feat(restart): audit lifecycle events and durable incidents (#665)

Add restart_audit with mcp.restart.* event schema, redacted emission via
gitea_audit, correlation ids, and incident materialization for failed drain
and break-glass. Wire gitea_request_mcp_restart to always audit impact
previews and fail closed on privileged apply when the audit sink is enabled
but write fails.

Closes #665

allocator_service.py

@@ -23,7 +23,6 @@ import json
 import os
 import uuid
 from dataclasses import dataclass, field
-from datetime import datetime, timezone
 from typing import Any, Mapping, Sequence
 
 from control_plane_db import (
@@ -739,46 +738,6 @@ def normalize_exclude_issue_numbers(
     return sorted(out)
 
 
-def _claim_expires_at(claim: Any) -> datetime | None:
-    """Parse a claim's ``expires_at``, or ``None`` when it is absent/malformed."""
-    if not isinstance(claim, Mapping):
-        return None
-    text = str(claim.get("expires_at") or "").strip()
-    if not text:
-        return None
-    if text.endswith("Z"):
-        text = text[:-1] + "+00:00"
-    try:
-        parsed = datetime.fromisoformat(text)
-    except ValueError:
-        return None
-    if parsed.tzinfo is None:
-        parsed = parsed.replace(tzinfo=timezone.utc)
-    return parsed.astimezone(timezone.utc)
-
-
-def _drop_expired_claims(
-    claims: Mapping[tuple[str, int], dict[str, Any]],
-    *,
-    now: datetime | None = None,
-) -> dict[tuple[str, int], dict[str, Any]]:
-    """Claims minus those whose lease has already expired (#643).
-
-    The read-only mirror of ``expire_stale_leases``: the sweep marks such rows
-    ``expired`` so they stop being returned as claims, and this reaches the same
-    view without writing. A claim with no parseable ``expires_at`` is **kept** —
-    an unreadable expiry is not evidence that work is free.
-    """
-    moment = now or datetime.now(timezone.utc)
-    kept: dict[tuple[str, int], dict[str, Any]] = {}
-    for key, claim in (claims or {}).items():
-        expires_at = _claim_expires_at(claim)
-        if expires_at is not None and expires_at <= moment:
-            continue
-        kept[key] = claim
-    return kept
-
-
 def candidate_set_fingerprint(
     candidates: Sequence[WorkCandidate],
     *,
@@ -867,22 +826,12 @@ def allocate_next_work(
     exclude_issue_numbers: Sequence[int] | None = None,
     expected_candidate_set_fingerprint: str | None = None,
     allocation_mode: str | None = None,
-    side_effect_free: bool = False,
 ) -> dict[str, Any]:
     """Select and optionally reserve the next work unit via control-plane DB.
 
     *apply=False* (default): dry-run selection only — no lease/assignment.
     *apply=True*: atomic ``assign_and_lease`` for the selected candidate.
 
-    *side_effect_free* (#643): a dry run that writes **nothing** to the
-    control-plane DB. A plain ``apply=False`` still registered a session row and
-    swept stale leases globally, so a caller advertising a read-only preview was
-    mutating on every call. Under this flag both writes are suppressed and stale
-    leases are instead filtered out of the claim map in memory, which yields the
-    same selection the sweep would have produced without persisting anything.
-    Incompatible with *apply* — the combination fails closed rather than
-    silently reserving.
-
     *allocation_mode* (#840): ``cross_role`` (default for controller) inspects
     the complete queue and returns one authoritative selection naming the
     required downstream role/profile/action. ``role_scoped`` keeps prior
@@ -936,57 +885,40 @@ def allocate_next_work(
             "allocation_mode": (allocation_mode or "").strip() or None,
         }
 
-    # A side-effect-free run may never reserve: reserving is a write, and the
-    # flag is the caller's assertion that this call writes nothing (#643).
-    if side_effect_free and apply:
+    session_id = (session_id or "").strip() or f"alloc-{uuid.uuid4().hex[:12]}"
+    try:
+        db.upsert_session(
+            session_id=session_id,
+            role=role_norm,
+            profile=profile_name,
+            pid=os.getpid(),
+            controller_instance_id=controller_instance_id,
+        )
+    except Exception as exc:  # noqa: BLE001 — surface structured
         return {
             "success": False,
             "outcome": OUTCOME_NO_SAFE,
-            "apply": True,
             "reasons": [
-                "side_effect_free is incompatible with apply=True; an "
-                "assignment is a write (fail closed, #643)"
+                f"failed to register session in control-plane DB: {exc} "
+                "(fail closed, #613)"
             ],
             "skipped": [],
             "assignment": None,
             "substrate": "control_plane_db",
         }
 
-    session_id = (session_id or "").strip() or f"alloc-{uuid.uuid4().hex[:12]}"
-    if not side_effect_free:
-        try:
-            db.upsert_session(
-                session_id=session_id,
-                role=role_norm,
-                profile=profile_name,
-                pid=os.getpid(),
-                controller_instance_id=controller_instance_id,
-            )
-        except Exception as exc:  # noqa: BLE001 — surface structured
-            return {
-                "success": False,
-                "outcome": OUTCOME_NO_SAFE,
-                "reasons": [
-                    f"failed to register session in control-plane DB: {exc} "
-                    "(fail closed, #613)"
-                ],
-                "skipped": [],
-                "assignment": None,
-                "substrate": "control_plane_db",
-            }
-
-        # Expire stale leases globally before selection.
-        try:
-            db.expire_stale_leases()
-        except Exception as exc:  # noqa: BLE001
-            return {
-                "success": False,
-                "outcome": OUTCOME_NO_SAFE,
-                "reasons": [f"lease expiry failed: {exc} (fail closed)"],
-                "skipped": [],
-                "assignment": None,
-                "substrate": "control_plane_db",
-            }
+    # Expire stale leases globally before selection.
+    try:
+        db.expire_stale_leases()
+    except Exception as exc:  # noqa: BLE001
+        return {
+            "success": False,
+            "outcome": OUTCOME_NO_SAFE,
+            "reasons": [f"lease expiry failed: {exc} (fail closed)"],
+            "skipped": [],
+            "assignment": None,
+            "substrate": "control_plane_db",
+        }
 
     terminal = None
     try:
@@ -1021,12 +953,6 @@ def allocate_next_work(
                 "assignment": None,
                 "substrate": "control_plane_db",
             }
-        if side_effect_free:
-            # ``list_active_claims`` filters on status alone, so without the
-            # global sweep an already-expired lease would still read as a live
-            # claim and the preview would report work as taken that is free.
-            # Drop those in memory: same view the sweep produces, no write.
-            claims = _drop_expired_claims(claims)
 
     try:
         exclude_nums = normalize_exclude_issue_numbers(exclude_issue_numbers)

docs/mcp-restart-audit.md

@@ -0,0 +1,93 @@
+# MCP restart audit events and incidents (#665)
+
+Restarts and recovery attempts leave a forensic trail. Failed drains and
+break-glass paths also raise durable Gitea incident issues so unsafe restarts
+cannot be silently repeated.
+
+Parent umbrella: **#655**. Related: impact coordinator **#658**, drain proof
+**#661**, restart classes **#663**, break-glass **#664**, post-restart reconcile
+**#662**, vision **#652**, roadmap **#653**, console recovery **#642**.
+
+## Components
+
+| Piece | Where | Responsibility |
+|-------|-------|----------------|
+| Event schema + emission | `restart_audit.py` | `mcp.restart.*` vocabulary, redacted payload builder, append-only sink via `gitea_audit` |
+| Fail-closed privileged gate | `restart_audit.require_audit_or_deny` | When `GITEA_AUDIT_LOG` is set and the write fails, privileged apply is denied |
+| Incident descriptors | `restart_audit.build_incident_descriptor` | Durable follow-up issues (failed drain, break-glass, reconcile unresolved, unguarded) |
+| Materializer | `restart_audit.materialize_incident` | Injected `create_issue_fn` (network kept out of pure tests) |
+| Wiring | `gitea_request_mcp_restart` | Correlation id, impact-preview audit, apply-gate / break-glass audit + incident creation |
+
+## Event vocabulary
+
+| Event type | When |
+|------------|------|
+| `mcp.restart.impact_preview` | Every `gitea_request_mcp_restart` evaluation |
+| `mcp.restart.drain_enter` | Drain window starts (schema reserved; emit from drain path) |
+| `mcp.restart.drain_exit` | Drain window ends |
+| `mcp.restart.drain_proof` | Drain-proof verification result |
+| `mcp.restart.apply_gate` | Apply hard gate (`dry_run=False`) |
+| `mcp.restart.break_glass` | Authorized break-glass bypass |
+| `mcp.restart.post_restart_reconcile` | Post-restart reconcile outcome |
+| `mcp.restart.narrower_recovery` | Narrower recovery attempt recorded |
+| `mcp.restart.unguarded_detected` | Unguarded restart path detected |
+
+All free text is redacted before sink write or issue body assembly. Emission
+never raises; callers decide fail-closed policy.
+
+## Correlation
+
+Each restart lifecycle mints a short `correlation_id` (`rst-` + 16 hex) shared
+across impact preview → apply gate → incident descriptors so operators can join
+the trail.
+
+## Privileged deny-on-audit-fail
+
+Rollout policy (issue #665):
+
+1. Configure `GITEA_AUDIT_LOG` so writes land.
+2. Only then enforce deny when a privileged restart path cannot audit.
+
+When audit is **not** configured, privileged apply still proceeds (no false
+denials during rollout). When audit **is** configured and the write fails,
+`apply_authorized` is cleared.
+
+## Incidents
+
+| Kind | Trigger |
+|------|---------|
+| `restart_failed_drain` | Apply denied by drain hard gate / failed proof |
+| `restart_break_glass` | Any authorized break-glass apply |
+| `restart_reconcile_unresolved` | Post-restart reconcile left work unresolved |
+| `restart_unguarded_detected` | Unguarded restart attempt detected |
+
+Break-glass **always** creates an incident descriptor (and a Gitea issue when
+the create path is available). Failed drain does the same. Incident bodies
+include correlation id, session, class, scope, proof id, and redacted reasons.
+
+Default labels: `mcp-health`, `safety`, `observability`, `status:ready`,
+`type:bug`, `workflow-hardening`.
+
+## Tool payload surface
+
+`gitea_request_mcp_restart` returns:
+
+* `correlation_id` — lifecycle join key
+* `restart_audit.impact_preview_written` — sink success for the preview event
+* `restart_audit.apply_gate_written` — sink success for apply/break-glass (apply only)
+* `restart_audit.incident_result` — materialization outcome when an incident was required
+* `incident` — durable descriptor (when gate requires follow-up)
+
+## Security
+
+* No secrets in audit payloads or issue bodies.
+* This module never restarts a process.
+* Drain proof verification remains #661; audit only records the decision.
+* Incident creation failures are recorded in `incident_result.reasons` and never
+  crash the restart evaluation path (audit write failure still fails closed for
+  privileged apply when the sink is enabled).
+
+## Tests
+
+See `tests/test_restart_audit.py`: schema, redaction, emission, deny policy,
+incident materialization mocks, break-glass / failed-drain selection.

