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

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")),
+    )

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/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.

master_parity_gate.py

@@ -24,26 +24,12 @@ from __future__ import annotations
 
 import os
 import subprocess
-import time
-
-# Live-remote head cache: the parity gate runs on every mutation and every
-# runtime-context read, so the ``git ls-remote`` result is cached briefly to
-# avoid a network round-trip per call (#610). Keyed by (root, remote, branch).
-_REMOTE_HEAD_CACHE: dict[tuple[str, str, str], tuple[float, str | None]] = {}
-_REMOTE_HEAD_TTL = 60.0
-
-
-def _clear_remote_head_cache() -> None:
-    """Reset the live-remote head cache (test isolation / forced refresh)."""
-    _REMOTE_HEAD_CACHE.clear()
 
 # Environment escape hatches (ops + tests):
 #   GITEA_MCP_DISABLE_PARITY_GATE  -> disable enforcement entirely (fail open).
 #   GITEA_TEST_CURRENT_HEAD        -> force the "current" HEAD read, for tests.
 ENV_DISABLE = "GITEA_MCP_DISABLE_PARITY_GATE"
 ENV_TEST_CURRENT_HEAD = "GITEA_TEST_CURRENT_HEAD"
-# GITEA_TEST_LIVE_REMOTE_HEAD -> force the live remote master read, for tests.
-ENV_TEST_LIVE_REMOTE_HEAD = "GITEA_TEST_LIVE_REMOTE_HEAD"
 
 
 def read_git_head(root: str) -> str | None:
@@ -72,57 +58,6 @@ def read_git_head(root: str) -> str | None:
     return (res.stdout or "").strip() or None
 
 
-def read_remote_master_head(
-    root: str,
-    remote: str = "origin",
-    branch: str = "master",
-    ttl: float = _REMOTE_HEAD_TTL,
-) -> str | None:
-    """Return the live remote ``branch`` commit SHA, or ``None`` (#610).
-
-    Resolves the *live* target commit via ``git ls-remote`` so parity can tell
-    a daemon that is behind the live remote master apart from one whose local
-    checkout simply hasn't been pulled. ``None`` means the live head could not
-    be resolved (offline, no such remote, git unavailable, error) -- callers
-    must treat unknown live state as *not mutation-safe* while never blocking
-    read-only diagnostics. A ``GITEA_TEST_LIVE_REMOTE_HEAD`` override takes
-    precedence so the wiring can be exercised deterministically and offline.
-
-    The result is cached for *ttl* seconds per (root, remote, branch) so the
-    gate does not run a network probe on every mutation/read (``ttl=0`` forces
-    a live probe). Both hits and ``None`` misses are cached to bound offline
-    latency; the env override bypasses the cache and the subprocess entirely.
-    """
-    forced = os.environ.get(ENV_TEST_LIVE_REMOTE_HEAD)
-    if forced is not None:
-        return forced.strip() or None
-    if not root:
-        return None
-    key = (root, remote, branch)
-    now = time.monotonic()
-    if ttl > 0:
-        cached = _REMOTE_HEAD_CACHE.get(key)
-        if cached is not None and (now - cached[0]) < ttl:
-            return cached[1]
-    sha: str | None = None
-    try:
-        res = subprocess.run(
-            ["git", "-C", root, "ls-remote", remote, f"refs/heads/{branch}"],
-            capture_output=True,
-            text=True,
-            check=False,
-            timeout=5,
-        )
-        if res.returncode == 0:
-            lines = (res.stdout or "").strip().splitlines()
-            if lines:
-                sha = lines[0].split("\t", 1)[0].split()[0].strip() or None
-    except Exception:
-        sha = None
-    _REMOTE_HEAD_CACHE[key] = (now, sha)
-    return sha
-
-
 def capture_startup_parity(root: str, head: str | None = None) -> dict:
     """Capture the process source-tree baseline once at server startup.
 
@@ -137,38 +72,18 @@ def _short(sha: str | None) -> str:
     return sha[:12] if sha else "unknown"
 
 
-def assess_master_parity(
+def assess_master_parity(startup: dict | None, current_head: str | None) -> dict:
-    startup: dict | None,
-    current_head: str | None,
-    live_remote_head: str | None = None,
-) -> dict:
     """Compare the startup baseline against the current on-disk ``HEAD``.
 
