Compare commits

..
Author SHA1 Message Date
jcwalker3 4ff4d2acc9 Merge branch 'master' into feat/issue-642-sanctioned-restart-controls 2026-07-24 02:07:44 -05:00
jcwalker3 fc8fe329d2 Merge branch 'master' into feat/issue-642-sanctioned-restart-controls 2026-07-23 22:22:36 -05:00
sysadminandClaude Opus 4.8 e593444eea feat(webui): sanctioned restart and graceful reload controls (Closes #642)
Adds a gated `system.restart_namespace` action so operators and workers can
restart or gracefully reload MCP namespaces through an authorized, audited
path instead of manual host process killing (#630).

- webui/sanctioned_restart.py: restart/reload operation model, dry-run
  intent preview, confirmation-string enforcement, audit emission, and
  post-restart health verification. Fails closed on unknown auth, missing
  capability, or ambiguous target namespace.
- webui/console_authz.py: RBAC entries for the restart capability with
  secret redaction preserved.
- webui/gated_actions.py: registers the restart action in the gated action
  framework so it cannot be invoked without capability + confirmation.
- task_capability_map.py: capability mapping for the restart operation.
- docs/sanctioned-restart-controls.md: operator documentation for the
  sanctioned path and the explicit prohibition on pkill recovery.
- docs/webui-authz-audit.md: audit model updated for restart events.
- tests/test_webui_sanctioned_restart.py: authorized preview, unauthorized
  deny, confirmation enforcement, contamination classification, and audit
  emission coverage.

No unrestricted kill path is exposed; manual pkill remains classified as
contamination and continues to block clean claims.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
2026-07-23 23:19:21 -04:00
14 changed files with 1304 additions and 1217 deletions
-29
View File
@@ -599,35 +599,6 @@ class ControlPlaneDB:
(_ts(), session_id),
)
def list_sessions(
self,
*,
statuses: Sequence[str] | None = None,
limit: int = 500,
) -> list[dict[str, Any]]:
"""List session rows for restart / impact analysis (#658).
Read-only. Sessions are the process-level unit an MCP restart
disrupts, so the restart coordinator inventories them to compute blast
radius. Optional ``statuses`` filter (e.g. ``('active',)``) narrows to
live rows. Never returns secrets — only operational metadata.
"""
clauses: list[str] = []
params: list[Any] = []
if statuses:
placeholders = ", ".join("?" for _ in statuses)
clauses.append(f"status IN ({placeholders})")
params.extend(statuses)
where = ("WHERE " + " AND ".join(clauses)) if clauses else ""
sql = (
f"SELECT * FROM sessions {where} "
"ORDER BY last_heartbeat_at DESC LIMIT ?"
)
params.append(max(1, int(limit)))
with self._tx(immediate=False) as conn:
rows = conn.execute(sql, params).fetchall()
return [dict(r) for r in rows]
# ── work items ────────────────────────────────────────────────────────
def upsert_work_item(
-95
View File
@@ -1,95 +0,0 @@
# MCP restart coordinator and impact analysis (#658)
Before any sanctioned MCP restart, a central coordinator evaluates the live
control-plane state and produces an **impact preview** so operators and the web
console (#642 / #652) can see the blast radius *before* concurrent LLM work is
disrupted. Uncoordinated restarts destroy in-flight author/reviewer/merger work
and give operators no way to see what they are about to break.
This lands the coordinator + impact DTO + a dry-run MCP tool. It is the single
sanctioned entry point for restart evaluation post-#657 (which inventoried the
restart/reload/kill paths). The **mutative apply** path — actually performing a
restart — is a later child gated by a drain proof and is explicitly out of
scope here.
## Components
| Piece | Where | Responsibility |
|-------|-------|----------------|
| `restart_coordinator.evaluate_restart_impact` | `restart_coordinator.py` | Pure classification: inventory → impact report DTO. No I/O, no restart. |
| `RestartImpactReport` / `SessionImpact` / `LeaseImpact` | `restart_coordinator.py` | Console-facing DTO (`.as_dict()` is JSON-serializable). |
| `ControlPlaneDB.list_sessions` | `control_plane_db.py` | Read-only session inventory (the process-level unit a restart kills). |
| `gitea_request_mcp_restart` | `gitea_mcp_server.py` | MCP tool: gathers inventory from the #613 DB, calls the coordinator, returns the report. Dry-run only. |
## Dimensions evaluated
The coordinator classifies the inventory across the dimensions #658 requires:
- **Sessions** — every active MCP session; a restart terminates all of them.
Liveness = `status == active` **and** the owner pid is alive **and** the
heartbeat is fresh (default window 15 min). Dead/stale sessions do not count
toward blast radius.
- **Leases / locks** — control-plane leases joined with work items and their
freshness (`lease_lifecycle.classify_lease_freshness`). Only `active` (live
owner) leases are *disruptive*; expired / released / dead-process leases never
withhold a restart.
- **Issue / PR work** — the issues and PRs behind disruptive leases.
- **Mutations / critical sections** — a live lease carrying an author worktree
or a mutating phase (`implementing`, `publishing`, `merging`, …) is a
critical section a restart must not sever.
- **Terminal (merge) lock** — an active terminal lock always makes a restart
unsafe.
- **Prior recovery attempts** — narrower recovery already tried (e.g. sanctioned
client reconnects) is echoed so the operator sees the escalation history.
## Verdict
Exactly three verdicts, matching the acceptance criteria:
| Verdict | `allow_restart` | Meaning |
|---------|-----------------|---------|
| `safe` | `true` | No other live sessions, no live leases, no terminal lock. |
| `unsafe` | `false` | Live work would be disrupted and no operator override is present — **or** the inventory could not be completed (fail closed). |
| `override` | `true` | Live work present, but an operator override accepts the blast radius. |
`override_would_allow` tells the console whether an override path exists for the
current state. `blast_radius` is a `none` / `low` / `medium` / `high` severity
band derived from the affected session and work counts.
### Fail closed
If the control-plane inventory cannot be completed (DB unavailable, a listing
failed), `inventory_complete` is `false` and the verdict is `unsafe` / deny. An
incomplete evaluation must never green-light a restart.
### Operator override authority
Override authority is read from the environment variable
`GITEA_OPERATOR_RESTART_OVERRIDE_AUTHORIZATION` and **never** from a tool
argument. A worker session cannot set an environment variable on an
already-running daemon, so override cannot be self-asserted (same pattern as the
#630 daemon-maintenance authorization). The `request_override` tool argument only
expresses caller intent; it takes effect solely when the environment
authorization is present.
## The tool
```text
gitea_request_mcp_restart(remote, host, org, repo,
dry_run=True, request_override=False,
session_id=None, limit=200)
```
Read-only, dry-run, and it **never restarts anything**. `apply_supported` is
always `false`; passing `dry_run=False` performs no restart and reports that
apply is gated by a drain proof (a separate child).
## Audit
Every evaluation carries an `audit_record` (event, coordinator version, verdict,
allow decision, blast radius, counts, timestamp) so restart decisions are
auditable. No secrets flow through the coordinator — session ids, pids, and
profiles are operational metadata only.
A representative dry-run report is in
[`mcp-restart-impact-sample.json`](./mcp-restart-impact-sample.json).
-148
View File
@@ -1,148 +0,0 @@
{
"coordinator_version": "1.0.0-issue-658",
"evaluated_at": "2026-07-24T06:00:00+00:00",
"dry_run": true,
"restart_performed": false,
"inventory_complete": true,
"incomplete_reasons": [],
"verdict": "unsafe",
"allow_restart": false,
"override_would_allow": true,
"operator_override": false,
"blast_radius": "high",
"reasons": [
"live work would be disrupted; restart denied without operator override",
"1 critical section(s) in flight (active lease with a live owner)"
],
"affected_sessions": [
{
"session_id": "prgs-author-30988-d6f43c25",
"role": "author",
"profile": "prgs-author",
"pid": 1,
"status": "active",
"alive": true,
"heartbeat_stale": false,
"is_requester": false,
"live": true
},
{
"session_id": "prgs-reviewer-4157-0ce9",
"role": "reviewer",
"profile": "prgs-reviewer",
"pid": 1,
"status": "active",
"alive": true,
"heartbeat_stale": false,
"is_requester": true,
"live": true
}
],
"affected_leases": [
{
"lease_id": "lease-abc",
"session_id": "prgs-author-30988-d6f43c25",
"role": "author",
"phase": "implementing",
"freshness": "active",
"work_kind": "issue",
"work_number": 658,
"worktree_path": "/repo/branches/feat-issue-658",
"disruptive": true,
"is_mutation": true,
"is_critical_section": true
},
{
"lease_id": "lease-dead",
"session_id": "prgs-author-91485",
"role": "author",
"phase": "allocated",
"freshness": "stale_dead_process",
"work_kind": "issue",
"work_number": 651,
"worktree_path": null,
"disruptive": false,
"is_mutation": false,
"is_critical_section": false
}
],
"critical_sections": [
{
"lease_id": "lease-abc",
"session_id": "prgs-author-30988-d6f43c25",
"role": "author",
"phase": "implementing",
"freshness": "active",
"work_kind": "issue",
"work_number": 658,
"worktree_path": "/repo/branches/feat-issue-658",
"disruptive": true,
"is_mutation": true,
"is_critical_section": true
}
],
"affected_issues": [
658
],
"affected_prs": [],
"mutations": [
{
"lease_id": "lease-abc",
"session_id": "prgs-author-30988-d6f43c25",
"role": "author",
"phase": "implementing",
"freshness": "active",
"work_kind": "issue",
"work_number": 658,
"worktree_path": "/repo/branches/feat-issue-658",
"disruptive": true,
"is_mutation": true,
"is_critical_section": true
}
],
"terminal_lock": null,
"ack_state": {
"prgs-author-30988-d6f43c25": "pending"
},
"prior_recovery_attempts": [
{
"kind": "client_reconnect",
"at": "2026-07-24T06:00:00+00:00",
"outcome": "insufficient"
}
],
"counts": {
"sessions_total": 2,
"sessions_live_other": 1,
"leases_total": 2,
"leases_disruptive": 1,
"critical_sections": 1,
"mutations": 1,
"affected_issues": 1,
"affected_prs": 0,
"prior_recovery_attempts": 1
},
"audit_record": {
"event": "restart_impact_evaluated",
"coordinator_version": "1.0.0-issue-658",
"evaluated_at": "2026-07-24T06:00:00+00:00",
"dry_run": true,
"operator_override": false,
"requesting_session_id": "prgs-reviewer-4157-0ce9",
"inventory_complete": true,
"verdict": "unsafe",
"allow_restart": false,
"blast_radius": "high",
"counts": {
"sessions_total": 2,
"sessions_live_other": 1,
"leases_total": 2,
"leases_disruptive": 1,
"critical_sections": 1,
"mutations": 1,
"affected_issues": 1,
"affected_prs": 0,
"prior_recovery_attempts": 1
}
}
}
-1
View File
@@ -135,7 +135,6 @@ that gates each call, not which tools exist.
