden)
+
+        self.assertTrue(rev_review_ok, "example-reviewer must allow review")
+        self.assertFalse(rev_merge_ok, "example-reviewer must not allow merge")
+        self.assertTrue(merg_merge_ok, "example-merger must allow merge")
+
     def test_broken_contexts_config_reports_problems(self):
         data = contexts_config()
         data["profiles"]["prgs-author"]["context"] = "nope"

tests/test_conflict_fix_classification.py

@@ -0,0 +1,142 @@
+"""Tests for live PR head re-pin before conflict-fix classification (#522)."""
+
+from __future__ import annotations
+
+import unittest
+
+from conflict_fix_classification import (
+    CLASSIFICATION_CONFLICT_FIX_NEEDED,
+    CLASSIFICATION_INCOMPLETE,
+    CLASSIFICATION_LIVE_MERGEABLE,
+    CLASSIFICATION_STALE_INVENTORY_SKIP,
+    assess_conflict_fix_classification,
+    assess_conflict_fix_classification_final_report,
+)
+
+
+def _sha(prefix: str) -> str:
+    return (prefix + "0" * 40)[:40]
+
+
+class TestConflictFixClassification(unittest.TestCase):
+    def test_stale_inventory_mergeable_skip(self):
+        """PR #508 style: inventory mergeable:false/stale head, live mergeable:true."""
+        result = assess_conflict_fix_classification(
+            pr_number=508,
+            inventory_head_sha=_sha("dad1dc8"),
+            inventory_mergeable=False,
+            live_head_sha=_sha("3f3d6cb"),
+            live_mergeable=True,
+        )
+        self.assertEqual(result["classification"], CLASSIFICATION_STALE_INVENTORY_SKIP)
+        self.assertTrue(result["skip_author_mutation"])
+        self.assertFalse(result["worktree_allowed"])
+        self.assertTrue(result["inventory_stale_head"])
+        self.assertTrue(result["inventory_stale_mergeable"])
+        self.assertEqual(result["pinned_head_sha"], _sha("3f3d6cb"))
+
+    def test_stale_inventory_head_only_live_mergeable_true(self):
+        """PR #493 style: head moved; live still mergeable."""
+        result = assess_conflict_fix_classification(
+            pr_number=493,
+            inventory_head_sha=_sha("685e627"),
+            inventory_mergeable=True,
+            live_head_sha=_sha("4561d7a"),
+            live_mergeable=True,
+        )
+        self.assertEqual(result["classification"], CLASSIFICATION_STALE_INVENTORY_SKIP)
+        self.assertTrue(result["skip_author_mutation"])
+        self.assertFalse(result["worktree_allowed"])
+        self.assertTrue(result["inventory_stale_head"])
+        self.assertEqual(result["pinned_head_sha"], _sha("4561d7a"))
+
+    def test_live_conflict_allows_worktree_on_pinned_head(self):
+        result = assess_conflict_fix_classification(
+            pr_number=99,
+            inventory_head_sha=_sha("aaaaaaa"),
+            inventory_mergeable=False,
+            live_head_sha=_sha("bbbbbbb"),
+            live_mergeable=False,
+        )
+        self.assertEqual(result["classification"], CLASSIFICATION_CONFLICT_FIX_NEEDED)
+        self.assertTrue(result["worktree_allowed"])
+        self.assertFalse(result["skip_author_mutation"])
+        self.assertTrue(result["inventory_stale_head"])
+        self.assertEqual(result["pinned_head_sha"], _sha("bbbbbbb"))
+
+    def test_matching_inventory_live_mergeable_skip(self):
+        head = _sha("cccccccc")
+        result = assess_conflict_fix_classification(
+            pr_number=10,
+            inventory_head_sha=head,
+            inventory_mergeable=True,
+            live_head_sha=head,
+            live_mergeable=True,
+        )
+        self.assertEqual(result["classification"], CLASSIFICATION_LIVE_MERGEABLE)
+        self.assertFalse(result["worktree_allowed"])
+        self.assertTrue(result["skip_author_mutation"])
+        self.assertFalse(result["inventory_stale_head"])
+
+    def test_missing_live_head_incomplete(self):
+        result = assess_conflict_fix_classification(
+            pr_number=1,
+            inventory_head_sha=_sha("ddddddd"),
+            inventory_mergeable=False,
+            live_head_sha=None,
+            live_mergeable=False,
+        )
+        self.assertEqual(result["classification"], CLASSIFICATION_INCOMPLETE)
+        self.assertFalse(result["worktree_allowed"])
+        self.assertTrue(result["skip_author_mutation"])
+        self.assertTrue(any("live PR head" in r for r in result["reasons"]))
+
+    def test_short_sha_rejected(self):
+        result = assess_conflict_fix_classification(
+            pr_number=1,
+            inventory_head_sha="abc1234",
+            inventory_mergeable=False,
+            live_head_sha="def5678",
+            live_mergeable=False,
+        )
+        self.assertEqual(result["classification"], CLASSIFICATION_INCOMPLETE)
+        self.assertFalse(result["worktree_allowed"])
+
+
+class TestConflictFixClassificationFinalReport(unittest.TestCase):
+    def test_non_conflict_report_not_applicable(self):
+        result = assess_conflict_fix_classification_final_report(
+            "Implemented feature without merge issues."
+        )
+        self.assertTrue(result["proven"])
+        self.assertFalse(result["applicable"])
+
+    def test_conflict_report_requires_tool_live_head_classification(self):
+        result = assess_conflict_fix_classification_final_report(
+            "Did conflict-fix work on PR #99."
+        )
+        self.assertFalse(result["proven"])
+        self.assertTrue(result["applicable"])
+        joined = " ".join(result["reasons"])
+        self.assertIn("gitea_assess_conflict_fix_classification", joined)
+        self.assertIn("Live head SHA", joined)
+        self.assertIn("classification", joined.lower())
+
+    def test_good_conflict_report_passes(self):
+        live = _sha("3f3d6cb")
+        inv = _sha("dad1dc8")
+        text = f"""
+Conflict-fix classification: stale_inventory_skip
+Called gitea_assess_conflict_fix_classification before worktree creation.
+Inventory head SHA: {inv}
+Live head SHA: {live}
+Use live head only; skip author mutation.
+"""
+        result = assess_conflict_fix_classification_final_report(text)
+        self.assertTrue(result["proven"], msg=result.get("reasons"))
+        self.assertEqual(result["live_head_sha"], live)
+        self.assertEqual(result["inventory_head_sha"], inv)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_control_plane_db.py