-    Pure: all HEADs are supplied by the caller. Returns a structured result:
+    Pure: both HEADs are supplied by the caller. Returns a structured result:
 
     - ``in_parity``    -- server code matches the on-disk master (or parity
       could not be determined, which is not treated as stale).
     - ``stale``        -- the on-disk master has definitively advanced past the
       running process.
-    - ``restart_required`` -- ``stale`` or ``live_stale``; the recovery action.
+    - ``restart_required`` -- alias of ``stale``; the recovery action.
-    - ``determinable`` -- whether both local HEADs were known well enough to
+    - ``determinable`` -- whether both HEADs were known well enough to compare.
-      compare.
     - ``startup_head`` / ``current_head`` / ``reasons``.
-
-    #610 adds live-remote awareness so a daemon that is stale relative to the
-    *live* remote master cannot report a mutation-safe result even when the
-    local checkout HEAD still matches the daemon's startup commit:
-
-    - ``daemon_start_head`` -- the commit the running process started at
-      (alias of ``startup_head``, named for clarity in reports).
-    - ``local_head`` -- the on-disk checkout HEAD (alias of ``current_head``).
-    - ``live_remote_head`` -- the live remote target commit, or ``None`` when it
-      could not be fetched.
-    - ``live_known`` -- whether the live remote target was resolved.
-    - ``live_stale`` -- the live remote master has advanced past the running
-      process (daemon is behind live master) even if local parity is green.
-    - ``mutation_safe`` -- the daemon code, local checkout, and live remote
-      target all agree; the only state in which a mutation may rely on parity.
     """
     startup_head = (startup or {}).get("startup_head")
     reasons: list[str] = []
@@ -176,56 +91,32 @@ def assess_master_parity(
     if startup_head is None:
         reasons.append(
             "startup commit was not captured; code parity cannot be enforced")
-        return _result(True, False, False, startup_head, current_head,
+        return _result(True, False, False, startup_head, current_head, reasons)
-                       live_remote_head, False, reasons)
 
     if current_head is None:
         reasons.append(
             "current workspace HEAD could not be read; code parity cannot be "
             "enforced")
-        return _result(True, False, False, startup_head, current_head,
+        return _result(True, False, False, startup_head, current_head, reasons)
-                       live_remote_head, False, reasons)
 
-    local_in_parity = startup_head == current_head
+    if startup_head == current_head:
-    local_stale = not local_in_parity
+        return _result(True, False, True, startup_head, current_head, reasons)
-    if local_stale:
-        reasons.append(
-            f"MCP server started at commit {_short(startup_head)} but the "
-            f"workspace master is now {_short(current_head)}; restart the "
-            f"server to load the current capability gates")
 
-    live_known = live_remote_head is not None
+    reasons.append(
-    live_stale = live_known and live_remote_head != startup_head
+        f"MCP server started at commit {_short(startup_head)} but the workspace "
-    if live_stale:
+        f"master is now {_short(current_head)}; restart the server to load the "
-        reasons.append(
+        f"current capability gates")
-            f"live remote master is {_short(live_remote_head)} but the MCP "
+    return _result(False, True, True, startup_head, current_head, reasons)
-            f"server started at {_short(startup_head)}; the daemon is stale "
-            f"relative to live master -- restart/reconnect before mutating")
-
-    return _result(
-        local_in_parity, local_stale, True, startup_head, current_head,
-        live_remote_head, live_stale, reasons)
 
 
-def _result(in_parity, stale, determinable, startup_head, current_head,
+def _result(in_parity, stale, determinable, startup_head, current_head, reasons):
-            live_remote_head, live_stale, reasons):
-    live_known = live_remote_head is not None
-    mutation_safe = (
-        determinable and in_parity and live_known and not live_stale)
     return {
         "in_parity": in_parity,
         "stale": stale,
-        "restart_required": stale or live_stale,
+        "restart_required": stale,
         "determinable": determinable,
         "startup_head": startup_head,
         "current_head": current_head,
-        # #610 distinguished signals:
-        "daemon_start_head": startup_head,
-        "local_head": current_head,
-        "live_remote_head": live_remote_head,
-        "live_known": live_known,
-        "live_stale": live_stale,
-        "mutation_safe": mutation_safe,
         "reasons": list(reasons),
     }
 
@@ -239,13 +130,11 @@ def parity_block_reasons(assessment: dict) -> list[str]:
     """Block reasons for a mutation gate (empty when the mutation may proceed).
 