docs/mcp-restart-coordinator.md

@@ -33,6 +33,7 @@ recovery behavior for all nine classes.
 | `ControlPlaneDB.list_sessions` | `control_plane_db.py` | Read-only session inventory (the process-level unit a restart kills). |
 | `gitea_request_mcp_restart` | `gitea_mcp_server.py` | MCP tool: gathers inventory from the #613 DB, calls the coordinator, returns the report, and on `dry_run=False` runs the #661 drain-proof hard gate. Never restarts a process. |
 | `drain_proof.gate_apply_restart` | `drain_proof.py` | The #661 hard gate: verifies a drain proof against the current impact fingerprint, or records an authorized break-glass bypass. |
+| `restart_audit` | `restart_audit.py` | #665 forensic trail: `mcp.restart.*` events via `gitea_audit`, correlation ids, durable incidents for failed drain / break-glass. See [`mcp-restart-audit.md`](./mcp-restart-audit.md). |
 
 ## Dimensions evaluated
 

docs/webui-authz-audit.md

@@ -94,7 +94,6 @@ already define, and a regression test asserts each mapping matches.
 | `record_analytics_usage` | operator | gated_write | `runtime.record_analytics_usage` | Yes | No | No | 2 |
 | `system.reload_namespace` | controller | privileged | `runtime.reload_namespace` | Yes | No | No | 2 |
 | `system.restart_namespace` | admin | destructive | `runtime.restart_namespace` | Yes | **Yes** | **Yes** | 2 |
-| `initiate_workflow` | operator | gated_write | `gitea.read` | Yes | No | No | 2 |
 
 **Dual control** means the acting principal may not be the sole authority: a
 second distinct principal must confirm. **Break-glass** means the action is
@@ -113,12 +112,6 @@ by the console — both hand off to a host supervisor, and neither exposes a raw
 process kill. See
 [`sanctioned-restart-controls.md`](sanctioned-restart-controls.md) (#642).
 
-`initiate_workflow` (#643) is operator-class because its outcome is a *claim*,
-not a Gitea verdict. Requesting reviewer or merger work reserves that work
-through the allocator; it does not grant the right to approve or merge, which
-stays with the MCP role profile and its own capability gates. See
-[`webui-requests.md`](webui-requests.md).
-
 ### Authorization decision
 
 `authorize(action_id, principal, for_execution=False)` returns a decision
@@ -133,24 +126,9 @@ record and **denies by default**. The deny reasons are closed and enumerated:
 | `phase_not_active` | Execution requested for an action whose phase is not open. |
 | `allowed_preview_only` | Authorized — preview only, execution still disabled. |
 
-There is no implicit allow branch.
-
-`execution_enabled` on the decision reports whether the action has a live
-execution path at all, and is computed by `execution_wired(action)`. There are
-exactly two ways to be wired:
-
-1. the action's `phase` is at or below `ACTIVE_PHASE`; or
-2. the action declares an `execution_env_flag` **and** that variable is set.
-
-Every action that declares no flag therefore reports `execution_enabled: false`
-while the console is in Phase 1, so no caller can read an allow as permission
-to mutate. The per-action flag exists because raising `ACTIVE_PHASE` would
-enable execution for every action of that phase at once, including ones whose
-execution path is not implemented. One implemented action goes live on its own
-flag instead of dragging its unimplemented phase-mates with it.
-
-`initiate_workflow` is the only action that currently declares a flag
-(`WEBUI_REQUESTS_EXECUTION`), and it stays denied until an operator sets it.
+There is no implicit allow branch. Even the allow result reports
+`execution_enabled: false` while the console is in Phase 1, so no caller can
+read an allow as permission to mutate.
 
 ## Secret redaction
 
@@ -257,22 +235,13 @@ second one. The integration points are already wired and observable:
   instead of adding a parallel check.
 - **`GET /api/console/security-model`** publishes the RBAC matrix, redaction
   policy, and audit policy as JSON for operators and tests.
-- **`POST /api/v1/requests/preview` and `.../apply`** (#643) are the first
-  actions to use this model for a real execution path. Preview always returns a
-  decision and an audited `previewed` record; apply requires `confirm=true`,
-  emits `succeeded` or `denied`, and reserves work only through the allocator.
-  See [`webui-requests.md`](webui-requests.md).
 
-A Phase 2 action must: use `execution_wired` rather than a private enable flag,
-implement the confirmation and dual-control flow the matrix already declares,
-emit a `succeeded` or `failed` record alongside the `gitea_audit` mutation
-record, and keep `viewer` unable to reach any of it. Turning on execution
-without the confirmation flow contradicts a declared requirement and is a
-review failure, not a shortcut.
-
-Raising `ACTIVE_PHASE` remains the way to open a whole phase at once, and is
-deliberately *not* what #643 did: an action-scoped opt-in cannot enable an
-action whose execution path nobody wrote.
+To open Phase 2, a child issue must: raise `ACTIVE_PHASE`, implement the
+confirmation and dual-control flow the matrix already declares, emit a
+`succeeded` or `failed` record alongside the `gitea_audit` mutation record, and
+keep `viewer` unable to reach any of it. Turning on execution without the
+confirmation flow contradicts a declared requirement and is a review failure,
+not a shortcut.
 
 ## Local-dev mode
 
@@ -325,7 +294,6 @@ Until Phase 2 wires it, probe protection rests on network placement alone, as
 | `WEBUI_ROLE_MAP` | unset | JSON subject → role map |
 | `WEBUI_REQUIRE_PROBE_AUTH` | unset | Require auth for non-public probes |
 | `WEBUI_CONSOLE_AUDIT_LOG` | unset | Append-only audit sink path |
-| `WEBUI_REQUESTS_EXECUTION` | unset | Opt in to `initiate_workflow` execution (#643) |
 
 All are read server-side only. None is ever rendered into a page or returned by
 an API.

docs/webui-requests.md

@@ -1,160 +0,0 @@
-# Web console requests: intent preview and workflow initiation (#643)
-
-**Phase 2. Preview is always live and always read-only. Initiation is wired but
-denied until an operator opts in.**
-
-Before this surface, starting role work meant pasting a prompt into a terminal
-and trusting the operator to have checked the allocator first. Nothing enforced
-that check, so two sessions could reach for the same issue and each believe it
-was theirs. This page replaces the paste with a *request*: a desired role, an
-issue or PR, and a stated intent, answered by an authorization decision and —
-on confirmation — an exclusive assignment from the allocator.
-
-| Concern | Module |
-|---------|--------|
-| Request model, preview, initiation | `webui/request_service.py` |
-| Form and preview rendering | `webui/request_views.py` |
-| Authorization | `webui/console_authz.py` (`initiate_workflow`) |
-| Audit | `webui/console_audit.py` |
-| Ownership substrate | `allocator_service.py` + `control_plane_db.py` |
-
-## Surfaces
-
-| Path | Method | Purpose |
-|------|--------|---------|
-| `/requests` | GET | Request form |
-| `/requests` | POST | Render an intent preview. **Never assigns.** |
-| `/api/v1/requests/preview` | POST | Intent preview as JSON |
-| `/api/v1/requests/apply` | POST | Initiate — confirmed, audited, allocator-owned |
-
-The HTML form has no initiate button on purpose. Initiating requires a
-confirmed POST to `/api/v1/requests/apply`, so a stray form submission cannot
-reserve work as a side effect.
-
-## The request
-
-```json
-{
-  "desired_role": "author",
-  "work_kind": "issue",
-  "work_number": 643,
-  "intent_summary": "implement request preview and initiation",
-  "remote": "prgs",
-  "org": "Scaled-Tech-Consulting",
-  "repo": "Gitea-Tools",
-  "expected_head_sha": null
-}
-```
-
-`desired_role` is one of `author`, `reviewer`, `merger`, `reconciler`,
-`controller`. `work_kind` is `issue` or `pr`. `remote`/`org`/`repo` default to
-the first project in the registry when omitted; when neither the request nor
-the registry resolves them, the request is rejected rather than pointed at some
-other repository. `intent_summary` is required — it is what the audit record
-states as the reason — and is truncated to 500 characters.
-
-Parsing rejects rather than corrects. An unknown role, an unknown work kind, a
-non-positive number, or a missing intent each return `400` with a `reason_code`
-and the offending `field`.
-
-## Preview
-
-Five checks, each with its own verdict, reason code, and detail:
-
-| Check | Passes when |
-|-------|-------------|
-| `authorization` | The console principal holds `operator` or above |
-| `capability` | The desired role maps to a declared profile and MCP namespace |
-| `lease_availability` | No active claim holds the work unit |
-| `next_safe_action` | The allocator would independently select this exact work unit |
-| `head_pin` | PR work resolves to a head SHA, and a supplied SHA still matches |
-
-A preview also returns the role's `allowed_actions` and `prohibited_actions`
-(from `allocator_service.ROLE_ACTIONS`), the `required_profile` and
-`required_namespace` the work must run under, and a `correlation_id` that ties
-the preview to its audit record and to any assignment that follows.
-
-Preview is read-only in the strict sense: it calls the allocator with
-`apply=false` and writes nothing but an audit line. An unauthorized principal
-never reaches the allocator or the control-plane DB at all, so a denial cannot
-be used to enumerate the queue.
-
-## Initiation
-
-`POST /api/v1/requests/apply` refuses in this order, and every refusal returns
-before any assignment is attempted:
-
-| Condition | Outcome | Status |
-|-----------|---------|--------|
-| Unparseable request | `invalid_request` | 400 |
-| Not authorized, or execution not wired | `denied` | 403 |
-| `confirm` not set | `denied` / `confirmation_required` | 409 |
-| Work unit already claimed | `blocked` / `duplicate_assignment` | 409 |
-| Allocator would select other work | `wait` / `not_next_safe_work` | 409 |
-| Allocator declines on apply | `blocked` or `wait` | 409 |
-| Evidence unavailable | `wait` / `evidence_unavailable` | 503 |
-| Assigned | `assigned_work` | 201 |
-
-A success returns the assignment plus a `handoff` block naming the profile, the
-namespace, and the actions that stay forbidden — enough for the operator to
-continue in the right MCP namespace without guessing.
-
-### Why apply runs the allocator twice
-
-The allocator is the only source of exclusive ownership (#600 / #613), and it
-selects work; it does not take orders. So `apply` runs a dry-run first and
-proceeds only when the allocator would independently pick the requested work
-unit. If it would not, the request reports `wait` and mutates nothing.
-
-A request is therefore a *confirmation* of the allocator's decision, never an
-override of it. The apply call carries the dry-run's
-`candidate_set_fingerprint` as a CAS pin (#776), so a queue that changed
-between the two calls fails closed rather than assigning against a stale view.
-The result is checked again on the way out: an assignment naming a different
-work unit is not read as success.
-
-### Fail-closed defaults
-
-- An unreadable control-plane DB denies. It is never treated as "nothing holds
-  this work unit".
-- An incomplete queue inventory denies (#758). Ranking a partial candidate set
-  can select the wrong work.
-- An allocator that raises denies.
-- PR work with no resolvable head SHA denies; a supplied SHA that no longer
-  matches denies with `head_moved`.
-
-## Enabling initiation
-
-Execution is wired off. Set `WEBUI_REQUESTS_EXECUTION=1` to enable it for the
-`initiate_workflow` action only — see
-[`webui-authz-audit.md`](webui-authz-audit.md) for why this is an
-action-scoped flag rather than a phase bump. With the variable unset, `apply`
-returns `403` with `reason_code: unauthorized` no matter who asks.
-
-Enabling execution does **not** enable approvals or merges. Those are phase 3
-console actions and remain forbidden in every path here; the console reserves
-work and hands off, and the MCP role profile enforces what that role may then
-do.
-
-## Audit
-
-Every preview and every apply emits a console audit record (schema in
-[`webui-authz-audit.md`](webui-authz-audit.md)):
-
-| Event | `result` |
-|-------|----------|
-| Preview | `previewed` |
-| Refusal at any stage | `denied` |
-| Assignment created | `succeeded` |
-
-`correlation.request_id` carries the request's `correlation_id`, and a
-successful record's `metadata` carries `assignment_id` and `lease_id`, so an
-assignment can be traced back to the intent that produced it. The operator's
-`intent_summary` travels in `metadata` and passes through the standard
-redaction pass before persistence like every other field.
-
-## Non-goals
-
-- No browser-initiated approve or merge, in this phase or any other.
-- No bypass of allocator exclusive ownership; no self-selection of work.
-- No auto-start from raw monitoring incidents (#612 stays downstream).