- `gitea_release_merger_pr_lease`
- `gitea_release_reviewer_pr_lease`
- `gitea_release_workflow_lease`
- `gitea_request_mcp_restart`
- `gitea_resolve_task_capability`
- `gitea_resume_review_draft`
- `gitea_review_pr`
+122
View File
@@ -0,0 +1,122 @@
# Sanctioned restart and graceful reload controls (#642)
Sessions used to recover MCP connectivity by killing the host daemon
(`pkill -f mcp_server.py`, #630). That is forbidden and stays forbidden: it
kills every namespace on the host, contaminates whichever session survives, and
leaves no audit trail. This document describes the sanctioned replacement,
implemented in `webui/sanctioned_restart.py`.
## What the console will and will not do
The console **never** restarts anything. It authorizes an intent, records it,
and hands off to a host supervisor. There is no code path in which the console
sends a signal, spawns a process, or renders a kill command — a regression test
asserts the module contains no `subprocess`, `signal`, `os.kill`, `os.system`,
or `popen` reference, and that no returned payload contains a kill command.
## Operations
| Mode | Action | Minimum role | Behaviour |
|------|--------|--------------|-----------|
| `reload` | `system.reload_namespace` | controller | Host supervisor reloads the namespace in place, draining in-flight requests. |
| `restart` | `system.restart_namespace` | admin | Host supervisor restarts the namespace. In-flight requests are lost. |
Scope is always exactly one namespace. A fleet-wide restart is an explicit
non-goal: `all`, `*`, `fleet`, and an empty scope are refused with
`fleet_scope_not_permitted`, because that is precisely the blast radius the
forbidden kill already had. An unrecognised namespace is refused rather than
passed through to the host.
## The gate sequence
`assess_restart_request()` applies every gate in order and reports the first
failure with a stable reason code:
| Order | Gate | Reason code on failure |
|-------|------|------------------------|
| 1 | Mode is `restart` or `reload` | `unknown_mode` |
| 2 | Scope is a single known namespace | `fleet_scope_not_permitted`, `unknown_namespace` |
| 3 | Principal holds the required console role | `unauthorized` |
| 4 | Confirmation phrase supplied | `confirmation_required` |
| 5 | Confirmation names this namespace and mode | `confirmation_mismatch` |
| 6 | Out-of-band operator authorization present | `operator_authorization_missing` |
| 7 | Runtime is not contaminated | `contaminated_runtime` |
| 8 | Host restart hook configured | `restart_hook_not_configured` |
Passing every gate yields `host_action_required`, never "restarted".
### Confirmation binds the namespace
The required phrase is `"<mode> <namespace>"` — for example
`restart gitea-author`. Binding the namespace into the phrase is the point: a
confirmation typed for one namespace cannot be replayed against another.
### Operator authorization is not self-assertable
Host daemon maintenance is authorized out of band through
`GITEA_OPERATOR_DAEMON_MAINTENANCE_AUTHORIZATION`, read from the process
environment and nowhere else (#630; #710 finding F1). A worker session cannot
set an environment variable for an already-running daemon, so this cannot be
faked the way a tool argument could.
### The host hook
`GITEA_SANCTIONED_RESTART_HOOK` holds an opaque reference the *host* resolves —
a supervisor label such as a launchd job name, never a command line. With no
hook configured the request is refused; the console does not fall back to a
process kill. The value is read server-side and never rendered to a client.
## Manual kill remains contamination
`classify_restart_command()` classifies an operator-proposed recovery command.
A manual `pkill`/`kill`/`killall` of the MCP daemon is contamination, not a
restart: it returns `clean_claim_allowed: false` and builds a durable
contamination marker (redacted command only, never secrets) naming
`system.restart_namespace` as the sanctioned alternative.
A live, uncleared contamination marker also blocks a restart. This is stricter
than #630's task-scoped gate, which deliberately lets a contaminated worker keep
commenting and handing off: restarting a contaminated runtime would launder the
contamination rather than resolve it. Clear the marker through the reconciler
path first.
## Post-restart health verification
After the host supervisor acts, `verify_post_restart_health()` decides whether
the session may claim to be clean:
| Status | Meaning | Clean claim |
|--------|---------|-------------|
| `clean` | Required tool callable, proven through the live client namespace | Allowed |
| `unproven` | Reported healthy without live client-namespace evidence | Refused |
| `unhealthy` | Probe failed | Refused |
Only `probe_source=client_namespace` evidence clears a session. Static tool
registration is not proof, and neither is an offline subprocess probe — an IDE
client can hold a registered tool list while live calls fail with
`client is closing: EOF` (see
[`mcp-namespace-health.md`](mcp-namespace-health.md)).
## Audit
Every attempt — allowed or denied — is recorded through
`webui.console_audit` with actor, target namespace, mode, result, and reason
code, and is redacted before it is persisted. `system.restart_namespace` is
break-glass, so its records are retained for 730 days. Records carry
`process_kill_executed: false`, which is a fact about the code path rather than
a claim: no such path exists.
## Environment variables
| Variable | Purpose |
|----------|---------|
| `GITEA_SANCTIONED_RESTART_HOOK` | Host supervisor reference; absent means restart is refused. |
| `GITEA_OPERATOR_DAEMON_MAINTENANCE_AUTHORIZATION` | Out-of-band operator authorization reference. |
| `WEBUI_AUDIT_LOG` | Console audit sink; absent means records are built but not persisted. |
## Non-goals
* No unrestricted `kill` from the UI, in any role, in any phase.
* No fleet-wide restart.
* No silent auto-restart loop: every attempt is confirmed and audited.
* This does not implement the Phase 1 health API (#634).
+11 -2
View File
@@ -91,6 +91,8 @@ already define, and a regression test asserts each mapping matches.
| `close_pr` | controller | privileged | `gitea.pr.close` | Yes | No | No | 3 |
| `merge_pr` | controller | privileged | `gitea.pr.merge` | Yes | **Yes** | **Yes** | 3 |
| `delete_branch` | admin | destructive | `gitea.branch.delete` | Yes | **Yes** | **Yes** | 3 |
| `system.reload_namespace` | controller | privileged | `runtime.reload_namespace` | Yes | No | No | 2 |
| `system.restart_namespace` | admin | destructive | `runtime.restart_namespace` | Yes | **Yes** | **Yes** | 2 |
**Dual control** means the acting principal may not be the sole authority: a
second distinct principal must confirm. **Break-glass** means the action is
@@ -102,6 +104,13 @@ honouring it.
`delete_branch` is admin-only rather than controller because it is the one
irreversible action in the set.
`system.restart_namespace` is admin-only for the same reason: restarting a
namespace drops every in-flight request on it. `system.reload_namespace` drains
first, so it is privileged but not destructive. Neither action is ever executed
by the console — both hand off to a host supervisor, and neither exposes a raw
process kill. See
[`sanctioned-restart-controls.md`](sanctioned-restart-controls.md) (#642).
### Authorization decision
`authorize(action_id, principal, for_execution=False)` returns a decision
@@ -199,8 +208,8 @@ breaking the request it describes.
| Class | Applies to | Default |
|-------|-----------|---------|
| `standard` | Routine gated writes | 90 days |
| `privileged` | `review_pr`, `close_pr`, and any unclassifiable action | 365 days |
| `break_glass` | `merge_pr`, `delete_branch` | 730 days |
| `privileged` | `review_pr`, `close_pr`, `system.reload_namespace`, and any unclassifiable action | 365 days |
| `break_glass` | `merge_pr`, `delete_branch`, `system.restart_namespace` | 730 days |
Each record carries its own class, day count, and computed `expires_at`, so
retention is auditable per record rather than inferred from file age. An
-151
View File
@@ -2040,7 +2040,6 @@ import dependency_graph # noqa: E402 # #784 durable dependency edges
import control_plane_db # noqa: E402
import lease_lifecycle # noqa: E402
import workflow_dashboard # noqa: E402 # #605 live queue/lease dashboard
import restart_coordinator # noqa: E402 # #658 MCP restart coordinator/impact
import incident_bridge # noqa: E402
import sentry_observability # noqa: E402 (#606 optional Sentry observability)
import sentry_incident_bridge # noqa: E402 (#607 Sentry→Gitea incident bridge)
@@ -21490,156 +21489,6 @@ def gitea_workflow_dashboard(
return payload
@mcp.tool()
def gitea_request_mcp_restart(
remote: str = "dadeschools",
host: str | None = None,
org: str | None = None,
repo: str | None = None,
dry_run: bool = True,
request_override: bool = False,
session_id: str | None = None,
limit: int = 200,
) -> dict:
"""Evaluate a proposed MCP restart and return an impact preview (#658).
Central restart coordinator: gathers live control-plane state (sessions,
leases/locks, in-flight issue/PR work, mutations, worktrees) and returns a
blast-radius impact report with a ``safe`` / ``unsafe`` / ``override``
verdict, so the console (#642/#652) and operators can see what a restart
would disrupt *before* any concurrent LLM work is destroyed.
This tool is **dry-run and never restarts anything.** The mutative apply
path is a separate child gated by a drain proof (non-goal here); calling
with ``dry_run=False`` still performs no restart and reports that apply is
not yet available.
Operator override authority is read from the process environment
(``GITEA_OPERATOR_RESTART_OVERRIDE_AUTHORIZATION``), never self-asserted by
the requesting session: ``request_override`` only expresses caller intent
and takes effect solely when that environment authorization is present.
Fails closed: if the control-plane inventory cannot be completed, the
verdict is ``unsafe`` / deny (an incomplete evaluation must never green-light
a restart).