     A disabled gate or an in-parity / non-determinable assessment yields no
-    reasons. A definitively stale server blocks, and (#610) a daemon that is
+    reasons; only a definitively stale server blocks.
-    stale relative to the *live* remote master blocks even when the local
-    checkout HEAD still matches the daemon's startup commit.
     """
     if gate_disabled():
         return []
-    if assessment.get("stale") or assessment.get("live_stale"):
+    if assessment.get("stale"):
         return list(assessment.get("reasons") or
                     ["server code is stale relative to master (fail closed)"])
     return []
@@ -258,10 +147,6 @@ def parity_report(assessment: dict) -> dict:
         "restart_required": True,
         "startup_head": assessment.get("startup_head"),
         "current_head": assessment.get("current_head"),
-        # #610: name the live remote target so the report distinguishes a
-        # local-code stale from a daemon-behind-live-master stale.
-        "live_remote_head": assessment.get("live_remote_head"),
-        "live_stale": bool(assessment.get("live_stale")),
         "reasons": list(assessment.get("reasons") or []),
         "recovery": [
             "The running MCP server is executing code older than the current "
@@ -272,45 +157,6 @@ def parity_report(assessment: dict) -> dict:
     }
 
 
-def parity_resolver_disagreement(
-    assessment: dict,
-    resolver_restart_required: bool,
-) -> dict | None:
-    """Typed blocker when the resolver requires restart but parity looks green.
-
-    The capability resolver (``gitea_resolve_task_capability``) detects stale
-    runtime authoritatively for mutation safety (#610). When it requires a
-    restart, local-only parity must never override it: this returns a typed,
-    fail-closed blocker that names the resolver as authoritative. Returns
-    ``None`` when the resolver does not require a restart.
-    """
-    if not resolver_restart_required:
-        return None
-    parity_optimistic = bool(assessment.get("in_parity")) and not (
-        assessment.get("stale") or assessment.get("live_stale"))
-    return {
-        "kind": "parity_resolver_disagreement",
-        "restart_required": True,
-        "resolver_authoritative": True,
-        "parity_optimistic": parity_optimistic,
-        "daemon_start_head": assessment.get("daemon_start_head"),
-        "local_head": assessment.get("local_head"),
-        "live_remote_head": assessment.get("live_remote_head"),
-        "reasons": [
-            "The capability resolver requires a restart/reconnect (stale "
-            "runtime) but master-parity reported local code as in-parity. "
-            "The resolver is authoritative for mutation safety; do not mutate "
-            "on local parity alone. Restart/reconnect the Gitea MCP server "
-            "and re-verify before mutating.",
-        ],
-        "recovery": [
-            "Trust the resolver: treat this session as stale.",
-            "Restart or /mcp reconnect the Gitea MCP namespace so it reloads "
-            "current master and live target state, then re-run preflight.",
-        ],
-    }
-
-
 def format_parity(assessment: dict) -> str:
     """One-line human summary for logs / runtime context."""
     if assessment.get("stale"):

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,

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"

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,
+    **blocker_kwargs,
-    capability_blocked: bool = False,
 ) -> 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(
+    blockers = assess_workflow_blockers(**blocker_kwargs)
-        infra_stop=infra_stop,
-        capability_blocked=capability_blocked,
-    )
     reasons = list(blockers["reasons"])
 
     try:

stale_review_decision_lock.py

@@ -1,4 +1,4 @@
-"""Stale / moot #332 review-decision lock detection and cleanup policy (#594).
+"""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
@@ -6,6 +6,12 @@ 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.
@@ -23,6 +29,45 @@ from typing import Any
 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:
@@ -35,18 +80,125 @@ def last_terminal_mutation(lock: dict | None) -> dict | None:
     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,
     }
 
 
@@ -56,6 +208,7 @@ def lock_summary(lock: dict | None) -> dict[str, Any] | 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"),
@@ -67,16 +220,21 @@ def lock_summary(lock: dict | None) -> dict[str, Any] | None:
         "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"),
     }
@@ -88,13 +246,16 @@ def assess_stale_review_decision_lock(
     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).
+    """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 and #332 hard-stop remains in force.
+    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] = {
@@ -102,6 +263,10 @@ def assess_stale_review_decision_lock(
         "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,
@@ -141,8 +306,10 @@ def assess_stale_review_decision_lock(
 
