feat(pr-sync): native assess and author update-by-merge lifecycle

Prevent approved PRs from stalling when master advances. Add
gitea_assess_pr_sync_status and gitea_update_pr_branch_by_merge with
head/base pinning, author-only updates, conflict handoff, and approval
invalidation after head changes. Wire task capability map, sequential
controller routing in review-merge workflow, and hermetic AC tests.

.env.example

@@ -39,6 +39,27 @@ GITEA_AUDIT_LOG=/path/to/gitea-mcp-audit.log
 # only — never the token value. Surfaced by gitea_get_profile.
 GITEA_TOKEN_SOURCE=GITEA_TOKEN
 
+# ── Optional self-hosted Sentry observability (#606) ────────────────────────
+# Emits runtime errors, fail-closed workflow blockers, lease/terminal-lock/
+# stale-runtime collisions, and watchdog cron check-ins to a SELF-HOSTED Sentry
+# (https://sentry.prgs.cc/) — never Sentry Cloud. Gitea stays the source of
+# truth; Sentry is observe-only. OFF by default: with MCP_SENTRY_ENABLED unset
+# or SENTRY_DSN empty, nothing is initialised and no events are sent.
+#
+# Master gate. Truthy = 1/true/yes/on. Both this AND SENTRY_DSN are required.
+MCP_SENTRY_ENABLED=0
+# DSN for the self-hosted project (create a `gitea-tools-mcp` project in
+# https://sentry.prgs.cc/ and copy its DSN). Never commit a real DSN.
+SENTRY_DSN=
+# Deployment environment tag (local/dev/prod). Defaults to "development".
+SENTRY_ENVIRONMENT=development
+# Optional release identifier (e.g. a git SHA or version string).
+SENTRY_RELEASE=
+# Performance-trace sample rate, 0.0–1.0 (clamped). Default 0.0 (traces off).
+MCP_SENTRY_TRACES_SAMPLE_RATE=0.0
+# Set to 1 to forward Python logs to Sentry as structured logs. Default off.
+MCP_SENTRY_ENABLE_LOGS=0
+
 # Optional canonical runtime-profile config (#19). Instead of the fields above,
 # point every LLM launcher at ONE JSON file of named profiles and select one.
 # Secrets are referenced (keychain id / env var name), never inlined. See

branch_cleanup_guard.py

@@ -7,6 +7,19 @@ from typing import Any
 
 PROTECTED_BRANCHES = frozenset({"master", "main", "dev"})
 
+# Evidence / preservation branches must never be removed by cleanup tools
+# (e.g. chore/issue-681-preserve-review-session-wip).
+_PRESERVATION_MARKERS = ("preserve", "preservation", "evidence")
+
+
+def is_preservation_or_evidence_branch(branch: str | None) -> bool:
+    """Return True when *branch* is a preservation/evidence ref that must stay."""
+    if not branch:
+        return False
+    name = str(branch).lower()
+    return any(marker in name for marker in _PRESERVATION_MARKERS)
+
+
 _RAW_BRANCH_DELETE_PATTERNS = (
     re.compile(r"\bgit(?:\s+-C\s+\S+)?\s+branch\s+-[dD]\b[^\n\r]*", re.I),
     re.compile(r"\bgit(?:\s+-C\s+\S+)?\s+push\b[^\n\r]*\s--delete\b[^\n\r]*", re.I),
@@ -72,6 +85,11 @@ def assess_merged_pr_branch_cleanup(
         reasons.append("PR head branch is missing")
     if head_branch in protected:
         reasons.append(f"branch '{head_branch}' is protected")
+    if is_preservation_or_evidence_branch(head_branch):
+        reasons.append(
+            f"branch '{head_branch}' is a preservation/evidence branch and "
+            "cannot be deleted through merged-PR cleanup"
+        )
     if head_branch in open_pr_heads:
         reasons.append("an open PR still references this head branch")
     if head_on_target is False:
@@ -96,3 +114,490 @@ def assess_merged_pr_branch_cleanup(
         "block_reasons": reasons,
         "recommended_action": "delete_remote_branch" if safe else "keep_remote_branch",
     }
+
+
+# ---------------------------------------------------------------------------
+# #687 remediation: post-delete readback + active ownership protection
+# ---------------------------------------------------------------------------
+
+READBACK_NOT_FOUND = "not_found"
+READBACK_EXISTS = "exists"
+READBACK_AUTHENTICATION = "authentication_error"
+READBACK_AUTHORIZATION = "authorization_error"
+READBACK_TRANSPORT = "transport_error"
+READBACK_UNEXPECTED = "unexpected_response"
+READBACK_AMBIGUOUS_404 = "ambiguous_not_found"
+
+# Scope of a 404: only branch-scoped absence may set verified_absent.
+NOT_FOUND_SCOPE_BRANCH = "branch"
+NOT_FOUND_SCOPE_REPOSITORY = "repository"
+NOT_FOUND_SCOPE_HOST = "host"
+NOT_FOUND_SCOPE_UNKNOWN = "unknown"
+
+ERROR_CLASS_AUTHENTICATION = "authentication"
+ERROR_CLASS_AUTHORIZATION = "authorization"
+ERROR_CLASS_TRANSPORT = "transport"
+ERROR_CLASS_UNEXPECTED = "unexpected"
+
+OWNERSHIP_CATEGORY_AUTHOR_SESSION = "author_session"
+OWNERSHIP_CATEGORY_AUTHOR_LEASE = "author_lease"
+OWNERSHIP_CATEGORY_REVIEWER_LEASE = "reviewer_lease"
+OWNERSHIP_CATEGORY_MERGER_LEASE = "merger_lease"
+OWNERSHIP_CATEGORY_CONTROLLER_LEASE = "controller_lease"
+OWNERSHIP_CATEGORY_RECONCILER_LEASE = "reconciler_lease"
+OWNERSHIP_CATEGORY_WORKTREE_BINDING = "worktree_binding"
+OWNERSHIP_CATEGORY_INVENTORY_ERROR = "ownership_inventory_error"
+
+_ROLE_TO_OWNERSHIP_CATEGORY = {
+    "author": OWNERSHIP_CATEGORY_AUTHOR_LEASE,
+    "reviewer": OWNERSHIP_CATEGORY_REVIEWER_LEASE,
+    "merger": OWNERSHIP_CATEGORY_MERGER_LEASE,
+    "controller": OWNERSHIP_CATEGORY_CONTROLLER_LEASE,
+    "reconciler": OWNERSHIP_CATEGORY_RECONCILER_LEASE,
+}
+
+_ACTIVE_OWNERSHIP_STATUSES = frozenset(
+    {"active", "live", "claimed", "in_progress", "working", "pushing", "pushed"}
+)
+_TERMINAL_OWNERSHIP_STATUSES = frozenset(
+    {"released", "abandoned", "done", "blocked", "terminal", "closed"}
+)
+_EXPIRED_STATUSES = frozenset({"expired"})
+_STALE_STATUSES = frozenset({"stale", "stale_dead_process", "stale_missing_worktree"})
+
+
+def _norm_str(value: Any) -> str:
+    return str(value or "").strip()
+
+
+def normalize_host(host: str | None) -> str:
+    """Normalize a host identity for ownership matching (no credentials)."""
+    text = _norm_str(host).lower()
+    for prefix in ("https://", "http://"):
+        if text.startswith(prefix):
+            text = text[len(prefix) :]
+    # Drop path/query if a full URL slipped through.
+    text = text.split("/", 1)[0]
+    text = text.split("?", 1)[0]
+    return text.rstrip(".")
+
+
+def ownership_category_for_role(role: str | None) -> str:
+    """Map a role kind to a non-secret ownership category label."""
+    key = _norm_str(role).lower()
+    return _ROLE_TO_OWNERSHIP_CATEGORY.get(key, f"{key or 'unknown'}_lease")
+
+
+def classify_branch_readback_http_status(
+    status_code: int | None,
+    *,
+    not_found_scope: str | None = None,
+) -> dict[str, Any]:
+    """Classify a GET-branch HTTP status into a secret-free readback result.
+
+    R1: A bare/generic/repository/wrong-host 404 never yields
+    ``verified_absent=True``. Only an authoritative *branch-scoped* not-found
+    (``not_found_scope='branch'``) may verify deletion.
+    """
+    if status_code == 404:
+        scope = _norm_str(not_found_scope).lower() or NOT_FOUND_SCOPE_UNKNOWN
+        if scope == NOT_FOUND_SCOPE_BRANCH:
+            return {
+                "status": READBACK_NOT_FOUND,
+                "error_class": None,
+                "verified_absent": True,
+                "branch_present": False,
+                "not_found_scope": NOT_FOUND_SCOPE_BRANCH,
+                "reasons": [],
+            }
+        # repository / host / unknown / generic 404 — not verified absence
+        reason = {
+            NOT_FOUND_SCOPE_REPOSITORY: (
+                "post-delete readback 404 is repository-scoped, not branch absence"
+            ),
+            NOT_FOUND_SCOPE_HOST: (
+                "post-delete readback 404 is host-scoped, not branch absence"
+            ),
+        }.get(
+            scope,
+            "post-delete readback 404 is ambiguous (not branch-scoped); "
+            "cannot verify absence",
+        )
+        return {
+            "status": READBACK_AMBIGUOUS_404,
+            "error_class": ERROR_CLASS_UNEXPECTED,
+            "verified_absent": False,
+            "branch_present": None,
+            "not_found_scope": scope,
+            "reasons": [reason],
+        }
+    if status_code in (401, 407):
+        return {
+            "status": READBACK_AUTHENTICATION,
+            "error_class": ERROR_CLASS_AUTHENTICATION,
+            "verified_absent": False,
+            "branch_present": None,
+            "reasons": ["post-delete branch readback authentication failed"],
+        }
+    if status_code == 403:
+        return {
+            "status": READBACK_AUTHORIZATION,
+            "error_class": ERROR_CLASS_AUTHORIZATION,
+            "verified_absent": False,
+            "branch_present": None,
+            "reasons": ["post-delete branch readback authorization failed"],
+        }
+    if status_code is not None and 200 <= int(status_code) < 300:
+        return {
+            "status": READBACK_EXISTS,
+            "error_class": None,
+            "verified_absent": False,
+            "branch_present": True,
+            "reasons": ["post-delete readback found branch still present"],
+        }
+    if status_code is not None and int(status_code) >= 500:
+        return {
+            "status": READBACK_TRANSPORT,
+            "error_class": ERROR_CLASS_TRANSPORT,
+            "verified_absent": False,
+            "branch_present": None,
+            "reasons": ["post-delete branch readback transport/upstream failure"],
+        }
+    return {
+        "status": READBACK_UNEXPECTED,
+        "error_class": ERROR_CLASS_UNEXPECTED,
+        "verified_absent": False,
+        "branch_present": None,
+        "reasons": ["post-delete branch readback returned an unexpected response"],
+        "http_status": status_code,
+    }
+
+
+def _extract_http_status(exc: BaseException) -> int | None:
+    """Extract an HTTP status code from an exception chain (secret-free)."""
+    seen: set[int] = set()
+    current: BaseException | None = exc
+    while current is not None and id(current) not in seen:
+        seen.add(id(current))
+        for attr in ("code", "status", "status_code"):
+            value = getattr(current, attr, None)
+            if isinstance(value, int) and 100 <= value <= 599:
+                return value
+        text = str(current) if current is not None else ""
+        match = re.match(r"HTTP\s+(\d{3})\b", text)
+        if match:
+            return int(match.group(1))
+        current = current.__cause__ or current.__context__
+    return None
+
+
+def classify_branch_readback_exception(
+    exc: BaseException,
+    *,
+    not_found_scope: str | None = None,
+) -> dict[str, Any]:
+    """Classify a GET-branch exception without leaking credentials or bodies.
+
+    R1: substring ``404`` / ``not found`` alone never becomes verified_absent.
+    Callers must pass ``not_found_scope='branch'`` only after authoritative
+    proof that the repository/host is still reachable and the 404 is branch-level.
+    """
+    status_code = _extract_http_status(exc)
+    if status_code is None:
+        lower = str(exc).lower() if exc is not None else ""
+        if any(
+            token in lower
+            for token in (
+                "timed out",
+                "timeout",
+                "connection",
+                "network",
+                "temporarily unavailable",
+                "name or service not known",
+                "nodename nor servname",
+            )
+        ):
+            return {
+                "status": READBACK_TRANSPORT,
+                "error_class": ERROR_CLASS_TRANSPORT,
+                "verified_absent": False,
+                "branch_present": None,
+                "reasons": [
+                    "post-delete branch readback transport/upstream failure"
+                ],
+            }
+        if "unauthorized" in lower:
+            status_code = 401
+        elif "forbidden" in lower:
+            status_code = 403
+        elif "404" in lower or "not found" in lower:
+            # Ambiguous: do NOT treat as branch absence without scope proof.
+            status_code = 404
+            if not_found_scope is None:
+                not_found_scope = NOT_FOUND_SCOPE_UNKNOWN
+
+    if status_code is not None:
+        return classify_branch_readback_http_status(
+            status_code, not_found_scope=not_found_scope
+        )
+
+    return {
+        "status": READBACK_UNEXPECTED,
+        "error_class": ERROR_CLASS_UNEXPECTED,
+        "verified_absent": False,
+        "branch_present": None,
+        "reasons": ["post-delete branch readback returned an unexpected response"],
+    }
+
+
+def assess_post_delete_readback(readback: dict[str, Any] | None) -> dict[str, Any]:
+    """Decide whether DELETE success may be reported after branch readback.
+
+    Success requires authoritative branch-scoped not-found
+    (``verified_absent=True``). DELETE HTTP success alone is never enough.
+    Generic/repository/host 404 cannot verify absence (R1).
+    """
+    payload = dict(readback or {})
+    status = _norm_str(payload.get("status")) or READBACK_UNEXPECTED
+    # Only explicit verified_absent flag counts — never infer from status alone
+    # when status is a bare not_found without branch scope proof.
+    verified = bool(payload.get("verified_absent")) is True
+    if verified and status == READBACK_NOT_FOUND:
+        return {
+            "ok": True,
+            "success": True,
+            "verified_absent": True,
+            "readback": {
+                "status": READBACK_NOT_FOUND,
+                "verified_absent": True,
+                "branch_present": False,
+                "error_class": None,
+                "not_found_scope": NOT_FOUND_SCOPE_BRANCH,
+            },
+            "reasons": [],
+        }
+
+    reasons = list(payload.get("reasons") or [])
+    if not reasons:
+        if status == READBACK_EXISTS:
+            reasons = ["post-delete readback found branch still present"]
+        elif status == READBACK_AUTHENTICATION:
+            reasons = ["post-delete branch readback authentication failed"]
+        elif status == READBACK_AUTHORIZATION:
+            reasons = ["post-delete branch readback authorization failed"]
+        elif status == READBACK_TRANSPORT:
+            reasons = ["post-delete branch readback transport/upstream failure"]
+        elif status == READBACK_AMBIGUOUS_404:
+            reasons = [
+                "post-delete readback 404 is not branch-scoped; "
+                "cannot verify absence"
+            ]
+        else:
+            reasons = ["post-delete branch readback could not verify deletion"]
+
+    return {
+        "ok": False,
+        "success": False,
+        "verified_absent": False,
+        "readback": {
+            "status": status,
+            "verified_absent": False,
+            "branch_present": payload.get("branch_present"),
+            "error_class": payload.get("error_class"),
+            "not_found_scope": payload.get("not_found_scope"),
+        },
+        "reasons": reasons,
+        "blocker_kind": "post_delete_readback_failed",
+    }
+
+
+def cleanup_result_envelope(
+    *,
+    success: bool,
+    performed: bool,
+    delete_acknowledged: bool,
+    verified_absent: bool,
+    **extra: Any,
+) -> dict[str, Any]:
+    """R2: consistent top-level cleanup result fields on every return path."""
+    out: dict[str, Any] = {
+        "success": bool(success),
+        "performed": bool(performed),
+        "delete_acknowledged": bool(delete_acknowledged),
+        "verified_absent": bool(verified_absent),
+    }
+    out.update(extra)
+    return out
+
+
+def _repo_matches(
+    record: dict[str, Any],
+    *,
+    remote: str,
+    org: str,
+    repo: str,
+    host: str | None = None,
+) -> bool:
+    """Match ownership record to target remote/org/repo and normalized host."""
+    if (
+        _norm_str(record.get("remote")).lower() != _norm_str(remote).lower()
+        or _norm_str(record.get("org")).lower() != _norm_str(org).lower()
+        or _norm_str(record.get("repo")).lower() != _norm_str(repo).lower()
+    ):
+        return False
+    expected_host = normalize_host(host)
+    record_host = normalize_host(record.get("host") or record.get("host_name"))
+    # When both sides declare a host, they must agree after normalization.
+    # A record host that disagrees with the expected host is out of scope.
+    # Legacy records without host still match when remote/org/repo agree.
+    if expected_host and record_host and expected_host != record_host:
+        return False
+    return True
+
+
+def _branch_matches(record: dict[str, Any], branch: str) -> bool:
+    return _norm_str(record.get("branch")) == _norm_str(branch)
+
+
+def assess_ownership_record_activity(record: dict[str, Any]) -> dict[str, Any]:
+    """Classify one ownership record as blocking or non-blocking.
+
+    Distinguishes active ownership from expired/released/terminal/stale records.
+    Expired/stale records block unless reclaim_allowed is *explicitly* True
+    (O2: never treat missing/unknown reclaim as auto-allowed).
+    """
+    status = _norm_str(record.get("status")).lower()
+    category = _norm_str(record.get("category")) or "unknown"
+    reclaim_allowed = record.get("reclaim_allowed")
+
+    if category == OWNERSHIP_CATEGORY_INVENTORY_ERROR:
+        return {
+            "blocks": True,
+            "status": status or "unknown",
+            "category": category,
+            "reason": "ownership inventory failed closed",
+        }
+
+    if status in _TERMINAL_OWNERSHIP_STATUSES:
+        return {
+            "blocks": False,
+            "status": status,
+            "category": category,
+            "reason": f"{category} ownership is terminal/released ({status})",
+        }
+    if status in _ACTIVE_OWNERSHIP_STATUSES:
+        return {
+            "blocks": True,
+            "status": status,
+            "category": category,
+            "reason": f"active {category} ownership still uses the target branch",
+        }
+    if status in _EXPIRED_STATUSES or status in _STALE_STATUSES:
+        # O2: only explicit reclaim_allowed=True skips the block.
+        if reclaim_allowed is True:
+            return {
+                "blocks": False,
+                "status": status,
+                "category": category,
+                "reason": (
+                    f"{category} ownership is {status} and reclaimable; "
+                    "does not block deletion"
+                ),
+            }
+        return {
+            "blocks": True,
+            "status": status,
+            "category": category,
+            "reason": (
+                f"{status} {category} ownership still protects the target "
+                "branch (reclaim not proven; fail closed)"
+            ),
+        }
+    # Unknown status → fail closed
+    return {
+        "blocks": True,
+        "status": status or "unknown",
+        "category": category,
+        "reason": (
+            f"unclassified {category} ownership status "
+            f"'{status or 'unknown'}'; fail closed"
+        ),
+    }
+
+
+def assess_active_branch_ownership(
+    *,
+    remote: str,
+    org: str,
+    repo: str,
+    branch: str,
+    host: str | None = None,
+    records: list[dict[str, Any]] | None = None,
+) -> dict[str, Any]:
+    """Assess whether any active ownership still uses *branch* in *repo*.
+
+    Matching requires remote/org/repo/branch and, when provided, normalized
+    host identity. Other repositories, hosts, or branches never false-block.
+    """
+    target_branch = _norm_str(branch)
+    expected_host = normalize_host(host)
+    considered: list[dict[str, Any]] = []
+    blocking: list[dict[str, Any]] = []
+    ignored: list[dict[str, Any]] = []
+
+    for raw in records or []:
+        if not isinstance(raw, dict):
+            continue
+        if not _repo_matches(
+            raw, remote=remote, org=org, repo=repo, host=expected_host or None
+        ):
+            ignored.append(
+                {
+                    "category": _norm_str(raw.get("category")) or "unknown",
+                    "reason": "different repository or host scope",
+                }
+            )
+            continue
+        if not _branch_matches(raw, target_branch):
+            ignored.append(
+                {
+                    "category": _norm_str(raw.get("category")) or "unknown",
+                    "reason": "different branch",
+                }
+            )
+            continue
+        activity = assess_ownership_record_activity(raw)
+        entry = {
+            "category": activity["category"],
+            "status": activity["status"],
+            "blocks": activity["blocks"],
+            "reason": activity["reason"],
+        }
+        considered.append(entry)
+        if activity["blocks"]:
+            blocking.append(entry)
+
+    block = bool(blocking)
+    categories = sorted({b["category"] for b in blocking})
+    reasons = [
+        (
+            "active ownership protects branch "
+            f"'{target_branch}': " + "; ".join(b["reason"] for b in blocking)
+        )
+    ] if block else []
+    return {
+        "block": block,
+        "safe_to_delete": not block,
+        "remote": remote,
+        "org": org,
+        "repo": repo,
+        "host": expected_host or None,
+        "branch": target_branch,
+        "blocking_categories": categories,
+        "blocking": blocking,
+        "considered": considered,
+        "ignored_out_of_scope": ignored,
+        "reasons": reasons,
+        "blocker_kind": "active_branch_ownership" if block else None,
+        "recommended_action": "keep_remote_branch" if block else "delete_remote_branch",
+    }

docs/architecture/mcp-stable-control-runtime-policy-adr.md

@@ -0,0 +1,198 @@
+# ADR: Stable control runtime vs dev runtime (Gitea MCP)
+
+- **Status:** Accepted (policy effective immediately for LLM sessions; tooling may lag)
+- **Date:** 2026-07-09
+- **Tracking issue:** [#615](https://gitea.prgs.cc/Scaled-Tech-Consulting/Gitea-Tools/issues/615)
+- **Related:**
+  - [#543](https://gitea.prgs.cc/Scaled-Tech-Consulting/Gitea-Tools/issues/543) / `docs/mcp-namespace-health.md` — client-namespace health
+  - `docs/mcp-namespace-eof-recovery.md` — reconnect-only EOF recovery (no PID kill)
+  - [#558](https://gitea.prgs.cc/Scaled-Tech-Consulting/Gitea-Tools/issues/558) / `docs/mcp-daemon-import-guard.md` — sanctioned daemon
+  - [#557](https://gitea.prgs.cc/Scaled-Tech-Consulting/Gitea-Tools/issues/557) / `docs/bootstrap-review-path.md` — controller bootstrap for self-hosted fixes
+  - Allocator / control-plane ADR: `docs/architecture/mcp-allocator-control-plane-observability-adr.md` (#613 / PR #614)
+
+## 1. Context
+
+The Gitea MCP server is the **control plane** for real issue/PR mutations (create, comment, lock, review, merge, etc.). When author/reviewer/merger/reconciler sessions kill or restart that process, relaunch it from a feature worktree, or edit the checkout that process loads, operators observe:
+
+- Mid-session identity/preflight resets
+- Stale-runtime vs master parity failures
+- IDE transport EOF / “tool not found” while code on disk has changed
+- Accidental production mutations from experimental code
+
+This ADR separates **stable control runtime** from **dev/test runtime** and defines promotion proof.
+
+## 2. Decision
+
+### 2.1 Stable control runtime
+
+The Gitea MCP server used for **real workflow mutations** is the **stable control runtime**.
+
+Characteristics:
+
+- Loads a known, promoted revision of Gitea-Tools (or the packaged release layout operators designate)
+- Registered in the IDE/client as the production namespaces (`gitea-tools`, `gitea-reviewer`, `gitea-merger`, `gitea-reconciler`, etc.)
+- Holds production profile credentials via sanctioned keychain/env paths only
+
+### 2.2 Dev / test runtime
+
+MCP **server code** development and testing:
+
+- Happens in isolated **`branches/`** worktrees (or other non-stable checkouts)
+- May use a **separate** dev/test MCP runtime/process when process-level testing is required
+- **Must not** be used for real Gitea mutations on production issues/PRs
+
+### 2.3 Forbidden actions (normal sessions)
+
+Normal **author, reviewer, merger, and reconciler** LLM sessions **must not**:
+
+| Forbidden | Why |
+|-----------|-----|
+| Kill the running MCP server process | Drops all concurrent sessions; loses preflight state |
+| Restart / relaunch the MCP server process | Same as kill; causes stale/identity churn mid-workflow |
+| Relaunch MCP from a development worktree | Runs unpromoted code against production mutations |
+| Edit files in the stable runtime checkout | Hot-mutates control plane under concurrent users |
+| Use experimental/dev MCP for real Gitea mutations | Bypasses promotion proof and audit expectations |
+| Bypass or self-reset a stale master-parity gate | The gate is fail-closed; only an operator reload restores parity |
+
+**LLM-allowed vs operator-owned (authoritative split):**
+
+| Actor | May do | Must not do |
+|-------|--------|-------------|
+| **LLM session** | Call tools on the already-running stable namespaces; **client reconnect** after transport EOF (no process kill); pass `worktree_path` / role worktree args; report blockers and stop mutations when unhealthy/stale | Kill, restart, or relaunch any MCP process; bump config mtimes to force reload; edit the stable checkout; switch to a dev MCP for production mutations |
+| **Operator / release-manager** | Supervised restart/reload of the **stable** control runtime; dual-namespace client configuration; §2.4 promotions; incident recovery | — |
+
+EOF / transport recovery for LLM sessions: **client reconnect only** (see `docs/mcp-namespace-eof-recovery.md`). Do not “fix” health by killing PIDs or bumping MCP config mtimes as a normal session procedure.
+
+This ADR **supersedes** any older runbook wording that told the LLM to relaunch or restart the client/MCP as a self-service step. Where `docs/llm-workflow-runbooks.md` (or wiki runbooks) discuss dual-namespace setup or workspace rebind, **process restart/relaunch is operator-owned**; the LLM stops, reports, and waits.
+
+### 2.4 Promotion (operator / release-manager only)
+
+Promotion of a new revision into the stable control runtime is an **explicit operator/release-manager action**, not an LLM self-service step.
+
+A promotion **must record** (issue comment, release note, or promotion ledger):
+
+| Field | Description |
+|-------|-------------|
+| **previous runtime SHA** | Commit previously loaded by stable runtime |
+| **promoted runtime SHA** | Commit after promotion |
+| **source branch/PR** | Where the change was reviewed |
+| **restart/reload method** | How the process was cycled (e.g. supervised restart, client reload) |
+| **health check proof** | Client-namespace probe success (`gitea_whoami` / namespace health) |
+| **identity/profile proof** | Expected profile(s) and username(s) after reload |
+| **workspace/root proof** | Stable checkout path / root matches intended layout |
+| **mutation capability proof** | Required permissions for the target role present; forbidden ops still forbidden |
+| **rollback instructions** | How to restore previous SHA and re-verify health |
+
+Suggested durable marker:
+
+```text
+## MCP STABLE RUNTIME PROMOTION (#615)
+
+Status: COMPLETED | ROLLED_BACK | ABORTED
+Previous-SHA: <full sha>
+Promoted-SHA: <full sha>
+Source-PR: <number>
+Source-Branch: <name>
+Reload-Method: <text>
+Health-Proof: client_namespace whoami OK / assess_mcp_namespace_health OK
+Identity-Proof: profile=<name> user=<name>
+Workspace-Proof: root=<path>
+Mutation-Proof: allowed_ops include <…>; forbidden include <…>
+Rollback: checkout <previous sha>; reload method <…>; re-run health/identity proofs
+Operator: <username>
+Timestamp: <ISO-8601>
+```
+
+### 2.5 Unhealthy stable runtime → stop work
+
+If the stable MCP runtime is **unhealthy**, including any of:
+
+- client-namespace probes fail
+- wrong identity / wrong profile
+- wrong workspace root
+- missing mutation capability for the intended role
+- persistent EOF after **client reconnect**
+- **master parity is stale** (`startup_head` behind on-disk `master` / `restart_required` from the parity gate)
+
+then:
+
+1. **Normal PR / review / merge / issue-mutation work must stop immediately.**
+2. The session **reports** the unhealthy/stale state (tool error, CTH, or operator handoff) with startup vs current head when known.
+3. Do **not** improvise: no LLM process kill/restart, no dev-worktree MCP for production mutations, no env escape hatches, no manual gate bypass.
+4. Resume only after:
+   - an **operator** restores the runtime (see §2.6 for routine post-merge parity reload), **or**
+   - a **controlled** promotion/rollback completes with the §2.4 promotion record, **or**
+   - a controller invokes the narrow **bootstrap review path** (#557) when the defect is self-hosted and documented,
+   - **and** the session re-verifies health (and master parity when applicable) before the next mutation.
+
+### 2.6 Routine post-merge master-parity staleness (operator reload, not promotion)
+
+**Symptom:** After merges land on `master`, a long-lived stable MCP process still runs the pre-merge `startup_head`. The master-parity gate marks the server **stale** / `restart_required` and **blocks mutations**.
+
+**Sanctioned response (authoritative):**
+
+| Step | Actor | Action |
+|------|-------|--------|
+| 1 | LLM session | Mutations stop immediately when the gate reports stale. |
+| 2 | LLM session | Report the stale state (startup head, current master head, that operator reload is required). Do not retry mutations. |
+| 3 | **Operator** | Reload/restart the **stable** control MCP so it loads current `master` (supervised client/daemon reload). |
+| 4 | LLM session | Resume only after startup/current-head parity is verified (e.g. `gitea_get_runtime_context` / parity assessment shows in parity). |
+
+**Not a §2.4 promotion:** Catching the already-designated stable control checkout up to a newly advanced `master` is a **routine operator reload** of the stable runtime. It does **not** require the nine-field promotion ledger. Use §2.4 only when **changing which unpromoted/dev revision** becomes the stable control runtime (new source branch/PR into the stable designation).
+
+**Code note:** `master_parity_gate.py` may still say “restart the server” in machine-facing reason strings. That string names the **operator recovery action**, not an LLM self-service instruction. This ADR and the runbooks define the actor split.
+
+## 3. Relationship to other controls
+
+| Doc / mechanism | Interaction |
+|-----------------|-------------|
+| Namespace health (#543) | Proves IDE client can call tools; does not authorize restart |
+| EOF recovery | Reconnect only; no process kill |
+| Daemon import guard (#558) | Mutations require sanctioned daemon; not a bare shell import |
+| Bootstrap path (#557) | Only controller-authorized exception when live runtime cannot review its own fix |
+| Allocator / control-plane ADR | Coordination DB is separate; still depends on a healthy MCP surface for Gitea writes |
+
+## 4. Consequences
+
+### Positive
+
+- Predictable control plane for concurrent LLMs
+- Clear operator-only promotion gate with rollback
+- Aligns session behavior with health/EOF docs already landed
+
+### Costs
+
+- LLM sessions must wait when runtime is sick (no DIY restart)
+- Operators must maintain promotion discipline and dual-runtime config if they use a dev MCP
+
+### Non-goals
+
+- Does not ban operator-supervised restarts during incidents
+- Does not replace CI or code review for MCP changes
+- Does not authorize editing stable checkout “because tests need a quick fix”
+
+## 5. Implementation follow-ups (optional tooling)
+
+These may land in later issues; the **policy binds sessions now**:
+
+1. Session preflight that refuses mutations if workspace root equals a `branches/` feature worktree configured as “dev only.”
+2. Explicit `runtime_kind=stable|dev` in MCP config and `gitea_whoami` profile metadata.
+3. Promotion checklist script that emits the durable promotion marker fields.
+
+**Not optional (issue #615 acceptance criterion 2):** operator guide and runbooks **must** cross-link this ADR (see §6). Cross-links are documentation acceptance, not deferred tooling.
+
+## 6. Acceptance for this ADR
+
+1. Document merged under `docs/architecture/mcp-stable-control-runtime-policy-adr.md`.
+2. **Operator guide / runbooks cross-link this ADR** (`docs/wiki/Operator-Guide.md`, `docs/wiki/Runbooks.md`, `docs/llm-workflow-runbooks.md`).
+3. Issue #615 references this path.
+4. LLM/operator runbooks treat kill/restart/relaunch-from-worktree as **LLM violations**; process restart is **operator-owned**.
+5. Unhealthy runtime (including **stale master parity**) stops normal mutation work until operator restore/reload, promotion/rollback, or #557 bootstrap — then re-verify parity before mutating.
+6. Routine post-merge parity reload is documented as operator reload (§2.6), not an LLM self-restart and not a full §2.4 promotion.
+
+## 7. Document history
+
+| Date | Change |
+|------|--------|
+| 2026-07-09 | Initial ADR: stable vs dev runtime, forbidden session actions, promotion proof fields, stop-work rule |
+| 2026-07-16 | Review 443 remediation (#615 / PR #616): mandatory cross-links; LLM vs operator restart split; routine post-merge parity staleness (§2.6); stale parity in §2.5 unhealthy triggers |

docs/gitea-execution-profiles.md

@@ -238,11 +238,43 @@ narrow operation set:
 - `gitea.issue.comment`
 - `gitea.issue.close`
 - `gitea.pr.close`
+- `gitea.branch.delete` (merged-branch cleanup only — see below)
 
 Forbidden on reconciler profiles: `gitea.pr.approve`, `gitea.pr.merge`,
 `gitea.pr.review`, `gitea.pr.create`, `gitea.branch.push`, and
 `gitea.repo.commit`.
 
