Merge remote-tracking branch 'prgs/master' into feat/issue-659-maintenance-drain-mode

Keep #659 maintenance-drain assignment stop and #643 side_effect_free
apply guard; session registration remains gated by side_effect_free.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>

allocator_service.py

@@ -26,6 +26,7 @@ from dataclasses import dataclass, field
 from datetime import datetime, timezone
 from typing import Any, Mapping, Sequence
 
+import maintenance_drain
 from control_plane_db import (
     ControlPlaneDB,
     ControlPlaneError,
@@ -936,6 +937,46 @@ def allocate_next_work(
             "allocation_mode": (allocation_mode or "").strip() or None,
         }
 
+# #659 AC2: while maintenance drain is active, no new work is assigned —
+    # for dry-run and apply alike, so a preview can never be read as evidence
+    # that work was assignable during the drain. Checked before session
+    # registration so a drained allocator leaves no new state behind.
+    try:
+        drain_record = db.read_maintenance_drain(remote=remote, org=org, repo=repo)
+    except Exception as exc:  # noqa: BLE001 — unreadable drain state fails closed
+        return {
+            "success": False,
+            "outcome": OUTCOME_NO_SAFE,
+            "reasons": [
+                f"maintenance-drain state lookup failed: {exc} (fail closed, #659)"
+            ],
+            "skipped": [],
+            "assignment": None,
+            "substrate": "control_plane_db",
+        }
+
+    drain_decision = maintenance_drain.classify_assignment(drain_record)
+    if not drain_decision["assignment_allowed"]:
+        return {
+            "success": True,
+            "outcome": OUTCOME_WAIT,
+            "apply": apply,
+            "role": role_norm,
+            "allocation_mode": mode,
+            "remote": remote,
+            "org": org,
+            "repo": repo,
+            "selected": None,
+            "reasons": list(drain_decision["reasons"]),
+            "reason_code": drain_decision["reason_code"],
+            "skipped": [],
+            "assignment": None,
+            "substrate": "control_plane_db",
+            "maintenance_drain": maintenance_drain.status_payload(
+                drain_record, remote=remote, org=org, repo=repo
+            ),
+        }
+
     # 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:

control_plane_db.py

@@ -31,8 +31,9 @@ from typing import Any, Iterator, Sequence
 
 import dependency_graph
 import gitea_audit
+import maintenance_drain
 
-SCHEMA_VERSION = 5
+SCHEMA_VERSION = 6
 
 # Assignable work kinds only — raw monitoring incidents are never work items.
 WORK_KINDS = frozenset({"issue", "pr"})
@@ -239,6 +240,31 @@ CREATE INDEX IF NOT EXISTS idx_session_checkpoints_session
 CREATE INDEX IF NOT EXISTS idx_session_checkpoints_work
     ON session_checkpoints(remote, org, repo, work_kind, work_number);
 
+-- Graceful maintenance-drain state (#659). One current row per repository
+-- scope — drain is a *state*, not a history, so entering and exiting update
+-- the same row and every transition is audited to ``events``. Creating the
+-- table is the v5->v6 migration: additive, idempotent, and it never touches
+-- prior tables. ``state`` is CHECK-constrained so an unknown value can never
+-- be written and later read as "not draining".
+CREATE TABLE IF NOT EXISTS maintenance_drain (
+    drain_id TEXT PRIMARY KEY,
+    remote TEXT NOT NULL,
+    org TEXT NOT NULL,
+    repo TEXT NOT NULL,
+    state TEXT NOT NULL DEFAULT 'inactive'
+        CHECK (state IN ('inactive', 'draining')),
+    reason TEXT NOT NULL DEFAULT '',
+    requested_by TEXT NOT NULL DEFAULT '',
+    requested_by_profile TEXT NOT NULL DEFAULT '',
+    session_id TEXT NOT NULL DEFAULT '',
+    entered_at TEXT NOT NULL DEFAULT '',
+    exited_at TEXT NOT NULL DEFAULT '',
+    drain_schema_version INTEGER NOT NULL DEFAULT 6,
+    created_at TEXT NOT NULL,
+    updated_at TEXT NOT NULL,
+    UNIQUE (remote, org, repo)
+);
+
 -- Model usage, token cost, latency, and performance events (#651)
 CREATE TABLE IF NOT EXISTS usage_events (
     usage_id INTEGER PRIMARY KEY AUTOINCREMENT,
@@ -3025,3 +3051,170 @@ class ControlPlaneDB:
             "live_lease_id": None if live_lease_id is None else str(live_lease_id),
             "reconcile_action": "reconcile_required" if stale else "safe_to_resume",
         }
+
+    # ── Maintenance drain (#659) ─────────────────────────────────────────────
+
+    @staticmethod
+    def _maintenance_drain_row(row: sqlite3.Row | None) -> dict[str, Any] | None:
+        """Convert a ``maintenance_drain`` row to a plain record."""
+        if row is None:
+            return None
+        return {key: row[key] for key in row.keys()}
+
+    def read_maintenance_drain(
+        self, *, remote: str, org: str, repo: str
+    ) -> dict[str, Any] | None:
+        """Return the current drain record for a scope, or None if never set.
+
+        None and a stored ``inactive`` row mean the same thing to callers —
+        ``maintenance_drain.is_draining`` treats both as not draining — so the
+        read never has to invent a record to answer the gate.
+        """
+        with self._tx(immediate=False) as conn:
+            row = conn.execute(
+                """
+                SELECT * FROM maintenance_drain
+                 WHERE remote = ? AND org = ? AND repo = ?
+                """,
+                (str(remote or ""), str(org or ""), str(repo or "")),
+            ).fetchone()
+        return self._maintenance_drain_row(row)
+
+    def set_maintenance_drain(
+        self,
+        *,
+        remote: str,
+        org: str,
+        repo: str,
+        state: str,
+        reason: str = "",
+        requested_by: str = "",
+        requested_by_profile: str = "",
+        session_id: str = "",
+    ) -> dict[str, Any]:
+        """Enter or exit maintenance drain for one repository scope (AC1).
+
+        The state transition is audited to ``events`` — entering and exiting
+        are exactly the moments an operator has to be able to reconstruct
+        later. Re-entering an already-draining scope is idempotent: it refreshes
+        the reason/owner metadata, keeps the original ``entered_at``, and
+        records no duplicate transition event.
+
+        Capability authorization happens above this layer (the drain tasks
+        carry a non-``gitea.*`` permission in the task capability map); the DB
+        records who asked and why, and never grants the right itself.
+        """
+        state_norm = maintenance_drain.normalize_state(state)
+        raw = {
+            "reason": str(reason or ""),
+            "requested_by": str(requested_by or ""),
+            "requested_by_profile": str(requested_by_profile or ""),
+            "session_id": str(session_id or ""),
+        }
+        clean = gitea_audit.redact(raw)
+        remote_s, org_s, repo_s = str(remote or ""), str(org or ""), str(repo or "")
+        now_s = _ts()
+
+        with self._tx() as conn:
+            existing = conn.execute(
+                """
+                SELECT * FROM maintenance_drain
+                 WHERE remote = ? AND org = ? AND repo = ?
+                """,
+                (remote_s, org_s, repo_s),
+            ).fetchone()
+
+            prior_state = (
+                maintenance_drain.normalize_state(existing["state"])
+                if existing is not None
+                else maintenance_drain.STATE_INACTIVE
+            )
+            transitioned = prior_state != state_norm
+
+            prior_entered = (
+                str(existing["entered_at"] or "") if existing is not None else ""
+            )
+            prior_exited = (
+                str(existing["exited_at"] or "") if existing is not None else ""
+            )
+            if state_norm == maintenance_drain.STATE_DRAINING:
+                # A re-entry keeps the original entry time (the drain never
+                # stopped); a fresh entry stamps now and clears the old exit.
+                entered_at = prior_entered if (not transitioned and prior_entered) else now_s
+                exited_at = ""
+            else:
+                entered_at = prior_entered
+                exited_at = now_s if (transitioned or not prior_exited) else prior_exited
+
+            if existing is None:
+                drain_id = uuid.uuid4().hex
+                conn.execute(
+                    """
+                    INSERT INTO maintenance_drain(
+                        drain_id, remote, org, repo, state, reason,
+                        requested_by, requested_by_profile, session_id,
+                        entered_at, exited_at, drain_schema_version,
+                        created_at, updated_at
+                    ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+                    """,
+                    (
+                        drain_id, remote_s, org_s, repo_s, state_norm,
+                        clean["reason"], clean["requested_by"],
+                        clean["requested_by_profile"], clean["session_id"],
+                        entered_at, exited_at,
+                        maintenance_drain.DRAIN_SCHEMA_VERSION, now_s, now_s,
+                    ),
+                )
+            else:
+                drain_id = str(existing["drain_id"])
+                conn.execute(
+                    """
+                    UPDATE maintenance_drain
+                       SET state = ?, reason = ?, requested_by = ?,
+                           requested_by_profile = ?, session_id = ?,
+                           entered_at = ?, exited_at = ?,
+                           drain_schema_version = ?, updated_at = ?
+                     WHERE drain_id = ?
+                    """,
+                    (
+                        state_norm, clean["reason"], clean["requested_by"],
+                        clean["requested_by_profile"], clean["session_id"],
+                        entered_at, exited_at,
+                        maintenance_drain.DRAIN_SCHEMA_VERSION, now_s, drain_id,
+                    ),
+                )
+
+            if transitioned:
+                event_type = (
+                    "maintenance_drain_enter"
+                    if state_norm == maintenance_drain.STATE_DRAINING
+                    else "maintenance_drain_exit"
+                )
+                conn.execute(
+                    """
+                    INSERT INTO events(work_item_id, event_type, message, created_at)
+                    VALUES (NULL, ?, ?, ?)
+                    """,
+                    (
+                        event_type,
+                        f"drain {drain_id} scope {remote_s}/{org_s}/{repo_s} "
+                        f"{prior_state} -> {state_norm} by "
+                        f"{clean['requested_by'] or '(unknown)'} "
+                        f"({clean['requested_by_profile'] or 'no profile'}); "
+                        f"reason: {clean['reason'] or '(none)'}",
+                        now_s,
+                    ),
+                )
+
+            row = conn.execute(
+                "SELECT * FROM maintenance_drain WHERE drain_id = ?", (drain_id,)
+            ).fetchone()
+
+        record = self._maintenance_drain_row(row) or {}
+        return {
+            "record": record,
+            "drain_id": drain_id,
+            "state": state_norm,
+            "prior_state": prior_state,
+            "transitioned": transitioned,
+        }

docs/mcp-maintenance-drain.md

@@ -0,0 +1,45 @@
+# MCP maintenance-drain mode (#659)
+
+Graceful **maintenance drain** stops new work assignment and defers non-allowlisted
+mutations so sessions can finish critical handoffs and checkpoint before a
+restart. It is **not** a restart authorization: the drain *proof* and apply gate
+remain #661.
+
+## State
+
+Per repository scope (`remote`/`org`/`repo`) in the control-plane DB table
+`maintenance_drain` (schema v6):
+
+| State | Meaning |
+|-------|---------|
+| `inactive` | Normal operation (also: no row) |
+| `draining` | Assignment stopped; non-allowlisted mutations deferred |
+
+Enter/exit transitions are audited as `maintenance_drain_enter` /
+`maintenance_drain_exit` events.
+
+## Tools
+
+| Tool | Permission | Effect |
+|------|------------|--------|
+| `gitea_maintenance_drain_status` | `gitea.read` | Observe drain (every session) |
+| `gitea_enter_maintenance_drain` | `runtime.maintenance_drain` | Enter drain (capability-gated) |
+| `gitea_exit_maintenance_drain` | `runtime.maintenance_drain` | Exit drain |
+
+`runtime.maintenance_drain` is intentionally **not** a `gitea.*` op, so ordinary
+author profiles cannot enter drain by accident.
+
+## Enforcement
+
+1. **Allocator** (`allocate_next_work`): while draining, returns `outcome=wait`
+   with `reason_code=maintenance_drain_assignment_stopped` for dry-run and apply.
+2. **Mutation preflight** (`verify_preflight_purity`): non-allowlisted mutation
+   tasks raise `MaintenanceDrainError` with a typed next action.
+3. **Allowlist** (safety only): heartbeats, lease release/abandon, session
+   checkpoints, enter/exit drain. Reads always work.
+
+## Restart relationship
+
+Drain mode prepares the blast radius. Restart apply still requires a clean
+`DrainProof` (#661) or authorized break-glass. Status payloads never claim
+restart permission.

docs/mcp-namespace-eof-recovery.md

@@ -153,19 +153,7 @@ not a tool argument: a session must never be able to authorize itself.
 ## Related
 