     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(
@@ -165,25 +332,46 @@ def assess_stale_review_decision_lock(
         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"]:
-        result["reasons"].append(
+        stale_by_head = bool(
-            f"terminal review mutation on open PR #{pr_number} is still active "
+            locked_head and current_head and not heads_equal(locked_head, current_head)
-            f"({action}); #332 hard-stop remains — cleanup forbidden (#594)"
         )
+        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)"

task_capability_map.py

@@ -139,6 +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",

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,
+Spawns a *separate* MCP server process from config via subprocess.Popen,
-performs the JSON-RPC handshake, and queries the tools list to verify
+performs the JSON-RPC handshake, verifies the required tool is registered,
-that the connection is fully operational and doesn't return EOF.
+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 run_connection_test(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 run_connection_test(name, config):
             bufsize=1,
             env=run_env
         )
-    except Exception as e:
+    except Exception as exc:
-        print(f"  [FAIL] Failed to spawn process: {e}")
+        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 run_connection_test(name, config):
     }
     
     try:
-        proc.stdin.write(json.dumps(init_req) + "\n")
+        _write_message(proc, init_req)
-        proc.stdin.flush()
         
         # Read response
-        line = proc.stdout.readline()
+        res, stderr_content = _read_json_line(proc)
-        if not line:
+        if res is None:
-            stderr_content = proc.stderr.read()
             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")
+        _write_message(proc, init_notif)
-        proc.stdin.flush()
         
         # Send tools/list request
         list_req = {
@@ -76,16 +120,27 @@ def run_connection_test(name, config):
             "params": {},
             "id": 2
         }
-        proc.stdin.write(json.dumps(list_req) + "\n")
+        _write_message(proc, list_req)
-        proc.stdin.flush()
         
-        line = proc.stdout.readline()
+        res, stderr_content = _read_json_line(proc)
-        if not line:
+        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 run_connection_test(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:
+    except Exception as exc:
-        print(f"  [FAIL] Error during handshake: {e}")
+        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 run_connection_test(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

@@ -66,6 +66,7 @@ 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)

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_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_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_master_parity_gate.py

@@ -78,95 +78,6 @@ class TestBlockReasonsAndReport(unittest.TestCase):
         self.assertTrue(report["recovery"])
 
 
-class TestLiveRemoteParity(unittest.TestCase):
-    """#610: parity must account for the live remote master, not just local.
-
-    The daemon can be stale relative to the live remote target while the local
-    checkout HEAD still matches the daemon's startup commit, so local parity
-    reports green even though a mutation would run against outdated code.
-    """
-
-    SHA_C = "c" * 40
-
-    def test_distinguishes_three_shas(self):
-        res = mp.assess_master_parity(
-            {"startup_head": SHA_A}, SHA_A, live_remote_head=SHA_B)
-        self.assertEqual(res["daemon_start_head"], SHA_A)
-        self.assertEqual(res["local_head"], SHA_A)
-        self.assertEqual(res["live_remote_head"], SHA_B)
-
-    def test_mutation_safe_only_when_all_three_match(self):
-        res = mp.assess_master_parity(
-            {"startup_head": SHA_A}, SHA_A, live_remote_head=SHA_A)
-        self.assertTrue(res["mutation_safe"])
-        self.assertTrue(res["live_known"])
-        self.assertFalse(res["live_stale"])
-
-    def test_live_stale_when_remote_advanced_past_daemon(self):
-        # Local checkout still matches the daemon start (local parity green),
-        # but the live remote master has advanced -> daemon is live-stale.
-        res = mp.assess_master_parity(
-            {"startup_head": SHA_A}, SHA_A, live_remote_head=SHA_B)
-        self.assertTrue(res["in_parity"])  # local parity still green
-        self.assertTrue(res["live_stale"])
-        self.assertFalse(res["mutation_safe"])
-        self.assertTrue(any("live" in r.lower() for r in res["reasons"]))
-
-    def test_live_unknown_is_not_mutation_safe_but_not_stale(self):
-        # Non-goal: unfetchable live remote must not be treated as stale for
-        # read-only, but a mutation-safe claim fails closed.
-        res = mp.assess_master_parity(
-            {"startup_head": SHA_A}, SHA_A, live_remote_head=None)
-        self.assertFalse(res["live_known"])
-        self.assertFalse(res["mutation_safe"])
-        self.assertFalse(res["live_stale"])
-        self.assertTrue(res["in_parity"])
-
-    def test_default_live_remote_preserves_legacy_shape(self):
-        # Callers that do not supply a live head keep the pre-#610 behavior:
-        # in-parity, not live-stale, no live-derived block.
-        res = mp.assess_master_parity({"startup_head": SHA_A}, SHA_A)
-        self.assertFalse(res["live_stale"])
-        self.assertEqual(mp.parity_block_reasons(res), [])
-
-
-class TestLiveStaleBlockAndReport(unittest.TestCase):
-    """#610: live-staleness must block mutations and surface a typed blocker."""
-
-    def test_live_stale_produces_block_reasons(self):
-        res = mp.assess_master_parity(
-            {"startup_head": SHA_A}, SHA_A, live_remote_head=SHA_B)
-        self.assertTrue(mp.parity_block_reasons(res))
-
-    def test_disable_env_suppresses_live_stale_block(self):
-        res = mp.assess_master_parity(
-            {"startup_head": SHA_A}, SHA_A, live_remote_head=SHA_B)
-        with patch.dict(os.environ, {mp.ENV_DISABLE: "1"}):
-            self.assertEqual(mp.parity_block_reasons(res), [])
-
-    def test_resolver_disagreement_returns_typed_blocker(self):
-        # Parity says local-green, resolver says restart required -> disagreement
-        # is a typed, fail-closed blocker naming the resolver as authoritative.
-        res = mp.assess_master_parity({"startup_head": SHA_A}, SHA_A)
-        blocker = mp.parity_resolver_disagreement(res, resolver_restart_required=True)
-        self.assertIsNotNone(blocker)
-        self.assertEqual(blocker["kind"], "parity_resolver_disagreement")
-        self.assertTrue(blocker["restart_required"])
-        self.assertTrue(blocker["resolver_authoritative"])
-
-    def test_no_disagreement_when_resolver_agrees(self):
-        res = mp.assess_master_parity({"startup_head": SHA_A}, SHA_A)
-        self.assertIsNone(
-            mp.parity_resolver_disagreement(res, resolver_restart_required=False))
-
-    def test_live_stale_report_names_live_remote(self):
-        res = mp.assess_master_parity(
-            {"startup_head": SHA_A}, SHA_A, live_remote_head=SHA_B)
-        report = mp.parity_report(res)
-        self.assertEqual(report["live_remote_head"], SHA_B)
-        self.assertTrue(report["restart_required"])
-
-
 class TestReadGitHead(unittest.TestCase):
     def test_test_override_takes_precedence(self):
         with patch.dict(os.environ, {mp.ENV_TEST_CURRENT_HEAD: SHA_B}):
@@ -184,78 +95,6 @@ class TestReadGitHead(unittest.TestCase):
             self.assertIsNone(mp.read_git_head(""))
 