"""
read_block = _profile_operation_gate("gitea.read")
if read_block:
return {
"success": False,
"read_only": True,
"dry_run": True,
"restart_performed": False,
"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,
"dry_run": True,
"restart_performed": False,
"reasons": [str(exc)],
}
inventory_complete = True
incomplete_reasons: list[str] = []
sessions: list[dict] = []
leases: list[dict] = []
terminal_lock: dict | None = None
db, db_errs = _control_plane_db_or_error()
if db is None:
inventory_complete = False
incomplete_reasons.extend(
db_errs or ["control-plane DB unavailable; cannot evaluate restart"]
)
else:
try:
sessions = db.list_sessions(statuses=("active",), limit=max(1, int(limit)))
except Exception as exc: # noqa: BLE001
inventory_complete = False
incomplete_reasons.append(
f"session inventory failed: {_redact(str(exc))}"
)
try:
lease_result = lease_lifecycle.list_active_leases(
db,
remote=remote if remote in REMOTES else remote,
org=o,
repo=r,
role=None,
include_non_active=False,
limit=max(1, int(limit)),
)
leases = list(lease_result.get("leases") or [])
except Exception as exc: # noqa: BLE001
inventory_complete = False
incomplete_reasons.append(
f"lease inventory failed: {_redact(str(exc))}"
)
try:
terminal = db.get_active_terminal_lock(
remote=remote if remote in REMOTES else remote,
org=o,
repo=r,
)
if terminal:
terminal_lock = dict(terminal)
except Exception as exc: # noqa: BLE001
inventory_complete = False
incomplete_reasons.append(
f"terminal lock lookup failed: {_redact(str(exc))}"
)
profile = get_profile()
profile_name = (profile.get("profile_name") or "").strip() or "session"
sid = (session_id or "").strip() or f"{profile_name}-{os.getpid()}"
# Override authority is read from the environment only — a worker session
# cannot set an env var for an already-running daemon, so it cannot be
# self-asserted the way a tool argument could (#630/#710 F1 pattern).
operator_authorized = bool(
(os.environ.get("GITEA_OPERATOR_RESTART_OVERRIDE_AUTHORIZATION") or "").strip()
)
operator_override = bool(request_override and operator_authorized)
inventory = {
"sessions": sessions,
"leases": leases,
"terminal_lock": terminal_lock,
"inventory_complete": inventory_complete,
"incomplete_reasons": incomplete_reasons,
}
report = restart_coordinator.evaluate_restart_impact(
inventory,
operator_override=operator_override,
requesting_session_id=sid,
dry_run=True, # coordinator is always analysis-only (#658)
)
payload = report.as_dict()
payload["success"] = True
payload["read_only"] = True
payload["remote"] = remote
payload["org"] = o
payload["repo"] = r
payload["requesting_session_id"] = sid
payload["operator_override_requested"] = bool(request_override)
payload["operator_override_authorized"] = operator_authorized
payload["apply_supported"] = False
if not dry_run:
payload["reasons"] = list(payload.get("reasons") or []) + [
"apply requested but not supported: sanctioned restart apply is "
"gated by a drain proof (separate child); no restart performed (#658)"
]
return payload
@mcp.tool()
def gitea_inspect_workflow_lease(
lease_id: str,
-451
View File
@@ -1,451 +0,0 @@
"""MCP restart coordinator and impact analysis (#658).
Before any sanctioned MCP restart, a central coordinator must evaluate the
live control-plane state — active sessions, leases/locks, in-flight issue/PR
work, mutations, worktrees, and recovery history — and produce an *impact
preview* so operators (and the web console, #642/#652) can see the blast
radius **before** concurrent LLM work is disrupted.
Design rules (mirrors the read-only posture of ``workflow_dashboard`` /
``lease_lifecycle``):
* **Pure classification.** :func:`evaluate_restart_impact` takes an already
gathered inventory and returns a structured report. It never touches the
network, the filesystem, or a live process, so multi-session fixtures can
drive every branch in unit tests. The coordinator *never restarts anything*;
a mutative apply path is a later child gated by a drain proof (non-goal here).
* **Fail closed.** If the inventory is not explicitly complete, the verdict is
``unsafe`` / deny — an incomplete evaluation must never green-light a restart.
* **No secrets.** Session ids, pids, and profiles are operational metadata, not
credentials; nothing secret flows through this module.
The single sanctioned entry point post-#657 is the MCP tool
``gitea_request_mcp_restart`` (dry-run by default), which gathers the inventory
from the #613 control-plane DB and calls :func:`evaluate_restart_impact`.
"""
from __future__ import annotations
from dataclasses import dataclass, field
from datetime import datetime, timezone
from typing import Any, Mapping, Sequence
import lease_lifecycle
COORDINATOR_VERSION = "1.0.0-issue-658"
# Restart verdicts. Exactly the three the acceptance criteria name.
VERDICT_SAFE = "safe"
VERDICT_UNSAFE = "unsafe"
VERDICT_OVERRIDE = "override"
# Blast-radius severity bands.
BLAST_NONE = "none"
BLAST_LOW = "low"
BLAST_MEDIUM = "medium"
BLAST_HIGH = "high"
# A live lease with a live owner process is treated as active in-flight work.
LEASE_FRESHNESS_LIVE = "active"
# Default staleness window for a session heartbeat (seconds). A session whose
# last heartbeat is older than this is not counted as live even if its row is
# still marked ``active`` — it is assumed dead/detached.
DEFAULT_SESSION_HEARTBEAT_STALE_SECONDS = 900
def _utc_now() -> datetime:
return datetime.now(timezone.utc)
def _parse_ts(value: str | None) -> datetime | None:
return lease_lifecycle._parse_ts(value)
@dataclass(frozen=True)
class SessionImpact:
"""One MCP session a restart would terminate."""
session_id: str
role: str | None
profile: str | None
pid: int | None
status: str | None
alive: bool | None
heartbeat_stale: bool
is_requester: bool
live: bool
def as_dict(self) -> dict[str, Any]:
return {
"session_id": self.session_id,
"role": self.role,
"profile": self.profile,
"pid": self.pid,
"status": self.status,
"alive": self.alive,
"heartbeat_stale": self.heartbeat_stale,
"is_requester": self.is_requester,
"live": self.live,
}
@dataclass(frozen=True)
class LeaseImpact:
"""One control-plane lease a restart would disrupt."""
lease_id: str | None
session_id: str | None
role: str | None
phase: str | None
freshness: str | None
work_kind: str | None
work_number: int | None
worktree_path: str | None
disruptive: bool
is_mutation: bool
is_critical_section: bool
def as_dict(self) -> dict[str, Any]:
return {
"lease_id": self.lease_id,
"session_id": self.session_id,
"role": self.role,
"phase": self.phase,
"freshness": self.freshness,
"work_kind": self.work_kind,
"work_number": self.work_number,
"worktree_path": self.worktree_path,
"disruptive": self.disruptive,
"is_mutation": self.is_mutation,
"is_critical_section": self.is_critical_section,
}
@dataclass(frozen=True)
class RestartImpactReport:
"""Impact preview DTO returned to the console / operator (#642/#652)."""
coordinator_version: str
evaluated_at: str
dry_run: bool
restart_performed: bool
inventory_complete: bool
verdict: str
allow_restart: bool
override_would_allow: bool
operator_override: bool
blast_radius: str
reasons: list[str]
affected_sessions: list[SessionImpact]
affected_leases: list[LeaseImpact]
critical_sections: list[LeaseImpact]
affected_issues: list[int]
affected_prs: list[int]
mutations: list[LeaseImpact]
terminal_lock: dict[str, Any] | None
ack_state: dict[str, str]
prior_recovery_attempts: list[dict[str, Any]]
counts: dict[str, int]
audit_record: dict[str, Any]
incomplete_reasons: list[str] = field(default_factory=list)
def as_dict(self) -> dict[str, Any]:
return {
"coordinator_version": self.coordinator_version,
"evaluated_at": self.evaluated_at,
"dry_run": self.dry_run,
"restart_performed": self.restart_performed,
"inventory_complete": self.inventory_complete,
"incomplete_reasons": list(self.incomplete_reasons),
"verdict": self.verdict,
"allow_restart": self.allow_restart,
"override_would_allow": self.override_would_allow,
"operator_override": self.operator_override,
"blast_radius": self.blast_radius,
"reasons": list(self.reasons),
"affected_sessions": [s.as_dict() for s in self.affected_sessions],
"affected_leases": [l.as_dict() for l in self.affected_leases],
"critical_sections": [l.as_dict() for l in self.critical_sections],
"affected_issues": list(self.affected_issues),
"affected_prs": list(self.affected_prs),
"mutations": [l.as_dict() for l in self.mutations],
"terminal_lock": self.terminal_lock,
"ack_state": dict(self.ack_state),
"prior_recovery_attempts": list(self.prior_recovery_attempts),
"counts": dict(self.counts),
"audit_record": dict(self.audit_record),
}
def _classify_session(
row: Mapping[str, Any],
*,
now: datetime,
requesting_session_id: str | None,
heartbeat_stale_seconds: int,
) -> SessionImpact:
session_id = str(row.get("session_id") or "")
pid = row.get("pid")
status = (row.get("status") or "").strip().lower() or None
alive = lease_lifecycle.is_process_alive(pid) if pid is not None else None
hb = _parse_ts(row.get("last_heartbeat_at"))
heartbeat_stale = bool(
hb is not None and (now - hb).total_seconds() > heartbeat_stale_seconds
)
live = bool(status == "active" and alive is not False and not heartbeat_stale)
return SessionImpact(
session_id=session_id,
role=row.get("role"),
profile=row.get("profile"),
pid=pid,
status=status,
alive=alive,
heartbeat_stale=heartbeat_stale,
is_requester=bool(
requesting_session_id and session_id == requesting_session_id
),
live=live,
)
# Lease phases that represent an active mutation in flight (as opposed to a
# mere allocation/claim with no work committed yet). An active lease in any of
# these phases is a critical section a restart must not sever.
_MUTATING_PHASES = frozenset(
{
"implementing",
"publishing",
"pushing",
"committing",
"reviewing",
"merging",
"reconciling",
"conflict_fix",
}
)
def _classify_lease(row: Mapping[str, Any]) -> LeaseImpact:
freshness_obj = row.get("freshness")
if isinstance(freshness_obj, Mapping):
freshness = str(freshness_obj.get("freshness") or "").strip().lower() or None
else:
freshness = str(freshness_obj or "").strip().lower() or None
phase = (row.get("phase") or "").strip().lower() or None
worktree = row.get("worktree_path")
disruptive = freshness == LEASE_FRESHNESS_LIVE
# A live lease is a mutation-in-flight if it carries an author worktree or
# its phase names a mutating step. All disruptive leases are critical
# sections a restart would sever regardless.
is_mutation = bool(
disruptive and (bool(worktree) or (phase in _MUTATING_PHASES))
)
number = row.get("work_number")
try:
number = int(number) if number is not None else None
except (TypeError, ValueError):
number = None
return LeaseImpact(
lease_id=row.get("lease_id"),
session_id=row.get("session_id"),
role=row.get("role"),
phase=phase,
freshness=freshness,
work_kind=(str(row.get("work_kind") or "").strip().lower() or None),
work_number=number,
worktree_path=worktree,
disruptive=disruptive,
is_mutation=is_mutation,
is_critical_section=disruptive,
)
def _blast_radius(*, session_count: int, work_count: int, mutation_count: int) -> str:
if mutation_count > 0 or work_count >= 3 or session_count >= 3:
return BLAST_HIGH
if work_count > 0 or session_count == 2:
return BLAST_MEDIUM
if session_count == 1:
return BLAST_LOW
return BLAST_NONE
def evaluate_restart_impact(
inventory: Mapping[str, Any],
*,
now: datetime | None = None,
operator_override: bool = False,
requesting_session_id: str | None = None,
dry_run: bool = True,
session_heartbeat_stale_seconds: int = DEFAULT_SESSION_HEARTBEAT_STALE_SECONDS,
) -> RestartImpactReport:
"""Evaluate a proposed MCP restart and return an impact preview.
``inventory`` is a mapping with:
* ``sessions`` — session rows (session_id, role, profile, pid, status,
last_heartbeat_at).
* ``leases`` — control-plane lease rows, each ideally carrying an enriched
``freshness`` dict (as :func:`lease_lifecycle.list_active_leases` returns);
a bare string freshness is also accepted.
* ``terminal_lock`` — the active terminal (merge) lock, if any.
* ``prior_recovery_attempts`` — narrower recovery attempts already tried
(e.g. sanctioned reconnects) so the operator sees escalation history.