+### Merged-branch cleanup ownership (`gitea.branch.delete`)
+
+The reconciler is the repository-supported owner of merged-PR source-branch
+cleanup: `task_capability_map` maps `cleanup_merged_pr_branch` (and
+`reconciliation_cleanup`) to role `reconciler` with permission
+`gitea.branch.delete`. Post-merge branch lifecycle is reconciliation work —
+it happens after the author, reviewer, and merger roles have completed, and
+it must not be reachable from those roles.
+
+Least-privilege constraints:
+
+- `gitea.branch.delete` is granted **only** to reconciler profiles. Author,
+  reviewer, and merger profiles must never hold it; `gitea_delete_branch`
+  and `gitea_cleanup_merged_pr_branch` fail closed on any profile without
+  the permission.
+- Even with the permission, reconciler deletion is only supported through the
+  guarded `gitea_cleanup_merged_pr_branch` path (#514 / #687): the PR must be
+  merged, the head an ancestor of the target, the branch not protected
+  (`master`/`main`/`dev`), the branch not a preservation/evidence ref (e.g.
+  `chore/issue-681-preserve-review-session-wip`), no open PR may still use the
+  head, and an explicit `CLEANUP MERGED PR <n> BRANCH <branch>` confirmation is
+  required. Raw `gitea_delete_branch` is **denied** to reconciler even when
+  `gitea.branch.delete` is present.
+- Raw `git branch -d` / `git push --delete` cleanup remains blocked by
+  `branch_cleanup_guard` and the final-report validator regardless of
+  profile permissions.
+- `gitea.branch.delete` has no short alias in `GITEA_OPERATION_ALIASES`;
+  write it fully qualified in `allowed_operations`. Migration must emit
+  canonical names such as `gitea.pr.close` (never bare `pr.close` /
+  `issue.close`, which the production normalizer rejects or drops).
+
 Launch a static `gitea-reconciler` MCP namespace with
 `GITEA_MCP_PROFILE=prgs-reconciler`. Profile shape is validated by
 `reconciler_profile.assess_reconciler_profile` (#304). Use the
@@ -251,6 +283,159 @@ Launch a static `gitea-reconciler` MCP namespace with
 fresh target-branch fetch, recorded target SHA, and ancestor proof. PRs whose
 heads are not already landed cannot be closed through this path.
 
+### Operational runbook: grant reconciler `gitea.branch.delete` (#687)
+
+Merging a code PR that updates `migrate_profiles.py` / `reconciler_profile.py`
+**does not** change the live operator profile on disk. Apply the profile
+change deliberately, then reconnect the client-managed namespace.
+
+1. **Approved migration / profile-update command** (from the repo root, using
+   the project venv if present):
+
+   ```bash
+   # Dry-run first (default): validates v2 output, writes nothing
+   python3 migrate_profiles.py -i ~/.config/gitea-tools/profiles.json
+
+   # Apply: creates backup then writes migrated v2 config
+   python3 migrate_profiles.py -i ~/.config/gitea-tools/profiles.json -w
+   # Optional explicit paths:
+   # python3 migrate_profiles.py -i ~/.config/gitea-tools/profiles.json \
+   #   -o ~/.config/gitea-tools/profiles.json \
+   #   --backup ~/.config/gitea-tools/profiles.json.bak -w
+   ```
+
+   If the live file is already v2, edit the reconciler identity’s
+   `allowed_operations` / `forbidden_operations` under
+   `environments.<env>.services.gitea.identities.reconciler` (or the
+   `prgs-reconciler` alias target) so allowed includes the canonical set
+   below — then re-validate with a load of the config (see step 3).
+
+2. **Inspect the generated (or edited) profile** — confirm the reconciler
+   identity, for example:
+
+   ```bash
+   python3 - <<'PY'
+   import json
+   from pathlib import Path
+   cfg = json.loads(Path.home().joinpath(".config/gitea-tools/profiles.json").read_text())
+   # v2 environments shape:
+   ident = cfg["environments"]["prgs"]["services"]["gitea"]["identities"]["reconciler"]
+   print("role:", ident.get("role"))
+   print("allowed:", ident.get("allowed_operations"))
+   print("forbidden:", ident.get("forbidden_operations"))
+   PY
+   ```
+
+3. **Validate canonical operation names and least privilege**
+
+   Expected canonical **allowed** (defaults after migration):
+
+   - `gitea.read`
+   - `gitea.pr.close` (required)
+   - `gitea.pr.comment`
+   - `gitea.issue.comment`
+   - `gitea.issue.close`
+   - `gitea.branch.delete` (recommended; cleanup only)
+
+   Expected **forbidden** includes at least: `gitea.pr.approve`,
+   `gitea.pr.merge`, `gitea.pr.review`, `gitea.pr.create`,
+   `gitea.branch.push`, `gitea.repo.commit`.
+
+   No shorthand (`pr.close`, `issue.close`, `pr.comment`) may remain.
+   Validate with the production loader:
+
+   ```bash
+   python3 - <<'PY'
+   import gitea_config, reconciler_profile
+   from pathlib import Path
+   path = str(Path.home() / ".config/gitea-tools/profiles.json")
+   gitea_config.load_config(path)  # fails closed on invalid config
+   # Or assess the reconciler lists directly after extracting them:
+   # print(reconciler_profile.assess_reconciler_profile(allowed, forbidden))
+   PY
+   ```
+
+4. **Merging PR #688 (or any code PR) does not update the live profile.**
+   Code changes only the migration helper, schema, docs, and tests. The
+   operator must still run `migrate_profiles.py -w` or an equivalent
+   authorized edit of `~/.config/gitea-tools/profiles.json`.
+
+5. **Supported apply method:** `python3 migrate_profiles.py … -w` (backup
+   created automatically) **or** operator-authorized edit of the live
+   profiles file after backup. Unsupported: silent mtime tricks, manual
+   process kill to “reload”, or undocumented env overrides.
+
+6. **Backup and validation:** `-w` copies the input to
+   `<input_path>.bak` (or `--backup PATH`) before writing. Re-run
+   `load_config` / `assess_reconciler_profile` after write. Keep the
+   `.bak` until live whoami/capability checks pass.
+
+7. **Client-managed namespace reconnect/reload:** reconnect or reload the
+   IDE MCP client so `gitea-reconciler` restarts from current `master` and
+   the updated `GITEA_MCP_PROFILE=prgs-reconciler` config. Do not hand-launch
+   `mcp_server.py` / `gitea_mcp_server.py` with ad hoc `GITEA_*` env
+   (see #686 / #630).
+
+8. **Live reverification** (through the client-managed `gitea-reconciler`
+   namespace only):
+
+   - `gitea_whoami` → identity + profile `prgs-reconciler`
+   - `gitea_assess_master_parity` → `stale=false`, `restart_required=false`
+   - `gitea_resolve_task_capability(task="cleanup_merged_pr_branch")` →
+     `allowed_in_current_session=true` only when permission and role match
+   - `gitea_resolve_task_capability(task="delete_branch")` →
+     **not** allowed for reconciler (role denial must be enforced)
+
+9. **Guarded cleanup usage** (example for a merged PR whose source branch
+   remains on the remote):
+
+   ```text
+   gitea_cleanup_merged_pr_branch(
+     pr_number=<N>,
+     branch=<exact PR head branch>,
+     confirmation="CLEANUP MERGED PR <N> BRANCH <exact PR head branch>",
+     remote="prgs",
+     org="Scaled-Tech-Consulting",
+     repo="Gitea-Tools",
+     worktree_path="<path under branches/>",
+   )
+   ```
+
+   The tool refuses unmerged PRs, protected branches, preservation/evidence
+   branches, open-PR heads, mismatched branch names, and wrong confirmation.
+
+10. **Prohibitions**
+
+    - No raw `git push --delete`, `git branch -d` / `-D`, or delete refspecs
+    - No arbitrary `gitea_delete_branch` from reconciler
+    - No unsupported profile switching mid-run without full re-preflight
+    - No ad hoc hand-edits of live profiles **unless** operator-authorized,
+      backed up, and revalidated as above
+
+Canonical migrated reconciler example:
+
+```json
+{
+  "role": "reconciler",
+  "allowed_operations": [
+    "gitea.read",
+    "gitea.pr.close",
+    "gitea.pr.comment",
+    "gitea.issue.comment",
+    "gitea.issue.close",
+    "gitea.branch.delete"
+  ],
+  "forbidden_operations": [
+    "gitea.pr.approve",
+    "gitea.pr.merge",
+    "gitea.pr.review",
+    "gitea.pr.create",
+    "gitea.branch.push",
+    "gitea.repo.commit"
+  ]
+}
+```
+
 ## Identity and fail-closed rules
 
 Before **any** mutating action, a workflow must know both:

docs/llm-workflow-runbooks.md

@@ -195,7 +195,7 @@ To avoid the bottleneck of relaunching/restarting the MCP server to switch betwe
   `gitea_reconcile_already_landed_pr` after ancestry proof — not for normal
   review or author workflows.
 
-* **Fallback:** If the dual-profile MCP launcher pattern is not supported or configured in the client, the LLM must relaunch or restart the client/MCP with the correct profile environment variable before claiming or working on any tasks.
+* **Fallback (operator-owned):** If the dual-profile MCP launcher pattern is not supported or configured in the client, **do not** have the LLM relaunch or restart the client/MCP. The LLM **stops** role-switching work, reports that the correct static namespace is missing, and waits for an **operator** to configure dual namespaces or reload the client with the correct `GITEA_MCP_PROFILE` for that role. Process restart/relaunch is operator-owned under the [stable control runtime ADR](architecture/mcp-stable-control-runtime-policy-adr.md) (#615).
 
 ## Setup runbook — interactive menu
 
@@ -1200,10 +1200,13 @@ When a mutation blocks on workspace binding:
 
 1. Read the error — it names the **resolved workspace path**, **role
    namespace**, and **binding source** (tool arg, env var, or process root).
-2. Reconnect or relaunch the correct namespace MCP server from the intended
-   workspace (or set the role-specific env var before launch).
-3. Pass `worktree_path` on reviewer/merger mutation tools when the active
-   branches/ worktree differs from the MCP process root.
+2. **LLM-allowed:** pass `worktree_path` on reviewer/merger mutation tools when
+   the active `branches/` worktree differs from the MCP process root; **client
+   reconnect** after transport EOF only (no process kill).
+3. **Operator-owned:** if the wrong namespace process was launched, or a role-
+   specific `GITEA_*_WORKTREE` must be set at process start, an **operator**
+   reloads/relaunches the correct static namespace MCP. LLM sessions must not
+   kill or restart MCP processes (see [stable control runtime ADR](architecture/mcp-stable-control-runtime-policy-adr.md)).
 4. **Do not** clean, reset, or discard foreign role worktrees to unblock your
    own namespace — that destroys another agent's WIP.
 
@@ -1213,9 +1216,10 @@ When posting a Canonical Thread Handoff after a binding blocker:
 
 - State which namespace was active (author / reviewer / merger / reconciler).
 - Quote the resolved workspace path and binding source from the error.
-- Name the safe reconnect action (relaunch MCP from `branches/...`, set
-  `GITEA_*_WORKTREE`, or pass `worktree_path`).
-- Explicitly note that foreign worktrees must not be cleaned to unblock.
+- Name the safe next action: pass `worktree_path` if that unblocks the tool, or
+  request an **operator** reload of the correct namespace MCP / env binding.
+- Explicitly note that foreign worktrees must not be cleaned to unblock, and
+  that the LLM must not self-restart the MCP process.
 
 ## Safety notes
 
@@ -1226,6 +1230,7 @@ When posting a Canonical Thread Handoff after a binding blocker:
 
 ## Related documents
 
+- [`architecture/mcp-stable-control-runtime-policy-adr.md`](architecture/mcp-stable-control-runtime-policy-adr.md) — stable control runtime vs dev runtime; LLM must not kill/restart MCP; operator-owned reload and promotions; routine post-merge parity staleness (#615).
 - [`reviewer-handoff-consistency.md`](reviewer-handoff-consistency.md) — reject contradictory reviewer handoffs (#501).
 - [`issue-acceptance-gate.md`](issue-acceptance-gate.md) — controller issue-acceptance audit after PR merge (#500).
 - [`../skills/llm-project-workflow/SKILL.md`](../skills/llm-project-workflow/SKILL.md) — portable cross-project LLM workflow skill.

docs/observability/sentry-integration.md

@@ -0,0 +1,138 @@
+# Self-hosted Sentry observability for the Gitea MCP server (#606)
+
+Optional, **off-by-default** instrumentation that reports MCP runtime errors,
+fail-closed workflow blockers, lease / terminal-lock / stale-runtime
+collisions, and recurring watchdog check-ins to a **self-hosted** Sentry at
+`https://sentry.prgs.cc/`.
+
+> **Gitea remains the source of truth.** Sentry is observe-only. It never
+> approves, merges, closes, or otherwise mutates Gitea workflow state, and it
+> never bypasses leases, #332, workflow roles, or the MCP gates. Sentry alerts
+> may only feed the *sanctioned* Gitea issue/comment path via the #612 incident
+> bridge — never a direct write.
+
+Implemented by [`sentry_observability.py`](../../sentry_observability.py).
+
+---
+
+## 1. Create the Sentry project
+
+1. Sign in to the self-hosted Sentry at **`https://sentry.prgs.cc/`** (this is
+   **not** Sentry Cloud — do not use `*.ingest.sentry.io`).
+2. Create a new **Python** project named **`gitea-tools-mcp`**.
+3. Open **Settings → Projects → gitea-tools-mcp → Client Keys (DSN)** and copy
+   the DSN. It looks like `https://<publickey>@sentry.prgs.cc/<project-id>`.
+4. **Never commit the DSN.** It is a runtime secret supplied via env var only.
+
+## 2. Configure the environment
+
+All configuration is env-var driven (see [`.env.example`](../../.env.example)):
+
+| Variable | Purpose | Default |
+|----------|---------|---------|
+| `MCP_SENTRY_ENABLED` | Master gate (`1/true/yes/on`). Required. | off |
+| `SENTRY_DSN` | Self-hosted DSN. Required. | *(empty)* |
+| `SENTRY_ENVIRONMENT` | `local` / `dev` / `prod` tag. | `development` |
+| `SENTRY_RELEASE` | Release id (git SHA or version). | *(none)* |
+| `MCP_SENTRY_TRACES_SAMPLE_RATE` | Perf-trace sample rate `0.0–1.0` (clamped). | `0.0` |
+| `MCP_SENTRY_ENABLE_LOGS` | Forward Python logs as structured logs. | off |
+
+**The feature stays completely off unless `MCP_SENTRY_ENABLED` is truthy *and*
+`SENTRY_DSN` is non-empty.** With either missing, `init_sentry()` is a no-op,
+the SDK is never initialised, and no events are sent — existing tool behaviour
+and API-call patterns are unchanged.
+
+### Per-environment examples
+
+```bash
+# local (quiet: capture errors/blockers, no traces)
+export MCP_SENTRY_ENABLED=1
+export SENTRY_DSN="https://<key>@sentry.prgs.cc/<id>"
+export SENTRY_ENVIRONMENT=local
+
+# dev (light tracing + logs)
+export MCP_SENTRY_ENABLED=1
+export SENTRY_DSN="https://<key>@sentry.prgs.cc/<id>"
+export SENTRY_ENVIRONMENT=dev
+export MCP_SENTRY_TRACES_SAMPLE_RATE=0.2
+export MCP_SENTRY_ENABLE_LOGS=1
+
+# prod (errors/blockers + low-rate tracing, release-tagged)
+export MCP_SENTRY_ENABLED=1
+export SENTRY_DSN="https://<key>@sentry.prgs.cc/<id>"
+export SENTRY_ENVIRONMENT=prod
+export SENTRY_RELEASE="$(git rev-parse --short HEAD)"
+export MCP_SENTRY_TRACES_SAMPLE_RATE=0.05
+```
+
+The optional SDK is pinned in [`requirements.txt`](../../requirements.txt)
+(`sentry-sdk==2.20.0`). It is imported lazily: if the package is absent, the
+module still imports and every entry point is a safe no-op.
+
+## 3. What is instrumented
+
+| Signal | Where | Notes |
+|--------|-------|-------|
+| Startup init | `gitea_mcp_server.py` `__main__`, before `mcp.run` | Prints a redaction-safe status line to stderr. |
+| Failing mutations (exceptions) | `_audited(...)` context manager | `capture_exception` with scrubbed tags. |
+| Fail-closed blockers / failed mutations | `_audit_pr_result(...)` (BLOCKED/FAILED) | Structured `capture_workflow_blocker` event incl. the canonical next action when available (criterion 7). |
+| Allocator watchdog check-ins | `gitea_allocate_next_work` tool | `allocator_health`, `stale_lease_scan`, `terminal_lock_scan`. |
+| Namespace-health check-in | `gitea_assess_mcp_namespace_health` tool | `namespace_health`. |
+
+All capture paths are **best-effort / fail open**: a Sentry outage or capture
+error never breaks an MCP tool success path.
+
+## 4. Cron / watchdog monitors
+
+`sentry_observability.MONITOR_SLUGS` defines stable check-in slugs:
+
+| Registry key | Sentry monitor slug | Wired at |
+|--------------|--------------------|----------|
+| `stale_lease_scan` | `gitea-mcp-stale-lease-scan` | allocator run (global lease expiry) |
+| `terminal_lock_scan` | `gitea-mcp-terminal-lock-scan` | allocator run (terminal-lock lookup) |
+| `allocator_health` | `gitea-mcp-allocator-health` | allocator run |
+| `namespace_health` | `gitea-mcp-namespace-health` | namespace-health probe |
+| `dashboard_freshness` | `gitea-mcp-dashboard-freshness` | call `monitor_checkin("dashboard_freshness", ...)` from the dashboard refresh job (#605) |
+| `reconciler_cleanup` | `gitea-mcp-reconciler-cleanup` | call `monitor_checkin("reconciler_cleanup", ...)` from the reconciler cleanup entrypoint |
+
+Create matching Cron monitors in Sentry with those slugs. Emit an
+`in_progress` check-in at job start and `ok`/`error` at completion via
+`sentry_observability.monitor_checkin(slug_key, status)`.
+
+## 5. Redaction guarantees (fail closed)
+
+Redaction fails *closed*: if a field cannot be proven safe it is dropped rather
+than sent. The `before_send` (and `before_send_log`) hook `scrub_event`
+recursively redacts every outgoing event; on any error it drops the event
+entirely. Guarantees, proven by `tests/test_sentry_observability.py`:
+
+- **No** tokens, passwords, keychain IDs, DSNs, cookies, or `user:pass@host`.
+- **No** raw session-state or full prompt/comment bodies — `session_id` is only
+  ever surfaced as a 12-char `session_id_hash`.
+- **No** private config contents or raw credential headers.
+- **No** full local filesystem paths — a worktree path collapses to a coarse
+  `worktree_category` (`author` / `reviewer` / `merger` / `reconciler` /
+  `branches` / `root` / `other`).
+- Only the allowlisted tag keys in `ALLOWED_TAG_KEYS` are ever attached.
+
+## 6. Coexistence with GlitchTip / the #612 incident bridge
+
+This is the **outbound** path (MCP → Sentry SDK). It complements — it does not
+replace — the **inbound** [`incident_bridge.py`](../../incident_bridge.py)
+(#612), which turns Sentry/GlitchTip *observations* into durable Gitea issues
+and `incident_links` rows.
+
+- Prefer **one** observability path per environment. Point the MCP server's
+  `SENTRY_DSN` at the same self-hosted `gitea-tools-mcp` project that the #612
+  bridge reconciles from, so an MCP-reported error and its Gitea issue line up.
+- GlitchTip is Sentry-protocol compatible; if an existing GlitchTip DSN is in
+  use, either migrate it to `https://sentry.prgs.cc/` or document the split
+  (MCP → Sentry, legacy → GlitchTip) explicitly for operators.
+- The bridge remains the **only** sanctioned route from an alert back into
+  Gitea workflow state.
+
+## 7. Non-goals
+
+- Sentry must **not** become the workflow source of truth.
+- Sentry must **not** approve, merge, close, or mutate Gitea workflow state.
+- Sentry must **not** bypass leases, #332, workflow roles, or the MCP gates.

docs/wiki/Operator-Guide.md

@@ -14,6 +14,7 @@ Handbook for LLM operators and human developers using the Gitea-Tools MCP server
 4. **No self-review / no self-merge** — The authenticated Gitea user must not approve or merge a PR they authored.
 5. **Follow the gates** — Prompts express intent; MCP tools enforce safety. Never bypass gates via prompt instructions.
 6. **Global LLM Worktree Rule** — Main checkout stays on `master`/`main`/`dev`; all mutations happen under `branches/`. Prove project root, `cwd`, branch, stable main-checkout branch, and session worktree path before editing. No exceptions.
+7. **Stable control runtime** — Real Gitea mutations use only the **stable** MCP control runtime. LLM sessions must not kill, restart, or relaunch MCP processes, edit the stable checkout, or use a dev MCP for production mutations. See the policy ADR: [mcp-stable-control-runtime-policy-adr.md](../architecture/mcp-stable-control-runtime-policy-adr.md) (#615).
 
 ## Supported Gitea instances
 
@@ -29,4 +30,5 @@ Always pass `remote` explicitly on tool calls. The server default is `dadeschool
 1. `gitea_whoami` — confirm authenticated user and profile.
 2. `gitea_get_runtime_context` — allowed/forbidden operations for this session.
 3. `gitea_resolve_task_capability` — prove the session may perform the planned task.
-4. For reviewer work: dry-run validation (`gitea_dry_run_pr_review`) before live review mutations.
+4. For reviewer work: dry-run validation (`gitea_dry_run_pr_review`) before live review mutations.
+5. Confirm master parity / runtime health when tools report stale or unhealthy control runtime — stop mutations and request an **operator** reload of the stable MCP (see [stable control runtime ADR](../architecture/mcp-stable-control-runtime-policy-adr.md)).

docs/wiki/Runbooks.md

@@ -12,6 +12,17 @@
 4. `gitea_mark_final_review_decision` → approve via `gitea_review_pr`.
 5. `gitea_merge_pr` with pinned head SHA and `confirmation="MERGE PR <n>"`.
 
+## Stable MCP control runtime (#615)
+
+Policy ADR: [mcp-stable-control-runtime-policy-adr.md](../architecture/mcp-stable-control-runtime-policy-adr.md).
+
+| Situation | Who acts | What to do |
+|-----------|----------|------------|
+| Transport EOF / missing tools | LLM | **Client reconnect only** — do not kill PIDs |
+| Wrong profile / dual-namespace missing | Operator | Configure or reload the correct static namespace(s) |
+| Master parity stale after merge | LLM stops + reports; **operator** reloads stable MCP | Resume only after parity re-verified |
+| Promote unpromoted MCP code to stable | Operator / release-manager only | Full §2.4 promotion record |
+
 ## Gitea Wiki sync
 
 The Gitea Wiki mirrors `docs/wiki/` (source of truth). After merging wiki changes:

gitea_auth.py

@@ -243,6 +243,192 @@ def _redact(text):
         return str(text)
 
 
+# ── Classified client failures (#699) ─────────────────────────────────────────
+# Subclasses of RuntimeError preserve existing ``except RuntimeError`` call
+# sites. Exception *messages* are fixed constants only — HTTP response bodies,
+# Keychain material, and arbitrary exception text are never stored on the
+# exception or re-emitted to tool results / daemon logs.
+
+
+# Fixed messages (must match mcp_tool_error_boundary.FIXED_MESSAGES keys used here).
+_MSG_AUTH_INVALID = "Gitea authentication failed: invalid or revoked credentials"
+_MSG_AUTH_FAILED = "Gitea authentication failed"
+_MSG_AUTHZ_SCOPE = "Gitea authorization failed: insufficient token scope"
+_MSG_AUTHZ_DENIED = "Gitea authorization failed: access denied"
+_MSG_NETWORK = "Network error contacting Gitea"
+_MSG_CONFIG = "Gitea configuration or credential resolution failed"
+_MSG_UPSTREAM = "Gitea upstream unavailable"
+_MSG_HTTP = "Gitea HTTP request failed"
+
+
+class GiteaClientError(RuntimeError):
+    """Base for known Gitea client failures with stable reason_code metadata."""
+
+    reason_code = "client_error"
+    error_class = "client"
+    http_status = None
+
+    def __init__(self, message=None, *, reason_code=None, http_status=None):
+        if reason_code is not None:
+            self.reason_code = reason_code
+        if http_status is not None:
+            self.http_status = http_status
+        # Message is always a fixed constant; callers cannot inject bodies.
+        fixed = message if message is not None else _MSG_HTTP
+        super().__init__(fixed)
+
+
+class GiteaAuthError(GiteaClientError):
+    """Authentication failure (invalid/revoked credentials → typically HTTP 401)."""
+
+    reason_code = "auth_invalid_token"
+    error_class = "authentication"
+    http_status = 401
+
+    def __init__(self, message=None, *, reason_code=None, http_status=None):
+        super().__init__(
+            message if message is not None else _MSG_AUTH_INVALID,
+            reason_code=reason_code or "auth_invalid_token",
+            http_status=http_status if http_status is not None else 401,
+        )
+
+
+class GiteaAuthzError(GiteaClientError):
+    """Authorization failure (HTTP 403 — scope deficiency or access denied)."""
+
+    reason_code = "authz_denied"
+    error_class = "authorization"
+    http_status = 403
+
+    def __init__(self, message=None, *, reason_code=None, http_status=None):
+        code = reason_code or "authz_denied"
+        if code == "authz_insufficient_scope":
+            fixed = _MSG_AUTHZ_SCOPE
+        else:
+            fixed = _MSG_AUTHZ_DENIED
+            code = "authz_denied"
+        super().__init__(
+            message if message is not None else fixed,
+            reason_code=code,
+            http_status=http_status if http_status is not None else 403,
+        )
+
+
+class GiteaNetworkError(GiteaClientError):
+    """Transport / DNS / timeout failure contacting Gitea."""
+
+    reason_code = "network_error"
+    error_class = "network"
+    http_status = None
+
+    def __init__(self, message=None, *, reason_code=None, http_status=None):
+        super().__init__(
+            message if message is not None else _MSG_NETWORK,
+            reason_code=reason_code or "network_error",
+            http_status=http_status,
+        )
+
+
+class GiteaConfigError(GiteaClientError):
+    """Local configuration / credential resolution failure (not HTTP auth)."""
+
+    reason_code = "config_error"
+    error_class = "configuration"
+    http_status = None
+
+    def __init__(self, message=None, *, reason_code=None, http_status=None):
+        super().__init__(
+            message if message is not None else _MSG_CONFIG,
+            reason_code=reason_code or "config_error",
+            http_status=http_status,
+        )
+
+
+class GiteaHttpError(GiteaClientError):
+    """Non-auth HTTP failure with fixed message (no response body)."""
+
+    reason_code = "http_error"
+    error_class = "client"
+    http_status = None
+
+    def __init__(self, message=None, *, reason_code=None, http_status=None):
+        code = reason_code or "http_error"
+        if code == "upstream_unavailable":
+            fixed = _MSG_UPSTREAM
+        else:
+            fixed = _MSG_HTTP
+            code = "http_error"
+        super().__init__(
+            message if message is not None else fixed,
+            reason_code=code,
+            http_status=http_status,
+        )
+
+
+def _looks_like_insufficient_scope(detail: str) -> bool:
+    """Internal: inspect redacted body *only* to refine 403 reason_code.
+
+    The body is never stored on the exception or returned to callers.
+    """
+    lower = (detail or "").lower()
+    markers = (
+        "insufficient scope",
+        "required scope",
+        "does not have at least one of required scope",
+        "token does not have",
+        "missing scope",
+        "scope(s)",
+    )
+    return any(m in lower for m in markers)
+
+
+def classify_http_status(code: int, *, body_hint: str = "") -> tuple[type, str, int]:
+    """Central HTTP status → (exception_class, reason_code, http_status).
+
+    Every HTTP 403 becomes authorization-class. Body text is used only as a
+    local hint for scope vs denied reason_code and is never returned.
+    """
+    if code == 401:
+        return (GiteaAuthError, "auth_invalid_token", 401)
+    if code == 403:
+        if _looks_like_insufficient_scope(body_hint or ""):
+            return (GiteaAuthzError, "authz_insufficient_scope", 403)
+        return (GiteaAuthzError, "authz_denied", 403)
+    if code in (502, 503, 504):
+        return (GiteaHttpError, "upstream_unavailable", code)
+    return (GiteaHttpError, "http_error", code)
+
+
+def raise_for_http_status(code: int, body: str = "") -> None:
+    """Raise a typed client error for *code* without embedding *body*.
+
+    *body* may be inspected only to choose scope vs denied for 403; it is
+    never placed on the exception message.
+    """
+    # Redact before any inspection; discard after classification.
+    try:
+        hint = _redact(body or "").strip()
+    except Exception:
+        hint = ""
+    exc_cls, reason, status = classify_http_status(code, body_hint=hint)
+    # Explicitly construct without passing body/hint into message.
+    if exc_cls is GiteaAuthError:
+        raise GiteaAuthError(reason_code=reason, http_status=status)
+    if exc_cls is GiteaAuthzError:
+        raise GiteaAuthzError(reason_code=reason, http_status=status)
+    if reason == "upstream_unavailable":
+        raise GiteaHttpError(
+            reason_code="upstream_unavailable",
+            http_status=status,
+        )
+    raise GiteaHttpError(reason_code="http_error", http_status=status)
+
+
+def _raise_http_error(code: int, detail: str = "") -> None:
+    """Backward-compatible alias — *detail* is never embedded in the error."""
+    raise_for_http_status(code, detail)
+
+
 def _add_query(url, **params):
     """Return *url* with the given query parameters added or overridden.
 