 
-class TestReadRemoteMasterHead(unittest.TestCase):
-    """#610: live remote master head reader (env-overridable, fails to None)."""
-
-    def test_test_override_takes_precedence(self):
-        with patch.dict(os.environ, {mp.ENV_TEST_LIVE_REMOTE_HEAD: SHA_B}):
-            self.assertEqual(mp.read_remote_master_head("/nonexistent"), SHA_B)
-
-    def test_blank_override_is_none(self):
-        with patch.dict(os.environ, {mp.ENV_TEST_LIVE_REMOTE_HEAD: "   "}):
-            self.assertIsNone(mp.read_remote_master_head("/nonexistent"))
-
-    def test_unfetchable_remote_is_none(self):
-        # No override; a bogus root/remote must fail closed to None, never raise.
-        env = {k: v for k, v in os.environ.items()
-               if k != mp.ENV_TEST_LIVE_REMOTE_HEAD}
-        with patch.dict(os.environ, env, clear=True):
-            self.assertIsNone(
-                mp.read_remote_master_head("/nonexistent", remote="nope"))
-
-
-class TestRemoteHeadCache(unittest.TestCase):
-    """#610: live remote reads are cached with a TTL to stay off the network.
-
-    The parity gate runs on every mutation and every runtime-context read, so an
-    unbounded ``git ls-remote`` per call would be a latency/flakiness regression.
-    """
-
-    def setUp(self):
-        mp._clear_remote_head_cache()
-        env = {k: v for k, v in os.environ.items()
-               if k != mp.ENV_TEST_LIVE_REMOTE_HEAD}
-        self._env = patch.dict(os.environ, env, clear=True)
-        self._env.start()
-        self.addCleanup(self._env.stop)
-        self.addCleanup(mp._clear_remote_head_cache)
-
-    def _fake_run(self, sha):
-        class _R:
-            returncode = 0
-            stdout = f"{sha}\trefs/heads/master\n"
-        calls = {"n": 0}
-
-        def run(*args, **kwargs):
-            calls["n"] += 1
-            return _R()
-        return run, calls
-
-    def test_second_call_within_ttl_uses_cache(self):
-        run, calls = self._fake_run(SHA_B)
-        with patch.object(mp.subprocess, "run", run):
-            a = mp.read_remote_master_head("/repo", remote="prgs", ttl=100)
-            b = mp.read_remote_master_head("/repo", remote="prgs", ttl=100)
-        self.assertEqual(a, SHA_B)
-        self.assertEqual(b, SHA_B)
-        self.assertEqual(calls["n"], 1)
-
-    def test_zero_ttl_bypasses_cache(self):
-        run, calls = self._fake_run(SHA_B)
-        with patch.object(mp.subprocess, "run", run):
-            mp.read_remote_master_head("/repo", remote="prgs", ttl=0)
-            mp.read_remote_master_head("/repo", remote="prgs", ttl=0)
-        self.assertEqual(calls["n"], 2)
-
-    def test_env_override_never_touches_subprocess(self):
-        run, calls = self._fake_run(SHA_B)
-        with patch.dict(os.environ, {mp.ENV_TEST_LIVE_REMOTE_HEAD: SHA_A}):
-            with patch.object(mp.subprocess, "run", run):
-                self.assertEqual(
-                    mp.read_remote_master_head("/repo", remote="prgs"), SHA_A)
-        self.assertEqual(calls["n"], 0)
-
-
 class TestServerWiring(unittest.TestCase):
     """Integration with the gate choke point in the server namespace."""
 
