Compare commits

..
Author SHA1 Message Date
sysadmin 6e6ca94338 fix(gate): stop classifying stale-runtime blocks as permission denials (Closes #897)
Stale-runtime and runtime-mode mutation refusals previously shared the
permission-denial channel, so permission_report claimed a missing op the
active profile already held and recommended gitea_activate_profile.
Typed blocker_kind payloads report reconnect-only recovery for staleness,
omit permission_report for non-permission gates, and fail closed when a
permission_report would invent a missing permission the profile holds.
2026-07-25 01:47:35 -04:00
21 changed files with 818 additions and 4632 deletions
-74
View File
@@ -23,7 +23,6 @@ import json
import os import os
import uuid import uuid
from dataclasses import dataclass, field from dataclasses import dataclass, field
from datetime import datetime, timezone
from typing import Any, Mapping, Sequence from typing import Any, Mapping, Sequence
from control_plane_db import ( from control_plane_db import (
@@ -739,46 +738,6 @@ def normalize_exclude_issue_numbers(
return sorted(out) return sorted(out)
def _claim_expires_at(claim: Any) -> datetime | None:
"""Parse a claim's ``expires_at``, or ``None`` when it is absent/malformed."""
if not isinstance(claim, Mapping):
return None
text = str(claim.get("expires_at") or "").strip()
if not text:
return None
if text.endswith("Z"):
text = text[:-1] + "+00:00"
try:
parsed = datetime.fromisoformat(text)
except ValueError:
return None
if parsed.tzinfo is None:
parsed = parsed.replace(tzinfo=timezone.utc)
return parsed.astimezone(timezone.utc)
def _drop_expired_claims(
claims: Mapping[tuple[str, int], dict[str, Any]],
*,
now: datetime | None = None,
) -> dict[tuple[str, int], dict[str, Any]]:
"""Claims minus those whose lease has already expired (#643).
The read-only mirror of ``expire_stale_leases``: the sweep marks such rows
``expired`` so they stop being returned as claims, and this reaches the same
view without writing. A claim with no parseable ``expires_at`` is **kept** —
an unreadable expiry is not evidence that work is free.
"""
moment = now or datetime.now(timezone.utc)
kept: dict[tuple[str, int], dict[str, Any]] = {}
for key, claim in (claims or {}).items():
expires_at = _claim_expires_at(claim)
if expires_at is not None and expires_at <= moment:
continue
kept[key] = claim
return kept
def candidate_set_fingerprint( def candidate_set_fingerprint(
candidates: Sequence[WorkCandidate], candidates: Sequence[WorkCandidate],
*, *,
@@ -867,22 +826,12 @@ def allocate_next_work(
exclude_issue_numbers: Sequence[int] | None = None, exclude_issue_numbers: Sequence[int] | None = None,
expected_candidate_set_fingerprint: str | None = None, expected_candidate_set_fingerprint: str | None = None,
allocation_mode: str | None = None, allocation_mode: str | None = None,
side_effect_free: bool = False,
) -> dict[str, Any]: ) -> dict[str, Any]:
"""Select and optionally reserve the next work unit via control-plane DB. """Select and optionally reserve the next work unit via control-plane DB.
*apply=False* (default): dry-run selection only — no lease/assignment. *apply=False* (default): dry-run selection only — no lease/assignment.
*apply=True*: atomic ``assign_and_lease`` for the selected candidate. *apply=True*: atomic ``assign_and_lease`` for the selected candidate.
*side_effect_free* (#643): a dry run that writes **nothing** to the
control-plane DB. A plain ``apply=False`` still registered a session row and
swept stale leases globally, so a caller advertising a read-only preview was
mutating on every call. Under this flag both writes are suppressed and stale
leases are instead filtered out of the claim map in memory, which yields the
same selection the sweep would have produced without persisting anything.
Incompatible with *apply* — the combination fails closed rather than
silently reserving.
*allocation_mode* (#840): ``cross_role`` (default for controller) inspects *allocation_mode* (#840): ``cross_role`` (default for controller) inspects
the complete queue and returns one authoritative selection naming the the complete queue and returns one authoritative selection naming the
required downstream role/profile/action. ``role_scoped`` keeps prior required downstream role/profile/action. ``role_scoped`` keeps prior
@@ -936,24 +885,7 @@ def allocate_next_work(
"allocation_mode": (allocation_mode or "").strip() or None, "allocation_mode": (allocation_mode or "").strip() or None,
} }
# A side-effect-free run may never reserve: reserving is a write, and the
# flag is the caller's assertion that this call writes nothing (#643).
if side_effect_free and apply:
return {
"success": False,
"outcome": OUTCOME_NO_SAFE,
"apply": True,
"reasons": [
"side_effect_free is incompatible with apply=True; an "
"assignment is a write (fail closed, #643)"
],
"skipped": [],
"assignment": None,
"substrate": "control_plane_db",
}
session_id = (session_id or "").strip() or f"alloc-{uuid.uuid4().hex[:12]}" session_id = (session_id or "").strip() or f"alloc-{uuid.uuid4().hex[:12]}"
if not side_effect_free:
try: try:
db.upsert_session( db.upsert_session(
session_id=session_id, session_id=session_id,
@@ -1021,12 +953,6 @@ def allocate_next_work(
"assignment": None, "assignment": None,
"substrate": "control_plane_db", "substrate": "control_plane_db",
} }
if side_effect_free:
# ``list_active_claims`` filters on status alone, so without the
# global sweep an already-expired lease would still read as a live
# claim and the preview would report work as taken that is free.
# Drop those in memory: same view the sweep produces, no write.
claims = _drop_expired_claims(claims)
try: try:
exclude_nums = normalize_exclude_issue_numbers(exclude_issue_numbers) exclude_nums = normalize_exclude_issue_numbers(exclude_issue_numbers)
-53
View File
@@ -1,53 +0,0 @@
# MCP restart classes and blast-radius permissions (#663)
This is the machine-enforced class matrix used by
`restart_coordinator.RESTART_CLASS_POLICIES`. It implements the narrower-first
recovery ladder from #655 and the authorization policy from #656, using the
path inventory from #657 and the impact coordinator from #658. Product and
delivery lineage: vision #652 and roadmap #653.
Unknown class names are denied. The coordinator requires both the class
permission and an eligible request role. Approval gates are additional: a
caller cannot turn a request permission into execution authority.
| Restart class | Required permission | Expected blast radius | Drain requirement | Approval requirement | Audit requirement | Recovery behavior |
|---|---|---|---|---|---|---|
| `client_reconnect` | `mcp.reconnect.client` | none | none | self service | class, actor, client namespace, reason, outcome | Reconnect only the caller's client transport. No daemon or peer work changes. |
| `session_reconnect` | `mcp.reconnect.session` | low | requesting-session safe point | self service | class, actor, session, reason, outcome | Rebind identity, capability, and workspace state for one session. |
| `worker_restart` | `mcp.restart.worker.request` | low | target worker | controller approval + automated gates | class, actor, worker, approval, scoped drain, outcome | Restart one worker after its own leases and mutations drain. |
| `role_runtime_restart` | `mcp.restart.role_runtime.request` | medium | target role runtime | controller approval + automated gates | class, actor, role namespace, approval, scoped drain, outcome | Restart and re-probe one role runtime; unrelated roles remain available. |
| `connector_restart` | `mcp.restart.connector.request` | medium | target connector | controller approval + automated gates | class, actor, connector, approval, scoped drain, outcome | Restart one connector while unrelated runtimes remain available. |
| `configuration_reload` | `mcp.reload.configuration.request` | low | mutation quiesce | controller approval + automated gates | class, actor, configuration revision, approval, outcome | Gracefully reload configuration without replacing the daemon. |
| `rolling_mcp_restart` | `mcp.restart.rolling.request` | medium | one instance at a time | controller approval + automated gates | class, actor, instance order, approval, per-instance drains, outcome | Drain, restart, verify, and restore each instance before advancing. |
| `full_mcp_restart` | `mcp.restart.full.request` | high | all sessions and mutations | controller approval + automated gates | class, actor, full impact, approval, full drain proof, outcome | Replace the complete MCP runtime only after a verified full drain. |
| `host_restart` | `mcp.restart.host.request` | high | all host work | controller approval + infrastructure operator | class, actor, host/change or incident id, approval, full drain proof, outcome | Hand off to infrastructure ownership and reconcile every runtime afterward. |
## Drain boundary
Only `full_mcp_restart` and `host_restart` set `full_drain_required=true`.
Reconnects and configuration reloads do not disrupt peer sessions. Worker,
role-runtime, and connector restarts evaluate only their explicitly named
target. Rolling restart drains one instance at a time. Missing required target
scope denies the request rather than silently widening it to a full restart.
## Permission and approval boundary
Author, reviewer, merger, and reconciler roles may self-request reconnects and
request scoped worker/role/connector/reload recovery. They cannot request
rolling, full, or host restart classes. Controller/operator/admin roles may
request the broader classes, while execution remains operator/admin-owned.
Controller approval is independently required for every class above a session
reconnect. Host restart additionally requires infrastructure-operator proof.
The MCP request tool derives class permissions from its authenticated runtime
role. It does not accept caller-supplied permissions. Controller and operator
authorization are read from the already-running daemon environment, never
from a request argument.
## Audit and failure behavior
Every impact audit and every console restart/reload audit includes a
`restart_class` field. The impact audit also includes the exact
`required_permission`. Unknown classes, missing permissions, ineligible roles,
missing approval, missing scoped targets, and incomplete inventory all deny
fail closed. Manual process kills remain forbidden and contaminating (#630).
+10 -67
View File
@@ -6,23 +6,11 @@ console (#642 / #652) can see the blast radius *before* concurrent LLM work is
disrupted. Uncoordinated restarts destroy in-flight author/reviewer/merger work disrupted. Uncoordinated restarts destroy in-flight author/reviewer/merger work
and give operators no way to see what they are about to break. and give operators no way to see what they are about to break.
This lands the coordinator + impact DTO + the MCP tool. It is the single 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 sanctioned entry point for restart evaluation post-#657 (which inventoried the
restart/reload/kill paths). 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
The **drain-proof hard gate now executes inside this tool** (#661, via PR #882): scope here.
an apply request (`dry_run=False`) is evaluated against a drain proof here and
denied when that proof is missing, expired, unclean, tampered with, or stale.
It is no longer a separate child operation. What remains a later child is only
the **execution** step — actually stopping and restoring a process. This tool
still never restarts anything: `apply_supported` is always `false` and
`restart_performed` is always `false`.
The coordinator now routes every request through the restart-class policy
matrix defined for #663. See
[`mcp-restart-classes.md`](./mcp-restart-classes.md) for permissions, expected
blast radius, scoped drain and approval requirements, audit fields, and
recovery behavior for all nine classes.
## Components ## Components
@@ -31,8 +19,7 @@ recovery behavior for all nine classes.
| `restart_coordinator.evaluate_restart_impact` | `restart_coordinator.py` | Pure classification: inventory → impact report DTO. No I/O, no restart. | | `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). | | `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). | | `ControlPlaneDB.list_sessions` | `control_plane_db.py` | Read-only session inventory (the process-level unit a restart kills). |
| `gitea_request_mcp_restart` | `gitea_mcp_server.py` | MCP tool: gathers inventory from the #613 DB, calls the coordinator, returns the report, and on `dry_run=False` runs the #661 drain-proof hard gate. Never restarts a process. | | `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. |
| `drain_proof.gate_apply_restart` | `drain_proof.py` | The #661 hard gate: verifies a drain proof against the current impact fingerprint, or records an authorized break-glass bypass. |
## Dimensions evaluated ## Dimensions evaluated
@@ -90,61 +77,17 @@ authorization is present.
```text ```text
gitea_request_mcp_restart(remote, host, org, repo, gitea_request_mcp_restart(remote, host, org, repo,
dry_run=True, request_override=False, dry_run=True, request_override=False,
session_id=None, limit=200, session_id=None, limit=200)
restart_class="full_mcp_restart",
target_session_id=None, target_role=None,
target_connector=None,
drain_proof_json=None,
request_break_glass=False)
``` ```
It **never restarts anything**: `apply_supported` is always `false` and Read-only, dry-run, and it **never restarts anything**. `apply_supported` is
`restart_performed` is always `false`. always `false`; passing `dry_run=False` performs no restart and reports that
apply is gated by a drain proof (a separate child).
### Dry-run versus apply
| Call | Behavior |
|------|----------|
| `dry_run=True` (default) | Read-only impact preview. No drain proof is required or consulted. |
| `dry_run=False` | The #661 drain-proof hard gate runs **in this tool**. The outcome is reported under `apply_gate` / `apply_authorized`; a denial also returns a durable `incident` descriptor. Still no restart. |
### Authorization ordering
An apply requires **both** authorizations, and they are independent:
1. **Restart-class authorization** (#663) — the requester's role and permissions
must allow the requested class, the class's approval requirement must be
satisfied, and any target-scoped class must name its target. Failing any of
these makes `allow_restart` `false`.