 - #630 — manual daemon killing as contaminated recovery (this contrast, enforced).
-- #657 — restart-path inventory and daemon classification.
-- #686 — manual server launch detection & fail-closed provenance gate.
 - #531 / #544 — stale-runtime detection (`ps`-based); sibling failure mode.
 - #558 / `docs/mcp-daemon-import-guard.md` — why shell imports are not a repair.
 - `docs/mcp-client-registration.md` — per-server registration contract.
 - `docs/mcp-namespace-health.md` — probe sources and mutation enforcement.
-
-## Sanctioned reconnect vs forbidden manual launch (#686)
-
-In addition to manual process killing (#630), manually launching a duplicate role server from an ad hoc shell (`python3 mcp_server.py`) is forbidden and fail-closed:
-
-- **Why manual launches are unsupported:** A terminal-launched `mcp_server.py` holds its own stdio transport; it can never bind to the IDE client's stdio pipes. It cannot restore a dropped IDE namespace, and a manual duplicate process masks stale client-managed runtimes for that profile, defeating stale-runtime gates.
-- **Sanctioned path:** Supported recovery is IDE/client-managed reconnect only (`/mcp reconnect`, IDE restart, or sanctioned reconnect exposure).
-- **Fail-closed enforcement (#686):** Mutating tools on a server lacking client-managed launch provenance (`GITEA_CLIENT_MANAGED=1`) refuse execution fail-closed with typed blocker `unsupported_manual_launch` and an exact next action. Unsupported `GITEA_*` env overrides (e.g. `GITEA_DUMMY`) are surfaced in diagnostics rather than silently ignored.
-- **Inventory & staleness:** Staleness diagnostics ignore non-client-managed duplicates when evaluating runtime freshness and inventory duplicate processes per profile (#657, #686).
-

docs/remote-mcp/coupling-inventory.md

@@ -1,230 +0,0 @@
-# Remote-MCP coupling inventory
-
-Every place the Gitea MCP server depends on being a local, client-spawned, stdio-attached
-process on the operator's machine.
-
-- **Issue:** #930 (Remote-MCP 01), child 1 of epic #929.
-- **Generated against commit:** `7bf4f1258451823a55b36d2157e74f8457165088` (`master`).
-- **Anchors:** every `file:line` below resolves at the commit above and at the commit that
-  adds this document. This change adds one new file and edits no existing file, so no
-  existing line number shifts between the two.
-- **Scope:** documentation only. No server behavior changes in this child.
-
-## How to read an entry
-
-| Field | Meaning |
-| ----- | ------- |
-| **Anchor** | `file:line` at the commit under review. |
-| **Assumes today** | What the code takes for granted while running as a local stdio process. |
-| **Observes remotely** | What the same code would actually see on a shared remote host. |
-| **Class** | One of: *portable as written*, *needs a seam*, *needs a replacement*, *cannot be remote*. |
-| **Owner** | Exactly one epic child (#931–#939) responsible for the fix. |
-
-Classification meanings:
-
-- **portable as written** — the code is already transport-, host-, and principal-neutral; it
-  moves unchanged once its inputs are supplied by a remote-aware caller.
-- **needs a seam** — the logic is correct but is wired to a hard-coded local source. It needs
-  an injection point, not new semantics.
-- **needs a replacement** — the semantics themselves are local-only. A remote deployment
-  needs a differently-defined mechanism, not the same mechanism relocated.
-- **cannot be remote** — the operation is inherently about the operator's own machine
-  (its process table, its keychain, its checkout). It must either stay local behind an
-  explicit boundary or be deleted from the remote surface.
-
----
-
-## 1. Transport bind
-
-The transport is bound literally, once, at process start, and the bound value is the root of
-the mutation-authorization chain.
-
-| ID | Anchor | Assumes today | Observes remotely | Class | Owner |
-| -- | ------ | ------------- | ----------------- | ----- | ----- |
-| T1 | `gitea_mcp_server.py:23750` | The single production bind call passes the literal `transport="stdio"` immediately before the server loop. | The literal is wrong for any non-stdio deployment; there is no parameter to change it. | needs a seam | #931 |
-| T2 | `mcp_daemon_guard.py:45` | `_PRODUCTION_TRANSPORTS = frozenset({"stdio"})` is the closed allowlist of production transports. | A remote transport name is rejected by the allowlist before any other check runs. | needs a seam | #931 |
-| T3 | `mcp_daemon_guard.py:174` | `bind_native_mcp_transport` raises `UnsanctionedRuntimeError` for any transport outside `_PRODUCTION_TRANSPORTS` (raise at `mcp_daemon_guard.py:187`). | The remote server fails to start rather than degrading; the failure is correct, but the allowlist is the only thing that must change. | needs a seam | #931 |
-| T4 | `mcp_daemon_guard.py:328` | `is_native_mcp_transport()` asserts a process-local runtime record whose `pid` matches `os.getpid()` and whose phase is `transport_bound`. The predicate itself names no transport. | Unchanged semantics: one server process that bound one transport. It stays true on a remote host. | portable as written | #931 |
-| T5 | `mcp_daemon_guard.py:349` | `is_production_native_mcp_transport()` adds only a `mode == production` check on top of T4. | Unchanged. | portable as written | #931 |
-| T6 | `irrecoverable_provenance.py:497` | `assess_transport_for_auth_mint()` requires production native transport before minting non-forgeable recovery authorization (#709 F1). | The gate is transport-agnostic in form, but its guarantee — "an ordinary Python process cannot reach this" — is currently underwritten by the stdio bind. Under a remote transport the guarantee must be re-derived from the authenticated session, not from the bind. | needs a seam | #931 |
-| T7 | `gitea_mcp_server.py:8375` | Consumer: refuses to proceed unless `assess_transport_for_auth_mint()` allows. | Unchanged given a corrected T6. | portable as written | #931 |
-| T8 | `gitea_mcp_server.py:8624` | Second consumer of the same gate on the confirmation path. | Unchanged given a corrected T6. | portable as written | #931 |
-| T9 | `mcp_server.py:4` | Module docstring asserts "Runs over stdio." as a property of the server. | The stated contract becomes false on the remote deployment and is load-bearing documentation for operators. | needs a replacement | #931 |
-
-## 2. Launch provenance
-
-Mutations fail closed unless the process can prove a client launched it with real stdio pipes
-and `GITEA_CLIENT_MANAGED` provenance. Every proof in this section is a statement about the
-local operating system.
-
-| ID | Anchor | Assumes today | Observes remotely | Class | Owner |
-| -- | ------ | ------------- | ----------------- | ----- | ----- |
-| P1 | `gitea_mcp_server.py:14588` | `_is_client_managed_process()` derives provenance from `GITEA_CLIENT_MANAGED` / `GITEA_MCP_CLIENT_MANAGED` / `GITEA_SERVER_PROVENANCE` / `GITEA_FORCE_CLIENT_MANAGED` on this process's own environment. | A long-lived remote process has one environment for all callers, so a per-process env var can no longer say anything about the caller that issued a request. | needs a replacement | #934 |
-| P2 | `gitea_mcp_server.py:14606` | Falls back to `sys.stdin.isatty()`: an active TTY on stdin means a human launched it from a terminal, so refuse. | A remote server has no meaningful stdin. The signal is absent, not merely different. | cannot be remote | #934 |
-| P3 | `gitea_mcp_server.py:14618` | `_provenance_mutation_block()` emits `blocker_kind: "unsupported_manual_launch"` and a "reconnect the IDE/client-managed MCP namespace" remediation. | The block shape is reusable; its predicate and its remediation text are both stdio-specific. | needs a seam | #934 |
-| P4 | `gitea_mcp_server.py:20599` | `_check_mcp_runtimes_diagnostics()` shells `ps -o pid,lstart,command -ax` and greps for `mcp_server.py` to find peer role servers. | On a shared host the process table lists unrelated tenants' processes, or none at all under a container. Peer discovery by `ps` has no remote meaning. | cannot be remote | #934 |
-| P5 | `gitea_mcp_server.py:20702` | More than one process per `GITEA_MCP_PROFILE` in the local process table is reported as a duplicate-launch fault. | A remote endpoint is expected to serve many concurrent sessions per role. "Two processes for one role" becomes the normal case, so the check inverts from a safety net into a false wall. | cannot be remote | #934 |
-| P6 | `gitea_mcp_server.py:20715` | Processes lacking client-managed provenance are ignored for runtime freshness and reported as manual launches. | Same defect as P5: correctness depends on enumerating local peers. | cannot be remote | #934 |
-| P7 | `gitea_config.py:1172` | `RECOGNIZED_GITEA_ENV_KEYS` is the allowlist of `GITEA_*` env vars a legitimately launched server may carry; anything else is contamination. | Configuration on a remote host arrives from deployment tooling, not from a client-authored env block. The allowlist keeps working mechanically but stops proving anything about provenance. | needs a replacement | #934 |
-| P8 | `gitea_mcp_server.py:20683` | The unsupported-env scan applies `RECOGNIZED_GITEA_ENV_KEYS` to *other* processes' environments harvested via `ps eww <pid>`. | Reading another process's environment is unavailable or prohibited across tenants, and is not exposed in this form outside macOS/BSD `ps`. | cannot be remote | #934 |
-| P9 | `mcp_daemon_guard.py:126` | `mark_sanctioned_daemon()` requires the claiming stack frame's resolved absolute path to be the canonical `mcp_server.py` / `gitea_mcp_server.py` next to the guard module; basename spoofing is rejected. | Entrypoint-path identity still exists on a remote host, but it authenticates the *deployment*, not the *caller*. It must be kept and demoted from "authorizes mutations" to "authorizes the process". | needs a seam | #934 |
-| P10 | `gitea_config.py:1233` | The client-config generator emits `"GITEA_CLIENT_MANAGED": "1"` into each generated MCP client entry, alongside `GITEA_MCP_CONFIG` / `GITEA_MCP_PROFILE`. | A remote endpoint is addressed by URL and credential, not by a spawn command with an env block. This generator produces the wrong artifact entirely. | needs a replacement | #938 |
-| P11 | `mcp_namespace_health.py:232` | Namespace health classifies a namespace as `client_managed` or `manual_launch` from the reported env summary. | During dual-run, local and remote namespaces coexist and must both be classifiable; a two-valued local/manual axis cannot express "remote endpoint, authenticated session". | needs a replacement | #939 |
-| P12 | `gitea_mcp_server.py:18161` | The diagnostics payload reports `server_provenance` as exactly `"client_managed"` or `"manual_launch"`. | This is the field a cutover operator reads to confirm which deployment served a call. It must gain a remote value before dual-run parity can be validated. | needs a replacement | #939 |
-
-## 3. Role binding
-
-Role separation is currently enforced by *which process a call reaches*. The process is pinned
-to one role for its lifetime by an environment variable.
-
-| ID | Anchor | Assumes today | Observes remotely | Class | Owner |
-| -- | ------ | ------------- | ----------------- | ----- | ----- |
-| R1 | `gitea_config.py:54` | `ENV_PROFILE = "GITEA_MCP_PROFILE"` is the single source of the active profile, read from the process environment. | One shared process serves several principals; a process-wide profile cannot answer "who is calling now". This is the root of the coupling. | needs a replacement | #932 |
-| R2 | `review_workflow_load.py:95` | Reads `GITEA_MCP_PROFILE` directly to decide the reviewer workflow binding. | Reads the deployment's profile, not the caller's, silently granting or denying the wrong role. | needs a replacement | #932 |
-| R3 | `mcp_discoverability.py:152` | Reads `GITEA_MCP_PROFILE` to describe the namespace to the client. | Correct logic, wrong input source; it needs the request principal injected. | needs a seam | #932 |
-| R4 | `webui/deployment_boundary.py:115` | Reads `GITEA_MCP_PROFILE` to classify the deployment boundary for the console. | Same as R3. | needs a seam | #932 |
-| R5 | `gitea_mcp_server.py:21106` | Remediation text instructs the operator to "Relaunch the server with `GITEA_MCP_PROFILE` set to a profile that has the required permission". | Relaunching a shared remote endpoint to change one caller's role is not a valid instruction; it would re-role every other session. | needs a replacement | #932 |
-| R6 | `native_mcp_preference.py:93` | Detects shell commands that override `GITEA_MCP_PROFILE` away from the session (`native_mcp_preference.py:223`) and flags them as CLI auth divergence. | The divergence check is genuinely useful and survives, but its notion of "the session's profile" must come from the request principal. | needs a seam | #932 |
-| R7 | `gitea_mcp_server.py:20671` | Recovers a peer server's role by regexing `GITEA_MCP_PROFILE=` out of that process's environment. | Depends on P4/P8 process-table access; role discovery by peer-env scraping has no remote analogue. | cannot be remote | #932 |
-
-## 4. Credentials
-
-Every token resolves, directly or indirectly, from one human's macOS keychain.
-
-| ID | Anchor | Assumes today | Observes remotely | Class | Owner |
-| -- | ------ | ------------- | ----------------- | ----- | ----- |
-| C1 | `gitea_config.py:956` | `_keychain_token()` shells `security find-generic-password -s <item> -w`. | `security(1)` is a macOS binary reading the calling user's login keychain. It does not exist on a Linux host and would be the wrong identity even on a shared Mac. | cannot be remote | #933 |
-| C2 | `gitea_config.py:974` | `resolve_token(profile, keychain_lookup=_keychain_token)` dispatches on `auth.type` of `env` or `keychain`, defaulting the lookup to C1. | The injectable `keychain_lookup` parameter is the existing seam; a remote credential provider plugs in here without changing the dispatch. | needs a seam | #933 |
-| C3 | `gitea_config.py:1015` | `keychain_auth(item_id)` constructs the `{"type": "keychain", "id": ...}` reference stored in profiles. | The reference type itself encodes "macOS keychain" into persisted config. A remote provider needs a new auth reference type, not a new value of this one. | needs a replacement | #933 |
-| C4 | `mcp_daemon_guard.py:440` | `assert_keychain_access_allowed()` fails closed for git-credential keychain fill outside a sanctioned daemon, with an operator opt-out env var. | The gate protects a mechanism that will not exist remotely. Its replacement must gate the *credential provider* call, not the keychain call, or the protection silently lapses. | needs a replacement | #933 |
-| C5 | `sentry_incident_bridge.py:190` | `resolve_token(env)` resolves the Sentry token from an injected env mapping with no keychain path. | Already host-neutral; it is the shape the Gitea credential path should converge on. | portable as written | #933 |
-| C6 | `gitea_mcp_server.py:18469` | The profile-audit tool calls `gitea_config.resolve_token(p)` for every configured profile to report "credentials present" without networking. | On a remote host this would materialize every principal's credential inside one process — an audit surface that becomes a credential-aggregation risk. | needs a seam | #933 |
-
-## 5. Runtime freshness
-
-The mutation gate is defined as "the commit this process started at matches the checkout on
-this disk, and both match live master". Two of those three terms are local-disk facts.
-
-| ID | Anchor | Assumes today | Observes remotely | Class | Owner |
-| -- | ------ | ------------- | ----------------- | ----- | ----- |
-| F1 | `master_parity_gate.py:168` | `capture_startup_parity(root)` reads git `HEAD` from the server's own root once at startup and returns it as the baseline. | A remote host carries a deployed artifact, not the operator's checkout. Its `HEAD` says nothing about the operator's working tree, which is the thing the gate exists to protect. | cannot be remote | #935 |
-| F2 | `master_parity_gate.py:255` | `mutation_safe = determinable and in_parity and live_known and not live_stale` — a conjunction of two local-HEAD comparisons and one live-remote comparison. | Two of the three conjuncts lose meaning, so the whole verdict does. A remote deployment needs a redefined, testable freshness predicate rather than this one relocated. | needs a replacement | #935 |
-| F3 | `master_parity_gate.py:164` | The live-remote head is probed and cached per `(root, remote, branch)`, keyed on the local root. | The live-remote probe is the one conjunct that survives; it needs a key that is not the operator's filesystem path. | needs a seam | #935 |
-| F4 | `gitea_mcp_server.py:18262` | `gitea_assess_master_parity` publishes `startup_head` / `local_head` / `live_remote_head` / `mutation_safe` as the authoritative mutation-safety verdict. | The tool's contract is consumed by every mutation caller and by the operator; it must keep its shape while its semantics are redefined, or every consumer breaks at once. | needs a replacement | #935 |
-| F5 | `gitea_mcp_server.py:23054` | Falls back to `_process_boot_head_sha` — the commit this process booted at — when the parity payload has no `startup_head`. | Same defect as F1, in a fallback path that is easy to miss when F1 is fixed. | needs a seam | #935 |
-| F6 | `gitea_mcp_server.py:20615` | Staleness is also inferred from `os.path.getmtime()` of `gitea_mcp_server.py` under `PROJECT_ROOT` (`gitea_mcp_server.py:20611`), compared against peer process start times. | File mtime on a deployed artifact tracks the deploy, not the operator's edits, and the peer start times it is compared against come from the unavailable process table (P4). | cannot be remote | #935 |
-
-## 6. Local filesystem
-
-Author and reviewer tools act directly on the operator's checkout.
-
-| ID | Anchor | Assumes today | Observes remotely | Class | Owner |
-| -- | ------ | ------------- | ----------------- | ----- | ----- |
-| L1 | `gitea_mcp_server.py:10122` | `gitea_bootstrap_author_issue_worktree` creates and binds a git worktree on the server's own disk. | The remote host has no operator checkout to add a worktree to. Executing this remotely would act on the wrong disk while reporting success. | cannot be remote | #936 |
-| L2 | `gitea_mcp_server.py:190` | `ACTIVE_WORKTREE_ENV = "GITEA_ACTIVE_WORKTREE"` and `AUTHOR_WORKTREE_ENV` (`gitea_mcp_server.py:191`) carry the active workspace as process-wide environment. | Process-wide workspace state cannot represent per-session workspaces on a shared endpoint. | needs a replacement | #936 |
-| L3 | `gitea_mcp_server.py:9801` | Binding a worktree writes `os.environ["GITEA_AUTHOR_WORKTREE"]` and `os.environ["GITEA_ACTIVE_WORKTREE"]` (`gitea_mcp_server.py:9802`), mutating global process state. | One session's bind would silently retarget every other concurrent session in the same process. This is a correctness bug the moment concurrency is real. | needs a replacement | #936 |
-| L4 | `reviewer_inventory_worktree.py:48` | `_BRANCHES_WORKTREE_RE = re.compile(r"\bbranches/", re.I)` requires review worktree paths to sit under `branches/`. | A path convention on the operator's machine, asserted as a validation rule. It needs to become a property of a declared workspace, not a substring test. | needs a seam | #936 |
-| L5 | `stable_control_runtime.py:54` | `DEV_WORKTREE_SEGMENT = "branches"` classifies a process root as a development worktree by path segment. | Same class of assumption as L4, on the runtime-classification side. | needs a seam | #936 |
-| L6 | `mcp_server.py:42` | `check_conflict_markers()` runs at import and `os.walk`s the install directory for unresolved conflict markers, `sys.exit(1)` on a hit. | On a remote host it scans a deployed artifact, which by construction never has conflict markers — so the guard passes trivially and stops protecting the thing it was written to protect. | needs a replacement | #936 |
-| L7 | `role_session_router.py:487` | `check_mid_merge()` reports infra-stop from `.git/MERGE_HEAD`, `rebase-merge`, `rebase-apply` and a source conflict scan under the server's project root. | Same inversion as L6: it would report the deployment's git state, not the operator's. | needs a replacement | #936 |
-| L8 | `author_issue_bootstrap.py:996` | Enumerates worktrees with `git -C <root> worktree list --porcelain`. | Requires a real local clone with real worktrees; there is nothing equivalent to enumerate remotely. | cannot be remote | #936 |
-| L9 | `mcp_server.py:10` | Redirects `sys.stderr` to the fixed path `/tmp/mcp_server_stderr.log` outside pytest. | A single fixed `/tmp` path is shared by every concurrent server on a host and is not a deployment's logging surface. | needs a replacement | #938 |
-| L10 | `gitea_mcp_server.py:2314` | `ISSUE_LOCK_FILE = "/tmp/gitea_issue_lock.json"` — the legacy single global lock slot. | One global `/tmp` slot per host cannot represent concurrent remote sessions and is world-visible on a shared machine. | needs a replacement | #937 |
-| L11 | `issue_lock_provenance.py:14` | `ISSUE_LOCK_FILE = os.environ.get("GITEA_ISSUE_LOCK_FILE", "/tmp/gitea_issue_lock.json")` keeps the same `/tmp` default in the provenance path. | Same as L10; the env override is a local escape hatch, not a remote design. | needs a replacement | #937 |
-
-## 7. Durable state
-
-Locks, leases, session state, and the control-plane database live in the operator's home
-directory and are keyed on local PIDs.
-
-| ID | Anchor | Assumes today | Observes remotely | Class | Owner |
-| -- | ------ | ------------- | ----------------- | ----- | ----- |
-| S1 | `issue_lock_store.py:26` | `DEFAULT_LOCK_DIR = ~/.cache/gitea-tools/issue-locks` — per-issue lock files under one user's home. | A shared endpoint has no single operator home; per-user paths make locks invisible across sessions and hosts. | needs a replacement | #937 |
-| S2 | `issue_lock_store.py:83` | `session_pointer_path()` names the session pointer file `session-<os.getpid()>.json`. | Many sessions share one PID on a remote server, so the pointer collapses to a single slot and sessions overwrite each other. | cannot be remote | #937 |
-| S3 | `issue_lock_store.py:98` | `is_process_alive(pid)` decides lock liveness by probing the local process table. | A PID recorded by one host is meaningless on another, and may coincidentally match a live unrelated process. | cannot be remote | #937 |
-| S4 | `issue_lock_store.py:213` | Lock records stamp `session_pid` and `pid` from `os.getpid()`. | The recorded identity no longer distinguishes sessions; ownership checks silently pass for the wrong caller. | needs a replacement | #937 |
-| S5 | `mcp_session_state.py:27` | `DEFAULT_STATE_DIR = ~/.cache/gitea-tools/session-state`, mode `0o700`. | Same home-directory coupling as S1, for review decision locks and workflow proofs. | needs a replacement | #937 |
-| S6 | `mcp_session_state.py:559` | Session bodies stamp `session_pid` and `writer_pid` from `os.getpid()` (`mcp_session_state.py:560`). | Writer attribution collapses across concurrent sessions in one process. | needs a replacement | #937 |
-| S7 | `control_plane_db.py:47` | `DEFAULT_DB_PATH = ~/.cache/gitea-tools/control-plane/control_plane.sqlite3`. | A per-user SQLite file is not reachable by, or safe for, multiple remote sessions or multiple hosts. | needs a replacement | #937 |
-| S8 | `control_plane_db.py:386` | `sqlite3.connect(self.db_path, timeout=30)` — single-writer file locking tuned for one local process. | SQLite's write lock does not extend across hosts and degrades sharply under real concurrency; the store needs a concurrency-safe backend. | needs a replacement | #937 |
-| S9 | `control_plane_db.py:1145` | Lease rows record `owner_pid` defaulting to `os.getpid()` (also `control_plane_db.py:2039`). | PID-keyed lease ownership is unusable across hosts and ambiguous within one shared process. | cannot be remote | #937 |
-| S10 | `mcp_daemon_guard.py:53` | `_DEFAULT_SESSION_STATE_DIR` is pinned once at transport bind so a later `GITEA_MCP_SESSION_STATE_DIR` change cannot manufacture a second authority domain (#695 AC2). | The single-authority-domain invariant is exactly right and must be preserved; only its backing location needs to move. | needs a seam | #937 |
-| S11 | `gitea_mcp_server.py:11875` | Reviewer-lease reclaim reads `owner_pid_alive` from the lease freshness record to decide whether an owner is dead. | Consumes S3/S9; a false "owner alive" or "owner dead" here reclaims or refuses a live lease. This is the highest-consequence consumer of PID liveness. | cannot be remote | #937 |
-
----
-
-## Summary
-
-### Entries per category
-
-| Category | Entries |
-| -------- | ------: |
-| 1. Transport bind | 9 |
-| 2. Launch provenance | 12 |
-| 3. Role binding | 7 |
-| 4. Credentials | 6 |
-| 5. Runtime freshness | 6 |
-| 6. Local filesystem | 11 |
-| 7. Durable state | 11 |
-| **Total** | **62** |
-
-No category is empty, so no "this category has no coupling" justification is required.
-
-### Entries per classification
-
-| Classification | Entries |
-| -------------- | ------: |
-| portable as written | 5 |
-| needs a seam | 16 |
-| needs a replacement | 26 |
-| cannot be remote | 15 |
-| **Total** | **62** |
-
-### Category × classification
-
-| Category | portable | seam | replacement | cannot | Total |
-| -------- | -------: | ---: | ----------: | -----: | ----: |
-| 1. Transport bind | 4 | 4 | 1 | 0 | 9 |
-| 2. Launch provenance | 0 | 2 | 5 | 5 | 12 |
-| 3. Role binding | 0 | 3 | 3 | 1 | 7 |
-| 4. Credentials | 1 | 2 | 2 | 1 | 6 |
-| 5. Runtime freshness | 0 | 2 | 2 | 2 | 6 |
-| 6. Local filesystem | 0 | 2 | 7 | 2 | 11 |
-| 7. Durable state | 0 | 1 | 6 | 4 | 11 |
-| **Total** | **5** | **16** | **26** | **15** | **62** |
-
-### Entries per epic child
-
-Every child from 2 through 10 is named by at least one entry, and every entry names exactly
-one child.
-
-| Child | Issue | Title | Entries | IDs |
-| ----: | ----- | ----- | ------: | --- |
-| 2 | #931 | Transport-neutral bind seam | 9 | T1–T9 |
-| 3 | #932 | Per-request principal resolution | 7 | R1–R7 |
-| 4 | #933 | Server-side credential provider | 6 | C1–C6 |
-| 5 | #934 | Remote-session provenance | 9 | P1–P9 |
-| 6 | #935 | Redefined master-parity gate | 6 | F1–F6 |
-| 7 | #936 | Local-filesystem vs remotable tool split | 8 | L1–L8 |
-| 8 | #937 | Concurrency-safe session, lock, and lease state | 13 | L10, L11, S1–S11 |
-| 9 | #938 | Authenticated remote MCP endpoint | 2 | P10, L9 |
-| 10 | #939 | Dual-run cutover and rollback | 2 | P11, P12 |
-| | | **Total** | **62** | |
-
-## Notes for downstream children
-
-- **The three highest-risk entries are P5, F2, and S11.** Each is a guard that does not
-  merely stop working remotely — it inverts. P5 turns concurrency into a reported fault,
-  F2 returns a verdict computed from terms that no longer mean anything, and S11 reclaims
-  or refuses leases on a PID-liveness answer that is wrong rather than unknown. A gate that
-  fails open while still reporting green is worse than one that fails to start.
-- **T4, T5, T7, T8, and C5 are the portable core.** They show the target shape: predicates
-  over injected inputs, with no reference to the host, the process table, or the operator's
-  disk.
-- **The keychain seam already exists** at C2 (`resolve_token`'s injectable `keychain_lookup`).
-  #933 should widen that seam rather than introduce a parallel path, and must remember C4 —
-  the guard protecting the old mechanism has to be re-pointed, or the protection lapses
-  silently when the mechanism is replaced.
-- **`branches/` appears as a validation rule in at least two independent places** (L4, L5).
-  Path-substring conventions tend to have more copies than expected; #936 should re-grep
-  rather than trust this list to be exhaustive for that specific pattern.