@@ -0,0 +1,824 @@
+"""Tests for control-plane DB substrate (#613)."""
+
+from __future__ import annotations
+
+import os
+import tempfile
+import threading
+import unittest
+from concurrent.futures import ThreadPoolExecutor, as_completed
+from datetime import timedelta
+
+from control_plane_db import (
+    ControlPlaneDB,
+    InvalidWorkKindError,
+    LeaseRequiredError,
+    WORK_KINDS,
+    _ts,
+    _utc_now,
+)
+
+
+class ControlPlaneDBTest(unittest.TestCase):
+    def setUp(self) -> None:
+        self._tmp = tempfile.TemporaryDirectory()
+        self.db_path = os.path.join(self._tmp.name, "cp.sqlite3")
+        self.db = ControlPlaneDB(self.db_path)
+
+    def tearDown(self) -> None:
+        self._tmp.cleanup()
+
+    def test_schema_and_architecture_meta(self) -> None:
+        import sqlite3
+
+        conn = sqlite3.connect(self.db_path)
+        try:
+            rows = dict(conn.execute("SELECT key, value FROM schema_meta").fetchall())
+        finally:
+            conn.close()
+        self.assertEqual(rows["schema_version"], "2")
+        self.assertIn("DB coordinates", rows["architecture"])
+        self.assertIn("bridge", rows["architecture"].lower())
+
+    def test_rejects_raw_incident_as_work_kind(self) -> None:
+        with self.assertRaises(InvalidWorkKindError):
+            self.db.upsert_work_item(
+                remote="prgs",
+                org="org",
+                repo="repo",
+                kind="sentry_incident",
+                number=1,
+            )
+        with self.assertRaises(InvalidWorkKindError):
+            self.db.assign_and_lease(
+                session_id="s1",
+                role="author",
+                remote="prgs",
+                org="org",
+                repo="repo",
+                kind="glitchtip_incident",
+                number=9,
+            )
+        self.assertEqual(WORK_KINDS, frozenset({"issue", "pr"}))
+
+    def test_atomic_assign_and_lease_fields(self) -> None:
+        self.db.upsert_session(session_id="s-a", role="author", profile="prgs-author")
+        result = self.db.assign_and_lease(
+            session_id="s-a",
+            role="author",
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+            kind="issue",
+            number=613,
+            expected_head_sha="abc123",
+            allowed_actions=("implement", "comment"),
+            forbidden_actions=("approve", "merge"),
+        )
+        self.assertEqual(result.outcome, "assigned")
+        self.assertIsNotNone(result.assignment_id)
+        self.assertIsNotNone(result.lease_id)
+        self.assertEqual(result.role, "author")
+        self.assertEqual(result.work_kind, "issue")
+        self.assertEqual(result.work_number, 613)
+        self.assertEqual(result.expected_head_sha, "abc123")
+        self.assertIn("implement", result.allowed_actions)
+        self.assertIn("merge", result.forbidden_actions)
+        self.assertIsNotNone(result.expires_at)
+
+    def test_second_session_waits_on_foreign_lease(self) -> None:
+        self.db.upsert_session(session_id="s1", role="author")
+        self.db.upsert_session(session_id="s2", role="author")
+        first = self.db.assign_and_lease(
+            session_id="s1",
+            role="author",
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="pr",
+            number=100,
+            expected_head_sha="deadbeef",
+        )
+        self.assertEqual(first.outcome, "assigned")
+        second = self.db.assign_and_lease(
+            session_id="s2",
+            role="author",
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="pr",
+            number=100,
+            expected_head_sha="deadbeef",
+        )
+        self.assertEqual(second.outcome, "wait")
+        self.assertEqual(second.owner_session_id, "s1")
+
+    def test_owner_resume_refreshes_lease(self) -> None:
+        self.db.upsert_session(session_id="s1", role="reviewer")
+        a = self.db.assign_and_lease(
+            session_id="s1",
+            role="reviewer",
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="pr",
+            number=50,
+            expected_head_sha="head-50",
+        )
+        b = self.db.assign_and_lease(
+            session_id="s1",
+            role="reviewer",
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="pr",
+            number=50,
+            expected_head_sha="head-50",
+        )
+        self.assertEqual(b.outcome, "assigned")
+        self.assertEqual(b.lease_id, a.lease_id)
+        self.assertIn("owner-resume", b.reason)
+
+    def test_require_valid_assignment_gates_mutations(self) -> None:
+        self.db.upsert_session(session_id="s1", role="author")
+        self.db.assign_and_lease(
+            session_id="s1",
+            role="author",
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="issue",
+            number=7,
+            allowed_actions=("implement",),
+            forbidden_actions=("merge",),
+        )
+        proof = self.db.require_valid_assignment(
+            session_id="s1",
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="issue",
+            number=7,
+            action="implement",
+        )
+        self.assertEqual(proof["session_id"], "s1")
+        with self.assertRaises(LeaseRequiredError):
+            self.db.require_valid_assignment(
+                session_id="s1",
+                remote="prgs",
+                org="o",
+                repo="r",
+                kind="issue",
+                number=7,
+                action="merge",
+            )
+        with self.assertRaises(LeaseRequiredError):
+            self.db.require_valid_assignment(
+                session_id="s-other",
+                remote="prgs",
+                org="o",
+                repo="r",
+                kind="issue",
+                number=7,
+                action="implement",
+            )
+
+    def test_expired_lease_allows_reassign(self) -> None:
+        self.db.upsert_session(session_id="s1", role="author")
+        self.db.upsert_session(session_id="s2", role="author")
+        past = _utc_now() - timedelta(hours=1)
+        # Create lease already expired by using negative TTL edge via direct assign then expire
+        assigned = self.db.assign_and_lease(
+            session_id="s1",
+            role="author",
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="issue",
+            number=3,
+            lease_ttl_seconds=1,
+        )
+        self.assertEqual(assigned.outcome, "assigned")
+        # Force expiry in DB
+        import sqlite3
+
+        conn = sqlite3.connect(self.db_path)
+        try:
+            conn.execute(
+                "UPDATE leases SET expires_at = ? WHERE lease_id = ?",
+                (_ts(past), assigned.lease_id),
+            )
+            conn.commit()
+        finally:
+            conn.close()
+        n = self.db.expire_stale_leases()
+        self.assertGreaterEqual(n, 1)
+        second = self.db.assign_and_lease(
+            session_id="s2",
+            role="author",
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="issue",
+            number=3,
+        )
+        self.assertEqual(second.outcome, "assigned")
+        self.assertEqual(second.session_id, "s2")
+
+    def test_merged_work_never_assigned(self) -> None:
+        self.db.upsert_session(session_id="s1", role="merger")
+        self.db.upsert_work_item(
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="pr",
+            number=99,
+            state="merged",
+        )
+        result = self.db.assign_and_lease(
+            session_id="s1",
+            role="merger",
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="pr",
+            number=99,
+            expected_head_sha="merged-head",
+        )
+        self.assertEqual(result.outcome, "no_safe_work")
+
+    def test_four_concurrent_sessions_unique_assignments(self) -> None:
+        """Four concurrent assigners on four different issues — all succeed uniquely.
+
+        Also two concurrent assigners on the *same* issue: at most one assigned.
+        """
+        for i in range(4):
+            self.db.upsert_session(session_id=f"sess-{i}", role="author")
+
+        def claim_unique(i: int):
+            return self.db.assign_and_lease(
+                session_id=f"sess-{i}",
+                role="author",
+                remote="prgs",
+                org="o",
+                repo="r",
+                kind="issue",
+                number=1000 + i,
+            )
+
+        with ThreadPoolExecutor(max_workers=4) as pool:
+            results = [f.result() for f in as_completed([pool.submit(claim_unique, i) for i in range(4)])]
+        self.assertEqual({r.outcome for r in results}, {"assigned"})
+        numbers = sorted(r.work_number for r in results)
+        self.assertEqual(numbers, [1000, 1001, 1002, 1003])
+
+        # Contention on one item
+        self.db.upsert_session(session_id="c1", role="author")
+        self.db.upsert_session(session_id="c2", role="author")
+        self.db.upsert_session(session_id="c3", role="author")
+        self.db.upsert_session(session_id="c4", role="author")
+        barrier = threading.Barrier(4)
+        outcomes: list[str] = []
+        lock = threading.Lock()
+
+        def contend(sid: str) -> None:
+            barrier.wait()
+            res = self.db.assign_and_lease(
+                session_id=sid,
+                role="author",
+                remote="prgs",
+                org="o",
+                repo="r",
+                kind="issue",
+                number=7777,
+            )
+            with lock:
+                outcomes.append(res.outcome)
+
+        threads = [threading.Thread(target=contend, args=(f"c{i}",)) for i in range(1, 5)]
+        for t in threads:
+            t.start()
+        for t in threads:
+            t.join()
+        self.assertEqual(outcomes.count("assigned"), 1)
+        self.assertEqual(outcomes.count("wait"), 3)
+
+    def test_terminal_lock_index(self) -> None:
+        self.db.set_terminal_lock(
+            remote="prgs",
+            org="o",
+            repo="r",
+            terminal_pr=332,
+            review_id="rev-1",
+            decision="approve",
+        )
+        row = self.db.get_active_terminal_lock(remote="prgs", org="o", repo="r")
+        self.assertIsNotNone(row)
+        assert row is not None
+        self.assertEqual(row["terminal_pr"], 332)
+        self.assertEqual(row["status"], "active")
+
+    def test_incident_links_not_work_items(self) -> None:
+        link = self.db.upsert_incident_link(
+            provider="sentry",
+            provider_base_url="https://sentry.prgs.cc",
+            provider_org="prgs",
+            provider_project="gitea-tools-mcp",
+            provider_issue_id="12345",
+            gitea_org="Scaled-Tech-Consulting",
+            gitea_repo="Gitea-Tools",
+            gitea_issue_number=9001,
+            fingerprint="fp-1",
+        )
+        self.assertEqual(link["gitea_issue_number"], 9001)
+        found = self.db.get_incident_link_for_gitea_issue(
+            gitea_org="Scaled-Tech-Consulting",
+            gitea_repo="Gitea-Tools",
+            gitea_issue_number=9001,
+        )
+        self.assertIsNotNone(found)
+        # Linking does not create a work_item of incident kind
+        with self.assertRaises(InvalidWorkKindError):
+            self.db.upsert_work_item(
+                remote="prgs",
+                org="Scaled-Tech-Consulting",
+                repo="Gitea-Tools",
+                kind="sentry",
+                number=12345,
+            )
+
+    def test_heartbeat_and_release(self) -> None:
+        self.db.upsert_session(session_id="s1", role="author")
+        a = self.db.assign_and_lease(
+            session_id="s1",
+            role="author",
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="issue",
+            number=1,
+        )
+        hb = self.db.heartbeat_lease(a.lease_id, session_id="s1")
+        self.assertEqual(hb["lease_id"], a.lease_id)
+        self.db.release_lease(a.lease_id, session_id="s1")
+        # After release another session can claim
+        self.db.upsert_session(session_id="s2", role="author")
+        b = self.db.assign_and_lease(
+            session_id="s2",
+            role="author",
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="issue",
+            number=1,
+        )
+        self.assertEqual(b.outcome, "assigned")
+        self.assertEqual(b.session_id, "s2")
+
+    def test_require_valid_assignment_rejects_stale_head(self) -> None:
+        """Assignment must not authorize mutations after work-item head drifts."""
+        self.db.upsert_session(session_id="s1", role="author")
+        self.db.assign_and_lease(
+            session_id="s1",
+            role="author",
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="pr",
+            number=42,
+            expected_head_sha="head-v1",
+            allowed_actions=("implement",),
+        )
+        # Head drifts after assignment
+        self.db.upsert_work_item(
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="pr",
+            number=42,
+            current_head_sha="head-v2",
+        )
+        with self.assertRaises(LeaseRequiredError) as ctx:
+            self.db.require_valid_assignment(
+                session_id="s1",
+                remote="prgs",
+                org="o",
+                repo="r",
+                kind="pr",
+                number=42,
+                action="implement",
+            )
+        self.assertIn("stale head", str(ctx.exception).lower())
+
+    def test_require_valid_assignment_rejects_terminal_state(self) -> None:
+        """Assignment must not authorize mutations after work item is merged/closed."""
+        self.db.upsert_session(session_id="s1", role="author")
+        self.db.assign_and_lease(
+            session_id="s1",
+            role="author",
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="pr",
+            number=55,
+            expected_head_sha="abc",
+            allowed_actions=("implement",),
+        )
+        self.db.upsert_work_item(
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="pr",
+            number=55,
+            state="merged",
+            current_head_sha="abc",
+        )
+        with self.assertRaises(LeaseRequiredError) as ctx:
+            self.db.require_valid_assignment(
+                session_id="s1",
+                remote="prgs",
+                org="o",
+                repo="r",
+                kind="pr",
+                number=55,
+                action="implement",
+            )
+        self.assertIn("terminal", str(ctx.exception).lower())
+
+        self.db.upsert_work_item(
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="issue",
+            number=56,
+            state="open",
+        )
+        self.db.assign_and_lease(
+            session_id="s1",
+            role="author",
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="issue",
+            number=56,
+            allowed_actions=("implement",),
+        )
+        self.db.upsert_work_item(
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="issue",
+            number=56,
+            state="closed",
+        )
+        with self.assertRaises(LeaseRequiredError):
+            self.db.require_valid_assignment(
+                session_id="s1",
+                remote="prgs",
+                org="o",
+                repo="r",
+                kind="issue",
+                number=56,
+                action="implement",
+            )
+
+    def test_pr_assignment_requires_expected_head_sha(self) -> None:
+        """PR assign and mutation must fail closed without a head pin."""
+        self.db.upsert_session(session_id="s1", role="author")
+        with self.assertRaises(LeaseRequiredError) as ctx:
+            self.db.assign_and_lease(
+                session_id="s1",
+                role="author",
+                remote="prgs",
+                org="o",
+                repo="r",
+                kind="pr",
+                number=88,
+                expected_head_sha=None,
+                allowed_actions=("implement",),
+            )
+        self.assertIn("expected_head_sha", str(ctx.exception))
+
+        # Legacy path: force an unpinned PR assignment into the DB, then
+        # populate head and prove mutation is still rejected.
+        import sqlite3
+
+        self.db.upsert_work_item(
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="pr",
+            number=89,
+            current_head_sha=None,
+        )
+        conn = sqlite3.connect(self.db_path)
+        try:
+            wid = conn.execute(
+                "SELECT work_item_id FROM work_items WHERE kind='pr' AND number=89"
+            ).fetchone()[0]
+            conn.execute(
+                """
+                INSERT INTO sessions(session_id, role, started_at, last_heartbeat_at, status)
+                VALUES ('legacy', 'author', '2020-01-01T00:00:00Z', '2020-01-01T00:00:00Z', 'active')
+                """
+            )
+            conn.execute(
+                """
+                INSERT INTO leases(
+                    lease_id, work_item_id, session_id, role, phase,
+                    expires_at, heartbeat_at, status
+                ) VALUES (
+                    'lease-legacy', ?, 'legacy', 'author', 'claimed',
+                    '2099-01-01T00:00:00Z', '2020-01-01T00:00:00Z', 'active'
+                )
+                """,
+                (wid,),
+            )
+            conn.execute(
+                """
+                INSERT INTO assignments(
+                    assignment_id, work_item_id, session_id, lease_id,
+                    allowed_actions, forbidden_actions, expected_head_sha,
+                    role, status, created_at
+                ) VALUES (
+                    'asn-legacy', ?, 'legacy', 'lease-legacy',
+                    '["implement"]', '["merge"]', NULL,
+                    'author', 'active', '2020-01-01T00:00:00Z'
+                )
+                """,
+                (wid,),
+            )
+            conn.commit()
+        finally:
+            conn.close()
+        self.db.upsert_work_item(
+            remote="prgs",
+            org="o",
+            repo="r",
+            kind="pr",
+            number=89,
+            current_head_sha="populated-head",
+        )
+        with self.assertRaises(LeaseRequiredError) as ctx2:
+            self.db.require_valid_assignment(
+                session_id="legacy",
+                remote="prgs",
+                org="o",
+                repo="r",
+                kind="pr",
+                number=89,
+                action="implement",
+            )
+        self.assertIn("expected_head_sha pin", str(ctx2.exception))
+
+    def test_migrate_duplicate_null_scope_incident_links(self) -> None:
+        """Legacy NULL-scope duplicates must migrate without UNIQUE crash."""
+        import sqlite3
+
+        from control_plane_db import ControlPlaneDB, ControlPlaneError
+
+        # Build a v1-like table with nullable scope columns and insert dups
+        # that collapse under normalization, then open ControlPlaneDB on it.
+        path = os.path.join(self._tmp.name, "legacy_dups.sqlite3")
+        conn = sqlite3.connect(path)
+        try:
+            conn.executescript(
+                """
+                CREATE TABLE schema_meta (key TEXT PRIMARY KEY, value TEXT NOT NULL);
+                CREATE TABLE incident_links (
+                    link_id INTEGER PRIMARY KEY AUTOINCREMENT,
+                    provider TEXT NOT NULL,
+                    provider_base_url TEXT,
+                    provider_org TEXT,
+                    provider_project TEXT,
+                    provider_issue_id TEXT NOT NULL,
+                    provider_short_id TEXT,
+                    provider_permalink TEXT,
+                    fingerprint TEXT,
+                    gitea_org TEXT NOT NULL,
+                    gitea_repo TEXT NOT NULL,
+                    gitea_issue_number INTEGER NOT NULL,
+                    linked_pr_numbers TEXT,
+                    first_seen TEXT,
+                    last_seen TEXT,
+                    event_count INTEGER,
+                    status TEXT NOT NULL DEFAULT 'open',
+                    release_resolved_at TEXT,
+                    last_sync_at TEXT,
+                    UNIQUE (
+                        provider, provider_base_url, provider_org,
+                        provider_project, provider_issue_id
+                    )
+                );
+                INSERT INTO incident_links(
+                    provider, provider_base_url, provider_org, provider_project,
+                    provider_issue_id, gitea_org, gitea_repo, gitea_issue_number, status
+                ) VALUES
+                    ('sentry', NULL, NULL, NULL, 'dup-1', 'org', 'repo', 10, 'open'),
+                    ('sentry', NULL, NULL, NULL, 'dup-1', 'org', 'repo', 10, 'open');
+                """
+            )
+            # SQLite allows two NULL-scope rows with same provider/issue under UNIQUE.
+            n = conn.execute("SELECT COUNT(*) FROM incident_links").fetchone()[0]
+            self.assertEqual(n, 2)
+            conn.commit()
+        finally:
+            conn.close()
+
+        db = ControlPlaneDB(path)
+        conn2 = sqlite3.connect(path)
+        try:
+            n2 = conn2.execute("SELECT COUNT(*) FROM incident_links").fetchone()[0]
+            rows = conn2.execute(
+                "SELECT provider_base_url, provider_org, provider_project, gitea_issue_number "
+                "FROM incident_links"
+            ).fetchall()
+        finally:
+            conn2.close()
+        self.assertEqual(n2, 1)
+        self.assertEqual(rows[0][0], "")
+        self.assertEqual(rows[0][1], "")
+        self.assertEqual(rows[0][2], "")
+        self.assertEqual(rows[0][3], 10)
+        # Touch to silence unused import in type checkers if needed
+        self.assertTrue(issubclass(ControlPlaneError, Exception))
+        del db
+
+    def test_migrate_conflicting_duplicate_incident_links_fails_closed(self) -> None:
+        """Conflicting Gitea targets for the same provider key must fail closed."""
+        import sqlite3
+        from control_plane_db import ControlPlaneDB, ControlPlaneError
+
+        path = os.path.join(self._tmp.name, "legacy_conflict.sqlite3")
+        conn = sqlite3.connect(path)
+        try:
+            conn.executescript(
+                """
+                CREATE TABLE incident_links (
+                    link_id INTEGER PRIMARY KEY AUTOINCREMENT,
+                    provider TEXT NOT NULL,
+                    provider_base_url TEXT,
+                    provider_org TEXT,
+                    provider_project TEXT,
+                    provider_issue_id TEXT NOT NULL,
+                    gitea_org TEXT NOT NULL,
+                    gitea_repo TEXT NOT NULL,
+                    gitea_issue_number INTEGER NOT NULL,
+                    status TEXT NOT NULL DEFAULT 'open',
+                    UNIQUE (
+                        provider, provider_base_url, provider_org,
+                        provider_project, provider_issue_id
+                    )
+                );
+                INSERT INTO incident_links(
+                    provider, provider_base_url, provider_org, provider_project,
+                    provider_issue_id, gitea_org, gitea_repo, gitea_issue_number
+                ) VALUES
+                    ('sentry', NULL, NULL, NULL, 'dup-c', 'org', 'repo', 1),
+                    ('sentry', NULL, NULL, NULL, 'dup-c', 'org', 'repo', 2);
+                """
+            )
+            conn.commit()
+        finally:
+            conn.close()
+
+        with self.assertRaises(ControlPlaneError) as ctx:
+            ControlPlaneDB(path)
+        self.assertIn("conflicting", str(ctx.exception).lower())
+
+    def test_migrate_conflicting_observation_metadata_fails_closed(self) -> None:
+        """Same provider key + same Gitea target but differing obs metadata must fail closed.
+
+        Regression for silent data loss: migration used to keep lowest link_id and
+        delete peers after comparing only Gitea targets (#619 RC3).
+        """
+        import sqlite3
+        from control_plane_db import ControlPlaneDB, ControlPlaneError
+
+        path = os.path.join(self._tmp.name, "legacy_meta_conflict.sqlite3")
+        conn = sqlite3.connect(path)
+        try:
+            conn.executescript(
+                """
+                CREATE TABLE schema_meta (key TEXT PRIMARY KEY, value TEXT NOT NULL);
+                CREATE TABLE incident_links (
+                    link_id INTEGER PRIMARY KEY AUTOINCREMENT,
+                    provider TEXT NOT NULL,
+                    provider_base_url TEXT,
+                    provider_org TEXT,
+                    provider_project TEXT,
+                    provider_issue_id TEXT NOT NULL,
+                    provider_short_id TEXT,
+                    provider_permalink TEXT,
+                    fingerprint TEXT,
+                    gitea_org TEXT NOT NULL,
+                    gitea_repo TEXT NOT NULL,
+                    gitea_issue_number INTEGER NOT NULL,
+                    linked_pr_numbers TEXT,
+                    first_seen TEXT,
+                    last_seen TEXT,
+                    event_count INTEGER,
+                    status TEXT NOT NULL DEFAULT 'open',
+                    release_resolved_at TEXT,
+                    last_sync_at TEXT,
+                    UNIQUE (
+                        provider, provider_base_url, provider_org,
+                        provider_project, provider_issue_id
+                    )
+                );
+                INSERT INTO incident_links(
+                    provider, provider_base_url, provider_org, provider_project,
+                    provider_issue_id, provider_permalink, fingerprint,
+                    gitea_org, gitea_repo, gitea_issue_number,
+                    event_count, status, first_seen, last_seen
+                ) VALUES
+                    (
+                        'sentry', NULL, NULL, NULL, 'dup-meta',
+                        'https://sentry.example/issues/1', 'fingerprint-A',
+                        'org', 'repo', 42,
+                        1, 'open', '2026-01-01T00:00:00Z', '2026-01-01T01:00:00Z'
+                    ),
+                    (
+                        'sentry', NULL, NULL, NULL, 'dup-meta',
+                        'https://sentry.example/issues/1', 'fingerprint-B',
+                        'org', 'repo', 42,
+                        99, 'resolved', '2026-01-01T00:00:00Z', '2026-01-02T00:00:00Z'
+                    );
+                """
+            )
+            n = conn.execute("SELECT COUNT(*) FROM incident_links").fetchone()[0]
+            self.assertEqual(n, 2)
+            conn.commit()
+        finally:
+            conn.close()
+
+        with self.assertRaises(ControlPlaneError) as ctx:
+            ControlPlaneDB(path)
+        msg = str(ctx.exception).lower()
+        self.assertIn("conflicting", msg)
+        self.assertIn("observation metadata", msg)
+
+        # Rows must still be present — migration must not delete before failing.
+        conn2 = sqlite3.connect(path)
+        try:
+            remaining = conn2.execute("SELECT COUNT(*) FROM incident_links").fetchone()[0]
+            fps = {
+                r[0]
+                for r in conn2.execute(
+                    "SELECT fingerprint FROM incident_links ORDER BY link_id"
+                ).fetchall()
+            }
+        finally:
+            conn2.close()
+        self.assertEqual(remaining, 2)
+        self.assertEqual(fps, {"fingerprint-A", "fingerprint-B"})
+
+    def test_incident_links_minimal_upsert_is_canonical(self) -> None:
+        """Repeated minimal upserts must update one row (NULL-safe uniqueness)."""
+        a = self.db.upsert_incident_link(
+            provider="sentry",
+            provider_issue_id="inc-1",
+            gitea_org="org",
+            gitea_repo="repo",
+            gitea_issue_number=1,
+        )
+        b = self.db.upsert_incident_link(
+            provider="sentry",
+            provider_issue_id="inc-1",
+            gitea_org="org",
+            gitea_repo="repo",
+            gitea_issue_number=2,
+            # omit optional scope fields again
+        )
+        c = self.db.upsert_incident_link(
+            provider="sentry",
+            provider_issue_id="inc-1",
+            gitea_org="org",
+            gitea_repo="repo",
+            gitea_issue_number=3,
+            provider_base_url=None,
+            provider_org="",
+            provider_project="  ",
+        )
+        self.assertEqual(a["link_id"], b["link_id"])
+        self.assertEqual(b["link_id"], c["link_id"])
+        self.assertEqual(c["gitea_issue_number"], 3)
+        self.assertEqual(c["provider_base_url"], "")
+        self.assertEqual(c["provider_org"], "")
+        self.assertEqual(c["provider_project"], "")
+
+        import sqlite3
+
+        conn = sqlite3.connect(self.db_path)
+        try:
+            n = conn.execute(
+                "SELECT COUNT(*) FROM incident_links WHERE provider_issue_id = ?",
+                ("inc-1",),
+            ).fetchone()[0]
+        finally:
+            conn.close()
+        self.assertEqual(n, 1)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_controller_closure_baseline_proof.py

@@ -0,0 +1,113 @@
+"""Controller-closure baseline-proof gate tests (#529, criterion 6)."""
+
+import unittest
+
+from controller_closure_baseline_proof import (
+    assess_controller_closure_baseline_proof,
+)
+from premerge_baseline_proof import (
+    CLEAN_PASS,
+    PREMERGE_BASELINE_PROVEN_FAILURE,
+    UNRESOLVED_REGRESSION_RISK,
+)
+from final_report_validator import assess_final_report_validator
+
+# Complete pre-merge proof fields for a baseline claim (see #533).
+_PROOF_FIELDS = (
+    "Pre-merge base commit: 1a2b3c4d5e6f7a8b9c0d1e2f3a4b5c6d7e8f9a0b\n"
+    "Tested commit: 1a2b3c4d5e6f7a8b9c0d1e2f3a4b5c6d7e8f9a0b\n"
+    "Command: venv/bin/python -m pytest tests/test_foo.py -q\n"
+    "Exit status: 1\n"
+    "Failure signature: AssertionError: None is not true\n"
+)
+
+
+class TestControllerClosureBaselineProof(unittest.TestCase):
+    def test_empty_report_skipped_and_allowed(self):
+        result = assess_controller_closure_baseline_proof("")
+        self.assertFalse(result["block"])
+        self.assertTrue(result["skipped"])
+        self.assertEqual(result["label"], CLEAN_PASS)
+
+    def test_none_report_allowed(self):
+        result = assess_controller_closure_baseline_proof(None)
+        self.assertFalse(result["block"])
+        self.assertTrue(result["skipped"])
+
+    def test_clean_pass_closure_allowed(self):
+        result = assess_controller_closure_baseline_proof(
+            "Closing #529. Validation: full suite passed, exit status 0. Clean pass."
+        )
+        self.assertFalse(result["block"])
+        self.assertEqual(result["label"], CLEAN_PASS)
+
+    def test_expected_preexisting_failure_without_proof_blocked(self):
+        report = (
+            "Closing #529. Full suite: 1 failed. This is an expected "
+            "pre-existing failure, safe to close."
+        )
+        result = assess_controller_closure_baseline_proof(report)
+        self.assertTrue(result["block"])
+        self.assertFalse(result["proven"])
+        self.assertEqual(result["label"], UNRESOLVED_REGRESSION_RISK)
+        self.assertTrue(result["reasons"])
+        self.assertTrue(result["safe_next_action"])
+
+    def test_current_master_reproduction_only_blocked(self):
+        report = (
+            "Closing #529. Full suite: 1 failed. Pre-existing baseline failure — "
+            "reproduced on current master after merge.\n"
+            "Command: venv/bin/python -m pytest tests/test_foo.py -q\n"
+            "Exit status: 1\n"
+            "Failure signature: AssertionError: None is not true\n"
+        )
+        result = assess_controller_closure_baseline_proof(report)
+        self.assertTrue(result["block"])
+
+    def test_proven_baseline_closure_allowed(self):
+        report = (
+            "Closing #529. Full suite: 1 failed, an expected pre-existing "
+            "baseline failure proven on the PR pre-merge base commit.\n"
+            + _PROOF_FIELDS
+        )
+        result = assess_controller_closure_baseline_proof(report)
+        self.assertFalse(result["block"])
+        self.assertEqual(result["label"], PREMERGE_BASELINE_PROVEN_FAILURE)
+
+
+class TestControllerCloseTaskKind(unittest.TestCase):
+    """The composable validator must cover the controller_close task kind."""
+
+    def test_controller_close_blocks_unproven_baseline(self):
+        report = (
+            "Full suite: 1 failed. Expected pre-existing failure, closing the "
+            "tracking issue."
+        )
+        result = assess_final_report_validator(report, "controller_close")
+        self.assertTrue(result["blocked"])
+        self.assertTrue(
+            any(
+                "premerge_baseline_proof" in f["rule_id"]
+                for f in result["findings"]
+            )
+        )
+
+    def test_controller_close_alias_close_issue(self):
+        report = (
+            "Full suite: 1 failed. Expected pre-existing failure, closing the "
+            "tracking issue."
+        )
+        result = assess_final_report_validator(report, "close_issue")
+        self.assertTrue(result["blocked"])
+
+    def test_controller_close_allows_proven_baseline(self):
+        report = (
+            "Full suite: 1 failed, expected pre-existing baseline failure proven "
+            "on the PR pre-merge base commit.\n" + _PROOF_FIELDS
+        )
+        result = assess_final_report_validator(report, "controller_close")
+        self.assertFalse(result["blocked"])
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_create_issue.py