@@ -266,13 +105,6 @@ class TestServerWiring(unittest.TestCase):
         self._saved = self.srv._STARTUP_PARITY
         self.srv._STARTUP_PARITY = {"root": self.srv.PROJECT_ROOT,
                                     "startup_head": SHA_A}
-        # Keep the live-remote read hermetic (no real ls-remote network call):
-        # default the live master to the daemon start so parity is fully green
-        # unless a test overrides the live head explicitly (#610).
-        self._live_patch = patch.dict(
-            os.environ, {mp.ENV_TEST_LIVE_REMOTE_HEAD: SHA_A})
-        self._live_patch.start()
-        self.addCleanup(self._live_patch.stop)
 
     def tearDown(self):
         self.srv._STARTUP_PARITY = self._saved
@@ -315,36 +147,6 @@ class TestServerWiring(unittest.TestCase):
             self.assertTrue(out["in_parity"])
             self.assertNotIn("report", out)
 
-    # --- #610: live-remote wiring -------------------------------------------
-
-    def test_live_stale_blocks_mutation_though_local_green(self):
-        # Local checkout matches the daemon start (local parity green) but the
-        # live remote master has advanced -> mutations must fail closed.
-        with patch.dict(os.environ, {mp.ENV_TEST_CURRENT_HEAD: SHA_A,
-                                     mp.ENV_TEST_LIVE_REMOTE_HEAD: SHA_B}):
-            self.assertEqual(self.srv._master_parity_block("gitea.read"), [])
-            self.assertTrue(
-                self.srv._master_parity_block("gitea.pr.create"))
-
-    def test_assess_tool_exposes_three_distinct_shas(self):
-        with patch.dict(os.environ, {mp.ENV_TEST_CURRENT_HEAD: SHA_A,
-                                     mp.ENV_TEST_LIVE_REMOTE_HEAD: SHA_B}):
-            out = self.srv.gitea_assess_master_parity(remote="prgs")
-            self.assertEqual(out["daemon_start_head"], SHA_A)
-            self.assertEqual(out["local_head"], SHA_A)
-            self.assertEqual(out["live_remote_head"], SHA_B)
-            self.assertTrue(out["live_stale"])
-            self.assertFalse(out["mutation_safe"])
-            self.assertIn("report", out)
-
-    def test_assess_tool_mutation_safe_when_all_three_match(self):
-        with patch.dict(os.environ, {mp.ENV_TEST_CURRENT_HEAD: SHA_A,
-                                     mp.ENV_TEST_LIVE_REMOTE_HEAD: SHA_A}):
-            out = self.srv.gitea_assess_master_parity(remote="prgs")
-            self.assertTrue(out["mutation_safe"])
-            self.assertFalse(out["live_stale"])
-            self.assertNotIn("report", out)
-
 
 if __name__ == "__main__":
     unittest.main()