2. **Drain-proof gate** (#661) — a valid, unexpired, clean proof bound to the
current impact fingerprint, or an authorized break-glass.
`apply_authorized` is the conjunction: `gate.allow and allow_restart`. A clean
drain proof therefore cannot override a class or requester-role denial, and a
denied class never reports an authorized apply. `apply_gate` carries
`drain_gate_allow` and `restart_class_authorized` so a denial is attributable to
the authorization that produced it.
### Break-glass
Break-glass bypasses the **drain proof only** — never the restart-class matrix.
It is honoured solely when `request_break_glass` is set *and* the environment
carries `GITEA_BREAKGLASS_RESTART_AUTHORIZATION`; like operator override, the
tool argument expresses caller intent and cannot be self-asserted by a worker
session. `break_glass_requested` and `break_glass_authorized` are both reported,
so a bypass is never silent.
### Fail closed on apply
A missing, malformed, expired, unclean, tampered, or fingerprint-stale drain
proof denies the apply and returns an `incident` descriptor. An unknown restart
class denies before any of this. Ambiguity always denies.
## Audit ## Audit
Every evaluation carries an `audit_record` (event, coordinator version, verdict, Every evaluation carries an `audit_record` (event, coordinator version, verdict,
restart class, required permission, allow decision, blast radius, counts, allow decision, blast radius, counts, timestamp) so restart decisions are
timestamp) so restart decisions are
auditable. No secrets flow through the coordinator — session ids, pids, and auditable. No secrets flow through the coordinator — session ids, pids, and
profiles are operational metadata only. profiles are operational metadata only.
+9 -41
View File
@@ -94,7 +94,6 @@ already define, and a regression test asserts each mapping matches.
| `record_analytics_usage` | operator | gated_write | `runtime.record_analytics_usage` | Yes | No | No | 2 | | `record_analytics_usage` | operator | gated_write | `runtime.record_analytics_usage` | Yes | No | No | 2 |
| `system.reload_namespace` | controller | privileged | `runtime.reload_namespace` | Yes | No | No | 2 | | `system.reload_namespace` | controller | privileged | `runtime.reload_namespace` | Yes | No | No | 2 |
| `system.restart_namespace` | admin | destructive | `runtime.restart_namespace` | Yes | **Yes** | **Yes** | 2 | | `system.restart_namespace` | admin | destructive | `runtime.restart_namespace` | Yes | **Yes** | **Yes** | 2 |
| `initiate_workflow` | operator | gated_write | `gitea.read` | Yes | No | No | 2 |
**Dual control** means the acting principal may not be the sole authority: a **Dual control** means the acting principal may not be the sole authority: a
second distinct principal must confirm. **Break-glass** means the action is second distinct principal must confirm. **Break-glass** means the action is
@@ -113,12 +112,6 @@ by the console — both hand off to a host supervisor, and neither exposes a raw
process kill. See process kill. See
[`sanctioned-restart-controls.md`](sanctioned-restart-controls.md) (#642). [`sanctioned-restart-controls.md`](sanctioned-restart-controls.md) (#642).
`initiate_workflow` (#643) is operator-class because its outcome is a *claim*,
not a Gitea verdict. Requesting reviewer or merger work reserves that work
through the allocator; it does not grant the right to approve or merge, which
stays with the MCP role profile and its own capability gates. See
[`webui-requests.md`](webui-requests.md).
### Authorization decision ### Authorization decision
`authorize(action_id, principal, for_execution=False)` returns a decision `authorize(action_id, principal, for_execution=False)` returns a decision
@@ -133,24 +126,9 @@ record and **denies by default**. The deny reasons are closed and enumerated:
| `phase_not_active` | Execution requested for an action whose phase is not open. | | `phase_not_active` | Execution requested for an action whose phase is not open. |
| `allowed_preview_only` | Authorized — preview only, execution still disabled. | | `allowed_preview_only` | Authorized — preview only, execution still disabled. |
There is no implicit allow branch. There is no implicit allow branch. Even the allow result reports
`execution_enabled: false` while the console is in Phase 1, so no caller can
`execution_enabled` on the decision reports whether the action has a live read an allow as permission to mutate.
execution path at all, and is computed by `execution_wired(action)`. There are
exactly two ways to be wired:
1. the action's `phase` is at or below `ACTIVE_PHASE`; or
2. the action declares an `execution_env_flag` **and** that variable is set.
Every action that declares no flag therefore reports `execution_enabled: false`
while the console is in Phase 1, so no caller can read an allow as permission
to mutate. The per-action flag exists because raising `ACTIVE_PHASE` would
enable execution for every action of that phase at once, including ones whose
execution path is not implemented. One implemented action goes live on its own
flag instead of dragging its unimplemented phase-mates with it.
`initiate_workflow` is the only action that currently declares a flag
(`WEBUI_REQUESTS_EXECUTION`), and it stays denied until an operator sets it.
## Secret redaction ## Secret redaction
@@ -257,22 +235,13 @@ second one. The integration points are already wired and observable:
instead of adding a parallel check. instead of adding a parallel check.
- **`GET /api/console/security-model`** publishes the RBAC matrix, redaction - **`GET /api/console/security-model`** publishes the RBAC matrix, redaction
policy, and audit policy as JSON for operators and tests. policy, and audit policy as JSON for operators and tests.
- **`POST /api/v1/requests/preview` and `.../apply`** (#643) are the first
actions to use this model for a real execution path. Preview always returns a
decision and an audited `previewed` record; apply requires `confirm=true`,
emits `succeeded` or `denied`, and reserves work only through the allocator.
See [`webui-requests.md`](webui-requests.md).
A Phase 2 action must: use `execution_wired` rather than a private enable flag, To open Phase 2, a child issue must: raise `ACTIVE_PHASE`, implement the
implement the confirmation and dual-control flow the matrix already declares, confirmation and dual-control flow the matrix already declares, emit a
emit a `succeeded` or `failed` record alongside the `gitea_audit` mutation `succeeded` or `failed` record alongside the `gitea_audit` mutation record, and
record, and keep `viewer` unable to reach any of it. Turning on execution keep `viewer` unable to reach any of it. Turning on execution without the
without the confirmation flow contradicts a declared requirement and is a confirmation flow contradicts a declared requirement and is a review failure,
review failure, not a shortcut. not a shortcut.
Raising `ACTIVE_PHASE` remains the way to open a whole phase at once, and is
deliberately *not* what #643 did: an action-scoped opt-in cannot enable an
action whose execution path nobody wrote.
## Local-dev mode ## Local-dev mode
@@ -325,7 +294,6 @@ Until Phase 2 wires it, probe protection rests on network placement alone, as
| `WEBUI_ROLE_MAP` | unset | JSON subject → role map | | `WEBUI_ROLE_MAP` | unset | JSON subject → role map |
| `WEBUI_REQUIRE_PROBE_AUTH` | unset | Require auth for non-public probes | | `WEBUI_REQUIRE_PROBE_AUTH` | unset | Require auth for non-public probes |
| `WEBUI_CONSOLE_AUDIT_LOG` | unset | Append-only audit sink path | | `WEBUI_CONSOLE_AUDIT_LOG` | unset | Append-only audit sink path |
| `WEBUI_REQUESTS_EXECUTION` | unset | Opt in to `initiate_workflow` execution (#643) |
All are read server-side only. None is ever rendered into a page or returned by All are read server-side only. None is ever rendered into a page or returned by
an API. an API.
-160
View File
@@ -1,160 +0,0 @@
# Web console requests: intent preview and workflow initiation (#643)
**Phase 2. Preview is always live and always read-only. Initiation is wired but
denied until an operator opts in.**
Before this surface, starting role work meant pasting a prompt into a terminal
and trusting the operator to have checked the allocator first. Nothing enforced
that check, so two sessions could reach for the same issue and each believe it
was theirs. This page replaces the paste with a *request*: a desired role, an
issue or PR, and a stated intent, answered by an authorization decision and —
on confirmation — an exclusive assignment from the allocator.
| Concern | Module |
|---------|--------|
| Request model, preview, initiation | `webui/request_service.py` |
| Form and preview rendering | `webui/request_views.py` |
| Authorization | `webui/console_authz.py` (`initiate_workflow`) |
| Audit | `webui/console_audit.py` |
| Ownership substrate | `allocator_service.py` + `control_plane_db.py` |
## Surfaces
| Path | Method | Purpose |
|------|--------|---------|
| `/requests` | GET | Request form |
| `/requests` | POST | Render an intent preview. **Never assigns.** |
| `/api/v1/requests/preview` | POST | Intent preview as JSON |
| `/api/v1/requests/apply` | POST | Initiate — confirmed, audited, allocator-owned |
The HTML form has no initiate button on purpose. Initiating requires a
confirmed POST to `/api/v1/requests/apply`, so a stray form submission cannot
reserve work as a side effect.
## The request
```json
{
"desired_role": "author",
"work_kind": "issue",
"work_number": 643,
"intent_summary": "implement request preview and initiation",
"remote": "prgs",
"org": "Scaled-Tech-Consulting",
"repo": "Gitea-Tools",
"expected_head_sha": null
}
```
`desired_role` is one of `author`, `reviewer`, `merger`, `reconciler`,
`controller`. `work_kind` is `issue` or `pr`. `remote`/`org`/`repo` default to
the first project in the registry when omitted; when neither the request nor
the registry resolves them, the request is rejected rather than pointed at some
other repository. `intent_summary` is required — it is what the audit record
states as the reason — and is truncated to 500 characters.
Parsing rejects rather than corrects. An unknown role, an unknown work kind, a
non-positive number, or a missing intent each return `400` with a `reason_code`
and the offending `field`.
## Preview
Five checks, each with its own verdict, reason code, and detail:
| Check | Passes when |
|-------|-------------|
| `authorization` | The console principal holds `operator` or above |
| `capability` | The desired role maps to a declared profile and MCP namespace |
| `lease_availability` | No active claim holds the work unit |
| `next_safe_action` | The allocator would independently select this exact work unit |
| `head_pin` | PR work resolves to a head SHA, and a supplied SHA still matches |
A preview also returns the role's `allowed_actions` and `prohibited_actions`
(from `allocator_service.ROLE_ACTIONS`), the `required_profile` and
`required_namespace` the work must run under, and a `correlation_id` that ties
the preview to its audit record and to any assignment that follows.
Preview is read-only in the strict sense: it calls the allocator with
`apply=false` and writes nothing but an audit line. An unauthorized principal
never reaches the allocator or the control-plane DB at all, so a denial cannot
be used to enumerate the queue.
## Initiation
`POST /api/v1/requests/apply` refuses in this order, and every refusal returns
before any assignment is attempted:
| Condition | Outcome | Status |
|-----------|---------|--------|
| Unparseable request | `invalid_request` | 400 |
| Not authorized, or execution not wired | `denied` | 403 |
| `confirm` not set | `denied` / `confirmation_required` | 409 |
| Work unit already claimed | `blocked` / `duplicate_assignment` | 409 |
| Allocator would select other work | `wait` / `not_next_safe_work` | 409 |
| Allocator declines on apply | `blocked` or `wait` | 409 |
| Evidence unavailable | `wait` / `evidence_unavailable` | 503 |
| Assigned | `assigned_work` | 201 |
A success returns the assignment plus a `handoff` block naming the profile, the
namespace, and the actions that stay forbidden — enough for the operator to
continue in the right MCP namespace without guessing.
### Why apply runs the allocator twice
The allocator is the only source of exclusive ownership (#600 / #613), and it
selects work; it does not take orders. So `apply` runs a dry-run first and
proceeds only when the allocator would independently pick the requested work
unit. If it would not, the request reports `wait` and mutates nothing.
A request is therefore a *confirmation* of the allocator's decision, never an
override of it. The apply call carries the dry-run's
`candidate_set_fingerprint` as a CAS pin (#776), so a queue that changed
between the two calls fails closed rather than assigning against a stale view.
The result is checked again on the way out: an assignment naming a different
work unit is not read as success.
### Fail-closed defaults
- An unreadable control-plane DB denies. It is never treated as "nothing holds
this work unit".
- An incomplete queue inventory denies (#758). Ranking a partial candidate set
can select the wrong work.
- An allocator that raises denies.
- PR work with no resolvable head SHA denies; a supplied SHA that no longer
matches denies with `head_moved`.
## Enabling initiation
Execution is wired off. Set `WEBUI_REQUESTS_EXECUTION=1` to enable it for the
`initiate_workflow` action only — see
[`webui-authz-audit.md`](webui-authz-audit.md) for why this is an
action-scoped flag rather than a phase bump. With the variable unset, `apply`
returns `403` with `reason_code: unauthorized` no matter who asks.
Enabling execution does **not** enable approvals or merges. Those are phase 3
console actions and remain forbidden in every path here; the console reserves
work and hands off, and the MCP role profile enforces what that role may then
do.
## Audit
Every preview and every apply emits a console audit record (schema in
[`webui-authz-audit.md`](webui-authz-audit.md)):
| Event | `result` |
|-------|----------|
| Preview | `previewed` |
| Refusal at any stage | `denied` |
| Assignment created | `succeeded` |
`correlation.request_id` carries the request's `correlation_id`, and a
successful record's `metadata` carries `assignment_id` and `lease_id`, so an
assignment can be traced back to the intent that produced it. The operator's
`intent_summary` travels in `metadata` and passes through the standard
redaction pass before persistence like every other field.