@@ -103,6 +103,37 @@ class TestAPIPayload(unittest.TestCase):
             self.assertEqual(payload["title"], "My Title")
             self.assertEqual(payload["body"], "My Body")
 
+    @patch("create_issue.get_credentials", return_value=FAKE_CREDS)
+    def test_applies_workflow_labels_by_name(self, _cred):
+        def api_side_effect(method, url, auth, payload=None):
+            if method == "GET" and url.endswith("/labels"):
+                return [
+                    {"id": 1, "name": "type:feature"},
+                    {"id": 2, "name": "status:ready"},
+                ]
+            if method == "POST" and url.endswith("/issues"):
+                return {"number": 7, "html_url": "http://x/7"}
+            if method == "PUT" and url.endswith("/issues/7/labels"):
+                return [{"name": "type:feature"}, {"name": "status:ready"}]
+            return {}
+
+        with patch("create_issue.api_request", side_effect=api_side_effect) as mock_api:
+            rc = create_issue.main([
+                "--title", "My Title",
+                "--type-label", "feature",
+                "--status-label", "ready",
+            ])
+        self.assertEqual(rc, 0)
+        put_call = next(c for c in mock_api.call_args_list if c[0][0] == "PUT")
+        self.assertEqual(put_call[0][3], {"labels": [1, 2]})
+
+    @patch("create_issue.get_credentials", return_value=FAKE_CREDS)
+    def test_require_workflow_labels_blocks_missing_labels(self, _cred):
+        with patch("create_issue.api_request") as mock_api:
+            rc = create_issue.main(["--title", "My Title", "--require-workflow-labels"])
+        self.assertEqual(rc, 1)
+        mock_api.assert_not_called()
+
     @patch("create_issue.get_credentials", return_value=FAKE_CREDS)
     def test_url_construction(self, _cred):
         with patch("create_issue.api_request",

tests/test_final_report_validator.py

@@ -114,6 +114,28 @@ def _reconcile_handoff(drop=(), **overrides):
     return text
 
 
+class TestTwoCommentWorkflowIntegration(unittest.TestCase):
+    def test_tagged_pair_produces_no_two_comment_findings(self):
+        from thread_state_ledger_validator import findings_for_final_report  # noqa: E402
+        from tests.test_thread_state_ledger_validator import (  # noqa: E402
+            _minimal_handoff,
+            _minimal_ledger,
+        )
+
+        report = _minimal_handoff() + "\n\n" + _minimal_ledger()
+        self.assertEqual(findings_for_final_report(report), [])
+
+    def test_tagged_handoff_without_ledger_blocks_via_validator(self):
+        from thread_state_ledger_validator import findings_for_final_report  # noqa: E402
+        from tests.test_thread_state_ledger_validator import _minimal_handoff  # noqa: E402
+
+        findings = findings_for_final_report(_minimal_handoff())
+        self.assertTrue(findings)
+        self.assertTrue(
+            any(f["severity"] == "block" for f in findings)
+        )
+
+
 class TestValidatorFinding(unittest.TestCase):
     def test_finding_shape(self):
         finding = validator_finding(
@@ -351,6 +373,92 @@ class TestReconciliationRules(unittest.TestCase):
         )
 
 
+class TestCanonicalStateUpdateRules(unittest.TestCase):
+    def test_claimed_state_comment_without_block_blocks(self):
+        report = _reconcile_handoff() + "\nPosted canonical state comment on PR #99."
+        result = assess_final_report_validator(report, "reconcile_already_landed")
+        self.assertTrue(result["blocked"])
+        self.assertTrue(
+            any(f["rule_id"] == "shared.canonical_state_update" for f in result["findings"])
+        )
+
+    def test_state_comment_missing_next_prompt_blocks(self):
+        report = (
+            _reconcile_handoff()
+            + """
+
+## Canonical PR State
+
+STATE:
+needs-review
+
+WHO_IS_NEXT:
+reviewer
+
+NEXT_ACTION:
+Review PR #99.
+
+NEXT_PROMPT:
+
+ISSUE:
+#98
+
+HEAD_SHA:
+0fdc8f582026b72a229d59a172c0a63ac4aaeaf9
+
+REVIEW_STATUS:
+none
+
+MERGE_READY:
+no
+"""
+        )
+        result = assess_final_report_validator(report, "reconcile_already_landed")
+        self.assertTrue(result["blocked"])
+        reasons = " ".join(f["reason"] for f in result["findings"])
+        self.assertIn("NEXT_PROMPT", reasons)
+
+    def test_valid_state_comment_claim_passes_shared_rule(self):
+        report = (
+            _reconcile_handoff()
+            + """
+
+## Canonical PR State
+
+STATE:
+needs-review
+
+WHO_IS_NEXT:
+reviewer
+
+NEXT_ACTION:
+Review PR #99 against the pinned head.
+
+NEXT_PROMPT:
+Load the review workflow and review PR #99.
+
+ISSUE:
+#98
+
+HEAD_SHA:
+0fdc8f582026b72a229d59a172c0a63ac4aaeaf9
+
+REVIEW_STATUS:
+none
+
+MERGE_READY:
+no
+
+BLOCKERS:
+none
+"""
+        )
+        result = assess_final_report_validator(report, "reconcile_already_landed")
+        self.assertFalse(
+            any(f["rule_id"] == "shared.canonical_state_update" for f in result["findings"])
+        )
+
+
 class TestCanonicalReconcileSchema(unittest.TestCase):
     """Issue #307: reconciliation workflows emit only the canonical schema."""
 
@@ -579,6 +687,31 @@ class TestReconcilerCloseProof(unittest.TestCase):
         )
 
 
+class TestCanonicalCommentPostClaim(unittest.TestCase):
+    def test_blocks_post_claim_when_validator_rejected_in_report(self):
+        report = "\n".join([
+            "## Controller Handoff",
+            "- MCP/Gitea mutations: issue comment posted",
+            "- Issue comments posted: 1 canonical state comment",
+            "canonical comment validation failed (fail closed before posting).",
+            '- canonical_comment_validation: {"allowed": false}',
+        ])
+        result = assess_final_report_validator(report, "work_issue")
+        rule_ids = [f["rule_id"] for f in result["findings"]]
+        self.assertIn("shared.canonical_comment_post_claim", rule_ids)
+        self.assertTrue(result["blocked"])
+
+    def test_allows_none_when_validator_rejected_without_post_claim(self):
+        report = "\n".join([
+            "## Controller Handoff",
+            "- Issue comments posted: none",
+            "canonical comment validation failed (fail closed before posting).",
+        ])
+        result = assess_final_report_validator(report, "work_issue")
+        rule_ids = [f["rule_id"] for f in result["findings"]]
+        self.assertNotIn("shared.canonical_comment_post_claim", rule_ids)
+
+
 class TestEntryPoint(unittest.TestCase):
     def test_unknown_task_kind_blocks(self):
         result = assess_final_report_validator("report", "unknown_mode")
@@ -594,8 +727,197 @@ class TestEntryPoint(unittest.TestCase):
 
     def test_supported_task_kinds_include_review_and_reconcile(self):
         self.assertIn("review_pr", FINAL_REPORT_TASK_KINDS)
+        self.assertIn("merge_pr", FINAL_REPORT_TASK_KINDS)
         self.assertIn("reconcile_already_landed", FINAL_REPORT_TASK_KINDS)
 
 
+class TestMergePrRules(unittest.TestCase):
+    def test_clean_merger_report_passes(self):
+        lines = [
+            "## Controller Handoff",
+            "",
+            "- Task: merge PR #203",
+            "- Repo: Scaled-Tech-Consulting/Gitea-Tools",
+            "- Role: merger",
+            "- Identity: sysadmin / prgs-merger",
+            "- Issue/PR: #182 / PR #203",
+            "- Branch/SHA: feat/x @ 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Files changed: review_proofs.py",
+            "- Validation: pytest in branches/review-203",
+            "- Mutations: merge completed",
+            "- File edits by reviewer: none",
+            "- Worktree/index mutations: none",
+            "- Git ref mutations: git fetch prgs master",
+            "- MCP/Gitea mutations: merge completed",
+            "- Review mutations: none",
+            "- Merge mutations: merged PR #203",
+            "- Cleanup mutations: none",
+            "- External-state mutations: none",
+            "- Read-only diagnostics: metadata check",
+            "- Current status: PR merged",
+            "- Blockers: none",
+            "- Next: none",
+            "- Safety: review and merge are separate roles",
+            "- Selected PR: #203",
+            "- Pinned reviewed head: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Reviewed head SHA: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Final live head SHA before approval: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Final live head SHA before merge: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Push occurred during validation: no",
+            "- Active profile: prgs-merger",
+            "- Role kind: merger",
+            "- Merge capability source: profile",
+            "- Explicit operator authorization: MERGE PR 203",
+            "- Expected head SHA: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Approval at current head: yes",
+            "- Merge result: PR merged successfully",
+            "- Cleanup status: complete",
+        ]
+        report = "\n".join(lines)
+        result = assess_final_report_validator(
+            report,
+            "merge_pr",
+        )
+        self.assertEqual(result["grade"], "A")
+        self.assertFalse(result["blocked"])
+
+    def test_manual_seeded_lease_claim_blocks_without_mcp_evidence(self):
+        lines = [
+            "## Controller Handoff",
+            "",
+            "- Task: merge PR #203",
+            "- Repo: Scaled-Tech-Consulting/Gitea-Tools",
+            "- Role: merger",
+            "- Identity: sysadmin / prgs-merger",
+            "- Issue/PR: #182 / PR #203",
+            "- Branch/SHA: feat/x @ 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Files changed: review_proofs.py",
+            "- Validation: pytest in branches/review-203",
+            "- Mutations: merge completed",
+            "- File edits by reviewer: none",
+            "- Worktree/index mutations: none",
+            "- Git ref mutations: git fetch prgs master",
+            "- MCP/Gitea mutations: merge completed",
+            "- Review mutations: none",
+            "- Merge mutations: merged using manually seeded lease proof",
+            "- Cleanup mutations: none",
+            "- External-state mutations: none",
+            "- Read-only diagnostics: metadata check",
+            "- Current status: PR merged",
+            "- Blockers: none",
+            "- Next: none",
+            "- Safety: review and merge are separate roles",
+            "- Selected PR: #203",
+            "- Pinned reviewed head: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Reviewed head SHA: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Final live head SHA before approval: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Final live head SHA before merge: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Push occurred during validation: no",
+            "- Active profile: prgs-merger",
+            "- Role kind: merger",
+            "- Merge capability source: profile",
+            "- Explicit operator authorization: MERGE PR 203",
+            "- Expected head SHA: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Approval at current head: yes",
+            "- Merge result: PR merged successfully",
+            "- Cleanup status: complete",
+        ]
+        report = "\n".join(lines)
+        result = assess_final_report_validator(report, "merge_pr")
+        self.assertTrue(result["blocked"])
+        codes = {f.get("rule_id") for f in result.get("findings") or []}
+        self.assertIn("shared.manual_lease_proof_handoff", codes)
+
+    def test_manual_seeded_claim_allowed_when_adoption_cited(self):
+        lines = [
+            "## Controller Handoff",
+            "",
+            "- Task: merge PR #203",
+            "- Repo: Scaled-Tech-Consulting/Gitea-Tools",
+            "- Role: merger",
+            "- Identity: sysadmin / prgs-merger",
+            "- Issue/PR: #182 / PR #203",
+            "- Branch/SHA: feat/x @ 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Files changed: review_proofs.py",
+            "- Validation: pytest in branches/review-203",
+            "- Mutations: merge completed",
+            "- File edits by reviewer: none",
+            "- Worktree/index mutations: none",
+            "- Git ref mutations: git fetch prgs master",
+            "- MCP/Gitea mutations: gitea_adopt_merger_pr_lease then merge",
+            "- Review mutations: none",
+            "- Merge mutations: historical manual seed replaced by sanctioned adoption",
+            "- Cleanup mutations: none",
+            "- External-state mutations: none",
+            "- Read-only diagnostics: metadata check",
+            "- Current status: PR merged",
+            "- Blockers: none",
+            "- Next: none",
+            "- Safety: review and merge are separate roles",
+            "- Selected PR: #203",
+            "- Pinned reviewed head: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Reviewed head SHA: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Final live head SHA before approval: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Final live head SHA before merge: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Push occurred during validation: no",
+            "- Active profile: prgs-merger",
+            "- Role kind: merger",
+            "- Merge capability source: profile",
+            "- Explicit operator authorization: MERGE PR 203",
+            "- Expected head SHA: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Approval at current head: yes",
+            "- lease_proof_source: gitea_adopt_merger_pr_lease",
+            "- lease_proof_kind: sanctioned_adoption",
+            "- adoption_comment_id: 8288",
+            "- Merge result: PR merged successfully",
+            "- Cleanup status: complete",
+        ]
+        report = "\n".join(lines)
+        result = assess_final_report_validator(report, "merge_pr")
+        self.assertFalse(result["blocked"])
+        codes = {f.get("rule_id") for f in result.get("findings") or []}
+        self.assertNotIn("shared.manual_lease_proof_handoff", codes)
+
+    def test_missing_merger_fields_blocks(self):
+        lines = [
+            "## Controller Handoff",
+            "",
+            "- Task: merge PR #203",
+            "- Repo: Scaled-Tech-Consulting/Gitea-Tools",
+            "- Role: merger",
+            "- Identity: sysadmin / prgs-merger",
+            "- Issue/PR: #182 / PR #203",
+            "- Branch/SHA: feat/x @ 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Files changed: review_proofs.py",
+            "- Validation: pytest in branches/review-203",
+            "- Mutations: merge completed",
+            "- File edits by reviewer: none",
+            "- Worktree/index mutations: none",
+            "- Git ref mutations: git fetch prgs master",
+            "- MCP/Gitea mutations: merge completed",
+            "- Review mutations: none",
+            "- Merge mutations: merged PR #203",
+            "- Cleanup mutations: none",
+            "- External-state mutations: none",
+            "- Read-only diagnostics: metadata check",
+            "- Current status: PR merged",
+            "- Blockers: none",
+            "- Next: none",
+            "- Safety: review and merge are separate roles",
+            "- Selected PR: #203",
+            "- Pinned reviewed head: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Reviewed head SHA: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Final live head SHA before approval: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Final live head SHA before merge: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Push occurred during validation: no",
+        ]
+        report = "\n".join(lines)
+        result = assess_final_report_validator(
+            report,
+            "merge_pr",
+        )
+        self.assertTrue(result["downgraded"])
+
+
 if __name__ == "__main__":
     unittest.main()