* ``inventory_complete`` — bool. **Must** be explicitly True; a missing or
falsy value forces a deny (fail closed).
* ``incomplete_reasons`` — optional reasons the inventory is incomplete.
The coordinator never restarts anything: ``restart_performed`` is always
False and the mutative apply path is a later drain-gated child.
"""
moment = now or _utc_now()
reasons: list[str] = []
inventory_complete = bool(inventory.get("inventory_complete", False))
incomplete_reasons = [str(r) for r in (inventory.get("incomplete_reasons") or [])]
sessions_raw: Sequence[Mapping[str, Any]] = inventory.get("sessions") or []
leases_raw: Sequence[Mapping[str, Any]] = inventory.get("leases") or []
terminal_lock = inventory.get("terminal_lock") or None
prior_recovery_attempts = [
dict(a) for a in (inventory.get("prior_recovery_attempts") or [])
]
session_impacts = [
_classify_session(
s,
now=moment,
requesting_session_id=requesting_session_id,
heartbeat_stale_seconds=session_heartbeat_stale_seconds,
)
for s in sessions_raw
]
lease_impacts = [_classify_lease(l) for l in leases_raw]
# Only *other* live sessions and live leases constitute blast radius: a
# restart that would kill only the requesting session with no other work in
# flight is safe.
other_live_sessions = [
s for s in session_impacts if s.live and not s.is_requester
]
disruptive_leases = [l for l in lease_impacts if l.disruptive]
critical_sections = [l for l in lease_impacts if l.is_critical_section]
mutations = [l for l in lease_impacts if l.is_mutation]
affected_issues = sorted(
{
l.work_number
for l in disruptive_leases
if l.work_kind == "issue" and l.work_number is not None
}
)
affected_prs = sorted(
{
l.work_number
for l in disruptive_leases
if l.work_kind == "pr" and l.work_number is not None
}
)
disruptive = bool(disruptive_leases or other_live_sessions or terminal_lock)
if not inventory_complete:
verdict = VERDICT_UNSAFE
allow_restart = False
reasons.append(
"inventory incomplete: restart evaluation cannot confirm blast "
"radius — deny (fail closed, #658)"
)
reasons.extend(incomplete_reasons)
elif not disruptive:
verdict = VERDICT_SAFE
allow_restart = True
reasons.append("no other live sessions, live leases, or terminal lock")
elif operator_override:
verdict = VERDICT_OVERRIDE
allow_restart = True
reasons.append(
"live work present; operator override accepts the blast radius"
)
else:
verdict = VERDICT_UNSAFE
allow_restart = False
reasons.append(
"live work would be disrupted; restart denied without operator "
"override"
)
if critical_sections and inventory_complete:
reasons.append(
f"{len(critical_sections)} critical section(s) in flight "
"(active lease with a live owner)"
)
if terminal_lock:
reasons.append("active terminal (merge) lock present")
override_would_allow = bool(inventory_complete and disruptive)
blast_radius = _blast_radius(
session_count=len(other_live_sessions),
work_count=len(affected_issues) + len(affected_prs),
mutation_count=len(mutations),
)
# Acknowledgement is a later child (drain protocol); expose per-session
# placeholders so the console can render the ack column now.
ack_state = {s.session_id: "pending" for s in other_live_sessions}
counts = {
"sessions_total": len(session_impacts),
"sessions_live_other": len(other_live_sessions),
"leases_total": len(lease_impacts),
"leases_disruptive": len(disruptive_leases),
"critical_sections": len(critical_sections),
"mutations": len(mutations),
"affected_issues": len(affected_issues),
"affected_prs": len(affected_prs),
"prior_recovery_attempts": len(prior_recovery_attempts),
}
audit_record = {
"event": "restart_impact_evaluated",
"coordinator_version": COORDINATOR_VERSION,
"evaluated_at": moment.isoformat(),
"dry_run": dry_run,
"operator_override": bool(operator_override),
"requesting_session_id": requesting_session_id,
"inventory_complete": inventory_complete,
"verdict": verdict,
"allow_restart": allow_restart,
"blast_radius": blast_radius,
"counts": counts,
}
return RestartImpactReport(
coordinator_version=COORDINATOR_VERSION,
evaluated_at=moment.isoformat(),
dry_run=dry_run,
restart_performed=False,
inventory_complete=inventory_complete,
verdict=verdict,
allow_restart=allow_restart,
override_would_allow=override_would_allow,
operator_override=bool(operator_override),
blast_radius=blast_radius,
reasons=reasons,
affected_sessions=session_impacts,
affected_leases=lease_impacts,
critical_sections=critical_sections,
affected_issues=affected_issues,
affected_prs=affected_prs,
mutations=mutations,
terminal_lock=dict(terminal_lock)
if isinstance(terminal_lock, Mapping)
else terminal_lock,
ack_state=ack_state,
prior_recovery_attempts=prior_recovery_attempts,
counts=counts,
audit_record=audit_record,
incomplete_reasons=incomplete_reasons,
)
+15
View File
@@ -346,6 +346,21 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
"role": "controller",
},
# #642: sanctioned host-daemon lifecycle controls. Deliberately *not* a
# ``gitea.*`` operation — restarting an MCP namespace is a host action, not
# a Gitea API call, and no configured Gitea profile should be able to
# satisfy it by accident. Authority comes from the console RBAC model plus
# out-of-band operator authorization (#630); these entries exist so the
# console cannot invent an authority the capability layer never declared.
"restart_namespace": {
"permission": "runtime.restart_namespace",
"role": "controller",
},
"reload_namespace": {
"permission": "runtime.reload_namespace",
"role": "controller",
},
# #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": {
-340
View File
@@ -1,340 +0,0 @@
"""Tests for the MCP restart coordinator and impact analysis (#658).
Multi-session fixtures exercise every verdict branch: safe, unsafe (live work),
override, and the fail-closed deny on incomplete inventory. Also covers the
critical-section deny path and the new ``ControlPlaneDB.list_sessions``.
"""
from __future__ import annotations
import os
import tempfile
import unittest
from datetime import datetime, timedelta, timezone
import restart_coordinator as rc
from control_plane_db import ControlPlaneDB
NOW = datetime(2026, 7, 24, 6, 0, 0, tzinfo=timezone.utc)
def _ts(dt: datetime) -> str:
return dt.isoformat()
def _live_pid() -> int:
return os.getpid()
def _dead_pid() -> int:
# A pid that is essentially never alive. os.kill(0) on it raises
# ProcessLookupError → is_process_alive False.
return 2_000_000_000
def _session(session_id, *, pid, status="active", heartbeat=None, role="author"):
return {
"session_id": session_id,
"role": role,
"profile": "prgs-author",
"pid": pid,
"status": status,
"last_heartbeat_at": _ts(heartbeat or NOW),
}
def _lease(
lease_id,
*,
session_id,
freshness,
kind="issue",
number=658,
phase="allocated",
worktree=None,
role="author",
):
return {
"lease_id": lease_id,
"session_id": session_id,
"role": role,
"phase": phase,
"work_kind": kind,
"work_number": number,
"worktree_path": worktree,
"freshness": {"freshness": freshness},
}
class EvaluateRestartImpactTest(unittest.TestCase):
def test_incomplete_inventory_denies_fail_closed(self) -> None:
report = rc.evaluate_restart_impact(
{"inventory_complete": False, "incomplete_reasons": ["db down"]},
now=NOW,
)
self.assertEqual(report.verdict, rc.VERDICT_UNSAFE)
self.assertFalse(report.allow_restart)
self.assertFalse(report.restart_performed)
self.assertIn("db down", report.incomplete_reasons)
self.assertTrue(
any("fail closed" in reasoning for reasoning in report.reasons)
)
def test_missing_completeness_flag_denies(self) -> None:
# No inventory_complete key at all → treated as incomplete.
report = rc.evaluate_restart_impact({}, now=NOW)
self.assertEqual(report.verdict, rc.VERDICT_UNSAFE)
self.assertFalse(report.allow_restart)
def test_no_other_work_is_safe(self) -> None:
report = rc.evaluate_restart_impact(
{
"inventory_complete": True,
"sessions": [_session("requester", pid=_live_pid())],
"leases": [],
},
now=NOW,
requesting_session_id="requester",
)
self.assertEqual(report.verdict, rc.VERDICT_SAFE)
self.assertTrue(report.allow_restart)
self.assertEqual(report.blast_radius, rc.BLAST_NONE)
self.assertEqual(report.affected_issues, [])
def test_dead_foreign_session_and_lease_are_not_disruptive(self) -> None:
report = rc.evaluate_restart_impact(
{
"inventory_complete": True,
"sessions": [
_session("requester", pid=_live_pid()),
_session("dead", pid=_dead_pid()),
],
"leases": [
_lease("l-dead", session_id="dead", freshness="stale_dead_process")
],
},
now=NOW,
requesting_session_id="requester",
)
self.assertEqual(report.verdict, rc.VERDICT_SAFE)
self.assertTrue(report.allow_restart)
self.assertEqual(report.counts["leases_disruptive"], 0)
self.assertEqual(report.counts["sessions_live_other"], 0)
def test_live_foreign_lease_denies_without_override(self) -> None:
report = rc.evaluate_restart_impact(
{
"inventory_complete": True,
"sessions": [
_session("requester", pid=_live_pid()),
_session("worker", pid=_live_pid()),
],
"leases": [
_lease(
"l1",
session_id="worker",
freshness="active",
worktree="/tmp/wt-658",
phase="implementing",
)
],
},
now=NOW,
requesting_session_id="requester",
)
self.assertEqual(report.verdict, rc.VERDICT_UNSAFE)
self.assertFalse(report.allow_restart)
# Critical section detected: active lease with a live owner.
self.assertEqual(len(report.critical_sections), 1)
self.assertEqual(report.affected_issues, [658])
self.assertEqual(report.counts["mutations"], 1)
self.assertTrue(report.override_would_allow)
self.assertEqual(report.blast_radius, rc.BLAST_HIGH)
# Placeholder ack state for the affected session.
self.assertEqual(report.ack_state.get("worker"), "pending")
def test_operator_override_allows_despite_live_work(self) -> None:
inv = {
"inventory_complete": True,
"sessions": [
_session("requester", pid=_live_pid()),
_session("worker", pid=_live_pid()),
],
"leases": [_lease("l1", session_id="worker", freshness="active")],
}
report = rc.evaluate_restart_impact(
inv,
now=NOW,
requesting_session_id="requester",
operator_override=True,
)
self.assertEqual(report.verdict, rc.VERDICT_OVERRIDE)
self.assertTrue(report.allow_restart)
self.assertFalse(report.restart_performed)
def test_deny_when_critical_section_open(self) -> None:
# A single live author lease in a mutating phase is a critical section
# that must deny an un-overridden restart.
report = rc.evaluate_restart_impact(
{
"inventory_complete": True,
"sessions": [_session("worker", pid=_live_pid())],
"leases": [
_lease(
"l1",
session_id="worker",
freshness="active",
phase="merging",
kind="pr",
number=900,
)
],
},
now=NOW,
requesting_session_id="requester",
)
self.assertEqual(report.verdict, rc.VERDICT_UNSAFE)
self.assertFalse(report.allow_restart)
self.assertEqual(report.affected_prs, [900])
self.assertEqual(len(report.critical_sections), 1)
def test_terminal_lock_makes_restart_unsafe(self) -> None:
report = rc.evaluate_restart_impact(
{
"inventory_complete": True,
"sessions": [_session("requester", pid=_live_pid())],
"leases": [],
"terminal_lock": {"terminal_pr": 812},
},
now=NOW,
requesting_session_id="requester",
)
self.assertEqual(report.verdict, rc.VERDICT_UNSAFE)
self.assertFalse(report.allow_restart)
self.assertIsNotNone(report.terminal_lock)
self.assertTrue(
any("terminal" in reasoning for reasoning in report.reasons)
)
def test_other_live_session_without_lease_is_disruptive(self) -> None:
report = rc.evaluate_restart_impact(
{
"inventory_complete": True,
"sessions": [
_session("requester", pid=_live_pid()),
_session("idle-but-live", pid=_live_pid()),
],
"leases": [],
},
now=NOW,
requesting_session_id="requester",
)
self.assertEqual(report.verdict, rc.VERDICT_UNSAFE)
self.assertEqual(report.counts["sessions_live_other"], 1)
def test_stale_heartbeat_session_not_counted_live(self) -> None:
stale = NOW - timedelta(hours=2)
report = rc.evaluate_restart_impact(
{
"inventory_complete": True,
"sessions": [
_session("requester", pid=_live_pid()),
_session("stale", pid=_live_pid(), heartbeat=stale),
],
"leases": [],
},
now=NOW,
requesting_session_id="requester",
)
self.assertEqual(report.verdict, rc.VERDICT_SAFE)
self.assertEqual(report.counts["sessions_live_other"], 0)
def test_prior_recovery_attempts_echoed(self) -> None:
report = rc.evaluate_restart_impact(
{
"inventory_complete": True,
"sessions": [_session("requester", pid=_live_pid())],
"leases": [],
"prior_recovery_attempts": [
{"kind": "client_reconnect", "at": _ts(NOW)}
],
},
now=NOW,
requesting_session_id="requester",
)
self.assertEqual(len(report.prior_recovery_attempts), 1)
self.assertEqual(report.counts["prior_recovery_attempts"], 1)
def test_bare_string_freshness_accepted(self) -> None:
lease = _lease("l1", session_id="worker", freshness="active")
lease["freshness"] = "active" # bare string, not a dict
report = rc.evaluate_restart_impact(
{
"inventory_complete": True,
"sessions": [_session("worker", pid=_live_pid())],
"leases": [lease],
},
now=NOW,
requesting_session_id="requester",
)
self.assertEqual(report.counts["leases_disruptive"], 1)
def test_as_dict_is_serializable_dto(self) -> None:
import json
report = rc.evaluate_restart_impact(
{
"inventory_complete": True,
"sessions": [_session("requester", pid=_live_pid())],
"leases": [],
},
now=NOW,
requesting_session_id="requester",
)
payload = report.as_dict()
# Round-trips through JSON — safe for the console DTO.
encoded = json.dumps(payload)
decoded = json.loads(encoded)
self.assertEqual(decoded["verdict"], rc.VERDICT_SAFE)
self.assertIn("audit_record", decoded)
self.assertEqual(decoded["audit_record"]["event"], "restart_impact_evaluated")
self.assertFalse(decoded["restart_performed"])
self.assertIn("coordinator_version", decoded)
class ListSessionsTest(unittest.TestCase):
def setUp(self) -> None:
self._tmp = tempfile.TemporaryDirectory()
self.db = ControlPlaneDB(os.path.join(self._tmp.name, "cp.sqlite3"))
def tearDown(self) -> None:
self._tmp.cleanup()
def test_list_sessions_filters_by_status(self) -> None:
self.db.upsert_session(session_id="a", role="author", pid=1, status="active")
self.db.upsert_session(session_id="b", role="author", pid=2, status="ended")
active = self.db.list_sessions(statuses=("active",))
ids = {row["session_id"] for row in active}
self.assertEqual(ids, {"a"})
every = self.db.list_sessions()
self.assertEqual({row["session_id"] for row in every}, {"a", "b"})
def test_list_sessions_feeds_coordinator(self) -> None:
self.db.upsert_session(
session_id="requester", role="author", pid=os.getpid(), status="active"
)
report = rc.evaluate_restart_impact(
{
"inventory_complete": True,
"sessions": self.db.list_sessions(statuses=("active",)),
"leases": [],
},
now=NOW,
requesting_session_id="requester",
)
self.assertEqual(report.counts["sessions_total"], 1)
if __name__ == "__main__": # pragma: no cover
unittest.main()
+502
View File
@@ -0,0 +1,502 @@
"""Sanctioned restart / graceful reload control tests (#642).
Acceptance criteria under test:
1. The sanctioned restart path is implemented behind gates (capability,
confirmation, operator authorization, host hook).
2. Manual ``pkill`` stays forbidden and is classified as contamination.
3. Post-restart mutations require clean health/session proof.
4. Authorized restart preview, unauthorized deny, contamination classification.
5. No entry point exposes a raw kill.
"""
import json
import os
import tempfile
import unittest
import mcp_namespace_health
import runtime_recovery_guard
from task_capability_map import TASK_CAPABILITY_MAP
from webui import console_audit, console_authz, gated_actions, sanctioned_restart
NAMESPACE = "gitea-author"
# An operator-authorized, hook-configured host. Passed explicitly so no test
# depends on (or mutates) the real process environment.
READY_ENV = {
sanctioned_restart.RESTART_HOOK_ENV: "launchd:cc.prgs.gitea-author",
runtime_recovery_guard.OPERATOR_AUTHORIZATION_ENV: "ops-ticket-4821",
}
def admin(subject: str = "[email protected]") -> console_authz.Principal:
return console_authz.Principal(
subject=subject,
role=console_authz.ADMIN,
identity_source=console_authz.IDENTITY_ACCESS_PROXY,
authenticated=True,
)
def viewer() -> console_authz.Principal:
return console_authz.Principal(
subject="[email protected]",
role=console_authz.VIEWER,
identity_source=console_authz.IDENTITY_ACCESS_PROXY,
authenticated=True,
)
class TestCapabilityWiring(unittest.TestCase):
"""AC1: authority is declared, not invented by the console."""
def test_actions_resolve_through_the_capability_map(self):
for action_id in (
sanctioned_restart.ACTION_RESTART_NAMESPACE,
sanctioned_restart.ACTION_RELOAD_NAMESPACE,
):
with self.subTest(action=action_id):
action = console_authz.get_action(action_id)
self.assertIsNotNone(action)
self.assertIn(action.task_key, TASK_CAPABILITY_MAP)
self.assertEqual(
action.mcp_permission,
TASK_CAPABILITY_MAP[action.task_key]["permission"],
)
def test_restart_permission_is_not_a_gitea_operation(self):
"""No configured Gitea profile should satisfy a host restart."""
permission = TASK_CAPABILITY_MAP["restart_namespace"]["permission"]
self.assertFalse(permission.startswith("gitea."))
def test_restart_is_destructive_dual_control_break_glass(self):
action = console_authz.get_action(
sanctioned_restart.ACTION_RESTART_NAMESPACE
)
self.assertEqual(action.action_class, console_authz.CLASS_DESTRUCTIVE)
self.assertEqual(action.minimum_role, console_authz.ADMIN)
self.assertTrue(action.dual_control)
self.assertTrue(action.break_glass)
self.assertTrue(action.requires_confirmation)
def test_reload_is_privileged_but_not_destructive(self):
action = console_authz.get_action(
sanctioned_restart.ACTION_RELOAD_NAMESPACE
)
self.assertEqual(action.action_class, console_authz.CLASS_PRIVILEGED)
self.assertTrue(action.requires_confirmation)
class TestPreview(unittest.TestCase):
"""AC4: an authorized preview renders the plan without executing it."""
def test_preview_lists_the_mutation_ledger(self):
preview = sanctioned_restart.build_restart_preview(
NAMESPACE, principal=admin(), env=READY_ENV
)
steps = [entry["step"] for entry in preview["mutation_ledger"]]
self.assertEqual(
steps, ["quiesce", "host_restart_hook", "health_recheck", "audit"]
)
self.assertTrue(preview["scope_valid"])
self.assertTrue(preview["post_restart_verification_required"])
def test_reload_preview_drains_instead_of_restarting(self):
preview = sanctioned_restart.build_restart_preview(
NAMESPACE, sanctioned_restart.MODE_RELOAD,
principal=admin(), env=READY_ENV,
)
steps = [entry["step"] for entry in preview["mutation_ledger"]]
self.assertIn("host_graceful_reload", steps)
self.assertNotIn("host_restart_hook", steps)
def test_preview_never_enables_execution(self):
preview = sanctioned_restart.build_restart_preview(
NAMESPACE, principal=admin(), env=READY_ENV
)
self.assertFalse(preview["execution_enabled"])
self.assertFalse(preview["authorization"]["execution_enabled"])
def test_confirmation_phrase_binds_the_namespace(self):
self.assertTrue(
sanctioned_restart.confirmation_matches(
NAMESPACE, sanctioned_restart.MODE_RESTART,
"restart gitea-author",
)
)
# A phrase typed for one namespace must not authorize another.
self.assertFalse(
sanctioned_restart.confirmation_matches(
"gitea-merger", sanctioned_restart.MODE_RESTART,
"restart gitea-author",
)
)
class TestGates(unittest.TestCase):
"""AC1/AC4: every gate denies with a stable reason code."""
def _assess(self, **kwargs):
params = {
"principal": admin(),
"confirmation": f"restart {NAMESPACE}",
"env": READY_ENV,
}
params.update(kwargs)
namespace = params.pop("namespace", NAMESPACE)
mode = params.pop("mode", sanctioned_restart.MODE_RESTART)
return sanctioned_restart.assess_restart_request(
namespace, mode, **params
)
def test_authorized_confirmed_request_passes_every_gate(self):
result = self._assess()
self.assertTrue(result["allowed"])
self.assertEqual(
result["reason_code"], sanctioned_restart.ALLOW_HOST_ACTION_REQUIRED
)
def test_passing_every_gate_is_not_an_execution_grant(self):
"""An allowed request still never lets the console touch the process."""