gitea_mcp_server.py

@@ -2069,6 +2069,7 @@ import lease_policy  # noqa: E402
 import workflow_dashboard  # noqa: E402  # #605 live queue/lease dashboard
 import restart_coordinator  # noqa: E402  # #658 MCP restart coordinator/impact
 import drain_proof  # noqa: E402  # #661 pre-restart drain proof and hard gate
+import restart_audit  # noqa: E402  # #665 restart audit events + incidents
 import incident_bridge  # noqa: E402
 import sentry_observability  # noqa: E402  (#606 optional Sentry observability)
 import sentry_incident_bridge  # noqa: E402  (#607 Sentry→Gitea incident bridge)
@@ -22750,6 +22751,38 @@ def gitea_request_mcp_restart(
     # and a durable incident is raised. Break-glass is the only bypass and its
     # authorization is read from the environment, never self-asserted.
     payload["apply_supported"] = False
+    # #665: correlation id threads impact preview → apply gate → incidents.
+    correlation_id = restart_audit.new_correlation_id()
+    payload["correlation_id"] = correlation_id
+    auth_user = None
+    try:
+        # remote-only: host override is for operator diagnostics, not required here
+        auth_user = (gitea_whoami(remote=remote) or {}).get("username")
+    except Exception:  # noqa: BLE001 — identity is best-effort for audit
+        auth_user = None
+    preview_audit = restart_audit.record_restart_lifecycle(
+        event_type=restart_audit.EVENT_IMPACT_PREVIEW,
+        outcome=str(report.verdict or "unknown"),
+        correlation_id=correlation_id,
+        remote=remote,
+        org=o,
+        repo=r,
+        requesting_session_id=sid,
+        restart_class=restart_class,
+        profile_name=profile_name,
+        authenticated_username=auth_user,
+        reasons=list(report.reasons or []),
+        details={
+            "dry_run": True,
+            "allow_restart": bool(report.allow_restart),
+            "inventory_complete": inventory_complete,
+        },
+        privileged=False,
+    )
+    payload["restart_audit"] = {
+        "correlation_id": correlation_id,
+        "impact_preview_written": preview_audit["audit_written"],
+    }
     if not dry_run:
         proof_obj: dict | None = None
         proof_parse_error: str | None = None
@@ -22809,6 +22842,86 @@ def gitea_request_mcp_restart(
         )
         if not gate.allow and gate.incident is not None:
             payload["incident"] = gate.incident
+
+        # #665: audit apply-gate + materialize durable incidents for failed
+        # drain and break-glass. Privileged apply denies if audit is enabled
+        # and the sink write fails.
+        incident_desc = restart_audit.incident_from_apply_gate(
+            gate_payload={
+                **gate_payload,
+                "incident": gate.incident,
+                "allow": gate.allow,
+            },
+            break_glass=break_glass,
+            correlation_id=correlation_id,
+            requesting_session_id=sid,
+            restart_class=restart_class,
+            remote=remote,
+            org=o,
+            repo=r,
+        )
+        if incident_desc is not None:
+            payload["incident"] = incident_desc
+
+        def _create_restart_incident_issue(
+            *, title, body, labels, org=None, repo=None, **_kw
+        ):
+            return gitea_create_issue(
+                title=title,
+                body=body,
+                labels=labels,
+                remote=remote,
+                host=h,
+                org=org or o,
+                repo=repo or r,
+            )
+
+        apply_audit = restart_audit.record_restart_lifecycle(
+            event_type=(
+                restart_audit.EVENT_BREAK_GLASS
+                if break_glass
+                else restart_audit.EVENT_APPLY_GATE
+            ),
+            outcome=(
+                "break_glass"
+                if break_glass
+                else ("allow" if payload["apply_authorized"] else "deny")
+            ),
+            correlation_id=correlation_id,
+            remote=remote,
+            org=o,
+            repo=r,
+            requesting_session_id=sid,
+            restart_class=restart_class,
+            profile_name=profile_name,
+            authenticated_username=auth_user,
+            reasons=list(gate_payload.get("reasons") or []),
+            details={
+                "apply_authorized": payload["apply_authorized"],
+                "drain_gate_allow": gate_payload.get("drain_gate_allow"),
+                "restart_class_authorized": restart_class_authorized,
+                "break_glass": break_glass,
+                "proof_id": gate_payload.get("proof_id"),
+            },
+            privileged=True,
+            create_incident=incident_desc,
+            create_issue_fn=_create_restart_incident_issue
+            if incident_desc is not None
+            else None,
+            dry_run_incident=False,
+        )
+        payload["restart_audit"] = {
+            "correlation_id": correlation_id,
+            "impact_preview_written": preview_audit["audit_written"],
+            "apply_gate_written": apply_audit["audit_written"],
+            "incident_result": apply_audit.get("incident_result"),
+        }
+        if apply_audit["deny_reasons"]:
+            payload["apply_authorized"] = False
+            payload["reasons"] = list(payload.get("reasons") or []) + list(
+                apply_audit["deny_reasons"]
+            )
+            payload["success"] = True
     return payload
 
 