tests/test_head_scoped_review_decision_lock.py

@@ -0,0 +1,397 @@
+"""Head-scoped #332 review-decision locks (#620).
+
+Proves:
+  * REQUEST_CHANGES on head A does not block mark_ready/submit on head B
+  * APPROVE on head B is allowed after RC on head A (same open PR)
+  * same-head duplicate terminal remains blocked
+  * open-PR cleanup remains forbidden; assessment reports stale_by_head
+  * historical mutations keep their head_sha (preserved ledger)
+  * PR #619-style: old RC at 036b78e…, current head 2429d9d…, approve allowed
+"""
+
+from __future__ import annotations
+
+import os
+import unittest
+from unittest.mock import patch
+
+import mcp_server
+import stale_review_decision_lock as srdl
+
+HEAD_A = "036b78e31ea5d036452b3a52e0e086b01e0c763f"
+HEAD_B = "2429d9d2e826e519eb8eb4ade45987c00838aefb"
+HEAD_C = "c" * 40
+
+
+def _lock(mutations=None, correction=False, ready_pr=None, ready_head=None, ready_action=None):
+    return {
+        "task": "review_pr",
+        "remote": "prgs",
+        "org": "Scaled-Tech-Consulting",
+        "repo": "Gitea-Tools",
+        "session_pid": os.getpid(),
+        "session_profile": "prgs-reviewer",
+        "session_profile_lock": "prgs-reviewer",
+        "profile_identity": "prgs-reviewer",
+        "final_review_decision_ready": False,
+        "ready_pr_number": ready_pr,
+        "ready_action": ready_action,
+        "ready_expected_head_sha": ready_head,
+        "ready_remote": "prgs" if ready_pr else None,
+        "ready_org": "Scaled-Tech-Consulting" if ready_pr else None,
+        "ready_repo": "Gitea-Tools" if ready_pr else None,
+        "live_mutations": list(mutations or []),
+        "correction_authorized": correction,
+        "correction_reason": None,
+    }
+
+
+RC_619_LEGACY = {
+    "pr_number": 619,
+    "action": "request_changes",
+    "review_id": 410,
+    "review_state": "request_changes",
+    # no head_sha — pre-#620 durable ledger shape
+}
+RC_619_HEAD_A = {
+    "pr_number": 619,
+    "action": "request_changes",
+    "review_id": 410,
+    "review_state": "request_changes",
+    "head_sha": HEAD_A,
+}
+APPROVE_619_HEAD_B = {
+    "pr_number": 619,
+    "action": "approve",
+    "review_id": 411,
+    "review_state": "approve",
+    "head_sha": HEAD_B,
+}
+
+
+def _seed(mutations=None, **kwargs):
+    import review_workflow_load
+
+    review_workflow_load.record_review_workflow_load(mcp_server.PROJECT_ROOT)
+    mcp_server._save_review_decision_lock(_lock(mutations, **kwargs))
+    mcp_server.gitea_load_review_workflow()
+
+
+def _open_pr(pr_number=619, head=HEAD_B):
+    return {
+        "number": pr_number,
+        "state": "open",
+        "merged": False,
+        "merged_at": None,
+        "head": {"sha": head},
+    }
+
+
+def _no_lease():
+    return {"block": False, "reasons": [], "mutation_allowed": True}
+
+
+def _feedback(blocking=False, stale=False, success=True):
+    return {
+        "success": success,
+        "has_blocking_change_requests": blocking,
+        "review_feedback_stale": stale,
+        "current_head_sha": HEAD_B,
+    }
+
+
+class TestPureHeadScopeHelpers(unittest.TestCase):
+    def test_mutation_head_prefers_recorded_sha(self):
+        m = {"pr_number": 1, "head_sha": HEAD_A}
+        self.assertEqual(srdl.mutation_head_sha(m), HEAD_A)
+
+    def test_legacy_mutation_uses_ready_expected_for_same_pr(self):
+        lock = _lock(
+            [RC_619_LEGACY],
+            ready_pr=619,
+            ready_head=HEAD_A,
+            ready_action="request_changes",
+        )
+        self.assertEqual(srdl.mutation_head_sha(RC_619_LEGACY, lock), HEAD_A)
+
+    def test_legacy_mutation_ignores_ready_for_other_pr(self):
+        lock = _lock([RC_619_LEGACY], ready_pr=1, ready_head=HEAD_A)
+        self.assertIsNone(srdl.mutation_head_sha(RC_619_LEGACY, lock))
+
+    def test_prior_blocks_same_head_not_other_head(self):
+        lock = _lock([RC_619_HEAD_A])
+        self.assertTrue(
+            srdl.prior_live_mutations_block_boundary(
+                lock, pr_number=619, expected_head_sha=HEAD_A
+            )
+        )
+        self.assertFalse(
+            srdl.prior_live_mutations_block_boundary(
+                lock, pr_number=619, expected_head_sha=HEAD_B
+            )
+        )
+
+    def test_backfill_stamps_legacy_terminals(self):
+        lock = _lock(
+            [dict(RC_619_LEGACY)],
+            ready_pr=619,
+            ready_head=HEAD_A,
+            ready_action="request_changes",
+        )
+        srdl.backfill_terminal_heads_from_ready(lock)
+        self.assertEqual(lock["live_mutations"][0]["head_sha"], HEAD_A)
+
+
+class TestHardStopHeadScope(unittest.TestCase):
+    def tearDown(self):
+        mcp_server._save_review_decision_lock(None)
+        mcp_server.review_workflow_load.clear_review_workflow_load()
+
+    def test_rc_head_a_allows_mark_ready_head_b(self):
+        _seed(
+            [RC_619_HEAD_A],
+            ready_pr=619,
+            ready_head=HEAD_A,
+            ready_action="request_changes",
+        )
+        self.assertEqual(
+            mcp_server.terminal_review_hard_stop_reasons(
+                619, "mark_ready", expected_head_sha=HEAD_B
+            ),
+            [],
+        )
+
+    def test_rc_head_a_blocks_mark_ready_same_head(self):
+        _seed(
+            [RC_619_HEAD_A],
+            ready_pr=619,
+            ready_head=HEAD_A,
+            ready_action="request_changes",
+        )
+        reasons = mcp_server.terminal_review_hard_stop_reasons(
+            619, "mark_ready", expected_head_sha=HEAD_A
+        )
+        self.assertTrue(reasons)
+        self.assertIn("#332", reasons[0])
+
+    def test_rc_head_a_blocks_other_pr(self):
+        _seed([RC_619_HEAD_A], ready_pr=619, ready_head=HEAD_A)
+        reasons = mcp_server.terminal_review_hard_stop_reasons(
+            700, "mark_ready", expected_head_sha=HEAD_B
+        )
+        self.assertTrue(reasons)
+
+    def test_legacy_619_ledger_allows_new_head(self):
+        """PR #619-style durable lock without mutation head_sha."""
+        _seed(
+            [RC_619_LEGACY],
+            ready_pr=619,
+            ready_head=HEAD_A,
+            ready_action="request_changes",
+        )
+        self.assertEqual(
+            mcp_server.terminal_review_hard_stop_reasons(
+                619, "mark_ready", expected_head_sha=HEAD_B
+            ),
+            [],
+        )
+
+
+class TestMarkFinalAndRecord(unittest.TestCase):
+    def tearDown(self):
+        mcp_server._save_review_decision_lock(None)
+        mcp_server.review_workflow_load.clear_review_workflow_load()
+
+    def _mark(self, pr, action, head, feedback=None):
+        with patch("mcp_server._list_pr_lease_comments", return_value=[]), patch(
+            "mcp_server._pr_work_lease_reviewer_block", return_value=_no_lease()
+        ), patch.object(
+            mcp_server,
+            "gitea_get_pr_review_feedback",
+            return_value=feedback or _feedback(blocking=False, stale=True),
+        ), patch.object(
+            mcp_server,
+            "gitea_check_pr_eligibility",
+            return_value={"eligible": True, "head_sha": head},
+        ):
+            return mcp_server.gitea_mark_final_review_decision(
+                pr_number=pr,
+                action=action,
+                expected_head_sha=head,
+                remote="prgs",
+                org="Scaled-Tech-Consulting",
+                repo="Gitea-Tools",
+            )
+
+    def test_rc_then_rc_on_new_head(self):
+        _seed(
+            [RC_619_HEAD_A],
+            ready_pr=619,
+            ready_head=HEAD_A,
+            ready_action="request_changes",
+        )
+        # Prior RC at head A is unresolved but head moved → feedback stale.
+        res = self._mark(
+            619,
+            "request_changes",
+            HEAD_B,
+            feedback=_feedback(blocking=True, stale=True),
+        )
+        self.assertTrue(res.get("marked_ready"), res)
+        lock = mcp_server._load_review_decision_lock()
+        # Historical head A preserved on mutation after backfill.
+        heads = {
+            m.get("head_sha")
+            for m in lock["live_mutations"]
+            if m.get("action") == "request_changes"
+        }
+        self.assertIn(HEAD_A, heads)
+        self.assertEqual(lock["ready_expected_head_sha"], HEAD_B)
+
+    def test_rc_then_approve_on_new_head(self):
+        _seed(
+            [RC_619_HEAD_A],
+            ready_pr=619,
+            ready_head=HEAD_A,
+            ready_action="request_changes",
+        )
+        res = self._mark(619, "approve", HEAD_B)
+        self.assertTrue(res.get("marked_ready"), res)
+        self.assertTrue(res.get("head_scoped"))
+
+    def test_same_head_rc_still_blocked_by_hard_stop(self):
+        _seed(
+            [RC_619_HEAD_A],
+            ready_pr=619,
+            ready_head=HEAD_A,
+            ready_action="request_changes",
+        )
+        res = self._mark(619, "approve", HEAD_A)
+        self.assertFalse(res.get("marked_ready"))
+        self.assertTrue(any("#332" in r for r in res.get("reasons") or []))
+
+    def test_pr619_style_legacy_lock_approve_on_current_head(self):
+        _seed(
+            [RC_619_LEGACY],
+            ready_pr=619,
+            ready_head=HEAD_A,
+            ready_action="request_changes",
+        )
+        res = self._mark(619, "approve", HEAD_B)
+        self.assertTrue(res.get("marked_ready"), res)
+        lock = mcp_server._load_review_decision_lock()
+        # Backfill should have stamped HEAD_A onto the legacy mutation.
+        self.assertEqual(lock["live_mutations"][0].get("head_sha"), HEAD_A)
+        self.assertEqual(lock["ready_expected_head_sha"], HEAD_B)
+
+    def test_record_live_mutation_stores_head(self):
+        _seed(ready_pr=619, ready_head=HEAD_B, ready_action="approve")
+        lock = mcp_server._load_review_decision_lock()
+        lock["final_review_decision_ready"] = True
+        lock["ready_pr_number"] = 619
+        lock["ready_expected_head_sha"] = HEAD_B
+        mcp_server._save_review_decision_lock(lock)
+        mcp_server.record_live_review_mutation(619, "approve", review_id=99)
+        stored = mcp_server._load_review_decision_lock()["live_mutations"][-1]
+        self.assertEqual(stored["head_sha"], HEAD_B)
+        self.assertEqual(stored["pr_number"], 619)
+
+    def test_submit_gate_allows_new_head_after_prior_terminal(self):
+        """check_review_decision_gate must not block different-head submit."""
+        mutations = [RC_619_HEAD_A]
+        _seed(
+            mutations,
+            ready_pr=619,
+            ready_head=HEAD_B,
+            ready_action="approve",
+        )
+        lock = mcp_server._load_review_decision_lock()
+        lock["final_review_decision_ready"] = True
+        lock["ready_pr_number"] = 619
+        lock["ready_action"] = "approve"
+        lock["ready_expected_head_sha"] = HEAD_B
+        lock["ready_remote"] = "prgs"
+        lock["ready_org"] = "Scaled-Tech-Consulting"
+        lock["ready_repo"] = "Gitea-Tools"
+        mcp_server._save_review_decision_lock(lock)
+        reasons = mcp_server.check_review_decision_gate(
+            619,
+            "approve",
+            final_review_decision_ready=True,
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+        )
+        self.assertEqual(reasons, [], reasons)
+
+    def test_submit_gate_blocks_same_head_duplicate(self):
+        mutations = [RC_619_HEAD_A]
+        _seed(
+            mutations,
+            ready_pr=619,
+            ready_head=HEAD_A,
+            ready_action="request_changes",
+        )
+        lock = mcp_server._load_review_decision_lock()
+        lock["final_review_decision_ready"] = True
+        lock["ready_pr_number"] = 619
+        lock["ready_action"] = "request_changes"
+        lock["ready_expected_head_sha"] = HEAD_A
+        lock["ready_remote"] = "prgs"
+        lock["ready_org"] = "Scaled-Tech-Consulting"
+        lock["ready_repo"] = "Gitea-Tools"
+        mcp_server._save_review_decision_lock(lock)
+        reasons = mcp_server.check_review_decision_gate(
+            619,
+            "request_changes",
+            final_review_decision_ready=True,
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+        )
+        self.assertTrue(reasons)
+
+
+class TestAssessmentOpenPrHead(unittest.TestCase):
+    def test_open_pr_stale_by_head_no_cleanup(self):
+        lock = _lock(
+            [RC_619_HEAD_A],
+            ready_pr=619,
+            ready_head=HEAD_A,
+            ready_action="request_changes",
+        )
+        a = srdl.assess_stale_review_decision_lock(
+            lock, pr_live=_open_pr(619, HEAD_B)
+        )
+        self.assertTrue(a["has_lock"])
+        self.assertFalse(a["is_moot"])
+        self.assertFalse(a["cleanup_allowed"])
+        self.assertTrue(a["stale_by_head"])
+        self.assertTrue(a["fresh_review_on_current_head_allowed"])
+        self.assertEqual(a["locked_head_sha"], HEAD_A)
+        self.assertEqual(a["current_pr_head_sha"], HEAD_B)
+
+    def test_open_pr_same_head_no_fresh(self):
+        lock = _lock([RC_619_HEAD_A], ready_pr=619, ready_head=HEAD_A)
+        a = srdl.assess_stale_review_decision_lock(
+            lock, pr_live=_open_pr(619, HEAD_A)
+        )
+        self.assertFalse(a["stale_by_head"])
+        self.assertFalse(a["fresh_review_on_current_head_allowed"])
+        self.assertFalse(a["cleanup_allowed"])
+
+    def test_historical_mutation_preserved_in_summary(self):
+        lock = _lock(
+            [RC_619_HEAD_A, APPROVE_619_HEAD_B],
+            ready_pr=619,
+            ready_head=HEAD_B,
+            ready_action="approve",
+        )
+        summary = srdl.lock_summary(lock)
+        self.assertEqual(summary["live_mutations_count"], 2)
+        self.assertEqual(summary["last_terminal"]["head_sha"], HEAD_B)
+        self.assertEqual(summary["locked_head_sha"], HEAD_B)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_issue_540_comment_role_poison.py

@@ -198,10 +198,13 @@ class TestReconcilerCommentThroughCanonicalPath(unittest.TestCase):
         srv._preflight_capability_baseline_porcelain = ""
         self._orig_in_test = srv._preflight_in_test_mode
         srv._preflight_in_test_mode = lambda: False
+        self._env_patch = patch.dict(os.environ, {"GITEA_MCP_DISABLE_PARITY_GATE": "1"}, clear=False)
+        self._env_patch.start()
 
     def tearDown(self):
         srv._preflight_in_test_mode = self._orig_in_test
         srv._preflight_resolved_role = None
+        self._env_patch.stop()
 
     @patch("gitea_mcp_server._get_workspace_porcelain", return_value="")
     @patch("gitea_mcp_server._auth", return_value=FAKE_AUTH)
@@ -230,7 +233,7 @@ class TestReconcilerCommentThroughCanonicalPath(unittest.TestCase):
                 os.environ.pop("GITEA_ACTIVE_WORKTREE", None)
                 os.environ.pop("GITEA_RECONCILER_WORKTREE", None)
                 result = srv.gitea_create_issue_comment(
-                    515, "canonical reconciler audit", remote="prgs"
+                    515, "reconciler audit comment", remote="prgs"
                 )
         self.assertTrue(result["success"])
         self.assertEqual(result["comment_id"], 9001)

tests/test_issue_comment_workspace_guard.py

@@ -107,7 +107,7 @@ class TestIssueCommentWorkspaceGuard(unittest.TestCase):
                 with self.assertRaises(RuntimeError) as ctx:
                     srv.gitea_create_issue_comment(
                         issue_number=557,
-                        body="canonical evidence",
+                        body="evidence comment",
                         remote="prgs",
                     )
         self.assertIn("stable control checkout", str(ctx.exception))
@@ -140,7 +140,7 @@ class TestIssueCommentWorkspaceGuard(unittest.TestCase):
                         with patch.dict(os.environ, self.AUTHOR_ENV, clear=True):
                             result = srv.gitea_create_issue_comment(
                                 issue_number=557,
-                                body="canonical evidence",
+                                body="evidence comment",
                                 remote="prgs",
                                 org="Scaled-Tech-Consulting",
                                 repo="Gitea-Tools",
@@ -153,7 +153,7 @@ class TestIssueCommentWorkspaceGuard(unittest.TestCase):
         method, url, _auth_arg, payload = mock_api.call_args[0]
         self.assertEqual(method, "POST")
         self.assertIn("/repos/Scaled-Tech-Consulting/Gitea-Tools/issues/557/comments", url)
-        self.assertEqual(payload, {"body": "canonical evidence"})
+        self.assertEqual(payload, {"body": "evidence comment"})
 