result = self._assess()
self.assertTrue(result["allowed"])
self.assertFalse(result["execution_enabled"])
self.assertFalse(result["console_executes"])
def test_unauthorized_principal_is_denied(self):
result = self._assess(principal=viewer())
self.assertFalse(result["allowed"])
self.assertEqual(
result["reason_code"], sanctioned_restart.DENY_UNAUTHORIZED
)
def test_anonymous_principal_is_denied(self):
result = self._assess(principal=None)
self.assertFalse(result["allowed"])
self.assertEqual(
result["reason_code"], sanctioned_restart.DENY_UNAUTHORIZED
)
def test_missing_confirmation_is_denied(self):
result = self._assess(confirmation=None)
self.assertFalse(result["allowed"])
self.assertEqual(
result["reason_code"], sanctioned_restart.DENY_CONFIRMATION_MISSING
)
def test_confirmation_for_another_namespace_is_denied(self):
result = self._assess(confirmation="restart gitea-merger")
self.assertFalse(result["allowed"])
self.assertEqual(
result["reason_code"], sanctioned_restart.DENY_CONFIRMATION_MISMATCH
)
def test_missing_operator_authorization_is_denied(self):
env = {sanctioned_restart.RESTART_HOOK_ENV: "launchd:cc.prgs.author"}
result = self._assess(env=env)
self.assertFalse(result["allowed"])
self.assertEqual(
result["reason_code"],
sanctioned_restart.DENY_OPERATOR_AUTHORIZATION,
)
def test_missing_host_hook_is_denied_without_kill_fallback(self):
env = {
runtime_recovery_guard.OPERATOR_AUTHORIZATION_ENV: "ops-ticket-1",
}
result = self._assess(env=env)
self.assertFalse(result["allowed"])
self.assertEqual(
result["reason_code"], sanctioned_restart.DENY_HOOK_NOT_CONFIGURED
)
def test_fleet_scope_is_refused(self):
for scope in ("all", "*", "fleet"):
with self.subTest(scope=scope):
result = self._assess(
namespace=scope, confirmation=f"restart {scope}"
)
self.assertFalse(result["allowed"])
self.assertEqual(
result["reason_code"], sanctioned_restart.DENY_FLEET_SCOPE
)
def test_unknown_namespace_is_refused(self):
result = self._assess(
namespace="gitea-nope", confirmation="restart gitea-nope"
)
self.assertFalse(result["allowed"])
self.assertEqual(
result["reason_code"], sanctioned_restart.DENY_UNKNOWN_NAMESPACE
)
def test_unknown_mode_is_refused(self):
result = self._assess(mode="obliterate")
self.assertFalse(result["allowed"])
self.assertEqual(
result["reason_code"], sanctioned_restart.DENY_UNKNOWN_MODE
)
def test_live_contamination_marker_blocks_restart(self):
marker = runtime_recovery_guard.build_contamination_record(
reason_class=runtime_recovery_guard.REASON_MANUAL_DAEMON_KILL,
command_redacted="pkill -f mcp_server.py",
)
result = self._assess(contamination_marker=marker)
self.assertFalse(result["allowed"])
self.assertEqual(
result["reason_code"], sanctioned_restart.DENY_CONTAMINATED_RUNTIME
)
def test_reconciler_cleared_marker_no_longer_blocks(self):
marker = runtime_recovery_guard.build_contamination_record(
reason_class=runtime_recovery_guard.REASON_MANUAL_DAEMON_KILL,
command_redacted="pkill -f mcp_server.py",
)
marker = dict(marker, cleared_by_reconciler=True)
result = self._assess(contamination_marker=marker)
self.assertTrue(result["allowed"])
class TestExecutionNeverKills(unittest.TestCase):
"""AC5: no path exposes or runs a raw process kill."""
def test_authorized_execution_defers_to_the_host_supervisor(self):
result = sanctioned_restart.execute_restart(
NAMESPACE,
principal=admin(),
confirmation=f"restart {NAMESPACE}",
env=READY_ENV,
)
self.assertTrue(result["allowed"])
self.assertFalse(result["success"])
self.assertFalse(result["process_kill_executed"])
self.assertEqual(
result["outcome"], sanctioned_restart.ALLOW_HOST_ACTION_REQUIRED
)
def test_denied_execution_reports_the_refusing_gate(self):
result = sanctioned_restart.execute_restart(
NAMESPACE, principal=viewer(), confirmation=f"restart {NAMESPACE}",
env=READY_ENV,
)
self.assertFalse(result["allowed"])
self.assertEqual(
result["outcome"], sanctioned_restart.DENY_UNAUTHORIZED
)
self.assertFalse(result["process_kill_executed"])
def test_module_never_spawns_a_process(self):
path = os.path.join(
os.path.dirname(os.path.dirname(os.path.abspath(__file__))),
"webui", "sanctioned_restart.py",
)
with open(path, encoding="utf-8") as handle:
source = handle.read()
for forbidden in (
"import subprocess", "import signal", "os.kill", "os.system",
"popen",
):
with self.subTest(forbidden=forbidden):
self.assertNotIn(forbidden, source.lower())
def test_no_surface_returns_a_kill_command(self):
payloads = [
sanctioned_restart.build_restart_preview(
NAMESPACE, principal=admin(), env=READY_ENV
),
sanctioned_restart.restart_policy(),
sanctioned_restart.execute_restart(
NAMESPACE, principal=admin(),
confirmation=f"restart {NAMESPACE}", env=READY_ENV,
),
]
for payload in payloads:
rendered = json.dumps(payload, default=str).lower()
self.assertNotIn("kill -9", rendered)
self.assertNotIn("pkill -f", rendered)
def test_policy_declares_no_raw_kill_and_no_silent_restart(self):
policy = sanctioned_restart.restart_policy()
self.assertFalse(policy["raw_kill_exposed"])
self.assertFalse(policy["console_executes_process_kill"])
self.assertFalse(policy["fleet_scope_permitted"])
self.assertFalse(policy["silent_auto_restart_permitted"])
self.assertTrue(policy["audit_required"])
class TestContaminationClassification(unittest.TestCase):
"""AC2: manual pkill is contamination, and it blocks clean claims."""
def test_manual_daemon_pkill_is_contamination(self):
result = sanctioned_restart.classify_restart_command(
"pkill -f mcp_server.py"
)
self.assertTrue(result["contamination"])
self.assertFalse(result["clean_claim_allowed"])
self.assertIsNotNone(result["contamination_marker"])
self.assertEqual(
result["sanctioned_alternative"],
sanctioned_restart.ACTION_RESTART_NAMESPACE,
)
def test_broad_process_kill_is_contamination(self):
result = sanctioned_restart.classify_restart_command("killall -9 Python")
self.assertTrue(result["contamination"])
self.assertFalse(result["clean_claim_allowed"])
def test_marker_names_the_sanctioned_alternative(self):
result = sanctioned_restart.classify_restart_command(
"pkill -f mcp_server.py"
)
marker = result["contamination_marker"]
self.assertIn(
sanctioned_restart.ACTION_RESTART_NAMESPACE, marker["detail"]
)
def test_benign_command_is_not_contamination(self):
result = sanctioned_restart.classify_restart_command("git status")
self.assertFalse(result["contamination"])
self.assertTrue(result["clean_claim_allowed"])
def test_no_command_is_not_contamination(self):
result = sanctioned_restart.classify_restart_command(None)
self.assertFalse(result["contamination"])
self.assertTrue(result["clean_claim_allowed"])
class TestPostRestartHealth(unittest.TestCase):
"""AC3: a clean post-restart claim needs live client-namespace proof."""
def test_live_client_probe_clears_the_session(self):
result = sanctioned_restart.verify_post_restart_health(
NAMESPACE,
probe_result={"success": True},
probe_source=mcp_namespace_health.PROBE_SOURCE_CLIENT,
registered_tools=["gitea_whoami"],
required_tool="gitea_whoami",
)
self.assertEqual(result["status"], sanctioned_restart.HEALTH_CLEAN)
self.assertTrue(result["clean_claim_allowed"])
self.assertTrue(result["mutations_allowed"])
def test_offline_probe_does_not_clear_the_session(self):
result = sanctioned_restart.verify_post_restart_health(
NAMESPACE,
probe_result={"success": True},
probe_source=mcp_namespace_health.PROBE_SOURCE_OFFLINE,
registered_tools=["gitea_whoami"],
required_tool="gitea_whoami",
)
self.assertFalse(result["clean_claim_allowed"])
self.assertFalse(result["mutations_allowed"])
def test_failed_probe_is_unhealthy(self):
result = sanctioned_restart.verify_post_restart_health(
NAMESPACE,
probe_result={"success": False, "error": "client is closing: EOF"},
probe_source=mcp_namespace_health.PROBE_SOURCE_CLIENT,
registered_tools=["gitea_whoami"],
required_tool="gitea_whoami",
)
self.assertEqual(result["status"], sanctioned_restart.HEALTH_UNHEALTHY)
self.assertFalse(result["clean_claim_allowed"])
def test_static_registration_alone_never_clears_the_session(self):
result = sanctioned_restart.verify_post_restart_health(
NAMESPACE,
registered_tools=["gitea_whoami"],
required_tool="gitea_whoami",
)
self.assertFalse(result["clean_claim_allowed"])
class TestAuditEmission(unittest.TestCase):
"""Every restart attempt is audited with actor, target, and result."""
def _run(self, principal, sink):
prior = os.environ.get(console_audit.AUDIT_LOG_ENV)
os.environ[console_audit.AUDIT_LOG_ENV] = sink
try:
return sanctioned_restart.execute_restart(
NAMESPACE,
principal=principal,
confirmation=f"restart {NAMESPACE}",
env=READY_ENV,
request_id="req-642",
)
finally:
if prior is None:
os.environ.pop(console_audit.AUDIT_LOG_ENV, None)
else:
os.environ[console_audit.AUDIT_LOG_ENV] = prior
def test_allowed_attempt_is_written_with_actor_and_target(self):
with tempfile.TemporaryDirectory() as tmp:
sink = os.path.join(tmp, "audit.jsonl")
result = self._run(admin(), sink)
self.assertTrue(result["audit"]["written"])
with open(sink, encoding="utf-8") as handle:
record = json.loads(handle.read().strip())
self.assertEqual(
record["action"], sanctioned_restart.ACTION_RESTART_NAMESPACE
)
self.assertEqual(record["target"]["namespace"], NAMESPACE)
self.assertEqual(record["target"]["mode"], "restart")
self.assertEqual(record["result"], console_audit.RESULT_ALLOWED)
self.assertEqual(record["actor"]["subject"], "[email protected]")
self.assertFalse(record["metadata"]["process_kill_executed"])
def test_denied_attempt_is_audited_too(self):
with tempfile.TemporaryDirectory() as tmp:
sink = os.path.join(tmp, "audit.jsonl")
self._run(viewer(), sink)
with open(sink, encoding="utf-8") as handle:
record = json.loads(handle.read().strip())
self.assertEqual(record["result"], console_audit.RESULT_DENIED)
self.assertEqual(
record["reason_code"], sanctioned_restart.DENY_UNAUTHORIZED
)
def test_restart_audit_uses_break_glass_retention(self):
action = console_authz.get_action(
sanctioned_restart.ACTION_RESTART_NAMESPACE
)
self.assertEqual(
console_audit.retention_class_for(action),
console_audit.RETENTION_BREAK_GLASS,
)
class TestRegistrySurface(unittest.TestCase):
"""AC5: the console surfaces the control, still disabled, with no kill."""