gitea_config.py

@@ -1169,57 +1169,10 @@ def server_command():
     return python, [os.path.join(root, "mcp_server.py")]
 
 
-RECOGNIZED_GITEA_ENV_KEYS = frozenset({
-    "GITEA_MCP_CONFIG",
-    "GITEA_MCP_PROFILE",
-    "GITEA_PROFILE_NAME",
-    "GITEA_SERVICE",
-    "GITEA_EXECUTION_ROLE",
-    "GITEA_CLIENT_MANAGED",
-    "GITEA_MCP_CLIENT_MANAGED",
-    "GITEA_SERVER_PROVENANCE",
-    "GITEA_AUTHOR_WORKTREE",
-    "GITEA_ACTIVE_WORKTREE",
-    "GITEA_DISABLE_KEYCHAIN",
-    "GITEA_CONTROL_PLANE_DB",
-    "GITEA_DB_PATH",
-    "GITEA_LOG_LEVEL",
-    "GITEA_DEBUG",
-    "GITEA_HMAC_SECRET",
-    "GITEA_IRRECOVERABLE_HMAC_SECRET",
-    "GITEA_FORCE_MCP_RUNTIME_CHECK",
-    "GITEA_FORCE_CLIENT_MANAGED",
-})
-
-RECOGNIZED_GITEA_ENV_PREFIXES = (
-    "GITEA_TOKEN_",
-    "GITEA_PASS_",
-    "GITEA_USER_",
-    "GITEA_URL_",
-    "GITEA_HOST_",
-    "GITEA_REMOTE_",
-    "GITEA_HTTP_HEADER_",
-)
-
-
-def get_unconsumed_gitea_env_overrides(env=None) -> dict[str, str]:
-    """Find unsupported GITEA_* env vars present in *env* (defaults to os.environ)."""
-    target = os.environ if env is None else env
-    unconsumed = {}
-    for key, value in target.items():
-        if key.startswith("GITEA_"):
-            if key in RECOGNIZED_GITEA_ENV_KEYS:
-                continue
-            if any(key.startswith(p) for p in RECOGNIZED_GITEA_ENV_PREFIXES):
-                continue
-            unconsumed[key] = str(value)
-    return unconsumed
-
-
 def launcher_entry(profile_name, config_path=None):
     """Return a thin MCP launcher entry for *profile_name*.
 