     @patch("gitea_mcp_server._auth", return_value=FAKE_AUTH)
     @patch("gitea_mcp_server.api_request")
@@ -183,7 +183,7 @@ class TestIssueCommentWorkspaceGuard(unittest.TestCase):
                             with self.assertRaises(RuntimeError) as ctx:
                                 srv.gitea_create_issue_comment(
                                     issue_number=557,
-                                    body="canonical evidence",
+                                    body="evidence comment",
                                     remote="prgs",
                                     worktree_path=outside_worktree,
                                 )
@@ -198,7 +198,7 @@ class TestIssueCommentWorkspaceGuard(unittest.TestCase):
             with self.assertRaises(RuntimeError) as ctx:
                 srv.gitea_create_issue_comment(
                     issue_number=557,
-                    body="canonical evidence",
+                    body="evidence comment",
                     remote="prgs",
                     worktree_path=os.path.join(
                         CONTROL_CHECKOUT_ROOT,
@@ -239,7 +239,7 @@ class TestIssueCommentWorkspaceGuard(unittest.TestCase):
                         with patch.dict(os.environ, denied_env, clear=True):
                             result = srv.gitea_create_issue_comment(
                                 issue_number=557,
-                                body="canonical evidence",
+                                body="evidence comment",
                                 remote="prgs",
                                 worktree_path=valid_worktree,
                             )

tests/test_issue_content_gate.py

@@ -0,0 +1,195 @@
+"""Tests for the pre-create issue content gate (Issue #582)."""
+import sys
+import unittest
+from unittest.mock import patch
+
+sys.path.insert(0, str(__import__("pathlib").Path(__file__).resolve().parent.parent))
+
+from issue_content_gate import (  # noqa: E402
+    assess_issue_content,
+    find_vague_reference,
+    has_durable_source_pointer,
+    normalize_text,
+    pre_create_issue_content_gate,
+)
+from mcp_server import gitea_create_issue  # noqa: E402
+
+FAKE_AUTH = "Basic dGVzdDp0ZXN0"
+ISSUE_WRITE_ENV = {
+    "GITEA_ALLOWED_OPERATIONS": "gitea.issue.create",
+}
+
+
+class TestNormalizeAndPointers(unittest.TestCase):
+
+    def test_normalize_strips_punctuation_and_case(self):
+        self.assertEqual(normalize_text("  The Drafted-Issue!  "), "the drafted issue")
+
+    def test_issue_ref_is_durable_pointer(self):
+        self.assertTrue(has_durable_source_pointer("See #402 for the spec"))
+
+    def test_file_path_is_durable_pointer(self):
+        self.assertTrue(has_durable_source_pointer("Draft in task_capability_map.py"))
+
+    def test_scratchpad_is_durable_pointer(self):
+        self.assertTrue(has_durable_source_pointer("Full text in scratchpad/draft.md"))
+
+    def test_url_is_durable_pointer(self):
+        self.assertTrue(
+            has_durable_source_pointer("https://gitea.prgs.cc/issues/1 has it")
+        )
+
+    def test_plain_text_has_no_durable_pointer(self):
+        self.assertFalse(has_durable_source_pointer("just some words here"))
+
+
+class TestFindVagueReference(unittest.TestCase):
+
+    def test_bare_vague_phrases_are_flagged(self):
+        for text in (
+            "the drafted issue",
+            "The prepared issue",
+            "the issue we discussed",
+            "the previous draft",
+            "Create the drafted issue",
+            "please file the prepared issue",
+        ):
+            with self.subTest(text=text):
+                self.assertIsNotNone(find_vague_reference(text))
+
+    def test_durable_pointer_defeats_vague_reference(self):
+        # Same vague phrase but with a durable pointer -> not vague.
+        self.assertIsNone(find_vague_reference("the drafted issue in #402"))
+        self.assertIsNone(
+            find_vague_reference("the prepared issue: see scratchpad/draft.md")
+        )
+
+    def test_long_specific_body_with_incidental_phrase_is_not_vague(self):
+        body = (
+            "As discussed, the create_issue tool must reject vague references. "
+            "Add a preflight check that lists the exact missing fields and "
+            "returns BLOCKED + DIAGNOSE with concrete acceptance criteria."
+        )
+        self.assertIsNone(find_vague_reference(body))
+
+    def test_concrete_short_body_is_not_vague(self):
+        self.assertIsNone(find_vague_reference("Fix null deref in auth handler"))
+
+    def test_empty_is_not_vague(self):
+        self.assertIsNone(find_vague_reference(""))
+
+
+class TestAssessIssueContent(unittest.TestCase):
+
+    def test_missing_title_is_incomplete(self):
+        result = assess_issue_content("", "some body")
+        self.assertFalse(result["complete"])
+        self.assertIn("title", result["missing_fields"])
+
+    def test_vague_body_is_incomplete_and_diagnosed(self):
+        result = assess_issue_content("Add the thing", "the drafted issue")
+        self.assertFalse(result["complete"])
+        self.assertIn("body", result["vague_fields"])
+        self.assertIn("vague reference", result["diagnose"])
+
+    def test_vague_title_is_incomplete(self):
+        result = assess_issue_content("the prepared issue", "")
+        self.assertFalse(result["complete"])
+        self.assertIn("title", result["vague_fields"])
+
+    def test_complete_content_passes(self):
+        result = assess_issue_content(
+            "Block vague issue creation",
+            "Add a preflight gate that rejects placeholder references.",
+        )
+        self.assertTrue(result["complete"])
+        self.assertEqual(result["missing_fields"], [])
+        self.assertEqual(result["vague_fields"], [])
+
+    def test_title_only_is_allowed(self):
+        # Empty body must NOT block: title-only creation stays allowed.
+        result = assess_issue_content("A concrete specific title", "")
+        self.assertTrue(result["complete"])
+
+    def test_durable_pointer_body_passes(self):
+        result = assess_issue_content(
+            "Implement the drafted change",
+            "the drafted issue is fully specified in #582",
+        )
+        self.assertTrue(result["complete"])
+
+    def test_allow_incomplete_override(self):
+        result = assess_issue_content(
+            "the drafted issue", "the drafted issue", allow_incomplete=True
+        )
+        self.assertTrue(result["complete"])
+        self.assertTrue(result["override_applied"])
+
+    def test_gate_wrapper_sets_performed(self):
+        blocked = pre_create_issue_content_gate("Add x", "the drafted issue")
+        self.assertFalse(blocked["performed"])
+        ok = pre_create_issue_content_gate("Add x", "concrete actionable body")
+        self.assertTrue(ok["performed"])
+
+
+class TestCreateIssueContentMCPGate(unittest.TestCase):
+
+    @patch("mcp_server.role_session_router.check_author_mutation_after_reviewer_stop")
+    @patch("mcp_server.api_request")
+    @patch("mcp_server.api_get_all")
+    @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
+    def test_blocks_vague_reference_without_creating(
+        self, _auth, mock_get_all, mock_api, mock_role_check
+    ):
+        mock_role_check.return_value = (True, [])
+        with patch.dict(__import__("os").environ, ISSUE_WRITE_ENV, clear=True):
+            result = gitea_create_issue(
+                title="Create the drafted issue",
+                body="the drafted issue",
+                remote="prgs",
+            )
+        self.assertFalse(result["performed"])
+        self.assertIn("content_gate", result)
+        self.assertIn("body", result["content_gate"]["vague_fields"])
+        self.assertTrue(any("BLOCKED + DIAGNOSE" in r for r in result["reasons"]))
+        mock_api.assert_not_called()
+        mock_get_all.assert_not_called()
+
+    @patch("mcp_server.role_session_router.check_author_mutation_after_reviewer_stop")
+    @patch("mcp_server.api_request")
+    @patch("mcp_server.api_get_all", return_value=[])
+    @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
+    def test_creates_when_content_is_concrete(
+        self, _auth, _get_all, mock_api, mock_role_check
+    ):
+        mock_role_check.return_value = (True, [])
+        mock_api.return_value = {"number": 7, "html_url": "https://x/issues/7"}
+        with patch.dict(__import__("os").environ, ISSUE_WRITE_ENV, clear=True):
+            result = gitea_create_issue(
+                title="Block vague issue creation",
+                body="Add a preflight gate rejecting placeholder references.",
+                remote="prgs",
+            )
+        self.assertEqual(result["number"], 7)
+
+    @patch("mcp_server.role_session_router.check_author_mutation_after_reviewer_stop")
+    @patch("mcp_server.api_request")
+    @patch("mcp_server.api_get_all", return_value=[])
+    @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
+    def test_override_creates_despite_vague_content(
+        self, _auth, _get_all, mock_api, mock_role_check
+    ):
+        mock_role_check.return_value = (True, [])
+        mock_api.return_value = {"number": 8, "html_url": "https://x/issues/8"}
+        with patch.dict(__import__("os").environ, ISSUE_WRITE_ENV, clear=True):
+            result = gitea_create_issue(
+                title="the drafted issue",
+                body="the drafted issue",
+                remote="prgs",
+                allow_incomplete_content=True,
+            )
+        self.assertEqual(result["number"], 8)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_issue_workflow_labels.py

@@ -0,0 +1,73 @@
+"""Tests for canonical issue workflow label policy (#513)."""
+
+from __future__ import annotations
+
+import sys
+import unittest
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+import issue_workflow_labels as labels  # noqa: E402
+
+
+class TestIssueWorkflowLabelValidation(unittest.TestCase):
+    def test_valid_labeled_issue(self):
+        result = labels.assess_issue_labels(["type:feature", "status:ready"])
+        self.assertTrue(result["valid"])
+        self.assertEqual(result["type_labels"], ["type:feature"])
+        self.assertEqual(result["status_labels"], ["status:ready"])
+
+    def test_issue_missing_type_label(self):
+        result = labels.assess_issue_labels(["status:ready"])
+        self.assertFalse(result["valid"])
+        self.assertIn("issue is missing a type:* label", result["errors"])
+
+    def test_issue_missing_status_label(self):
+        result = labels.assess_issue_labels(["type:bug"])
+        self.assertFalse(result["valid"])
+        self.assertIn("issue is missing a status:* label", result["errors"])
+
+    def test_discussion_issue_missing_type_discussion(self):
+        result = labels.assess_issue_labels(
+            ["type:feature", "status:triage"],
+            discussion=True,
+        )
+        self.assertFalse(result["valid"])
+        self.assertIn("discussion issue is missing type:discussion", result["errors"])
+
+    def test_multiple_conflicting_status_labels(self):
+        result = labels.assess_issue_labels(
+            ["type:feature", "status:ready", "status:blocked"]
+        )
+        self.assertFalse(result["valid"])
+        self.assertTrue(
+            any("multiple active status:* labels" in err for err in result["errors"])
+        )
+
+
+class TestIssueWorkflowStatusTransitions(unittest.TestCase):
+    def test_status_transition_removes_old_status_label(self):
+        result = labels.transition_status_labels(
+            ["type:feature", "status:ready", "workflow"],
+            "in-progress",
+        )
+        self.assertEqual(result, ["type:feature", "workflow", "status:in-progress"])
+
+    def test_pr_open_transition_applies_status_pr_open(self):
+        result = labels.transition_status_labels(
+            ["type:feature", "status:in-progress"],
+            "pr-open",
+        )
+        self.assertEqual(result, ["type:feature", "status:pr-open"])
+
+    def test_duplicate_transition_applies_status_duplicate(self):
+        result = labels.transition_status_labels(
+            ["type:process", "status:triage"],
+            "duplicate",
+        )
+        self.assertEqual(result, ["type:process", "status:duplicate"])
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_issue_write_tool_gates.py

@@ -164,13 +164,14 @@ class TestAllowedIssueWritesProceed(IssueWriteGateBase):
             result = mcp_server.gitea_close_issue(issue_number=9, remote="prgs")
         self.assertTrue(result.get("success"))
 
+    @patch("mcp_server.api_get_all", return_value=[{"id": 10, "name": "status:in-progress"}])
     @patch("mcp_server.api_request")
     @patch("mcp_server.get_auth_header", return_value="token author-pass")
-    def test_resolver_allowed_mark_issue_proceeds(self, _auth, mock_api):
+    def test_resolver_allowed_mark_issue_proceeds(self, _auth, mock_api, _labels):
         def api_side_effect(method, url, auth, payload=None):
-            if method == "GET" and url.endswith("/labels?limit=100"):
-                return [{"id": 10, "name": "status:in-progress"}]
-            if method == "POST" and "/issues/9/labels" in url:
+            if method == "GET" and "/issues/9" in url:
+                return {"labels": []}
+            if method == "PUT" and "/issues/9/labels" in url:
                 return [{"name": "status:in-progress"}]
             if method == "POST" and "/issues/9/comments" in url:
                 return {"id": 501}
@@ -209,4 +210,4 @@ class TestCreateIssueMissingPermissionReport(IssueWriteGateBase):
 
 
 if __name__ == "__main__":
-    unittest.main()
+    unittest.main()

tests/test_lock_issue_mcp_registration.py

@@ -97,7 +97,7 @@ class TestCreatePrLockRegistrationFlow(unittest.TestCase):
         "mcp_server.issue_lock_worktree.read_worktree_git_state",
         return_value=_clean_master_git_state_for_lock(),
     )
-    @patch("mcp_server.api_get_all", return_value=[])
+    @patch("mcp_server.api_get_all", return_value=[{"id": 4, "name": "status:pr-open"}])
     @patch("mcp_server.role_session_router.check_author_mutation_after_reviewer_stop",
            return_value=(True, []))
     @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
@@ -105,7 +105,11 @@ class TestCreatePrLockRegistrationFlow(unittest.TestCase):
         self, _auth, _role, _api, _git_state, mock_api_request
     ):
         worktree = os.path.realpath(os.getcwd())
-        mock_api_request.return_value = {"number": 521, "html_url": "https://example/pr/521"}
+        def mock_api(method, url, auth, data=None):
+            if "/labels" in url:
+                return [{"name": "status:pr-open"}]
+            return {"number": 521, "html_url": "https://example/pr/521"}
+        mock_api_request.side_effect = mock_api
         lock_res = gitea_lock_issue(
             issue_number=521,
             branch_name="feat/issue-521-lock-issue-registration",

tests/test_manage_labels.py

@@ -11,6 +11,7 @@ from unittest.mock import MagicMock, call, patch
 
 sys.path.insert(0, str(__import__("pathlib").Path(__file__).resolve().parent.parent))
 import manage_labels  # noqa: E402
+import issue_workflow_labels  # noqa: E402
 
 
 FAKE_AUTH = "Basic dGVzdDp0ZXN0"  # base64("test:test")
@@ -129,6 +130,11 @@ class TestConstants(unittest.TestCase):
         names = [l["name"] for l in manage_labels.LABELS]
         self.assertIn("status:in-progress", names)
 
+    def test_canonical_workflow_labels_are_defined(self):
+        names = {l["name"] for l in manage_labels.LABELS}
+        for spec in issue_workflow_labels.CANONICAL_LABEL_SPECS:
+            self.assertIn(spec.name, names)
+
     def test_all_mapped_labels_are_defined(self):
         defined = {l["name"] for l in manage_labels.LABELS}
         for issue, names in manage_labels.MAPPING.items():

tests/test_mcp_daemon_guard.py

@@ -0,0 +1,67 @@
+"""Tests for sanctioned MCP daemon guards (#558)."""
+
+from __future__ import annotations
+
+import os
+import unittest
+from unittest.mock import patch
+
+import mcp_daemon_guard
+import gitea_auth
+
+
+class TestMcpDaemonGuard(unittest.TestCase):
+    def test_unsanctioned_blocks_mutation_runtime(self):
+        env = {k: v for k, v in os.environ.items() if k not in {
+            mcp_daemon_guard.SANCTIONED_DAEMON_ENV,
+            mcp_daemon_guard.ALLOW_DIRECT_IMPORT_ENV,
+            "PYTEST_CURRENT_TEST",
+        }}
+        with patch.dict(os.environ, env, clear=True):
+            with self.assertRaises(mcp_daemon_guard.UnsanctionedRuntimeError):
+                mcp_daemon_guard.assert_sanctioned_mutation_runtime("test")
+
+    def test_pytest_allows_runtime(self):
+        # Running under pytest already sets PYTEST_CURRENT_TEST.
+        mcp_daemon_guard.assert_sanctioned_mutation_runtime("pytest")
+
+    def test_mark_sanctioned_allows(self):
+        env = {k: v for k, v in os.environ.items() if k != "PYTEST_CURRENT_TEST"}
+        env[mcp_daemon_guard.SANCTIONED_DAEMON_ENV] = "1"
+        with patch.dict(os.environ, env, clear=True):
+            mcp_daemon_guard.assert_sanctioned_mutation_runtime("daemon")
+
+    def test_keychain_blocked_without_sanction(self):
+        env = {
+            k: v
+            for k, v in os.environ.items()
+            if k
+            not in {
+                mcp_daemon_guard.SANCTIONED_DAEMON_ENV,
+                mcp_daemon_guard.ALLOW_DIRECT_IMPORT_ENV,
+                mcp_daemon_guard.ALLOW_KEYCHAIN_CLI_ENV,
+                "PYTEST_CURRENT_TEST",
+            }
+        }
+        with patch.dict(os.environ, env, clear=True):
+            with self.assertRaises(mcp_daemon_guard.UnsanctionedRuntimeError):
+                mcp_daemon_guard.assert_keychain_access_allowed()
+
+    def test_get_auth_header_blocked_when_unsanctioned(self):
+        env = {
+            k: v
+            for k, v in os.environ.items()
+            if k
+            not in {
+                mcp_daemon_guard.SANCTIONED_DAEMON_ENV,
+                mcp_daemon_guard.ALLOW_DIRECT_IMPORT_ENV,
+                "PYTEST_CURRENT_TEST",
+            }
+        }
+        with patch.dict(os.environ, env, clear=True):
+            with self.assertRaises(mcp_daemon_guard.UnsanctionedRuntimeError):
+                gitea_auth.get_auth_header("gitea.prgs.cc")
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_mcp_menu_script.py

@@ -105,6 +105,19 @@ class TestMcpMenuScript(unittest.TestCase):
         self.assertIn("./mcp-menu.sh", docs_text)
         self.assertIn("placeholder", docs_text.lower())
 