@@ -315,23 +501,24 @@ def api_request(method, url, auth_header, payload=None, *,
     """Make an authenticated JSON request to the Gitea API.
 
     Returns parsed JSON on success (or ``None`` for an empty body), and raises
-    ``RuntimeError`` on failure.
+    a classified client error on failure.
 
     On HTTP 429 the request is retried up to *max_retries* times: honoring a
     valid ``Retry-After`` header (seconds or HTTP-date) when present, otherwise
     using capped jittered exponential backoff. Successful responses are
     unchanged.
 
-    All failures are converted to a ``RuntimeError`` with a clear, secret
-    -redacted message (no raw stack traces or credential material):
+    Failures raise typed exceptions with **fixed messages only** (#699). HTTP
+    response bodies are read solely for local 403 reason refinement and are
+    never stored on exceptions or returned to callers:
 
-    - Non-429 HTTP errors surface the status code and a redacted response body.
-      502/503/504 upstream errors get an explicit "Gitea upstream unavailable"
-      message.
-    - Timeouts and network/DNS failures (``URLError`` / ``TimeoutError``) surface
-      a generic "network error contacting Gitea" message.
-    - A malformed (non-JSON) success body surfaces a "malformed JSON response"
-      message rather than a raw decode error.
+    - HTTP 401 → :class:`GiteaAuthError` (``auth_invalid_token``)
+    - HTTP 403 → :class:`GiteaAuthzError` (scope or denied)
+    - 502/503/504 → :class:`GiteaHttpError` (``upstream_unavailable``)
+    - Other non-429 HTTP → :class:`GiteaHttpError` (``http_error``)
+    - Timeouts / DNS / ``URLError`` → :class:`GiteaNetworkError`
+    - Malformed success JSON → plain ``RuntimeError`` (programming/protocol;
+      not reclassified as authentication)
 
     The ``*_func`` parameters and ``timeout`` are injection points for
     deterministic testing.
@@ -369,22 +556,23 @@ def api_request(method, url, auth_header, payload=None, *,
                 error_body = e.read().decode("utf-8", errors="replace")
             except Exception:
                 error_body = ""
-            detail = _redact(error_body).strip()
-            if e.code in (502, 503, 504):
-                msg = f"HTTP {e.code}: Gitea upstream unavailable"
-                raise RuntimeError(f"{msg}: {detail}" if detail else msg) from e
-            raise RuntimeError(f"HTTP {e.code}: {detail}") from e
+            # Classify from status (+ local body hint). Body is not embedded.
+            try:
+                raise_for_http_status(e.code, error_body)
+            except GiteaClientError:
+                raise
+            # Defensive: raise_for_http_status always raises.
+            raise GiteaHttpError(http_status=e.code) from e  # pragma: no cover
         except (urllib.error.URLError, TimeoutError) as e:
-            reason = getattr(e, "reason", e)
-            raise RuntimeError(
-                f"network error contacting Gitea: {_redact(reason)}"
-            ) from e
+            # Fixed message only — do not embed URLError reason (may leak paths).
+            raise GiteaNetworkError(reason_code="network_error") from e
 
         if not body:
             return None
         try:
             return json.loads(body)
         except ValueError as e:
+            # Programming/protocol failure — not authentication.
             raise RuntimeError("malformed JSON response from Gitea") from e
 
 

mcp_session_state.py

@@ -46,8 +46,15 @@ KIND_IRRECOVERABLE_DECISION_PROVENANCE = "irrecoverable_decision_provenance"
 KIND_IRRECOVERABLE_PROVENANCE_AUTH = "irrecoverable_provenance_authorization"
 
 # Kinds that must survive the default session-state TTL (forensic / recovery).
+#
+# KIND_DECISION_LOCK is recovery-critical (#720): terminal review provenance is
+# not disposable cache. A generic four-hour TTL must not drop old-head evidence
+# or make ``fresh_review_on_current_head_allowed`` unreachable. Same-head / same-
+# run #332 protections still apply once the ledger is loadable. Other session
+# kinds (workflow load, drafts, etc.) remain TTL-bound.
 RECOVERY_CRITICAL_KINDS = frozenset(
     {
+        KIND_DECISION_LOCK,
         KIND_DECISION_LOCK_ARCHIVE,
         KIND_POST_MERGE_DECISION_RECOVERY,
         KIND_IRRECOVERABLE_DECISION_PROVENANCE,
@@ -245,6 +252,16 @@ def _write_json(path: str, data: dict[str, Any]) -> None:
                 pass
 
 
+def is_recovery_critical_record(record: dict[str, Any] | None, kind: str | None = None) -> bool:
+    """True when a durable record must outlive the generic session-state TTL."""
+    if not record and not kind:
+        return False
+    record_kind = ((record or {}).get("kind") or kind or "").strip()
+    if record_kind in RECOVERY_CRITICAL_KINDS:
+        return True
+    return bool((record or {}).get("recovery_critical"))
+
+
 def identity_match_reasons(
     record: dict[str, Any] | None,
     *,
@@ -288,9 +305,7 @@ def identity_match_reasons(
     else:
         age = _now_utc() - recorded_at
         kind = (record.get("kind") or "").strip()
-        ttl_exempt = kind in RECOVERY_CRITICAL_KINDS or bool(
-            record.get("recovery_critical")
-        )
+        ttl_exempt = is_recovery_critical_record(record, kind=kind)
         if age > timedelta(hours=ttl_hours()) and not ttl_exempt:
             reasons.append(
                 f"session state expired after {ttl_hours():g}h (fail closed)"
@@ -300,6 +315,113 @@ def identity_match_reasons(
     return reasons
 
 
+def inspect_state_envelope(
+    *,
+    kind: str,
+    remote: str | None = None,
+    org: str | None = None,
+    repo: str | None = None,
+    profile_identity: str | None = None,
+    state_dir: str | None = None,
+) -> dict[str, Any]:
+    """Read-only disk inspection for assessment when TTL would otherwise hide state (#720).
+
+    Does **not** apply identity/TTL rejection to the returned presence flags.
+    Callers use this to distinguish:
+      * no file on disk
+      * file present but TTL would reject a non-critical kind
+      * recovery-critical ledger (e.g. KIND_DECISION_LOCK) still loadable
+    Never mutates files. Never returns secrets.
+    """
+    profile = current_profile_identity(profile_identity=profile_identity)
+    path = state_file_path(
+        kind=kind,
+        remote=remote,
+        org=org,
+        repo=repo,
+        profile_identity=profile,
+        state_dir=state_dir,
+    )
+    result: dict[str, Any] = {
+        "kind": kind,
+        "profile_identity": profile,
+        "path_basename": os.path.basename(path),
+        "on_disk": False,
+        "has_payload": False,
+        "recorded_at": None,
+        "updated_at": None,
+        "age_hours": None,
+        "ttl_hours": ttl_hours(),
+        "age_exceeds_default_ttl": False,
+        "recovery_critical": kind in RECOVERY_CRITICAL_KINDS,
+        "ttl_exempt": kind in RECOVERY_CRITICAL_KINDS,
+        "would_ttl_reject": False,
+        "identity_reasons": [],
+        "summary": "no session-state file on disk",
+    }
+    if not path or not os.path.exists(path):
+        return result
+    result["on_disk"] = True
+    envelope = _read_json(path)
+    if not envelope:
+        result["summary"] = "session-state file present but unreadable or empty"
+        return result
+    payload = envelope.get("payload")
+    merged: dict[str, Any] = dict(payload) if isinstance(payload, dict) else {}
+    result["has_payload"] = isinstance(payload, dict)
+    for key in (
+        "kind",
+        "remote",
+        "org",
+        "repo",
+        "profile_identity",
+        "session_profile_lock",
+        "recorded_at",
+        "updated_at",
+        "writer_pid",
+        "recovery_critical",
+    ):
+        if key in envelope and key not in merged:
+            merged[key] = envelope[key]
+    if not merged.get("kind"):
+        merged["kind"] = kind
+    recorded_at = _parse_iso(merged.get("recorded_at") or merged.get("updated_at"))
+    result["recorded_at"] = merged.get("recorded_at") or merged.get("updated_at")
+    result["updated_at"] = merged.get("updated_at") or merged.get("recorded_at")
+    if recorded_at is not None:
+        age = _now_utc() - recorded_at
+        age_hours = age.total_seconds() / 3600.0
+        result["age_hours"] = age_hours
+        result["age_exceeds_default_ttl"] = age > timedelta(hours=ttl_hours())
+    ttl_exempt = is_recovery_critical_record(merged, kind=kind)
+    result["recovery_critical"] = ttl_exempt
+    result["ttl_exempt"] = ttl_exempt
+    identity_reasons = identity_match_reasons(
+        merged,
+        remote=remote,
+        org=org,
+        repo=repo,
+        profile_identity=profile,
+    )
+    result["identity_reasons"] = list(identity_reasons)
+    result["would_ttl_reject"] = any("expired" in r for r in identity_reasons)
+    if result["has_payload"] and ttl_exempt:
+        result["summary"] = (
+            "recovery-critical session-state present on disk and TTL-exempt; "
+            "load via load_state for full payload"
+        )
+    elif result["has_payload"] and result["would_ttl_reject"]:
+        result["summary"] = (
+            "session-state file present on disk but generic TTL would reject load "
+            f"(age_hours={result.get('age_hours')!r}, ttl={ttl_hours():g}h)"
+        )
+    elif result["has_payload"]:
+        result["summary"] = "session-state file present and within TTL / identity gates"
+    else:
+        result["summary"] = "session-state file present without a dict payload"
+    return result
+
+
 def load_state(
     *,
     kind: str,

mcp_tool_error_boundary.py

@@ -0,0 +1,451 @@
+"""MCP tool-boundary error mapping for known Gitea client failures (#699).
+
+Known authentication / authorization / network / configuration failures leave
+the tool boundary as a sanitized structured ``CallToolResult`` with
+``isError=True``. Stdio transport remains connected.
+
+Design constraints (reviewer-ratified, #699 / PR #701):
+
+1. **No secret material** in tool results or daemon logs. Messages are fixed
+   constants keyed by ``reason_code``; HTTP bodies / exception text never
+   surface. Sanitization failure fails closed to ``internal_error``.
+2. **Narrow boundary** wraps the original FastMCP ``Tool.run`` success path;
+   re-raises framework control-flow exceptions (``UrlElicitationRequiredError``);
+   maps only typed client failures. Installation is idempotent.
+3. **No RuntimeError substring heuristics.** Only explicit typed
+   authentication / authorization / network / configuration exceptions
+   receive those labels.
+4. **HTTP classification** lives in ``gitea_auth.classify_http_status``;
+   every 403 is authorization-class.
+"""
+
+from __future__ import annotations
+
+import json
+import logging
+import sys
+from typing import Any
+
+logger = logging.getLogger("gitea_mcp.tool_error_boundary")
+
+# Stable reason codes (#699).
+REASON_AUTH_FAILED = "auth_failed"
+REASON_AUTH_INVALID_TOKEN = "auth_invalid_token"
+REASON_AUTHZ_INSUFFICIENT_SCOPE = "authz_insufficient_scope"
+REASON_AUTHZ_DENIED = "authz_denied"
+REASON_NETWORK_ERROR = "network_error"
+REASON_CONFIG_ERROR = "config_error"
+REASON_INTERNAL_ERROR = "internal_error"
+REASON_UPSTREAM_UNAVAILABLE = "upstream_unavailable"
+REASON_HTTP_ERROR = "http_error"
+
+ERROR_CLASS_AUTHENTICATION = "authentication"
+ERROR_CLASS_AUTHORIZATION = "authorization"
+ERROR_CLASS_NETWORK = "network"
+ERROR_CLASS_CONFIGURATION = "configuration"
+ERROR_CLASS_INTERNAL = "internal"
+ERROR_CLASS_UPSTREAM = "upstream"
+
+# Fixed, secret-free operator messages. Never interpolate HTTP bodies,
+# Keychain contents, tokens, or arbitrary exception text.
+FIXED_MESSAGES: dict[str, str] = {
+    REASON_AUTH_FAILED: "Gitea authentication failed",
+    REASON_AUTH_INVALID_TOKEN: (
+        "Gitea authentication failed: invalid or revoked credentials"
+    ),
+    REASON_AUTHZ_INSUFFICIENT_SCOPE: (
+        "Gitea authorization failed: insufficient token scope"
+    ),
+    REASON_AUTHZ_DENIED: "Gitea authorization failed: access denied",
+    REASON_NETWORK_ERROR: "Network error contacting Gitea",
+    REASON_CONFIG_ERROR: "Gitea configuration or credential resolution failed",
+    REASON_INTERNAL_ERROR: "Internal tool error",
+    REASON_UPSTREAM_UNAVAILABLE: "Gitea upstream unavailable",
+    REASON_HTTP_ERROR: "Gitea HTTP request failed",
+}
+
+_INSTALL_FLAG = "_gitea_auth_boundary_installed"
+_ORIGINAL_ATTR = "_gitea_auth_boundary_original"
+
+
+def fixed_message(reason_code: str) -> str:
+    """Return the fixed sanitized message for *reason_code* (fail closed)."""
+    return FIXED_MESSAGES.get(reason_code, FIXED_MESSAGES[REASON_INTERNAL_ERROR])
+
+
+def _safe_profile_name() -> str | None:
+    try:
+        from gitea_auth import get_profile
+
+        name = (get_profile() or {}).get("profile_name")
+        if name is None:
+            return None
+        text = str(name).strip()
+        # Profile names are non-secret identifiers; still bound length.
+        return text[:80] if text else None
+    except Exception:
+        return None
+
+
+def _is_framework_control_flow(exc: BaseException) -> bool:
+    """True for exceptions the MCP framework must re-raise unchanged."""
+    try:
+        from mcp.shared.exceptions import UrlElicitationRequiredError
+
+        if isinstance(exc, UrlElicitationRequiredError):
+            return True
+    except Exception:
+        pass
+    # BaseException subclasses that must never become tool isError payloads.
+    if isinstance(exc, (KeyboardInterrupt, SystemExit, GeneratorExit)):
+        return True
+    return False
+
+
+def is_known_client_failure(exc: BaseException) -> bool:
+    """True only for explicit typed Gitea client / config failures.
+
+    Never true for arbitrary ``RuntimeError`` (reviewer finding #3).
+    """
+    try:
+        import gitea_auth
+
+        if isinstance(
+            exc,
+            (
+                gitea_auth.GiteaAuthError,
+                gitea_auth.GiteaAuthzError,
+                gitea_auth.GiteaNetworkError,
+                gitea_auth.GiteaConfigError,
+                gitea_auth.GiteaHttpError,
+            ),
+        ):
+            return True
+    except Exception:
+        return False
+    try:
+        import gitea_config
+
+        if isinstance(exc, gitea_config.ConfigError):
+            return True
+    except Exception:
+        pass
+    return False
+
+
+def classify_exception(exc: BaseException) -> dict[str, Any]:
+    """Return structured classification with **fixed** messages only.
+
+    Only typed authentication / authorization / network / configuration
+    failures receive those labels. Unexpected programming failures are
+    ``internal_error``. HTTP bodies and exception text are never copied
+    into ``message``.
+    """
+    try:
+        return _classify_exception_impl(exc)
+    except Exception:
+        # Fail closed: sanitization / classification failure must not leak.
+        return {
+            "reason_code": REASON_INTERNAL_ERROR,
+            "error_class": ERROR_CLASS_INTERNAL,
+            "http_status": None,
+            "message": fixed_message(REASON_INTERNAL_ERROR),
+            "transport_survives": True,
+        }
+
+
+def _classify_exception_impl(exc: BaseException) -> dict[str, Any]:
+    import gitea_auth
+
+    if isinstance(exc, gitea_auth.GiteaAuthError):
+        code = getattr(exc, "reason_code", None) or REASON_AUTH_INVALID_TOKEN
+        if code not in (
+            REASON_AUTH_FAILED,
+            REASON_AUTH_INVALID_TOKEN,
+        ):
+            code = REASON_AUTH_INVALID_TOKEN
+        return {
+            "reason_code": code,
+            "error_class": ERROR_CLASS_AUTHENTICATION,
+            "http_status": getattr(exc, "http_status", None) or 401,
+            "message": fixed_message(code),
+            "transport_survives": True,
+        }
+    if isinstance(exc, gitea_auth.GiteaAuthzError):
+        code = getattr(exc, "reason_code", None) or REASON_AUTHZ_DENIED
+        if code not in (REASON_AUTHZ_DENIED, REASON_AUTHZ_INSUFFICIENT_SCOPE):
+            code = REASON_AUTHZ_DENIED
+        return {
+            "reason_code": code,
+            "error_class": ERROR_CLASS_AUTHORIZATION,
+            "http_status": getattr(exc, "http_status", None) or 403,
+            "message": fixed_message(code),
+            "transport_survives": True,
+        }
+    if isinstance(exc, gitea_auth.GiteaNetworkError):
+        return {
+            "reason_code": REASON_NETWORK_ERROR,
+            "error_class": ERROR_CLASS_NETWORK,
+            "http_status": getattr(exc, "http_status", None),
+            "message": fixed_message(REASON_NETWORK_ERROR),
+            "transport_survives": True,
+        }
+    if isinstance(exc, gitea_auth.GiteaConfigError):
+        return {
+            "reason_code": REASON_CONFIG_ERROR,
+            "error_class": ERROR_CLASS_CONFIGURATION,
+            "http_status": getattr(exc, "http_status", None),
+            "message": fixed_message(REASON_CONFIG_ERROR),
+            "transport_survives": True,
+        }
+    if isinstance(exc, gitea_auth.GiteaHttpError):
+        code = getattr(exc, "reason_code", None) or REASON_HTTP_ERROR
+        if code == REASON_UPSTREAM_UNAVAILABLE:
+            error_class = ERROR_CLASS_UPSTREAM
+        else:
+            error_class = ERROR_CLASS_INTERNAL
+            code = REASON_HTTP_ERROR
+        return {
+            "reason_code": code,
+            "error_class": error_class,
+            "http_status": getattr(exc, "http_status", None),
+            "message": fixed_message(code),
+            "transport_survives": True,
+        }
+
+    try:
+        import gitea_config
+
+        if isinstance(exc, gitea_config.ConfigError):
+            return {
+                "reason_code": REASON_CONFIG_ERROR,
+                "error_class": ERROR_CLASS_CONFIGURATION,
+                "http_status": None,
+                "message": fixed_message(REASON_CONFIG_ERROR),
+                "transport_survives": True,
+            }
+    except Exception:
+        pass
+
+    # Unwrap FastMCP ToolError cause when the original was a typed failure.
+    cause = getattr(exc, "__cause__", None)
+    if cause is not None and cause is not exc and is_known_client_failure(cause):
+        return _classify_exception_impl(cause)
+
+    # No message-substring authentication heuristics (reviewer finding #3).
+    return {
+        "reason_code": REASON_INTERNAL_ERROR,
+        "error_class": ERROR_CLASS_INTERNAL,
+        "http_status": None,
+        "message": fixed_message(REASON_INTERNAL_ERROR),
+        "transport_survives": True,
+    }
+
+
+def build_structured_error_payload(
+    classification: dict[str, Any],
+    *,
+    tool_name: str | None = None,
+    profile_name: str | None = None,
+) -> dict[str, Any]:
+    """LLM-safe structured payload — fixed message + typed metadata only."""
+    try:
+        reason = str(classification.get("reason_code") or REASON_INTERNAL_ERROR)
+        message = fixed_message(reason)
+        # Refuse to emit any classification message that is not the fixed constant.
+        if classification.get("message") != message:
+            message = fixed_message(reason)
+        payload: dict[str, Any] = {
+            "success": False,
+            "isError": True,
+            "reason_code": reason if reason in FIXED_MESSAGES else REASON_INTERNAL_ERROR,
+            "error_class": classification.get("error_class") or ERROR_CLASS_INTERNAL,
+            "message": message,
+            "transport_survives": True,
+            "retryable": classification.get("error_class")
+            in {
+                ERROR_CLASS_AUTHENTICATION,
+                ERROR_CLASS_NETWORK,
+                ERROR_CLASS_CONFIGURATION,
+            },
+        }
+        status = classification.get("http_status")
+        if isinstance(status, int):
+            payload["http_status"] = status
+        if tool_name and isinstance(tool_name, str):
+            # Tool names are identifiers, not secrets; bound length.
+            payload["tool"] = tool_name[:120]
+        if profile_name and isinstance(profile_name, str):
+            payload["profile"] = profile_name[:80]
+        return payload
+    except Exception:
+        return {
+            "success": False,
+            "isError": True,
+            "reason_code": REASON_INTERNAL_ERROR,
+            "error_class": ERROR_CLASS_INTERNAL,
+            "message": fixed_message(REASON_INTERNAL_ERROR),
+            "transport_survives": True,
+            "retryable": False,
+        }
+
+
+def log_sanitized_daemon_reason(
+    classification: dict[str, Any],
+    *,
+    tool_name: str | None = None,
+    stream=None,
+) -> None:
+    """Daemon log: reason codes only — never exception text or response bodies."""
+    stream = stream if stream is not None else sys.stderr
+    try:
+        reason = classification.get("reason_code") or REASON_INTERNAL_ERROR
+        error_class = classification.get("error_class") or ERROR_CLASS_INTERNAL
+        # Only emit known tokens; never classification['message'] from callers
+        # that might have been poisoned.
+        if reason not in FIXED_MESSAGES:
+            reason = REASON_INTERNAL_ERROR
+            error_class = ERROR_CLASS_INTERNAL
+        parts = [
+            "mcp_tool_error",
+            f"reason_code={reason}",
+            f"error_class={error_class}",
+        ]
+        if tool_name and isinstance(tool_name, str):
+            parts.append(f"tool={tool_name[:120]}")
+        status = classification.get("http_status")
+        if isinstance(status, int):
+            parts.append(f"http_status={status}")
+        # Intentionally no detail= / message= field — secrets lived there.
+        line = " ".join(parts)
+        stream.write(line + "\n")
+        if hasattr(stream, "flush"):
+            stream.flush()
+        logger.warning(line)
+    except Exception:
+        # Fail closed: never fall back to logging the exception.
+        try:
+            stream.write(
+                "mcp_tool_error reason_code=internal_error "
+                "error_class=internal\n"
+            )
+            if hasattr(stream, "flush"):
+                stream.flush()
+        except Exception:
+            pass
+
+
+def to_call_tool_result(
+    exc: BaseException,
+    *,
+    tool_name: str | None = None,
+    profile_name: str | None = None,
+    log: bool = True,
+) -> Any:
+    """Build a FastMCP ``CallToolResult`` with ``isError=True`` for *exc*."""
+    from mcp.types import CallToolResult, TextContent
+
+    try:
+        classification = classify_exception(exc)
+        if log:
+            log_sanitized_daemon_reason(classification, tool_name=tool_name)
+        payload = build_structured_error_payload(
+            classification, tool_name=tool_name, profile_name=profile_name
+        )
+        text = json.dumps(payload, indent=2, sort_keys=True)
+        return CallToolResult(
+            content=[TextContent(type="text", text=text)],
+            structuredContent=payload,
+            isError=True,
+        )
+    except Exception:
+        # Absolute fail-closed path — no exception text.
+        fallback = {
+            "success": False,
+            "isError": True,
+            "reason_code": REASON_INTERNAL_ERROR,
+            "error_class": ERROR_CLASS_INTERNAL,
+            "message": fixed_message(REASON_INTERNAL_ERROR),
+            "transport_survives": True,
+            "retryable": False,
+        }
+        return CallToolResult(
+            content=[
+                TextContent(
+                    type="text",
+                    text=json.dumps(fallback, indent=2, sort_keys=True),
+                )
+            ],
+            structuredContent=fallback,
+            isError=True,
+        )
+
+
+def install_tool_run_boundary(Tool) -> bool:
+    """Install a **narrow** error boundary around FastMCP ``Tool.run``.
+
+    Strategy (preserves framework semantics):
+
+    * Call the **original** ``Tool.run`` for the success path (async, return
+      types, convert_result, protocol behavior unchanged).
+    * Re-raise ``UrlElicitationRequiredError`` and other control-flow
+      exceptions without mapping to ``internal_error``.
+    * Map typed Gitea client failures (and ToolError whose ``__cause__`` is
+      typed) to structured ``CallToolResult(isError=True)``.
+    * Map remaining unexpected tool failures to fixed ``internal_error``
+      isError results (transport survival) without secret-bearing text.
+    * Idempotent: second install is a no-op and returns ``False``.
+    """
+    if getattr(Tool.run, _INSTALL_FLAG, False):
+        return False
+
+    from mcp.server.fastmcp.exceptions import ToolError
+    from mcp.shared.exceptions import UrlElicitationRequiredError
+
+    original_run = Tool.run
+
+    async def run_boundary(
+        self,
+        arguments: dict[str, Any],
+        context=None,
+        convert_result: bool = False,
+    ) -> Any:
+        try:
+            return await original_run(
+                self,
+                arguments,
+                context=context,
+                convert_result=convert_result,
+            )
+        except UrlElicitationRequiredError:
+            # Framework control-flow — must not become internal_error.
+            raise
+        except BaseException as exc:
+            if _is_framework_control_flow(exc):
+                raise
+            if not isinstance(exc, Exception):
+                raise
+
+            # Prefer typed cause under FastMCP ToolError wrappers.
+            target: BaseException = exc
+            if isinstance(exc, ToolError) and exc.__cause__ is not None:
+                target = exc.__cause__
+
+            # Known client failures → structured isError with reason codes.
+            # Unexpected failures → fixed internal_error isError (no secrets).
+            profile_name = _safe_profile_name()
+            return to_call_tool_result(
+                target,
+                tool_name=getattr(self, "name", None),
+                profile_name=profile_name,
+            )
+
+    setattr(run_boundary, _INSTALL_FLAG, True)
+    setattr(run_boundary, _ORIGINAL_ATTR, original_run)
+    Tool.run = run_boundary  # type: ignore[method-assign]
+    return True
+
+
+def boundary_is_installed(Tool) -> bool:
+    """True when the #699 boundary is active on *Tool.run*."""
+    return bool(getattr(Tool.run, _INSTALL_FLAG, False))