restart_audit.py

@@ -0,0 +1,426 @@
+"""MCP restart lifecycle audit events and incident materialization (#665).
+
+Restarts and recovery attempts must leave a forensic trail: impact previews,
+drain enter/exit, drain-proof results, apply gate verdicts, break-glass, and
+post-restart reconcile outcomes. Failed drains and break-glass must also raise
+durable Gitea incident issues so they cannot be silently repeated.
+
+This module is the pure + sink layer for that trail:
+
+* **Schema** — ``mcp.restart.*`` event names and a redacted payload builder.
+* **Emission** — append-only via :mod:`gitea_audit` (off when ``GITEA_AUDIT_LOG``
+  is unset; privileged apply can still *require* a successful write).
+* **Incidents** — descriptors for failed drain / break-glass / unguarded restart,
+  plus an optional materializer that creates a Gitea issue through an injected
+  ``create_issue_fn`` (keeps this module free of network I/O in tests).
+
+Design rules:
+
+* **No secrets.** All free text is redacted before write or issue body assembly.
+* **Never raises from emission.** ``emit_restart_event`` returns False on sink
+  failure so callers can decide fail-closed policy for privileged restarts.
+* **Does not restart.** Audit never executes a process restart.
+* **Drain proof stays #661.** This module records what the gate decided; it
+  does not re-verify proofs.
+"""
+
+from __future__ import annotations
+
+import uuid
+from datetime import datetime, timezone
+from typing import Any, Callable, Mapping, Sequence
+
+import gitea_audit
+
+# ── Event vocabulary (stable identifiers for operators + tests) ───────────────
+
+EVENT_IMPACT_PREVIEW = "mcp.restart.impact_preview"
+EVENT_DRAIN_ENTER = "mcp.restart.drain_enter"
+EVENT_DRAIN_EXIT = "mcp.restart.drain_exit"
+EVENT_DRAIN_PROOF = "mcp.restart.drain_proof"
+EVENT_APPLY_GATE = "mcp.restart.apply_gate"
+EVENT_BREAK_GLASS = "mcp.restart.break_glass"
+EVENT_POST_RESTART_RECONCILE = "mcp.restart.post_restart_reconcile"
+EVENT_NARROWER_RECOVERY = "mcp.restart.narrower_recovery"
+EVENT_UNGUARDED_DETECTED = "mcp.restart.unguarded_detected"
+
+RESTART_EVENT_TYPES: frozenset[str] = frozenset(
+    {
+        EVENT_IMPACT_PREVIEW,
+        EVENT_DRAIN_ENTER,
+        EVENT_DRAIN_EXIT,
+        EVENT_DRAIN_PROOF,
+        EVENT_APPLY_GATE,
+        EVENT_BREAK_GLASS,
+        EVENT_POST_RESTART_RECONCILE,
+        EVENT_NARROWER_RECOVERY,
+        EVENT_UNGUARDED_DETECTED,
+    }
+)
+
+# Incident kinds (durable Gitea issues).
+INCIDENT_FAILED_DRAIN = "restart_failed_drain"
+INCIDENT_BREAK_GLASS = "restart_break_glass"
+INCIDENT_RECONCILE_UNRESOLVED = "restart_reconcile_unresolved"
+INCIDENT_UNGUARDED = "restart_unguarded_detected"
+
+DEFAULT_INCIDENT_LABELS: tuple[str, ...] = (
+    "mcp-health",
+    "safety",
+    "observability",
+    "status:ready",
+    "type:bug",
+    "workflow-hardening",
+)
+
+CreateIssueFn = Callable[..., dict[str, Any]]
+
+
+def _utc_now_iso() -> str:
+    return datetime.now(timezone.utc).isoformat()
+
+
+def new_correlation_id() -> str:
+    """Mint a short correlation id shared across a restart lifecycle."""
+    return f"rst-{uuid.uuid4().hex[:16]}"
+
+
+def build_restart_event(
+    *,
+    event_type: str,
+    outcome: str,
+    correlation_id: str | None = None,
+    remote: str | None = None,
+    org: str | None = None,
+    repo: str | None = None,
+    requesting_session_id: str | None = None,
+    restart_class: str | None = None,
+    profile_name: str | None = None,
+    authenticated_username: str | None = None,
+    reasons: Sequence[str] | None = None,
+    details: Mapping[str, Any] | None = None,
+    now: str | None = None,
+) -> dict[str, Any]:
+    """Build a redacted ``mcp.restart.*`` audit event.
+
+    Raises ``ValueError`` on unknown event types so a typo cannot silently land
+    under a free-form action name.
+    """
+    name = str(event_type or "").strip()
+    if name not in RESTART_EVENT_TYPES:
+        raise ValueError(
+            f"unknown restart audit event_type {name!r}; expected one of "
+            f"{sorted(RESTART_EVENT_TYPES)}"
+        )
+    redacted_reasons = [
+        gitea_audit.redact(str(r)) for r in (reasons or []) if str(r).strip()
+    ]
+    redacted_details = gitea_audit.redact(dict(details or {}))
+    if not isinstance(redacted_details, dict):
+        redacted_details = {"value": redacted_details}
+
+    event = gitea_audit.build_event(
+        action=name,
+        result=str(outcome or "unknown"),
+        remote=remote,
+        repository=f"{org}/{repo}" if org and repo else None,
+        profile_name=profile_name,
+        authenticated_username=authenticated_username,
+        reason="; ".join(redacted_reasons) if redacted_reasons else None,
+        request_metadata={
+            "event_family": "mcp.restart",
+            "correlation_id": correlation_id or new_correlation_id(),
+            "restart_class": restart_class,
+            "requesting_session_id": requesting_session_id,
+            "org": org,
+            "repo": repo,
+            "details": redacted_details,
+            "reasons": redacted_reasons,
+        },
+        now=now or _utc_now_iso(),
+        operation=name,
+    )
+    event["action_type"] = "restart_lifecycle"
+    event["event_type"] = name
+    event["correlation_id"] = (event.get("request_metadata") or {}).get(
+        "correlation_id"
+    )
+    return event
+
+
+def emit_restart_event(event: Mapping[str, Any], *, path: str | None = None) -> bool:
+    """Append *event* to the audit sink. Never raises. Returns write success."""
+    try:
+        return bool(gitea_audit.write_event(dict(event), path=path))
+    except Exception:
+        return False
+
+
+def require_audit_or_deny(
+    *,
+    privileged: bool,
+    written: bool,
+    audit_enabled: bool | None = None,
+) -> list[str]:
+    """Return deny reasons when a privileged restart path fails to audit.
+
+    When audit is not configured (``GITEA_AUDIT_LOG`` unset), privileged apply
+    still proceeds under the rollout policy "enable audit before enforcing
+    deny-on-audit-fail" — but *if* audit is enabled and the write fails,
+    privileged apply is denied (fail closed).
+    """
+    enabled = (
+        gitea_audit.audit_enabled() if audit_enabled is None else bool(audit_enabled)
+    )
+    if not privileged:
+        return []
+    if not enabled:
+        return []
+    if written:
+        return []
+    return [
+        "privileged restart path requires a successful audit write; "
+        "audit sink failed (fail closed, #665)"
+    ]
+
+
+# ── Incident descriptors ──────────────────────────────────────────────────────
+
+
+def build_incident_descriptor(
+    *,
+    kind: str,
+    reasons: Sequence[str],
+    correlation_id: str | None = None,
+    requesting_session_id: str | None = None,
+    restart_class: str | None = None,
+    remote: str | None = None,
+    org: str | None = None,
+    repo: str | None = None,
+    proof_id: str | None = None,
+    at: str | None = None,
+) -> dict[str, Any]:
+    """Build a durable incident descriptor (no network)."""
+    titles = {
+        INCIDENT_FAILED_DRAIN: "Restart denied: drain proof failed the hard gate",
+        INCIDENT_BREAK_GLASS: "Break-glass MCP restart authorized",
+        INCIDENT_RECONCILE_UNRESOLVED: "Post-restart reconcile left unresolved work",
+        INCIDENT_UNGUARDED: "Unguarded MCP restart attempt detected",
+    }
+    title = titles.get(kind, f"MCP restart incident ({kind})")
+    redacted_reasons = [
+        gitea_audit.redact(str(r)) for r in reasons if str(r).strip()
+    ]
+    return {
+        "kind": kind,
+        "title": title,
+        "labels": list(DEFAULT_INCIDENT_LABELS),
+        "reasons": redacted_reasons,
+        "correlation_id": correlation_id,
+        "requesting_session_id": requesting_session_id,
+        "restart_class": restart_class,
+        "remote": remote,
+        "org": org,
+        "repo": repo,
+        "proof_id": proof_id,
+        "at": at or _utc_now_iso(),
+        "source": "restart_audit#665",
+    }
+
+
+def incident_body(descriptor: Mapping[str, Any]) -> str:
+    """Render a redacted markdown body for a Gitea incident issue."""
+    reasons = descriptor.get("reasons") or []
+    reason_lines = "\n".join(f"- {gitea_audit.redact(str(r))}" for r in reasons) or (
+        "- (no reasons recorded)"
+    )
+    return "\n".join(
+        [
+            "<!-- mcp-restart-incident:v1 -->",
+            f"## MCP restart incident (`{descriptor.get('kind')}`)",
+            "",
+            f"**Correlation:** `{descriptor.get('correlation_id') or 'none'}`",
+            f"**Session:** `{descriptor.get('requesting_session_id') or 'none'}`",
+            f"**Class:** `{descriptor.get('restart_class') or 'none'}`",
+            f"**Scope:** `{descriptor.get('remote')}/{descriptor.get('org')}/"
+            f"{descriptor.get('repo')}`",
+            f"**At:** `{descriptor.get('at')}`",
+            f"**Proof id:** `{descriptor.get('proof_id') or 'none'}`",
+            "",
+            "### Reasons",
+            reason_lines,
+            "",
+            "### Operator next steps",
+            "- Treat this as durable follow-up work under the restart-governance umbrella (#655).",
+            "- Do not invent a second restart path; use sanctioned coordinator tools only.",
+            "- Raw secrets must never appear in this issue (already redacted).",
+            "",
+            f"_Source: {descriptor.get('source')}_",
+        ]
+    )
+
+
+def materialize_incident(
+    descriptor: Mapping[str, Any],
+    *,
+    create_issue_fn: CreateIssueFn | None,
+    dry_run: bool = False,
+) -> dict[str, Any]:
+    """Create a Gitea issue from *descriptor* when *create_issue_fn* is provided.
+
+    Returns a result dict with ``created`` / ``issue_number`` / ``dry_run`` /
+    ``reasons``. Never raises.
+    """
+    base: dict[str, Any] = {
+        "created": False,
+        "dry_run": bool(dry_run),
+        "issue_number": None,
+        "kind": descriptor.get("kind"),
+        "reasons": [],
+        "descriptor": dict(descriptor),
+    }
+    if dry_run:
+        base["reasons"] = ["dry-run only; no Gitea issue created"]
+        return base
+    if create_issue_fn is None:
+        base["reasons"] = [
+            "create_issue_fn not provided; incident descriptor retained only"
+        ]
+        return base
+    try:
+        result = create_issue_fn(
+            title=str(descriptor.get("title") or "MCP restart incident"),
+            body=incident_body(descriptor),
+            labels=list(descriptor.get("labels") or DEFAULT_INCIDENT_LABELS),
+            org=descriptor.get("org"),
+            repo=descriptor.get("repo"),
+        )
+        number = None
+        if isinstance(result, dict):
+            number = result.get("number") or result.get("issue_number")
+        if number is not None:
+            base["created"] = True
+            base["issue_number"] = int(number)
+            base["reasons"] = [f"created incident issue #{int(number)}"]
+        else:
+            base["reasons"] = ["create_issue_fn returned no issue number"]
+    except Exception as exc:  # noqa: BLE001 — never break restart path here
+        base["reasons"] = [
+            f"incident issue creation failed: {gitea_audit.redact(str(exc))}"
+        ]
+    return base
+
+
+def record_restart_lifecycle(
+    *,
+    event_type: str,
+    outcome: str,
+    correlation_id: str,
+    remote: str | None = None,
+    org: str | None = None,
+    repo: str | None = None,
+    requesting_session_id: str | None = None,
+    restart_class: str | None = None,
+    profile_name: str | None = None,
+    authenticated_username: str | None = None,
+    reasons: Sequence[str] | None = None,
+    details: Mapping[str, Any] | None = None,
+    privileged: bool = False,
+    create_incident: Mapping[str, Any] | None = None,
+    create_issue_fn: CreateIssueFn | None = None,
+    dry_run_incident: bool = False,
+    audit_path: str | None = None,
+) -> dict[str, Any]:
+    """Emit one restart audit event and optionally materialize an incident.
+
+    Returns ``{event, audit_written, deny_reasons, incident_result}``.
+    """
+    event = build_restart_event(
+        event_type=event_type,
+        outcome=outcome,
+        correlation_id=correlation_id,
+        remote=remote,
+        org=org,
+        repo=repo,
+        requesting_session_id=requesting_session_id,
+        restart_class=restart_class,
+        profile_name=profile_name,
+        authenticated_username=authenticated_username,
+        reasons=reasons,
+        details=details,
+    )
+    written = emit_restart_event(event, path=audit_path)
+    deny = require_audit_or_deny(privileged=privileged, written=written)
+    incident_result = None
+    if create_incident is not None:
+        incident_result = materialize_incident(
+            create_incident,
+            create_issue_fn=create_issue_fn,
+            dry_run=dry_run_incident,
+        )
+    return {
+        "event": event,
+        "audit_written": written,
+        "deny_reasons": deny,
+        "incident_result": incident_result,
+        "correlation_id": correlation_id,
+    }
+
+
+def incident_from_apply_gate(
+    *,
+    gate_payload: Mapping[str, Any],
+    break_glass: bool,
+    correlation_id: str,
+    requesting_session_id: str | None,
+    restart_class: str | None,
+    remote: str | None,
+    org: str | None,
+    repo: str | None,
+) -> dict[str, Any] | None:
+    """Choose an incident descriptor from an apply-gate payload, if required."""
+    reasons = list(gate_payload.get("reasons") or [])
+    proof_id = gate_payload.get("proof_id")
+    if break_glass:
+        return build_incident_descriptor(
+            kind=INCIDENT_BREAK_GLASS,
+            reasons=reasons
+            or ["break-glass restart path used; durable incident required (#665)"],
+            correlation_id=correlation_id,
+            requesting_session_id=requesting_session_id,
+            restart_class=restart_class,
+            remote=remote,
+            org=org,
+            repo=repo,
+            proof_id=proof_id if isinstance(proof_id, str) else None,
+        )
+    # Failed drain / deny path.
+    incident = gate_payload.get("incident")
+    if isinstance(incident, Mapping) and incident:
+        # Normalize gate-provided descriptor into our schema.
+        return build_incident_descriptor(
+            kind=INCIDENT_FAILED_DRAIN,
+            reasons=list(incident.get("reasons") or reasons),
+            correlation_id=correlation_id,
+            requesting_session_id=requesting_session_id
+            or incident.get("requesting_session_id"),
+            restart_class=restart_class,
+            remote=remote,
+            org=org,
+            repo=repo,
+            proof_id=incident.get("proof_id") or proof_id,
+            at=incident.get("at"),
+        )
+    if not gate_payload.get("allow") and not gate_payload.get("drain_gate_allow", True):
+        return build_incident_descriptor(
+            kind=INCIDENT_FAILED_DRAIN,
+            reasons=reasons or ["restart apply denied"],
+            correlation_id=correlation_id,
+            requesting_session_id=requesting_session_id,
+            restart_class=restart_class,
+            remote=remote,
+            org=org,
+            repo=repo,
+            proof_id=proof_id if isinstance(proof_id, str) else None,
+        )
+    return None