+    def test_reviewer_skip_stale_request_changes_prompt_discoverable(self):
+        # #482: the skip-already-reviewed-stale-REQUEST_CHANGES reviewer prompt
+        # must be reachable from the reviewer menu and documented.
+        label = "Skip already-reviewed stale REQUEST_CHANGES PR and hand off to author"
+        reviewer_fn = self._extract_function("show_reviewer_prompts")
+        self.assertIn(label, reviewer_fn, "new reviewer prompt label must appear in the reviewer menu")
+        # The prompt must instruct: no duplicate terminal review mutation for a
+        # non-stale REQUEST_CHANGES head, and must carry the author handoff.
+        self.assertIn("do NOT submit another terminal review mutation", reviewer_fn)
+        self.assertIn("author-ready fix prompt", reviewer_fn)
+        docs_text = DOCS.read_text(encoding="utf-8")
+        self.assertIn("REQUEST_CHANGES", docs_text)
+
     def _extract_function(self, name: str) -> str:
         marker = f"{name}() {{"
         start = self.content.index(marker)

tests/test_mcp_namespace_health.py

@@ -0,0 +1,208 @@
+import unittest
+
+import gitea_mcp_server
+import mcp_namespace_health
+import review_merge_state_machine as rmsm
+
+
+class TestMcpNamespaceHealth(unittest.TestCase):
+    def setUp(self):
+        gitea_mcp_server._LIVE_NAMESPACE_HEALTH.clear()
+
+    def test_registered_tool_but_live_eof_blocks_merge(self):
+        result = mcp_namespace_health.classify_namespace_probe(
+            "gitea-reviewer",
+            required_tool="gitea_whoami",
+            registered_tools=["gitea_whoami", "gitea_list_profiles"],
+            probe_result={
+                "success": False,
+                "error": "client is closing: EOF",
+            },
+            process={
+                "pid": 4321,
+                "profile": "prgs-reviewer",
+                "env": {
+                    "GITEA_MCP_PROFILE": "prgs-reviewer",
+                    "GITEA_TOKEN": "must-not-leak",
+                },
+            },
+            config_path="/Users/jasonwalker/.gemini/config/mcp_config.json",
+            probe_source="client_namespace",
+        )
+
+        self.assertFalse(result["healthy"])
+        self.assertEqual(result["error_type"], "namespace_eof")
+        self.assertTrue(result["required_tool_registered"])
+        self.assertFalse(result["required_tool_callable"])
+        self.assertTrue(result["blocks_merge_workflow"])
+        self.assertFalse(result["ide_namespace_proven"])
+        self.assertEqual(result["probe_source"], "client_namespace")
+        self.assertEqual(result["diagnostics"]["process_pid"], 4321)
+        self.assertEqual(result["diagnostics"]["profile"], "prgs-reviewer")
+        self.assertEqual(
+            result["diagnostics"]["env"]["GITEA_MCP_PROFILE"],
+            "prgs-reviewer",
+        )
+        self.assertNotIn("GITEA_TOKEN", result["diagnostics"]["env"])
+        self.assertIn("gitea-reviewer", result["reasons"][0])
+        self.assertIn("gitea_whoami", result["reasons"][0])
+
+    def test_successful_client_namespace_invocation_is_ide_proven(self):
+        result = mcp_namespace_health.classify_namespace_probe(
+            "gitea-author",
+            registered_tools=["gitea_whoami"],
+            probe_result={"success": True, "result": {"authenticated": True}},
+            process={"pid": 1234, "profile": "prgs-author"},
+            config_path="/tmp/mcp_config.json",
+            probe_source="client_namespace",
+        )
+
+        self.assertTrue(result["healthy"])
+        self.assertTrue(result["required_tool_registered"])
+        self.assertTrue(result["required_tool_callable"])
+        self.assertTrue(result["ide_namespace_proven"])
+        self.assertFalse(result["blocks_merge_workflow"])
+        self.assertIsNone(result["error_type"])
+
+    def test_offline_spawn_success_is_not_ide_proof(self):
+        result = mcp_namespace_health.classify_namespace_probe(
+            "gitea-merger",
+            registered_tools=["gitea_whoami"],
+            probe_result={"success": True, "result": {}},
+            process={"pid": 99, "profile": "prgs-merger"},
+            probe_source="offline_spawn",
+        )
+        self.assertTrue(result["healthy"])
+        self.assertFalse(result["ide_namespace_proven"])
+        self.assertFalse(result["blocks_merge_workflow"])
+        self.assertTrue(
+            any("offline_spawn" in r for r in result["reasons"])
+        )
+
+    def test_registered_missing_required_tool_fails_before_probe_success(self):
+        result = mcp_namespace_health.classify_namespace_probe(
+            "gitea-tools",
+            registered_tools=["gitea_whoami"],
+            probe_result={"success": True, "result": {}},
+            probe_source="client_namespace",
+        )
+
+        self.assertFalse(result["healthy"])
+        self.assertEqual(result["required_tool"], "gitea_list_profiles")
+        self.assertFalse(result["required_tool_registered"])
+        self.assertEqual(result["error_type"], "tool_missing")
+
+    def test_server_tool_exposes_same_assessment_and_records_session(self):
+        result = gitea_mcp_server.gitea_assess_mcp_namespace_health(
+            "gitea-merger",
+            registered_tools=["gitea_whoami"],
+            probe_result={"success": False, "error": "transport closed"},
+            process={"pid": 9876, "profile": "prgs-merger"},
+            probe_source="client_namespace",
+        )
+
+        self.assertFalse(result["success"])
+        self.assertEqual(result["error_type"], "namespace_eof")
+        self.assertEqual(result["namespace"], "gitea-merger")
+        self.assertEqual(result["diagnostics"]["process_pid"], 9876)
+        self.assertIn("gitea-merger", gitea_mcp_server._LIVE_NAMESPACE_HEALTH)
+        gate = gitea_mcp_server._live_namespace_health_gate("merge_pr")
+        self.assertTrue(gate)
+        self.assertTrue(any("gitea-merger" in r for r in gate))
+
+
+class TestLiveNamespaceBlocksMerge(unittest.TestCase):
+    """AC5: a broken live namespace must hard-block the review/merge state machine."""
+
+    def setUp(self):
+        gitea_mcp_server._LIVE_NAMESPACE_HEALTH.clear()
+
+    def _merge_ready_completion(self):
+        # Completion through PRE_MERGE_RECHECK is the state where a clean merge
+        # is otherwise allowed (see test_merge_allowed_with_pre_merge_gates).
+        idx = rmsm.REVIEW_MERGE_STATES.index("PRE_MERGE_RECHECK")
+        return {state: True for state in rmsm.REVIEW_MERGE_STATES[: idx + 1]}
+
+    def _all_gates(self):
+        return {gate: True for gate in rmsm._PRE_MERGE_REQUIRED_GATES}
+
+    def test_assess_workflow_blockers_flags_live_namespace_broken(self):
+        clean = rmsm.assess_workflow_blockers()
+        self.assertFalse(clean["block"])
+
+        broken = rmsm.assess_workflow_blockers(live_namespace_broken=True)
+        self.assertTrue(broken["block"])
+        self.assertTrue(any("namespace" in r.lower() for r in broken["reasons"]))
+
+    def test_can_merge_blocks_even_when_all_gates_pass(self):
+        # Without the namespace blocker a fully-complete workflow can merge...
+        allowed = rmsm.can_merge(
+            self._merge_ready_completion(), pre_merge_gates=self._all_gates()
+        )
+        self.assertTrue(allowed["allowed"])
+
+        # ...but a broken live namespace overrides every satisfied gate.
+        blocked = rmsm.can_merge(
+            self._merge_ready_completion(),
+            pre_merge_gates=self._all_gates(),
+            live_namespace_broken=True,
+        )
+        self.assertTrue(blocked["block"])
+        self.assertFalse(blocked["allowed"])
+
+    def test_workflow_status_forwards_namespace_blocker(self):
+        status = rmsm.workflow_status(
+            self._merge_ready_completion(), live_namespace_broken=True
+        )
+        self.assertFalse(status["merge_allowed"])
+        self.assertFalse(status["approve_allowed"])
+
+    def test_server_tool_blocks_merge_on_live_namespace_broken(self):
+        result = gitea_mcp_server.gitea_assess_review_merge_state_machine(
+            state_completion=self._merge_ready_completion(),
+            pre_merge_gates=self._all_gates(),
+            live_namespace_broken=True,
+        )
+        self.assertTrue(result["blockers"]["block"])
+        self.assertFalse(result["merge"]["allowed"])
+
+    def test_classify_verdict_bridges_into_merge_block(self):
+        # The classify verdict is the intended feed for live_namespace_broken.
+        verdict = mcp_namespace_health.classify_namespace_probe(
+            "gitea-merger",
+            registered_tools=["gitea_whoami", "gitea_adopt_merger_pr_lease"],
+            probe_result={"success": False, "error": "client is closing: EOF"},
+            process={"pid": 555, "profile": "prgs-merger"},
+            probe_source="client_namespace",
+        )
+        self.assertTrue(verdict["blocks_merge_workflow"])
+        blocked = rmsm.can_merge(
+            self._merge_ready_completion(),
+            pre_merge_gates=self._all_gates(),
+            live_namespace_broken=verdict["blocks_merge_workflow"],
+        )
+        self.assertFalse(blocked["allowed"])
+
+    def test_offline_spawn_does_not_authorize_mutation_gate(self):
+        gitea_mcp_server.gitea_assess_mcp_namespace_health(
+            "gitea-merger",
+            registered_tools=["gitea_whoami"],
+            probe_result={"success": True, "result": {}},
+            probe_source="offline_spawn",
+        )
+        gate = gitea_mcp_server._live_namespace_health_gate("merge_pr")
+        self.assertTrue(gate)
+        self.assertTrue(any("offline_spawn" in r or "client_namespace" in r for r in gate))
+
+    def test_client_namespace_healthy_clears_mutation_gate(self):
+        gitea_mcp_server.gitea_assess_mcp_namespace_health(
+            "gitea-merger",
+            registered_tools=["gitea_whoami"],
+            probe_result={"success": True, "result": {}},
+            probe_source="client_namespace",
+        )
+        self.assertEqual(gitea_mcp_server._live_namespace_health_gate("merge_pr"), [])
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_mcp_server.py

@@ -91,6 +91,16 @@ def _visible_approval_reviews(reviewer="reviewer-bot", sha="abc123"):
 
 _DEFAULT_LEASE_SESSION = "mcp-test-reviewer-lease"
 _NO_PR_WORK_LEASE_BLOCK = {"block": False, "reasons": [], "mutation_allowed": True}
+WORKFLOW_REPO_LABELS = [
+    {"id": 1, "name": "type:feature"},
+    {"id": 2, "name": "status:in-progress"},
+    {"id": 3, "name": "status:ready"},
+    {"id": 4, "name": "status:pr-open"},
+]
+
+
+def _issue_with_labels(*names):
+    return {"labels": [{"name": name} for name in names]}
 
 
 def _reviewer_lease_comment(
@@ -305,6 +315,22 @@ class TestCreateIssue(unittest.TestCase):
         self.assertIn("gitea.prgs.cc", url)
         self.assertIn("Scaled-Tech-Consulting", url)
 
+    @patch("mcp_server.role_session_router.check_author_mutation_after_reviewer_stop",
+           return_value=(True, []))
+    @patch("mcp_server.api_request")
+    @patch("mcp_server.api_get_all", return_value=[])
+    @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
+    def test_create_issue_required_workflow_labels_blocks(self, _auth, _get_all, mock_api, _role):
+        with patch.dict(os.environ, ISSUE_WRITE_ENV, clear=True):
+            result = gitea_create_issue(
+                title="Test issue",
+                require_workflow_labels=True,
+            )
+        self.assertFalse(result["success"])
+        self.assertFalse(result["performed"])
+        self.assertIn("issue is missing a type:* label", result["reasons"])
+        mock_api.assert_not_called()
+
 
 # ---------------------------------------------------------------------------
 # Create PR
@@ -315,13 +341,24 @@ class TestCreatePR(unittest.TestCase):
         "mcp_server.issue_duplicate_context_fetcher",
         return_value=([], [], {"status": "not_claimed"}),
     )
+    @patch("mcp_server.api_get_all", return_value=WORKFLOW_REPO_LABELS)
     @patch("mcp_server.role_session_router.check_author_mutation_after_reviewer_stop",
            return_value=(True, []))
     @patch("mcp_server.api_request")
     @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
-    def test_creates_pr(self, _auth, mock_api, _role, _dup_fetcher):
+    def test_creates_pr(self, _auth, mock_api, _role, _labels, _dup_fetcher):
         worktree = os.path.realpath(os.getcwd())
-        mock_api.return_value = {"number": 3, "html_url": "https://example.com/pulls/3"}
+
+        def api_side_effect(method, url, auth, payload=None):
+            if method == "GET" and "/issues/123" in url:
+                return _issue_with_labels("type:feature", "status:in-progress")
+            if method == "POST" and url.endswith("/pulls"):
+                return {"number": 3, "html_url": "https://example.com/pulls/3"}
+            if method == "PUT" and url.endswith("/issues/123/labels"):
+                return [{"name": "type:feature"}, {"name": "status:pr-open"}]
+            return {}
+
+        mock_api.side_effect = api_side_effect
         with tempfile.TemporaryDirectory() as lock_dir:
             env = {**CREATE_PR_ENV, "GITEA_ISSUE_LOCK_DIR": lock_dir}
             with patch.dict(os.environ, env, clear=True):
@@ -334,22 +371,37 @@ class TestCreatePR(unittest.TestCase):
                 )
         self.assertEqual(result["number"], 3)
         self.assertNotIn("url", result)
-        payload = mock_api.call_args[0][3]
+        post_call = next(c for c in mock_api.call_args_list if c[0][0] == "POST")
+        payload = post_call[0][3]
         self.assertEqual(payload["head"], "feat/x")
         self.assertEqual(payload["base"], "main")
         self.assertIn("Closes #123", payload["title"])
+        put_call = next(c for c in mock_api.call_args_list if c[0][0] == "PUT")
+        self.assertEqual(put_call[0][3], {"labels": [1, 4]})
+        self.assertTrue(result["issue_status_transition"]["performed"])
 
     @patch(
         "mcp_server.issue_duplicate_context_fetcher",
         return_value=([], [], {"status": "not_claimed"}),
     )
+    @patch("mcp_server.api_get_all", return_value=WORKFLOW_REPO_LABELS)
     @patch("mcp_server.role_session_router.check_author_mutation_after_reviewer_stop",
            return_value=(True, []))
     @patch("mcp_server.api_request")
     @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
-    def test_create_pr_reveal_opt_in_includes_url(self, _auth, mock_api, _role, _dup_fetcher):
+    def test_create_pr_reveal_opt_in_includes_url(self, _auth, mock_api, _role, _labels, _dup_fetcher):
         worktree = os.path.realpath(os.getcwd())
-        mock_api.return_value = {"number": 3, "html_url": "https://example.com/pulls/3"}
+
+        def api_side_effect(method, url, auth, payload=None):
+            if method == "GET" and "/issues/123" in url:
+                return _issue_with_labels("type:feature", "status:in-progress")
+            if method == "POST" and url.endswith("/pulls"):
+                return {"number": 3, "html_url": "https://example.com/pulls/3"}
+            if method == "PUT" and url.endswith("/issues/123/labels"):
+                return [{"name": "type:feature"}, {"name": "status:pr-open"}]
+            return {}
+
+        mock_api.side_effect = api_side_effect
         with tempfile.TemporaryDirectory() as lock_dir:
             env = {**CREATE_PR_ENV, "GITEA_ISSUE_LOCK_DIR": lock_dir, "GITEA_MCP_REVEAL_ENDPOINTS": "1"}
             with patch.dict(os.environ, env, clear=True):
@@ -362,6 +414,38 @@ class TestCreatePR(unittest.TestCase):
                 )
         self.assertIn("pulls/3", result["url"])
 
+    @patch(
+        "mcp_server.issue_duplicate_context_fetcher",
+        return_value=([], [], {"status": "not_claimed"}),
+    )
+    @patch("mcp_server.api_get_all", return_value=[{"id": 1, "name": "type:feature"}])
+    @patch("mcp_server.role_session_router.check_author_mutation_after_reviewer_stop",
+           return_value=(True, []))
+    @patch("mcp_server.api_request")
+    @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
+    def test_create_pr_blocks_when_pr_open_status_label_missing(
+        self, _auth, mock_api, _role, _labels, _dup_fetcher
+    ):
+        worktree = os.path.realpath(os.getcwd())
+        mock_api.return_value = _issue_with_labels("type:feature", "status:in-progress")
+        with tempfile.TemporaryDirectory() as lock_dir:
+            env = {**CREATE_PR_ENV, "GITEA_ISSUE_LOCK_DIR": lock_dir}
+            with patch.dict(os.environ, env, clear=True):
+                _bind_test_lock(issue_number=123, branch_name="feat/x", worktree_path=worktree)
+                result = gitea_create_pr(
+                    title="feat: X Closes #123",
+                    head="feat/x",
+                    base="main",
+                    worktree_path=worktree,
+                )
+        self.assertFalse(result["success"])
+        self.assertFalse(result["performed"])
+        self.assertIn("status:pr-open", result["reasons"][0])
+        self.assertFalse(
+            any(c[0][0] == "POST" and c[0][1].endswith("/pulls")
+                for c in mock_api.call_args_list)
+        )
+
     @patch("mcp_server.role_session_router.check_author_mutation_after_reviewer_stop",
            return_value=(True, []))
     @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
@@ -486,26 +570,33 @@ class TestViewIssue(unittest.TestCase):
 # ---------------------------------------------------------------------------
 class TestMarkIssue(unittest.TestCase):
 