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_review_drafts.py

@@ -0,0 +1,287 @@
+"""Tests for preserving and resuming prepared Gitea review drafts (#609)."""
+
+from __future__ import annotations
+
+import os
+import sys
+import tempfile
+import unittest
+from pathlib import Path
+from unittest.mock import patch, MagicMock
+
+sys_path_root = str(Path(__file__).resolve().parent.parent)
+if sys_path_root not in sys.path:
+    sys.path.insert(0, sys_path_root)
+
+import mcp_session_state
+import gitea_mcp_server
+import reviewer_pr_lease
+
+
+class TestReviewDrafts(unittest.TestCase):
+    def setUp(self):
+        self._tmpdir = tempfile.TemporaryDirectory()
+        self.state_dir = self._tmpdir.name
+        self._env = patch.dict(
+            os.environ,
+            {
+                mcp_session_state.STATE_DIR_ENV: self.state_dir,
+                mcp_session_state.SESSION_PROFILE_LOCK_ENV: "prgs-reviewer",
+                "GITEA_MCP_PROFILE": "prgs-reviewer",
+                "GITEA_PROFILE_NAME": "prgs-reviewer",
+                "PYTEST_CURRENT_TEST": "1",  # skip runtime stale checks
+            },
+            clear=False,
+        )
+        self._env.start()
+        
+        # Mock workspace binding to pass in test context
+        self._nwb_patch = patch(
+            "gitea_mcp_server.nwb.assess_namespace_mutation_workspace",
+            return_value={"block": False, "mutation_workspace": "/tmp/test-worktree"},
+        )
+        self._nwb_patch.start()
+
+        # Mock authentication headers
+        self._auth_patch = patch(
+            "gitea_mcp_server.get_auth_header",
+            return_value="Bearer mock-token",
+        )
+        self._auth_patch.start()
+
+        self._username_patch = patch(
+            "gitea_mcp_server._authenticated_username",
+            return_value="sysadmin",
+        )
+        self._username_patch.start()
+        
+        # Clear/Mock local session lease in-memory state
+        reviewer_pr_lease.clear_session_lease()
+
+    def tearDown(self):
+        self._username_patch.stop()
+        self._auth_patch.stop()
+        self._nwb_patch.stop()
+        self._env.stop()
+        self._tmpdir.cleanup()
+        reviewer_pr_lease.clear_session_lease()
+
+    @patch("gitea_mcp_server.api_request")
+    def test_save_draft_success(self, mock_api):
+        print("GITEA_MCP_SERVER FILE:", gitea_mcp_server.__file__)
+        print("DIR OF GITEA_MCP_SERVER:", dir(gitea_mcp_server))
+        mock_api.return_value = {
+            "head": {"sha": "headsha1234567890"},
+            "base": {"ref": "master", "sha": "basesha0987654321"},
+        }
+        res = gitea_mcp_server.gitea_save_review_draft(
+            pr_number=587,
+            action="approve",
+            body="Good changes",
+            expected_head_sha="headsha1234567890",
+            validation_commands="pytest tests/",
+            validation_results="all pass",
+            blocker_reason="stale daemon",
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+            worktree_path="/tmp/test-worktree",
+        )
+        self.assertTrue(res.get("success"))
+        self.assertEqual(res.get("head_sha"), "headsha1234567890")
+        
+        # Load draft and verify fields
+        draft = mcp_session_state.load_state(
+            kind=mcp_session_state.KIND_REVIEW_DRAFT,
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+            profile_identity="prgs-reviewer",
+        )
+        self.assertIsNotNone(draft)
+        self.assertEqual(draft.get("pr_number"), 587)
+        self.assertEqual(draft.get("action"), "approve")
+        self.assertEqual(draft.get("body"), "Good changes")
+        self.assertEqual(draft.get("validation_commands"), "pytest tests/")
+        self.assertEqual(draft.get("validation_results"), "all pass")
+        self.assertEqual(draft.get("blocker_reason"), "stale daemon")
+        self.assertEqual(os.path.realpath(draft.get("worktree_path")), os.path.realpath("/tmp/test-worktree"))
+
+    @patch("gitea_mcp_server.api_request")
+    @patch("gitea_mcp_server._fetch_pr_comments")
+    @patch("gitea_mcp_server.gitea_submit_pr_review")
+    def test_resume_draft_and_submit_success(self, mock_submit, mock_comments, mock_api):
+        # 1. Save draft
+        mock_api.return_value = {
+            "state": "open",
+            "head": {"sha": "headsha1234567890"},
+            "base": {"ref": "master", "sha": "basesha0987654321"},
+        }
+        
+        gitea_mcp_server.gitea_save_review_draft(
+            pr_number=587,
+            action="approve",
+            body="Good changes",
+            expected_head_sha="headsha1234567890",
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+            worktree_path="/tmp/test-worktree",
+        )
+        
+        # Seed local session lease
+        reviewer_pr_lease.record_session_lease({
+            "pr_number": 587,
+            "session_id": "session-1234",
+        })
+        
+        # Mock Gitea comments to return active reviewer lease owned by us
+        mock_comments.return_value = [