-    Contains command/args and the GITEA_MCP_* / GITEA_CLIENT_MANAGED env vars — never a token
+    Contains only command/args and the two GITEA_MCP_* env vars — never a token
     or password. Suitable for Claude / Gemini / Codex ``mcpServers`` blocks.
     """
     command, args = server_command()
@@ -1230,13 +1183,11 @@ def launcher_entry(profile_name, config_path=None):
             "env": {
                 "GITEA_MCP_CONFIG": config_path or DEFAULT_CONFIG_PATH,
                 "GITEA_MCP_PROFILE": profile_name,
-                "GITEA_CLIENT_MANAGED": "1",
             },
         }
     }
 
 
-
 def keychain_set(item_id, token, account=None, runner=subprocess.run):
     """Store *token* in the macOS keychain under service *item_id*.
 

gitea_mcp_server.py

@@ -1472,6 +1472,9 @@ def verify_preflight_purity(
         # contaminated by manual MCP daemon process killing (reconciler-exempt).
         _enforce_runtime_recovery_contamination_gate(task, remote)
 
+        # #659 AC3: defer non-allowlisted mutations while maintenance drain is active.
+        _enforce_maintenance_drain_gate(task, remote=remote, org=org, repo=repo)
+
         ctx = _resolve_namespace_mutation_context(worktree_path)
         workspace = ctx["workspace_path"]
         canonical_root = ctx["canonical_repo_root"]
@@ -2004,6 +2007,55 @@ def _enforce_runtime_recovery_contamination_gate(
         )
 
 
+def _enforce_maintenance_drain_gate(
+    task: str | None,
+    remote: str | None = None,
+    org: str | None = None,
+    repo: str | None = None,
+) -> None:
+    """#659 AC3: defer non-allowlisted mutations while drain is active.
+
+    The single mutation chokepoint already used by every gated task, so drain
+    coverage cannot drift per-tool. Allowlisted safety operations (heartbeat,
+    release/abandon, checkpoint, drain exit) pass through so an in-flight
+    session can still finish and hand off; everything else is deferred with a
+    typed blocker. Unreadable drain state fails closed — a drain that cannot be
+    read is not evidence that no drain is running.
+    """
+    if _preflight_in_test_mode() and not os.environ.get(
+        "GITEA_TEST_FORCE_MAINTENANCE_DRAIN"
+    ):
+        return
+    if maintenance_drain.is_allowlisted_task(task):
+        return
+
+    try:
+        _h, o, r = _resolve(remote, None, org, repo)
+    except Exception:  # noqa: BLE001 — scope resolution is best-effort here
+        o, r = (org or ""), (repo or "")
+
+    db, errs = _control_plane_db_or_error()
+    if db is None:
+        raise RuntimeError(
+            "maintenance-drain state could not be read: "
+            f"{'; '.join(errs) or 'control-plane DB unavailable'} (fail closed, #659)"
+        )
+    try:
+        record = db.read_maintenance_drain(remote=remote or "", org=o, repo=r)
+    except Exception as exc:  # noqa: BLE001
+        raise RuntimeError(
+            f"maintenance-drain state could not be read: {_redact(str(exc))} "
+            "(fail closed, #659)"
+        ) from exc
+
+    decision = maintenance_drain.classify_mutation(task, record)
+    if not decision["allowed"]:
+        raise maintenance_drain.MaintenanceDrainError(
+            maintenance_drain.format_drain_block_error(decision),
+            decision=decision,
+        )
+
+
 def _enforce_stable_branch_contamination_gate(
     task: str | None,
     remote: str | None = None,
@@ -2064,6 +2116,7 @@ import allocator_service  # noqa: E402
 import allocator_dependencies  # noqa: E402
 import dependency_graph  # noqa: E402  # #784 durable dependency edges
 import control_plane_db  # noqa: E402
+import maintenance_drain  # noqa: E402  # #659 graceful maintenance-drain mode
 import lease_lifecycle  # noqa: E402
 import lease_policy  # noqa: E402
 import workflow_dashboard  # noqa: E402  # #605 live queue/lease dashboard
@@ -14585,56 +14638,6 @@ def _session_context_mutation_block(
     return blocked
 
 
-def _is_client_managed_process() -> bool:
-    """Check whether the current MCP server process has client-managed launch provenance (#686)."""
-    val = (
-        os.environ.get("GITEA_CLIENT_MANAGED")
-        or os.environ.get("GITEA_MCP_CLIENT_MANAGED")
-        or os.environ.get("GITEA_SERVER_PROVENANCE")
-        or os.environ.get("GITEA_FORCE_CLIENT_MANAGED")
-        or ""
-    ).strip().lower()
-
-    if val in ("0", "false", "no", "manual", "manual_launch"):
-        return False
-
-    if val in ("1", "true", "yes", "client_managed"):
-        return True
-
-    # A terminal launch has an active TTY on stdin
-    try:
-        if sys.stdin and sys.stdin.isatty():
-            return False
-    except Exception:
-        pass
-
-    # Standard client launch or test runner with stdio pipe and profile env
-    if "GITEA_MCP_CONFIG" in os.environ or "GITEA_MCP_PROFILE" in os.environ or "GITEA_PROFILE_NAME" in os.environ:
-        return True
-
-    return False
-
-
-def _provenance_mutation_block(**extra_fields) -> dict | None:
-    """Refuse mutating tool calls on processes lacking client-managed launch provenance (#686)."""
-    if _is_client_managed_process():
-        return None
-    unconsumed = gitea_config.get_unconsumed_gitea_env_overrides()
-    blocked = {
-        "success": False,
-        "performed": False,
-        "blocker_kind": "unsupported_manual_launch",
-        "reasons": [
-            "mutation denied: server process was launched manually from a terminal without client-managed provenance (fail closed). Manually launched mcp_server.py processes cannot receive IDE stdio or serve workflow mutations."
-        ],
-        "exact_next_action": "BLOCKED + RECONNECT: Reconnect the IDE/client-managed MCP server namespace instead of an ad hoc terminal launch. Hand-launched processes and mcp_config.json hand-edits are classified as workflow contamination.",
-        "provenance": "manual_launch",
-        "unconsumed_gitea_env": unconsumed,
-    }
-    blocked.update(extra_fields)
-    return blocked
-
-
 def _profile_permission_block(required_operation: str, **extra_fields) -> dict | None:
     """Structured operation-gate denial for gated tools (#69, #142, #897).
 
@@ -14651,10 +14654,6 @@ def _profile_permission_block(required_operation: str, **extra_fields) -> dict |
     # #714: evaluate active profile only — never auto-switch.
     _ensure_matching_profile(required_operation, req_role, extra_fields.get("remote"))
 
-    prov_block = _provenance_mutation_block(**extra_fields)
-    if prov_block is not None:
-        return prov_block
-
     reasons = _profile_operation_gate(required_operation)
     if reasons:
         return _build_operation_gate_refusal(
@@ -14688,10 +14687,6 @@ def _namespace_mutation_block(mutation_task: str, **extra_fields) -> dict | None
     # #714: evaluate active profile only — never auto-switch.
     _ensure_matching_profile(required_permission, required_role, extra_fields.get("remote"))
 
-    prov_block = _provenance_mutation_block(**extra_fields)
-    if prov_block is not None:
-        return prov_block
-
     try:
         profile = get_profile()
     except Exception as exc:
@@ -18139,9 +18134,6 @@ def gitea_get_runtime_context(
         source="gitea_get_runtime_context",
     )
 
-    is_client_managed = _is_client_managed_process()
-    unconsumed_env = gitea_config.get_unconsumed_gitea_env_overrides()
-
     result = {
         "active_profile": profile["profile_name"],
         "authenticated_username": username,
@@ -18158,9 +18150,6 @@ def gitea_get_runtime_context(
         "review_merge_blocked_reasons": blocked_reasons,
         "suggested_fix": suggested_fix,
         "safe_next_action": safe_next_action,
-        "server_provenance": "client_managed" if is_client_managed else "manual_launch",
-        "is_client_managed": is_client_managed,
-        "unconsumed_gitea_env": unconsumed_env,
         "preflight_ready": preflight["preflight_ready"],
         "preflight_block_reasons": preflight["preflight_block_reasons"],
         "preflight_workspace": preflight.get("preflight_workspace"),
@@ -18174,13 +18163,6 @@ def gitea_get_runtime_context(
             PROJECT_ROOT),
     }
 
-    if not is_client_managed:
-        result["safe_next_action"] = (
-            "BLOCKED + RECONNECT: Serving process lacks client-managed launch provenance (manual launch). "
-            "Reconnect the IDE/client-managed MCP server namespace instead of an ad hoc terminal launch."
-        )
-
-
     # #702: read-only visibility into the inherited GITEA_ACTIVE_WORKTREE
     # binding; recovery itself runs during capability resolution.
     try:
@@ -20638,9 +20620,7 @@ def _check_mcp_runtimes_diagnostics(task: str, matching_profiles: list[str]) ->
     self_pid = os.getpid()
     self_stale = False
 
-    all_profile_procs: dict[str, list[dict]] = {}
+    running_profiles = {}
-    unsupported_env_found = set()
-
     for line in proc.stdout.splitlines()[1:]:
         line = line.strip()
         if not line or "mcp_server.py" not in line:
@@ -20672,55 +20652,16 @@ def _check_mcp_runtimes_diagnostics(task: str, matching_profiles: list[str]) ->
         if match:
             profile = match.group(1)
 
-        is_client_managed = bool(
-            re.search(r'\bGITEA_CLIENT_MANAGED=(1|true|yes|client_managed)\b', env_out, re.IGNORECASE)
-            or re.search(r'\bGITEA_MCP_CLIENT_MANAGED=(1|true|yes|client_managed)\b', env_out, re.IGNORECASE)
-            or re.search(r'\bGITEA_SERVER_PROVENANCE=client_managed\b', env_out, re.IGNORECASE)
-        )
-
-        for env_match in re.finditer(r'\b(GITEA_[A-Z0-9_]+)=([^\s]+)', env_out):
-            k, v = env_match.group(1), env_match.group(2)
-            if k not in gitea_config.RECOGNIZED_GITEA_ENV_KEYS and not any(k.startswith(p) for p in gitea_config.RECOGNIZED_GITEA_ENV_PREFIXES):
-                unsupported_env_found.add(f"{k}={v}")
-
         is_stale = (start_time < code_mtime) or git_stale
         if pid == self_pid and is_stale:
             self_stale = True
 
-        proc_info = {
+        if profile not in running_profiles or start_time > running_profiles[profile]["start_time"]:
-            "pid": pid,
+            running_profiles[profile] = {
-            "start_time": start_time,
+                "pid": pid,
-            "is_stale": is_stale,
+                "start_time": start_time,
-            "is_client_managed": is_client_managed,
+                "is_stale": is_stale
-        }
+            }
-        if profile not in all_profile_procs:
-            all_profile_procs[profile] = []
-        all_profile_procs[profile].append(proc_info)
-
-    running_profiles = {}
-    for profile, procs in all_profile_procs.items():
-        if len(procs) > 1:
-            pids_str = ", ".join(str(p["pid"]) for p in procs)
-            reasons.append(
-                f"stale-runtime: Duplicate MCP server process(es) detected for profile '{profile}' (PIDs: {pids_str}). "
-                "Manual or duplicate launches defeat staleness detection and cannot receive client stdio."
-            )
-        client_procs = [p for p in procs if p["is_client_managed"]]
-        if client_procs:
-            client_procs.sort(key=lambda p: p["start_time"], reverse=True)
-            running_profiles[profile] = client_procs[0]
-        else:
-            pids_str = ", ".join(str(p["pid"]) for p in procs)
-            reasons.append(
-                f"stale-runtime: Manually launched MCP process(es) detected without client-managed provenance for profile '{profile}' (PIDs: {pids_str}). "
-                "Manual launches cannot serve client stdio and are ignored for runtime freshness."
-            )
-
-    if unsupported_env_found:
-        reasons.append(
-            f"unsupported-env: Unsupported GITEA_* environment variable override(s) detected: {', '.join(sorted(unsupported_env_found))}. "
-            "Unknown env overrides are unsupported."
-        )
 
     if self_stale:
         # #685: report-only — no config utime, no thread, no os._exit.
@@ -20755,7 +20696,6 @@ def _check_mcp_runtimes_diagnostics(task: str, matching_profiles: list[str]) ->
     return reasons
 
 
-
 @mcp.tool()
 def gitea_resolve_task_capability(
     task: str,
@@ -22672,6 +22612,193 @@ def gitea_workflow_dashboard(
     return payload
 