migrate_profiles.py

@@ -20,12 +20,114 @@ if PROJECT_ROOT not in sys.path:
 import gitea_config
 
 
-AUTHOR_DEFAULT_ALLOWED = ["read", "branch", "commit", "push", "open_pr", "comment"]
-AUTHOR_DEFAULT_FORBIDDEN = ["approve", "request_changes", "merge"]
-REVIEWER_DEFAULT_ALLOWED = [
-    "read", "review", "comment", "approve", "request_changes", "merge"
+# Defaults emit *canonical* operation names only. Shorthand that is not in
+# gitea_config.GITEA_OPERATION_ALIASES (e.g. ``pr.close``, ``issue.close``)
+# is silently dropped by the production loader and must never appear here.
+AUTHOR_DEFAULT_ALLOWED = [
+    "gitea.read",
+    "gitea.branch.create",
+    "gitea.repo.commit",
+    "gitea.branch.push",
+    "gitea.pr.create",
+    "gitea.pr.comment",
 ]
-REVIEWER_DEFAULT_FORBIDDEN = ["branch", "commit", "push", "open_pr"]
+AUTHOR_DEFAULT_FORBIDDEN = [
+    "gitea.pr.approve",
+    "gitea.pr.request_changes",
+    "gitea.pr.merge",
+]
+REVIEWER_DEFAULT_ALLOWED = [
+    "gitea.read",
+    "gitea.pr.review",
+    "gitea.pr.comment",
+    "gitea.pr.approve",
+    "gitea.pr.request_changes",
+    "gitea.pr.merge",
+]
+REVIEWER_DEFAULT_FORBIDDEN = [
+    "gitea.branch.create",
+    "gitea.repo.commit",
+    "gitea.branch.push",
+    "gitea.pr.create",
+]
+# Required reconciler ops (read + pr.close) plus recommended comment/close and
+# branch.delete for guarded merged-PR cleanup. All names must normalize via
+# gitea_config.normalize_operation without being dropped.
+RECONCILER_DEFAULT_ALLOWED = [
+    "gitea.read",
+    "gitea.pr.close",
+    "gitea.pr.comment",
+    "gitea.issue.comment",
+    "gitea.issue.close",
+    "gitea.branch.delete",
+]
+RECONCILER_DEFAULT_FORBIDDEN = [
+    "gitea.pr.approve",
+    "gitea.pr.merge",
+    "gitea.pr.review",
+    "gitea.pr.create",
+    "gitea.branch.push",
+    "gitea.repo.commit",
+]
+
+# Migration-only expansions for common shorthands that are *not* in
+# GITEA_OPERATION_ALIASES. Emitted output is always the canonical form so a
+# second canonicalize pass is a no-op (idempotent).
+_MIGRATION_ONLY_ALIASES = {
+    "pr.close": "gitea.pr.close",
+    "pr.comment": "gitea.pr.comment",
+    "issue.close": "gitea.issue.close",
+    "branch.delete": "gitea.branch.delete",
+}
+
+# Reconciler required ops that must survive migration (from reconciler_profile).
+RECONCILER_REQUIRED_CANONICAL = ("gitea.read", "gitea.pr.close")
+
+
+def canonicalize_operation(op: str) -> str:
+    """Return a canonical operation name accepted by the production loader.
+
+    Fail closed on unknown/ambiguous spellings so required permissions cannot
+    be silently dropped by ``check_operation`` later.
+    """
+    if not isinstance(op, str) or not op.strip():
+        raise ValueError("operation must be a non-empty string (fail closed)")
+    op = op.strip()
+    try:
+        return gitea_config.normalize_operation(op)
+    except gitea_config.ConfigError:
+        pass
+    if op in _MIGRATION_ONLY_ALIASES:
+        return _MIGRATION_ONLY_ALIASES[op]
+    raise ValueError(
+        f"operation {op!r} cannot be canonicalized for migration "
+        "(unknown/ambiguous; fail closed — production loader would drop it)"
+    )
+
+
+def canonicalize_operations(ops, *, context: str = "operations") -> list[str]:
+    """Canonicalize a list of operations; preserve order, drop duplicates."""
+    if not isinstance(ops, list):
+        raise ValueError(f"{context} must be a list (fail closed)")
+    out: list[str] = []
+    seen: set[str] = set()
+    for entry in ops:
+        canon = canonicalize_operation(entry)
+        if canon not in seen:
+            seen.add(canon)
+            out.append(canon)
+    return out
+
+
+def _assert_reconciler_required_survive(allowed: list[str], profile_name: str) -> None:
+    """Fail visibly when migration would leave a reconciler without required ops."""
+    missing = [op for op in RECONCILER_REQUIRED_CANONICAL if op not in set(allowed)]
+    if missing:
+        raise ValueError(
+            f"Profile '{profile_name}' (reconciler) is missing required "
+            f"operation(s) after migration: {missing}. Refusing to emit a "
+            "profile that would silently fail pr.close / read (fail closed)."
+        )
 
 
 def infer_role(name, execution_profile):
@@ -90,9 +192,11 @@ def migrate_v1_to_v2(v1_data):
             ident_name = "reviewer"
         elif role == "author":
             ident_name = "author"
+        elif role == "reconciler":
+            ident_name = "reconciler"
         else:
             role = prof.get("role")
-            if role not in (None, "author", "reviewer"):
+            if role not in (None, "author", "reviewer", "reconciler"):
                 raise ValueError(
                     f"Profile '{name}' has unsupported role {role!r}"
                 )
@@ -124,20 +228,35 @@ def migrate_v1_to_v2(v1_data):
                 raise ValueError(
                     f"Profile '{name}' operation fields must be lists"
                 )
-            identity_data["allowed_operations"] = list(allowed)
-            identity_data["forbidden_operations"] = list(forbidden)
+            try:
+                identity_data["allowed_operations"] = canonicalize_operations(
+                    allowed, context=f"profile '{name}' allowed_operations"
+                )
+                identity_data["forbidden_operations"] = canonicalize_operations(
+                    forbidden, context=f"profile '{name}' forbidden_operations"
+                )
+            except ValueError as exc:
+                raise ValueError(f"Profile '{name}': {exc}") from exc
         elif role == "author":
             identity_data["allowed_operations"] = list(AUTHOR_DEFAULT_ALLOWED)
             identity_data["forbidden_operations"] = list(AUTHOR_DEFAULT_FORBIDDEN)
         elif role == "reviewer":
             identity_data["allowed_operations"] = list(REVIEWER_DEFAULT_ALLOWED)
             identity_data["forbidden_operations"] = list(REVIEWER_DEFAULT_FORBIDDEN)
+        elif role == "reconciler":
+            identity_data["allowed_operations"] = list(RECONCILER_DEFAULT_ALLOWED)
+            identity_data["forbidden_operations"] = list(RECONCILER_DEFAULT_FORBIDDEN)
         else:
             raise ValueError(
                 f"Profile '{name}' has no explicit operation lists and no "
                 "unambiguous author/reviewer role marker (fail closed)"
             )
 
+        if role == "reconciler":
+            _assert_reconciler_required_survive(
+                identity_data["allowed_operations"], name
+            )
+
         # Nest inside environments/services structure
         env = environments.setdefault(env_name, {})
         services = env.setdefault("services", {})

pr_sync_status.py

@@ -0,0 +1,648 @@
+"""PR synchronization and conflict-remediation lifecycle (#PR-SYNC).
+
+Pure assessment helpers for:
+
+* ``gitea_assess_pr_sync_status`` — recommend the next sanctioned action for an
+  open PR when the base branch advances, approvals go stale, or conflicts appear.
+* ``gitea_update_pr_branch_by_merge`` preflight — author-only, fail-closed pin
+  of both PR head and live base head; never rebase/force-push.
+
+All recommendation logic is hermetic (no network) so unit tests cover every
+acceptance path without Gitea credentials.
+"""
+
+from __future__ import annotations
+
+import re
+from typing import Any
+
+_FULL_SHA = re.compile(r"^[0-9a-f]{40}$", re.IGNORECASE)
+
+# Recommended next actions (controller / skill vocabulary).
+ACTION_MERGE_NOW = "merge_now"
+ACTION_UPDATE_BRANCH_BY_MERGE = "update_branch_by_merge"
+ACTION_AUTHOR_CONFLICT_REMEDIATION = "author_conflict_remediation"
+ACTION_FRESH_REVIEW_REQUIRED = "fresh_review_required"
+ACTION_BLOCKED = "blocked"
+
+_VALID_ACTIONS = frozenset({
+    ACTION_MERGE_NOW,
+    ACTION_UPDATE_BRANCH_BY_MERGE,
+    ACTION_AUTHOR_CONFLICT_REMEDIATION,
+    ACTION_FRESH_REVIEW_REQUIRED,
+    ACTION_BLOCKED,
+})
+
+# Author-only mutation; reviewer/merger must never update author branches.
+_AUTHOR_UPDATE_ROLES = frozenset({"author"})
+_DENIED_UPDATE_ROLES = frozenset({"reviewer", "merger", "reconciler", "mixed", "limited"})
+
+# Allowed Gitea update style — merge only (never rebase).
+UPDATE_STYLE_MERGE = "merge"
+_FORBIDDEN_UPDATE_STYLES = frozenset({"rebase", "rebase-merge", "squash", "force"})
+
+
+def _normalize_sha(value: str | None) -> str | None:
+    text = (value or "").strip().lower()
+    if not text:
+        return None
+    return text if _FULL_SHA.match(text) else None
+
+
+def _normalize_role(role: str | None) -> str:
+    return (role or "").strip().lower() or "unknown"
+
+
+def assess_pr_sync_status(
+    *,
+    host: str | None = None,
+    org: str | None = None,
+    repo: str | None = None,
+    pr_number: int,
+    pr_state: str | None = None,
+    source_branch: str | None = None,
+    pr_head_sha: str | None = None,
+    base_head_sha: str | None = None,
+    commits_behind: int | None = None,
+    mergeable: bool | None = None,
+    has_conflicts: bool | None = None,
+    branch_protection_requires_current_base: bool | None = None,
+    approval_at_current_head: bool | None = None,
+    checks_status: str | None = None,
+    active_author_lock: bool | None = None,
+    active_reviewer_lease: bool | None = None,
+    active_merger_lease: bool | None = None,
+    prepared_verdict_head_sha: str | None = None,
+    checks_required: bool = True,
+) -> dict[str, Any]:
+    """Recommend the next sanctioned PR lifecycle action.
+
+    Decision order (fail closed):
+
+    1. Incomplete identity / open state / head SHAs → ``blocked``
+    2. Conflicts (or mergeable false with conflict signal) →
+       ``author_conflict_remediation``
+    3. Head changed after approval / prepared verdict for former head →
+       ``fresh_review_required`` (unless conflicts already routed author work)
+    4. Behind live base + branch protection requires current base +
+       auto-mergeable → ``update_branch_by_merge``
+    5. Approval at current head + mergeable + checks ok (+ update not
+       required) → ``merge_now``
+    6. Otherwise ``blocked`` with structured reasons
+    """
+    reasons: list[str] = []
+    pr_head = _normalize_sha(pr_head_sha)
+    base_head = _normalize_sha(base_head_sha)
+    prepared_head = _normalize_sha(prepared_verdict_head_sha)
+    state = (pr_state or "").strip().lower()
+    checks = (checks_status or "unknown").strip().lower()
+    behind = commits_behind if isinstance(commits_behind, int) and commits_behind >= 0 else None
+    requires_current = bool(branch_protection_requires_current_base)
+    approval_ok = bool(approval_at_current_head)
+
+    # Derive conflict when caller only supplies mergeable=False.
+    if has_conflicts is None and mergeable is False:
+        has_conflicts = True
+    conflicts = bool(has_conflicts) if has_conflicts is not None else None
+
+    result: dict[str, Any] = {
+        "host": (host or "").strip() or None,
+        "org": (org or "").strip() or None,
+        "repo": (repo or "").strip() or None,
+        "pr_number": pr_number,
+        "pr_state": state or None,
+        "source_branch": (source_branch or "").strip() or None,
+        "pr_head_sha": pr_head,
+        "base_head_sha": base_head,
+        "commits_behind": behind,
+        "mergeable": mergeable,
+        "has_conflicts": conflicts,
+        "branch_protection_requires_current_base": requires_current,
+        "approval_at_current_head": approval_ok if approval_at_current_head is not None else None,
+        "checks_status": checks,
+        "active_locks_and_leases": {
+            "author_lock": bool(active_author_lock) if active_author_lock is not None else None,
+            "reviewer_lease": bool(active_reviewer_lease) if active_reviewer_lease is not None else None,
+            "merger_lease": bool(active_merger_lease) if active_merger_lease is not None else None,
+        },
+        "prepared_verdict_head_sha": prepared_head,
+        "recommended_next_action": ACTION_BLOCKED,
+        "approval_valid_for_merge": False,
+        "stale_approval": False,
+        "stale_prepared_verdict": False,
+        "reasons": reasons,
+        "success": True,
+        "performed": False,
+    }
+
+    if not isinstance(pr_number, int) or pr_number <= 0:
+        reasons.append("pr_number must be a positive integer (fail closed)")
+        return result
+
+    if state and state not in ("open",):
+        reasons.append(f"PR is not open (state={state}); cannot synchronize or merge")
+        result["recommended_next_action"] = ACTION_BLOCKED
+        return result
+    if not state:
+        reasons.append("PR state missing (fail closed)")
+        return result
+
+    if pr_head is None:
+        reasons.append(
+            "exact PR head SHA missing or not a full 40-char hex SHA (fail closed)"
+        )
+    if base_head is None:
+        reasons.append(
+            "exact live base head SHA missing or not a full 40-char hex SHA (fail closed)"
+        )
+    if behind is None:
+        reasons.append("commits_behind missing or invalid (fail closed)")
+    if mergeable is None:
+        reasons.append("mergeable signal missing (fail closed)")
+    if approval_at_current_head is None:
+        reasons.append("approval_at_current_head missing (fail closed)")
+    if branch_protection_requires_current_base is None:
+        reasons.append(
+            "branch_protection_requires_current_base missing (fail closed)"
+        )
+
+    if reasons:
+        result["recommended_next_action"] = ACTION_BLOCKED
+        return result
+
+    # Stale prepared verdict / approval across heads.
+    stale_prepared = bool(prepared_head and prepared_head != pr_head)
+    result["stale_prepared_verdict"] = stale_prepared
+    stale_approval = not approval_ok
+    result["stale_approval"] = stale_approval
+    result["approval_valid_for_merge"] = bool(approval_ok and not stale_prepared)
+
+    # ── Conflicts: author remediation in dedicated worktree ──────────────
+    if conflicts is True or mergeable is False:
+        if conflicts is True or mergeable is False:
+            # Distinguish pure non-mergeable without explicit conflict flag
+            # still routes author remediation (Gitea cannot auto-update).
+            reasons.append(
+                f"PR #{pr_number} has conflicts or is not mergeable at head "
+                f"{pr_head}; route author conflict remediation in the existing "
+                "issue/PR worktree under branches/ (never force-push or rebase)"
+            )
+            if stale_approval:
+                reasons.append(
+                    "any approval at a former head is invalid; after remediation "
+                    "require a fresh independent review at the new exact head"
+                )
+            result["recommended_next_action"] = ACTION_AUTHOR_CONFLICT_REMEDIATION
+            result["approval_valid_for_merge"] = False
+            return result
+
+    # ── Stale approval / prepared verdict at former head ─────────────────
+    if not approval_ok or stale_prepared:
+        if behind and behind > 0 and requires_current and mergeable is True:
+            # Must update first; update will also invalidate approval.
+            reasons.append(
+                f"PR is {behind} commit(s) behind live base and branch protection "
+                "requires current base; automatic merge-from-base is available"
+            )
+            reasons.append(
+                "approval is not valid at the current head (or prepared verdict "
+                "is head-scoped to a former SHA); after update require fresh review"
+            )
+            result["recommended_next_action"] = ACTION_UPDATE_BRANCH_BY_MERGE
+            result["approval_valid_for_merge"] = False
+            return result
+        reasons.append(
+            "approval is not valid at the exact current PR head "
+            f"({pr_head}); never reuse a former-head approval for merge"
+        )
+        if stale_prepared:
+            reasons.append(
+                f"prepared verdict pinned to former head {prepared_head} cannot "
+                f"authorize review/merge at current head {pr_head}"
+            )
+        if active_reviewer_lease:
+            reasons.append(
+                "active reviewer lease must be released or superseded for the "
+                "new head before a fresh independent review"
+            )
+        if active_merger_lease:
+            reasons.append(
+                "active merger lease cannot cross heads; release or re-acquire "
+                "at the new exact head"
+            )
+        result["recommended_next_action"] = ACTION_FRESH_REVIEW_REQUIRED
+        result["approval_valid_for_merge"] = False
+        return result
+
+    # ── Outdated + protection requires current base, auto-updatable ──────
+    if behind and behind > 0 and requires_current:
+        if mergeable is True and conflicts is not True:
+            reasons.append(
+                f"PR is {behind} commit(s) behind live base {base_head}; "
+                "branch protection requires the PR branch to contain current base; "
+                "Gitea can merge base into the PR branch without conflicts"
+            )
+            reasons.append(
+                "route author-only update_branch_by_merge; never rebase or force-push; "
+                "new head invalidates prior approval and requires fresh independent review"
+            )
+            result["recommended_next_action"] = ACTION_UPDATE_BRANCH_BY_MERGE
+            # Approval today is at old head that will change — not mergeable yet
+            # for final merge until re-reviewed, but assess marks update path.
+            result["approval_valid_for_merge"] = False
+            result["stale_approval"] = True  # will become stale after update
+            return result
+        reasons.append(
+            "update required by branch protection but automatic merge is not available"
+        )
+        result["recommended_next_action"] = ACTION_BLOCKED
+        return result
+
+    # ── Checks gate for merge_now ────────────────────────────────────────
+    if checks_required and checks not in ("success", "passed", "ok", "none", "skipped", "not_required"):
+        if checks in ("pending", "running", "queued"):
+            reasons.append(f"required checks are not finished (status={checks})")
+            result["recommended_next_action"] = ACTION_BLOCKED
+            return result
+        if checks in ("failure", "failed", "error", "cancelled"):
+            reasons.append(f"required checks failed (status={checks})")
+            result["recommended_next_action"] = ACTION_BLOCKED
+            return result
+        # unknown — fail closed when checks_required
+        if checks == "unknown":
+            reasons.append("checks status unknown (fail closed)")
+            result["recommended_next_action"] = ACTION_BLOCKED
+            return result
+
+    # ── Ready to merge without update ────────────────────────────────────
+    # Includes: current with approval; outdated when update is NOT required.
+    if approval_ok and mergeable is True and conflicts is not True:
+        if behind and behind > 0 and not requires_current:
+            reasons.append(
+                f"PR is {behind} commit(s) behind live base but branch protection "
+                "does not require the latest base; preserve the approved head"
+            )
+        else:
+            reasons.append(
+                "PR has a valid approval at the exact current head, is conflict-free "
+                "and mergeable; do not update the branch unnecessarily"
+            )
+        reasons.append("route directly to the sanctioned merger workflow (merge_now)")
+        result["recommended_next_action"] = ACTION_MERGE_NOW
+        result["approval_valid_for_merge"] = True
+        return result
+
+    reasons.append("no sanctioned next action matched the observed PR state (fail closed)")
+    result["recommended_next_action"] = ACTION_BLOCKED
+    return result
+
+
+def assess_update_pr_branch_preflight(
+    *,
+    role_kind: str | None,
+    expected_pr_head_sha: str | None,
+    live_pr_head_sha: str | None,
+    expected_base_head_sha: str | None,
+    live_base_head_sha: str | None,
+    has_conflicts: bool | None = None,
+    mergeable: bool | None = None,
+    style: str | None = UPDATE_STYLE_MERGE,
+    has_author_lock: bool | None = None,
+    worktree_path: str | None = None,
+    worktree_owns_source_branch: bool | None = None,
+    control_checkout_clean: bool | None = None,
+    master_parity_ok: bool | None = None,
+    force_push: bool = False,
+    rebase: bool = False,
+) -> dict[str, Any]:
+    """Author-only preflight for update-by-merge; fail closed on any race.
+
+    When conflicts exist, returns a structured author-remediation handoff and
+    sets ``mutation_allowed=False`` so no partial remote update is performed.
+    """
+    reasons: list[str] = []
+    role = _normalize_role(role_kind)
+    exp_pr = _normalize_sha(expected_pr_head_sha)
+    live_pr = _normalize_sha(live_pr_head_sha)
+    exp_base = _normalize_sha(expected_base_head_sha)
+    live_base = _normalize_sha(live_base_head_sha)
+    style_norm = (style or "").strip().lower() or UPDATE_STYLE_MERGE
+
+    conflicts = has_conflicts
+    if conflicts is None and mergeable is False:
+        conflicts = True
+
+    result: dict[str, Any] = {
+        "mutation_allowed": False,
+        "performed": False,
+        "style": style_norm,
+        "role_kind": role,
+        "expected_pr_head_sha": exp_pr,
+        "live_pr_head_sha": live_pr,
+        "expected_base_head_sha": exp_base,
+        "live_base_head_sha": live_base,
+        "head_race": False,
+        "base_race": False,
+        "has_conflicts": conflicts,
+        "author_remediation_handoff": False,
+        "approval_invalidated_for_former_head": False,
+        "force_push": bool(force_push),
+        "rebase": bool(rebase),
+        "reasons": reasons,
+        "success": True,
+    }
+
+    # Role gate — author only.
+    if role not in _AUTHOR_UPDATE_ROLES:
+        reasons.append(
+            f"role '{role}' cannot update an author PR branch "
+            "(author-only; reviewer/merger denial)"
+        )
+        return result
+
+    if force_push:
+        reasons.append("force-push is forbidden for PR branch update (fail closed)")
+        return result
+    if rebase or style_norm in _FORBIDDEN_UPDATE_STYLES:
+        reasons.append(
+            f"update style '{style_norm}' forbidden; only style=merge is allowed "
+            "(never rebase)"
+        )
+        return result
+    if style_norm != UPDATE_STYLE_MERGE:
+        reasons.append(
+            f"unknown update style '{style_norm}'; expected '{UPDATE_STYLE_MERGE}'"
+        )
+        return result
+
+    if not exp_pr or not live_pr:
+        reasons.append(
+            "expected and live PR head SHAs must be full 40-char hex (fail closed)"
+        )
+    if not exp_base or not live_base:
+        reasons.append(
+            "expected and live base head SHAs must be full 40-char hex (fail closed)"
+        )
+    if reasons:
+        return result
+
+    if exp_pr != live_pr:
+        result["head_race"] = True
+        reasons.append(
+            f"PR head race: expected {exp_pr} but live is {live_pr} "
+            "(fail closed; no partial mutation)"
+        )
+        return result
+    if exp_base != live_base:
+        result["base_race"] = True
+        reasons.append(
+            f"base head race: expected {exp_base} but live is {live_base} "
+            "(fail closed; no partial mutation)"
+        )
+        return result
+
+    if has_author_lock is not True:
+        reasons.append(
+            "existing issue/PR lock required before update_branch_by_merge (fail closed)"
+        )
+    wt = (worktree_path or "").strip()
+    if not wt:
+        reasons.append("existing PR worktree path required under branches/ (fail closed)")
+    else:
+        norm = wt.replace("\\", "/")
+        if "/branches/" not in norm and not norm.startswith("branches/"):
+            reasons.append(
+                f"worktree_path '{wt}' must be under branches/ (fail closed)"
+            )
+    if worktree_owns_source_branch is False:
+        reasons.append(
+            "worktree does not own the PR source branch (fail closed)"
+        )
+    if control_checkout_clean is False:
+        reasons.append("control checkout is not clean (fail closed)")
+    if master_parity_ok is False:
+        reasons.append("runtime/master parity failed (fail closed)")
+
+    if conflicts is True:
+        result["author_remediation_handoff"] = True
+        reasons.append(
+            "conflicts present: return structured author-remediation handoff "
+            "without creating a partial remote update"
+        )
+        reasons.append(
+            "resolve conflicts explicitly in the existing dedicated worktree, "
+            "run focused and regression tests, commit/push via sanctioned author "
+            "workflow, then route the new exact head to independent review"
+        )
+        return result
+
+    if mergeable is False and conflicts is not False:
+        result["author_remediation_handoff"] = True
+        reasons.append(
+            "PR is not mergeable; refuse automatic update and hand off to "
+            "author conflict remediation (fail closed)"
+        )
+        return result
+
+    if reasons:
+        return result
+
+    result["mutation_allowed"] = True
+    reasons.append(
+        "preflight passed: author may merge live base into the PR branch via "
+        "native MCP update (style=merge only)"
+    )
+    return result
+
+
+def assess_post_update_head_transition(
+    *,
+    former_pr_head_sha: str | None,
+    new_pr_head_sha: str | None,
+    former_approval_head_sha: str | None = None,
+    former_reviewer_lease_head_sha: str | None = None,
+    former_merger_lease_head_sha: str | None = None,
+    prepared_verdict_head_sha: str | None = None,
+) -> dict[str, Any]:
+    """After a successful update-by-merge, invalidate cross-head artifacts.
+
+    The new head never inherits approval, reviewer/merger leases, or prepared
+    verdicts from the former head.
+    """
+    former = _normalize_sha(former_pr_head_sha)
+    new = _normalize_sha(new_pr_head_sha)
+    reasons: list[str] = []
+    result: dict[str, Any] = {
+        "former_pr_head_sha": former,
+        "new_pr_head_sha": new,
+        "head_changed": bool(former and new and former != new),
+        "approval_invalidated": False,
+        "reviewer_lease_superseded": False,
+        "merger_lease_superseded": False,
+        "prepared_verdict_invalidated": False,
+        "recommended_next_action": ACTION_BLOCKED,
+        "reasons": reasons,
+        "success": True,
+    }
+
+    if not former or not new:
+        reasons.append("former and new PR head SHAs required (fail closed)")
+        return result
+    if former == new:
+        reasons.append(
+            "PR head unchanged after update; unexpected for merge-from-base"
+        )
+        result["recommended_next_action"] = ACTION_BLOCKED
+        return result
+
+    result["head_changed"] = True
+    # Approval at former head is always void at new head.
+    former_approval = _normalize_sha(former_approval_head_sha) or former
+    if former_approval != new:
+        result["approval_invalidated"] = True
+        reasons.append(
+            f"approval for former head {former_approval} is invalid at new head "
+            f"{new}; never preserve approval across a head change"
+        )
+
+    rev_lease = _normalize_sha(former_reviewer_lease_head_sha)
+    if rev_lease and rev_lease != new:
+        result["reviewer_lease_superseded"] = True
+        reasons.append(
+            f"reviewer lease for head {rev_lease} cannot cross to {new}; "
+            "release or supersede before fresh review"
+        )
+    elif rev_lease is None:
+        # Unknown lease head still must not authorize at new head.
+        result["reviewer_lease_superseded"] = True
+        reasons.append(
+            "any reviewer lease scoped to the former head is superseded at the new head"
+        )
+
+    mer_lease = _normalize_sha(former_merger_lease_head_sha)
+    if mer_lease and mer_lease != new:
+        result["merger_lease_superseded"] = True
+        reasons.append(
+            f"merger lease for head {mer_lease} cannot cross to {new}"
+        )
+    else:
+        result["merger_lease_superseded"] = True
+        reasons.append(
+            "any merger lease scoped to the former head is superseded at the new head"
+        )
+
+    prepared = _normalize_sha(prepared_verdict_head_sha)
+    if prepared and prepared != new:
+        result["prepared_verdict_invalidated"] = True
+        reasons.append(
+            f"prepared verdict for head {prepared} cannot authorize the new head {new}"
+        )
+    elif prepared is None:
+        result["prepared_verdict_invalidated"] = True
+        reasons.append(
+            "prepared verdicts associated with the former head are invalidated"
+        )
+
+    result["recommended_next_action"] = ACTION_FRESH_REVIEW_REQUIRED
+    reasons.append(
+        "route the new exact head to independent review "
+        f"({ACTION_FRESH_REVIEW_REQUIRED})"
+    )
+    return result
+
+
+def assess_sequential_queue_step(
+    *,
+    just_merged: bool,
+    master_refreshed: bool,
+    next_pr_number: int | None = None,
+) -> dict[str, Any]:
+    """Controller sequential processing: reassess only after merge + master refresh."""
+    reasons: list[str] = []
+    if just_merged and not master_refreshed:
+        reasons.append(
+            "master must be refreshed after each merge before reassessing the next PR "
+            "(do not update every PR simultaneously)"
+        )
+        return {
+            "reassess_allowed": False,
+            "process_next": False,
+            "next_pr_number": next_pr_number,
+            "reasons": reasons,
+            "success": True,
+        }
+    if not just_merged:
+        reasons.append("no merge completed; sequential step does not advance")
+        return {
+            "reassess_allowed": False,
+            "process_next": False,
+            "next_pr_number": next_pr_number,
+            "reasons": reasons,
+            "success": True,
+        }
+    if next_pr_number:
+        reasons.append(
+            "merge completed and live master refreshed; reassess the next PR "
+            f"#{next_pr_number}"
+        )
+    else:
+        reasons.append(
+            "merge completed and live master refreshed; reassess the next PR"
+        )
+    return {
+        "reassess_allowed": True,
+        "process_next": True,
+        "next_pr_number": next_pr_number,
+        "post_merge_cleanup_handoff": True,
+        "reasons": reasons,
+        "success": True,
+    }
+
+
+def merge_approval_usable_at_head(
+    *,
+    current_head_sha: str | None,
+    approved_head_sha: str | None,
+) -> dict[str, Any]:
+    """Stale approval cannot authorize merge (head-scoped only)."""
+    current = _normalize_sha(current_head_sha)
+    approved = _normalize_sha(approved_head_sha)
+    ok = bool(current and approved and current == approved)
+    reasons: list[str] = []
+    if not ok:
+        reasons.append(
+            f"stale approval: approved head '{approved or '(none)'}' does not "
+            f"match current head '{current or '(none)'}'; cannot authorize merge"
+        )
+    return {
+        "approval_usable": ok,
+        "current_head_sha": current,
+        "approved_head_sha": approved,
+        "reasons": reasons,
+    }
+
+
+def lease_usable_at_head(
+    *,
+    lease_kind: str,
+    lease_head_sha: str | None,
+    current_head_sha: str | None,
+) -> dict[str, Any]:
+    """Reviewer/merger leases cannot cross heads."""
+    current = _normalize_sha(current_head_sha)
+    lease_head = _normalize_sha(lease_head_sha)
+    kind = (lease_kind or "").strip().lower() or "unknown"
+    ok = bool(current and lease_head and current == lease_head)
+    reasons: list[str] = []
+    if not ok:
+        reasons.append(
+            f"stale {kind} lease: lease head '{lease_head or '(none)'}' cannot "
+            f"authorize work at current head '{current or '(none)'}'"
+        )
+    return {
+        "lease_usable": ok,
+        "lease_kind": kind,
+        "lease_head_sha": lease_head,
+        "current_head_sha": current,
+        "reasons": reasons,
+    }

reconciler_profile.py

@@ -18,6 +18,11 @@ RECONCILER_RECOMMENDED_OPERATIONS = (
     "gitea.pr.comment",
     "gitea.issue.comment",
     "gitea.issue.close",
+    # Merged-branch cleanup is reconciler-owned (task_capability_map maps
+    # cleanup_merged_pr_branch -> reconciler). The permission is only
+    # exercisable through the guarded gitea_cleanup_merged_pr_branch path
+    # (#514): merged proof, protected-branch refusal, explicit confirmation.
+    "gitea.branch.delete",
 )
 