+    @patch("mcp_server.api_get_all", return_value=WORKFLOW_REPO_LABELS)
     @patch("mcp_server.api_request")
     @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
-    def test_start_adds_label(self, _auth, mock_api):
-        # labels, add label, post claim heartbeat comment
-        mock_api.side_effect = [
-            [{"id": 10, "name": "status:in-progress"}],
-            [{"name": "status:in-progress"}],
-            {"id": 99},
-        ]
+    def test_start_adds_label(self, _auth, mock_api, _labels):
+        def api_side_effect(method, url, auth, payload=None):
+            if method == "GET" and "/issues/5" in url:
+                return _issue_with_labels("type:feature", "status:ready")
+            if method == "PUT" and url.endswith("/issues/5/labels"):
+                return [{"name": "type:feature"}, {"name": "status:in-progress"}]
+            if method == "POST" and url.endswith("/issues/5/comments"):
+                return {"id": 99}
+            return {}
+
+        mock_api.side_effect = api_side_effect
         with patch.dict(os.environ, ISSUE_WRITE_ENV, clear=True):
             result = gitea_mark_issue(issue_number=5, action="start")
         self.assertTrue(result["success"])
         self.assertIn("claimed", result["message"])
         self.assertTrue(result.get("heartbeat_posted"))
+        put_call = next(c for c in mock_api.call_args_list if c[0][0] == "PUT")
+        self.assertEqual(put_call[0][3], {"labels": [1, 2]})
 
+    @patch("mcp_server.api_get_all", return_value=WORKFLOW_REPO_LABELS)
     @patch("mcp_server.api_request")
     @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
-    def test_done_removes_label(self, _auth, mock_api):
+    def test_done_removes_label(self, _auth, mock_api, _labels):
         mock_api.side_effect = [
-            [{"id": 10, "name": "status:in-progress"}],
             None,
         ]
         with patch.dict(os.environ, ISSUE_WRITE_ENV, clear=True):
@@ -517,10 +608,10 @@ class TestMarkIssue(unittest.TestCase):
         with self.assertRaises(ValueError):
             gitea_mark_issue(issue_number=5, action="pause")
 
+    @patch("mcp_server.api_get_all", return_value=[])
     @patch("mcp_server.api_request")
     @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
-    def test_missing_label_raises(self, _auth, mock_api):
-        mock_api.return_value = []  # no labels exist
+    def test_missing_label_raises(self, _auth, mock_api, _labels):
         with patch.dict(os.environ, ISSUE_WRITE_ENV, clear=True):
             with self.assertRaises(RuntimeError):
                 gitea_mark_issue(issue_number=5, action="start")
@@ -683,6 +774,9 @@ class TestMergePR(unittest.TestCase):
     def setUp(self):
         import reviewer_pr_lease
 
+        # Clean ledger each merge test so residual/host durable #332 state
+        # cannot short-circuit eligibility gates (#590 / #594).
+        mcp_server._save_review_decision_lock(None)
         mcp_server.gitea_load_review_workflow()
         self._lease_patch = _install_owned_reviewer_lease(8)
         self._lease_patch.start()
@@ -861,6 +955,19 @@ class TestMergePR(unittest.TestCase):
 
     # -- identity / profile / eligibility fail-closed -------------------------
 
+    @patch("mcp_server.api_request")
+    @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
+    def test_reviewer_profile_cannot_merge(self, _auth, mock_api):
+        env = {"GITEA_PROFILE_NAME": "prgs-reviewer",
+               "GITEA_ALLOWED_OPERATIONS": "read,approve"}
+        with patch.dict(os.environ, env, clear=True):
+            with self.assertRaises(RuntimeError) as ctx:
+                gitea_merge_pr(
+                    pr_number=8, confirmation=self._confirm(8), remote="prgs"
+                )
+        self.assertIn("Reviewer profile cannot merge. Use a merger profile/session after formal approval at current head.", str(ctx.exception))
+        mock_api.assert_not_called()
+
     @patch("mcp_server.api_request")
     @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
     def test_self_author_cannot_merge(self, _auth, mock_api):
@@ -901,15 +1008,72 @@ class TestMergePR(unittest.TestCase):
 
     @patch("mcp_server.api_request")
     @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
-    def test_profile_without_merge_permission_blocks(self, _auth, mock_api):
+    def test_env_clear_does_not_adopt_host_review_mutation_ledger(
+        self, _auth, mock_api
+    ):
+        """#590: patch.dict(clear=True) must not load host terminal mutations.
+
+        Simulates a dirty host session-state file for profile gitea-default
+        (the profile active when env is fully cleared). Isolation must keep
+        the #332 hard-stop ledger clean so the empty-profile gate fires.
+        """
+        import tempfile
+
+        import mcp_session_state
+
+        poison_dir = tempfile.mkdtemp(prefix="gitea-host-poison-")
+        mcp_session_state.save_state(
+            kind=mcp_session_state.KIND_DECISION_LOCK,
+            profile_identity="gitea-default",
+            state_dir=poison_dir,
+            payload={
+                "task": "review_pr",
+                "remote": "prgs",
+                "final_review_decision_ready": True,
+                "ready_pr_number": 8,
+                "ready_action": "request_changes",
+                "live_mutations": [
+                    {
+                        "pr_number": 8,
+                        "action": "request_changes",
+                        "review_id": 99,
+                        "review_state": "request_changes",
+                    }
+                ],
+            },
+        )
+        # If isolation only used the env var, clear=True would fall back to
+        # DEFAULT_STATE_DIR and adopt this poison ledger.
+        mcp_server._REVIEW_DECISION_LOCK = None
         mock_api.side_effect = [{"login": "merger-bot"}, self._pr("author-bot")]
+        with patch.object(mcp_session_state, "DEFAULT_STATE_DIR", poison_dir):
+            with patch.dict(os.environ, {}, clear=True):
+                r = gitea_merge_pr(
+                    pr_number=8,
+                    confirmation=self._confirm(8),
+                    remote="prgs",
+                )
+        self.assertFalse(r["performed"])
+        self.assertIn(
+            "profile has no configured allowed operations (fail closed)",
+            r["reasons"],
+        )
+        self.assertFalse(
+            any("terminal review mutation already consumed" in x for x in r["reasons"]),
+            msg=f"host ledger leaked into reasons: {r['reasons']}",
+        )
+        self._assert_no_merge_call(mock_api)
+
+    @patch("mcp_server.api_request")
+    @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
+    def test_profile_without_merge_permission_blocks(self, _auth, mock_api):
         env = {"GITEA_PROFILE_NAME": "gitea-reviewer",
                "GITEA_ALLOWED_OPERATIONS": "read,review,approve"}
         with patch.dict(os.environ, env, clear=True):
-            r = gitea_merge_pr(
-                pr_number=8, confirmation=self._confirm(8), remote="prgs")
-        self.assertFalse(r["performed"])
-        self.assertIn("profile is not allowed to merge", r["reasons"])
+            with self.assertRaises(RuntimeError) as ctx:
+                gitea_merge_pr(
+                    pr_number=8, confirmation=self._confirm(8), remote="prgs")
+        self.assertIn("Reviewer profile cannot merge. Use a merger profile/session after formal approval at current head.", str(ctx.exception))
         self._assert_no_merge_call(mock_api)
 
     # -- PR state / mergeability ----------------------------------------------
@@ -2569,6 +2733,56 @@ class TestTrackerHygieneCleanup(unittest.TestCase):
         self.assertTrue(res["success"])
         self.assertEqual(res["cleanup_status"].get(1), "not present")
 
+    def test_close_issue_blocks_unproven_expected_preexisting_failure(self):
+        # #529: a closure report calling a non-zero suite exit an "expected
+        # pre-existing failure" without pre-merge proof must fail closed and
+        # never PATCH the issue state.
+        patched = []
+
+        def api_side_effect(method, url, auth, payload=None):
+            if method == "PATCH":
+                patched.append(url)
+            return {}
+        self.mock_api.side_effect = api_side_effect
+
+        res = gitea_close_issue(
+            issue_number=1,
+            closure_report=(
+                "Full suite: 1 failed. Expected pre-existing failure, safe to close."
+            ),
+        )
+        self.assertFalse(res["success"])
+        self.assertTrue(res.get("blocked"))
+        self.assertTrue(res.get("reasons"))
+        self.assertFalse(
+            patched, "must not PATCH issue state when the closure gate blocks"
+        )
+
+    def test_close_issue_allows_proven_baseline_closure(self):
+        def api_side_effect(method, url, auth, payload=None):
+            if method == "PATCH" and "issues/1" in url:
+                return {"state": "closed"}
+            if method == "GET" and "labels" in url and "issues" not in url:
+                return [{"name": "bug", "id": 2}]
+            if method == "GET" and "issues/1" in url:
+                return {"labels": [{"name": "bug"}]}
+            return {}
+        self.mock_api.side_effect = api_side_effect
+
+        res = gitea_close_issue(
+            issue_number=1,
+            closure_report=(
+                "Full suite: 1 failed, expected pre-existing baseline failure "
+                "proven on the PR pre-merge base commit.\n"
+                "Pre-merge base commit: 1a2b3c4d5e6f7a8b9c0d1e2f3a4b5c6d7e8f9a0b\n"
+                "Tested commit: 1a2b3c4d5e6f7a8b9c0d1e2f3a4b5c6d7e8f9a0b\n"
+                "Command: venv/bin/python -m pytest -q\n"
+                "Exit status: 1\n"
+                "Failure signature: AssertionError: None is not true\n"
+            ),
+        )
+        self.assertTrue(res["success"])
+
     def test_merge_pr_with_closes_removes_label(self):
         import reviewer_pr_lease
 
@@ -3093,6 +3307,20 @@ class TestIssueCommentTools(unittest.TestCase):
         self.assertFalse(result["success"])
         mock_api.assert_not_called()
 
+    @patch("mcp_server.api_request")
+    @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
+    def test_create_tagged_handoff_missing_mutation_ledger_blocked(
+        self, _auth, mock_api
+    ):
+        body = "[CONTROLLER HANDOFF] PR #1 — test\n\nBlockers:\n- none"
+        with patch.dict(os.environ, self.AUTHOR_ENV, clear=True):
+            result = gitea_create_issue_comment(
+                issue_number=9, body=body, remote="prgs")
+        self.assertFalse(result["success"])
+        self.assertFalse(result["performed"])
+        self.assertTrue(result["reasons"])
+        mock_api.assert_not_called()
+
     @patch("mcp_server.api_request")
     @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
     def test_create_empty_body_blocked(self, _auth, mock_api):
@@ -3102,6 +3330,36 @@ class TestIssueCommentTools(unittest.TestCase):
         self.assertFalse(result["success"])
         mock_api.assert_not_called()
 
+    @patch("mcp_server.api_request")
+    @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
+    def test_create_casual_comment_allowed(self, _auth, mock_api):
+        mock_api.return_value = self._comment(556, "gitea-author", "casual")
+        with patch.dict(os.environ, self.AUTHOR_ENV, clear=True):
+            result = gitea_create_issue_comment(
+                issue_number=9,
+                body="Thanks, I will check this.",
+                remote="prgs",
+            )
+        self.assertTrue(result["success"])
+        self.assertTrue(result["performed"])
+        mock_api.assert_called_once()
+
+    @patch("mcp_server.api_request")
+    @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
+    def test_create_workflow_comment_missing_fields_blocked(self, _auth, mock_api):
+        with patch.dict(os.environ, self.AUTHOR_ENV, clear=True):
+            result = gitea_create_issue_comment(
+                issue_number=9,
+                body="Blocked, author should fix.",
+                remote="prgs",
+            )
+        self.assertFalse(result["success"])
+        self.assertFalse(result["performed"])
+        self.assertIn("canonical_comment_validation", result)
+        self.assertFalse(result["canonical_comment_validation"]["allowed"])
+        self.assertTrue(result["canonical_comment_validation"]["is_workflow_comment"])
+        mock_api.assert_not_called()
+
     @patch("mcp_server.api_request")
     @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
     def test_create_missing_issue_error_is_redacted(self, _auth, mock_api):
@@ -3765,13 +4023,24 @@ class TestIssueLocking(unittest.TestCase):
                     )
         self.assertIn("lock provenance", str(ctx.exception).lower())
 
+    @patch("mcp_server.api_get_all", return_value=WORKFLOW_REPO_LABELS)
     @patch("mcp_server.api_request")
     @patch("mcp_server.role_session_router.check_author_mutation_after_reviewer_stop",
            return_value=(True, []))
     @patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
-    def test_create_pr_honors_scratch_worktree_lock(self, _auth, _role, mock_api):
+    def test_create_pr_honors_scratch_worktree_lock(self, _auth, _role, mock_api, _labels):
         scratch = os.path.realpath("/tmp/gitea-tools-author-scratch/issue-249-e2e")
-        mock_api.return_value = {"number": 250, "html_url": "https://example/pr/250"}
+
+        def api_side_effect(method, url, auth, payload=None):
+            if method == "GET" and "/issues/249" in url:
+                return _issue_with_labels("type:feature", "status:in-progress")
+            if method == "POST" and url.endswith("/pulls"):
+                return {"number": 250, "html_url": "https://example/pr/250"}
+            if method == "PUT" and url.endswith("/issues/249/labels"):
+                return [{"name": "type:feature"}, {"name": "status:pr-open"}]
+            return {}
+
+        mock_api.side_effect = api_side_effect
         _bind_test_lock(
             issue_number=249,
             branch_name="feat/issue-249-issue-lock-scratch-worktree",
@@ -3786,6 +4055,7 @@ class TestIssueLocking(unittest.TestCase):
                 worktree_path=scratch,
             )
         self.assertEqual(res["number"], 250)
+        self.assertTrue(res["issue_status_transition"]["performed"])
 
 
 # ---------------------------------------------------------------------------
@@ -4075,7 +4345,7 @@ class TestIssue546Deadlock(unittest.TestCase):
             res = mcp_server.gitea_submit_pr_review(
                 pr_number=550,
                 action="approve",
-                body="APPROVED",
+                body="",
                 expected_head_sha="abc123",
                 final_review_decision_ready=True,
                 remote="prgs",
@@ -4129,3 +4399,236 @@ class TestIssue546Deadlock(unittest.TestCase):
             self.assertIsNone(reviewer_pr_lease.get_session_lease())
             # verify comment phase is released
             self.assertIn("phase: released", posted_comments[0]["body"])
+
+    def test_reviewer_pr_lease_gate_resolves_identity_with_host(self):
+        """Lease mutation gate must resolve identity using host, not remote alias."""
+        import mcp_server
+
+        resolved_hosts = []
+
+        def tracking_username(host):
+            resolved_hosts.append(host)
+            return None if host in {"prgs", "dadeschools"} else "reviewer-bot"
+
+        with _install_owned_reviewer_lease(
+            550,
+            session_id=_DEFAULT_LEASE_SESSION,
+            head_sha="abc123",
+        ), patch(
+            "mcp_server._resolve",
+            return_value=("gitea.prgs.cc", "Scaled-Tech-Consulting", "Gitea-Tools"),
+        ), patch(
+            "mcp_server._authenticated_username",
+            side_effect=tracking_username,
+        ):
+            reasons = mcp_server._reviewer_pr_lease_gate(
+                pr_number=550,
+                remote="prgs",
+                host=None,
+                org=None,
+                repo=None,
+                mutation="approve",
+                live_head_sha="abc123",
+                pinned_head_sha="abc123",
+            )
+
+        self.assertEqual(reasons, [])
+        self.assertIn("gitea.prgs.cc", resolved_hosts)
+        self.assertNotIn("prgs", resolved_hosts)
+
+    def test_acquire_reviewer_pr_lease_resolves_identity_with_host(self):
+        """Acquire path must not pass a remote alias into identity lookup."""
+        import mcp_server
+
+        resolved_hosts = []
+        posted = []
+
+        def tracking_username(host):
+            resolved_hosts.append(host)
+            return None if host in {"prgs", "dadeschools"} else "reviewer-bot"
+
+        def mock_api(method, url, auth, data=None):
+            if "/pulls/" in url:
+                return {
+                    "user": {"login": "author-user"},
+                    "state": "open",
+                    "head": {"sha": "abc123"},
+                    "mergeable": True,
+                }
+            if "/comments" in url:
+                if method == "POST":
+                    posted.append(data["body"])
+                    return {"id": 1003}
+                return []
+            return {}
+
+        with patch("mcp_server.api_request", side_effect=mock_api), patch(
+            "mcp_server._authenticated_username",
+            side_effect=tracking_username,
+        ), patch(
+            "mcp_server._resolve",
+            return_value=("gitea.prgs.cc", "Scaled-Tech-Consulting", "Gitea-Tools"),
+        ):
+            res = mcp_server.gitea_acquire_reviewer_pr_lease(
+                pr_number=550,
+                worktree="/workspace",
+                candidate_head="abc123",
+                remote="prgs",
+            )
+
+        self.assertTrue(res.get("success"), res)
+        self.assertTrue(res.get("acquired"), res)
+        self.assertEqual(res.get("comment_id"), 1003)
+        self.assertTrue(posted)
+        self.assertIn("gitea.prgs.cc", resolved_hosts)
+        self.assertNotIn("prgs", resolved_hosts)
+
+    def test_adopt_merger_pr_lease_resolves_identity_with_host(self):
+        """Adopt path must not pass a remote alias into identity lookup."""
+        import mcp_server
+        import reviewer_pr_lease
+
+        reviewer_pr_lease.clear_session_lease()
+        head = "a" * 40
+        resolved_hosts = []
+        posted = []
+        reviewer_comment = _reviewer_lease_comment(
+            550,
+            session_id="reviewer-session",
+            head_sha=head,
+            reviewer="reviewer-bot",
+        )
+
+        def tracking_username(host):
+            resolved_hosts.append(host)
+            return None if host in {"prgs", "dadeschools"} else "merger-bot"
+
+        def mock_api(method, url, auth, data=None):
+            if "/pulls/" in url and "/comments" not in url:
+                return {
+                    "number": 550,
+                    "user": {"login": "author-user"},
+                    "state": "open",
+                    "head": {"sha": head},
+                    "mergeable": True,
+                    "merged": False,
+                }
+            if "/comments" in url:
+                if method == "POST":
+                    posted.append(data["body"])
+                    return {"id": 1004}
+                return [reviewer_comment]
+            return {}
+
+        merger_profile = {
+            "profile_name": "prgs-merger",
+            "allowed_operations": ["gitea.read", "gitea.pr.comment", "gitea.pr.merge"],
+            "forbidden_operations": [],
+        }
+        with patch("mcp_server.get_profile", return_value=merger_profile), patch(
+            "mcp_server.api_request",
+            side_effect=mock_api,
+        ), patch(
+            "mcp_server._authenticated_username",
+            side_effect=tracking_username,
+        ), patch(
+            "mcp_server._resolve",
+            return_value=("gitea.prgs.cc", "Scaled-Tech-Consulting", "Gitea-Tools"),
+        ), patch(
+            "mcp_server.gitea_get_pr_review_feedback",
+            return_value={
+                "approval_at_current_head": True,
+                "latest_approved_head_sha": head,
+            },
+        ):
+            res = mcp_server.gitea_adopt_merger_pr_lease(
+                pr_number=550,
+                worktree="/workspace",
+                expected_head_sha=head,
+                remote="prgs",
+            )
+
+        self.assertTrue(res.get("success"), res)
+        self.assertTrue(res.get("adopted"), res)
+        self.assertEqual(res.get("adoption_comment_id"), 1004)
+        self.assertTrue(posted)
+        self.assertIn("gitea.prgs.cc", resolved_hosts)
+        self.assertNotIn("prgs", resolved_hosts)
+
+    def test_release_reviewer_pr_lease_same_identity_cross_session(self):
+        """Same reviewer identity may release a lease claimed by another session.
+
+        Regression: release used to call ``_authenticated_username(remote)``
+        with the remote alias (e.g. ``prgs``) instead of the resolved host,
+        so identity resolved empty and same-identity release fail-closed even
+        when the authenticated user owned the lease.
+        """
+        import mcp_server
+        import reviewer_pr_lease
+
+        mcp_server.gitea_resolve_task_capability(task="review_pr", remote="prgs")
+        mcp_server.gitea_load_review_workflow()
+        reviewer_pr_lease.clear_session_lease()
+
+        foreign_session = "46820-dd78cdc4aacc"
+        comments = [
+            _reviewer_lease_comment(
+                457,
+                session_id=foreign_session,
+                head_sha="ef287eaf5841d9e542a4e888ce0ae7d679dbd685",
+                reviewer="sysadmin",
+            )
+        ]
+        posted = []
+        resolved_hosts = []
+
+        def mock_api(method, url, auth, data=None):
+            if "/api/v1/user" in url:
+                return {"login": "sysadmin"}
+            if "/comments" in url:
+                if method == "POST":
+                    new_c = {
+                        "id": 8071,
+                        "body": data["body"],
+                        "user": {"login": "sysadmin"},
+                    }
+                    comments.append(new_c)
+                    posted.append(new_c)
+                    return {"id": 8071}
+                return comments
+            if "/pulls/" in url:
+                return {
+                    "user": {"login": "jcwalker3"},
+                    "state": "open",
+                    "head": {"sha": "ef287eaf5841d9e542a4e888ce0ae7d679dbd685"},
+                    "mergeable": False,
+                }
+            return {}
+
+        def tracking_username(host):
+            resolved_hosts.append(host)
+            # Empty identity when passed a remote alias (the pre-fix bug path).
+            if host in {"prgs", "dadeschools"}:
+                return None
+            return "sysadmin"
+
+        with patch("mcp_server.api_request", side_effect=mock_api), patch(
+            "mcp_server._authenticated_username", side_effect=tracking_username
+        ), patch(
+            "mcp_server._resolve",
+            return_value=("gitea.prgs.cc", "Scaled-Tech-Consulting", "Gitea-Tools"),
+        ), patch("mcp_server._auth", return_value={"Authorization": "token x"}), patch(
+            "mcp_server._verify_role_mutation_workspace", return_value=None
+        ):
+            res = mcp_server.gitea_release_reviewer_pr_lease(
+                pr_number=457, remote="prgs"
+            )
+
+        self.assertTrue(res.get("success"), res)
+        self.assertTrue(res.get("released"), res)
+        self.assertEqual(res.get("comment_id"), 8071)
+        self.assertTrue(posted)
+        self.assertIn("phase: released", posted[0]["body"])
+        # Must resolve identity with host, never the remote alias alone.
+        self.assertIn("gitea.prgs.cc", resolved_hosts)
+        self.assertNotIn("prgs", resolved_hosts)