tests/test_allocator_service.py

@@ -7,7 +7,6 @@ import tempfile
 import threading
 import unittest
 from concurrent.futures import ThreadPoolExecutor, as_completed
-from datetime import datetime, timezone
 
 from allocator_service import (
     OUTCOME_ASSIGNED,
@@ -16,7 +15,6 @@ from allocator_service import (
     OUTCOME_PREVIEW,
     OUTCOME_WAIT,
     WorkCandidate,
-    _drop_expired_claims,
     allocate_next_work,
     candidate_from_dict,
     classify_skip,
@@ -364,161 +362,5 @@ class AllocatorServiceTest(unittest.TestCase):
         self.assertIn("unavailable", res["reasons"][0].lower())
 
 
-class SideEffectFreeAllocationTest(unittest.TestCase):
-    """``side_effect_free`` dry runs write nothing to the control plane (#643).
-
-    A plain ``apply=False`` still called ``upsert_session`` and
-    ``expire_stale_leases`` before the apply branch was consulted, so a caller
-    advertising a read-only preview mutated on every call — one unreferenced
-    session row per preview, plus a global lease sweep.
-    """
-
-    def setUp(self) -> None:
-        self._tmp = tempfile.TemporaryDirectory()
-        self.db = ControlPlaneDB(os.path.join(self._tmp.name, "cp.sqlite3"))
-
-    def tearDown(self) -> None:
-        self._tmp.cleanup()
-
-    def _alloc(self, **kwargs):
-        defaults = dict(
-            db=self.db,
-            session_id="s-preview",
-            role="author",
-            remote="prgs",
-            org="org",
-            repo="repo",
-            candidates=[
-                WorkCandidate(kind="issue", number=643, labels=("status:ready",))
-            ],
-            apply=False,
-            profile_name="prgs-author",
-            username="jcwalker3",
-        )
-        defaults.update(kwargs)
-        return allocate_next_work(**defaults)
-
-    def _session_ids(self) -> set[str]:
-        return {str(r.get("session_id")) for r in self.db.list_sessions()}
-
-    def test_side_effect_free_preview_writes_no_session_row(self):
-        before = self._session_ids()
-        result = self._alloc(side_effect_free=True)
-        self.assertEqual(result["outcome"], OUTCOME_PREVIEW)
-        self.assertEqual(self._session_ids(), before)
-        self.assertNotIn("s-preview", self._session_ids())
-
-    def test_plain_dry_run_still_registers_a_session(self):
-        # The default is unchanged for every existing caller.
-        self._alloc()
-        self.assertIn("s-preview", self._session_ids())
-
-    def test_repeated_previews_do_not_accumulate_rows(self):
-        for index in range(5):
-            self._alloc(side_effect_free=True, session_id=f"s-{index}")
-        self.assertEqual(self._session_ids(), set())
-
-    def test_side_effect_free_does_not_sweep_stale_leases(self):
-        self.db.upsert_session(session_id="owner", role="author", pid=1)
-        assigned = self.db.assign_and_lease(
-            session_id="owner",
-            role="author",
-            remote="prgs",
-            org="org",
-            repo="repo",
-            kind="issue",
-            number=999,
-            lease_ttl_seconds=-60,  # already expired
-        )
-        self.assertEqual(assigned.outcome, "assigned")
-
-        self._alloc(side_effect_free=True)
-
-        # The expired row is still 'active' in the DB: nothing swept it.
-        statuses = {
-            r["lease_id"]: r["status"]
-            for r in self.db.list_leases(
-                remote="prgs", org="org", repo="repo",
-                statuses=("active", "expired"),
-            )
-        }
-        self.assertEqual(statuses.get(assigned.lease_id), "active")
-
-    def test_expired_claims_are_filtered_in_memory_so_work_stays_selectable(self):
-        """The read-only mirror of the sweep: expired claims must not block."""
-        self.db.upsert_session(session_id="owner", role="author", pid=1)
-        self.db.assign_and_lease(
-            session_id="owner",
-            role="author",
-            remote="prgs",
-            org="org",
-            repo="repo",
-            kind="issue",
-            number=643,
-            lease_ttl_seconds=-60,  # expired: must not withhold #643
-        )
-        result = self._alloc(side_effect_free=True)
-        self.assertEqual(result["outcome"], OUTCOME_PREVIEW)
-        self.assertEqual(result["selected"]["number"], 643)
-
-    def test_a_live_claim_still_withholds_the_work(self):
-        self.db.upsert_session(session_id="owner", role="author", pid=1)
-        self.db.assign_and_lease(
-            session_id="owner",
-            role="author",
-            remote="prgs",
-            org="org",
-            repo="repo",
-            kind="issue",
-            number=643,
-            lease_ttl_seconds=3600,
-        )
-        result = self._alloc(side_effect_free=True)
-        self.assertNotEqual(result["outcome"], OUTCOME_ASSIGNED)
-        self.assertNotEqual((result.get("selected") or {}).get("number"), 643)
-
-    def test_side_effect_free_with_apply_fails_closed(self):
-        result = self._alloc(side_effect_free=True, apply=True)
-        self.assertFalse(result["success"])
-        self.assertEqual(result["outcome"], OUTCOME_NO_SAFE)
-        self.assertIsNone(result["assignment"])
-        self.assertIn("incompatible with apply", result["reasons"][0])
-        # And it reserved nothing.
-        self.assertEqual(
-            self.db.list_leases(remote="prgs", org="org", repo="repo"), []
-        )
-
-
-class DropExpiredClaimsTest(unittest.TestCase):
-    """The in-memory expiry filter behind side-effect-free previews (#643)."""
-
-    def test_unparseable_expiry_is_kept_rather_than_assumed_free(self):
-        claims = {
-            ("issue", 1): {"lease_id": "l1", "expires_at": "not-a-date"},
-            ("issue", 2): {"lease_id": "l2"},
-            ("issue", 3): {"lease_id": "l3", "expires_at": None},
-        }
-        self.assertEqual(_drop_expired_claims(claims), claims)
-
-    def test_expired_dropped_and_future_kept(self):
-        now = datetime(2026, 7, 25, 12, 0, tzinfo=timezone.utc)
-        claims = {
-            ("issue", 1): {"expires_at": "2026-07-25T11:59:59+00:00"},
-            ("issue", 2): {"expires_at": "2026-07-25T12:00:01+00:00"},
-            ("issue", 3): {"expires_at": "2026-07-25T12:00:00+00:00"},  # boundary
-        }
-        kept = _drop_expired_claims(claims, now=now)
-        self.assertEqual(set(kept), {("issue", 2)})
-
-    def test_naive_and_zulu_timestamps_are_treated_as_utc(self):
-        now = datetime(2026, 7, 25, 12, 0, tzinfo=timezone.utc)
-        claims = {
-            ("issue", 1): {"expires_at": "2026-07-25T11:00:00"},  # naive, past
-            ("issue", 2): {"expires_at": "2026-07-25T13:00:00Z"},  # zulu, future
-        }
-        kept = _drop_expired_claims(claims, now=now)
-        self.assertEqual(set(kept), {("issue", 2)})
-
-
 if __name__ == "__main__":
     unittest.main()