 RECONCILER_FORBIDDEN_OPERATIONS = (

requirements.txt

@@ -31,6 +31,7 @@ python-multipart==0.0.32
 referencing==0.37.0
 rich==15.0.0
 rpds-py==2026.5.1
+sentry-sdk==2.20.0
 shellingham==1.5.4
 sse-starlette==3.4.5
 starlette==1.3.1

sentry_observability.py

@@ -0,0 +1,535 @@
+"""Optional self-hosted Sentry observability for the Gitea MCP server (#606).
+
+Adds env-var-gated Sentry SDK instrumentation so runtime errors, fail-closed
+workflow blockers, lease/terminal-lock/stale-runtime collisions, and recurring
+watchdog check-ins are visible in a *self-hosted* Sentry at
+``https://sentry.prgs.cc/`` — never Sentry Cloud, and never as the workflow
+source of truth (Gitea stays canonical).
+
+Design constraints (mirror ``gitea_audit`` and the #612 incident bridge):
+
+- **Off by default.** With ``MCP_SENTRY_ENABLED`` false/unset *or* ``SENTRY_DSN``
+  empty, ``init_sentry`` is a no-op and no events are ever sent — existing tool
+  behaviour and API-call patterns are unchanged (acceptance criterion 1).
+- **Fail *open* for observability.** A Sentry outage, a missing ``sentry_sdk``
+  package, or any capture error must never break an MCP tool success path. Every
+  public entry point swallows its own exceptions.
+- **Fail *closed* for redaction.** If a field cannot be proven safe it is dropped
+  rather than sent. Tokens, passwords, keychain IDs, DSNs, private config, raw
+  session-state, full prompt bodies, and full filesystem paths never leave here.
+- **No hard dependency.** ``sentry_sdk`` is imported lazily; the module is fully
+  importable and testable without it installed.
+
+Sentry is observe-only: it must not approve, merge, close, or otherwise mutate
+Gitea workflow state, nor bypass leases, #332, or MCP gates. Alerts may only feed
+the sanctioned Gitea issue/comment path via the #612 incident bridge.
+"""
+
+from __future__ import annotations
+
+import hashlib
+import os
+import re
+from dataclasses import dataclass
+from typing import Any
+
+# Reuse the most comprehensive existing scrubber so redaction stays consistent
+# with the #612 incident bridge (tokens, DSNs, cookies, bearer/basic, keychain
+# ids, session ids, user:pass@host).
+from incident_bridge import redact_text as _redact_text
+
+# Second, complementary scrubber: catches bare ``token <value>`` /
+# ``Bearer <value>`` / ``Basic <value>`` prefixes and raw URLs that the
+# incident-bridge delimiter patterns miss.
+from gitea_audit import _redact_str as _redact_prefixes
+
+# ── Optional SDK (lazy, never a hard dependency) ────────────────────────────
+try:  # pragma: no cover - trivial import guard
+    import sentry_sdk  # type: ignore
+except Exception:  # pragma: no cover - absence is a supported state
+    sentry_sdk = None  # type: ignore
+
+
+# ── Env var names (single source of truth) ──────────────────────────────────
+ENV_ENABLED = "MCP_SENTRY_ENABLED"
+ENV_DSN = "SENTRY_DSN"
+ENV_ENVIRONMENT = "SENTRY_ENVIRONMENT"
+ENV_RELEASE = "SENTRY_RELEASE"
+ENV_TRACES_SAMPLE_RATE = "MCP_SENTRY_TRACES_SAMPLE_RATE"
+ENV_ENABLE_LOGS = "MCP_SENTRY_ENABLE_LOGS"
+
+_TRUTHY = frozenset({"1", "true", "yes", "on"})
+
+REDACTED = "[REDACTED]"
+REDACTED_PATH = "[REDACTED_PATH]"
+
+
+# ── Cron / watchdog monitor slugs (acceptance criterion 6) ──────────────────
+# Stable slugs for the recurring/watchdog jobs #606 wants check-ins for. The
+# slug is the durable monitor identity in Sentry; the wiring call sites pass one
+# of these keys (or an explicit slug) to ``monitor_checkin``.
+MONITOR_SLUGS: dict[str, str] = {
+    "stale_lease_scan": "gitea-mcp-stale-lease-scan",
+    "terminal_lock_scan": "gitea-mcp-terminal-lock-scan",
+    "allocator_health": "gitea-mcp-allocator-health",
+    "namespace_health": "gitea-mcp-namespace-health",
+    "dashboard_freshness": "gitea-mcp-dashboard-freshness",
+    "reconciler_cleanup": "gitea-mcp-reconciler-cleanup",
+}
+
+_CHECKIN_STATUSES = frozenset({"in_progress", "ok", "error"})
+
+
+# ── Tag allowlist (issue "Suggested Sentry tags/context") ───────────────────
+# Only these keys are ever attached as Sentry tags. Anything else is dropped so
+# a caller cannot accidentally leak a sensitive value through a tag.
+ALLOWED_TAG_KEYS = frozenset({
+    "role",
+    "profile",
+    "namespace",
+    "repo",
+    "org",
+    "issue_number",
+    "pr_number",
+    "blocker_type",
+    "workflow_hash",
+    "session_id_hash",  # hash only — never the raw session id
+    "pid",
+    "worktree_category",  # category, never the full sensitive path
+    "lease_comment_id",
+    "expected_head_sha",
+    "current_head_sha",
+    "terminal_lock_state",
+    "capability",
+    "mutation_tool",
+})
+
+# Absolute-path shapes that must never be sent verbatim (macOS/Linux + temp).
+_PATH_RE = re.compile(r"(?:/private)?/(?:Users|home|tmp|var|opt|Volumes)/[^\s\"']*")
+
+# ``extra`` keys whose *full* contents are forbidden by the redaction rules
+# (raw session-state, full prompt/comment bodies, private config blobs, raw
+# headers).
+_FORBIDDEN_EXTRA_KEYS = frozenset({
+    "prompt",
+    "prompt_body",
+    "next_prompt",
+    "body",
+    "raw_body",
+    "session_state",
+    "session_state_contents",
+    "config",
+    "config_contents",
+    "private_config",
+    "headers",
+    "authorization",
+})
+
+
+# ── Configuration ───────────────────────────────────────────────────────────
+@dataclass(frozen=True)
+class SentryConfig:
+    """Immutable snapshot of the Sentry env configuration."""
+
+    enabled: bool = False
+    dsn: str | None = None
+    environment: str = "development"
+    release: str | None = None
+    traces_sample_rate: float = 0.0
+    enable_logs: bool = False
+
+    @property
+    def active(self) -> bool:
+        """True only when the operator both opted in *and* supplied a DSN.
+
+        This is the single gate that keeps the feature off by default: enabling
+        the flag without a DSN (or vice versa) sends nothing.
+        """
+        return bool(self.enabled and self.dsn)
+
+    def safe_summary(self) -> dict[str, Any]:
+        """Operator-facing status with **no** DSN value (only presence)."""
+        return {
+            "enabled": self.enabled,
+            "dsn_present": bool(self.dsn),
+            "environment": self.environment,
+            "release": self.release,
+            "traces_sample_rate": self.traces_sample_rate,
+            "enable_logs": self.enable_logs,
+            "active": self.active,
+        }
+
+
+def _env_bool(name: str, env: dict[str, str]) -> bool:
+    return (env.get(name) or "").strip().lower() in _TRUTHY
+
+
+def _env_float(name: str, default: float, env: dict[str, str]) -> float:
+    raw = (env.get(name) or "").strip()
+    if not raw:
+        return default
+    try:
+        val = float(raw)
+    except (TypeError, ValueError):
+        return default
+    # Clamp to Sentry's valid [0.0, 1.0] sample-rate range.
+    if val < 0.0:
+        return 0.0
+    if val > 1.0:
+        return 1.0
+    return val
+
+
+def load_config(env: dict[str, str] | None = None) -> SentryConfig:
+    """Build a :class:`SentryConfig` from the environment (read at call time)."""
+    env = dict(os.environ if env is None else env)
+    dsn = (env.get(ENV_DSN) or "").strip() or None
+    return SentryConfig(
+        enabled=_env_bool(ENV_ENABLED, env),
+        dsn=dsn,
+        environment=(env.get(ENV_ENVIRONMENT) or "").strip() or "development",
+        release=(env.get(ENV_RELEASE) or "").strip() or None,
+        traces_sample_rate=_env_float(ENV_TRACES_SAMPLE_RATE, 0.0, env),
+        enable_logs=_env_bool(ENV_ENABLE_LOGS, env),
+    )
+
+
+def sdk_available() -> bool:
+    """True when the optional ``sentry_sdk`` package is importable."""
+    return sentry_sdk is not None
+
+
+# ── Redaction (fail closed) ─────────────────────────────────────────────────
+def sanitize_path(value: Any) -> str:
+    """Reduce a filesystem path to a non-sensitive *category* token.
+
+    Full local paths must never be sent. We keep only a coarse worktree
+    category derived from the path shape (author/reviewer/merger/reconciler/
+    branches/root/other).
+    """
+    text = "" if value is None else str(value)
+    low = text.lower()
+    if not text:
+        return "unknown"
+    # Order matters: more specific role markers before the generic "branches".
+    if "reconcile" in low:
+        return "reconciler"
+    if "review" in low:
+        return "reviewer"
+    if "merge" in low or "merger" in low:
+        return "merger"
+    if "author" in low or re.search(r"/branches/(?:feat|fix|docs|chore|issue)", low):
+        return "author"
+    if "/branches/" in low:
+        return "branches"
+    if low.rstrip("/").endswith("gitea-tools"):
+        return "root"
+    return "other"
+
+
+def redact_value(value: Any) -> Any:
+    """Recursively redact a JSON-able value: secret text, absolute paths, and
+    known-sensitive dict keys are removed. Fail closed — any error drops the
+    value entirely rather than risk leaking it."""
+    try:
+        if isinstance(value, dict):
+            out: dict[str, Any] = {}
+            for k, v in value.items():
+                key = str(k)
+                low = key.lower()
+                if low in _FORBIDDEN_EXTRA_KEYS or any(
+                    s in low
+                    for s in ("token", "secret", "password", "cookie", "auth", "dsn", "keychain")
+                ):
+                    out[key] = REDACTED
+                    continue
+                out[key] = redact_value(v)
+            return out
+        if isinstance(value, (list, tuple)):
+            return [redact_value(v) for v in value]
+        if isinstance(value, str):
+            scrubbed = _redact_text(value)
+            scrubbed = _redact_prefixes(scrubbed)
+            scrubbed = _PATH_RE.sub(REDACTED_PATH, scrubbed)
+            return scrubbed
+        return value
+    except Exception:
+        return REDACTED
+
+
+def hash_session_id(session_id: Any) -> str:
+    """Short, stable, non-reversible fingerprint of a session id."""
+    digest = hashlib.sha256(str(session_id).encode("utf-8", "replace")).hexdigest()
+    return digest[:12]
+
+
+def build_tags(**kwargs: Any) -> dict[str, str]:
+    """Return a scrubbed, allowlisted tag dict.
+
+    ``session_id`` is accepted but only ever surfaced as ``session_id_hash``.
+    ``worktree_path`` collapses to ``worktree_category``. Any non-allowlisted
+    key, or a value that still contains redacted material after scrubbing, is
+    dropped.
+    """
+    raw: dict[str, Any] = dict(kwargs)
+
+    # Hash the session id — never emit it raw.
+    session_id = raw.pop("session_id", None)
+    if session_id and "session_id_hash" not in raw:
+        raw["session_id_hash"] = hash_session_id(session_id)
+
+    # A full worktree path collapses to a category tag.
+    wt = raw.pop("worktree_path", None)
+    if wt and "worktree_category" not in raw:
+        raw["worktree_category"] = sanitize_path(wt)
+
+    out: dict[str, str] = {}
+    for key, val in raw.items():
+        if key not in ALLOWED_TAG_KEYS:
+            continue
+        if val is None:
+            continue
+        scrubbed = redact_value(val)
+        text = str(scrubbed)
+        if not text or REDACTED in text or REDACTED_PATH in text:
+            continue
+        if len(text) > 200:
+            text = text[:200] + "…"
+        out[key] = text
+    return out
+
+
+def scrub_event(event: Any, hint: Any = None) -> dict[str, Any] | None:
+    """Sentry ``before_send`` / ``before_send_log`` hook.
+
+    Recursively redacts the outgoing event. On *any* failure it returns ``None``
+    so the event is dropped rather than sent unscrubbed (fail closed for
+    redaction).
+    """
+    try:
+        if not isinstance(event, dict):
+            return None
+        scrubbed = redact_value(event)
+        # Drop server_name if it leaked a hostname/path; PID is kept via tags.
+        scrubbed.pop("server_name", None)
+        return scrubbed
+    except Exception:
+        return None
+
+
+# ── Event builders (pure, independently testable) ───────────────────────────
+def build_blocker_event(
+    blocker_type: str,
+    *,
+    message: str | None = None,
+    next_action: str | None = None,
+    level: str = "warning",
+    tags: dict[str, Any] | None = None,
+    extra: dict[str, Any] | None = None,
+) -> dict[str, Any]:
+    """Build a redacted, structured Sentry event for a workflow blocker.
+
+    ``next_action`` maps the issue's "canonical next action when available"
+    requirement (acceptance criterion 7).
+    """
+    merged_tags = dict(tags or {})
+    merged_tags.setdefault("blocker_type", blocker_type)
+    safe_tags = build_tags(**merged_tags)
+
+    safe_extra = redact_value(dict(extra or {}))
+    if next_action:
+        # A short canonical next action is allowed (it is not a full prompt).
+        safe_extra["canonical_next_action"] = redact_value(str(next_action)[:500])
+
+    event: dict[str, Any] = {
+        "message": redact_value(message or blocker_type),
+        "level": level if level in ("debug", "info", "warning", "error", "fatal") else "warning",
+        "logger": "gitea-mcp.workflow",
+        "tags": safe_tags,
+        "extra": safe_extra,
+        "fingerprint": ["workflow-blocker", blocker_type],
+    }
+    return event
+
+
+def build_checkin_payload(
+    monitor: str,
+    status: str,
+    *,
+    check_in_id: str | None = None,
+    duration: float | None = None,
+) -> dict[str, Any]:
+    """Build a Sentry cron check-in payload for one of :data:`MONITOR_SLUGS`.
+
+    ``monitor`` may be a registry key (e.g. ``"stale_lease_scan"``) or an
+    explicit slug. Raises ``ValueError`` on an unknown status so callers cannot
+    silently send a malformed check-in.
+    """
+    if status not in _CHECKIN_STATUSES:
+        raise ValueError(
+            f"invalid check-in status {status!r}; expected one of {sorted(_CHECKIN_STATUSES)}"
+        )
+    slug = MONITOR_SLUGS.get(monitor, monitor)
+    payload: dict[str, Any] = {"monitor_slug": slug, "status": status}
+    if check_in_id:
+        payload["check_in_id"] = str(check_in_id)
+    if duration is not None:
+        try:
+            payload["duration"] = float(duration)
+        except (TypeError, ValueError):
+            pass
+    return payload
+
+
+# ── Runtime init + capture (fail open) ──────────────────────────────────────
+_STATE: dict[str, Any] = {"initialized": False, "config": None}
+
+
+def is_initialized() -> bool:
+    return bool(_STATE.get("initialized"))
+
+
+def active_config() -> SentryConfig | None:
+    return _STATE.get("config")
+
+
+def reset_for_tests() -> None:
+    """Clear module init state. Test-only helper (never called in production)."""
+    _STATE["initialized"] = False
+    _STATE["config"] = None
+
+
+def init_sentry(config: SentryConfig | None = None) -> dict[str, Any]:
+    """Initialise the Sentry SDK if (and only if) enabled + DSN + SDK present.
+
+    Idempotent and never raises. Returns an operator-safe status dict (no DSN
+    value). Behaviour is unchanged when the feature is off.
+    """
+    cfg = config or load_config()
+    status: dict[str, Any] = {"initialized": False, **cfg.safe_summary()}
+    try:
+        if not cfg.active:
+            status["reason"] = "disabled (MCP_SENTRY_ENABLED false or SENTRY_DSN empty)"
+            _STATE["config"] = cfg
+            return status
+        if not sdk_available():
+            status["reason"] = "sentry_sdk not installed"
+            _STATE["config"] = cfg
+            return status
+
+        init_kwargs: dict[str, Any] = {
+            "dsn": cfg.dsn,
+            "environment": cfg.environment,
+            "release": cfg.release,
+            "traces_sample_rate": cfg.traces_sample_rate,
+            "before_send": scrub_event,
+            "send_default_pii": False,
+        }
+        if cfg.enable_logs:
+            # sentry-sdk 2.x captures Python logs as structured logs when the
+            # experimental logs feature is enabled; scrub those too.
+            init_kwargs["_experiments"] = {
+                "enable_logs": True,
+                "before_send_log": scrub_event,
+            }
+        sentry_sdk.init(**init_kwargs)  # type: ignore[union-attr]
+        _STATE["initialized"] = True
+        _STATE["config"] = cfg
+        status["initialized"] = True
+        status["reason"] = "sentry initialised"
+    except Exception as exc:  # fail open: observability must not block startup
+        status["reason"] = f"init failed (ignored): {type(exc).__name__}"
+        _STATE["initialized"] = False
+    return status
+
+
+def _set_scope_tags(scope: Any, tags: dict[str, str]) -> None:
+    for key, val in tags.items():
+        try:
+            scope.set_tag(key, val)
+        except Exception:
+            pass
+
+
+def capture_workflow_blocker(
+    blocker_type: str,
+    *,
+    message: str | None = None,
+    next_action: str | None = None,
+    level: str = "warning",
+    tags: dict[str, Any] | None = None,
+    extra: dict[str, Any] | None = None,
+) -> dict[str, Any]:
+    """Capture a fail-closed workflow blocker as a structured Sentry event.
+
+    Always returns the redacted event dict (so callers/tests can inspect it),
+    and sends it to Sentry only when initialised. Fail open.
+    """
+    event = build_blocker_event(
+        blocker_type,
+        message=message,
+        next_action=next_action,
+        level=level,
+        tags=tags,
+        extra=extra,
+    )
+    try:
+        if is_initialized() and sdk_available():
+            sentry_sdk.capture_event(event)  # type: ignore[union-attr]
+    except Exception:
+        pass
+    return event
+
+
+def capture_exception(
+    exc: BaseException,
+    *,
+    tags: dict[str, Any] | None = None,
+    extra: dict[str, Any] | None = None,
+) -> bool:
+    """Capture a runtime exception with scrubbed tags. Fail open.
+
+    Returns True only when the event was handed to an initialised SDK.
+    """
+    try:
+        if not (is_initialized() and sdk_available()):
+            return False
+        safe_tags = build_tags(**(tags or {}))
+        safe_extra = redact_value(dict(extra or {}))
+        with sentry_sdk.push_scope() as scope:  # type: ignore[union-attr]
+            _set_scope_tags(scope, safe_tags)
+            for key, val in safe_extra.items():
+                try:
+                    scope.set_extra(key, val)
+                except Exception:
+                    pass
+            sentry_sdk.capture_exception(exc)  # type: ignore[union-attr]
+        return True
+    except Exception:
+        return False
+
+
+def monitor_checkin(
+    monitor: str,
+    status: str,
+    *,
+    check_in_id: str | None = None,
+    duration: float | None = None,
+) -> dict[str, Any] | None:
+    """Send a Sentry cron check-in for a watchdog job. Fail open.
+
+    Returns the payload (for inspection/tests), or ``None`` if the status was
+    invalid. Only transmits when initialised.
+    """
+    try:
+        payload = build_checkin_payload(
+            monitor, status, check_in_id=check_in_id, duration=duration
+        )
+    except ValueError:
+        return None
+    try:
+        if is_initialized() and sdk_available() and hasattr(sentry_sdk, "capture_checkin"):
+            sentry_sdk.capture_checkin(**payload)  # type: ignore[union-attr]
+    except Exception:
+        pass
+    return payload

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

@@ -33,22 +33,34 @@ Steps:
    *If the current identity does not match the required role (or is the PR author), STOP. Relaunch/switch to the correct profile first.*
 2. Verify authenticated identity + active profile.
 3. Confirm PR #<pr>: author (not you), state open, mergeable, review approved. Check if PR body uses `Closes #N` or `Fixes #N`; if it uses `Implements #N` or `Refs #N`, manual closing will be needed in step 29.
-4. Capability evidence (#179): cite the exact gitea_resolve_task_capability
+4. **PR sync assess (required):** call `gitea_assess_pr_sync_status` with
+   explicit `remote`/`org`/`repo`. Route on `recommended_next_action`:
+   - `merge_now` → continue merger path (do **not** update the branch)
+   - `update_branch_by_merge` → STOP; hand off to **author** for
+     `gitea_update_pr_branch_by_merge` (pins expected PR head + base head)
+   - `author_conflict_remediation` → STOP; author worktree conflict fix
+   - `fresh_review_required` → STOP; independent re-review at current head
+   - `blocked` → STOP and diagnose
+   Never merge on a former-head approval after update/remediation.
+5. Capability evidence (#179): cite the exact gitea_resolve_task_capability
    output (or runtime context) proving merge_pr is allowed — a bare
    "capability checks passed" claim is downgraded.
-5. Final live-state recheck (#179), immediately before the merge mutation —
+6. Final live-state recheck (#179), immediately before the merge mutation —
    re-read the live PR and prove:
    - PR still open
    - live head SHA still equals the pinned/reviewed head SHA
    - base branch unchanged
    - no undismissed REQUEST_CHANGES / blocking review state remains
    If any recheck fails → STOP, re-pin, re-validate.
-6. If any gate fails → STOP and report.
-7. Merge with explicit confirmation (e.g. confirmation="MERGE PR <pr>"),
+7. If any gate fails → STOP and report.
+8. Merge with explicit confirmation (e.g. confirmation="MERGE PR <pr>"),
    pinning the reviewed head SHA (expected_head_sha) and, where supported,
    the changed-file set.
-8. Confirm remote master now contains the merge commit (or the expected changes if squash merged).
+9. Confirm remote master now contains the merge commit (or the expected changes if squash merged).
    *Note: Gitea PR "closed" state is NOT equivalent to "merged". Do not assume a closed PR succeeded without verifying the actual landed changes.*
+10. **Sequential queue:** after merge, refresh live `master`, run post-merge
+    cleanup handoff, then reassess the **next** PR (do not batch-update all
+    open PRs).
 
 Post-merge cleanup (#517): merger sessions must NOT perform ad hoc cleanup.
 - Record merge mutations separately from cleanup mutations in the controller handoff.

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

@@ -950,9 +950,53 @@ Final reports must state:
 * final live head SHA before merge
 * whether any push occurred during validation
 
+## 26D. PR synchronization and conflict-remediation lifecycle
+
+**Do not treat “approved” as the final readiness state.** For every approved
+open PR, call `gitea_assess_pr_sync_status` (native MCP only) and route by
+`recommended_next_action`:
+
+| Action | Meaning | Next role / tools |
+|--------|---------|-------------------|
+| `merge_now` | Valid approval at exact current head; conflict-free; update not required; checks ok | Merger: sanctioned merge workflow only — **do not** update the branch |
+| `update_branch_by_merge` | Behind live base; protection requires current base; Gitea can merge base without conflicts | **Author only:** `gitea_update_pr_branch_by_merge` with pinned `expected_pr_head_sha` + `expected_base_head_sha` |
+| `author_conflict_remediation` | Conflicts / not auto-updatable | **Author only:** existing `branches/` worktree, issue lock, merge master, resolve, test, push; never force-push/rebase |
+| `fresh_review_required` | Head changed after approval, or update/remediation produced a new head | Independent reviewer at the **new exact head**; old approvals/leases/verdicts are void |
+| `blocked` | Other gate (checks, incomplete facts, closed PR, …) | Diagnose; do not merge or update |
+
+### Hard rules
+
+* Pin both expected PR head and expected base head for every update. Either
+  race → fail closed with no partial mutation.
+* Never rebase or force-push author branches.
+* Never update an author branch from a reviewer or merger profile.
+* Never preserve approval, reviewer lease, merger lease, or prepared verdict
+  across a head change.
+* Process PRs **sequentially**: synchronize/remediate one → review new head →
+  merge → refresh live `master` → reassess the next PR. Do not update every
+  open PR at once (each merge restales the rest).
+* Conflict remediation only in the existing dedicated issue/PR worktree under
+  `branches/`. Do not delete that worktree until the updated PR is merged and
+  cleanup eligibility is proven.
+* Post-merge: canonical cleanup handoff to reconciler (section 28).
+
+### After `gitea_update_pr_branch_by_merge` succeeds
+
+1. Treat former-head approval as invalidated.
+2. Release/supersede obsolete reviewer and merger leases.
+3. Route `recommended_next_action=fresh_review_required` at the new head.
+4. Independent re-review, then merger lease/adopt + merge at the new head only.
+
+All Gitea reads/mutations use native MCP. Never substitute direct API, curl,
+tea/gh, Web UI mutation by an LLM, database changes, raw Git push, or token
+access.
+
 ## 27. Merge rules
 
-Before merge, rerun fresh live checks:
+Before merge, call `gitea_assess_pr_sync_status` when the PR is approved/open
+and may be behind base. Only proceed with merge when
+`recommended_next_action` is `merge_now` and approval remains at the current
+head. Then rerun fresh live checks:
 
 * whoami
 * active profile/runtime

task_capability_map.py

@@ -64,6 +64,24 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
         "permission": "gitea.branch.push",
         "role": "author",
     },
+    # PR synchronization lifecycle: assess is read-only (any role with gitea.read);
+    # update-by-merge is author-only and mutates the PR head via Gitea API.
+    "assess_pr_sync_status": {
+        "permission": "gitea.read",
+        "role": "author",
+    },
+    "gitea_assess_pr_sync_status": {
+        "permission": "gitea.read",
+        "role": "author",
+    },
+    "update_pr_branch_by_merge": {
+        "permission": "gitea.branch.push",
+        "role": "author",
+    },
+    "gitea_update_pr_branch_by_merge": {
+        "permission": "gitea.branch.push",
+        "role": "author",
+    },
     "review_pr": {
         "permission": "gitea.pr.review",
         "role": "reviewer",
@@ -84,7 +102,7 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
     },
     "adopt_merger_pr_lease": {
         "permission": "gitea.pr.comment",
-        "role": "reviewer",
+        "role": "merger",
     },
     # #691: guarded non-owner cleanup of obsolete comment-backed reviewer leases.
     # Apply path posts lease release + audit comments (gitea.pr.comment).

tests/test_api_reliability.py

@@ -79,41 +79,46 @@ class TestApiRequestFailures(unittest.TestCase):
     @patch("gitea_auth.urllib.request.urlopen")
     def test_timeout_converted_to_runtimeerror(self, mock_open):
         mock_open.side_effect = TimeoutError("timed out")
-        with self.assertRaises(RuntimeError) as ctx:
+        with self.assertRaises(gitea_auth.GiteaNetworkError) as ctx:
             gitea_auth.api_request("GET", URL, FAKE_AUTH)
-        self.assertIn("network error contacting Gitea", str(ctx.exception))
+        # Fixed message only (#699) — still a RuntimeError subclass.
+        self.assertIsInstance(ctx.exception, RuntimeError)
+        self.assertEqual(str(ctx.exception), "Network error contacting Gitea")
 
     @patch("gitea_auth.urllib.request.urlopen")
     def test_dns_network_failure_converted(self, mock_open):
         mock_open.side_effect = urllib.error.URLError("Name or service not known")
-        with self.assertRaises(RuntimeError) as ctx:
+        with self.assertRaises(gitea_auth.GiteaNetworkError) as ctx:
             gitea_auth.api_request("GET", URL, FAKE_AUTH)
-        self.assertIn("network error contacting Gitea", str(ctx.exception))
+        self.assertEqual(str(ctx.exception), "Network error contacting Gitea")
 
     @patch("gitea_auth.urllib.request.urlopen")
     def test_502_upstream_message(self, mock_open):
         mock_open.side_effect = http_error(502, "bad gateway")
-        with self.assertRaises(RuntimeError) as ctx:
+        with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
             gitea_auth.api_request("GET", URL, FAKE_AUTH)
         msg = str(ctx.exception)
-        self.assertIn("HTTP 502", msg)
-        self.assertIn("upstream unavailable", msg)
+        self.assertEqual(msg, "Gitea upstream unavailable")
+        self.assertEqual(ctx.exception.reason_code, "upstream_unavailable")
+        self.assertEqual(ctx.exception.http_status, 502)
 
     @patch("gitea_auth.urllib.request.urlopen")
     def test_503_upstream_message(self, mock_open):
         mock_open.side_effect = http_error(503, "")
-        with self.assertRaises(RuntimeError) as ctx:
+        with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
             gitea_auth.api_request("GET", URL, FAKE_AUTH)
-        self.assertIn("HTTP 503", str(ctx.exception))
-        self.assertIn("upstream unavailable", str(ctx.exception))
+        self.assertEqual(str(ctx.exception), "Gitea upstream unavailable")
+        self.assertEqual(ctx.exception.http_status, 503)
 
     @patch("gitea_auth.urllib.request.urlopen")
     def test_malformed_error_payload_does_not_crash(self, mock_open):
-        # Non-JSON garbage error body must still yield a clean RuntimeError.
+        # Non-JSON garbage error body must still yield a clean typed error
+        # with a fixed message (no body echo — #699).
         mock_open.side_effect = http_error(500, "<html>garbage</html>")
-        with self.assertRaises(RuntimeError) as ctx:
+        with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
             gitea_auth.api_request("GET", URL, FAKE_AUTH)
-        self.assertIn("HTTP 500", str(ctx.exception))
+        self.assertEqual(str(ctx.exception), "Gitea HTTP request failed")
+        self.assertNotIn("<html>", str(ctx.exception))
 
     @patch("gitea_auth.urllib.request.urlopen")
     def test_malformed_success_json_raises_clean_error(self, mock_open):
@@ -126,16 +131,17 @@ class TestApiRequestFailures(unittest.TestCase):
     def test_no_secret_leak_in_error_body(self, mock_open):
         mock_open.side_effect = http_error(
             400, "failed: token supersecret123 rejected")
-        with self.assertRaises(RuntimeError) as ctx:
+        with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
             gitea_auth.api_request("GET", URL, FAKE_AUTH)
         msg = str(ctx.exception)
         self.assertNotIn("supersecret123", msg)
-        self.assertIn(gitea_audit.REDACTED, msg)
+        # Fixed message — body never appears (stronger than redaction).
+        self.assertEqual(msg, "Gitea HTTP request failed")
 