+            {
+                "id": 1,
+                "user": {"username": "sysadmin"},
+                "body": (
+                    "<!-- mcp-review-lease:v1 -->\n"
+                    "repo: Scaled-Tech-Consulting/Gitea-Tools\n"
+                    "pr: #587\n"
+                    "reviewer_identity: sysadmin\n"
+                    "profile: prgs-reviewer\n"
+                    "session_id: session-1234\n"
+                    "phase: claimed\n"
+                ),
+            }
+        ]
+        
+        mock_submit.return_value = {"performed": True, "success": True}
+        
+        # 2. Resume draft
+        res = gitea_mcp_server.gitea_resume_review_draft(
+            pr_number=587,
+            submit=True,
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+            worktree_path="/tmp/test-worktree",
+        )
+        
+        self.assertTrue(res.get("success"))
+        self.assertTrue(res.get("marked_ready"))
+        self.assertTrue(res.get("submitted"))
+        mock_submit.assert_called_once()
+        
+        # Verify draft was deleted after successful submit
+        draft = mcp_session_state.load_state(
+            kind=mcp_session_state.KIND_REVIEW_DRAFT,
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+            profile_identity="prgs-reviewer",
+        )
+        self.assertIsNone(draft)
+
+    @patch("gitea_mcp_server.api_request")
+    @patch("gitea_mcp_server._fetch_pr_comments")
+    def test_resume_draft_fails_checks(self, mock_comments, mock_api):
+        # Save a draft
+        mock_api.return_value = {
+            "state": "open",
+            "head": {"sha": "headsha1234567890"},
+            "base": {"ref": "master", "sha": "basesha0987654321"},
+        }
+        gitea_mcp_server.gitea_save_review_draft(
+            pr_number=587,
+            action="approve",
+            body="Good changes",
+            expected_head_sha="headsha1234567890",
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+            worktree_path="/tmp/test-worktree",
+        )
+        
+        # Seed local session lease
+        reviewer_pr_lease.record_session_lease({
+            "pr_number": 587,
+            "session_id": "session-1234",
+        })
+        
+        # Mock Gitea comments to return active reviewer lease owned by us
+        mock_comments.return_value = [
+            {
+                "id": 1,
+                "user": {"username": "sysadmin"},
+                "body": (
+                    "<!-- mcp-review-lease:v1 -->\n"
+                    "repo: Scaled-Tech-Consulting/Gitea-Tools\n"
+                    "pr: #587\n"
+                    "reviewer_identity: sysadmin\n"
+                    "profile: prgs-reviewer\n"
+                    "session_id: session-1234\n"
+                    "phase: claimed\n"
+                ),
+            }
+        ]
+        
+        # Case A: PR closed
+        mock_api.return_value = {
+            "state": "closed",
+            "head": {"sha": "headsha1234567890"},
+            "base": {"ref": "master", "sha": "basesha0987654321"},
+        }
+        res = gitea_mcp_server.gitea_resume_review_draft(
+            pr_number=587,
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+            worktree_path="/tmp/test-worktree",
+        )
+        self.assertFalse(res.get("success"))
+        self.assertIn("PR #587 is not open", res.get("reasons")[0])
+        
+        # Case B: Head changed
+        mock_api.return_value = {
+            "state": "open",
+            "head": {"sha": "headsha_NEW"},
+            "base": {"ref": "master", "sha": "basesha0987654321"},
+        }
+        res = gitea_mcp_server.gitea_resume_review_draft(
+            pr_number=587,
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+            worktree_path="/tmp/test-worktree",
+        )
+        self.assertFalse(res.get("success"))
+        self.assertIn("PR head SHA changed", res.get("reasons")[0])
+        
+        # Case C: Target branch changed
+        mock_api.return_value = {
+            "state": "open",
+            "head": {"sha": "headsha1234567890"},
+            "base": {"ref": "master", "sha": "basesha_NEW"},
+        }
+        res = gitea_mcp_server.gitea_resume_review_draft(
+            pr_number=587,
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+            worktree_path="/tmp/test-worktree",
+        )
+        self.assertFalse(res.get("success"))
+        self.assertIn("target branch SHA changed", res.get("reasons")[0])
+        
+        # Case D: Worktree mismatch
+        mock_api.return_value = {
+            "state": "open",
+            "head": {"sha": "headsha1234567890"},
+            "base": {"ref": "master", "sha": "basesha0987654321"},
+        }
+        res = gitea_mcp_server.gitea_resume_review_draft(
+            pr_number=587,
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+            worktree_path="/tmp/different-worktree",
+        )
+        self.assertFalse(res.get("success"))
+        self.assertIn("worktree binding mismatch", res.get("reasons")[0])