tests/test_restart_audit.py

@@ -0,0 +1,342 @@
+"""Tests for MCP restart lifecycle audit events and incidents (#665)."""
+
+from __future__ import annotations
+
+import json
+import os
+import tempfile
+import unittest
+from unittest.mock import patch
+
+import gitea_audit
+import restart_audit as ra
+
+
+class TestEventSchema(unittest.TestCase):
+    def test_all_lifecycle_event_types_are_named(self):
+        expected = {
+            "mcp.restart.impact_preview",
+            "mcp.restart.drain_enter",
+            "mcp.restart.drain_exit",
+            "mcp.restart.drain_proof",
+            "mcp.restart.apply_gate",
+            "mcp.restart.break_glass",
+            "mcp.restart.post_restart_reconcile",
+            "mcp.restart.narrower_recovery",
+            "mcp.restart.unguarded_detected",
+        }
+        self.assertEqual(set(ra.RESTART_EVENT_TYPES), expected)
+
+    def test_build_restart_event_core_fields(self):
+        event = ra.build_restart_event(
+            event_type=ra.EVENT_IMPACT_PREVIEW,
+            outcome="safe",
+            correlation_id="rst-abc123",
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+            requesting_session_id="sess-1",
+            restart_class="full_mcp_restart",
+            profile_name="prgs-author",
+            authenticated_username="bot",
+            reasons=["inventory complete"],
+            details={"allow_restart": True},
+            now="2026-07-25T12:00:00+00:00",
+        )
+        self.assertEqual(event["event_type"], ra.EVENT_IMPACT_PREVIEW)
+        self.assertEqual(event["action"], ra.EVENT_IMPACT_PREVIEW)
+        self.assertEqual(event["action_type"], "restart_lifecycle")
+        self.assertEqual(event["result"], "safe")
+        self.assertEqual(event["correlation_id"], "rst-abc123")
+        self.assertEqual(event["profile_name"], "prgs-author")
+        self.assertEqual(event["authenticated_username"], "bot")
+        meta = event["request_metadata"]
+        self.assertEqual(meta["event_family"], "mcp.restart")
+        self.assertEqual(meta["correlation_id"], "rst-abc123")
+        self.assertEqual(meta["restart_class"], "full_mcp_restart")
+        self.assertEqual(meta["details"]["allow_restart"], True)
+
+    def test_unknown_event_type_raises(self):
+        with self.assertRaises(ValueError) as ctx:
+            ra.build_restart_event(
+                event_type="mcp.restart.not_a_real_event",
+                outcome="x",
+                correlation_id="rst-1",
+            )
+        self.assertIn("unknown restart audit event_type", str(ctx.exception))
+
+    def test_reasons_and_details_are_redacted(self):
+        event = ra.build_restart_event(
+            event_type=ra.EVENT_APPLY_GATE,
+            outcome="deny",
+            correlation_id="rst-sec",
+            reasons=["token secret-xyz rejected", "ok"],
+            details={"token": "leak-token", "status": "denied"},
+        )
+        self.assertNotIn("secret-xyz", event.get("reason") or "")
+        meta = event["request_metadata"]
+        self.assertEqual(meta["details"]["token"], gitea_audit.REDACTED)
+        self.assertEqual(meta["details"]["status"], "denied")
+        for reason in meta["reasons"]:
+            self.assertNotIn("secret-xyz", reason)
+
+    def test_new_correlation_id_shape(self):
+        cid = ra.new_correlation_id()
+        self.assertTrue(cid.startswith("rst-"))
+        self.assertEqual(len(cid), len("rst-") + 16)
+
+
+class TestEmitAndRequire(unittest.TestCase):
+    def test_emit_appends_json_line(self):
+        with tempfile.TemporaryDirectory() as d:
+            path = os.path.join(d, "audit.log")
+            event = ra.build_restart_event(
+                event_type=ra.EVENT_DRAIN_PROOF,
+                outcome="pass",
+                correlation_id="rst-write",
+            )
+            self.assertTrue(ra.emit_restart_event(event, path=path))
+            with open(path, encoding="utf-8") as fh:
+                lines = fh.read().splitlines()
+            self.assertEqual(len(lines), 1)
+            loaded = json.loads(lines[0])
+            self.assertEqual(loaded["event_type"], ra.EVENT_DRAIN_PROOF)
+            self.assertEqual(loaded["correlation_id"], "rst-write")
+
+    def test_emit_never_raises(self):
+        self.assertFalse(
+            ra.emit_restart_event({"action": "x"}, path="/no/such/dir/audit.log")
+        )
+
+    def test_require_audit_denies_privileged_when_write_fails_and_enabled(self):
+        deny = ra.require_audit_or_deny(
+            privileged=True, written=False, audit_enabled=True
+        )
+        self.assertEqual(len(deny), 1)
+        self.assertIn("fail closed", deny[0])
+
+    def test_require_audit_allows_when_audit_disabled(self):
+        # Rollout policy: enable audit before enforcing deny-on-audit-fail.
+        deny = ra.require_audit_or_deny(
+            privileged=True, written=False, audit_enabled=False
+        )
+        self.assertEqual(deny, [])
+
+    def test_require_audit_noop_for_non_privileged(self):
+        deny = ra.require_audit_or_deny(
+            privileged=False, written=False, audit_enabled=True
+        )
+        self.assertEqual(deny, [])
+
+    def test_require_audit_allows_when_written(self):
+        deny = ra.require_audit_or_deny(
+            privileged=True, written=True, audit_enabled=True
+        )
+        self.assertEqual(deny, [])
+
+
+class TestIncidents(unittest.TestCase):
+    def test_break_glass_descriptor(self):
+        desc = ra.build_incident_descriptor(
+            kind=ra.INCIDENT_BREAK_GLASS,
+            reasons=["break-glass authorized"],
+            correlation_id="rst-bg",
+            requesting_session_id="s1",
+            restart_class="full_mcp_restart",
+            remote="prgs",
+            org="O",
+            repo="R",
+        )
+        self.assertEqual(desc["kind"], ra.INCIDENT_BREAK_GLASS)
+        self.assertIn("Break-glass", desc["title"])
+        self.assertIn("mcp-health", desc["labels"])
+        self.assertEqual(desc["source"], "restart_audit#665")
+
+    def test_incident_body_redacts_and_includes_correlation(self):
+        desc = ra.build_incident_descriptor(
+            kind=ra.INCIDENT_FAILED_DRAIN,
+            reasons=["token secret-xyz failed proof"],
+            correlation_id="rst-body",
+            remote="prgs",
+            org="O",
+            repo="R",
+            proof_id="proof-1",
+        )
+        body = ra.incident_body(desc)
+        self.assertIn("rst-body", body)
+        self.assertIn("proof-1", body)
+        self.assertIn("mcp-restart-incident:v1", body)
+        self.assertNotIn("secret-xyz", body)
+
+    def test_materialize_dry_run(self):
+        desc = ra.build_incident_descriptor(
+            kind=ra.INCIDENT_FAILED_DRAIN,
+            reasons=["denied"],
+            correlation_id="rst-dr",
+        )
+        result = ra.materialize_incident(desc, create_issue_fn=lambda **k: {}, dry_run=True)
+        self.assertFalse(result["created"])
+        self.assertTrue(result["dry_run"])
+        self.assertIn("dry-run", result["reasons"][0])
+
+    def test_materialize_without_create_fn(self):
+        desc = ra.build_incident_descriptor(
+            kind=ra.INCIDENT_FAILED_DRAIN,
+            reasons=["denied"],
+            correlation_id="rst-nfn",
+        )
+        result = ra.materialize_incident(desc, create_issue_fn=None)
+        self.assertFalse(result["created"])
+        self.assertIn("create_issue_fn not provided", result["reasons"][0])
+
+    def test_materialize_creates_issue(self):
+        created = {}
+
+        def _create(*, title, body, labels, org=None, repo=None, **_kw):
+            created["title"] = title
+            created["body"] = body
+            created["labels"] = labels
+            created["org"] = org
+            created["repo"] = repo
+            return {"number": 999}
+
+        desc = ra.build_incident_descriptor(
+            kind=ra.INCIDENT_BREAK_GLASS,
+            reasons=["break-glass"],
+            correlation_id="rst-create",
+            org="O",
+            repo="R",
+        )
+        result = ra.materialize_incident(desc, create_issue_fn=_create)
+        self.assertTrue(result["created"])
+        self.assertEqual(result["issue_number"], 999)
+        self.assertIn("Break-glass", created["title"])
+        self.assertIn("rst-create", created["body"])
+        self.assertEqual(created["org"], "O")
+
+    def test_materialize_never_raises_on_create_failure(self):
+        def _boom(**_kw):
+            raise RuntimeError("token secret-xyz network")
+
+        desc = ra.build_incident_descriptor(
+            kind=ra.INCIDENT_FAILED_DRAIN,
+            reasons=["x"],
+            correlation_id="rst-boom",
+        )
+        result = ra.materialize_incident(desc, create_issue_fn=_boom)
+        self.assertFalse(result["created"])
+        self.assertIn("failed", result["reasons"][0])
+        self.assertNotIn("secret-xyz", result["reasons"][0])
+
+
+class TestIncidentFromApplyGate(unittest.TestCase):
+    def test_break_glass_always_incident(self):
+        desc = ra.incident_from_apply_gate(
+            gate_payload={"allow": True, "reasons": [], "proof_id": None},
+            break_glass=True,
+            correlation_id="rst-bg2",
+            requesting_session_id="s",
+            restart_class="full_mcp_restart",
+            remote="prgs",
+            org="O",
+            repo="R",
+        )
+        self.assertIsNotNone(desc)
+        self.assertEqual(desc["kind"], ra.INCIDENT_BREAK_GLASS)
+
+    def test_failed_drain_from_gate_incident(self):
+        desc = ra.incident_from_apply_gate(
+            gate_payload={
+                "allow": False,
+                "drain_gate_allow": False,
+                "reasons": ["proof expired"],
+                "incident": {
+                    "reasons": ["proof expired"],
+                    "proof_id": "p1",
+                },
+            },
+            break_glass=False,
+            correlation_id="rst-fd",
+            requesting_session_id="s",
+            restart_class="full_mcp_restart",
+            remote="prgs",
+            org="O",
+            repo="R",
+        )
+        self.assertIsNotNone(desc)
+        self.assertEqual(desc["kind"], ra.INCIDENT_FAILED_DRAIN)
+        self.assertEqual(desc["proof_id"], "p1")
+
+    def test_allow_without_break_glass_no_incident(self):
+        desc = ra.incident_from_apply_gate(
+            gate_payload={
+                "allow": True,
+                "drain_gate_allow": True,
+                "reasons": [],
+            },
+            break_glass=False,
+            correlation_id="rst-ok",
+            requesting_session_id="s",
+            restart_class="full_mcp_restart",
+            remote="prgs",
+            org="O",
+            repo="R",
+        )
+        self.assertIsNone(desc)
+
+
+class TestRecordLifecycle(unittest.TestCase):
+    def test_record_emits_and_materializes(self):
+        created = []
+
+        def _create(**kwargs):
+            created.append(kwargs)
+            return {"number": 42}
+
+        with tempfile.TemporaryDirectory() as d:
+            path = os.path.join(d, "audit.log")
+            with patch.dict(os.environ, {"GITEA_AUDIT_LOG": path}, clear=False):
+                incident = ra.build_incident_descriptor(
+                    kind=ra.INCIDENT_BREAK_GLASS,
+                    reasons=["bg"],
+                    correlation_id="rst-lc",
+                    org="O",
+                    repo="R",
+                )
+                out = ra.record_restart_lifecycle(
+                    event_type=ra.EVENT_BREAK_GLASS,
+                    outcome="break_glass",
+                    correlation_id="rst-lc",
+                    remote="prgs",
+                    org="O",
+                    repo="R",
+                    privileged=True,
+                    create_incident=incident,
+                    create_issue_fn=_create,
+                    audit_path=path,
+                )
+        self.assertTrue(out["audit_written"])
+        self.assertEqual(out["deny_reasons"], [])
+        self.assertTrue(out["incident_result"]["created"])
+        self.assertEqual(out["incident_result"]["issue_number"], 42)
+        self.assertEqual(len(created), 1)
+
+    def test_privileged_deny_when_audit_write_fails(self):
+        with patch.dict(
+            os.environ, {"GITEA_AUDIT_LOG": "/no/such/dir/a.log"}, clear=False
+        ):
+            with patch("restart_audit.emit_restart_event", return_value=False):
+                with patch("gitea_audit.audit_enabled", return_value=True):
+                    out = ra.record_restart_lifecycle(
+                        event_type=ra.EVENT_APPLY_GATE,
+                        outcome="deny",
+                        correlation_id="rst-deny",
+                        privileged=True,
+                        audit_path="/no/such/dir/a.log",
+                    )
+        self.assertFalse(out["audit_written"])
+        self.assertEqual(len(out["deny_reasons"]), 1)
+
+
+if __name__ == "__main__":
+    unittest.main()