     @patch("gitea_auth.urllib.request.urlopen")
     def test_auth_header_never_in_error(self, mock_open):
         mock_open.side_effect = http_error(400, "bad request")
-        with self.assertRaises(RuntimeError) as ctx:
+        with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
             gitea_auth.api_request("GET", URL, FAKE_AUTH)
         self.assertNotIn(FAKE_AUTH, str(ctx.exception))
 

tests/test_audit_reconciliation_mode.py

@@ -27,7 +27,13 @@ from task_capability_map import required_permission, required_role
 
 DELETE_PROFILE = {
     "profile_name": "prgs-author-delete",
-    "allowed_operations": ["gitea.read", "gitea.branch.delete"],
+    "role": "author",
+    "allowed_operations": [
+        "gitea.read",
+        "gitea.pr.create",
+        "gitea.branch.push",
+        "gitea.branch.delete",
+    ],
     "forbidden_operations": [],
     "audit_label": "prgs-author-delete",
 }

tests/test_issue_720_expired_decision_lock.py

@@ -0,0 +1,499 @@
+"""#720: Expired old-head KIND_DECISION_LOCK must not block fresh review.
+
+Reproduction shape (PR #616):
+  * REQUEST_CHANGES terminal at head A
+  * open PR advanced to head B
+  * durable decision lock age > default 4h TTL
+  * fresh_review_on_current_head_allowed is true but unreachable under TTL-first reject
+  * mark_final fails with "session state expired after 4h"
+  * assessment may report "no lock" while the file remains on disk
+
+Security invariants preserved:
+  * same-head second terminal remains fail-closed (#332/#620)
+  * REQUEST_CHANGES is never treated as approval
+  * historical mutations remain on the ledger
+  * merged/closed moot cleanup still allowed (#594)
+  * irrecoverable provenance still requires #709 authorization
+  * ordinary profiles do not gain gitea.decision_lock.irrecoverable_recovery
+"""
+
+from __future__ import annotations
+
+import os
+import tempfile
+import unittest
+from datetime import datetime, timedelta, timezone
+from pathlib import Path
+from unittest.mock import patch
+
+import sys
+
+ROOT = str(Path(__file__).resolve().parent.parent)
+if ROOT not in sys.path:
+    sys.path.insert(0, ROOT)
+
+import mcp_session_state as ss
+import mcp_server
+import stale_review_decision_lock as srdl
+import task_capability_map
+
+HEAD_A = "a0fffae576673ba7df7456b32e6aec916581bdfb"
+HEAD_B = "a6a2243aad9c3e385fc70509f4941a0f0ec33162"
+HEAD_SAME = HEAD_A
+
+RC_616_A = {
+    "pr_number": 616,
+    "action": "request_changes",
+    "review_id": 443,
+    "review_state": "request_changes",
+    "head_sha": HEAD_A,
+}
+
+
+def _lock(mutations=None, **kwargs):
+    base = {
+        "task": "review_pr",
+        "kind": ss.KIND_DECISION_LOCK,
+        "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": kwargs.get("ready_pr"),
+        "ready_action": kwargs.get("ready_action"),
+        "ready_expected_head_sha": kwargs.get("ready_head"),
+        "ready_remote": "prgs" if kwargs.get("ready_pr") else None,
+        "ready_org": "Scaled-Tech-Consulting" if kwargs.get("ready_pr") else None,
+        "ready_repo": "Gitea-Tools" if kwargs.get("ready_pr") else None,
+        "live_mutations": list(mutations or []),
+        "correction_authorized": False,
+        "correction_reason": None,
+    }
+    return base
+
+
+def _open_pr(pr_number=616, head=HEAD_B, merged=False, closed=False):
+    state = "closed" if closed or merged else "open"
+    return {
+        "number": pr_number,
+        "state": state,
+        "merged": merged,
+        "merged_at": "2026-07-16T12:00:00Z" if merged else None,
+        "merge_commit_sha": "m" * 40 if merged else None,
+        "head": {"sha": head},
+    }
+
+
+def _no_lease():
+    return {"block": False, "reasons": [], "mutation_allowed": True}
+
+
+def _feedback(blocking=False, stale=True):
+    return {
+        "success": True,
+        "has_blocking_change_requests": blocking,
+        "review_feedback_stale": stale,
+        "current_head_sha": HEAD_B,
+    }
+
+
+def _age_lock_payload(lock: dict, hours: float = 5.0) -> dict:
+    """Rewrite timestamps to *hours* ago (simulates durable age without touching prod)."""
+    aged = (datetime.now(timezone.utc) - timedelta(hours=hours)).isoformat().replace(
+        "+00:00", "Z"
+    )
+    out = dict(lock)
+    out["recorded_at"] = aged
+    out["updated_at"] = aged
+    return out
+
+
+class TestIssue720ExpiredDecisionLockLifecycle(unittest.TestCase):
+    def setUp(self):
+        self._tmp = tempfile.TemporaryDirectory()
+        self.env = patch.dict(
+            os.environ,
+            {
+                ss.STATE_DIR_ENV: self._tmp.name,
+                ss.SESSION_PROFILE_LOCK_ENV: "prgs-reviewer",
+                "GITEA_MCP_PROFILE": "prgs-reviewer",
+                "GITEA_PROFILE_NAME": "prgs-reviewer",
+            },
+            clear=False,
+        )
+        self.env.start()
+        mcp_server._REVIEW_DECISION_LOCK = None
+        import review_workflow_load
+
+        review_workflow_load.clear_review_workflow_load()
+        review_workflow_load.record_review_workflow_load(mcp_server.PROJECT_ROOT)
+        mcp_server.gitea_load_review_workflow()
+
+    def tearDown(self):
+        mcp_server._REVIEW_DECISION_LOCK = None
+        import review_workflow_load
+
+        review_workflow_load.clear_review_workflow_load()
+        self.env.stop()
+        self._tmp.cleanup()
+
+    def _persist_aged_lock(self, mutations, hours: float = 5.0, **kwargs):
+        """Write decision lock aged > TTL to the temp durable store (test-only)."""
+        payload = _age_lock_payload(_lock(mutations, **kwargs), hours=hours)
+        saved = ss.save_state(
+            kind=ss.KIND_DECISION_LOCK,
+            payload=payload,
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+            profile_identity="prgs-reviewer",
+        )
+        # save_state refreshes updated_at; re-age the on-disk envelope for TTL tests.
+        path = ss.state_file_path(
+            kind=ss.KIND_DECISION_LOCK,
+            profile_identity="prgs-reviewer",
+            state_dir=self._tmp.name,
+        )
+        aged = (datetime.now(timezone.utc) - timedelta(hours=hours)).isoformat().replace(
+            "+00:00", "Z"
+        )
+        import json
+
+        with open(path, encoding="utf-8") as fh:
+            envelope = json.load(fh)
+        envelope["recorded_at"] = aged
+        envelope["updated_at"] = aged
+        if isinstance(envelope.get("payload"), dict):
+            envelope["payload"]["recorded_at"] = aged
+            envelope["payload"]["updated_at"] = aged
+        with open(path, "w", encoding="utf-8") as fh:
+            json.dump(envelope, fh, indent=2, sort_keys=True)
+            fh.write("\n")
+        # Drop memory so subsequent loads hit durable store.
+        mcp_server._REVIEW_DECISION_LOCK = None
+        return saved
+
+    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},
+        ), patch.object(
+            mcp_server.mcp_daemon_guard,
+            "assert_sanctioned_mutation_runtime",
+            return_value=None,
+        ), patch.object(
+            mcp_server.mcp_daemon_guard,
+            "assert_no_direct_import_bypass",
+            return_value=None,
+        ):
+            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",
+            )
+
+    # --- AC regression matrix ---
+
+    def test_under_four_hours_fresh_review_at_b_allowed(self):
+        self._persist_aged_lock(
+            [RC_616_A],
+            hours=1.0,
+            ready_pr=616,
+            ready_head=HEAD_A,
+            ready_action="request_changes",
+        )
+        res = self._mark(616, "approve", HEAD_B)
+        self.assertTrue(res.get("marked_ready"), res)
+
+    def test_over_four_hours_fresh_review_at_b_still_allowed(self):
+        """Primary #720 defect: age > TTL must not block head-B mark_final."""
+        self._persist_aged_lock(
+            [RC_616_A],
+            hours=5.0,
+            ready_pr=616,
+            ready_head=HEAD_A,
+            ready_action="request_changes",
+        )
+        # Prove durable load is possible for recovery-critical decision locks.
+        loaded = ss.load_state(
+            kind=ss.KIND_DECISION_LOCK,
+            profile_identity="prgs-reviewer",
+        )
+        self.assertIsNotNone(
+            loaded,
+            "expired KIND_DECISION_LOCK must remain loadable (not generic TTL cache)",
+        )
+        res = self._mark(616, "approve", HEAD_B)
+        self.assertTrue(
+            res.get("marked_ready"),
+            f"expected mark_ready on head B after >4h; got {res}",
+        )
+        reasons = " ".join(res.get("reasons") or [])
+        self.assertNotIn("session state expired", reasons)
+
+    def test_historical_review_at_a_preserved_and_stale(self):
+        self._persist_aged_lock(
+            [RC_616_A],
+            hours=5.0,
+            ready_pr=616,
+            ready_head=HEAD_A,
+            ready_action="request_changes",
+        )
+        res = self._mark(616, "approve", HEAD_B)
+        self.assertTrue(res.get("marked_ready"), res)
+        lock = mcp_server._load_review_decision_lock()
+        self.assertIsNotNone(lock)
+        hist = [m for m in lock["live_mutations"] if m.get("review_id") == 443]
+        self.assertEqual(len(hist), 1)
+        self.assertEqual(hist[0]["head_sha"], HEAD_A)
+        self.assertEqual(hist[0]["action"], "request_changes")
+        a = srdl.assess_stale_review_decision_lock(
+            lock, pr_live=_open_pr(616, HEAD_B)
+        )
+        self.assertTrue(a["stale_by_head"])
+        self.assertTrue(a["fresh_review_on_current_head_allowed"])
+        self.assertEqual(a["locked_head_sha"], HEAD_A)
+
+    def test_no_reuse_approval_from_head_a(self):
+        """REQUEST_CHANGES at A is never an approval credential for B."""
+        self._persist_aged_lock([RC_616_A], hours=5.0)
+        lock = ss.load_state(
+            kind=ss.KIND_DECISION_LOCK, profile_identity="prgs-reviewer"
+        )
+        last = srdl.last_terminal_mutation(lock)
+        self.assertEqual(last.get("action"), "request_changes")
+        self.assertNotEqual(last.get("action"), "approve")
+        # Gate must still require a new mark/submit for head B; prior RC is not approve.
+        reasons = mcp_server.terminal_review_hard_stop_reasons(
+            616, "mark_ready", expected_head_sha=HEAD_B
+        )
+        self.assertEqual(reasons, [])
+
+    def test_second_terminal_mutation_at_b_same_run_blocked(self):
+        self._persist_aged_lock(
+            [RC_616_A],
+            hours=5.0,
+            ready_pr=616,
+            ready_head=HEAD_A,
+            ready_action="request_changes",
+        )
+        res = self._mark(616, "approve", HEAD_B)
+        self.assertTrue(res.get("marked_ready"), res)
+        # Record terminal approve at B (same run).
+        lock = mcp_server._load_review_decision_lock()
+        lock["final_review_decision_ready"] = True
+        lock["ready_pr_number"] = 616
+        lock["ready_action"] = "approve"
+        lock["ready_expected_head_sha"] = HEAD_B
+        mcp_server._save_review_decision_lock(lock)
+        mcp_server.record_live_review_mutation(616, "approve", review_id=999)
+        # Second terminal at same head B must hard-stop.
+        hard = mcp_server.terminal_review_hard_stop_reasons(
+            616, "mark_ready", expected_head_sha=HEAD_B
+        )
+        self.assertTrue(hard)
+        res2 = self._mark(616, "approve", HEAD_B)
+        self.assertFalse(res2.get("marked_ready"))
+
+    def test_open_pr_same_head_expired_still_fail_closed(self):
+        self._persist_aged_lock(
+            [RC_616_A],
+            hours=5.0,
+            ready_pr=616,
+            ready_head=HEAD_A,
+            ready_action="request_changes",
+        )
+        res = self._mark(616, "approve", HEAD_SAME)
+        self.assertFalse(res.get("marked_ready"), res)
+        self.assertTrue(
+            any("#332" in r or "already consumed" in r for r in (res.get("reasons") or [])),
+            res,
+        )
+
+    def test_merged_pr_moot_cleanup_still_allowed(self):
+        self._persist_aged_lock(
+            [RC_616_A],
+            hours=5.0,
+            ready_pr=616,
+            ready_head=HEAD_A,
+            ready_action="request_changes",
+        )
+        lock = ss.load_state(
+            kind=ss.KIND_DECISION_LOCK, profile_identity="prgs-reviewer"
+        )
+        a = srdl.assess_stale_review_decision_lock(
+            lock, pr_live=_open_pr(616, HEAD_A, merged=True)
+        )
+        self.assertTrue(a["is_moot"])
+        self.assertTrue(a["cleanup_allowed"])
+        self.assertFalse(a["fresh_review_on_current_head_allowed"])
+
+    def test_assessment_reports_expired_old_head_not_absent(self):
+        self._persist_aged_lock(
+            [RC_616_A],
+            hours=5.0,
+            ready_pr=616,
+            ready_head=HEAD_A,
+            ready_action="request_changes",
+        )
+        # Disk presence + load after lifecycle fix.
+        path = ss.state_file_path(
+            kind=ss.KIND_DECISION_LOCK,
+            profile_identity="prgs-reviewer",
+            state_dir=self._tmp.name,
+        )
+        self.assertTrue(os.path.exists(path))
+        loaded = ss.load_state(
+            kind=ss.KIND_DECISION_LOCK, profile_identity="prgs-reviewer"
+        )
+        self.assertIsNotNone(loaded)
+        inspect = ss.inspect_state_envelope(
+            kind=ss.KIND_DECISION_LOCK,
+            profile_identity="prgs-reviewer",
+            state_dir=self._tmp.name,
+        )
+        self.assertTrue(inspect.get("on_disk"))
+        self.assertTrue(inspect.get("has_payload"))
+        self.assertTrue(inspect.get("recovery_critical") or inspect.get("ttl_exempt"))
+        self.assertTrue(inspect.get("age_hours", 0) >= 4.0)
+        a = srdl.assess_stale_review_decision_lock(
+            loaded, pr_live=_open_pr(616, HEAD_B)
+        )
+        self.assertTrue(a["has_lock"])
+        self.assertNotIn("no review decision lock present", " ".join(a["reasons"]))
+        self.assertTrue(a["stale_by_head"])
+        self.assertEqual(a["last_terminal_action"], "request_changes")
+
+    def test_existing_serialized_records_compatible(self):
+        """Pre-fix ledgers without recovery_critical flag still load via kind."""
+        payload = _age_lock_payload(_lock([RC_616_A]), hours=8.0)
+        payload.pop("recovery_critical", None)
+        # Manually write pre-#720-shaped envelope (kind only on envelope).
+        path = ss.state_file_path(
+            kind=ss.KIND_DECISION_LOCK,
+            profile_identity="prgs-reviewer",
+            state_dir=self._tmp.name,
+        )
+        import json
+
+        os.makedirs(self._tmp.name, exist_ok=True)
+        aged = payload["recorded_at"]
+        envelope = {
+            "kind": ss.KIND_DECISION_LOCK,
+            "remote": "prgs",
+            "org": "Scaled-Tech-Consulting",
+            "repo": "Gitea-Tools",
+            "profile_identity": "prgs-reviewer",
+            "session_profile_lock": "prgs-reviewer",
+            "recorded_at": aged,
+            "updated_at": aged,
+            "writer_pid": os.getpid(),
+            "payload": payload,
+        }
+        with open(path, "w", encoding="utf-8") as fh:
+            json.dump(envelope, fh, indent=2, sort_keys=True)
+            fh.write("\n")
+        loaded = ss.load_state(
+            kind=ss.KIND_DECISION_LOCK, profile_identity="prgs-reviewer"
+        )
+        self.assertIsNotNone(loaded)
+        self.assertEqual(loaded["live_mutations"][0]["review_id"], 443)
+
+    def test_decision_lock_is_recovery_critical_kind(self):
+        self.assertIn(ss.KIND_DECISION_LOCK, ss.RECOVERY_CRITICAL_KINDS)
+
+    def test_workflow_load_still_ttl_expires(self):
+        """Do not make every session-state kind permanently TTL-exempt."""
+        aged = (datetime.now(timezone.utc) - timedelta(hours=5)).isoformat().replace(
+            "+00:00", "Z"
+        )
+        rec = {
+            "kind": ss.KIND_WORKFLOW_LOAD,
+            "recorded_at": aged,
+            "updated_at": aged,
+            "profile_identity": "prgs-reviewer",
+            "session_profile_lock": "prgs-reviewer",
+        }
+        reasons = ss.identity_match_reasons(
+            rec, profile_identity="prgs-reviewer"
+        )
+        self.assertTrue(any("expired" in r for r in reasons), reasons)
+
+    def test_irrecoverable_permission_not_on_ordinary_profiles(self):
+        perm = "gitea.decision_lock.irrecoverable_recovery"
+        # Capability map must not map ordinary author/reviewer/merger tasks to it.
+        for task in (
+            "create_issue",
+            "comment_issue",
+            "review_pr",
+            "merge_pr",
+            "lock_issue",
+            "create_pr",
+        ):
+            req = task_capability_map.required_permission(task)
+            self.assertNotEqual(req, perm, msg=task)
+
+    def test_structured_error_when_same_head_expired(self):
+        self._persist_aged_lock(
+            [RC_616_A],
+            hours=5.0,
+            ready_pr=616,
+            ready_head=HEAD_A,
+            ready_action="request_changes",
+        )
+        res = self._mark(616, "approve", HEAD_A)
+        self.assertFalse(res.get("marked_ready"))
+        reasons = res.get("reasons") or []
+        self.assertTrue(reasons)
+        blob = " ".join(reasons)
+        # Actionable recovery text from hard-stop (not generic internal_error).
+        self.assertIn("#332", blob)
+        self.assertTrue(
+            "#620" in blob or "head moved" in blob or "new expected_head_sha" in blob
+            or "already consumed" in blob
+        )
+        self.assertNotIn("internal_error", blob.lower())
+
+
+class TestIssue720InspectEnvelope(unittest.TestCase):
+    def setUp(self):
+        self._tmp = tempfile.TemporaryDirectory()
+        self.env = patch.dict(
+            os.environ,
+            {
+                ss.STATE_DIR_ENV: self._tmp.name,
+                ss.SESSION_PROFILE_LOCK_ENV: "prgs-reviewer",
+            },
+            clear=False,
+        )
+        self.env.start()
+
+    def tearDown(self):
+        self.env.stop()
+        self._tmp.cleanup()
+
+    def test_inspect_missing_file(self):
+        info = ss.inspect_state_envelope(
+            kind=ss.KIND_DECISION_LOCK,
+            profile_identity="prgs-reviewer",
+            state_dir=self._tmp.name,
+        )
+        self.assertFalse(info["on_disk"])
+        self.assertFalse(info["has_payload"])
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_mcp_server.py

@@ -1446,10 +1446,16 @@ class TestReviewPR(unittest.TestCase):
 class TestDeleteBranch(unittest.TestCase):
 
     DELETE_PROFILE = {
-        "profile_name": "test-deleter",
-        "allowed_operations": ["gitea.read", "gitea.branch.delete"],
+        "profile_name": "test-author-deleter",
+        "role": "author",
+        "allowed_operations": [
+            "gitea.read",
+            "gitea.pr.create",
+            "gitea.branch.push",
+            "gitea.branch.delete",
+        ],
         "forbidden_operations": [],
-        "audit_label": "test-deleter",
+        "audit_label": "test-author-deleter",
     }
 
     @patch("mcp_server.get_profile", return_value=DELETE_PROFILE)

tests/test_migrate_profiles.py

@@ -92,14 +92,19 @@ class TestMigrateProfiles(unittest.TestCase):
         author = prgs_gitea["identities"]["author"]
         self.assertEqual(author["username"], "jcwalker3")
         self.assertEqual(author["auth"]["id"], "redacted-author-ref")
-        self.assertEqual(author["allowed_operations"], ["read", "comment"])
-        self.assertEqual(author["forbidden_operations"], ["approve", "merge"])
+        self.assertEqual(
+            author["allowed_operations"], ["gitea.read", "gitea.pr.comment"]
+        )
+        self.assertEqual(
+            author["forbidden_operations"],
+            ["gitea.pr.approve", "gitea.pr.merge"],
+        )
 
         reviewer = prgs_gitea["identities"]["reviewer"]
         self.assertEqual(reviewer["role"], "reviewer")
         self.assertEqual(reviewer["username"], "sysadmin")
         self.assertEqual(reviewer["auth"]["id"], "redacted-reviewer-ref")
-        self.assertIn("merge", reviewer["allowed_operations"])
+        self.assertIn("gitea.pr.merge", reviewer["allowed_operations"])
 
     def test_alias_generation(self):
         """Test that aliases are correctly generated to support old profile names."""
@@ -188,7 +193,7 @@ class TestMigrateProfiles(unittest.TestCase):
         self.assertNotIn("token", stdout_output.lower())
 
     def test_explicit_operations_are_preserved(self):
-        """Explicit v1 permissions must not be replaced by role defaults."""
+        """Explicit v1 permissions are canonicalized, not replaced by role defaults."""
         v1_data = json.loads(json.dumps(self.v1_content))
         v1_data["profiles"]["prgs-reviewer"]["allowed_operations"] = ["read"]
         v1_data["profiles"]["prgs-reviewer"]["forbidden_operations"] = ["merge"]
@@ -198,8 +203,8 @@ class TestMigrateProfiles(unittest.TestCase):
             v2_data["environments"]["prgs"]["services"]["gitea"]
             ["identities"]["reviewer"]
         )
-        self.assertEqual(reviewer["allowed_operations"], ["read"])
-        self.assertEqual(reviewer["forbidden_operations"], ["merge"])
+        self.assertEqual(reviewer["allowed_operations"], ["gitea.read"])
+        self.assertEqual(reviewer["forbidden_operations"], ["gitea.pr.merge"])
 
     def test_inferred_role_defaults_only_when_unambiguous(self):
         """Role defaults are allowed only for clear author/reviewer profiles."""
@@ -306,6 +311,171 @@ class TestMigrateProfiles(unittest.TestCase):
                 migrate_profiles.main()
             self.assertEqual(cm.exception.code, 1)
 
+    def test_reconciler_profile_migration(self):
+        """Legacy reconciler shorthands migrate to valid canonical operations."""
+        import gitea_config
+        import reconciler_profile
+
+        v1_data = {
+            "version": 1,
+            "profiles": {
+                "prgs-reconciler": {
+                    "base_url": "redacted-prgs-service",
+                    "username": "reconciler-agent",
+                    "auth": {"type": "keychain", "id": "reconciler-ref"},
+                    "execution_profile": "prgs-reconciler",
+                    "allowed_operations": [
+                        "read",
+                        "pr.close",
+                        "pr.comment",
+                        "issue.comment",
+                        "issue.close",
+                        "gitea.branch.delete",
+                    ],
+                    "forbidden_operations": [
+                        "merge",
+                        "approve",
+                        "review",
+                        "pr.create",
+                        "branch.push",
+                        "commit",
+                    ],
+                }
+            }
+        }
+        v2_data = migrate_profiles.migrate_v1_to_v2(v1_data)
+        reconciler = (
+            v2_data["environments"]["prgs"]["services"]["gitea"]
+            ["identities"]["reconciler"]
+        )
+        self.assertEqual(reconciler["role"], "reconciler")
+        allowed = reconciler["allowed_operations"]
+        forbidden = reconciler["forbidden_operations"]
+        # No invalid shorthand remains
+        for bad in ("pr.close", "pr.comment", "issue.close", "read", "merge"):
+            self.assertNotIn(bad, allowed)
+            self.assertNotIn(bad, forbidden)
+        for required in (
+            "gitea.read",
+            "gitea.pr.close",
+            "gitea.pr.comment",
+            "gitea.issue.comment",
+            "gitea.issue.close",
+            "gitea.branch.delete",
+        ):
+            self.assertIn(required, allowed)
+            # Production loader accepts every allowed op
+            self.assertEqual(
+                gitea_config.normalize_operation(required), required
+            )
+        self.assertEqual(v2_data["aliases"]["prgs-reconciler"], "prgs.gitea.reconciler")
+        assessment = reconciler_profile.assess_reconciler_profile(allowed, forbidden)
+        self.assertTrue(assessment["valid"])
+        self.assertTrue(migrate_profiles.validate_v2_data(v2_data))
+
+    def test_reconciler_profile_defaults(self):
+        """Reconciler defaults are fully canonical and loader-valid."""
+        import gitea_config
+        import reconciler_profile
+
+        v1_data = {
+            "version": 1,
+            "profiles": {
+                "prgs-reconciler": {
+                    "base_url": "redacted-prgs-service",
+                    "username": "reconciler-agent",
+                    "auth": {"type": "keychain", "id": "reconciler-ref"},
+                    "execution_profile": "prgs-reconciler",
+                }
+            }
+        }
+        v2_data = migrate_profiles.migrate_v1_to_v2(v1_data)
+        reconciler = (
+            v2_data["environments"]["prgs"]["services"]["gitea"]
+            ["identities"]["reconciler"]
+        )
+        self.assertEqual(reconciler["role"], "reconciler")
+        self.assertEqual(
+            reconciler["allowed_operations"],
+            migrate_profiles.RECONCILER_DEFAULT_ALLOWED,
+        )
+        self.assertEqual(
+            reconciler["forbidden_operations"],
+            migrate_profiles.RECONCILER_DEFAULT_FORBIDDEN,
+        )
+        for op in reconciler["allowed_operations"]:
+            self.assertEqual(gitea_config.normalize_operation(op), op)
+            self.assertTrue(op.startswith("gitea."))
+        assessment = reconciler_profile.assess_reconciler_profile(
+            reconciler["allowed_operations"],
+            reconciler["forbidden_operations"],
+        )
+        self.assertTrue(assessment["valid"])
+        self.assertNotIn(
+            "gitea.branch.delete", assessment["missing_recommended_operations"]
+        )
+
+    def test_reconciler_migration_idempotent_canonicalize(self):
+        """Second canonicalize of already-canonical ops is a no-op."""
+        first = migrate_profiles.canonicalize_operations(
+            list(migrate_profiles.RECONCILER_DEFAULT_ALLOWED)
+        )
+        second = migrate_profiles.canonicalize_operations(first)
+        self.assertEqual(first, second)
+        self.assertEqual(first, list(migrate_profiles.RECONCILER_DEFAULT_ALLOWED))
+
+    def test_reconciler_missing_required_fails_visibly(self):
+        """Missing gitea.pr.close after migration fails closed (not silent drop)."""
+        v1_data = {
+            "version": 1,
+            "profiles": {
+                "prgs-reconciler": {
+                    "base_url": "redacted-prgs-service",
+                    "username": "reconciler-agent",
+                    "auth": {"type": "keychain", "id": "reconciler-ref"},
+                    "execution_profile": "prgs-reconciler",
+                    "allowed_operations": ["read", "gitea.branch.delete"],
+                    "forbidden_operations": ["merge"],
+                }
+            },
+        }
+        with self.assertRaisesRegex(ValueError, "missing required"):
+            migrate_profiles.migrate_v1_to_v2(v1_data)
+
+    def test_unknown_operation_fails_visibly(self):
+        v1_data = {
+            "version": 1,
+            "profiles": {
+                "prgs-author": {
+                    "base_url": "redacted-prgs-service",
+                    "username": "jcwalker3",
+                    "auth": {"type": "keychain", "id": "hidden-author-ref"},
+                    "execution_profile": "prgs-author",
+                    "allowed_operations": ["read", "not.a.real.op"],
+                    "forbidden_operations": ["merge"],
+                }
+            },
+        }
+        with self.assertRaisesRegex(ValueError, "cannot be canonicalized"):
+            migrate_profiles.migrate_v1_to_v2(v1_data)
+
+    def test_role_inference_author_reviewer_merger_reconciler(self):
+        self.assertEqual(
+            migrate_profiles.infer_role("prgs-author", "prgs-author"), "author"
+        )
+        self.assertEqual(
+            migrate_profiles.infer_role("prgs-reviewer", "prgs-reviewer"),
+            "reviewer",
+        )
+        self.assertEqual(
+            migrate_profiles.infer_role("prgs-reconciler", "prgs-reconciler"),
+            "reconciler",
+        )
+        self.assertIsNone(
+            migrate_profiles.infer_role("prgs-merger", "prgs-merger")
+        )
+
 