## Non-goals
- No browser-initiated approve or merge, in this phase or any other.
- No bypass of allocator exclusive ownership; no self-selection of work.
- No auto-start from raw monitoring incidents (#612 stays downstream).
+299 -127
View File
@@ -9552,15 +9552,13 @@ def gitea_edit_pr(
if closing: if closing:
gate_reasons = _profile_operation_gate("gitea.pr.close") gate_reasons = _profile_operation_gate("gitea.pr.close")
if gate_reasons: if gate_reasons:
return { return _build_operation_gate_refusal(
"success": False, "gitea.pr.close",
"performed": False, gate_reasons,
"pr_number": pr_number, pr_number=pr_number,
"requested_state": "closed", requested_state="closed",
"required_permission": "gitea.pr.close", required_permission="gitea.pr.close",
"reasons": gate_reasons, )
"permission_report": _permission_block_report("gitea.pr.close"),
}
h, o, r = _resolve(remote, host, org, repo) h, o, r = _resolve(remote, host, org, repo)
auth = _auth(h) auth = _auth(h)
@@ -13823,13 +13821,17 @@ def gitea_view_issue(
def _permission_block_report(required_operation: str, def _permission_block_report(required_operation: str,
identity: str | None = None) -> dict: identity: str | None = None) -> dict:
"""Structured, LLM-safe explanation of a permission denial (#142). """Structured, LLM-safe explanation of a permission denial (#142, #897).
Built only after a gate has already refused; it adds guidance to the Built only after a gate has already refused; it adds guidance to the
refusal and never widens any permission, performs network I/O, or refusal and never widens any permission, performs network I/O, or
raises (fail-soft: degrades to a minimal fail-closed report). Names raises (fail-soft: degrades to a minimal fail-closed report). Names
configured profiles only never auth references, tokens, endpoint configured profiles only never auth references, tokens, endpoint
URLs, or keychain IDs. URLs, or keychain IDs.
#897: never fabricate a missing permission when the active profile
already allows the operation. That path is a diagnostic defect (the
refusal was not a permission denial), not a cue to switch profiles.
""" """
report = { report = {
"requested_operation": required_operation, "requested_operation": required_operation,
@@ -13841,6 +13843,7 @@ def _permission_block_report(required_operation: str,
"matching_configured_profiles": [], "matching_configured_profiles": [],
"runtime_switching_supported": False, "runtime_switching_supported": False,
"different_mcp_namespace_required": True, "different_mcp_namespace_required": True,
"diagnostic_defect": False,
"exact_safe_next_action": ( "exact_safe_next_action": (
"Ask the operator to fix GITEA_MCP_CONFIG/GITEA_MCP_PROFILE; " "Ask the operator to fix GITEA_MCP_CONFIG/GITEA_MCP_PROFILE; "
"the active profile could not be resolved (fail closed)."), "the active profile could not be resolved (fail closed)."),
@@ -13855,6 +13858,32 @@ def _permission_block_report(required_operation: str,
report["active_allowed_operations"] = ( report["active_allowed_operations"] = (
profile.get("allowed_operations") or []) profile.get("allowed_operations") or [])
# #897: fail closed as a diagnostic defect when the active profile
# already holds the operation — callers must not invent "missing".
try:
holds, _hold_reason = gitea_config.check_operation(
required_operation,
profile.get("allowed_operations") or [],
profile.get("forbidden_operations") or [],
)
except Exception:
holds = False
if holds:
report["missing_permission"] = None
report["required_permission"] = required_operation
report["diagnostic_defect"] = True
report["different_mcp_namespace_required"] = False
report["exact_safe_next_action"] = (
"Diagnostic defect: the active profile already allows "
f"{required_operation}. This is not a permission denial — "
"inspect blocker_kind / reasons (stale-runtime or runtime-mode). "
"Do not call gitea_activate_profile or switch MCP sessions."
)
report["matching_configured_profiles"] = [
p for p in [profile.get("profile_name")] if p
]
return report
matching = [] matching = []
try: try:
config = gitea_config.load_config() or {} config = gitea_config.load_config() or {}
@@ -13903,6 +13932,205 @@ def _permission_block_report(required_operation: str,
return report return report
def _reason_is_stale_runtime(reason: str) -> bool:
"""True when *reason* is a master-parity / stale-daemon refusal (#897)."""
r = (reason or "").lower()
if not r:
return False
if "stale relative to live master" in r:
return True
if "server code is stale" in r:
return True
if "daemon is stale" in r:
return True
if "started at commit" in r and "workspace master is now" in r:
return True
if "mcp server started at" in r and "stale" in r:
return True
if "restart the server to load the current capability gates" in r:
return True
if "restart/reconnect before mutating" in r:
return True
return False
def _reason_is_runtime_mode(reason: str) -> bool:
"""True when *reason* is a stable-control / runtime-mode refusal (#897)."""
r = (reason or "").lower()
if not r:
return False
if _reason_is_stale_runtime(reason):
return False
if "runtime mode could not be assessed" in r:
return True
if "runtime mode is" in r:
return True
if "stable control runtime" in r:
return True
if "dev-test" in r and ("runtime" in r or "production" in r):
return True
if "development worktree" in r or "dev worktree" in r:
return True
if "launched from a 'branches/" in r or "launched from a \"branches/" in r:
return True
if "process-root / active-workspace alignment" in r:
return True
if "namespace" in r and "reproof" in r:
return True
return False
def _reason_is_permission(reason: str) -> bool:
"""True when *reason* is a genuine profile-permission denial (#897)."""
r = (reason or "").lower()
if not r:
return False
if _reason_is_stale_runtime(reason) or _reason_is_runtime_mode(reason):
return False
if "profile could not be resolved" in r:
return True
if "profile has no configured allowed operations" in r:
return True
if "profile forbids" in r:
return True
if "profile is not allowed to" in r:
return True
if "unrecognized forbidden operation" in r:
return True
return False
def _classify_operation_gate_reasons(reasons: list[str]) -> dict:
"""Partition gate reasons into stale / runtime-mode / permission (#897)."""
stale: list[str] = []
runtime_mode: list[str] = []
permission: list[str] = []
other: list[str] = []
for reason in reasons or []:
if _reason_is_stale_runtime(reason):
stale.append(reason)
elif _reason_is_runtime_mode(reason):
runtime_mode.append(reason)
elif _reason_is_permission(reason):
permission.append(reason)
else:
other.append(reason)
return {
"stale_runtime": stale,
"runtime_mode": runtime_mode,
"permission": permission,
"other": other,
}
def _stale_runtime_reconnect_action() -> str:
"""Sanctioned recovery for a stale daemon — reconnect only (#685/#897)."""
return (
"Reconnect the IDE/client MCP session so the server reloads at the "
"current master head. Do not call gitea_activate_profile or switch "
"MCP role sessions — profile switching does not clear a stale daemon."
)
def _build_operation_gate_refusal(
required_operation: str,
reasons: list[str],
**extra_fields,
) -> dict:
"""Structured gate refusal with typed blockers (#897).
Stale-runtime and runtime-mode refusals never attach a
``permission_report`` and never recommend profile switching. True
permission denials still get ``permission_report``. When both apply,
causes are reported separately under distinct fields.
"""
classified = _classify_operation_gate_reasons(reasons)
stale = classified["stale_runtime"]
runtime_mode = classified["runtime_mode"]
permission = classified["permission"]
other = classified["other"]
blocked: dict = {
"success": False,
"performed": False,
"reasons": list(reasons),
"mutation_performed": False,
"session_context_audit": session_ctx.mutation_context_audit_fields(),
"gate_reason_classes": {
"stale_runtime": list(stale),
"runtime_mode": list(runtime_mode),
"permission": list(permission),
"other": list(other),
},
}
if stale:
parity = _current_master_parity()
blocked["blocker_kind"] = "runtime_reconnect_required"
blocked["restart_required"] = True
blocked["stop_required"] = True
blocked["startup_head"] = parity.get("startup_head")
blocked["current_head"] = parity.get("current_head")
blocked["daemon_start_head"] = (
parity.get("daemon_start_head") or parity.get("startup_head")
)
blocked["local_head"] = (
parity.get("local_head") or parity.get("current_head")
)
blocked["live_remote_head"] = parity.get("live_remote_head")
blocked["live_stale"] = bool(parity.get("live_stale"))
blocked["live_known"] = bool(parity.get("live_known"))
blocked["exact_safe_next_action"] = _stale_runtime_reconnect_action()
if permission or other:
blocked["permission_block_reasons"] = list(permission) + list(other)
blocked["stale_runtime_reasons"] = list(stale)
# Never attach permission_report for a staleness refusal.
blocked.update(extra_fields)
return blocked
if runtime_mode:
blocked["blocker_kind"] = "runtime_mode_blocked"
blocked["restart_required"] = False
blocked["stop_required"] = True
blocked["exact_safe_next_action"] = (
"Real workflow mutations run only on the promoted stable control "
"runtime. Promote/reload the stable runtime; do not call "
"gitea_activate_profile or switch MCP role sessions to clear a "
"runtime-mode block."
)
if permission or other:
blocked["permission_block_reasons"] = list(permission) + list(other)
blocked["runtime_mode_reasons"] = list(runtime_mode)
blocked.update(extra_fields)
return blocked
# Pure permission (or unclassified-as-permission) denial.
blocked["blocker_kind"] = "permission_denied"
blocked["permission_report"] = _permission_block_report(required_operation)
blocked.update(extra_fields)
return blocked
def _permission_report_for_gate_reasons(
required_operation: str,
reasons: list[str] | None,
) -> dict | None:
"""Attach ``permission_report`` only for true permission denials (#897).
Call sites that historically always attached a permission report after
``_profile_operation_gate`` should use this so stale/runtime refusals
do not emit a fabricated missing-permission payload.
"""
if not reasons:
return None
classified = _classify_operation_gate_reasons(reasons)
if classified["stale_runtime"] or classified["runtime_mode"]:
return None
if not (classified["permission"] or classified["other"]):
return None
return _permission_block_report(required_operation)
def _role_for_operation(op: str) -> str | None: def _role_for_operation(op: str) -> str | None:
# Normalize op first # Normalize op first
try: try:
@@ -14079,7 +14307,7 @@ def _master_parity_block(op: str) -> list[str]:
def _profile_operation_gate(op: str) -> list[str]: def _profile_operation_gate(op: str) -> list[str]:
"""Profile permission check for a single gated operation (#126, #216, #420). """Profile permission check for a single gated operation (#126, #216, #420, #897).
Issue discussion comments are gated separately from the gitea.pr.* Issue discussion comments are gated separately from the gitea.pr.*
review/merge family: listing requires ``gitea.read``, creating requires review/merge family: listing requires ``gitea.read``, creating requires
@@ -14092,21 +14320,26 @@ def _profile_operation_gate(op: str) -> list[str]:
capability gate that has since been merged, and when the runtime itself is capability gate that has since been merged, and when the runtime itself is
not the promoted stable control runtime (#615) -- a dev/test or unknown not the promoted stable control runtime (#615) -- a dev/test or unknown
runtime holds production credentials but has not been promoted. runtime holds production credentials but has not been promoted.
#897: collect *all* independent refusal classes (stale, runtime-mode,
permission) rather than short-circuiting after the first. Callers that
only need a boolean still treat any non-empty list as blocked; typed
consumers (``_build_operation_gate_refusal``) can separate causes.
""" """
stale_reasons = _master_parity_block(op) reasons: list[str] = []
if stale_reasons: reasons.extend(_master_parity_block(op))
return stale_reasons reasons.extend(_runtime_mode_block(op))
runtime_reasons = _runtime_mode_block(op)
if runtime_reasons:
return runtime_reasons
try: try:
profile = get_profile() profile = get_profile()
except Exception as exc: except Exception as exc:
return [f"profile could not be resolved (fail closed): {_redact(str(exc))}"] reasons.append(
f"profile could not be resolved (fail closed): {_redact(str(exc))}"
)
return reasons
op_ok, op_reason = gitea_config.check_operation( op_ok, op_reason = gitea_config.check_operation(
op, profile["allowed_operations"], profile["forbidden_operations"]) op, profile["allowed_operations"], profile["forbidden_operations"])
if op_ok: if op_ok:
return [] return reasons
if _try_auto_switch_for_operation(op): if _try_auto_switch_for_operation(op):
try: try:
@@ -14114,17 +14347,26 @@ def _profile_operation_gate(op: str) -> list[str]:
op_ok, op_reason = gitea_config.check_operation( op_ok, op_reason = gitea_config.check_operation(
op, profile["allowed_operations"], profile["forbidden_operations"]) op, profile["allowed_operations"], profile["forbidden_operations"])
if op_ok: if op_ok:
return [] return reasons
except Exception as exc: except Exception as exc:
return [f"profile could not be resolved (fail closed): {_redact(str(exc))}"] reasons.append(
f"profile could not be resolved (fail closed): {_redact(str(exc))}"
)
return reasons
if op_reason == "no-allowed-operations": if op_reason == "no-allowed-operations":
return ["profile has no configured allowed operations (fail closed)"] reasons.append(
if op_reason == "forbidden": "profile has no configured allowed operations (fail closed)"
return [f"profile forbids '{op}'"] )
if op_reason == "invalid-forbidden-entry": elif op_reason == "forbidden":
return ["profile has an unrecognized forbidden operation entry (fail closed)"] reasons.append(f"profile forbids '{op}'")
return [f"profile is not allowed to {op}"] elif op_reason == "invalid-forbidden-entry":
reasons.append(
"profile has an unrecognized forbidden operation entry (fail closed)"
)
else:
reasons.append(f"profile is not allowed to {op}")
return reasons
def _mutation_config_authority_block(required_operation: str) -> dict | None: def _mutation_config_authority_block(required_operation: str) -> dict | None:
@@ -14344,10 +14586,14 @@ def _session_context_mutation_block(
def _profile_permission_block(required_operation: str, **extra_fields) -> dict | None: def _profile_permission_block(required_operation: str, **extra_fields) -> dict | None:
"""Structured permission denial for gated tools (#69, #142). """Structured operation-gate denial for gated tools (#69, #142, #897).