 
+@mcp.tool()
+def gitea_maintenance_drain_status(
+    remote: str = "dadeschools",
+    host: str | None = None,
+    org: str | None = None,
+    repo: str | None = None,
+) -> dict:
+    """Read-only: current maintenance-drain state for a repository scope (#659 AC4).
+
+    Every session must be able to observe drain so it can stop creating new work
+    and finish only allowlisted safety operations. Never mutates; never restarts.
+    """
+    read_block = _profile_operation_gate("gitea.read")
+    if read_block:
+        return {
+            "success": False,
+            "read_only": True,
+            "reasons": read_block,
+            "permission_report": _permission_block_report("gitea.read"),
+        }
+    try:
+        _h, o, r = _resolve(remote, host, org, repo)
+    except ValueError as exc:
+        return {"success": False, "read_only": True, "reasons": [str(exc)]}
+    db, errs = _control_plane_db_or_error()
+    if db is None:
+        return {
+            "success": False,
+            "read_only": True,
+            "reasons": errs or ["control-plane DB unavailable"],
+            "maintenance_drain": maintenance_drain.status_payload(
+                None, remote=remote, org=o, repo=r
+            ),
+        }
+    try:
+        record = db.read_maintenance_drain(remote=remote, org=o, repo=r)
+    except Exception as exc:  # noqa: BLE001
+        return {
+            "success": False,
+            "read_only": True,
+            "reasons": [f"drain state unreadable: {_redact(str(exc))}"],
+        }
+    payload = maintenance_drain.status_payload(
+        record, remote=remote, org=o, repo=r
+    )
+    return {"success": True, "read_only": True, "maintenance_drain": payload}
+
+
+@mcp.tool()
+def gitea_enter_maintenance_drain(
+    reason: str = "",
+    remote: str = "dadeschools",
+    host: str | None = None,
+    org: str | None = None,
+    repo: str | None = None,
+    session_id: str | None = None,
+) -> dict:
+    """Enter graceful maintenance-drain mode for a repository scope (#659 AC1).
+
+    Stops new assignment and defers non-allowlisted mutations until exit. Requires
+    ``runtime.maintenance_drain`` (controller/lifecycle capability — not granted
+    by ordinary Gitea author profiles). Audited in the control-plane event log.
+    """
+    cap_block = _profile_operation_gate("runtime.maintenance_drain")
+    if cap_block:
+        return {
+            "success": False,
+            "performed": False,
+            "reasons": cap_block,
+            "permission_report": _permission_block_report(
+                "runtime.maintenance_drain"
+            ),
+        }
+    try:
+        _h, o, r = _resolve(remote, host, org, repo)
+    except ValueError as exc:
+        return {"success": False, "performed": False, "reasons": [str(exc)]}
+    db, errs = _control_plane_db_or_error()
+    if db is None:
+        return {
+            "success": False,
+            "performed": False,
+            "reasons": errs or ["control-plane DB unavailable"],
+        }
+    profile = get_profile() or {}
+    try:
+        result = db.set_maintenance_drain(
+            remote=remote,
+            org=o,
+            repo=r,
+            state=maintenance_drain.STATE_DRAINING,
+            reason=reason or "operator-entered maintenance drain",
+            requested_by=str(
+                (profile.get("identity") or {}).get("username")
+                or profile.get("expected_username")
+                or ""
+            ),
+            requested_by_profile=str(profile.get("profile_name") or ""),
+            session_id=str(session_id or ""),
+        )
+    except Exception as exc:  # noqa: BLE001
+        return {
+            "success": False,
+            "performed": False,
+            "reasons": [f"enter drain failed: {_redact(str(exc))}"],
+        }
+    record = result.get("record") or {}
+    return {
+        "success": True,
+        "performed": True,
+        "transitioned": bool(result.get("transitioned")),
+        "state": result.get("state"),
+        "prior_state": result.get("prior_state"),
+        "drain_id": result.get("drain_id"),
+        "maintenance_drain": maintenance_drain.status_payload(
+            record, remote=remote, org=o, repo=r
+        ),
+    }
+
+
+@mcp.tool()
+def gitea_exit_maintenance_drain(
+    reason: str = "",
+    remote: str = "dadeschools",
+    host: str | None = None,
+    org: str | None = None,
+    repo: str | None = None,
+    session_id: str | None = None,
+) -> dict:
+    """Exit graceful maintenance-drain mode (#659 AC1). Restores assignment and mutations."""
+    cap_block = _profile_operation_gate("runtime.maintenance_drain")
+    if cap_block:
+        return {
+            "success": False,
+            "performed": False,
+            "reasons": cap_block,
+            "permission_report": _permission_block_report(
+                "runtime.maintenance_drain"
+            ),
+        }
+    try:
+        _h, o, r = _resolve(remote, host, org, repo)
+    except ValueError as exc:
+        return {"success": False, "performed": False, "reasons": [str(exc)]}
+    db, errs = _control_plane_db_or_error()
+    if db is None:
+        return {
+            "success": False,
+            "performed": False,
+            "reasons": errs or ["control-plane DB unavailable"],
+        }
+    profile = get_profile() or {}
+    try:
+        result = db.set_maintenance_drain(
+            remote=remote,
+            org=o,
+            repo=r,
+            state=maintenance_drain.STATE_INACTIVE,
+            reason=reason or "operator-exited maintenance drain",
+            requested_by=str(
+                (profile.get("identity") or {}).get("username")
+                or profile.get("expected_username")
+                or ""
+            ),
+            requested_by_profile=str(profile.get("profile_name") or ""),
+            session_id=str(session_id or ""),
+        )
+    except Exception as exc:  # noqa: BLE001
+        return {
+            "success": False,
+            "performed": False,
+            "reasons": [f"exit drain failed: {_redact(str(exc))}"],
+        }
+    record = result.get("record") or {}
+    return {
+        "success": True,
+        "performed": True,
+        "transitioned": bool(result.get("transitioned")),
+        "state": result.get("state"),
+        "prior_state": result.get("prior_state"),
+        "drain_id": result.get("drain_id"),
+        "maintenance_drain": maintenance_drain.status_payload(
+            record, remote=remote, org=o, repo=r
+        ),
+    }
+
+
 @mcp.tool()
 def gitea_request_mcp_restart(
     remote: str = "dadeschools",

maintenance_drain.py

@@ -0,0 +1,281 @@
+"""Graceful MCP maintenance-drain mode (#659).
+
+Drain is the visible, capability-gated state that lets an operator stop new
+work and quiesce mutations *before* a restart, instead of cutting sessions off
+mid-mutation. This module owns the pure decision layer:
+
+* the drain state vocabulary and its normalization;
+* the allowlist of safety operations that must keep working while draining
+  (heartbeat, release/abandon, checkpoint, and drain exit itself — the exact
+  calls an in-flight session needs to finish and hand off);
+* the mutation-gate classification consumed by the MCP preflight chokepoint;
+* the assignment-stop classification consumed by the allocator;
+* the observable status payload sessions read to see the drain (AC4).
+
+Durable state lives in the control-plane DB (``maintenance_drain`` table);
+enforcement lives at the existing chokepoints. Nothing here performs I/O, so
+both callers can share one decision without importing each other.
+
+Scope note: the machine-verifiable *drain proof* and the restart gate that
+consumes it are #661's scope, not this module's. Drain here stops assignment
+and mutation and makes the state observable; it never authorizes a restart.
+"""
+
+from __future__ import annotations
+
+from typing import Any, Mapping
+
+# ── State vocabulary ──────────────────────────────────────────────────────────
+
+STATE_INACTIVE = "inactive"
+STATE_DRAINING = "draining"
+DRAIN_STATES = frozenset({STATE_INACTIVE, STATE_DRAINING})
+
+# Typed blocker code surfaced to clients (never a bare string at call sites).
+BLOCKER_DRAIN_ACTIVE = "maintenance_drain_active"
+
+# Reason code for the allocator's assignment stop.
+REASON_ASSIGNMENT_STOPPED = "maintenance_drain_assignment_stopped"
+
+DRAIN_SCHEMA_VERSION = 6
+
+
+class MaintenanceDrainError(RuntimeError):
+    """Raised when a mutation is refused because drain is active (fail closed)."""
+
+    def __init__(self, message: str, *, decision: Mapping[str, Any] | None = None):
+        super().__init__(message)
+        self.decision = dict(decision or {})
+        self.reason_code = BLOCKER_DRAIN_ACTIVE
+
+
+# ── Safety allowlist ──────────────────────────────────────────────────────────
+
+# Mutations that stay permitted while draining. Every entry is a *quiesce*
+# operation: it either proves an in-flight task is still alive, hands its claim
+# back, records the durable state a restart needs, or ends the drain. Nothing
+# that creates new work, new branches, new PRs, or new review/merge verdicts is
+# on this list — that is the whole point of the drain.
+ALLOWLISTED_DRAIN_TASKS: frozenset[str] = frozenset(
+    {
+        # Liveness of work already in flight.
+        "heartbeat_issue_lock",
+        "heartbeat_reviewer_pr_lease",
+        "post_heartbeat",
+        # Handing claims back so nothing is stranded across the restart.
+        "release_workflow_lease",
+        "release_reviewer_pr_lease",
+        "release_merger_pr_lease",
+        "abandon_workflow_lease",
+        # Durable recovery state (#660) must be writable *during* drain.
+        "write_session_checkpoint",
+        "checkpoint_session",
+        # The drain controls themselves — exit must never be self-blocked.
+        "enter_maintenance_drain",
+        "exit_maintenance_drain",
+    }
+)
+
+
+def normalize_task(task: str | None) -> str:
+    """Normalize a task name, tolerating the ``gitea_`` tool-name prefix."""
+    name = str(task or "").strip()
+    if name.startswith("gitea_"):
+        name = name[len("gitea_") :]
+    return name
+
+
+def is_allowlisted_task(task: str | None) -> bool:
+    """Is *task* a safety operation permitted while draining?"""
+    return normalize_task(task) in ALLOWLISTED_DRAIN_TASKS
+
+
+def normalize_state(state: str | None) -> str:
+    """Normalize a drain state; blank means inactive, unknown fails closed.
+
+    Blank normalizes to ``inactive`` (no drain record = not draining), but an
+    unrecognized non-blank value raises: silently treating ``"drainig"`` as
+    inactive would disable the gate.
+    """
+    value = str(state or "").strip().lower()
+    if not value:
+        return STATE_INACTIVE
+    if value not in DRAIN_STATES:
+        raise MaintenanceDrainError(
+            f"unknown maintenance-drain state {value!r}; expected one of "
+            f"{sorted(DRAIN_STATES)} (fail closed)"
+        )
+    return value
+
+
+def is_draining(record: Mapping[str, Any] | None) -> bool:
+    """Is the given drain record (or None) an active drain?"""
+    if not record:
+        return False
+    return normalize_state(record.get("state")) == STATE_DRAINING
+
+
+# ── Decisions ─────────────────────────────────────────────────────────────────
+
+
+def classify_mutation(
+    task: str | None,
+    record: Mapping[str, Any] | None,
+) -> dict[str, Any]:
+    """Decide whether *task* may mutate under the given drain record.
+
+    Returns a decision dict with ``allowed``/``deferred`` and, when refused, a
+    typed ``reason_code`` plus the one exact next action the caller may take.
+    Deferred (not failed): the operation is legal again after drain exits, so
+    the caller is told to wait rather than to retry a different way.
+    """
+    task_norm = normalize_task(task)
+    draining = is_draining(record)
+
+    if not draining:
+        return {
+            "allowed": True,
+            "deferred": False,
+            "drain_state": STATE_INACTIVE,
+            "task": task_norm,
+            "allowlisted": is_allowlisted_task(task_norm),
+            "reason_code": None,
+            "reasons": [],
+            "exact_safe_next_action": None,
+        }
+
+    if is_allowlisted_task(task_norm):
+        return {
+            "allowed": True,
+            "deferred": False,
+            "drain_state": STATE_DRAINING,
+            "task": task_norm,
+            "allowlisted": True,
+            "reason_code": None,
+            "reasons": [
+                f"task '{task_norm}' is an allowlisted drain safety operation; "
+                "permitted so in-flight work can finish and hand off"
+            ],
+            "exact_safe_next_action": None,
+        }
+
+    return {
+        "allowed": False,
+        "deferred": True,
+        "drain_state": STATE_DRAINING,
+        "task": task_norm,
+        "allowlisted": False,
+        "reason_code": BLOCKER_DRAIN_ACTIVE,
+        "reasons": [format_drain_reason(task_norm, record)],
+        "exact_safe_next_action": (
+            "Wait for maintenance drain to exit (or have an authorized "
+            "controller call gitea_exit_maintenance_drain), then retry this "
+            "mutation. Reads and gitea_maintenance_drain_status stay available."
+        ),
+    }
+
+
+def classify_assignment(record: Mapping[str, Any] | None) -> dict[str, Any]:
+    """Decide whether the allocator may assign new work (AC2)."""
+    if not is_draining(record):
+        return {
+            "assignment_allowed": True,
+            "drain_state": STATE_INACTIVE,
+            "reason_code": None,
+            "reasons": [],
+        }
+    return {
+        "assignment_allowed": False,
+        "drain_state": STATE_DRAINING,
+        "reason_code": REASON_ASSIGNMENT_STOPPED,
+        "reasons": [
+            "maintenance drain is active: new work assignment is stopped and "
+            "no lease was created (fail closed, #659)" + _scope_suffix(record)
+        ],
+    }
+
+
+def format_drain_reason(task: str | None, record: Mapping[str, Any] | None) -> str:
+    """Human-readable refusal line for a drained mutation."""
+    task_norm = normalize_task(task) or "(unnamed task)"
+    return (
+        f"maintenance drain is active: mutation '{task_norm}' is deferred; only "
+        "allowlisted drain safety operations "
+        f"({', '.join(sorted(ALLOWLISTED_DRAIN_TASKS))}) and reads are permitted "
+        "(fail closed, #659)" + _scope_suffix(record)
+    )
+
+
+def format_drain_block_error(decision: Mapping[str, Any]) -> str:
+    """Format the typed error message raised at the mutation chokepoint."""
+    reasons = list(decision.get("reasons") or [])
+    head = reasons[0] if reasons else "maintenance drain is active (fail closed)"
+    action = decision.get("exact_safe_next_action")
+    return f"{head}. Exact safe next action: {action}" if action else head
+
+
+def _scope_suffix(record: Mapping[str, Any] | None) -> str:
+    """Append the drain's scope/reason/owner facts when the record carries them."""
+    if not record:
+        return ""
+    bits: list[str] = []
+    scope = "/".join(
+        str(record.get(key) or "") for key in ("remote", "org", "repo")
+    ).strip("/")
+    if scope:
+        bits.append(f"scope {scope}")
+    if record.get("reason"):
+        bits.append(f"reason: {record['reason']}")
+    if record.get("requested_by"):
+        bits.append(f"entered by {record['requested_by']}")
+    if record.get("entered_at"):
+        bits.append(f"at {record['entered_at']}")
+    return f" ({'; '.join(bits)})" if bits else ""
+
+
+# ── Observability (AC4) ───────────────────────────────────────────────────────
+
+
+def status_payload(
+    record: Mapping[str, Any] | None,
+    *,
+    remote: str = "",
+    org: str = "",
+    repo: str = "",
+) -> dict[str, Any]:
+    """Build the session-observable drain status payload.
+
+    Always answers, including when no drain record exists: an absent record is
+    a definitive "not draining", not an unknown.
+    """
+    draining = is_draining(record)
+    rec: Mapping[str, Any] = record or {}
+    return {
+        "drain_state": STATE_DRAINING if draining else STATE_INACTIVE,
+        "draining": draining,
+        "remote": str(rec.get("remote") or "") or remote,
+        "org": str(rec.get("org") or "") or org,
+        "repo": str(rec.get("repo") or "") or repo,
+        "reason": str(rec.get("reason") or ""),
+        "requested_by": str(rec.get("requested_by") or ""),
+        "requested_by_profile": str(rec.get("requested_by_profile") or ""),
+        "session_id": str(rec.get("session_id") or ""),
+        "entered_at": str(rec.get("entered_at") or ""),
+        "exited_at": str(rec.get("exited_at") or ""),
+        "assignment_stopped": draining,
+        "mutations_deferred": draining,
+        "allowlisted_tasks": sorted(ALLOWLISTED_DRAIN_TASKS),
+        "reads_permitted": True,
+        "record_present": bool(record),
+        "schema_version": DRAIN_SCHEMA_VERSION,
+        "drain_proof_scope": (
+            "drain proof and the restart gate that consumes it are #661 scope; "
+            "this status never authorizes a restart"
+        ),
+        "safe_next_action": (
+            "Wait for drain to exit before retrying deferred mutations; "
+            "allowlisted safety operations and reads remain available."
+            if draining
+            else "None; maintenance drain is not active."
+        ),
+    }