webui/app.py

@@ -72,8 +72,6 @@ from webui.system_health import (
     snapshot_to_dict as system_health_to_dict,
 )
 from webui.system_health_views import render_system_health_page
-from webui import request_service
-from webui.request_views import render_requests_page
 
 _READ_ONLY_METHODS = frozenset({"GET", "HEAD", "OPTIONS"})
 _AUDIT_MUTATION_PATHS = frozenset({"/audit", "/api/audit"})
@@ -741,109 +739,6 @@ async def api_v1_analytics_ingest(request: Request) -> JSONResponse:
     )
 
 
-def _default_request_scope() -> dict[str, str]:
-    """Resolve remote/org/repo from the project registry for request forms.
-
-    Returns an empty mapping when the registry cannot be read, which makes
-    ``parse_request`` reject a request that did not name its own scope rather
-    than letting it default to some other repository.
-    """
-    from webui.queue_loader import _host_from_url  # host normalisation helper
-
-    registry, error = _load_project_registry()
-    if error is not None or not registry.projects:
-        return {}
-    project = registry.projects[0]
-    host = _host_from_url(project.remote_host)
-    return {
-        "remote": _derive_remote(host),
-        "org": project.gitea_owner or "",
-        "repo": project.repo_name or "",
-    }
-
-
-async def _request_payload(request: Request) -> dict[str, object]:
-    """Read a request body as JSON or form-encoded. Never raises."""
-    content_type = (request.headers.get("content-type") or "").lower()
-    if "application/json" in content_type:
-        try:
-            body = await request.json()
-        except Exception:
-            return {}
-        return dict(body) if isinstance(body, dict) else {}
-    try:
-        form = await request.form()
-    except Exception:
-        return {}
-    return {key: form[key] for key in form}
-
-
-async def requests_page(request: Request) -> HTMLResponse:
-    """Operator request form and intent preview (#643).
-
-    POST here only ever *previews*. Initiation is a separate confirmed call to
-    ``/api/v1/requests/apply`` so that submitting this form cannot reserve
-    work as a side effect.
-    """
-    submitted: dict[str, object] = {}
-    preview = None
-    error = None
-    if request.method == "POST":
-        submitted = await _request_payload(request)
-        work_request, error = request_service.parse_request(
-            submitted, default_scope=_default_request_scope()
-        )
-        if work_request is not None:
-            preview = request_service.preview_request(
-                work_request,
-                principal=resolve_principal(headers=dict(request.headers)),
-            )
-    return HTMLResponse(
-        render_requests_page(
-            preview=preview, error=error, submitted=submitted
-        )
-    )
-
-
-async def api_v1_request_preview(request: Request) -> JSONResponse:
-    """Dry-run authorization and intent preview for a work request (#643)."""
-    payload = await _request_payload(request)
-    work_request, error = request_service.parse_request(
-        payload, default_scope=_default_request_scope()
-    )
-    if work_request is None:
-        return JSONResponse(error.to_dict(), status_code=400)
-    preview = request_service.preview_request(
-        work_request,
-        principal=resolve_principal(headers=dict(request.headers)),
-    )
-    return JSONResponse(
-        preview.to_dict(), status_code=200 if preview.authorized else 403
-    )
-
-
-async def api_v1_request_apply(request: Request) -> JSONResponse:
-    """Initiate a previewed work request through the allocator (#643).
-
-    Fail-closed at every step: unauthorized, unconfirmed, not-next-safe, and
-    already-claimed all return without attempting an assignment.
-    """
-    payload = await _request_payload(request)
-    work_request, error = request_service.parse_request(
-        payload, default_scope=_default_request_scope()
-    )
-    if work_request is None:
-        return JSONResponse(error.to_dict(), status_code=400)
-    confirm = _truthy_flag(str(payload.get("confirm") or ""))
-    result = request_service.apply_request(
-        work_request,
-        principal=resolve_principal(headers=dict(request.headers)),
-        confirm=confirm,
-    )
-    status = int(result.pop("status_code", 403))
-    return JSONResponse(result, status_code=status)
-
-
 async def method_not_allowed(request: Request, _exc: Exception) -> Response:
     path = request.url.path
     if path in _AUDIT_MUTATION_PATHS and request.method == "POST":
@@ -911,17 +806,6 @@ def create_app(*, bind_host: str | None = None) -> Starlette:
                 api_action_attempt,
                 methods=["POST"],
             ),
-            Route("/requests", requests_page, methods=["GET", "POST"]),
-            Route(
-                "/api/v1/requests/preview",
-                api_v1_request_preview,
-                methods=["POST"],
-            ),
-            Route(
-                "/api/v1/requests/apply",
-                api_v1_request_apply,
-                methods=["POST"],
-            ),
             Route("/api/leases", api_leases, methods=["GET"]),
             Route("/api/v1/inventory", api_inventory, methods=["GET"]),
             Route(

webui/console_authz.py

@@ -115,12 +115,6 @@ class ConsoleAction:
     break_glass: bool
     phase: int
     summary: str
-    # Opt-in switch for an action whose execution path is genuinely wired
-    # ahead of its phase becoming globally active (#643). Naming a variable
-    # here enables nothing on its own: the variable must also be set in the
-    # environment. An action that leaves this ``None`` can only execute once
-    # ACTIVE_PHASE reaches its phase, exactly as before.
-    execution_env_flag: str | None = None
 
     @property
     def mcp_permission(self) -> str:
@@ -283,27 +277,6 @@ _ACTION_SPECS: tuple[ConsoleAction, ...] = (
         phase=2,
         summary="Restart one MCP namespace via the host supervisor.",
     ),
-    # #643: submit a work request — desired role, issue/PR, intent — and let
-    # the allocator reserve it. This is the one Phase 2 action whose execution
-    # path is actually implemented (``webui.request_service``), so it carries
-    # the opt-in flag; it stays denied until an operator sets that variable.
-    # Authority is operator-class because the outcome is a claim, not a Gitea
-    # verdict: initiating reviewer or merger *work* does not grant the right
-    # to approve or merge, which stays with the MCP role profile.
-    ConsoleAction(
-        action_id="initiate_workflow",
-        task_key="allocate_next_work",
-        action_class=CLASS_WRITE,
-        minimum_role=OPERATOR,
-        requires_confirmation=True,
-        dual_control=False,
-        break_glass=False,
-        phase=2,
-        summary=(
-            "Preview and initiate allocator-owned workflow work for a role."
-        ),
-        execution_env_flag="WEBUI_REQUESTS_EXECUTION",
-    ),
 )
 
 ACTIONS: dict[str, ConsoleAction] = {a.action_id: a for a in _ACTION_SPECS}
@@ -457,33 +430,6 @@ ALLOW_PREVIEW = "allowed_preview_only"
 # gated on this model landing; nothing here enables it.
 ACTIVE_PHASE = 1
 
-_TRUTHY = frozenset({"1", "true", "yes", "on"})
-
-
-def execution_wired(
-    action: ConsoleAction | None, env: dict[str, str] | None = None
-) -> bool:
-    """Whether *action* has a live execution path right now.
-
-    Two ways to be wired, and only two. The action's phase is active, or the
-    action declares an opt-in environment variable *and* that variable is set.
-    Everything else — including every action that never declares a flag — is
-    unwired, so the default across the registry stays deny.
-
-    Bumping ``ACTIVE_PHASE`` would enable execution for every action of that
-    phase at once. The per-action flag exists so a single implemented action
-    can go live without dragging its unimplemented phase-mates with it.
-    """
-    if action is None:
-        return False
-    if action.phase <= ACTIVE_PHASE:
-        return True
-    flag = (action.execution_env_flag or "").strip()
-    if not flag:
-        return False
-    source = env if env is not None else os.environ
-    return (source.get(flag) or "").strip().lower() in _TRUTHY
-
 
 @dataclass(frozen=True)
 class AuthorizationDecision:
@@ -523,19 +469,16 @@ def authorize(
     principal: Principal | None = None,
     *,
     for_execution: bool = False,
-    env: dict[str, str] | None = None,
 ) -> AuthorizationDecision:
     """Decide whether *principal* may invoke *action_id*. Deny by default.
 