Returns a block dict when the active profile forbids *required_operation*, Returns a block dict when the active profile forbids *required_operation*,
or ``None`` when the gate passes. Never performs network I/O. the daemon is stale, or the runtime mode is not mutation-safe or
``None`` when the gate passes. Never performs network I/O.
#897: stale-runtime and runtime-mode refusals are typed
(``blocker_kind``) and never carry a ``permission_report``.
""" """
req_role = "reviewer" if any(required_operation.startswith(p) for p in ( req_role = "reviewer" if any(required_operation.startswith(p) for p in (
"gitea.pr.approve", "gitea.pr.merge", "gitea.pr.request_changes", "gitea.pr.review" "gitea.pr.approve", "gitea.pr.merge", "gitea.pr.request_changes", "gitea.pr.review"
@@ -14357,15 +14603,9 @@ def _profile_permission_block(required_operation: str, **extra_fields) -> dict |
reasons = _profile_operation_gate(required_operation) reasons = _profile_operation_gate(required_operation)
if reasons: if reasons:
blocked = { return _build_operation_gate_refusal(
"success": False, required_operation, reasons, **extra_fields
"performed": False, )
"reasons": reasons,
"permission_report": _permission_block_report(required_operation),
"session_context_audit": session_ctx.mutation_context_audit_fields(),
}
blocked.update(extra_fields)
return blocked
auth_block = _mutation_config_authority_block(required_operation) auth_block = _mutation_config_authority_block(required_operation)
if auth_block is not None: if auth_block is not None:
@@ -14494,20 +14734,14 @@ def gitea_acquire_reviewer_pr_lease(
"""Acquire a per-PR reviewer lease before review/merge mutations (#407).""" """Acquire a per-PR reviewer lease before review/merge mutations (#407)."""
read_block = _profile_operation_gate("gitea.read") read_block = _profile_operation_gate("gitea.read")
if read_block: if read_block:
return { return _build_operation_gate_refusal(
"success": False, "gitea.read", read_block, acquired=False
"acquired": False, )
"reasons": read_block,
"permission_report": _permission_block_report("gitea.read"),
}
comment_block = _profile_operation_gate("gitea.pr.comment") comment_block = _profile_operation_gate("gitea.pr.comment")
if comment_block: if comment_block:
return { return _build_operation_gate_refusal(
"success": False, "gitea.pr.comment", comment_block, acquired=False
"acquired": False, )
"reasons": comment_block,
"permission_report": _permission_block_report("gitea.pr.comment"),
}
# task=acquire_reviewer_pr_lease so verify_preflight_purity runs shared #604 # task=acquire_reviewer_pr_lease so verify_preflight_purity runs shared #604
# anti-stomp for the declared lease-acquire mutation inventory entry. # anti-stomp for the declared lease-acquire mutation inventory entry.
@@ -14623,20 +14857,14 @@ def gitea_acquire_merger_pr_lease(
""" """
read_block = _profile_operation_gate("gitea.read") read_block = _profile_operation_gate("gitea.read")
if read_block: if read_block:
return { return _build_operation_gate_refusal(
"success": False, "gitea.read", read_block, acquired=False
"acquired": False, )
"reasons": read_block,
"permission_report": _permission_block_report("gitea.read"),
}
comment_block = _profile_operation_gate("gitea.pr.comment") comment_block = _profile_operation_gate("gitea.pr.comment")
if comment_block: if comment_block:
return { return _build_operation_gate_refusal(
"success": False, "gitea.pr.comment", comment_block, acquired=False
"acquired": False, )
"reasons": comment_block,
"permission_report": _permission_block_report("gitea.pr.comment"),
}
merge_block = _profile_operation_gate("gitea.pr.merge") merge_block = _profile_operation_gate("gitea.pr.merge")
if merge_block: if merge_block:
return { return {
@@ -19375,14 +19603,12 @@ def gitea_update_pr_branch_by_merge(
# Permission: author branch push / PR mutation surface. # Permission: author branch push / PR mutation surface.
push_block = _profile_operation_gate("gitea.branch.push") push_block = _profile_operation_gate("gitea.branch.push")
if push_block: if push_block:
return { return _build_operation_gate_refusal(
"success": False, "gitea.branch.push",
"performed": False, push_block,
"mutation_allowed": False, mutation_allowed=False,
"reasons": push_block, role_kind=role,
"permission_report": _permission_block_report("gitea.branch.push"), )
"role_kind": role,
}
if role != "author": if role != "author":
pre = pr_sync_status.assess_update_pr_branch_preflight( pre = pr_sync_status.assess_update_pr_branch_preflight(
@@ -22343,17 +22569,12 @@ def gitea_request_mcp_restart(
request_override: bool = False, request_override: bool = False,
session_id: str | None = None, session_id: str | None = None,
limit: int = 200, limit: int = 200,
restart_class: str = "full_mcp_restart",
target_session_id: str | None = None,
target_role: str | None = None,
target_connector: str | None = None,
drain_proof_json: str | None = None, drain_proof_json: str | None = None,
request_break_glass: bool = False, request_break_glass: bool = False,
) -> dict: ) -> dict:
"""Evaluate a proposed MCP restart and return an impact preview (#658). """Evaluate a proposed MCP restart and return an impact preview (#658).
Central restart coordinator: resolves the requested restart class, gathers Central restart coordinator: gathers live control-plane state (sessions,
live control-plane state (sessions,
leases/locks, in-flight issue/PR work, mutations, worktrees) and returns a leases/locks, in-flight issue/PR work, mutations, worktrees) and returns a
blast-radius impact report with a ``safe`` / ``unsafe`` / ``override`` blast-radius impact report with a ``safe`` / ``unsafe`` / ``override``
verdict, so the console (#642/#652) and operators can see what a restart verdict, so the console (#642/#652) and operators can see what a restart
@@ -22367,16 +22588,7 @@ def gitea_request_mcp_restart(
only when ``request_break_glass`` is set *and* the environment carries only when ``request_break_glass`` is set *and* the environment carries
``GITEA_BREAKGLASS_RESTART_AUTHORIZATION``. Even an authorized gate performs ``GITEA_BREAKGLASS_RESTART_AUTHORIZATION``. Even an authorized gate performs
no restart here; actual execution is a further child. The gate outcome is no restart here; actual execution is a further child. The gate outcome is
reported under ``apply_gate``. reported under ``apply_gate`` / ``apply_authorized``.
``apply_authorized`` requires **both** authorizations to pass: the #661 drain
gate *and* the #663 restart-class matrix (``allow_restart``). They are
independent the drain gate proves the blast radius was drained and knows
nothing about whether this requester may request this class so a class the
matrix denied never reports an authorized apply. Break-glass bypasses the
drain proof only; it never bypasses the class matrix. ``apply_gate`` carries
``drain_gate_allow`` and ``restart_class_authorized`` so a denial is
attributable to the authorization that produced it.
Operator override authority is read from the process environment Operator override authority is read from the process environment
(``GITEA_OPERATOR_RESTART_OVERRIDE_AUTHORIZATION``), never self-asserted by (``GITEA_OPERATOR_RESTART_OVERRIDE_AUTHORIZATION``), never self-asserted by
@@ -22461,9 +22673,6 @@ def gitea_request_mcp_restart(
profile = get_profile() profile = get_profile()
profile_name = (profile.get("profile_name") or "").strip() or "session" profile_name = (profile.get("profile_name") or "").strip() or "session"
requester_role = (
profile.get("role_kind") or profile.get("role") or ""
).strip().lower()
sid = (session_id or "").strip() or f"{profile_name}-{os.getpid()}" sid = (session_id or "").strip() or f"{profile_name}-{os.getpid()}"
# Override authority is read from the environment only — a worker session # Override authority is read from the environment only — a worker session
@@ -22473,15 +22682,6 @@ def gitea_request_mcp_restart(
(os.environ.get("GITEA_OPERATOR_RESTART_OVERRIDE_AUTHORIZATION") or "").strip() (os.environ.get("GITEA_OPERATOR_RESTART_OVERRIDE_AUTHORIZATION") or "").strip()
) )
operator_override = bool(request_override and operator_authorized) operator_override = bool(request_override and operator_authorized)
controller_approved = bool(
(
os.environ.get("GITEA_CONTROLLER_RESTART_APPROVAL_AUTHORIZATION")
or ""
).strip()
)
requester_permissions = restart_coordinator.permissions_for_role(
requester_role
)
inventory = { inventory = {
"sessions": sessions, "sessions": sessions,
@@ -22496,14 +22696,6 @@ def gitea_request_mcp_restart(
operator_override=operator_override, operator_override=operator_override,
requesting_session_id=sid, requesting_session_id=sid,
dry_run=True, # coordinator is always analysis-only (#658) dry_run=True, # coordinator is always analysis-only (#658)
restart_class=restart_class,
requester_role=requester_role,
requester_permissions=requester_permissions,
controller_approved=controller_approved,
operator_authorized=operator_authorized,
target_session_id=target_session_id,
target_role=target_role,
target_connector=target_connector,
) )
payload = report.as_dict() payload = report.as_dict()
@@ -22515,9 +22707,6 @@ def gitea_request_mcp_restart(
payload["requesting_session_id"] = sid payload["requesting_session_id"] = sid
payload["operator_override_requested"] = bool(request_override) payload["operator_override_requested"] = bool(request_override)
payload["operator_override_authorized"] = operator_authorized payload["operator_override_authorized"] = operator_authorized
payload["controller_approval_authorized"] = controller_approved
payload["requester_role"] = requester_role
payload["requester_permissions"] = list(requester_permissions)
# Actual restart execution remains a further child; this tool never restarts # Actual restart execution remains a further child; this tool never restarts
# a process. What #661 adds is the *hard gate*: an apply request (dry_run # a process. What #661 adds is the *hard gate*: an apply request (dry_run
# False) must present a valid, unexpired, clean drain proof, or it is denied # False) must present a valid, unexpired, clean drain proof, or it is denied
@@ -22555,25 +22744,8 @@ def gitea_request_mcp_restart(
gate_payload["reasons"] = [proof_parse_error] + list( gate_payload["reasons"] = [proof_parse_error] + list(
gate_payload.get("reasons") or [] gate_payload.get("reasons") or []
) )
# The #663 restart-class matrix and the #661 drain gate are two
# independent authorizations, and an apply requires BOTH. ``gate.allow``
# proves only that the blast radius was drained — or that break-glass
# was authorized — and knows nothing about whether this requester may
# request this class at all. Conjoining them keeps a class the matrix
# denied from ever reporting an authorized apply, and keeps break-glass
# scoped to what it is for: bypassing the drain proof, never the
# least-privilege class matrix.
restart_class_authorized = bool(report.allow_restart)
gate_payload["drain_gate_allow"] = bool(gate.allow)
gate_payload["restart_class_authorized"] = restart_class_authorized
if not restart_class_authorized:
gate_payload["reasons"] = list(gate_payload.get("reasons") or []) + [
"restart class authorization denied; apply denied regardless of "
"drain proof or break-glass (fail closed, #663)",
*(report.authorization_reasons or []),
]
payload["apply_gate"] = gate_payload payload["apply_gate"] = gate_payload
payload["apply_authorized"] = bool(gate.allow and restart_class_authorized) payload["apply_authorized"] = gate.allow
payload["break_glass_requested"] = bool(request_break_glass) payload["break_glass_requested"] = bool(request_break_glass)
payload["break_glass_authorized"] = break_glass_authorized payload["break_glass_authorized"] = break_glass_authorized
# Even an authorized gate performs no restart here: execution is a later # Even an authorized gate performs no restart here: execution is a later
+14 -370
View File
@@ -28,12 +28,11 @@ from __future__ import annotations
from dataclasses import dataclass, field from dataclasses import dataclass, field
from datetime import datetime, timezone from datetime import datetime, timezone
from enum import Enum
from typing import Any, Mapping, Sequence from typing import Any, Mapping, Sequence
import lease_lifecycle import lease_lifecycle
COORDINATOR_VERSION = "1.1.0-issue-663" COORDINATOR_VERSION = "1.0.0-issue-658"
# Restart verdicts. Exactly the three the acceptance criteria name. # Restart verdicts. Exactly the three the acceptance criteria name.