tests/test_mcp_stale_runtime.py

@@ -67,5 +67,66 @@ class TestMcpStaleRuntime(unittest.TestCase):
         # But does NOT contain missing author profile error
         self.assertFalse(any("None of the matching profiles for task" in r for r in reasons_author))
 
+    @patch("subprocess.run")
+    @patch("os.path.getmtime")
+    @patch("os.path.exists")
+    @patch("os.getpid")
+    @patch.dict("os.environ", {"GITEA_FORCE_MCP_RUNTIME_CHECK": "1"})
+    def test_git_head_change_triggers_staleness(self, mock_getpid, mock_exists, mock_getmtime, mock_run):
+        # Set boot SHA to FAKE1 and current to FAKE2
+        gitea_mcp_server._process_boot_head_sha = "FAKE1"
+        mock_getpid.return_value = 12345
+        mock_exists.return_value = True
+
+        # Code time is in the past (fresh process chronologically)
+        code_time = datetime(2026, 7, 8, 11, 0, 0)
+        mock_getmtime.return_value = code_time.timestamp()
+
+        ps_output = (
+            "  PID LSTART COMMAND\n"
+            "12345 Wed Jul  8 12:00:00 2026 /path/to/python mcp_server.py\n"
+        )
+
+        mock_run_ps = MagicMock()
+        mock_run_ps.stdout = ps_output
+
+        mock_run_env = MagicMock()
+        mock_run_env.stdout = "GITEA_MCP_PROFILE=prgs-author"
+
+        mock_run_git = MagicMock()
+        mock_run_git.stdout = "FAKE2" # different SHA
+
+        def side_effect(args, **kwargs):
+            if args[0] == "ps" and "eww" in args:
+                return mock_run_env
+            elif args[0] == "ps":
+                return mock_run_ps
+            elif args[0] == "git" and "rev-parse" in args:
+                return mock_run_git
+            raise ValueError(f"Unexpected: {args}")
+
+        mock_run.side_effect = side_effect
+
+        # Stale even though process started AFTER code mtime, because git HEAD changed
+        reasons = gitea_mcp_server._check_mcp_runtimes_diagnostics("create_issue", ["prgs-author"])
+        self.assertTrue(any("stale-runtime: The active Gitea MCP server process is stale" in r for r in reasons))
+
+    @patch("threading.Thread")
+    @patch("os.utime")
+    @patch("os.path.exists")
+    @patch.dict("os.environ", {"MCP_CONFIG_PATH": "/tmp/mcp_config.json"})
+    def test_auto_restart_trigger_touches_and_spawns(self, mock_exists, mock_utime, mock_thread):
+        mock_exists.return_value = True
+        gitea_mcp_server._restart_triggered = False
+
+        # Ensure we are not skipped in test mode for testing purposes
+        with patch("gitea_mcp_server._preflight_in_test_mode", return_value=False):
+            gitea_mcp_server._trigger_mcp_auto_restart()
+
+        mock_utime.assert_called_once_with("/tmp/mcp_config.json", None)
+        mock_thread.assert_called_once()
+        self.assertTrue(gitea_mcp_server._restart_triggered)
+
+
 if __name__ == "__main__":
     unittest.main()

tests/test_merged_cleanup_reconcile.py

@@ -4,7 +4,7 @@ import os
 import sys
 import tempfile
 import unittest
-from unittest.mock import patch, MagicMock
+from unittest.mock import MagicMock, Mock, patch
 
 sys.path.insert(0, str(__import__("pathlib").Path(__file__).resolve().parent.parent))
 
@@ -163,7 +163,7 @@ class TestMergedCleanupReport(unittest.TestCase):
             "branch refs/heads/feat/issue-11-x\n"
             "HEAD cafebabe\n\n"
         )
-        mock_run.return_value = MagicMock(returncode=0, stdout=mock_output)
+        mock_run.return_value = Mock(returncode=0, stdout=mock_output)
         res = mcr.discover_local_worktrees("/repo/Gitea-Tools")
         self.assertEqual(res, {"feat/issue-11-x": "/repo/Gitea-Tools/branches/custom-name"})
 
@@ -177,14 +177,23 @@ class TestMergedCleanupReport(unittest.TestCase):
             "branch refs/heads/feat/issue-11-x\n"
             "HEAD cafebabe\n\n"
         )
-        mock_run.return_value = MagicMock(returncode=0, stdout=mock_output)
-        mock_state.return_value = {
-            "exists": True,
-            "clean": True,
-            "current_branch": "feat/issue-11-x",
-            "head_sha": "cafebabe",
-            "dirty_files": [],
-        }
+        mock_run.return_value = Mock(returncode=0, stdout=mock_output)
+        mock_state.side_effect = [
+            {
+                "exists": False,
+                "clean": None,
+                "current_branch": None,
+                "head_sha": None,
+                "dirty_files": [],
+            },
+            {
+                "exists": True,
+                "clean": True,
+                "current_branch": "feat/issue-11-x",
+                "head_sha": "cafebabe",
+                "dirty_files": [],
+            },
+        ]
 
         report = mcr.build_reconciliation_report(
             project_root="/repo/Gitea-Tools",
@@ -209,29 +218,190 @@ class TestMergedCleanupReport(unittest.TestCase):
         self.assertEqual(local["worktree_path"], "/repo/Gitea-Tools/branches/custom-name")
         self.assertEqual(local["match_type"], "branch")
 
+    @patch("merged_cleanup_reconcile.read_local_worktree_state")
     @patch("subprocess.run")
-    def test_remove_local_worktree_uses_discovered_path(self, mock_run):
-        mock_output = (
-            "worktree /repo/Gitea-Tools\n"
-            "bare\n\n"
-            "worktree /repo/Gitea-Tools/branches/custom-name\n"
-            "branch refs/heads/feat/issue-11-x\n"
-            "HEAD cafebabe\n\n"
+    def test_build_report_discovers_issue_alias_worktree(self, mock_run, mock_state):
+        mock_run.return_value = Mock(
+            returncode=0,
+            stdout=(
+                "worktree /repo/Gitea-Tools\n"
+                "HEAD aaaa\n"
+                "branch refs/heads/master\n\n"
+                "worktree /repo/Gitea-Tools/branches/issue-510-workspace-binding-isolation\n"
+                "HEAD cafebabe\n"
+                "branch refs/heads/feat/issue-510-workspace-binding-isolation\n\n"
+            ),
         )
-        # First call is discover_local_worktrees, second is git worktree remove
-        mock_run.side_effect = [
-            MagicMock(returncode=0, stdout=mock_output),
-            MagicMock(returncode=0, stdout="", stderr=""),
+        mock_state.side_effect = [
+            {
+                "exists": False,
+                "clean": None,
+                "current_branch": None,
+                "head_sha": None,
+                "dirty_files": [],
+            },
+            {
+                "exists": True,
+                "clean": True,
+                "current_branch": "feat/issue-510-workspace-binding-isolation",
+                "head_sha": "cafebabe",
+                "dirty_files": [],
+            },
         ]
 
-        with patch("os.path.isdir", return_value=True):
-            result = mcr.remove_local_worktree("/repo/Gitea-Tools", "feat/issue-11-x")
+        report = mcr.build_reconciliation_report(
+            project_root="/repo/Gitea-Tools",
+            closed_prs=[
+                {
+                    "number": 512,
+                    "title": "merged cleanup",
+                    "body": "Closes #510",
+                    "head": {
+                        "ref": "feat/issue-510-workspace-binding-isolation",
+                        "sha": "cafebabe",
+                    },
+                    "merged_at": "2026-07-06T12:00:00Z",
+                    "merge_commit_sha": "abc123",
+                }
+            ],
+            open_prs=[],
+            remote_branch_exists={"feat/issue-510-workspace-binding-isolation": True},
+            head_on_master={512: True},
+            delete_capability_allowed=True,
+            target_ref="prgs/master",
+        )
+
+        local = report["entries"][0]["local_worktree"]
+        self.assertTrue(local["safe_to_remove_worktree"])
+        self.assertEqual(local["match_type"], "branch")
+        self.assertEqual(
+            local["expected_worktree_path"],
+            "/repo/Gitea-Tools/branches/feat-issue-510-workspace-binding-isolation",
+        )
+        self.assertEqual(
+            local["discovered_worktree_path"],
+            "/repo/Gitea-Tools/branches/issue-510-workspace-binding-isolation",
+        )
+
+    @patch("merged_cleanup_reconcile.read_local_worktree_state")
+    @patch("subprocess.run")
+    def test_ambiguous_issue_alias_worktrees_fail_closed(self, mock_run, mock_state):
+        mock_run.return_value = Mock(
+            returncode=0,
+            stdout=(
+                "worktree /repo/Gitea-Tools/branches/issue-510-one\n"
+                "HEAD cafebabe\n"
+                "branch refs/heads/feat/issue-510-workspace-binding-isolation\n\n"
+                "worktree /repo/Gitea-Tools/branches/issue-510-two\n"
+                "HEAD cafebabe\n"
+                "branch refs/heads/feat/issue-510-workspace-binding-isolation\n\n"
+            ),
+        )
+        mock_state.return_value = {
+            "exists": False,
+            "clean": None,
+            "current_branch": None,
+            "head_sha": None,
+            "dirty_files": [],
+        }
+
+        report = mcr.build_reconciliation_report(
+            project_root="/repo/Gitea-Tools",
+            closed_prs=[
+                {
+                    "number": 512,
+                    "title": "merged cleanup",
+                    "body": "Closes #510",
+                    "head": {
+                        "ref": "feat/issue-510-workspace-binding-isolation",
+                        "sha": "cafebabe",
+                    },
+                    "merged_at": "2026-07-06T12:00:00Z",
+                    "merge_commit_sha": "abc123",
+                }
+            ],
+            open_prs=[],
+            remote_branch_exists={"feat/issue-510-workspace-binding-isolation": True},
+            head_on_master={512: True},
+            delete_capability_allowed=True,
+            target_ref="prgs/master",
+        )
+
+        local = report["entries"][0]["local_worktree"]
+        self.assertFalse(local["safe_to_remove_worktree"])
+        self.assertEqual(local["match_type"], "ambiguous_alias")
+        self.assertIn("ambiguous local worktree aliases", local["block_reasons"][0])
+
+    @patch("merged_cleanup_reconcile.is_head_ancestor_of_ref", return_value=True)
+    @patch("merged_cleanup_reconcile.read_local_worktree_state")
+    @patch("subprocess.run")
+    def test_alias_head_on_target_branch_is_safe_cleanup_commit(
+        self, mock_run, mock_state, _ancestor
+    ):
+        mock_run.return_value = Mock(
+            returncode=0,
+            stdout=(
+                "worktree /repo/Gitea-Tools/branches/issue-510-workspace-binding-isolation\n"
+                "HEAD deadbeef\n"
+                "branch refs/heads/feat/issue-510-workspace-binding-isolation\n\n"
+            ),
+        )
+        mock_state.side_effect = [
+            {
+                "exists": False,
+                "clean": None,
+                "current_branch": None,
+                "head_sha": None,
+                "dirty_files": [],
+            },
+            {
+                "exists": True,
+                "clean": True,
+                "current_branch": "feat/issue-510-workspace-binding-isolation",
+                "head_sha": "deadbeef",
+                "dirty_files": [],
+            },
+        ]
+
+        state = mcr.resolve_cleanup_worktree_state(
+            project_root="/repo/Gitea-Tools",
+            head_branch="feat/issue-510-workspace-binding-isolation",
+            issue_number=510,
+            pr_head_sha="cafebabe",
+            target_ref="prgs/master",
+        )
+
+        self.assertTrue(state["exists"])
+        self.assertEqual(state["match_type"], "branch")
+        self.assertEqual(
+            state["discovered_worktree_path"],
+            "/repo/Gitea-Tools/branches/issue-510-workspace-binding-isolation",
+        )
+
+    @patch("os.path.isdir", return_value=True)
+    @patch("subprocess.run")
+    def test_remove_local_worktree_uses_assessed_path(self, mock_run, _isdir):
+        mock_run.return_value = Mock(returncode=0, stdout="", stderr="")
+        result = mcr.remove_local_worktree(
+            "/repo/Gitea-Tools",
+            "feat/issue-510-workspace-binding-isolation",
+            worktree_path="/repo/Gitea-Tools/branches/issue-510-workspace-binding-isolation",
+        )
+
         self.assertTrue(result["success"])
-        self.assertTrue(result["performed"])
-        self.assertEqual(result["worktree_path"], "/repo/Gitea-Tools/branches/custom-name")
-        # Assert git worktree remove was called with the custom path
-        mock_run.assert_any_call(
-            ["git", "-C", "/repo/Gitea-Tools", "worktree", "remove", "/repo/Gitea-Tools/branches/custom-name"],
+        self.assertEqual(
+            result["worktree_path"],
+            "/repo/Gitea-Tools/branches/issue-510-workspace-binding-isolation",
+        )
+        mock_run.assert_called_once_with(
+            [
+                "git",
+                "-C",
+                "/repo/Gitea-Tools",
+                "worktree",
+                "remove",
+                "/repo/Gitea-Tools/branches/issue-510-workspace-binding-isolation",
+            ],
             capture_output=True,
             text=True,
             check=False,
@@ -440,4 +610,4 @@ class TestReviewerScratchCleanup(unittest.TestCase):
 
 
 if __name__ == "__main__":
-    unittest.main()
+    unittest.main()