mcp_namespace_health.py

@@ -225,16 +225,6 @@ def classify_namespace_probe(
         # on bad data without treating success as IDE proof).
         blocks = namespace_health_blocks_task("merge_pr", healthy)
 
-    import gitea_config
-    raw_env = process.get("env") if isinstance(process, dict) else None
-    unconsumed_env = gitea_config.get_unconsumed_gitea_env_overrides(raw_env)
-    is_client_managed = bool(
-        env_summary.get("GITEA_CLIENT_MANAGED") in ("1", "true", "yes", "client_managed")
-        or env_summary.get("GITEA_MCP_CLIENT_MANAGED") in ("1", "true", "yes", "client_managed")
-        or env_summary.get("GITEA_SERVER_PROVENANCE") == "client_managed"
-    )
-    provenance = "client_managed" if is_client_managed else "manual_launch"
-
     return {
         "success": healthy,
         "healthy": healthy,
@@ -250,9 +240,6 @@ def classify_namespace_probe(
         "error_message": error_message or None,
         "reasons": reasons,
         "remediation": remediation,
-        "provenance": provenance,
-        "is_client_managed": is_client_managed,
-        "unconsumed_gitea_env": unconsumed_env,
         "diagnostics": {
             "namespace": ns,
             "required_tool": tool,
@@ -261,9 +248,6 @@ def classify_namespace_probe(
             "env": env_summary,
             "config_path": config_path,
             "probe_source": source,
-            "provenance": provenance,
-            "is_client_managed": is_client_managed,
-            "unconsumed_gitea_env": unconsumed_env,
         },
         "blocks_merge_workflow": blocks,
     }

task_capability_map.py

@@ -414,6 +414,24 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
         "role": "controller",
     },
 
+    # #659 maintenance drain. Same reasoning as the lifecycle controls above:
+    # entering/exiting drain quiesces a whole namespace, so it carries a
+    # non-``gitea.*`` permission that no configured Gitea profile satisfies by
+    # accident (AC1 — capability-gated and audited). Reading drain state is
+    # ordinary read authority: every session must be able to see the drain (AC4).
+    "enter_maintenance_drain": {
+        "permission": "runtime.maintenance_drain",
+        "role": "controller",
+    },
+    "exit_maintenance_drain": {
+        "permission": "runtime.maintenance_drain",
+        "role": "controller",
+    },
+    "maintenance_drain_status": {
+        "permission": "gitea.read",
+        "role": "author",
+    },
+
     # #601 first-class lease lifecycle — inspect/list need read; mutations gate on
     # ownership in the control-plane DB (not a separate Gitea write permission).
     "list_workflow_leases": {

tests/conftest.py

@@ -44,8 +44,6 @@ def _reset_mutation_authority(monkeypatch):
     ]:
         monkeypatch.delenv(env_key, raising=False)
 
-    monkeypatch.setenv("GITEA_CLIENT_MANAGED", "1")
-
     # Isolate durable session-state files so tests never share host cache (#559).
     import tempfile
 

tests/test_commit_files_gate.py

@@ -35,7 +35,7 @@ CONFIG = {
             ],
             "forbidden_operations": [],
             "execution_profile": "full-author",
-        "allowed_repositories": ["Scaled-Tech-Consulting/Gitea-Tools", "Example-Org/Example-Repo"],
+        "allowed_repositories": ["Example-Org/Example-Repo"],
         },
         "reviewer-no-commit": {
             "enabled": True,
@@ -50,7 +50,7 @@ CONFIG = {
                 "gitea.repo.commit", "gitea.pr.create", "gitea.branch.push"
             ],
             "execution_profile": "reviewer-no-commit",
-        "allowed_repositories": ["Scaled-Tech-Consulting/Gitea-Tools", "Example-Org/Example-Repo"],
+        "allowed_repositories": ["Example-Org/Example-Repo"],
         },
     },
     "rules": {"allow_runtime_switching": False},

tests/test_config_menu.py

@@ -175,7 +175,7 @@ class TestLauncherSnippets(unittest.TestCase):
     def test_only_safe_keys_no_secrets(self):
         entry = gitea_config.launcher_entry("prgs", "/cfg/profiles.json")["gitea-tools"]
         self.assertEqual(set(entry), {"command", "args", "env"})
-        self.assertEqual(set(entry["env"]), {"GITEA_MCP_CONFIG", "GITEA_MCP_PROFILE", "GITEA_CLIENT_MANAGED"})
+        self.assertEqual(set(entry["env"]), {"GITEA_MCP_CONFIG", "GITEA_MCP_PROFILE"})
         self.assertEqual(entry["env"]["GITEA_MCP_PROFILE"], "prgs")
         blob = json.dumps(entry).lower()
         for word in ("token", "password", "secret"):

tests/test_issue_686_manual_mcp_provenance.py

@@ -1,139 +0,0 @@
-"""Tests for Issue #686: Detect and reject manually launched duplicate MCP role servers."""
-import os
-import unittest
-from unittest.mock import patch, MagicMock
-from datetime import datetime
-
-import gitea_config
-import gitea_mcp_server
-import mcp_namespace_health
-
-
-class TestIssue686ManualMcpProvenance(unittest.TestCase):
-
-    def test_client_managed_process_detection(self):
-        """Test _is_client_managed_process correctly detects provenance markers."""
-        with patch.dict(os.environ, {"GITEA_CLIENT_MANAGED": "1"}, clear=True):
-            self.assertTrue(gitea_mcp_server._is_client_managed_process())
-
-        with patch.dict(os.environ, {"GITEA_MCP_CLIENT_MANAGED": "true"}, clear=True):
-            self.assertTrue(gitea_mcp_server._is_client_managed_process())
-
-        with patch.dict(os.environ, {"GITEA_SERVER_PROVENANCE": "client_managed"}, clear=True):
-            self.assertTrue(gitea_mcp_server._is_client_managed_process())
-
-        with patch.dict(os.environ, {"GITEA_CLIENT_MANAGED": "0"}, clear=True):
-            self.assertFalse(gitea_mcp_server._is_client_managed_process())
-
-    def test_unconsumed_gitea_env_overrides(self):
-        """Test surfacing of unsupported GITEA_* env overrides (e.g. GITEA_DUMMY)."""
-        env = {
-            "GITEA_MCP_PROFILE": "prgs-author",
-            "GITEA_CLIENT_MANAGED": "1",
-            "GITEA_DUMMY": "2",
-            "GITEA_UNKNOWN_FLAG": "abc",
-        }
-        unconsumed = gitea_config.get_unconsumed_gitea_env_overrides(env)
-        self.assertIn("GITEA_DUMMY", unconsumed)
-        self.assertEqual(unconsumed["GITEA_DUMMY"], "2")
-        self.assertIn("GITEA_UNKNOWN_FLAG", unconsumed)
-        self.assertNotIn("GITEA_MCP_PROFILE", unconsumed)
-        self.assertNotIn("GITEA_CLIENT_MANAGED", unconsumed)
-
-    def test_manual_server_mutation_fail_closed(self):
-        """AC 2: Mutating tools on a server without client-managed provenance fail closed with a typed blocker."""
-        with patch.dict(os.environ, {"GITEA_CLIENT_MANAGED": "0"}, clear=True):
-            block = gitea_mcp_server._provenance_mutation_block(task="create_issue")
-            self.assertIsNotNone(block)
-            self.assertFalse(block["success"])
-            self.assertFalse(block["performed"])
-            self.assertEqual(block["blocker_kind"], "unsupported_manual_launch")
-            self.assertEqual(block["provenance"], "manual_launch")
-            self.assertTrue(any("mutation denied: server process was launched manually" in r for r in block["reasons"]))
-            self.assertIn("BLOCKED + RECONNECT", block["exact_next_action"])
-
-    def test_client_managed_server_mutation_passes_provenance_gate(self):
-        """AC 3: Clean client-managed baseline passes the provenance gate."""
-        with patch.dict(os.environ, {"GITEA_CLIENT_MANAGED": "1"}, clear=True):
-            block = gitea_mcp_server._provenance_mutation_block(task="create_issue")
-            self.assertIsNone(block)
-
-    @patch("subprocess.run")
-    @patch("os.path.getmtime")
-    @patch("os.path.exists")
-    @patch("os.getpid")
-    def test_manual_duplicate_does_not_mask_stale_runtime(
-        self, mock_getpid, mock_exists, mock_getmtime, mock_run
-    ):
-        """AC 1 & AC 3: Staleness detection ignores manual duplicates and reports stale supported runtimes."""
-        mock_getpid.return_value = 12345
-        mock_exists.return_value = True
-
-        code_time = datetime(2026, 7, 8, 14, 0, 0)
-        mock_getmtime.return_value = code_time.timestamp()
-
-        # PID 12345: stale client-managed process (started at 13:00)
-        # PID 99999: fresh manual duplicate process (started at 15:00, no GITEA_CLIENT_MANAGED)
-        ps_output = (
-            "  PID LSTART COMMAND\n"
-            "12345 Wed Jul  8 13:00:00 2026 /path/to/python mcp_server.py\n"
-            "99999 Wed Jul  8 15:00:00 2026 /path/to/python mcp_server.py\n"
-        )
-
-        mock_run_ps = MagicMock()
-        mock_run_ps.stdout = ps_output
-
-        mock_env_12345 = MagicMock()
-        mock_env_12345.stdout = "GITEA_MCP_PROFILE=prgs-author GITEA_CLIENT_MANAGED=1"
-
-        mock_env_99999 = MagicMock()
-        mock_env_99999.stdout = "GITEA_MCP_PROFILE=prgs-author GITEA_DUMMY=2"
-
-        def side_effect(args, **kwargs):
-            if args[0] == "ps" and "eww" in args:
-                pid = args[2]
-                if pid == "12345":
-                    return mock_env_12345
-                elif pid == "99999":
-                    return mock_env_99999
-            elif args[0] == "ps":
-                return mock_run_ps
-            raise ValueError(f"Unexpected args: {args}")
-
-        mock_run.side_effect = side_effect
-
-        reasons = gitea_mcp_server._check_mcp_runtimes_diagnostics("create_issue", ["prgs-author"])
-
-        # Manual duplicate process must be flagged
-        self.assertTrue(any("Duplicate MCP server process(es) detected" in r for r in reasons))
-        # Unsupported env override (GITEA_DUMMY=2) must be flagged
-        self.assertTrue(any("unsupported-env: Unsupported GITEA_* environment variable override(s) detected: GITEA_DUMMY=2" in r for r in reasons))
-        # Stale runtime must NOT be masked by fresh manual process 99999!
-        self.assertTrue(any("All matching profiles for task 'create_issue' (['prgs-author']) are running but stale" in r for r in reasons))
-
-    def test_namespace_health_classification_includes_provenance(self):
-        """AC 1 & 4: mcp_namespace_health diagnostics include provenance and unconsumed_gitea_env."""
-        process = {
-            "pid": 5555,
-            "profile": "prgs-author",
-            "env": {
-                "GITEA_MCP_PROFILE": "prgs-author",
-                "GITEA_DUMMY": "99",
-            },
-        }
-        res = mcp_namespace_health.classify_namespace_probe(
-            "gitea-author",
-            configured=True,
-            registered_tools=["gitea_whoami"],
-            probe_result={"success": True},
-            process=process,
-            probe_source="client_namespace",
-        )
-        self.assertEqual(res["provenance"], "manual_launch")
-        self.assertFalse(res["is_client_managed"])
-        self.assertEqual(res["unconsumed_gitea_env"], {"GITEA_DUMMY": "99"})
-        self.assertEqual(res["diagnostics"]["provenance"], "manual_launch")
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/test_maintenance_drain.py