VERDICT_SAFE = "safe" VERDICT_SAFE = "safe"
@@ -55,194 +54,6 @@ LEASE_FRESHNESS_LIVE = "active"
DEFAULT_SESSION_HEARTBEAT_STALE_SECONDS = 900 DEFAULT_SESSION_HEARTBEAT_STALE_SECONDS = 900
class RestartClass(str, Enum):
"""The only restart/recovery classes accepted by the coordinator."""
CLIENT_RECONNECT = "client_reconnect"
SESSION_RECONNECT = "session_reconnect"
WORKER_RESTART = "worker_restart"
ROLE_RUNTIME_RESTART = "role_runtime_restart"
CONNECTOR_RESTART = "connector_restart"
CONFIGURATION_RELOAD = "configuration_reload"
ROLLING_MCP_RESTART = "rolling_mcp_restart"
FULL_MCP_RESTART = "full_mcp_restart"
HOST_RESTART = "host_restart"
@dataclass(frozen=True)
class RestartClassPolicy:
"""Least-privilege policy for one :class:`RestartClass`."""
restart_class: RestartClass
required_permission: str
expected_blast_radius: str
drain_requirement: str
full_drain_required: bool
approval_requirement: str
audit_requirement: str
recovery_behavior: str
request_roles: tuple[str, ...]
execution_roles: tuple[str, ...]
def as_dict(self) -> dict[str, Any]:
return {
"restart_class": self.restart_class.value,
"required_permission": self.required_permission,
"expected_blast_radius": self.expected_blast_radius,
"drain_requirement": self.drain_requirement,
"full_drain_required": self.full_drain_required,
"approval_requirement": self.approval_requirement,
"audit_requirement": self.audit_requirement,
"recovery_behavior": self.recovery_behavior,
"request_roles": list(self.request_roles),
"execution_roles": list(self.execution_roles),
}
WORKER_ROLES = ("author", "reviewer", "merger", "reconciler")
CONTROL_ROLES = ("controller", "operator", "admin")
ALL_REQUEST_ROLES = WORKER_ROLES + CONTROL_ROLES
RESTART_CLASS_POLICIES: dict[RestartClass, RestartClassPolicy] = {
RestartClass.CLIENT_RECONNECT: RestartClassPolicy(
RestartClass.CLIENT_RECONNECT,
"mcp.reconnect.client",
BLAST_NONE,
"none",
False,
"self_service",
"record class, actor, client namespace, reason, and outcome",
"Reconnect only the caller's client transport; no daemon or peer session changes.",
ALL_REQUEST_ROLES,
ALL_REQUEST_ROLES,
),
RestartClass.SESSION_RECONNECT: RestartClassPolicy(
RestartClass.SESSION_RECONNECT,
"mcp.reconnect.session",
BLAST_LOW,
"requesting_session_safe_point",
False,
"self_service",
"record class, actor, session id, reason, and outcome",
"Rebind identity, capability, and workspace state for one session.",
ALL_REQUEST_ROLES,
ALL_REQUEST_ROLES,
),
RestartClass.WORKER_RESTART: RestartClassPolicy(
RestartClass.WORKER_RESTART,
"mcp.restart.worker.request",
BLAST_LOW,
"target_worker",
False,
"controller_approval_and_automated_gates",
"record class, actor, target worker, approval, drain proof, and outcome",
"Restart one worker after its own lease and mutation scope is drained.",
ALL_REQUEST_ROLES,
("operator", "admin"),
),
RestartClass.ROLE_RUNTIME_RESTART: RestartClassPolicy(
RestartClass.ROLE_RUNTIME_RESTART,
"mcp.restart.role_runtime.request",
BLAST_MEDIUM,
"target_role_runtime",
False,
"controller_approval_and_automated_gates",
"record class, actor, role namespace, approval, drain proof, and outcome",
"Restart only the selected role runtime and then re-probe that namespace.",
ALL_REQUEST_ROLES,
("operator", "admin"),
),
RestartClass.CONNECTOR_RESTART: RestartClassPolicy(
RestartClass.CONNECTOR_RESTART,
"mcp.restart.connector.request",
BLAST_MEDIUM,
"target_connector",
False,
"controller_approval_and_automated_gates",
"record class, actor, connector id, approval, drain proof, and outcome",
"Restart one connector while unrelated role runtimes remain available.",
ALL_REQUEST_ROLES,
("operator", "admin"),
),
RestartClass.CONFIGURATION_RELOAD: RestartClassPolicy(
RestartClass.CONFIGURATION_RELOAD,
"mcp.reload.configuration.request",
BLAST_LOW,
"mutation_quiesce",
False,
"controller_approval_and_automated_gates",
"record class, actor, configuration revision, approval, and outcome",
"Gracefully reload configuration without replacing the daemon process.",
ALL_REQUEST_ROLES,
("operator", "admin"),
),
RestartClass.ROLLING_MCP_RESTART: RestartClassPolicy(
RestartClass.ROLLING_MCP_RESTART,
"mcp.restart.rolling.request",
BLAST_MEDIUM,
"one_instance_at_a_time",
False,
"controller_approval_and_automated_gates",
"record class, actor, instance order, approval, per-instance drains, and outcome",
"Drain, restart, verify, and restore one instance before advancing to the next.",
CONTROL_ROLES,
("operator", "admin"),
),
RestartClass.FULL_MCP_RESTART: RestartClassPolicy(
RestartClass.FULL_MCP_RESTART,
"mcp.restart.full.request",
BLAST_HIGH,
"all_sessions_and_mutations",
True,
"controller_approval_and_automated_gates",
"record class, actor, full impact report, approval, drain proof, and outcome",
"Stop and restore the complete MCP runtime only after a verified full drain.",
CONTROL_ROLES,
("operator", "admin"),
),
RestartClass.HOST_RESTART: RestartClassPolicy(
RestartClass.HOST_RESTART,
"mcp.restart.host.request",
BLAST_HIGH,
"all_host_work",
True,
"controller_approval_plus_infrastructure_operator",
"record class, actor, host, incident or change id, approval, drain proof, and outcome",
"Hand off to infrastructure ownership; reconcile every runtime after the host returns.",
("controller", "operator", "admin"),
("operator", "admin"),
),
}
def resolve_restart_class(value: RestartClass | str) -> RestartClass:
"""Resolve a restart class or fail closed for an unknown value."""
if isinstance(value, RestartClass):
return value
try:
return RestartClass(str(value).strip())
except ValueError as exc:
raise ValueError(f"unknown restart class {value!r}; deny (fail closed)") from exc
def restart_class_policy(value: RestartClass | str) -> RestartClassPolicy:
"""Return the canonical policy for *value*."""
return RESTART_CLASS_POLICIES[resolve_restart_class(value)]
def permissions_for_role(role: str | None) -> tuple[str, ...]:
"""Return request permissions granted to a workflow role by this policy."""
normalized = str(role or "").strip().lower()
return tuple(
policy.required_permission
for policy in RESTART_CLASS_POLICIES.values()
if normalized in policy.request_roles
)
def _utc_now() -> datetime: def _utc_now() -> datetime:
return datetime.now(timezone.utc) return datetime.now(timezone.utc)
@@ -264,7 +75,6 @@ class SessionImpact:
heartbeat_stale: bool heartbeat_stale: bool
is_requester: bool is_requester: bool
live: bool live: bool
connector: str | None = None
def as_dict(self) -> dict[str, Any]: def as_dict(self) -> dict[str, Any]:
return { return {
@@ -277,7 +87,6 @@ class SessionImpact:
"heartbeat_stale": self.heartbeat_stale, "heartbeat_stale": self.heartbeat_stale,
"is_requester": self.is_requester, "is_requester": self.is_requester,
"live": self.live, "live": self.live,
"connector": self.connector,
} }
@@ -296,7 +105,6 @@ class LeaseImpact:
disruptive: bool disruptive: bool
is_mutation: bool is_mutation: bool
is_critical_section: bool is_critical_section: bool
connector: str | None = None
def as_dict(self) -> dict[str, Any]: def as_dict(self) -> dict[str, Any]:
return { return {
@@ -311,7 +119,6 @@ class LeaseImpact:
"disruptive": self.disruptive, "disruptive": self.disruptive,
"is_mutation": self.is_mutation, "is_mutation": self.is_mutation,
"is_critical_section": self.is_critical_section, "is_critical_section": self.is_critical_section,
"connector": self.connector,
} }
@@ -320,13 +127,6 @@ class RestartImpactReport:
"""Impact preview DTO returned to the console / operator (#642/#652).""" """Impact preview DTO returned to the console / operator (#642/#652)."""
coordinator_version: str coordinator_version: str
restart_class: str
restart_policy: dict[str, Any]
policy_enforced: bool
permission_authorized: bool
role_authorized: bool
approval_satisfied: bool
authorization_reasons: list[str]
evaluated_at: str evaluated_at: str
dry_run: bool dry_run: bool
restart_performed: bool restart_performed: bool
@@ -353,13 +153,6 @@ class RestartImpactReport:
def as_dict(self) -> dict[str, Any]: def as_dict(self) -> dict[str, Any]:
return { return {
"coordinator_version": self.coordinator_version, "coordinator_version": self.coordinator_version,
"restart_class": self.restart_class,
"restart_policy": dict(self.restart_policy),
"policy_enforced": self.policy_enforced,
"permission_authorized": self.permission_authorized,
"role_authorized": self.role_authorized,
"approval_satisfied": self.approval_satisfied,
"authorization_reasons": list(self.authorization_reasons),
"evaluated_at": self.evaluated_at, "evaluated_at": self.evaluated_at,
"dry_run": self.dry_run, "dry_run": self.dry_run,
"restart_performed": self.restart_performed, "restart_performed": self.restart_performed,
@@ -413,7 +206,6 @@ def _classify_session(
requesting_session_id and session_id == requesting_session_id requesting_session_id and session_id == requesting_session_id
), ),
live=live, live=live,
connector=(str(row.get("connector") or "").strip() or None),
) )
@@ -466,7 +258,6 @@ def _classify_lease(row: Mapping[str, Any]) -> LeaseImpact:
disruptive=disruptive, disruptive=disruptive,
is_mutation=is_mutation, is_mutation=is_mutation,
is_critical_section=disruptive, is_critical_section=disruptive,
connector=(str(row.get("connector") or "").strip() or None),
) )
@@ -488,14 +279,6 @@ def evaluate_restart_impact(
requesting_session_id: str | None = None, requesting_session_id: str | None = None,
dry_run: bool = True, dry_run: bool = True,
session_heartbeat_stale_seconds: int = DEFAULT_SESSION_HEARTBEAT_STALE_SECONDS, session_heartbeat_stale_seconds: int = DEFAULT_SESSION_HEARTBEAT_STALE_SECONDS,
restart_class: RestartClass | str | None = None,
requester_role: str | None = None,
requester_permissions: Sequence[str] | None = None,
controller_approved: bool = False,
operator_authorized: bool = False,
target_session_id: str | None = None,
target_role: str | None = None,
target_connector: str | None = None,
) -> RestartImpactReport: ) -> RestartImpactReport:
"""Evaluate a proposed MCP restart and return an impact preview. """Evaluate a proposed MCP restart and return an impact preview.