 if __name__ == "__main__":
     unittest.main()
+

tests/test_pr_sync_status.py

@@ -0,0 +1,338 @@
+"""Hermetic tests for PR synchronization / conflict-remediation lifecycle."""
+
+from __future__ import annotations
+
+import unittest
+
+from pr_sync_status import (
+    ACTION_AUTHOR_CONFLICT_REMEDIATION,
+    ACTION_BLOCKED,
+    ACTION_FRESH_REVIEW_REQUIRED,
+    ACTION_MERGE_NOW,
+    ACTION_UPDATE_BRANCH_BY_MERGE,
+    assess_post_update_head_transition,
+    assess_pr_sync_status,
+    assess_sequential_queue_step,
+    assess_update_pr_branch_preflight,
+    lease_usable_at_head,
+    merge_approval_usable_at_head,
+)
+
+
+def _sha(prefix: str) -> str:
+    return (prefix + "0" * 40)[:40]
+
+
+PR_HEAD = _sha("aaaaaaaa")
+BASE_HEAD = _sha("bbbbbbbb")
+NEW_HEAD = _sha("cccccccc")
+OLD_HEAD = _sha("dddddddd")
+
+
+def _base_kwargs(**overrides):
+    data = {
+        "host": "gitea.prgs.cc",
+        "org": "Scaled-Tech-Consulting",
+        "repo": "Gitea-Tools",
+        "pr_number": 100,
+        "pr_state": "open",
+        "source_branch": "fix/issue-100",
+        "pr_head_sha": PR_HEAD,
+        "base_head_sha": BASE_HEAD,
+        "commits_behind": 0,
+        "mergeable": True,
+        "has_conflicts": False,
+        "branch_protection_requires_current_base": False,
+        "approval_at_current_head": True,
+        "checks_status": "success",
+        "active_author_lock": True,
+        "active_reviewer_lease": False,
+        "active_merger_lease": False,
+    }
+    data.update(overrides)
+    return data
+
+
+class TestAssessPrSyncStatus(unittest.TestCase):
+    def test_approved_current_mergeable_merge_now(self):
+        result = assess_pr_sync_status(**_base_kwargs())
+        self.assertEqual(result["recommended_next_action"], ACTION_MERGE_NOW)
+        self.assertTrue(result["approval_valid_for_merge"])
+        self.assertFalse(result["stale_approval"])
+        self.assertEqual(result["pr_head_sha"], PR_HEAD)
+        self.assertEqual(result["base_head_sha"], BASE_HEAD)
+
+    def test_approved_outdated_update_not_required_merge_now(self):
+        result = assess_pr_sync_status(
+            **_base_kwargs(
+                commits_behind=3,
+                branch_protection_requires_current_base=False,
+            )
+        )
+        self.assertEqual(result["recommended_next_action"], ACTION_MERGE_NOW)
+        self.assertTrue(result["approval_valid_for_merge"])
+        self.assertTrue(any("does not require" in r for r in result["reasons"]))
+
+    def test_outdated_update_required_no_conflict(self):
+        result = assess_pr_sync_status(
+            **_base_kwargs(
+                commits_behind=2,
+                branch_protection_requires_current_base=True,
+                mergeable=True,
+                has_conflicts=False,
+            )
+        )
+        self.assertEqual(
+            result["recommended_next_action"], ACTION_UPDATE_BRANCH_BY_MERGE
+        )
+        self.assertFalse(result["approval_valid_for_merge"])
+        self.assertTrue(any("update_branch_by_merge" in r for r in result["reasons"]))
+
+    def test_outdated_has_conflicts_author_remediation(self):
+        result = assess_pr_sync_status(
+            **_base_kwargs(
+                commits_behind=5,
+                branch_protection_requires_current_base=True,
+                mergeable=False,
+                has_conflicts=True,
+            )
+        )
+        self.assertEqual(
+            result["recommended_next_action"], ACTION_AUTHOR_CONFLICT_REMEDIATION
+        )
+        self.assertFalse(result["approval_valid_for_merge"])
+
+    def test_stale_approval_fresh_review_required(self):
+        result = assess_pr_sync_status(
+            **_base_kwargs(
+                approval_at_current_head=False,
+                commits_behind=0,
+            )
+        )
+        self.assertEqual(
+            result["recommended_next_action"], ACTION_FRESH_REVIEW_REQUIRED
+        )
+        self.assertTrue(result["stale_approval"])
+        self.assertFalse(result["approval_valid_for_merge"])
+
+    def test_stale_prepared_verdict_cannot_cross_heads(self):
+        result = assess_pr_sync_status(
+            **_base_kwargs(
+                approval_at_current_head=True,
+                prepared_verdict_head_sha=OLD_HEAD,
+            )
+        )
+        self.assertEqual(
+            result["recommended_next_action"], ACTION_FRESH_REVIEW_REQUIRED
+        )
+        self.assertTrue(result["stale_prepared_verdict"])
+        self.assertFalse(result["approval_valid_for_merge"])
+
+    def test_missing_heads_fail_closed(self):
+        result = assess_pr_sync_status(
+            **_base_kwargs(pr_head_sha="short", base_head_sha=None)
+        )
+        self.assertEqual(result["recommended_next_action"], ACTION_BLOCKED)
+        self.assertTrue(any("PR head" in r for r in result["reasons"]))
+
+    def test_closed_pr_blocked(self):
+        result = assess_pr_sync_status(**_base_kwargs(pr_state="closed"))
+        self.assertEqual(result["recommended_next_action"], ACTION_BLOCKED)
+
+    def test_failed_checks_block_merge_now(self):
+        result = assess_pr_sync_status(**_base_kwargs(checks_status="failure"))
+        self.assertEqual(result["recommended_next_action"], ACTION_BLOCKED)
+
+    def test_stale_approval_with_update_required_routes_update(self):
+        result = assess_pr_sync_status(
+            **_base_kwargs(
+                approval_at_current_head=False,
+                commits_behind=1,
+                branch_protection_requires_current_base=True,
+                mergeable=True,
+                has_conflicts=False,
+            )
+        )
+        self.assertEqual(
+            result["recommended_next_action"], ACTION_UPDATE_BRANCH_BY_MERGE
+        )
+
+
+class TestUpdatePrBranchPreflight(unittest.TestCase):
+    def _ok_kwargs(self, **overrides):
+        data = {
+            "role_kind": "author",
+            "expected_pr_head_sha": PR_HEAD,
+            "live_pr_head_sha": PR_HEAD,
+            "expected_base_head_sha": BASE_HEAD,
+            "live_base_head_sha": BASE_HEAD,
+            "has_conflicts": False,
+            "mergeable": True,
+            "style": "merge",
+            "has_author_lock": True,
+            "worktree_path": "/Users/x/Development/Gitea-Tools/branches/issue-100",
+            "worktree_owns_source_branch": True,
+            "control_checkout_clean": True,
+            "master_parity_ok": True,
+            "force_push": False,
+            "rebase": False,
+        }
+        data.update(overrides)
+        return data
+
+    def test_author_allowed_when_preflight_clean(self):
+        result = assess_update_pr_branch_preflight(**self._ok_kwargs())
+        self.assertTrue(result["mutation_allowed"])
+        self.assertFalse(result["head_race"])
+        self.assertFalse(result["base_race"])
+
+    def test_head_race_fail_closed(self):
+        result = assess_update_pr_branch_preflight(
+            **self._ok_kwargs(live_pr_head_sha=NEW_HEAD)
+        )
+        self.assertFalse(result["mutation_allowed"])
+        self.assertTrue(result["head_race"])
+        self.assertTrue(any("PR head race" in r for r in result["reasons"]))
+
+    def test_base_race_fail_closed(self):
+        result = assess_update_pr_branch_preflight(
+            **self._ok_kwargs(live_base_head_sha=NEW_HEAD)
+        )
+        self.assertFalse(result["mutation_allowed"])
+        self.assertTrue(result["base_race"])
+        self.assertTrue(any("base head race" in r for r in result["reasons"]))
+
+    def test_conflicts_structured_handoff_no_mutation(self):
+        result = assess_update_pr_branch_preflight(
+            **self._ok_kwargs(has_conflicts=True, mergeable=False)
+        )
+        self.assertFalse(result["mutation_allowed"])
+        self.assertTrue(result["author_remediation_handoff"])
+        self.assertTrue(any("conflicts" in r.lower() for r in result["reasons"]))
+
+    def test_reviewer_denied(self):
+        result = assess_update_pr_branch_preflight(
+            **self._ok_kwargs(role_kind="reviewer")
+        )
+        self.assertFalse(result["mutation_allowed"])
+        self.assertTrue(any("author-only" in r for r in result["reasons"]))
+
+    def test_merger_denied(self):
+        result = assess_update_pr_branch_preflight(
+            **self._ok_kwargs(role_kind="merger")
+        )
+        self.assertFalse(result["mutation_allowed"])
+        self.assertTrue(any("author-only" in r for r in result["reasons"]))
+
+    def test_no_force_push(self):
+        result = assess_update_pr_branch_preflight(
+            **self._ok_kwargs(force_push=True)
+        )
+        self.assertFalse(result["mutation_allowed"])
+        self.assertTrue(any("force-push" in r for r in result["reasons"]))
+
+    def test_no_rebase(self):
+        result = assess_update_pr_branch_preflight(
+            **self._ok_kwargs(style="rebase", rebase=True)
+        )
+        self.assertFalse(result["mutation_allowed"])
+        self.assertTrue(any("rebase" in r for r in result["reasons"]))
+
+    def test_missing_lock_fail_closed(self):
+        result = assess_update_pr_branch_preflight(
+            **self._ok_kwargs(has_author_lock=False)
+        )
+        self.assertFalse(result["mutation_allowed"])
+
+    def test_worktree_not_under_branches(self):
+        result = assess_update_pr_branch_preflight(
+            **self._ok_kwargs(worktree_path="/tmp/not-a-branches-path")
+        )
+        self.assertFalse(result["mutation_allowed"])
+        self.assertTrue(any("branches/" in r for r in result["reasons"]))
+
+
+class TestPostUpdateHeadTransition(unittest.TestCase):
+    def test_update_invalidates_approval_and_requires_fresh_review(self):
+        result = assess_post_update_head_transition(
+            former_pr_head_sha=PR_HEAD,
+            new_pr_head_sha=NEW_HEAD,
+            former_approval_head_sha=PR_HEAD,
+            former_reviewer_lease_head_sha=PR_HEAD,
+            former_merger_lease_head_sha=PR_HEAD,
+            prepared_verdict_head_sha=PR_HEAD,
+        )
+        self.assertTrue(result["head_changed"])
+        self.assertTrue(result["approval_invalidated"])
+        self.assertTrue(result["reviewer_lease_superseded"])
+        self.assertTrue(result["merger_lease_superseded"])
+        self.assertTrue(result["prepared_verdict_invalidated"])
+        self.assertEqual(
+            result["recommended_next_action"], ACTION_FRESH_REVIEW_REQUIRED
+        )
+
+    def test_same_head_unexpected(self):
+        result = assess_post_update_head_transition(
+            former_pr_head_sha=PR_HEAD,
+            new_pr_head_sha=PR_HEAD,
+        )
+        self.assertFalse(result["head_changed"])
+        self.assertEqual(result["recommended_next_action"], ACTION_BLOCKED)
+
+
+class TestStaleArtifacts(unittest.TestCase):
+    def test_stale_approval_cannot_authorize_merge(self):
+        result = merge_approval_usable_at_head(
+            current_head_sha=NEW_HEAD,
+            approved_head_sha=PR_HEAD,
+        )
+        self.assertFalse(result["approval_usable"])
+
+    def test_fresh_approval_usable(self):
+        result = merge_approval_usable_at_head(
+            current_head_sha=NEW_HEAD,
+            approved_head_sha=NEW_HEAD,
+        )
+        self.assertTrue(result["approval_usable"])
+
+    def test_stale_reviewer_lease_cannot_cross_heads(self):
+        result = lease_usable_at_head(
+            lease_kind="reviewer",
+            lease_head_sha=PR_HEAD,
+            current_head_sha=NEW_HEAD,
+        )
+        self.assertFalse(result["lease_usable"])
+
+    def test_stale_merger_lease_cannot_cross_heads(self):
+        result = lease_usable_at_head(
+            lease_kind="merger",
+            lease_head_sha=PR_HEAD,
+            current_head_sha=NEW_HEAD,
+        )
+        self.assertFalse(result["lease_usable"])
+
+
+class TestSequentialQueue(unittest.TestCase):
+    def test_reassess_after_merge_and_master_refresh(self):
+        result = assess_sequential_queue_step(
+            just_merged=True,
+            master_refreshed=True,
+            next_pr_number=101,
+        )
+        self.assertTrue(result["reassess_allowed"])
+        self.assertTrue(result["process_next"])
+        self.assertTrue(result["post_merge_cleanup_handoff"])
+        self.assertEqual(result["next_pr_number"], 101)
+
+    def test_block_reassess_without_master_refresh(self):
+        result = assess_sequential_queue_step(
+            just_merged=True,
+            master_refreshed=False,
+            next_pr_number=101,
+        )
+        self.assertFalse(result["reassess_allowed"])
+        self.assertTrue(any("master must be refreshed" in r for r in result["reasons"]))
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_reconciler_profile.py

@@ -82,6 +82,42 @@ class TestReconcilerProfileModel(unittest.TestCase):
             "reconciler",
         )
 
+    def test_branch_delete_is_recommended_for_reconciler(self):
+        self.assertIn(
+            "gitea.branch.delete",
+            reconciler_profile.RECONCILER_RECOMMENDED_OPERATIONS,
+        )
+        self.assertNotIn(
+            "gitea.branch.delete",
+            reconciler_profile.RECONCILER_REQUIRED_OPERATIONS,
+        )
+
+    def test_reconciler_with_branch_delete_stays_valid(self):
+        allowed = PRGS_RECONCILER_ALLOWED + ["gitea.branch.delete"]
+        result = reconciler_profile.assess_reconciler_profile(
+            allowed,
+            PRGS_RECONCILER_FORBIDDEN,
+        )
+        self.assertTrue(result["is_reconciler_profile"])
+        self.assertTrue(result["valid"])
+        self.assertNotIn(
+            "gitea.branch.delete", result["missing_recommended_operations"]
+        )
+        self.assertEqual(
+            mcp_server._role_kind(allowed, PRGS_RECONCILER_FORBIDDEN),
+            "reconciler",
+        )
+
+    def test_reconciler_without_branch_delete_reports_missing_recommended(self):
+        result = reconciler_profile.assess_reconciler_profile(
+            PRGS_RECONCILER_ALLOWED,
+            PRGS_RECONCILER_FORBIDDEN,
+        )
+        self.assertTrue(result["valid"])
+        self.assertIn(
+            "gitea.branch.delete", result["missing_recommended_operations"]
+        )
+
 
 if __name__ == "__main__":
     unittest.main()

tests/test_retry_backoff.py

@@ -122,9 +122,11 @@ class TestApiRequestRetry(unittest.TestCase):
         sleep.assert_not_called()
 
     def test_non_429_error_raises_immediately(self):
-        with self.assertRaises(RuntimeError) as ctx:
+        with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
             _call([_http_error(500, body=b"boom")])
-        self.assertIn("HTTP 500", str(ctx.exception))
+        # Fixed message only (#699) — no response body echo.
+        self.assertEqual(str(ctx.exception), "Gitea HTTP request failed")
+        self.assertEqual(ctx.exception.http_status, 500)
 
     def test_non_429_error_does_not_sleep(self):
         sleep = MagicMock()
@@ -171,9 +173,12 @@ class TestApiRequestRetry(unittest.TestCase):
         # max_retries=3 -> 3 sleeps, then the 4th failure raises.
         errors = [_http_error(429, retry_after="1") for _ in range(4)]
         sleep = MagicMock()
-        with self.assertRaises(RuntimeError) as ctx:
+        with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
             _call(errors, sleep_func=sleep, max_retries=3)
-        self.assertIn("HTTP 429", str(ctx.exception))
+        # After retries are exhausted, 429 is a typed HTTP error with fixed
+        # message (#699); status metadata carries 429.
+        self.assertEqual(str(ctx.exception), "Gitea HTTP request failed")
+        self.assertEqual(ctx.exception.http_status, 429)
         self.assertEqual(sleep.call_count, 3)
 
     def test_no_infinite_loop_when_always_429(self):

tests/test_sentry_observability.py

@@ -0,0 +1,412 @@
+"""Tests for optional self-hosted Sentry observability (#606).
+
+Covers the pure module (config, redaction, event/check-in builders) and the
+runtime capture paths using a fake ``sentry_sdk``, so nothing ever touches the
+network. Critically proves the feature is a no-op when disabled or DSN-less
+(acceptance criterion 1) and that secrets/paths/session-state are never sent
+(criterion 5).
+"""
+
+import sys
+import contextlib
+from pathlib import Path
+
+import pytest
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+import sentry_observability as so  # noqa: E402
+
+
+# ── Fake SDK ────────────────────────────────────────────────────────────────
+class _FakeScope:
+    def __init__(self):
+        self.tags = {}
+        self.extras = {}
+
+    def set_tag(self, k, v):
+        self.tags[k] = v
+
+    def set_extra(self, k, v):
+        self.extras[k] = v
+
+
+class FakeSentrySDK:
+    """Minimal stand-in exposing the SDK surface sentry_observability uses."""
+
+    def __init__(self):
+        self.init_kwargs = None
+        self.events = []
+        self.exceptions = []
+        self.checkins = []
+        self.last_scope = None
+
+    def init(self, **kwargs):
+        self.init_kwargs = kwargs
+
+    def capture_event(self, event):
+        self.events.append(event)
+
+    def capture_exception(self, exc):
+        self.exceptions.append(exc)
+
+    def capture_checkin(self, **payload):
+        self.checkins.append(payload)
+
+    @contextlib.contextmanager
+    def push_scope(self):
+        self.last_scope = _FakeScope()
+        yield self.last_scope
+
+
+@pytest.fixture(autouse=True)
+def _reset_state():
+    """Isolate module init state between tests."""
+    so.reset_for_tests()
+    yield
+    so.reset_for_tests()
+
+
+@pytest.fixture
+def fake_sdk(monkeypatch):
+    sdk = FakeSentrySDK()
+    monkeypatch.setattr(so, "sentry_sdk", sdk)
+    return sdk
+
+
+# ── Config / gating ─────────────────────────────────────────────────────────
+def test_disabled_by_default_empty_env():
+    cfg = so.load_config(env={})
+    assert cfg.enabled is False
+    assert cfg.active is False
+
+
+def test_enabled_flag_without_dsn_is_not_active():
+    cfg = so.load_config(env={"MCP_SENTRY_ENABLED": "1"})
+    assert cfg.enabled is True
+    assert cfg.dsn is None
+    assert cfg.active is False  # DSN required
+
+
+def test_dsn_without_enabled_flag_is_not_active():
+    cfg = so.load_config(env={"SENTRY_DSN": "https://[email protected]/1"})
+    assert cfg.active is False
+
+
+def test_active_requires_enabled_and_dsn():
+    cfg = so.load_config(
+        env={"MCP_SENTRY_ENABLED": "true", "SENTRY_DSN": "https://[email protected]/1"}
+    )
+    assert cfg.active is True
+
+
+def test_truthy_variants():
+    for val in ("1", "true", "YES", "On"):
+        cfg = so.load_config(env={"MCP_SENTRY_ENABLED": val})
+        assert cfg.enabled is True
+    for val in ("0", "false", "no", "", "off"):
+        cfg = so.load_config(env={"MCP_SENTRY_ENABLED": val})
+        assert cfg.enabled is False
+
+
+def test_traces_sample_rate_parsed_and_clamped():
+    assert so.load_config(env={"MCP_SENTRY_TRACES_SAMPLE_RATE": "0.25"}).traces_sample_rate == 0.25
+    assert so.load_config(env={"MCP_SENTRY_TRACES_SAMPLE_RATE": "5"}).traces_sample_rate == 1.0
+    assert so.load_config(env={"MCP_SENTRY_TRACES_SAMPLE_RATE": "-1"}).traces_sample_rate == 0.0
+    assert so.load_config(env={"MCP_SENTRY_TRACES_SAMPLE_RATE": "junk"}).traces_sample_rate == 0.0
+
+
+def test_safe_summary_has_no_dsn_value():
+    cfg = so.load_config(
+        env={"MCP_SENTRY_ENABLED": "1", "SENTRY_DSN": "https://[email protected]/1"}
+    )
+    summary = cfg.safe_summary()
+    assert summary["dsn_present"] is True
+    assert "secret" not in repr(summary)
+    assert "dsn" not in summary  # only presence, never the value
+
+
+# ── init_sentry ─────────────────────────────────────────────────────────────
+def test_init_noop_when_disabled(fake_sdk):
+    status = so.init_sentry(so.load_config(env={}))
+    assert status["initialized"] is False
+    assert fake_sdk.init_kwargs is None  # no SDK init
+    assert so.is_initialized() is False
+
+
+def test_init_noop_when_enabled_but_missing_dsn(fake_sdk):
+    status = so.init_sentry(so.load_config(env={"MCP_SENTRY_ENABLED": "1"}))
+    assert status["initialized"] is False
+    assert fake_sdk.init_kwargs is None
+
+
+def test_init_reports_missing_sdk(monkeypatch):
+    monkeypatch.setattr(so, "sentry_sdk", None)
+    status = so.init_sentry(
+        so.load_config(
+            env={"MCP_SENTRY_ENABLED": "1", "SENTRY_DSN": "https://[email protected]/1"}
+        )
+    )
+    assert status["initialized"] is False
+    assert "not installed" in status["reason"]
+
+
+def test_init_configures_sdk_with_scrubber(fake_sdk):
+    status = so.init_sentry(
+        so.load_config(
+            env={
+                "MCP_SENTRY_ENABLED": "1",
+                "SENTRY_DSN": "https://[email protected]/1",
+                "SENTRY_ENVIRONMENT": "prod",
+                "MCP_SENTRY_TRACES_SAMPLE_RATE": "0.1",
+            }
+        )
+    )
+    assert status["initialized"] is True
+    assert so.is_initialized() is True
+    kw = fake_sdk.init_kwargs
+    assert kw["dsn"] == "https://[email protected]/1"
+    assert kw["environment"] == "prod"
+    assert kw["traces_sample_rate"] == 0.1
+    assert kw["before_send"] is so.scrub_event
+    assert kw["send_default_pii"] is False
+
+
+def test_init_enable_logs_wires_log_scrubber(fake_sdk):
+    so.init_sentry(
+        so.load_config(
+            env={
+                "MCP_SENTRY_ENABLED": "1",
+                "SENTRY_DSN": "https://[email protected]/1",
+                "MCP_SENTRY_ENABLE_LOGS": "1",
+            }
+        )
+    )
+    exp = fake_sdk.init_kwargs["_experiments"]
+    assert exp["enable_logs"] is True
+    assert exp["before_send_log"] is so.scrub_event
+
+
+def test_init_never_raises_on_sdk_failure(monkeypatch):
+    class Boom:
+        def init(self, **kwargs):
+            raise RuntimeError("sentry down")
+
+    monkeypatch.setattr(so, "sentry_sdk", Boom())
+    status = so.init_sentry(
+        so.load_config(
+            env={"MCP_SENTRY_ENABLED": "1", "SENTRY_DSN": "https://[email protected]/1"}
+        )
+    )
+    assert status["initialized"] is False
+    assert "init failed" in status["reason"]
+
+
+# ── Redaction (fail closed) ─────────────────────────────────────────────────
+def test_build_tags_allowlist_only():
+    tags = so.build_tags(role="author", secret_thing="leak", pid=123)
+    assert tags["role"] == "author"
+    assert tags["pid"] == "123"
+    assert "secret_thing" not in tags
+
+
+def test_build_tags_hashes_session_id():
+    tags = so.build_tags(session_id="prgs-author-20479-cf9ac178")
+    assert "session_id" not in tags
+    assert "session_id_hash" in tags
+    assert tags["session_id_hash"] != "prgs-author-20479-cf9ac178"
+    assert len(tags["session_id_hash"]) == 12
+
+
+def test_build_tags_collapses_worktree_path():
+    tags = so.build_tags(
+        worktree_path="/Users/x/Development/Gitea-Tools/branches/issue-606-sentry-observability"
+    )
+    assert "worktree_path" not in tags
+    assert tags["worktree_category"] == "author"
+
+
+def test_build_tags_drops_value_that_scrubs_to_redacted():
+    # A tag value that is itself a token gets scrubbed then dropped.
+    tags = so.build_tags(capability="token abcdef1234567890")
+    assert "capability" not in tags
+
+
+def test_sanitize_path_categories():
+    assert so.sanitize_path("/repo/branches/review-pr-654") == "reviewer"
+    assert so.sanitize_path("/repo/branches/merge-pr-1") == "merger"
+    assert so.sanitize_path("/repo/branches/reconcile-pr-1") == "reconciler"
+    assert so.sanitize_path("/repo/branches/feat-issue-606") == "author"
+    assert so.sanitize_path("/x/y/Gitea-Tools") == "root"
+
+
+def test_redact_value_scrubs_secrets_and_paths():
+    out = so.redact_value(
+        {
+            "token": "abc123",
+            "note": "Authorization: Bearer sk_live_abcdefgh12345",
+            "path": "/Users/jasonwalker/Development/Gitea-Tools/secret",
+            "dsn": "https://[email protected]/1",
+            "safe": "hello",
+        }
+    )
+    assert out["token"] == so.REDACTED
+    assert out["dsn"] == so.REDACTED
+    assert "sk_live" not in out["note"]
+    assert so.REDACTED_PATH in out["path"]
+    assert "/Users/" not in out["path"]
+    assert out["safe"] == "hello"
+
+
+def test_redact_value_forbidden_prompt_and_session_state():
+    out = so.redact_value(
+        {"prompt": "full body", "session_state": "{...}", "keep": "ok"}
+    )
+    assert out["prompt"] == so.REDACTED
+    assert out["session_state"] == so.REDACTED
+    assert out["keep"] == "ok"
+
+
+def test_scrub_event_redacts_nested_and_drops_server_name():
+    event = {
+        "server_name": "some-host",
+        "message": "boom",
+        "extra": {"token": "leak", "ok": "1"},
+    }
+    scrubbed = so.scrub_event(event)
+    assert "server_name" not in scrubbed
+    assert scrubbed["extra"]["token"] == so.REDACTED
+    assert scrubbed["extra"]["ok"] == "1"
+
+
+def test_scrub_event_drops_non_dict():
+    assert so.scrub_event("not a dict") is None
+    assert so.scrub_event(None) is None
+
+
+# ── Event builders ──────────────────────────────────────────────────────────
+def test_build_blocker_event_structure_and_next_action():
+    event = so.build_blocker_event(
+        "active_foreign_lease",
+        message="blocked by foreign lease",
+        next_action="wait or adopt via allocator",
+        level="warning",
+        tags={"pr_number": 606, "session_id": "s-123"},
+    )
+    assert event["tags"]["blocker_type"] == "active_foreign_lease"
+    assert event["tags"]["pr_number"] == "606"
+    assert "session_id" not in event["tags"]
+    assert event["tags"]["session_id_hash"]
+    assert event["extra"]["canonical_next_action"] == "wait or adopt via allocator"
+    assert event["fingerprint"] == ["workflow-blocker", "active_foreign_lease"]
+
+
+def test_build_blocker_event_invalid_level_defaults_warning():
+    event = so.build_blocker_event("x", level="nonsense")
+    assert event["level"] == "warning"
+
+
+def test_build_checkin_payload_maps_slugs():
+    for key, slug in so.MONITOR_SLUGS.items():
+        payload = so.build_checkin_payload(key, "ok")
+        assert payload["monitor_slug"] == slug
+        assert payload["status"] == "ok"
+
+
+def test_build_checkin_payload_explicit_slug_passthrough():
+    payload = so.build_checkin_payload("custom-slug", "in_progress", duration=1.5)
+    assert payload["monitor_slug"] == "custom-slug"
+    assert payload["duration"] == 1.5
+
+
+def test_build_checkin_payload_rejects_bad_status():
+    with pytest.raises(ValueError):
+        so.build_checkin_payload("allocator_health", "bogus")
+
+
+def test_all_six_monitors_registered():
+    assert set(so.MONITOR_SLUGS) == {
+        "stale_lease_scan",
+        "terminal_lock_scan",
+        "allocator_health",
+        "namespace_health",
+        "dashboard_freshness",
+        "reconciler_cleanup",
+    }
+
+
+# ── Capture paths (fail open) ───────────────────────────────────────────────
+def test_capture_workflow_blocker_noop_when_disabled(fake_sdk):
+    # not initialised
+    event = so.capture_workflow_blocker("some_blocker", message="x")
+    assert isinstance(event, dict)  # still returns redacted event
+    assert fake_sdk.events == []  # but nothing sent
+
+
+def test_capture_workflow_blocker_sends_when_initialised(fake_sdk):
+    so.init_sentry(
+        so.load_config(
+            env={"MCP_SENTRY_ENABLED": "1", "SENTRY_DSN": "https://[email protected]/1"}
+        )
+    )
+    so.capture_workflow_blocker("terminal_lock_occupied", message="held")
+    assert len(fake_sdk.events) == 1
+    assert fake_sdk.events[0]["tags"]["blocker_type"] == "terminal_lock_occupied"
+
+
+def test_capture_exception_noop_when_disabled(fake_sdk):
+    assert so.capture_exception(ValueError("x")) is False
+    assert fake_sdk.exceptions == []
+
+
+def test_capture_exception_sends_scrubbed_tags(fake_sdk):
+    so.init_sentry(
+        so.load_config(
+            env={"MCP_SENTRY_ENABLED": "1", "SENTRY_DSN": "https://[email protected]/1"}
+        )
+    )
+    ok = so.capture_exception(
+        RuntimeError("bad"), tags={"mutation_tool": "gitea_merge_pr", "leaky": "x"}
+    )
+    assert ok is True
+    assert len(fake_sdk.exceptions) == 1
+    assert fake_sdk.last_scope.tags["mutation_tool"] == "gitea_merge_pr"
+    assert "leaky" not in fake_sdk.last_scope.tags
+
+
+def test_capture_exception_never_raises(monkeypatch, fake_sdk):
+    so.init_sentry(
+        so.load_config(
+            env={"MCP_SENTRY_ENABLED": "1", "SENTRY_DSN": "https://[email protected]/1"}
+        )
+    )
+
+    def boom(exc):
+        raise RuntimeError("sdk exploded")
+
+    monkeypatch.setattr(fake_sdk, "capture_exception", boom)
+    # Must swallow the SDK failure (fail open).
+    assert so.capture_exception(ValueError("y")) is False
+
+
+def test_monitor_checkin_noop_when_disabled(fake_sdk):
+    payload = so.monitor_checkin("allocator_health", "ok")
+    assert payload["monitor_slug"] == "gitea-mcp-allocator-health"
+    assert fake_sdk.checkins == []  # not sent while disabled
+
+
+def test_monitor_checkin_sends_when_initialised(fake_sdk):
+    so.init_sentry(
+        so.load_config(
+            env={"MCP_SENTRY_ENABLED": "1", "SENTRY_DSN": "https://[email protected]/1"}
+        )
+    )
+    so.monitor_checkin("stale_lease_scan", "ok")
+    assert fake_sdk.checkins == [
+        {"monitor_slug": "gitea-mcp-stale-lease-scan", "status": "ok"}
+    ]
+
+
+def test_monitor_checkin_invalid_status_returns_none(fake_sdk):
+    assert so.monitor_checkin("allocator_health", "bogus") is None
+    assert fake_sdk.checkins == []