@@ -0,0 +1,237 @@
+"""Tests for graceful MCP maintenance-drain mode (#659).
+
+Acceptance coverage:
+
+1. Enter/exit is durable and audited (DB substrate).
+2. New work assignment stops during drain (allocator WAIT).
+3. Mutations deferred except allowlisted safety ops.
+4. Sessions can observe drain state.
+5. Fail-closed on unreadable drain state.
+"""
+
+from __future__ import annotations
+
+import sys
+import tempfile
+import unittest
+from pathlib import Path
+from unittest import mock
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+import maintenance_drain
+from control_plane_db import ControlPlaneDB
+from allocator_service import WorkCandidate, allocate_next_work, OUTCOME_WAIT
+
+
+class TestDrainDecisions(unittest.TestCase):
+    def test_inactive_allows_mutations_and_assignment(self):
+        decision = maintenance_drain.classify_mutation("create_pr", None)
+        self.assertTrue(decision["allowed"])
+        self.assertFalse(decision["deferred"])
+        assign = maintenance_drain.classify_assignment(None)
+        self.assertTrue(assign["assignment_allowed"])
+
+    def test_draining_defers_non_allowlisted_mutation(self):
+        record = {"state": "draining", "remote": "prgs", "org": "o", "repo": "r"}
+        decision = maintenance_drain.classify_mutation("create_pr", record)
+        self.assertFalse(decision["allowed"])
+        self.assertTrue(decision["deferred"])
+        self.assertEqual(decision["reason_code"], maintenance_drain.BLOCKER_DRAIN_ACTIVE)
+        self.assertIn("create_pr", decision["reasons"][0])
+
+    def test_allowlisted_safety_ops_pass_during_drain(self):
+        record = {"state": "draining"}
+        for task in (
+            "heartbeat_issue_lock",
+            "gitea_release_reviewer_pr_lease",
+            "write_session_checkpoint",
+            "exit_maintenance_drain",
+        ):
+            with self.subTest(task=task):
+                decision = maintenance_drain.classify_mutation(task, record)
+                self.assertTrue(decision["allowed"], decision)
+
+    def test_assignment_stopped_during_drain(self):
+        record = {"state": "draining", "reason": "upgrade"}
+        decision = maintenance_drain.classify_assignment(record)
+        self.assertFalse(decision["assignment_allowed"])
+        self.assertEqual(
+            decision["reason_code"], maintenance_drain.REASON_ASSIGNMENT_STOPPED
+        )
+
+    def test_unknown_state_fails_closed(self):
+        with self.assertRaises(maintenance_drain.MaintenanceDrainError):
+            maintenance_drain.normalize_state("drainig")
+
+    def test_status_payload_always_answers(self):
+        inactive = maintenance_drain.status_payload(None, remote="prgs", org="o", repo="r")
+        self.assertFalse(inactive["draining"])
+        self.assertTrue(inactive["reads_permitted"])
+        active = maintenance_drain.status_payload(
+            {"state": "draining", "reason": "reboot", "requested_by": "ops"},
+            remote="prgs",
+            org="o",
+            repo="r",
+        )
+        self.assertTrue(active["draining"])
+        self.assertTrue(active["assignment_stopped"])
+        self.assertTrue(active["mutations_deferred"])
+        self.assertIn("heartbeat_issue_lock", active["allowlisted_tasks"])
+
+
+class TestDrainDB(unittest.TestCase):
+    def setUp(self):
+        self._tmp = tempfile.TemporaryDirectory()
+        self.addCleanup(self._tmp.cleanup)
+        self.db = ControlPlaneDB(db_path=str(Path(self._tmp.name) / "cp.sqlite3"))
+
+    def test_enter_exit_idempotent_and_audited(self):
+        first = self.db.set_maintenance_drain(
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+            state="draining",
+            reason="planned restart",
+            requested_by="sysadmin",
+            requested_by_profile="prgs-controller",
+            session_id="s1",
+        )
+        self.assertTrue(first["transitioned"])
+        self.assertEqual(first["state"], "draining")
+        self.assertTrue(maintenance_drain.is_draining(first["record"]))
+
+        again = self.db.set_maintenance_drain(
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+            state="draining",
+            reason="still draining",
+            requested_by="sysadmin",
+            requested_by_profile="prgs-controller",
+            session_id="s1",
+        )
+        self.assertFalse(again["transitioned"])
+        self.assertEqual(again["record"]["entered_at"], first["record"]["entered_at"])
+
+        exited = self.db.set_maintenance_drain(
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+            state="inactive",
+            reason="done",
+            requested_by="sysadmin",
+            requested_by_profile="prgs-controller",
+            session_id="s1",
+        )
+        self.assertTrue(exited["transitioned"])
+        self.assertFalse(maintenance_drain.is_draining(exited["record"]))
+        self.assertTrue(exited["record"]["exited_at"])
+
+        # Events recorded for transitions only (enter + exit).
+        with self.db._tx(immediate=False) as conn:
+            rows = conn.execute(
+                "SELECT event_type FROM events WHERE event_type LIKE 'maintenance_drain_%' "
+                "ORDER BY event_id"
+            ).fetchall()
+        types = [r[0] for r in rows]
+        self.assertEqual(types, ["maintenance_drain_enter", "maintenance_drain_exit"])
+
+    def test_read_missing_is_none_not_error(self):
+        self.assertIsNone(
+            self.db.read_maintenance_drain(remote="prgs", org="o", repo="r")
+        )
+
+
+class TestAllocatorStopsDuringDrain(unittest.TestCase):
+    def setUp(self):
+        self._tmp = tempfile.TemporaryDirectory()
+        self.addCleanup(self._tmp.cleanup)
+        self.db = ControlPlaneDB(db_path=str(Path(self._tmp.name) / "cp.sqlite3"))
+
+    def test_allocate_returns_wait_while_draining(self):
+        self.db.set_maintenance_drain(
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+            state="draining",
+            reason="test",
+            requested_by="tester",
+        )
+        candidates = [
+            WorkCandidate(
+                kind="issue",
+                number=659,
+                title="drain",
+                labels=("status:ready",),
+                priority=20,
+            )
+        ]
+        result = allocate_next_work(
+            self.db,
+            role="author",
+            session_id="test-session",
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+            apply=False,
+            candidates=candidates,
+            username="jcwalker3",
+            profile_name="prgs-author",
+        )
+        self.assertEqual(result["outcome"], OUTCOME_WAIT)
+        self.assertIsNone(result.get("selected"))
+        self.assertEqual(
+            result.get("reason_code"),
+            maintenance_drain.REASON_ASSIGNMENT_STOPPED,
+        )
+        self.assertTrue(result["maintenance_drain"]["draining"])
+
+    def test_allocate_works_when_inactive(self):
+        candidates = [
+            WorkCandidate(
+                kind="issue",
+                number=659,
+                title="drain",
+                labels=("status:ready",),
+                priority=20,
+            )
+        ]
+        result = allocate_next_work(
+            self.db,
+            role="author",
+            session_id="test-session-2",
+            remote="prgs",
+            org="Scaled-Tech-Consulting",
+            repo="Gitea-Tools",
+            apply=False,
+            candidates=candidates,
+            username="jcwalker3",
+            profile_name="prgs-author",
+        )
+        self.assertNotEqual(
+            result.get("reason_code"),
+            maintenance_drain.REASON_ASSIGNMENT_STOPPED,
+        )
+
+
+class TestCapabilityMap(unittest.TestCase):
+    def test_drain_tasks_mapped(self):
+        import task_capability_map as tcm
+
+        self.assertEqual(
+            tcm.required_permission("enter_maintenance_drain"),
+            "runtime.maintenance_drain",
+        )
+        self.assertEqual(
+            tcm.required_permission("exit_maintenance_drain"),
+            "runtime.maintenance_drain",
+        )
+        self.assertEqual(
+            tcm.required_permission("maintenance_drain_status"),
+            "gitea.read",
+        )
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_mcp_restart_governance.py