@@ -518,61 +301,6 @@ def evaluate_restart_impact(
""" """
moment = now or _utc_now() moment = now or _utc_now()
reasons: list[str] = [] reasons: list[str] = []
authorization_reasons: list[str] = []
# ``None`` preserves the pre-#663 impact-only API for callers that have not
# yet been migrated. All MCP requests pass an explicit class and therefore
# take the fail-closed policy path.
policy_enforced = restart_class is not None
try:
resolved_class = resolve_restart_class(
restart_class or RestartClass.FULL_MCP_RESTART
)
policy = RESTART_CLASS_POLICIES[resolved_class]
unknown_class = False
except ValueError as exc:
resolved_class = None
policy = None
unknown_class = True
authorization_reasons.append(str(exc))
normalized_role = str(requester_role or "").strip().lower()
granted = {str(p).strip() for p in (requester_permissions or ())}
if policy_enforced and policy is not None:
permission_authorized = policy.required_permission in granted
role_authorized = normalized_role in policy.request_roles
if not permission_authorized:
authorization_reasons.append(
f"missing required permission {policy.required_permission!r}"
)
if not role_authorized:
authorization_reasons.append(
f"role {normalized_role or 'unknown'!r} may not request "
f"{policy.restart_class.value}"
)
elif unknown_class:
permission_authorized = False
role_authorized = False
else:
permission_authorized = True
role_authorized = True
if policy_enforced and policy is not None:
approval = policy.approval_requirement
if approval == "self_service":
approval_satisfied = True
elif approval == "controller_approval_plus_infrastructure_operator":
approval_satisfied = bool(controller_approved and operator_authorized)
else:
approval_satisfied = bool(controller_approved)
if not approval_satisfied:
authorization_reasons.append(
f"approval requirement not satisfied: {approval}"
)
elif unknown_class:
approval_satisfied = False
else:
approval_satisfied = True
inventory_complete = bool(inventory.get("inventory_complete", False)) inventory_complete = bool(inventory.get("inventory_complete", False))
incomplete_reasons = [str(r) for r in (inventory.get("incomplete_reasons") or [])] incomplete_reasons = [str(r) for r in (inventory.get("incomplete_reasons") or [])]
@@ -595,67 +323,15 @@ def evaluate_restart_impact(
] ]
lease_impacts = [_classify_lease(l) for l in leases_raw] lease_impacts = [_classify_lease(l) for l in leases_raw]
# Route impact through the selected class. Narrow classes never inherit a # Only *other* live sessions and live leases constitute blast radius: a
# full-runtime drain merely because unrelated work exists. # restart that would kill only the requesting session with no other work in
target_complete = True # flight is safe.
if resolved_class in {
RestartClass.CLIENT_RECONNECT,
RestartClass.SESSION_RECONNECT,
RestartClass.CONFIGURATION_RELOAD,
}:
scoped_sessions: list[SessionImpact] = []
scoped_leases: list[LeaseImpact] = []
elif resolved_class == RestartClass.WORKER_RESTART:
selected_session = (target_session_id or "").strip()
target_complete = bool(selected_session)
scoped_sessions = [
s for s in session_impacts if s.session_id == selected_session
]
scoped_leases = [
l for l in lease_impacts if l.session_id == selected_session
]
elif resolved_class == RestartClass.ROLE_RUNTIME_RESTART:
selected_role = (target_role or "").strip().lower()
target_complete = bool(selected_role)
scoped_sessions = [
s for s in session_impacts if str(s.role or "").lower() == selected_role
]
scoped_leases = [
l for l in lease_impacts if str(l.role or "").lower() == selected_role
]
elif resolved_class == RestartClass.CONNECTOR_RESTART:
selected_connector = (target_connector or "").strip()
target_complete = bool(selected_connector)
scoped_sessions = [
s for s in session_impacts if s.connector == selected_connector
]
scoped_leases = [
l for l in lease_impacts if l.connector == selected_connector
]
else:
scoped_sessions = list(session_impacts)
scoped_leases = list(lease_impacts)
if policy_enforced and not target_complete:
authorization_reasons.append(
f"target required for {resolved_class.value if resolved_class else 'unknown class'}"
)
other_live_sessions = [ other_live_sessions = [
s for s in scoped_sessions if s.live and not s.is_requester s for s in session_impacts if s.live and not s.is_requester
] ]
disruptive_leases = [l for l in scoped_leases if l.disruptive] disruptive_leases = [l for l in lease_impacts if l.disruptive]
critical_sections = [l for l in scoped_leases if l.is_critical_section] critical_sections = [l for l in lease_impacts if l.is_critical_section]
mutations = [l for l in scoped_leases if l.is_mutation] mutations = [l for l in lease_impacts if l.is_mutation]
terminal_lock_in_scope = (
terminal_lock
if resolved_class
not in {
RestartClass.CLIENT_RECONNECT,
RestartClass.SESSION_RECONNECT,
}
else None
)
affected_issues = sorted( affected_issues = sorted(
{ {
@@ -672,24 +348,9 @@ def evaluate_restart_impact(
} }
) )
disruptive = bool( disruptive = bool(disruptive_leases or other_live_sessions or terminal_lock)
disruptive_leases or other_live_sessions or terminal_lock_in_scope
)
authorization_ok = bool( if not inventory_complete:
not unknown_class
and permission_authorized
and role_authorized
and approval_satisfied
and target_complete
)
if policy_enforced and not authorization_ok:
verdict = VERDICT_UNSAFE
allow_restart = False
reasons.append("restart class authorization denied (fail closed)")
reasons.extend(authorization_reasons)
elif not inventory_complete:
verdict = VERDICT_UNSAFE verdict = VERDICT_UNSAFE
allow_restart = False allow_restart = False
reasons.append( reasons.append(
@@ -720,7 +381,7 @@ def evaluate_restart_impact(
f"{len(critical_sections)} critical section(s) in flight " f"{len(critical_sections)} critical section(s) in flight "
"(active lease with a live owner)" "(active lease with a live owner)"
) )
if terminal_lock_in_scope: if terminal_lock:
reasons.append("active terminal (merge) lock present") reasons.append("active terminal (merge) lock present")
override_would_allow = bool(inventory_complete and disruptive) override_would_allow = bool(inventory_complete and disruptive)
@@ -750,12 +411,6 @@ def evaluate_restart_impact(
audit_record = { audit_record = {
"event": "restart_impact_evaluated", "event": "restart_impact_evaluated",
"coordinator_version": COORDINATOR_VERSION, "coordinator_version": COORDINATOR_VERSION,
"restart_class": (
resolved_class.value if resolved_class else str(restart_class or "")
),
"required_permission": (
policy.required_permission if policy is not None else None
),
"evaluated_at": moment.isoformat(), "evaluated_at": moment.isoformat(),
"dry_run": dry_run, "dry_run": dry_run,
"operator_override": bool(operator_override), "operator_override": bool(operator_override),
@@ -769,15 +424,6 @@ def evaluate_restart_impact(
return RestartImpactReport( return RestartImpactReport(
coordinator_version=COORDINATOR_VERSION, coordinator_version=COORDINATOR_VERSION,
restart_class=(
resolved_class.value if resolved_class else str(restart_class or "")
),
restart_policy=policy.as_dict() if policy is not None else {},
policy_enforced=policy_enforced,
permission_authorized=permission_authorized,
role_authorized=role_authorized,
approval_satisfied=approval_satisfied,
authorization_reasons=authorization_reasons,
evaluated_at=moment.isoformat(), evaluated_at=moment.isoformat(),
dry_run=dry_run, dry_run=dry_run,
restart_performed=False, restart_performed=False,
@@ -794,11 +440,9 @@ def evaluate_restart_impact(
affected_issues=affected_issues, affected_issues=affected_issues,
affected_prs=affected_prs, affected_prs=affected_prs,
mutations=mutations, mutations=mutations,
terminal_lock=( terminal_lock=dict(terminal_lock)
dict(terminal_lock_in_scope) if isinstance(terminal_lock, Mapping)
if isinstance(terminal_lock_in_scope, Mapping) else terminal_lock,
else terminal_lock_in_scope
),
ack_state=ack_state, ack_state=ack_state,
prior_recovery_attempts=prior_recovery_attempts, prior_recovery_attempts=prior_recovery_attempts,
counts=counts, counts=counts,
-158
View File
@@ -7,7 +7,6 @@ import tempfile
import threading import threading
import unittest import unittest
from concurrent.futures import ThreadPoolExecutor, as_completed from concurrent.futures import ThreadPoolExecutor, as_completed
from datetime import datetime, timezone
from allocator_service import ( from allocator_service import (
OUTCOME_ASSIGNED, OUTCOME_ASSIGNED,
@@ -16,7 +15,6 @@ from allocator_service import (
OUTCOME_PREVIEW, OUTCOME_PREVIEW,
OUTCOME_WAIT, OUTCOME_WAIT,
WorkCandidate, WorkCandidate,
_drop_expired_claims,
allocate_next_work, allocate_next_work,
candidate_from_dict, candidate_from_dict,
classify_skip, classify_skip,
@@ -364,161 +362,5 @@ class AllocatorServiceTest(unittest.TestCase):
self.assertIn("unavailable", res["reasons"][0].lower()) self.assertIn("unavailable", res["reasons"][0].lower())
class SideEffectFreeAllocationTest(unittest.TestCase):
"""``side_effect_free`` dry runs write nothing to the control plane (#643).
A plain ``apply=False`` still called ``upsert_session`` and
``expire_stale_leases`` before the apply branch was consulted, so a caller
advertising a read-only preview mutated on every call — one unreferenced
session row per preview, plus a global lease sweep.
"""
def setUp(self) -> None:
self._tmp = tempfile.TemporaryDirectory()
self.db = ControlPlaneDB(os.path.join(self._tmp.name, "cp.sqlite3"))
def tearDown(self) -> None:
self._tmp.cleanup()
def _alloc(self, **kwargs):
defaults = dict(
db=self.db,
session_id="s-preview",
role="author",
remote="prgs",
org="org",
repo="repo",
candidates=[
WorkCandidate(kind="issue", number=643, labels=("status:ready",))
],
apply=False,
profile_name="prgs-author",
username="jcwalker3",
)
defaults.update(kwargs)
return allocate_next_work(**defaults)
def _session_ids(self) -> set[str]:
return {str(r.get("session_id")) for r in self.db.list_sessions()}
def test_side_effect_free_preview_writes_no_session_row(self):
before = self._session_ids()
result = self._alloc(side_effect_free=True)
self.assertEqual(result["outcome"], OUTCOME_PREVIEW)
self.assertEqual(self._session_ids(), before)
self.assertNotIn("s-preview", self._session_ids())
def test_plain_dry_run_still_registers_a_session(self):
# The default is unchanged for every existing caller.
self._alloc()
self.assertIn("s-preview", self._session_ids())
def test_repeated_previews_do_not_accumulate_rows(self):
for index in range(5):
self._alloc(side_effect_free=True, session_id=f"s-{index}")
self.assertEqual(self._session_ids(), set())
def test_side_effect_free_does_not_sweep_stale_leases(self):
self.db.upsert_session(session_id="owner", role="author", pid=1)
assigned = self.db.assign_and_lease(
session_id="owner",
role="author",
remote="prgs",
org="org",
repo="repo",
kind="issue",
number=999,
lease_ttl_seconds=-60, # already expired
)
self.assertEqual(assigned.outcome, "assigned")
self._alloc(side_effect_free=True)
# The expired row is still 'active' in the DB: nothing swept it.
statuses = {
r["lease_id"]: r["status"]
for r in self.db.list_leases(
remote="prgs", org="org", repo="repo",
statuses=("active", "expired"),
)
}
self.assertEqual(statuses.get(assigned.lease_id), "active")
def test_expired_claims_are_filtered_in_memory_so_work_stays_selectable(self):
"""The read-only mirror of the sweep: expired claims must not block."""
self.db.upsert_session(session_id="owner", role="author", pid=1)
self.db.assign_and_lease(
session_id="owner",
role="author",
remote="prgs",
org="org",
repo="repo",
kind="issue",
number=643,
lease_ttl_seconds=-60, # expired: must not withhold #643
)
result = self._alloc(side_effect_free=True)
self.assertEqual(result["outcome"], OUTCOME_PREVIEW)
self.assertEqual(result["selected"]["number"], 643)
def test_a_live_claim_still_withholds_the_work(self):
self.db.upsert_session(session_id="owner", role="author", pid=1)
self.db.assign_and_lease(
session_id="owner",
role="author",
remote="prgs",
org="org",
repo="repo",
kind="issue",
number=643,
lease_ttl_seconds=3600,
)
result = self._alloc(side_effect_free=True)
self.assertNotEqual(result["outcome"], OUTCOME_ASSIGNED)
self.assertNotEqual((result.get("selected") or {}).get("number"), 643)
def test_side_effect_free_with_apply_fails_closed(self):
result = self._alloc(side_effect_free=True, apply=True)
self.assertFalse(result["success"])
self.assertEqual(result["outcome"], OUTCOME_NO_SAFE)
self.assertIsNone(result["assignment"])
self.assertIn("incompatible with apply", result["reasons"][0])
# And it reserved nothing.
self.assertEqual(
self.db.list_leases(remote="prgs", org="org", repo="repo"), []
)
class DropExpiredClaimsTest(unittest.TestCase):
"""The in-memory expiry filter behind side-effect-free previews (#643)."""
def test_unparseable_expiry_is_kept_rather_than_assumed_free(self):
claims = {
("issue", 1): {"lease_id": "l1", "expires_at": "not-a-date"},
("issue", 2): {"lease_id": "l2"},
("issue", 3): {"lease_id": "l3", "expires_at": None},
}
self.assertEqual(_drop_expired_claims(claims), claims)
def test_expired_dropped_and_future_kept(self):
now = datetime(2026, 7, 25, 12, 0, tzinfo=timezone.utc)
claims = {
("issue", 1): {"expires_at": "2026-07-25T11:59:59+00:00"},
("issue", 2): {"expires_at": "2026-07-25T12:00:01+00:00"},
("issue", 3): {"expires_at": "2026-07-25T12:00:00+00:00"}, # boundary
}
kept = _drop_expired_claims(claims, now=now)
self.assertEqual(set(kept), {("issue", 2)})
def test_naive_and_zulu_timestamps_are_treated_as_utc(self):
now = datetime(2026, 7, 25, 12, 0, tzinfo=timezone.utc)
claims = {
("issue", 1): {"expires_at": "2026-07-25T11:00:00"}, # naive, past
("issue", 2): {"expires_at": "2026-07-25T13:00:00Z"}, # zulu, future
}
kept = _drop_expired_claims(claims, now=now)
self.assertEqual(set(kept), {("issue", 2)})
if __name__ == "__main__": if __name__ == "__main__":
unittest.main() unittest.main()
@@ -1,381 +0,0 @@
"""``apply_authorized`` requires BOTH authorizations (#886 review blocker B1).