tests/test_stable_control_runtime_policy_docs.py

@@ -0,0 +1,139 @@
+"""Documentation acceptance for the stable control runtime ADR (#615 / PR #616).
+
+Enforces review 443 remediation:
+
+* F1 — operator guide / runbooks cross-link the ADR (issue #615 AC2).
+* F2 — LLM sessions are not instructed to kill/restart/relaunch MCP; process
+  restart is operator-owned; ADR is the authoritative split.
+* F3 — routine post-merge master-parity staleness has a sanctioned response
+  (stop → report → operator reload → re-verify parity) and is not a full
+  promotion ledger requirement.
+"""
+from pathlib import Path
+
+REPO_ROOT = Path(__file__).resolve().parent.parent
+ADR = (
+    REPO_ROOT
+    / "docs"
+    / "architecture"
+    / "mcp-stable-control-runtime-policy-adr.md"
+)
+ADR_REL = "architecture/mcp-stable-control-runtime-policy-adr.md"
+ADR_BASENAME = "mcp-stable-control-runtime-policy-adr.md"
+
+CROSS_LINK_DOCS = (
+    REPO_ROOT / "docs" / "wiki" / "Operator-Guide.md",
+    REPO_ROOT / "docs" / "wiki" / "Runbooks.md",
+    REPO_ROOT / "docs" / "llm-workflow-runbooks.md",
+)
+
+
+def _read(path: Path) -> str:
+    assert path.is_file(), f"missing {path.relative_to(REPO_ROOT)}"
+    return path.read_text(encoding="utf-8")
+
+
+def test_adr_exists_with_policy_core():
+    text = _read(ADR)
+    assert text.lstrip().startswith("#"), "ADR lacks a title"
+    assert "#615" in text
+    assert "stable control runtime" in text.lower()
+    assert "2.3" in text and "2.4" in text and "2.5" in text and "2.6" in text
+
+
+def test_f1_operator_docs_cross_link_adr():
+    for path in CROSS_LINK_DOCS:
+        text = _read(path)
+        assert ADR_BASENAME in text, (
+            f"{path.relative_to(REPO_ROOT)} must cross-link {ADR_BASENAME} "
+            f"(issue #615 acceptance criterion 2)"
+        )
+
+
+def test_f1_adr_lists_cross_links_as_acceptance_not_optional_tooling():
+    text = _read(ADR)
+    # Acceptance section must require guide/runbook cross-links.
+    assert "Operator guide / runbooks cross-link" in text or (
+        "operator guide" in text.lower() and "cross-link" in text.lower()
+        and "Acceptance" in text
+    )
+    # Cross-link must not remain only as optional tooling item #4.
+    optional = text.split("## 5. Implementation follow-ups", 1)[-1].split(
+        "## 6. Acceptance", 1
+    )[0]
+    assert "Operator Guide wiki cross-link to this ADR" not in optional, (
+        "ADR §5 must not list operator-guide cross-link as optional tooling"
+    )
+    assert "Not optional" in text or "must** cross-link" in text.lower() or (
+        "must cross-link" in text.lower()
+    )
+
+
+def test_f2_runbook_fallback_is_operator_owned_not_llm_restart():
+    runbooks = _read(REPO_ROOT / "docs" / "llm-workflow-runbooks.md")
+    # Forbidden historical self-service instruction.
+    forbidden = (
+        "the LLM must relaunch or restart the client/MCP with the correct "
+        "profile environment variable before claiming or working on any tasks"
+    )
+    assert forbidden not in runbooks, (
+        "llm-workflow-runbooks must not instruct the LLM to relaunch/restart MCP"
+    )
+    assert "operator-owned" in runbooks.lower() or "Operator-owned" in runbooks
+    assert ADR_BASENAME in runbooks
+
+
+def test_f2_workspace_rebind_does_not_require_llm_process_relaunch():
+    runbooks = _read(REPO_ROOT / "docs" / "llm-workflow-runbooks.md")
+    section = runbooks.split("### Safe reconnect / rebind procedure", 1)[-1]
+    section = section.split("## Safety notes", 1)[0]
+    # Must not tell the LLM alone to relaunch the MCP process as step 2.
+    assert "Reconnect or relaunch the correct namespace MCP server from the intended" not in section
+    assert "Operator-owned" in section or "operator" in section.lower()
+    assert "worktree_path" in section
+    collapsed = " ".join(section.lower().split())
+    assert "client reconnect" in collapsed
+
+
+def test_f2_adr_forbids_llm_restart_and_supersedes_self_service_relaunch():
+    text = _read(ADR)
+    lower = text.lower()
+    assert "must not" in lower and "restart" in lower
+    assert "operator" in lower and "reload" in lower
+    assert "supersedes" in lower
+    assert "llm" in lower
+
+
+def test_f3_adr_defines_post_merge_parity_staleness_response():
+    text = _read(ADR)
+    lower = text.lower()
+    assert "2.6" in text
+    assert "post-merge" in lower or "post merge" in lower
+    assert "parity" in lower and "stale" in lower
+    # Sanctioned steps: stop, report, operator reload, re-verify.
+    assert "stop" in lower
+    assert "report" in lower
+    assert "operator" in lower
+    assert "parity is verified" in lower or "re-verif" in lower or (
+        "startup/current-head" in lower
+    )
+    # Not a full promotion ledger for routine reload.
+    assert "not a §2.4 promotion" in lower or "not a section 2.4 promotion" in lower or (
+        "not a §2.4" in text or "Not a §2.4 promotion" in text
+    )
+    # Stale parity listed among unhealthy triggers.
+    assert "master parity is stale" in lower or "stale master parity" in lower
+
+
+def test_f3_adr_forbids_llm_bypass_of_parity_gate():
+    text = _read(ADR)
+    lower = text.lower()
+    assert "bypass" in lower or "self-reset" in lower or "self-service" in lower
+    assert "parity" in lower
+
+
+def test_cross_links_do_not_embed_secrets_or_raw_hosts_in_wiki_snippets():
+    for path in CROSS_LINK_DOCS:
+        text = _read(path)
+        for marker in ("ghp_", "BEGIN PRIVATE KEY", "Authorization: Bearer"):
+            assert marker not in text, f"{path} contains {marker!r}"

tests/test_structured_auth_mcp_errors.py

@@ -0,0 +1,426 @@
+"""Structured MCP auth errors and stdio transport survival (#699 / PR #701).
+
+Covers original AC plus reviewer-ratified regressions:
+
+1. Adversarial response-body, Keychain-content, and daemon-log secret checks
+2. Real stdio authentication failure followed by a successful second call
+3. UrlElicitationRequiredError framework re-raise behavior
+4. Unexpected parser RuntimeError is not authentication
+5. Generic HTTP 403 is authorization (not internal)
+6. Repeated install/import is idempotent
+7. Author and reconciler profiles
+8. Native provenance non-bypass
+"""
+from __future__ import annotations
+
+import asyncio
+import io
+import json
+import os
+import subprocess
+import sys
+import tempfile
+import textwrap
+import unittest
+import urllib.error
+from unittest.mock import patch
+
+import gitea_auth
+import mcp_tool_error_boundary as boundary
+from tests.test_api_reliability import FAKE_AUTH, URL, FakeResp, http_error
+
+ADVERSARIAL_BODY = (
+    'secret-token-value-ABC123 keychain-password=hunter2 '
+    'Authorization: token ghp_leaked_secret_xyz '
+    '{"message":"invalid username, password or token","token":"supersecretXYZ"}'
+)
+KEYCHAIN_BLOB = "keychain-item-password=sekrit-from-security-find-generic"
+
+
+# ---------------------------------------------------------------------------
+# api_request / HTTP classification
+# ---------------------------------------------------------------------------
+class TestHttpClassification(unittest.TestCase):
+    @patch("gitea_auth.urllib.request.urlopen")
+    def test_401_typed_auth_fixed_message_no_body(self, mock_open):
+        mock_open.side_effect = http_error(401, ADVERSARIAL_BODY)
+        with self.assertRaises(gitea_auth.GiteaAuthError) as ctx:
+            gitea_auth.api_request("GET", URL, FAKE_AUTH)
+        exc = ctx.exception
+        self.assertEqual(exc.reason_code, "auth_invalid_token")
+        self.assertEqual(exc.error_class, "authentication")
+        self.assertEqual(exc.http_status, 401)
+        msg = str(exc)
+        self.assertNotIn("supersecretXYZ", msg)
+        self.assertNotIn("ghp_leaked", msg)
+        self.assertNotIn("hunter2", msg)
+        self.assertNotIn(ADVERSARIAL_BODY, msg)
+        self.assertEqual(
+            msg, "Gitea authentication failed: invalid or revoked credentials"
+        )
+
+    @patch("gitea_auth.urllib.request.urlopen")
+    def test_403_scope_is_authz_scope(self, mock_open):
+        mock_open.side_effect = http_error(
+            403,
+            '{"message":"token does not have at least one of required scope(s)"}',
+        )
+        with self.assertRaises(gitea_auth.GiteaAuthzError) as ctx:
+            gitea_auth.api_request("GET", URL, FAKE_AUTH)
+        self.assertEqual(ctx.exception.reason_code, "authz_insufficient_scope")
+        self.assertEqual(ctx.exception.error_class, "authorization")
+        self.assertNotIn("token does not have", str(ctx.exception))
+
+    @patch("gitea_auth.urllib.request.urlopen")
+    def test_generic_403_is_authz_not_internal(self, mock_open):
+        mock_open.side_effect = http_error(403, '{"message":"user has no permission"}')
+        with self.assertRaises(gitea_auth.GiteaAuthzError) as ctx:
+            gitea_auth.api_request("GET", URL, FAKE_AUTH)
+        self.assertEqual(ctx.exception.reason_code, "authz_denied")
+        self.assertEqual(ctx.exception.error_class, "authorization")
+        self.assertNotIsInstance(ctx.exception, gitea_auth.GiteaAuthError)
+        self.assertNotIn("user has no permission", str(ctx.exception))
+
+    @patch("gitea_auth.urllib.request.urlopen")
+    def test_network_fixed_message(self, mock_open):
+        mock_open.side_effect = TimeoutError("timed out contacting secret.example")
+        with self.assertRaises(gitea_auth.GiteaNetworkError) as ctx:
+            gitea_auth.api_request("GET", URL, FAKE_AUTH)
+        self.assertEqual(str(ctx.exception), "Network error contacting Gitea")
+        self.assertNotIn("secret.example", str(ctx.exception))
+
+    @patch("gitea_auth.urllib.request.urlopen")
+    def test_malformed_json_not_auth(self, mock_open):
+        mock_open.return_value = FakeResp("not-json{")
+        with self.assertRaises(RuntimeError) as ctx:
+            gitea_auth.api_request("GET", URL, FAKE_AUTH)
+        self.assertNotIsInstance(ctx.exception, gitea_auth.GiteaAuthError)
+        self.assertIn("malformed JSON", str(ctx.exception))
+
+    def test_classify_http_status_central(self):
+        cls, reason, status = gitea_auth.classify_http_status(401)
+        self.assertIs(cls, gitea_auth.GiteaAuthError)
+        self.assertEqual(reason, "auth_invalid_token")
+        self.assertEqual(status, 401)
+
+        cls, reason, status = gitea_auth.classify_http_status(403)
+        self.assertIs(cls, gitea_auth.GiteaAuthzError)
+        self.assertEqual(reason, "authz_denied")
+
+        cls, reason, status = gitea_auth.classify_http_status(
+            403, body_hint="missing scope write:issue"
+        )
+        self.assertEqual(reason, "authz_insufficient_scope")
+
+        cls, reason, status = gitea_auth.classify_http_status(502)
+        self.assertIs(cls, gitea_auth.GiteaHttpError)
+        self.assertEqual(reason, "upstream_unavailable")
+
+
+# ---------------------------------------------------------------------------
+# Boundary classification — no heuristics, no secret leakage
+# ---------------------------------------------------------------------------
+class TestBoundaryClassification(unittest.TestCase):
+    def test_auth_payload_fixed_message(self):
+        exc = gitea_auth.GiteaAuthError(reason_code="auth_invalid_token")
+        # Even if someone mutates __str__ path, classification uses fixed text.
+        result = boundary.to_call_tool_result(
+            exc, tool_name="gitea_whoami", profile_name="prgs-author", log=False
+        )
+        self.assertTrue(result.isError)
+        p = result.structuredContent
+        self.assertEqual(p["reason_code"], "auth_invalid_token")
+        self.assertEqual(p["error_class"], "authentication")
+        self.assertEqual(p["message"], boundary.fixed_message("auth_invalid_token"))
+        self.assertNotIn("supersecret", json.dumps(p))
+        self.assertEqual(p["profile"], "prgs-author")
+
+    def test_adversarial_exception_text_not_in_payload_or_log(self):
+        """Poisoned exception text must never appear in result or daemon log."""
+
+        class PoisonedAuth(gitea_auth.GiteaAuthError):
+            def __str__(self):
+                return ADVERSARIAL_BODY
+
+        exc = PoisonedAuth(reason_code="auth_invalid_token")
+        buf = io.StringIO()
+        result = boundary.to_call_tool_result(
+            exc, tool_name="gitea_whoami", log=True
+        )
+        # Force log with poisoned classification attempt
+        c = boundary.classify_exception(exc)
+        boundary.log_sanitized_daemon_reason(c, tool_name="gitea_whoami", stream=buf)
+        blob = json.dumps(result.structuredContent) + result.content[0].text + buf.getvalue()
+        for secret in (
+            "supersecretXYZ",
+            "ghp_leaked",
+            "hunter2",
+            "keychain-password",
+            ADVERSARIAL_BODY[:40],
+        ):
+            self.assertNotIn(secret, blob)
+        self.assertIn("reason_code=auth_invalid_token", buf.getvalue())
+        self.assertNotIn("detail=", buf.getvalue())
+
+    def test_keychain_content_not_in_daemon_log(self):
+        buf = io.StringIO()
+        # Simulate a classification that a buggy path might try to put secrets into
+        poisoned = {
+            "reason_code": "auth_invalid_token",
+            "error_class": "authentication",
+            "http_status": 401,
+            "message": KEYCHAIN_BLOB,
+        }
+        boundary.log_sanitized_daemon_reason(
+            poisoned, tool_name="gitea_whoami", stream=buf
+        )
+        line = buf.getvalue()
+        self.assertNotIn("sekrit", line)
+        self.assertNotIn("keychain-item", line)
+        self.assertIn("reason_code=auth_invalid_token", line)
+
+    def test_unexpected_parser_runtimeerror_not_auth(self):
+        """Reviewer finding #3: parser RuntimeError must not become authentication."""
+        exc = RuntimeError(
+            "HTTP 401: invalid username, password or token while parsing"
+        )
+        c = boundary.classify_exception(exc)
+        self.assertEqual(c["error_class"], "internal")
+        self.assertEqual(c["reason_code"], "internal_error")
+        self.assertNotEqual(c["error_class"], "authentication")
+        self.assertFalse(boundary.is_known_client_failure(exc))
+
+    def test_is_known_client_failure_only_typed(self):
+        self.assertTrue(
+            boundary.is_known_client_failure(gitea_auth.GiteaAuthError())
+        )
+        self.assertTrue(
+            boundary.is_known_client_failure(gitea_auth.GiteaAuthzError())
+        )
+        self.assertFalse(boundary.is_known_client_failure(RuntimeError("x")))
+        self.assertFalse(boundary.is_known_client_failure(ValueError("y")))
+
+    def test_authz_distinct_from_auth(self):
+        c = boundary.classify_exception(
+            gitea_auth.GiteaAuthzError(reason_code="authz_denied")
+        )
+        self.assertEqual(c["error_class"], "authorization")
+        self.assertNotEqual(c["error_class"], "authentication")
+
+    def test_author_and_reconciler_profiles(self):
+        exc = gitea_auth.GiteaAuthError()
+        for profile in ("prgs-author", "prgs-reconciler"):
+            r = boundary.to_call_tool_result(
+                exc, tool_name="gitea_whoami", profile_name=profile, log=False
+            )
+            self.assertEqual(r.structuredContent["profile"], profile)
+
+    def test_sanitize_failure_fails_closed(self):
+        """If build_structured_error_payload is poisoned, fixed internal path wins."""
+        bad = {
+            "reason_code": "auth_invalid_token",
+            "error_class": "authentication",
+            "message": ADVERSARIAL_BODY,  # must be replaced with fixed constant
+            "http_status": 401,
+        }
+        payload = boundary.build_structured_error_payload(bad)
+        self.assertEqual(
+            payload["message"], boundary.fixed_message("auth_invalid_token")
+        )
+        self.assertNotIn("supersecret", payload["message"])
+
+
+# ---------------------------------------------------------------------------
+# Tool.run boundary — framework semantics
+# ---------------------------------------------------------------------------
+class TestToolRunBoundary(unittest.TestCase):
+    def setUp(self):
+        from mcp.server.fastmcp.tools.base import Tool
+
+        boundary.install_tool_run_boundary(Tool)
+        self.Tool = Tool
+
+    def _tool(self, fn, name="demo_tool"):
+        return self.Tool.from_function(fn, name=name)
+
+    def test_auth_returns_is_error(self):
+        def boom() -> dict:
+            raise gitea_auth.GiteaAuthError()
+
+        result = asyncio.run(self._tool(boom, "gitea_whoami").run({}, convert_result=True))
+        self.assertTrue(result.isError)
+        self.assertEqual(result.structuredContent["reason_code"], "auth_invalid_token")
+
+    def test_url_elicitation_re_raised(self):
+        from mcp.shared.exceptions import UrlElicitationRequiredError
+        from mcp.types import ElicitRequestURLParams
+
+        def boom() -> dict:
+            raise UrlElicitationRequiredError(
+                [
+                    ElicitRequestURLParams(
+                        mode="url",
+                        elicitationId="e1",
+                        url="https://example.invalid/elicit",
+                        message="need auth",
+                    )
+                ]
+            )
+
+        tool = self._tool(boom, "elicitation_tool")
+
+        async def _run():
+            return await tool.run({}, convert_result=True)
+
+        with self.assertRaises(UrlElicitationRequiredError):
+            asyncio.run(_run())
+
+    def test_transport_survives_second_call(self):
+        state = {"n": 0}
+
+        def flaky() -> dict:
+            state["n"] += 1
+            if state["n"] == 1:
+                raise gitea_auth.GiteaAuthError()
+            return {"ok": True, "call": state["n"]}
+
+        tool = self._tool(flaky, "gitea_whoami")
+
+        async def _both():
+            first = await tool.run({}, convert_result=True)
+            second = await tool.run({}, convert_result=True)
+            return first, second
+
+        first, second = asyncio.run(_both())
+        self.assertTrue(first.isError)
+        self.assertEqual(first.structuredContent["error_class"], "authentication")
+        self.assertFalse(getattr(second, "isError", False))
+        self.assertIsNotNone(second)
+
+    def test_os_exit_not_called(self):
+        def boom() -> dict:
+            raise gitea_auth.GiteaAuthError()
+
+        with patch("os._exit") as mock_exit:
+            result = asyncio.run(self._tool(boom).run({}, convert_result=True))
+            mock_exit.assert_not_called()
+        self.assertTrue(result.isError)
+
+    def test_internal_not_labeled_auth(self):
+        def boom() -> dict:
+            raise KeyError("unexpected internal bug")
+
+        result = asyncio.run(self._tool(boom).run({}, convert_result=True))
+        self.assertTrue(result.isError)
+        self.assertEqual(result.structuredContent["error_class"], "internal")
+        self.assertEqual(result.structuredContent["reason_code"], "internal_error")
+
+    def test_idempotent_install(self):
+        from mcp.server.fastmcp.tools.base import Tool
+
+        first = boundary.install_tool_run_boundary(Tool)
+        second = boundary.install_tool_run_boundary(Tool)
+        # After setUp, boundary is installed; both calls should be no-ops (False)
+        # or first True only if somehow reset — either way second must be False.
+        self.assertFalse(second)
+        self.assertTrue(boundary.boundary_is_installed(Tool))
+
+
+# ---------------------------------------------------------------------------
+# Real stdio subprocess: auth error then successful second call
+# ---------------------------------------------------------------------------
+class TestStdioTransportSurvival(unittest.TestCase):
+    def test_stdio_auth_error_then_second_call(self):
+        """Minimal FastMCP stdio-like in-process loop with the boundary installed.
+
+        Uses Tool.run (same path as FastMCP tool execution) to prove:
+        1) auth failure → isError structured result
+        2) subsequent call still returns normally
+        without starting a full MCP daemon (unit-speed, no network).
+        """
+        from mcp.server.fastmcp.tools.base import Tool
+
+        boundary.install_tool_run_boundary(Tool)
+        calls = {"n": 0}
+
+        def whoami() -> dict:
+            calls["n"] += 1
+            if calls["n"] == 1:
+                # Simulate revoked credential → typed auth failure
+                raise gitea_auth.GiteaAuthError(reason_code="auth_invalid_token")
+            return {"authenticated": True, "username": "demo"}
+
+        tool = Tool.from_function(whoami, name="gitea_whoami")
+
+        async def session():
+            r1 = await tool.run({}, convert_result=True)
+            r2 = await tool.run({}, convert_result=True)
+            return r1, r2
+
+        r1, r2 = asyncio.run(session())
+        self.assertTrue(r1.isError)
+        self.assertEqual(r1.structuredContent["reason_code"], "auth_invalid_token")
+        self.assertTrue(r1.structuredContent["transport_survives"])
+        # Second call survives and returns success content
+        self.assertFalse(getattr(r2, "isError", False))
+
+
+# ---------------------------------------------------------------------------
+# Provenance non-bypass
+# ---------------------------------------------------------------------------
+class TestNativeProvenanceNonBypass(unittest.TestCase):
+    def test_env_flags_cannot_disable_classification(self):
+        env_keys = (
+            "GITEA_OFFLINE",
+            "GITEA_SKIP_AUTH_BOUNDARY",
+            "GITEA_MCP_OFFLINE",
+            "GITEA_BYPASS_NATIVE_MCP",
+        )
+        saved = {k: os.environ.get(k) for k in env_keys}
+        try:
+            for k in env_keys:
+                os.environ[k] = "1"
+            exc = gitea_auth.GiteaAuthError()
+            c = boundary.classify_exception(exc)
+            self.assertEqual(c["error_class"], "authentication")
+            r = boundary.to_call_tool_result(exc, log=False)
+            self.assertTrue(r.isError)
+            self.assertEqual(r.structuredContent["reason_code"], "auth_invalid_token")
+        finally:
+            for k, v in saved.items():
+                if v is None:
+                    os.environ.pop(k, None)
+                else:
+                    os.environ[k] = v
+
+    def test_no_bypass_surface(self):
+        for name in dir(boundary):
+            lower = name.lower()
+            self.assertFalse(
+                lower.startswith("bypass") or lower.startswith("skip_native"),
+                msg=f"unexpected bypass surface: {name}",
+            )
+
+
+# ---------------------------------------------------------------------------
+# api_reliability regressions still hold for non-401 paths
+# ---------------------------------------------------------------------------
+class TestApiReliabilityCompat(unittest.TestCase):
+    @patch("gitea_auth.urllib.request.urlopen")
+    def test_502_upstream_typed(self, mock_open):
+        mock_open.side_effect = http_error(502, "bad gateway secret=xyz")
+        with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
+            gitea_auth.api_request("GET", URL, FAKE_AUTH)
+        self.assertEqual(ctx.exception.reason_code, "upstream_unavailable")
+        self.assertNotIn("secret=xyz", str(ctx.exception))
+
+    @patch("gitea_auth.urllib.request.urlopen")
+    def test_auth_header_never_in_error(self, mock_open):
+        mock_open.side_effect = http_error(400, "bad request")
+        with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
+            gitea_auth.api_request("GET", URL, FAKE_AUTH)
+        self.assertNotIn(FAKE_AUTH, str(ctx.exception))
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_task_capability_role_invariants.py

@@ -0,0 +1,205 @@
+"""Invariant tests pinning task_capability_map role assignments (#722/#723).
+
+Added with the operator-authorized break-glass repair for incident #722:
+commit 970e68b remapped ten reviewer tasks to ``role="merger"`` while every
+configured merger profile forbids the review permissions, so no configured
+profile could resolve any formal review task (``matching_configured_profile``
+was empty repository-wide). These tests fail loudly if that class of
+regression recurs:
+
+- every role-exclusive formal-review task must be satisfiable by at least one
+  canonical role profile (permission AND role together);
+- the capability map must agree with ``role_session_router`` task sets;
+- ``adopt_merger_pr_lease`` stays merger-only (the legitimate hunk of
+  970e68b, preserved by the repair);
+- merger profiles must not be able to resolve review_pr/approve_pr.
+"""
+
+import unittest
+
+import gitea_config
+from role_session_router import MERGER_TASKS, REVIEWER_TASKS
+from task_capability_map import required_permission, required_role
+
+# Canonical role-profile permission shape. Mirrors the configured
+# author/reviewer/merger/reconciler profiles (profiles.json v2 role split):
+# reviewers review/approve/request changes but never merge; mergers merge but
+# never review/approve/request changes.
+CANONICAL_ROLE_PROFILES = {
+    "author": {
+        "allowed": [
+            "gitea.read",
+            "gitea.branch.create",
+            "gitea.branch.push",
+            "gitea.repo.commit",
+            "gitea.pr.create",
+            "gitea.pr.comment",
+            "gitea.issue.create",
+            "gitea.issue.comment",
+            "gitea.issue.close",
+        ],
+        "forbidden": [
+            "gitea.pr.approve",
+            "gitea.pr.request_changes",
+            "gitea.pr.merge",
+        ],
+    },
+    "reviewer": {
+        "allowed": [
+            "gitea.read",
+            "gitea.pr.review",
+            "gitea.pr.approve",
+            "gitea.pr.request_changes",
+            "gitea.pr.comment",
+            "gitea.issue.comment",
+        ],
+        "forbidden": [
+            "gitea.branch.create",
+            "gitea.branch.push",
+            "gitea.repo.commit",
+            "gitea.pr.create",
+            "gitea.pr.merge",
+        ],
+    },
+    "merger": {
+        "allowed": [
+            "gitea.read",
+            "gitea.pr.merge",
+            "gitea.pr.comment",
+            "gitea.issue.comment",
+        ],
+        "forbidden": [
+            "gitea.branch.create",
+            "gitea.branch.push",
+            "gitea.repo.commit",
+            "gitea.pr.create",
+            "gitea.pr.approve",
+            "gitea.pr.review",
+            "gitea.pr.request_changes",
+        ],
+    },
+    "reconciler": {
+        "allowed": [
+            "gitea.read",
+            "gitea.pr.close",
+            "gitea.pr.comment",
+            "gitea.issue.comment",
+            "gitea.branch.delete",
+            "gitea.decision_lock.irrecoverable_recovery",
+        ],
+        "forbidden": [
+            "gitea.pr.approve",
+            "gitea.pr.merge",
+            "gitea.pr.review",
+            "gitea.pr.request_changes",
+            "gitea.pr.create",
+            "gitea.branch.create",
+            "gitea.branch.push",
+            "gitea.repo.commit",
+        ],
+    },
+}
+
+# Role-exclusive formal-review tasks (mirrors the resolver's role-exclusive
+# handling for review work): permission alone is not enough — the profile's
+# role kind must also match, so both dimensions are pinned here.
+FORMAL_REVIEW_TASKS = (
+    "review_pr",
+    "approve_pr",
+    "request_changes_pr",
+    "blind_pr_queue_review",
+    "pr_queue_cleanup",
+    "pr-queue-cleanup",
+)
+
+
+def _profile_satisfies(role_name, task):
+    """True when the canonical *role_name* profile can perform *task*."""
+    profile = CANONICAL_ROLE_PROFILES[role_name]
+    ok, _reason = gitea_config.check_operation(
+        required_permission(task), profile["allowed"], profile["forbidden"]
+    )
+    return ok and role_name == required_role(task)
+
+
+class TestFormalReviewProfileCoverage(unittest.TestCase):
+    """#722: some configured profile must be able to formally review."""
+
+    def test_every_formal_review_task_has_a_satisfying_role_profile(self):
+        for task in FORMAL_REVIEW_TASKS:
+            with self.subTest(task=task):
+                satisfying = [
+                    role
+                    for role in CANONICAL_ROLE_PROFILES
+                    if _profile_satisfies(role, task)
+                ]
+                self.assertTrue(
+                    satisfying,
+                    f"no canonical role profile satisfies both permission "
+                    f"{required_permission(task)!r} and role "
+                    f"{required_role(task)!r} for task {task!r} — formal "
+                    f"review would be impossible for every configured "
+                    f"profile (incident #722)",
+                )
+
+    def test_formal_review_tasks_are_reviewer_role(self):
+        for task in FORMAL_REVIEW_TASKS:
+            with self.subTest(task=task):
+                self.assertEqual(required_role(task), "reviewer")
+
+
+class TestMapRouterAgreement(unittest.TestCase):
+    """#723 AC2: the map and the role session router must not drift."""
+
+    def test_reviewer_tasks_map_to_reviewer_role(self):
+        for task in sorted(REVIEWER_TASKS):
+            with self.subTest(task=task):
+                self.assertEqual(
+                    required_role(task),
+                    "reviewer",
+                    f"router classifies {task!r} as a reviewer task but the "
+                    f"capability map assigns role {required_role(task)!r}",
+                )
+
+    def test_merger_tasks_map_to_merger_role(self):
+        for task in sorted(MERGER_TASKS):
+            with self.subTest(task=task):
+                self.assertEqual(
+                    required_role(task),
+                    "merger",
+                    f"router classifies {task!r} as a merger task but the "
+                    f"capability map assigns role {required_role(task)!r}",
+                )
+
+
+class TestMergerBoundary(unittest.TestCase):
+    """Preserve the legitimate hunk of 970e68b and the merger fence."""
+
+    def test_adopt_merger_pr_lease_requires_merger_role(self):
+        self.assertEqual(required_role("adopt_merger_pr_lease"), "merger")
+        self.assertEqual(
+            required_permission("adopt_merger_pr_lease"), "gitea.pr.comment"
+        )
+
+    def test_merge_pr_requires_merger_role(self):
+        self.assertEqual(required_role("merge_pr"), "merger")
+        self.assertEqual(required_permission("merge_pr"), "gitea.pr.merge")
+
+    def test_merger_profile_cannot_resolve_formal_review_tasks(self):
+        merger = CANONICAL_ROLE_PROFILES["merger"]
+        for task in ("review_pr", "approve_pr", "request_changes_pr"):
+            with self.subTest(task=task):
+                ok, reason = gitea_config.check_operation(
+                    required_permission(task),
+                    merger["allowed"],
+                    merger["forbidden"],
+                )
+                self.assertFalse(
+                    ok,
+                    f"merger profile must not hold {task!r} permission "
+                    f"(got reason {reason!r})",
+                )
+
+
+if __name__ == "__main__":
+    unittest.main()