def test_registry_exposes_both_actions_disabled(self):
registry = gated_actions.load_action_registry()
for action_id in (
sanctioned_restart.ACTION_RESTART_NAMESPACE,
sanctioned_restart.ACTION_RELOAD_NAMESPACE,
):
with self.subTest(action=action_id):
action = registry.get(action_id)
self.assertIsNotNone(action)
self.assertFalse(action.enabled)
def test_registry_preview_names_the_namespace_target(self):
preview = gated_actions.preview_action(
sanctioned_restart.ACTION_RESTART_NAMESPACE, namespace=NAMESPACE
)
target = preview["mutation_ledger"][0]["target"]
self.assertIn(NAMESPACE, target)
self.assertFalse(preview["enabled"])
def test_registry_attempt_fails_closed(self):
result = gated_actions.attempt_action(
sanctioned_restart.ACTION_RESTART_NAMESPACE, namespace=NAMESPACE
)
self.assertFalse(result["success"])
if __name__ == "__main__":
unittest.main()
+28
View File
@@ -236,6 +236,34 @@ _ACTION_SPECS: tuple[ConsoleAction, ...] = (
phase=3,
summary="Remove a remote feature branch.",
),
# #642: sanctioned daemon lifecycle. These exist so operators have an
# audited path off `pkill -f mcp_server.py` (#630). Restart drops every
# in-flight request on a namespace, so it carries the same dual-control and
# break-glass weight as a merge; reload drains first and is privileged but
# not destructive. Neither ever exposes a raw kill: execution is handed to
# a host supervisor by ``webui.sanctioned_restart``.
ConsoleAction(
action_id="system.reload_namespace",
task_key="reload_namespace",
action_class=CLASS_PRIVILEGED,
minimum_role=CONTROLLER,
requires_confirmation=True,
dual_control=False,
break_glass=False,
phase=2,
summary="Gracefully reload one MCP namespace via the host supervisor.",
),
ConsoleAction(
action_id="system.restart_namespace",
task_key="restart_namespace",
action_class=CLASS_DESTRUCTIVE,
minimum_role=ADMIN,
requires_confirmation=True,
dual_control=True,
break_glass=True,
phase=2,
summary="Restart one MCP namespace via the host supervisor.",
),
)
ACTIONS: dict[str, ConsoleAction] = {a.action_id: a for a in _ACTION_SPECS}
+13
View File
@@ -110,6 +110,8 @@ def _format_target(action_id: str, params: dict[str, Any]) -> str:
)
if action_id == "create_issue":
return f"issue {params.get('title', '?')!r}"
if action_id in {"system.restart_namespace", "system.reload_namespace"}:
return f"MCP namespace {params.get('namespace', '?')!r}"
return "unspecified"
@@ -165,6 +167,17 @@ def build_action_registry() -> ActionRegistry:
"gitea_create_issue_comment", "Post a PR review thread comment."),
("close_pr", "Close PR", "close_pr", "gitea_edit_pr",
"Close a pull request without merge."),
# #642: the sanctioned replacement for the forbidden manual daemon-kill
# recovery path (#630). The "tool" is a host supervisor hook, not an MCP
# call — the console never signals a process. Preview and gating live in
# ``webui.sanctioned_restart``; these stay disabled like every other
# registry entry.
("system.reload_namespace", "Reload MCP namespace", "reload_namespace",
"host.supervisor_reload",
"Gracefully reload one MCP namespace via the host supervisor."),
("system.restart_namespace", "Restart MCP namespace",
"restart_namespace", "host.supervisor_restart",
"Restart one MCP namespace via the host supervisor."),
)
actions = tuple(
GatedAction(
+613
View File
@@ -0,0 +1,613 @@
"""Sanctioned MCP restart and graceful reload controls (#642, Phase 2).
Sessions have historically recovered MCP connectivity by killing the host
daemon (``pkill -f mcp_server.py``, #630). That path stays forbidden: it kills
every namespace on the host, contaminates the surviving session, and leaves no
audit trail. This module is the sanctioned replacement.
A restart is modelled as a *gated action*, never as a command:
1. **Capability** the console action resolves through ``console_authz``
against ``task_capability_map``, so the console cannot invent an authority
the MCP layer does not already define.
2. **Preview** :func:`build_restart_preview` renders a mutation ledger and
the exact confirmation phrase. It never returns a shell command.
3. **Confirmation** the operator echoes a phrase naming the exact namespace
and mode. A phrase for one namespace never authorizes another.
4. **Operator authorization** host daemon maintenance is authorized out of
band through the environment (#630, and #710 finding F1: a worker session
cannot set an env var for an already-running daemon, so this cannot be
self-asserted the way a tool argument could).
5. **Execution** :func:`execute_restart` never spawns a process. Once every
gate passes it hands the request to the configured host-managed restart
hook; with no hook configured it fails closed.
6. **Health recheck** :func:`verify_post_restart_health` requires live
client-namespace probe evidence before any post-restart clean claim.
Manual ``pkill`` remains forbidden and is classified as contamination by
:func:`classify_restart_command`, which blocks clean claims (#630 AC3).
This module performs no I/O beyond reading its own environment configuration,
imports no MCP client, and holds no credential.
"""
from __future__ import annotations
import os
from dataclasses import asdict, dataclass
from typing import Any
import mcp_namespace_health
import runtime_recovery_guard
from webui import console_audit, console_authz
# --- Operations -------------------------------------------------------------
MODE_RESTART = "restart"
MODE_RELOAD = "reload"
MODES: tuple[str, ...] = (MODE_RESTART, MODE_RELOAD)
ACTION_RESTART_NAMESPACE = "system.restart_namespace"
ACTION_RELOAD_NAMESPACE = "system.reload_namespace"
ACTION_FOR_MODE: dict[str, str] = {
MODE_RESTART: ACTION_RESTART_NAMESPACE,
MODE_RELOAD: ACTION_RELOAD_NAMESPACE,
}
# Namespaces the console may target. An unlisted name fails closed rather than
# being passed through to a host hook.
KNOWN_NAMESPACES: tuple[str, ...] = tuple(
sorted(
set(mcp_namespace_health.DEFAULT_NAMESPACES)
| {"gitea-author", "gitea-reviewer", "gitea-merger",
"gitea-reconciler", "gitea-controller"}
)
)
# Scope tokens that would mean "everything at once". Explicit non-goal: the
# console never offers a fleet-wide restart, because that is the blast radius
# `pkill -f mcp_server.py` already had.
_FLEET_TOKENS = frozenset({"*", "all", "fleet", "any", ""})
# --- Environment configuration ----------------------------------------------
# Read server-side only; the value is an opaque host hook reference (e.g. a
# launchd label), never a command line, and is never rendered to a client.
RESTART_HOOK_ENV = "GITEA_SANCTIONED_RESTART_HOOK"
# --- Reason codes -----------------------------------------------------------
DENY_UNKNOWN_MODE = "unknown_mode"
DENY_UNKNOWN_NAMESPACE = "unknown_namespace"
DENY_FLEET_SCOPE = "fleet_scope_not_permitted"
DENY_UNAUTHORIZED = "unauthorized"
DENY_CONFIRMATION_MISSING = "confirmation_required"
DENY_CONFIRMATION_MISMATCH = "confirmation_mismatch"
DENY_OPERATOR_AUTHORIZATION = "operator_authorization_missing"
DENY_HOOK_NOT_CONFIGURED = "restart_hook_not_configured"
DENY_CONTAMINATED_RUNTIME = "contaminated_runtime"
ALLOW_HOST_ACTION_REQUIRED = "host_action_required"
# Post-restart verification outcomes.
HEALTH_CLEAN = "clean"
HEALTH_UNPROVEN = "unproven"
HEALTH_UNHEALTHY = "unhealthy"
def _clean(value: Any) -> str:
return str(value or "").strip()
# --- Mutation ledger --------------------------------------------------------
@dataclass(frozen=True)
class RestartLedgerEntry:
"""One planned step, shown before anything is asked of the host."""
sequence: int
step: str
summary: str
executes_process_kill: bool = False
def _mutation_ledger(namespace: str, mode: str) -> tuple[RestartLedgerEntry, ...]:
if mode == MODE_RELOAD:
middle = RestartLedgerEntry(
sequence=2,
step="host_graceful_reload",
summary=(
f"Ask the configured host supervisor to reload {namespace} "
"in place, draining in-flight requests. The console does not "
"signal the process itself."
),
)
else:
middle = RestartLedgerEntry(
sequence=2,
step="host_restart_hook",
summary=(
f"Ask the configured host supervisor to restart {namespace}. "
"The console never sends a signal and never runs a kill."
),
)
return (
RestartLedgerEntry(
sequence=1,
step="quiesce",
summary=(
f"Stop admitting new gated mutations for {namespace} and "
"record the intent before anything restarts."
),
),
middle,
RestartLedgerEntry(
sequence=3,
step="health_recheck",
summary=(
f"Re-probe {namespace} through the live client namespace and "
"prove the required tool is callable again."
),
),
RestartLedgerEntry(
sequence=4,
step="audit",
summary=(
"Append actor, target namespace, mode, and result to the "
"console audit log."
),
),
)
# --- Confirmation -----------------------------------------------------------
def confirmation_phrase(namespace: str, mode: str) -> str:
"""Exact phrase an operator must echo, naming the namespace and mode.
Binding the namespace into the phrase is the point: a confirmation typed
for ``gitea-author`` cannot be replayed against ``gitea-merger``.
"""
return f"{_clean(mode)} {_clean(namespace)}"
def confirmation_matches(
namespace: str, mode: str, confirmation: str | None
) -> bool:
"""Compare *confirmation* to the required phrase (exact, whitespace-trimmed)."""
return _clean(confirmation) == confirmation_phrase(namespace, mode)
# --- Scope validation -------------------------------------------------------
def _validate_scope(namespace: str, mode: str) -> tuple[str, str] | None:
"""Return ``(reason_code, detail)`` when the scope is refused."""
ns = _clean(namespace)
md = _clean(mode)
if md not in MODES:
return (
DENY_UNKNOWN_MODE,
f"Mode {md!r} is not one of {', '.join(MODES)}.",
)
if ns.lower() in _FLEET_TOKENS:
return (
DENY_FLEET_SCOPE,
(
"Fleet-wide restart is an explicit non-goal: it reproduces the "
"blast radius of `pkill -f mcp_server.py` (#630). Restart one "
"namespace at a time."
),
)
if ns not in KNOWN_NAMESPACES:
return (
DENY_UNKNOWN_NAMESPACE,
f"Namespace {ns!r} is not a known MCP namespace.",
)
return None
# --- Host hook --------------------------------------------------------------
def restart_hook(env: dict[str, str] | None = None) -> dict[str, Any]:
"""Report the configured host-managed restart hook.
The hook is a reference the *host* resolves (a supervisor label), not a
command this process runs. ``configured=False`` fails restart closed.
"""
source = env if env is not None else os.environ
reference = _clean(source.get(RESTART_HOOK_ENV))
return {
"configured": bool(reference),
"reference": reference or None,
"source": RESTART_HOOK_ENV if reference else None,
"self_assertable": False,
"console_executes_process": False,
}
# --- Preview ----------------------------------------------------------------
def build_restart_preview(
namespace: str,
mode: str = MODE_RESTART,
*,
principal: console_authz.Principal | None = None,
env: dict[str, str] | None = None,
) -> dict[str, Any]:
"""Render the dry-run preview for a restart/reload request.