The #663 restart-class matrix and the #661 drain-proof hard gate are independent
authorizations that first coexisted when PR #882 landed on master and PR #886
merged it into the restart-class branch. The union preserved both, but the apply
decision consulted only the drain gate::
payload["apply_authorized"] = gate.allow # pre-fix
so a clean drain proof or an authorized break-glass, which needs no proof at
all reported ``apply_authorized: True`` for a restart class the least-privilege
matrix had just denied, in the same payload that carried
``allow_restart: False`` and "role 'author' may not request full_mcp_restart".
These tests pin the conjunction and the properties that must survive it. They
exercise the real MCP tool, which previously had no test coverage at all that
absence is why the defect shipped.
"""
from __future__ import annotations
import json
import os
import unittest
from unittest.mock import patch
import drain_proof
import gitea_mcp_server as srv
CONTROLLER_APPROVAL_ENV = "GITEA_CONTROLLER_RESTART_APPROVAL_AUTHORIZATION"
BREAK_GLASS_ENV = "GITEA_BREAKGLASS_RESTART_AUTHORIZATION"
# A quiet control plane: nothing live, so the blast radius never masks the
# authorization outcome under test.
QUIET_SESSIONS: list[dict] = []
QUIET_LEASES: list[dict] = []
class _FakeDB:
"""Minimal control-plane DB stand-in for the restart inventory."""
def __init__(self, sessions=QUIET_SESSIONS, terminal=None):
self._sessions = list(sessions)
self._terminal = terminal
def list_sessions(self, statuses=None, limit=None):
return list(self._sessions)
def get_active_terminal_lock(self, remote=None, org=None, repo=None):
return self._terminal
def _profile(role: str) -> dict:
return {"profile_name": f"prgs-{role}", "role_kind": role, "role": role}
class _RestartToolHarness(unittest.TestCase):
"""Drives the real ``gitea_request_mcp_restart`` with a stubbed inventory."""
def _call(self, *, role: str, env: dict | None = None, **kwargs) -> dict:
environ = {k: v for k, v in os.environ.items()
if k not in (CONTROLLER_APPROVAL_ENV, BREAK_GLASS_ENV)}
environ.update(env or {})
with patch.object(srv, "_profile_operation_gate", return_value=None), \
patch.object(srv, "_resolve",
return_value=("gitea.prgs.cc",
"Scaled-Tech-Consulting",
"Gitea-Tools")), \
patch.object(srv, "get_profile", return_value=_profile(role)), \
patch.object(srv, "_control_plane_db_or_error",
return_value=(_FakeDB(), [])), \
patch.object(srv.lease_lifecycle, "list_active_leases",
return_value={"leases": list(QUIET_LEASES)}), \
patch.dict(os.environ, environ, clear=True):
return srv.gitea_request_mcp_restart(
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
session_id="probe-session",
**kwargs,
)
def _clean_proof_for(self, preview: dict) -> str:
"""Mint a genuinely clean, signature-valid proof bound to *preview*.
Built from the tool's own dry-run report, so the fingerprint matches and
the proof is rejected for authorization reasons only never because it
was stale or forged.
"""
proof = drain_proof.build_drain_proof(
impact_report=preview,
drain_state={
"assignments_stopped": True,
"checkpoints_complete": True,
"handoffs_verified": True,
"leases_handled": True,
"acks": {},
},
requesting_session_id="probe-session",
)
self.assertTrue(proof.clean, "harness must mint a clean proof")
return json.dumps(proof.as_dict())
class TestConjunction(_RestartToolHarness):
"""AC1/AC2 — the two authorizations are ANDed, in both directions."""
def test_gate_allow_with_class_denied_yields_apply_authorized_false(self):
# An author may not request full_mcp_restart (CONTROL_ROLES only).
preview = self._call(role="author", restart_class="full_mcp_restart")
self.assertFalse(preview["allow_restart"])
result = self._call(
role="author",
restart_class="full_mcp_restart",
dry_run=False,
drain_proof_json=self._clean_proof_for(preview),
)
self.assertTrue(result["apply_gate"]["drain_gate_allow"],
"drain gate itself should have allowed this proof")
self.assertFalse(result["apply_gate"]["restart_class_authorized"])
self.assertFalse(result["apply_authorized"],
"a clean proof must not authorize a denied class")
self.assertFalse(result["allow_restart"])
def test_gate_allow_with_class_allowed_can_yield_apply_authorized_true(self):
preview = self._call(
role="operator",
restart_class="full_mcp_restart",
env={CONTROLLER_APPROVAL_ENV: "operator-approved"},
)
self.assertTrue(preview["allow_restart"],
"operator + controller approval must authorize the class")
result = self._call(
role="operator",
restart_class="full_mcp_restart",
dry_run=False,
drain_proof_json=self._clean_proof_for(preview),
env={CONTROLLER_APPROVAL_ENV: "operator-approved"},
)
self.assertTrue(result["apply_gate"]["drain_gate_allow"])
self.assertTrue(result["apply_gate"]["restart_class_authorized"])
self.assertTrue(result["apply_authorized"],
"both authorizations pass; apply must be authorized")
def test_denial_is_attributable_to_the_authorization_that_caused_it(self):
preview = self._call(role="author", restart_class="full_mcp_restart")
result = self._call(
role="author",
restart_class="full_mcp_restart",
dry_run=False,
drain_proof_json=self._clean_proof_for(preview),
)
blob = " ".join(result["apply_gate"]["reasons"]).lower()
self.assertIn("restart class authorization denied", blob)
self.assertIn("full_mcp_restart", blob)
class TestProofCannotOverrideAuthorization(_RestartToolHarness):
"""AC3 — a clean proof never overrides a class or requester-role denial."""
def test_clean_proof_cannot_override_role_denial(self):
for role in ("author", "reviewer", "merger", "reconciler"):
with self.subTest(role=role):
preview = self._call(role=role, restart_class="full_mcp_restart")
result = self._call(
role=role,
restart_class="full_mcp_restart",
dry_run=False,
drain_proof_json=self._clean_proof_for(preview),
)
self.assertFalse(result["apply_authorized"])
def test_clean_proof_cannot_override_missing_controller_approval(self):
# Correct role, but the class demands controller approval and the
# environment carries none.
preview = self._call(role="operator", restart_class="full_mcp_restart")
self.assertFalse(preview["allow_restart"])
result = self._call(
role="operator",
restart_class="full_mcp_restart",
dry_run=False,
drain_proof_json=self._clean_proof_for(preview),
)
self.assertFalse(result["apply_authorized"])
def test_clean_proof_cannot_override_unknown_class(self):
preview = self._call(role="operator", restart_class="not_a_real_class",
env={CONTROLLER_APPROVAL_ENV: "yes"})
self.assertFalse(preview["allow_restart"])
result = self._call(
role="operator",
restart_class="not_a_real_class",
dry_run=False,
drain_proof_json=self._clean_proof_for(preview),
env={CONTROLLER_APPROVAL_ENV: "yes"},
)
self.assertFalse(result["apply_authorized"])
def test_clean_proof_cannot_override_missing_scope_target(self):
# worker_restart without target_session_id fails closed on scoping.
preview = self._call(role="operator", restart_class="worker_restart",
env={CONTROLLER_APPROVAL_ENV: "yes"})
self.assertFalse(preview["allow_restart"])
result = self._call(
role="operator",
restart_class="worker_restart",
dry_run=False,
drain_proof_json=self._clean_proof_for(preview),
env={CONTROLLER_APPROVAL_ENV: "yes"},
)
self.assertFalse(result["apply_authorized"])
class TestBreakGlassDoesNotCollapseTheMatrix(_RestartToolHarness):
"""AC4 — break-glass bypasses the drain proof only, never the class matrix."""
def test_break_glass_does_not_authorize_a_denied_class(self):
result = self._call(
role="author",
restart_class="host_restart",
dry_run=False,
request_break_glass=True,
env={BREAK_GLASS_ENV: "operator-issued"},
)
self.assertTrue(result["break_glass_authorized"])
self.assertTrue(result["apply_gate"]["drain_gate_allow"],
"break-glass does satisfy the drain gate")
self.assertFalse(result["apply_gate"]["restart_class_authorized"])
self.assertFalse(result["apply_authorized"],
"break-glass must not collapse the class matrix")
def test_break_glass_across_every_worker_role_and_restricted_class(self):
for role in ("author", "reviewer", "merger", "reconciler"):
for klass in ("rolling_mcp_restart", "full_mcp_restart",
"host_restart"):
with self.subTest(role=role, restart_class=klass):
result = self._call(
role=role,
restart_class=klass,
dry_run=False,
request_break_glass=True,
env={BREAK_GLASS_ENV: "operator-issued"},
)
self.assertFalse(result["apply_authorized"])
def test_break_glass_still_works_when_the_class_is_authorized(self):
# Break-glass keeps its purpose: skipping the drain proof for a caller
# the matrix does allow.
result = self._call(
role="operator",
restart_class="full_mcp_restart",
dry_run=False,
request_break_glass=True,
env={BREAK_GLASS_ENV: "operator-issued",
CONTROLLER_APPROVAL_ENV: "operator-approved"},
)
self.assertTrue(result["apply_authorized"])
self.assertEqual(result["apply_gate"]["verdict"], "break_glass")
def test_break_glass_is_not_self_assertable(self):
# Requested but no environment authorization -> no bypass, and the
# unproven apply is denied.
result = self._call(
role="operator",
restart_class="full_mcp_restart",
dry_run=False,
request_break_glass=True,
env={CONTROLLER_APPROVAL_ENV: "operator-approved"},
)
self.assertTrue(result["break_glass_requested"])
self.assertFalse(result["break_glass_authorized"])
self.assertFalse(result["apply_authorized"])
self.assertIn("incident", result)
class TestRestrictedClassesStayDenied(_RestartToolHarness):
"""AC5 — restricted classes remain denied to unauthorized requesters."""
def test_restricted_classes_denied_for_worker_roles(self):
for role in ("author", "reviewer", "merger", "reconciler"):
for klass in ("rolling_mcp_restart", "full_mcp_restart",
"host_restart"):
with self.subTest(role=role, restart_class=klass):
preview = self._call(
role=role,
restart_class=klass,
env={CONTROLLER_APPROVAL_ENV: "yes"},
)
self.assertFalse(preview["allow_restart"])
self.assertFalse(preview["permission_authorized"])
self.assertFalse(preview["role_authorized"])
def test_host_restart_needs_controller_and_infrastructure_operator(self):
# controller approval alone is not enough for host_restart.
preview = self._call(role="controller", restart_class="host_restart",
env={CONTROLLER_APPROVAL_ENV: "yes"})
self.assertFalse(preview["approval_satisfied"])
self.assertFalse(preview["allow_restart"])
class TestExistingPathsStillWork(_RestartToolHarness):
"""AC6 — valid scoped and unscoped restart paths are unaffected."""
def test_dry_run_never_reports_apply_authorization(self):
result = self._call(role="operator", restart_class="full_mcp_restart",
env={CONTROLLER_APPROVAL_ENV: "yes"})
self.assertNotIn("apply_authorized", result)
self.assertNotIn("apply_gate", result)
self.assertFalse(result["apply_supported"])
self.assertFalse(result["restart_performed"])
def test_self_service_unscoped_classes_authorize_for_every_role(self):
for role in ("author", "reviewer", "merger", "reconciler",
"controller", "operator", "admin"):
for klass in ("client_reconnect", "session_reconnect"):
with self.subTest(role=role, restart_class=klass):
preview = self._call(role=role, restart_class=klass)
self.assertTrue(preview["allow_restart"])
def test_scoped_class_with_target_authorizes_and_applies(self):
env = {CONTROLLER_APPROVAL_ENV: "operator-approved"}
preview = self._call(role="operator", restart_class="worker_restart",
target_session_id="worker-1", env=env)
self.assertTrue(preview["allow_restart"])
result = self._call(
role="operator",
restart_class="worker_restart",
target_session_id="worker-1",
dry_run=False,
drain_proof_json=self._clean_proof_for(preview),
env=env,
)
self.assertTrue(result["apply_authorized"])
def test_apply_still_denies_without_any_proof(self):
# The #661 hard gate is untouched by the conjunction.
result = self._call(
role="operator",
restart_class="full_mcp_restart",
dry_run=False,
env={CONTROLLER_APPROVAL_ENV: "operator-approved"},
)
self.assertFalse(result["apply_gate"]["drain_gate_allow"])
self.assertTrue(result["apply_gate"]["restart_class_authorized"])
self.assertFalse(result["apply_authorized"])
self.assertEqual(result["incident"]["kind"], "restart_drain_gate_denied")
def test_apply_denies_on_malformed_proof(self):
result = self._call(
role="operator",
restart_class="full_mcp_restart",
dry_run=False,
drain_proof_json="{not valid json",
env={CONTROLLER_APPROVAL_ENV: "operator-approved"},
)
self.assertFalse(result["apply_authorized"])
self.assertTrue(any("invalid drain_proof_json" in reason
for reason in result["apply_gate"]["reasons"]))
def test_tool_never_restarts_on_any_path(self):
for kwargs in (
{"restart_class": "client_reconnect"},
{"restart_class": "full_mcp_restart", "dry_run": False},
{"restart_class": "host_restart", "dry_run": False,
"request_break_glass": True},
):
with self.subTest(**kwargs):
result = self._call(role="operator", env={
CONTROLLER_APPROVAL_ENV: "yes", BREAK_GLASS_ENV: "yes"},
**kwargs)
self.assertFalse(result["restart_performed"])
self.assertFalse(result["apply_supported"])
if __name__ == "__main__":
unittest.main()
@@ -0,0 +1,453 @@
"""#897: stale-runtime / runtime-mode refusals must not look like permission denials.