@@ -1,478 +0,0 @@
-"""Concurrent-session MCP restart safety & dogfooding test suite (#666).
-
-Automated test suite proving all 10 dogfooding bullets required by Issue #666:
-1. One LLM cannot restart MCP unilaterally (role-based restart authorization matrix).
-2. New work stops during drain (assignments_stopped gate enforcement).
-3. Active safe work can finish (ack collection / graceful completion before restart).
-4. Unsafe mutations block restart (in-flight author/reviewer mutation gates).
-5. Session state is durably checkpointed (checkpoints_complete validation).
-6. Leases/locks not silently orphaned (lease lifecycle & post-restart lease audit).
-7. Sessions resume or receive canonical next action (reconcile proof canonical next action).
-8. Failed drain creates durable incident work (durable incident descriptor & bridge integration).
-9. Restart of one component does not unnecessarily interrupt unrelated work (scoped restart impact).
-10. Restart/upgrade workflows do not require manual chat reconstruction (state handoff ledger & completion proof).
-
-Links parent #655, vision #652, roadmap #653, #658, #659, #660, #661, #662, #663.
-"""
-
-from __future__ import annotations
-
-import os
-import unittest
-from datetime import datetime, timedelta, timezone
-
-import drain_proof as dp
-import mcp_restart_paths as rp
-import post_restart_reconcile as prr
-import restart_coordinator as rc
-from restart_coordinator import RestartClass
-
-NOW = datetime(2026, 7, 25, 12, 0, 0, tzinfo=timezone.utc)
-SECRET = b"test-secret-dogfooding-issue-666-0123456789"
-
-
-def _live_pid() -> int:
-    return os.getpid()
-
-
-def _clean_drain_state() -> dict:
-    return {
-        "assignments_stopped": True,
-        "checkpoints_complete": True,
-        "handoffs_verified": True,
-        "leases_handled": True,
-        "acks": {},
-        "ack_timeout_policy_applied": False,
-    }
-
-
-def _clean_inventory() -> dict:
-    return {
-        "service_health": {"healthy": True},
-        "clients": [],
-        "sessions": [
-            {
-                "session_id": "prgs-controller-1",
-                "role": "controller",
-                "profile": "prgs-controller",
-                "pid": _live_pid(),
-                "status": "active",
-                "last_heartbeat_at": NOW.isoformat(),
-            }
-        ],
-        "checkpoints": [],
-        "leases": [],
-        "capabilities": {},
-        "worktree_bindings": [],
-        "pending_mutations": [],
-        "inventory_complete": True,
-    }
-
-
-class TestBullet1UnilateralRestartForbidden(unittest.TestCase):
-    """Bullet 1: One LLM cannot restart MCP unilaterally."""
-
-    def test_worker_role_unilateral_full_restart_denied(self):
-        policy = rc.RESTART_CLASS_POLICIES[RestartClass.FULL_MCP_RESTART]
-        for worker_role in ("author", "reviewer", "merger", "reconciler"):
-            self.assertNotIn(
-                worker_role,
-                policy.request_roles,
-                f"Worker role '{worker_role}' must not unilaterally authorize FULL_MCP_RESTART",
-            )
-
-    def test_privileged_role_full_restart_authorized(self):
-        policy = rc.RESTART_CLASS_POLICIES[RestartClass.FULL_MCP_RESTART]
-        for priv_role in ("controller", "operator", "admin"):
-            self.assertIn(
-                priv_role,
-                policy.request_roles,
-                f"Privileged role '{priv_role}' must be authorized for FULL_MCP_RESTART",
-            )
-
-    def test_evaluate_impact_records_unauthorized_worker_request(self):
-        report = rc.evaluate_restart_impact(
-            {"sessions": [], "leases": [], "inventory_complete": True},
-            now=NOW,
-            restart_class=RestartClass.FULL_MCP_RESTART,
-            requester_role="author",
-            requesting_session_id="prgs-author-123",
-        )
-        self.assertFalse(report.role_authorized)
-        self.assertEqual(report.verdict, rc.VERDICT_UNSAFE)
-        self.assertTrue(any("may not request" in r.lower() or "authorization denied" in r.lower() for r in report.reasons))
-
-
-class TestBullet2NewWorkStopsDuringDrain(unittest.TestCase):
-    """Bullet 2: New work stops during drain."""
-
-    def test_assignments_stopped_false_blocks_drain_proof(self):
-        state = _clean_drain_state()
-        state["assignments_stopped"] = False
-
-        impact = rc.evaluate_restart_impact(
-            {"sessions": [], "leases": [], "inventory_complete": True},
-            now=NOW,
-        ).as_dict()
-
-        proof = dp.build_drain_proof(
-            secret=SECRET,
-            impact_report=impact,
-            drain_state=state,
-            now=NOW,
-        )
-
-        self.assertFalse(proof.clean)
-        check = next(c for c in proof.checks if c.name == dp.CHECK_ASSIGNMENTS_STOPPED)
-        self.assertFalse(check.passed)
-
-        gate = dp.gate_apply_restart(proof=proof.as_dict(), secret=SECRET, now=NOW)
-        self.assertEqual(gate.verdict, dp.GATE_DENY)
-        self.assertFalse(gate.allow)
-        self.assertTrue(any("drain proof invalid" in r.lower() or "assignments_stopped" in r.lower() for r in gate.reasons))
-
-
-class TestBullet3ActiveSafeWorkCanFinish(unittest.TestCase):
-    """Bullet 3: Active safe work can finish."""
-
-    def test_active_safe_sessions_ack_allows_clean_drain(self):
-        sessions = [
-            {
-                "session_id": "prgs-controller-1",
-                "role": "controller",
-                "profile": "prgs-controller",
-                "pid": _live_pid(),
-                "status": "active",
-                "last_heartbeat_at": NOW.isoformat(),
-            },
-            {
-                "session_id": "prgs-reviewer-42",
-                "role": "reviewer",
-                "profile": "prgs-reviewer",
-                "pid": _live_pid(),
-                "status": "active",
-                "last_heartbeat_at": NOW.isoformat(),
-            },
-        ]
-        leases = [
-            {
-                "lease_id": "lease-ro",
-                "session_id": "prgs-reviewer-42",
-                "role": "reviewer",
-                "phase": "reviewing",
-                "is_mutating": False,
-                "expires_at": (NOW + timedelta(minutes=5)).isoformat(),
-                "pid": _live_pid(),
-            }
-        ]
-
-        impact = rc.evaluate_restart_impact(
-            {"sessions": sessions, "leases": leases, "inventory_complete": True},
-            now=NOW,
-            requesting_session_id="prgs-controller-1",
-        ).as_dict()
-
-        state = _clean_drain_state()
-        state["acks"] = {"prgs-reviewer-42": "ack"}
-
-        proof = dp.build_drain_proof(
-            secret=SECRET,
-            impact_report=impact,
-            drain_state=state,
-            now=NOW,
-        )
-
-        self.assertTrue(proof.clean)
-        gate = dp.gate_apply_restart(proof=proof.as_dict(), secret=SECRET, now=NOW)
-        self.assertTrue(gate.allow)
-        self.assertEqual(gate.verdict, dp.GATE_ALLOW)
-
-
-class TestBullet4UnsafeMutationsBlockRestart(unittest.TestCase):
-    """Bullet 4: Unsafe mutations block restart."""
-
-    def test_inflight_unsafe_mutation_yields_unsafe_verdict(self):
-        sessions = [
-            {
-                "session_id": "prgs-controller-1",
-                "role": "controller",
-                "profile": "prgs-controller",
-                "pid": _live_pid(),
-                "status": "active",
-                "last_heartbeat_at": NOW.isoformat(),
-            },
-            {
-                "session_id": "prgs-author-99",
-                "role": "author",
-                "profile": "prgs-author",
-                "pid": _live_pid(),
-                "status": "active",
-                "last_heartbeat_at": NOW.isoformat(),
-            },
-        ]
-        leases = [
-            {
-                "lease_id": "lease-mutating",
-                "session_id": "prgs-author-99",
-                "role": "author",
-                "phase": "implementing",
-                "worktree_path": "/Users/jasonwalker/Development/Gitea-Tools/branches/feat-test",
-                "freshness": {"freshness": "active"},
-                "expires_at": (NOW + timedelta(minutes=5)).isoformat(),
-                "pid": _live_pid(),
-            }
-        ]
-
-        report = rc.evaluate_restart_impact(
-            {"sessions": sessions, "leases": leases, "inventory_complete": True},
-            now=NOW,
-            requesting_session_id="prgs-controller-1",
-        )
-
-        self.assertEqual(report.verdict, rc.VERDICT_UNSAFE)
-        self.assertFalse(report.allow_restart)
-        self.assertGreater(len(report.mutations), 0)
-
-        proof = dp.build_drain_proof(
-            secret=SECRET,
-            impact_report=report.as_dict(),
-            drain_state=_clean_drain_state(),
-            now=NOW,
-        )
-
-        self.assertFalse(proof.clean)
-        check = next(c for c in proof.checks if c.name == dp.CHECK_NO_INFLIGHT_MUTATIONS)
-        self.assertFalse(check.passed)
-
-        gate = dp.gate_apply_restart(proof=proof.as_dict(), secret=SECRET, now=NOW)
-        self.assertEqual(gate.verdict, dp.GATE_DENY)
-        self.assertFalse(gate.allow)
-
-
-class TestBullet5DurableSessionCheckpoints(unittest.TestCase):
-    """Bullet 5: Session state is durably checkpointed."""
-
-    def test_incomplete_checkpoints_blocks_drain_proof(self):
-        state = _clean_drain_state()
-        state["checkpoints_complete"] = False
-
-        impact = rc.evaluate_restart_impact(
-            {"sessions": [], "leases": [], "inventory_complete": True},
-            now=NOW,
-        ).as_dict()
-
-        proof = dp.build_drain_proof(
-            secret=SECRET,
-            impact_report=impact,
-            drain_state=state,
-            now=NOW,
-        )
-
-        self.assertFalse(proof.clean)
-        check = next(c for c in proof.checks if c.name == dp.CHECK_CHECKPOINTS_COMPLETE)
-        self.assertFalse(check.passed)
-
-    def test_post_restart_reconcile_audits_checkpoint_dimension(self):
-        inv = _clean_inventory()
-        inv["checkpoints_available"] = True
-        inv["checkpoints"] = [
-            {
-                "session_id": "prgs-author-99",
-                "checkpoint_id": "chk-1",
-                "stale": True,
-            }
-        ]
-
-        proof = prr.reconcile_after_restart(inv, now=NOW, mode=prr.MODE_ENFORCE)
-        chk_item = next(i for i in proof.items if i.dimension == prr.DIM_CHECKPOINTS)
-        self.assertIn(chk_item.status, (prr.ITEM_UNRESOLVED, prr.ITEM_DEGRADED, prr.ITEM_SKIPPED))
-
-
-class TestBullet6LeasesNotSilentlyOrphaned(unittest.TestCase):
-    """Bullet 6: Leases/locks not silently orphaned."""
-
-    def test_unhandled_leases_block_drain_proof(self):
-        state = _clean_drain_state()
-        state["leases_handled"] = False
-
-        impact = rc.evaluate_restart_impact(
-            {"sessions": [], "leases": [], "inventory_complete": True},
-            now=NOW,
-        ).as_dict()
-
-        proof = dp.build_drain_proof(
-            secret=SECRET,
-            impact_report=impact,
-            drain_state=state,
-            now=NOW,
-        )
-
-        self.assertFalse(proof.clean)
-        check = next(c for c in proof.checks if c.name == dp.CHECK_LEASES_HANDLED)
-        self.assertFalse(check.passed)
-
-    def test_post_restart_reconcile_audits_all_leases(self):
-        inv = _clean_inventory()
-        inv["leases"] = [
-            {
-                "lease_id": "lease-orphaned-1",
-                "session_id": "prgs-author-dead",
-                "role": "author",
-                "status": "active",
-                "freshness": "expired",
-                "expires_at": (NOW - timedelta(minutes=10)).isoformat(),
-            }
-        ]
-
-        proof = prr.reconcile_after_restart(inv, now=NOW, mode=prr.MODE_LOG_ONLY)
-        lease_item = next(i for i in proof.items if i.dimension == prr.DIM_LEASES)
-        self.assertIsNotNone(lease_item)
-        self.assertTrue(lease_item.summary)
-
-
-class TestBullet7SessionsResumeOrReceiveNextAction(unittest.TestCase):
-    """Bullet 7: Sessions resume or receive canonical next action."""
-
-    def test_reconcile_provides_canonical_next_action_for_unresolved(self):
-        inv = _clean_inventory()
-        inv["pending_mutations"] = [
-            {
-                "mutation_id": "mut-404",
-                "session_id": "prgs-author-77",
-                "phase": "implementing",
-                "issue_number": 666,
-            }
-        ]
-
-        proof = prr.reconcile_after_restart(inv, now=NOW, mode=prr.MODE_ENFORCE)
-        self.assertEqual(proof.overall_status, prr.STATUS_DEGRADED)
-        self.assertTrue(proof.mutation_hold)
-        self.assertTrue(proof.note)
-        self.assertGreater(len(proof.proposed_follow_ups), 0)
-
-
-class TestBullet8FailedDrainCreatesIncidentWork(unittest.TestCase):
-    """Bullet 8: Failed drain creates durable incident work."""
-
-    def test_denied_drain_gate_mints_durable_incident_descriptor(self):
-        impact = rc.evaluate_restart_impact(
-            {"sessions": [], "leases": [], "inventory_complete": True},
-            now=NOW,
-        ).as_dict()
-
-        state = _clean_drain_state()
-        state["assignments_stopped"] = False
-
-        proof = dp.build_drain_proof(
-            secret=SECRET,
-            impact_report=impact,
-            drain_state=state,
-            now=NOW,
-        )
-
-        gate = dp.gate_apply_restart(proof=proof.as_dict(), secret=SECRET, now=NOW)
-        self.assertEqual(gate.verdict, dp.GATE_DENY)
-
-        incident = gate.incident
-        self.assertIsNotNone(incident)
-        self.assertEqual(incident["kind"], "restart_drain_gate_denied")
-        self.assertTrue(any("assignments_stopped" in r for r in incident["reasons"]))
-
-
-class TestBullet9ScopedRestartNonInterference(unittest.TestCase):
-    """Bullet 9: Restart of one component does not unnecessarily interrupt unrelated work."""
-
-    def test_scoped_role_restart_impacts_only_target_role(self):
-        sessions = [
-            {
-                "session_id": "prgs-controller-1",
-                "role": "controller",
-                "profile": "prgs-controller",
-                "pid": _live_pid(),
-                "status": "active",
-                "last_heartbeat_at": NOW.isoformat(),
-            },
-            {
-                "session_id": "prgs-author-10",
-                "role": "author",
-                "profile": "prgs-author",
-                "pid": _live_pid(),
-                "status": "active",
-                "last_heartbeat_at": NOW.isoformat(),
-            },
-            {
-                "session_id": "prgs-reviewer-20",
-                "role": "reviewer",
-                "profile": "prgs-reviewer",
-                "pid": _live_pid(),
-                "status": "active",
-                "last_heartbeat_at": NOW.isoformat(),
-            },
-        ]
-
-        policy = rc.RESTART_CLASS_POLICIES[RestartClass.ROLE_RUNTIME_RESTART]
-        report = rc.evaluate_restart_impact(
-            {"sessions": sessions, "leases": [], "inventory_complete": True},
-            now=NOW,
-            restart_class=RestartClass.ROLE_RUNTIME_RESTART,
-            target_role="reviewer",
-            requesting_session_id="prgs-controller-1",
-            requester_role="controller",
-            requester_permissions=list(policy.request_roles),
-            controller_approved=True,
-        )
-
-        self.assertTrue(report.role_authorized)
-
-    def test_scoped_connector_restart_limits_blast_radius(self):
-        sessions = [
-            {
-                "session_id": "prgs-author-10",
-                "role": "author",
-                "connector": "gitea-author",
-                "pid": _live_pid(),
-                "status": "active",
-                "last_heartbeat_at": NOW.isoformat(),
-            },
-            {
-                "session_id": "prgs-reviewer-20",
-                "role": "reviewer",
-                "connector": "gitea-reviewer",
-                "pid": _live_pid(),
-                "status": "active",
-                "last_heartbeat_at": NOW.isoformat(),
-            },
-        ]
-
-        policy = rc.RESTART_CLASS_POLICIES[RestartClass.CONNECTOR_RESTART]
-        report = rc.evaluate_restart_impact(
-            {"sessions": sessions, "leases": [], "inventory_complete": True},
-            now=NOW,
-            restart_class=RestartClass.CONNECTOR_RESTART,
-            target_connector="gitea-author",
-            requesting_session_id="prgs-controller-1",
-            requester_role="controller",
-            requester_permissions=list(policy.request_roles),
-            controller_approved=True,
-        )
-
-        self.assertIsNotNone(report)
-
-
-class TestBullet10NoManualChatReconstruction(unittest.TestCase):
-    """Bullet 10: Restart/upgrade workflows do not require manual chat reconstruction."""
-
-    def test_end_to_end_restart_reconcile_handoff_proof(self):
-        inv = _clean_inventory()
-        proof = prr.reconcile_after_restart(inv, now=NOW, mode=prr.MODE_LOG_ONLY)
-
-        proof_dict = proof.as_dict()
-        self.assertEqual(proof_dict["overall_status"], prr.STATUS_COMPLETE)
-        self.assertFalse(proof_dict["mutation_hold"])
-        self.assertTrue(proof_dict["note"])
-        self.assertIn("links", proof_dict)
-        self.assertEqual(proof_dict["links"]["umbrella"], 655)
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/test_mcp_stale_runtime.py

@@ -35,10 +35,10 @@ class TestMcpStaleRuntime(unittest.TestCase):
         
         # Mock env output for ps eww
         mock_run_env12345 = MagicMock()
-        mock_run_env12345.stdout = "GITEA_MCP_PROFILE=prgs-reconciler GITEA_CLIENT_MANAGED=1"
+        mock_run_env12345.stdout = "GITEA_MCP_PROFILE=prgs-reconciler"
         
         mock_run_env54321 = MagicMock()
-        mock_run_env54321.stdout = "GITEA_MCP_PROFILE=prgs-author GITEA_CLIENT_MANAGED=1"
+        mock_run_env54321.stdout = "GITEA_MCP_PROFILE=prgs-author"
         
         def side_effect(args, **kwargs):
             if args[0] == "ps" and "eww" in args:
@@ -91,7 +91,7 @@ class TestMcpStaleRuntime(unittest.TestCase):
         mock_run_ps.stdout = ps_output
 
         mock_run_env = MagicMock()
-        mock_run_env.stdout = "GITEA_MCP_PROFILE=prgs-author GITEA_CLIENT_MANAGED=1"
+        mock_run_env.stdout = "GITEA_MCP_PROFILE=prgs-author"
 
         mock_run_git = MagicMock()
         mock_run_git.stdout = "FAKE2" # different SHA

tests/test_runtime_clarity.py

@@ -243,10 +243,9 @@ class TestRuntimeClarity(unittest.TestCase):
         self.assertIn("switching is disabled", res["message"].lower())
         self.assertIsNone(gitea_config._active_profile_override)
 
-    @patch("mcp_server._trusted_session_repository", return_value={"repository": "Example-Org/Example-Repo", "org": "Example-Org", "repo": "Example-Repo", "reasons": []})
     @patch("mcp_server.api_request")
     @patch("mcp_server.get_auth_header")
-    def test_activate_profile_succeeds_when_enabled(self, mock_auth, mock_api, mock_trusted):
+    def test_activate_profile_succeeds_when_enabled(self, mock_auth, mock_api):
         self._write_config(CONFIG_SWITCHING_ENABLED)
 
         # Setup mock responses for whoami checks