Read-only: no authorization is granted, no host is contacted, and the
result never contains a shell command.
"""
ns = _clean(namespace)
md = _clean(mode)
action_id = ACTION_FOR_MODE.get(md, ACTION_RESTART_NAMESPACE)
action = console_authz.get_action(action_id)
decision = console_authz.authorize(action_id, principal)
scope_error = _validate_scope(ns, md)
hook = restart_hook(env)
operator = runtime_recovery_guard.operator_authorization(env)
return {
"action_id": action_id,
"namespace": ns,
"mode": md,
"scope_valid": scope_error is None,
"scope_reason_code": scope_error[0] if scope_error else None,
"scope_detail": scope_error[1] if scope_error else None,
"required_role": action.minimum_role if action else None,
"required_permission": action.mcp_permission if action else None,
"action_class": action.action_class if action else None,
"dual_control": action.dual_control if action else True,
"break_glass": action.break_glass if action else True,
"requires_confirmation": True,
"confirmation_phrase": confirmation_phrase(ns, md),
"mutation_ledger": [asdict(entry) for entry in _mutation_ledger(ns, md)],
"authorization": decision.to_dict(),
"operator_authorization": operator,
"restart_hook": hook,
"execution_enabled": False,
"raw_process_kill_exposed": False,
"known_namespaces": list(KNOWN_NAMESPACES),
"post_restart_verification_required": True,
}
# --- Gate -------------------------------------------------------------------
def assess_restart_request(
namespace: str,
mode: str = MODE_RESTART,
*,
principal: console_authz.Principal | None = None,
confirmation: str | None = None,
contamination_marker: dict[str, Any] | None = None,
env: dict[str, str] | None = None,
) -> dict[str, Any]:
"""Decide whether a restart request may proceed to the host hook.
Every gate must pass. The first failure wins and is reported with a stable
reason code; a pass never means "restarted", only "may be handed to the
configured host hook".
"""
ns = _clean(namespace)
md = _clean(mode)
action_id = ACTION_FOR_MODE.get(md, ACTION_RESTART_NAMESPACE)
preview = build_restart_preview(ns, md, principal=principal, env=env)
def refuse(reason_code: str, detail: str) -> dict[str, Any]:
return {
"allowed": False,
"gates_passed": False,
"reason_code": reason_code,
"detail": detail,
"action_id": action_id,
"namespace": ns,
"mode": md,
"preview": preview,
"execution_enabled": False,
}
scope_error = _validate_scope(ns, md)
if scope_error is not None:
return refuse(*scope_error)
# Authority is checked as an authorization decision, not an execution
# grant. ``for_execution=True`` asks "may the console perform this write?",
# and the answer here is permanently no: step 2 of the ledger is a request
# to the host supervisor, so the console's Phase 2 execution gate is not
# the relevant gate. Every branch below keeps ``execution_enabled`` False
# and :func:`execute_restart` never touches a process.
decision = console_authz.authorize(action_id, principal)
if not decision.allowed:
return refuse(DENY_UNAUTHORIZED, decision.detail)
if not _clean(confirmation):
return refuse(
DENY_CONFIRMATION_MISSING,
(
"Type the confirmation phrase "
f"{preview['confirmation_phrase']!r} to proceed."
),
)
if not confirmation_matches(ns, md, confirmation):
return refuse(
DENY_CONFIRMATION_MISMATCH,
(
"Confirmation does not name this namespace and mode; expected "
f"{preview['confirmation_phrase']!r}."
),
)
operator = preview["operator_authorization"]
if not operator["authorized"]:
return refuse(
DENY_OPERATOR_AUTHORIZATION,
(
"Host daemon maintenance requires out-of-band operator "
"authorization via "
f"{runtime_recovery_guard.OPERATOR_AUTHORIZATION_ENV}."
),
)
# #630's task-scoped gate deliberately lets a contaminated worker keep
# commenting and handing off. Restart is stricter and unconditional: a
# runtime already contaminated by a manual kill must be reconciled before
# it is restarted again, or the restart just launders the contamination.
if contamination_marker and not contamination_marker.get(
"cleared_by_reconciler"
):
return refuse(
DENY_CONTAMINATED_RUNTIME,
(
"A live contamination marker is present; clear it through the "
"reconciler path before restarting."
),
)
hook = preview["restart_hook"]
if not hook["configured"]:
return refuse(
DENY_HOOK_NOT_CONFIGURED,
(
"No host-managed restart hook is configured "
f"({RESTART_HOOK_ENV}). The console will not fall back to a "
"process kill."
),
)
return {
"allowed": True,
"gates_passed": True,
"reason_code": ALLOW_HOST_ACTION_REQUIRED,
"detail": (
"Every gate passed. The restart must be performed by the "
"configured host supervisor; the console does not signal the "
"process."
),
"action_id": action_id,
"namespace": ns,
"mode": md,
"preview": preview,
"execution_enabled": False,
"console_executes": False,
"console_active_phase": console_authz.ACTIVE_PHASE,
}
# --- Execution --------------------------------------------------------------
def execute_restart(
namespace: str,
mode: str = MODE_RESTART,
*,
principal: console_authz.Principal | None = None,
confirmation: str | None = None,
contamination_marker: dict[str, Any] | None = None,
env: dict[str, str] | None = None,
request_id: str | None = None,
session_id: str | None = None,
) -> dict[str, Any]:
"""Run every gate, audit the outcome, and hand off to the host.
This function never spawns a process, never sends a signal, and never
builds a command line. ``success`` is False in both directions: a refused
request is refused, and an authorized request still requires the host
supervisor to act.
"""
assessment = assess_restart_request(
namespace,
mode,
principal=principal,
confirmation=confirmation,
contamination_marker=contamination_marker,
env=env,
)
action_id = assessment["action_id"]
allowed = assessment["allowed"]
audit = console_audit.record_event(
action_id=action_id,
result=(
console_audit.RESULT_ALLOWED if allowed
else console_audit.RESULT_DENIED
),
principal=principal,
target={"namespace": assessment["namespace"], "mode": assessment["mode"]},
reason_code=assessment["reason_code"],
detail=assessment["detail"],
request_id=request_id,
session_id=session_id,
metadata={
"gates_passed": assessment["gates_passed"],
"process_kill_executed": False,
"post_restart_verification_required": True,
},
)
return {
"success": False,
"outcome": (
ALLOW_HOST_ACTION_REQUIRED if allowed else assessment["reason_code"]
),
"allowed": allowed,
"detail": assessment["detail"],
"namespace": assessment["namespace"],
"mode": assessment["mode"],
"action_id": action_id,
"process_kill_executed": False,
"host_hook": assessment["preview"]["restart_hook"],
"next_action": (
"Have the host supervisor perform the restart, then call "
"verify_post_restart_health with live client-namespace evidence "
"before claiming a clean session."
if allowed
else assessment["detail"]
),
"assessment": assessment,
"audit": audit,
}
# --- Contamination classification -------------------------------------------
def classify_restart_command(
command: str | None,
*,
mcp_pids: list[Any] | tuple[Any, ...] | None = None,
session_id: str | None = None,
remote: str | None = None,
role: str | None = None,
) -> dict[str, Any]:
"""Classify an operator-proposed recovery command (#630 AC2).
A manual ``pkill``/``kill`` of the MCP daemon is contamination, not a
restart. When contaminating, a durable marker is returned so downstream
gated mutations and clean claims fail closed.
"""
classification = runtime_recovery_guard.classify_recovery_command(
command, mcp_pids=mcp_pids
)
contaminating = bool(classification.get("contamination"))
marker = None
if contaminating:
marker = runtime_recovery_guard.build_contamination_record(
reason_class=(
classification.get("reason_class")
or runtime_recovery_guard.REASON_MANUAL_DAEMON_KILL
),
command_redacted=classification.get("redacted_command"),
session_id=session_id,
remote=remote,
role=role,
detail=(
"Manual daemon kill is forbidden; use the sanctioned "
f"{ACTION_RESTART_NAMESPACE} gated action instead."
),
)
return {
"contamination": contaminating,
"sanctioned": not contaminating and not classification.get("process_kill"),
"clean_claim_allowed": not contaminating,
"reason_class": classification.get("reason_class"),
"redacted_command": classification.get("redacted_command"),
"classification": classification,
"contamination_marker": marker,
"sanctioned_alternative": ACTION_RESTART_NAMESPACE,
}
# --- Post-restart health verification ---------------------------------------
def verify_post_restart_health(
namespace: str,
*,
probe_result: dict[str, Any] | None = None,
probe_source: str | None = None,
registered_tools: list[str] | tuple[str, ...] | None = None,
required_tool: str | None = None,
profile: str | None = None,
) -> dict[str, Any]:
"""Require live proof a namespace is callable before any clean claim (AC3).
Static registration is not proof and neither is an offline subprocess
probe: only ``probe_source=client_namespace`` evidence can clear a
post-restart session for mutations.
"""
ns = _clean(namespace)
health = mcp_namespace_health.classify_namespace_probe(
ns,
required_tool=required_tool,
registered_tools=registered_tools,
probe_result=probe_result,
profile=profile,
probe_source=probe_source,
)
healthy = bool(health.get("healthy"))
proven = bool(health.get("ide_namespace_proven"))
if healthy and proven:
status = HEALTH_CLEAN
elif healthy:
status = HEALTH_UNPROVEN
else:
status = HEALTH_UNHEALTHY
reasons = list(health.get("reasons") or [])
if status == HEALTH_UNPROVEN:
reasons.append(
"Namespace reported healthy without live client-namespace "
"evidence; a post-restart clean claim requires "
f"probe_source={mcp_namespace_health.PROBE_SOURCE_CLIENT!r}."
)
return {
"namespace": ns,
"status": status,
"healthy": healthy,
"ide_namespace_proven": proven,
"clean_claim_allowed": status == HEALTH_CLEAN,
"mutations_allowed": status == HEALTH_CLEAN,
"reasons": reasons,
"health": health,
}
# --- Policy surface ---------------------------------------------------------
def restart_policy() -> dict[str, Any]:
"""Machine-readable description of the sanctioned restart contract."""
return {
"policy_version": 1,
"modes": list(MODES),
"actions": [ACTION_RESTART_NAMESPACE, ACTION_RELOAD_NAMESPACE],
"known_namespaces": list(KNOWN_NAMESPACES),
"fleet_scope_permitted": False,
"console_executes_process_kill": False,
"raw_kill_exposed": False,
"requires_confirmation": True,
"confirmation_binds_namespace": True,
"operator_authorization_env": (
runtime_recovery_guard.OPERATOR_AUTHORIZATION_ENV
),
"restart_hook_env": RESTART_HOOK_ENV,
"manual_kill_classified_as": runtime_recovery_guard.CONTAMINATION_KIND,
"post_restart_clean_claim_requires": (
mcp_namespace_health.PROBE_SOURCE_CLIENT
),
"audit_required": True,
"silent_auto_restart_permitted": False,
}