     ``for_execution`` distinguishes a read-only preview from a real invocation.
-    ``execution_enabled`` reports whether the action has a live execution path
-    at all (:func:`execution_wired`) — for every action without an explicit
-    opt-in flag that stays ``False`` while the console is in Phase 1, so no
-    caller can read an allow as permission to mutate.
+    Even an allowed decision reports ``execution_enabled=False`` while the
+    console is in Phase 1, so no caller can read an allow as permission to
+    mutate.
     """
     who = principal if principal is not None else ANONYMOUS
     action = get_action(action_id)
-    wired = execution_wired(action, env)
 
     if action is None:
         return AuthorizationDecision(
@@ -554,7 +497,7 @@ def authorize(
         "requires_confirmation": action.requires_confirmation,
         "dual_control": action.dual_control,
         "break_glass": action.break_glass,
-        "execution_enabled": wired,
+        "execution_enabled": False,
     }
 
     if not who.authenticated:
@@ -587,19 +530,13 @@ def authorize(
             **base,
         )
 
-    if for_execution and not wired:
+    if for_execution and action.phase > ACTIVE_PHASE:
         return AuthorizationDecision(
             allowed=False,
             reason_code=DENY_PHASE_NOT_ACTIVE,
             detail=(
                 f"Action {action_id!r} belongs to phase {action.phase}; the "
-                f"console is in phase {ACTIVE_PHASE}"
-                + (
-                    f" and {action.execution_env_flag} is not set"
-                    if action.execution_env_flag
-                    else ""
-                )
-                + ". Execution is not wired."
+                f"console is in phase {ACTIVE_PHASE}. Execution is not wired."
             ),
             **base,
         )
@@ -608,8 +545,8 @@ def authorize(
         allowed=True,
         reason_code=ALLOW_PREVIEW,
         detail=(
-            "Principal holds the required role. Execution proceeds only for an "
-            "action with a wired execution path; everything else is preview."
+            "Principal holds the required role. Preview only — execution "
+            "remains disabled until the Phase 2 action framework ships."
         ),
         **base,
     )

webui/nav.py

@@ -45,7 +45,6 @@ NAV_GROUPS: tuple[NavGroup, ...] = (
         NavItem("/queue", "Queue"),
         NavItem("/leases", "Leases"),
         NavItem("/actions", "Actions"),
-        NavItem("/requests", "Requests"),
     )),
     NavGroup("Runtime/Sessions", (
         NavItem("/runtime", "Runtime health"),

webui/request_views.py

@@ -1,164 +0,0 @@
-"""HTML views for the operator request surface (#643).
-
-The form is deliberately a *preview* form. It has no initiate button, because
-initiating requires a confirmed POST to ``/api/v1/requests/apply`` and a stray
-form submission must not be able to produce one by accident.
-
-Nothing rendered here is trusted input: every interpolated value is escaped,
-and the page renders only values the service already produced rather than
-echoing a raw request body back.
-"""
-
-from __future__ import annotations
-
-import html
-import json
-from typing import Any
-
-from webui.layout import render_page
-from webui.request_service import (
-    REQUESTABLE_ROLES,
-    WORK_KINDS,
-    RequestError,
-    RequestPreview,
-)
-
-REQUESTS_PATH = "/requests"
-PREVIEW_API_PATH = "/api/v1/requests/preview"
-APPLY_API_PATH = "/api/v1/requests/apply"
-
-
-def _escape(text: Any) -> str:
-    return html.escape(str(text if text is not None else ""), quote=True)
-
-
-REQUEST_PAGE_STYLES = """
-<style>
-  .request-form { display: grid; gap: 0.75rem; max-width: 44rem; }
-  .request-form label { display: grid; gap: 0.25rem; font-size: 0.9rem; }
-  .request-check { margin: 0.35rem 0; }
-  .request-check .verdict-ok { color: var(--accent); }
-  .request-check .verdict-fail { color: #d14; }
-  .request-prohibited code { margin-right: 0.4rem; }
-</style>
-"""
-
-
-def _options(values: tuple[str, ...], selected: Any) -> str:
-    return "".join(
-        f"<option value='{_escape(value)}'"
-        + (" selected" if selected == value else "")
-        + f">{_escape(value)}</option>"
-        for value in values
-    )
-
-
-def _form(values: dict[str, Any] | None = None) -> str:
-    current = dict(values or {})
-    number = current.get("work_number")
-    return (
-        f"<form class='request-form' method='post' action='{REQUESTS_PATH}'>"
-        "<label>Desired role<select name='desired_role'>"
-        f"{_options(REQUESTABLE_ROLES, current.get('desired_role'))}"
-        "</select></label>"
-        "<label>Work kind<select name='work_kind'>"
-        f"{_options(WORK_KINDS, current.get('work_kind'))}"
-        "</select></label>"
-        "<label>Issue or PR number"
-        "<input type='number' name='work_number' min='1' required "
-        f"value='{_escape(number) if number else ''}'></label>"
-        "<label>Intent summary"
-        "<input type='text' name='intent_summary' maxlength='500' required "
-        f"value='{_escape(current.get('intent_summary'))}'></label>"
-        "<label>Expected head SHA <span class='muted'>(PR work only)</span>"
-        "<input type='text' name='expected_head_sha' "
-        f"value='{_escape(current.get('expected_head_sha'))}'></label>"
-        "<button type='submit' class='copy-btn'>Preview request</button>"
-        "<p class='muted meta'>Preview is read-only and creates no assignment. "
-        f"Initiating requires a confirmed POST to <code>{APPLY_API_PATH}</code>."
-        "</p>"
-        "</form>"
-    )
-
-
-def _checks_block(preview: RequestPreview) -> str:
-    rows = []
-    for check in preview.checks:
-        verdict = "PASS" if check.ok else "FAIL"
-        css = "verdict-ok" if check.ok else "verdict-fail"
-        rows.append(
-            "<li class='request-check'>"
-            f"<span class='{css}'><strong>{verdict}</strong></span> "
-            f"<code>{_escape(check.name)}</code> — {_escape(check.detail)} "
-            f"<span class='muted meta'>({_escape(check.reason_code)})</span>"
-            "</li>"
-        )
-    return "<ul>" + "".join(rows) + "</ul>"
-
-
-def _preview_block(preview: RequestPreview) -> str:
-    verdict = "AUTHORIZED" if preview.authorized else "DENIED"
-    prohibited = "".join(
-        f"<code>{_escape(action)}</code>" for action in preview.prohibited_actions
-    )
-    request = preview.request
-    evidence = json.dumps(preview.allocator_evidence, indent=2, default=str)
-    return (
-        "<h3>Intent preview</h3>"
-        f"<p><strong>{verdict}</strong> — {_escape(preview.detail)}</p>"
-        "<p class='meta'>"
-        f"Role <code>{_escape(request.desired_role)}</code> · "
-        f"{_escape(request.work_kind)} <code>{_escape(request.display_ref)}</code>"
-        f" · profile <code>{_escape(preview.required_profile)}</code> · "
-        f"namespace <code>{_escape(preview.required_namespace)}</code> · "
-        f"permission <code>{_escape(preview.required_permission)}</code>"
-        "</p>"
-        f"<p>Intent: {_escape(request.intent_summary)}</p>"
-        f"{_checks_block(preview)}"
-        f"<p><strong>Next safe action:</strong> "
-        f"{_escape(preview.next_safe_action)}</p>"
-        "<p class='request-prohibited'><strong>Prohibited for this role:</strong> "
-        + (prohibited or "<span class='muted'>none declared</span>")
-        + "</p>"
-        "<p class='muted meta'>Correlation id "
-        f"<code>{_escape(preview.correlation_id)}</code></p>"
-        "<details><summary>Allocator evidence</summary>"
-        f"<pre class='prompt-text'>{_escape(evidence)}</pre>"
-        "</details>"
-    )
-
-
-def _error_block(error: RequestError) -> str:
-    field = (
-        f"<p class='meta'>Field: <code>{_escape(error.field_name)}</code></p>"
-        if error.field_name
-        else ""
-    )
-    return (
-        "<h3>Request rejected</h3>"
-        f"<p><strong>{_escape(error.reason_code)}</strong> — "
-        f"{_escape(error.detail)}</p>{field}"
-    )
-
-
-def render_requests_page(
-    *,
-    preview: RequestPreview | None = None,
-    error: RequestError | None = None,
-    submitted: dict[str, Any] | None = None,
-) -> str:
-    """Render the request form, plus a preview or rejection when one exists."""
-    body = (
-        "<h2>Requests</h2>"
-        "<p>Submit a work request — desired role, issue or PR, and intent — "
-        "and see whether it would be authorized before anything is reserved. "
-        "Initiation goes through the allocator (#600/#613); this console never "
-        "self-selects work, never approves, and never merges.</p>"
-        + _form(submitted)
-        + (_error_block(error) if error is not None else "")
-        + (_preview_block(preview) if preview is not None else "")
-        + f"<p class='meta'><a href='{PREVIEW_API_PATH}'>Preview API</a> · "
-        "<a href='/api/console/security-model'>RBAC model</a></p>"
-        + REQUEST_PAGE_STYLES
-    )
-    return render_page(title="Requests", body_html=body)

webui/traffic_loader.py

@@ -201,16 +201,6 @@ def _candidates_from_queue_snapshot(q_snap: QueueSnapshot) -> list[WorkCandidate
     return candidates
 
 
-def candidates_from_queue_snapshot(q_snap: QueueSnapshot) -> list[WorkCandidate]:
-    """Public alias for :func:`_candidates_from_queue_snapshot` (#643).
-
-    The request-initiation service ranks the same candidate set this view
-    renders, so both must agree on how a queue row becomes a candidate. One
-    construction, two callers — not two that can drift apart.
-    """
-    return _candidates_from_queue_snapshot(q_snap)
-
-
 def _claim_lease_records(inventory: dict[str, Any] | None) -> list[dict[str, Any]]:
     """Normalize ``build_claim_inventory`` entries into lease records.