Acceptance criteria (issue #897):
* Stale-runtime and runtime-mode refusals are typed distinctly from
profile-permission refusals (distinct ``blocker_kind``).
* A refusal caused by staleness or runtime mode never emits a
``permission_report`` and never names a permission the active profile holds.
* ``_permission_block_report`` verifies the active profile actually lacks the
operation before reporting it missing.
* A stale-runtime refusal reports reconnect-only recovery and never recommends
``gitea_activate_profile`` or an MCP session switch.
* The blocker payload states the observed heads (parity fields).
* Matrix across author / reviewer / merger / reconciler profiles.
* Regression: ``gitea_create_issue`` on a stale daemon under ``prgs-author``
never returns ``missing_permission: gitea.issue.create``.
"""
from __future__ import annotations
import os
import sys
import unittest
from unittest.mock import patch
sys.path.insert(0, str(__import__("pathlib").Path(__file__).resolve().parent.parent))
import gitea_config # noqa: E402
import gitea_mcp_server as mcp_server # noqa: E402
SHA_START = "7af40fb5ff7debd5e9165fe97d9c7c279358e175"
SHA_LIVE = "2f4dec832327513118f2fe92b74da25d124a01cb"
ROLE_MATRIX = (
(
"prgs-author",
"author",
"gitea.issue.create",
[
"gitea.read",
"gitea.issue.create",
"gitea.issue.comment",
"gitea.issue.close",
"gitea.branch.create",
"gitea.branch.push",
"gitea.pr.create",
"gitea.pr.comment",
"gitea.repo.commit",
],
["gitea.pr.approve", "gitea.pr.merge", "gitea.pr.request_changes"],
"gitea.pr.merge", # forbidden op for pure-permission case
),
(
"prgs-reviewer",
"reviewer",
"gitea.pr.review",
[
"gitea.read",
"gitea.pr.review",
"gitea.pr.approve",
"gitea.pr.request_changes",
"gitea.pr.comment",
"gitea.issue.comment",
],
["gitea.branch.push", "gitea.pr.create"],
"gitea.branch.push",
),
(
"prgs-merger",
"merger",
"gitea.pr.merge",
[
"gitea.read",
"gitea.pr.merge",
"gitea.pr.comment",
"gitea.issue.comment",
],
["gitea.pr.approve", "gitea.branch.push", "gitea.pr.create"],
"gitea.branch.push",
),
(
"prgs-reconciler",
"reconciler",
"gitea.branch.delete",
[
"gitea.read",
"gitea.branch.delete",
"gitea.pr.comment",
"gitea.issue.comment",
"gitea.pr.close",
"gitea.issue.close",
],
["gitea.pr.approve", "gitea.pr.merge"],
"gitea.pr.merge",
),
)
def _profile(name: str, role: str, allowed: list[str], forbidden: list[str]) -> dict:
return {
"profile_name": name,
"role": role,
"role_kind": role,
"allowed_operations": list(allowed),
"forbidden_operations": list(forbidden),
"identity": "test-user",
}
def _config(profiles: dict) -> dict:
return {
"version": 2,
"profiles": {
name: {
"role": p["role"],
"allowed_operations": p["allowed_operations"],
"forbidden_operations": p["forbidden_operations"],
}
for name, p in profiles.items()
},
"rules": {"allow_runtime_switching": True},
}
class Issue897Helpers(unittest.TestCase):
def test_classify_stale_reason_strings(self):
stale = (
f"live remote master is {SHA_LIVE[:12]} but the MCP server started "
f"at {SHA_START[:12]}; the daemon is stale relative to live master "
"-- restart/reconnect before mutating"
)
classified = mcp_server._classify_operation_gate_reasons([stale])
self.assertEqual(classified["stale_runtime"], [stale])
self.assertEqual(classified["permission"], [])
self.assertEqual(classified["runtime_mode"], [])
def test_classify_permission_reason(self):
reason = "profile is not allowed to gitea.pr.merge"
classified = mcp_server._classify_operation_gate_reasons([reason])
self.assertEqual(classified["permission"], [reason])
self.assertEqual(classified["stale_runtime"], [])
def test_classify_runtime_mode_reason(self):
reason = (
"runtime mode is 'dev-test' and the mutation targets the "
"production repository; dev/test runtimes must not mutate real "
"issues or PRs (ADR: stable control runtime vs dev runtime)"
)
classified = mcp_server._classify_operation_gate_reasons([reason])
self.assertEqual(classified["runtime_mode"], [reason])
self.assertEqual(classified["stale_runtime"], [])
class Issue897PermissionBlockReport(unittest.TestCase):
def test_holds_op_is_diagnostic_defect_not_missing_permission(self):
profile = _profile(
"prgs-author",
"author",
["gitea.read", "gitea.issue.create", "gitea.issue.comment"],
[],
)
with patch.object(mcp_server, "get_profile", return_value=profile), patch.object(
mcp_server.gitea_config, "load_config", return_value=_config({"prgs-author": profile})
), patch.object(
mcp_server.gitea_config, "is_runtime_switching_enabled", return_value=True
):
report = mcp_server._permission_block_report("gitea.issue.create")
self.assertTrue(report.get("diagnostic_defect"), report)
self.assertIsNone(report.get("missing_permission"), report)
action = (report.get("exact_safe_next_action") or "").lower()
# Must not *recommend* profile switching; mentioning the forbidden
# action in a "do not call" instruction is fine.
self.assertNotIn("call gitea_activate_profile with", action)
self.assertNotIn("switch to the author mcp session", action)
self.assertNotIn("switch to the reviewer mcp session", action)
self.assertIn("diagnostic defect", action)
def test_true_missing_permission_still_reports(self):
profile = _profile(
"prgs-author",
"author",
["gitea.read", "gitea.issue.create"],
["gitea.pr.merge"],
)
reviewer = _profile(
"prgs-reviewer",
"reviewer",
["gitea.read", "gitea.pr.merge", "gitea.pr.approve"],
[],
)
with patch.object(mcp_server, "get_profile", return_value=profile), patch.object(
mcp_server.gitea_config,
"load_config",
return_value=_config({"prgs-author": profile, "prgs-reviewer": reviewer}),
), patch.object(
mcp_server.gitea_config, "is_runtime_switching_enabled", return_value=True
):
report = mcp_server._permission_block_report("gitea.pr.merge")
self.assertFalse(report.get("diagnostic_defect"), report)
self.assertEqual(report.get("missing_permission"), "gitea.pr.merge")
self.assertIn("prgs-reviewer", report.get("matching_configured_profiles") or [])
class Issue897GateRefusalMatrix(unittest.TestCase):
def _stale_parity(self) -> dict:
return {
"in_parity": True,
"stale": False,
"restart_required": True,
"determinable": True,
"startup_head": SHA_START,
"current_head": SHA_START,
"daemon_start_head": SHA_START,
"local_head": SHA_START,
"live_remote_head": SHA_LIVE,
"live_known": True,
"live_stale": True,
"mutation_safe": False,
"reasons": [
f"live remote master is {SHA_LIVE[:12]} but the MCP server "
f"started at {SHA_START[:12]}; the daemon is stale relative "
"to live master -- restart/reconnect before mutating"
],
}
def test_stale_plus_permitted_op_all_roles(self):
for name, role, permitted_op, allowed, forbidden, _forbidden_op in ROLE_MATRIX:
with self.subTest(profile=name, op=permitted_op):
profile = _profile(name, role, allowed, forbidden)
parity = self._stale_parity()
with patch.object(mcp_server, "get_profile", return_value=profile), patch.object(
mcp_server, "_current_master_parity", return_value=parity
), patch.object(
mcp_server, "_master_parity_block", return_value=list(parity["reasons"])
), patch.object(
mcp_server, "_runtime_mode_block", return_value=[]
), patch.object(
mcp_server, "_ensure_matching_profile", return_value=None
), patch.object(
mcp_server.session_ctx,
"mutation_context_audit_fields",
return_value={"session_profile": name},
):
blocked = mcp_server._profile_permission_block(permitted_op)
self.assertIsNotNone(blocked, name)
assert blocked is not None
self.assertEqual(
blocked.get("blocker_kind"),
"runtime_reconnect_required",
blocked,
)
self.assertNotIn("permission_report", blocked, blocked)
self.assertTrue(blocked.get("restart_required"), blocked)
self.assertEqual(blocked.get("startup_head"), SHA_START, blocked)
self.assertEqual(blocked.get("live_remote_head"), SHA_LIVE, blocked)
action = (blocked.get("exact_safe_next_action") or "").lower()
self.assertIn("reconnect", action)
self.assertNotIn("call gitea_activate_profile with", action)
self.assertNotIn("switch to the author mcp session", action)
self.assertNotIn("switch to the reviewer mcp session", action)
def test_fresh_plus_forbidden_op_all_roles(self):
for name, role, _permitted, allowed, forbidden, forbidden_op in ROLE_MATRIX:
with self.subTest(profile=name, op=forbidden_op):
profile = _profile(name, role, allowed, forbidden)
with patch.object(mcp_server, "get_profile", return_value=profile), patch.object(
mcp_server, "_master_parity_block", return_value=[]
), patch.object(
mcp_server, "_runtime_mode_block", return_value=[]
), patch.object(
mcp_server, "_ensure_matching_profile", return_value=None
), patch.object(
mcp_server.session_ctx,
"mutation_context_audit_fields",
return_value={"session_profile": name},
), patch.object(
mcp_server.gitea_config,
"load_config",
return_value=_config({name: profile}),
), patch.object(
mcp_server.gitea_config, "is_runtime_switching_enabled", return_value=False
):
blocked = mcp_server._profile_permission_block(forbidden_op)
self.assertIsNotNone(blocked, name)
assert blocked is not None
self.assertEqual(blocked.get("blocker_kind"), "permission_denied", blocked)
self.assertIn("permission_report", blocked, blocked)
report = blocked["permission_report"]
self.assertEqual(report.get("missing_permission"), forbidden_op, report)
self.assertFalse(report.get("diagnostic_defect"), report)
# No runtime reconnect fields for pure permission denial
self.assertNotEqual(
blocked.get("blocker_kind"), "runtime_reconnect_required"
)
def test_stale_plus_forbidden_op_both_causes_separated(self):
for name, role, _permitted, allowed, forbidden, forbidden_op in ROLE_MATRIX:
with self.subTest(profile=name, op=forbidden_op):
profile = _profile(name, role, allowed, forbidden)
parity = self._stale_parity()
stale_reason = parity["reasons"][0]
with patch.object(mcp_server, "get_profile", return_value=profile), patch.object(
mcp_server, "_current_master_parity", return_value=parity
), patch.object(
mcp_server, "_master_parity_block", return_value=[stale_reason]
), patch.object(
mcp_server, "_runtime_mode_block", return_value=[]
), patch.object(
mcp_server, "_ensure_matching_profile", return_value=None
), patch.object(
mcp_server.session_ctx,
"mutation_context_audit_fields",
return_value={"session_profile": name},
):
# Gate collects both classes; force permission reason too.
with patch.object(
mcp_server,
"_profile_operation_gate",
return_value=[
stale_reason,
f"profile is not allowed to {forbidden_op}",
],
):
blocked = mcp_server._profile_permission_block(forbidden_op)
self.assertIsNotNone(blocked)
assert blocked is not None
self.assertEqual(
blocked.get("blocker_kind"), "runtime_reconnect_required", blocked
)
self.assertNotIn("permission_report", blocked, blocked)
self.assertIn("permission_block_reasons", blocked, blocked)
self.assertIn("stale_runtime_reasons", blocked, blocked)
classes = blocked.get("gate_reason_classes") or {}
self.assertTrue(classes.get("stale_runtime"), classes)
self.assertTrue(classes.get("permission"), classes)
def test_runtime_mode_block_no_permission_report(self):
profile = _profile(
"prgs-author",
"author",
["gitea.read", "gitea.issue.create"],
[],
)
runtime_reason = (
"runtime mode is 'dev-test' and the mutation targets the "
"production repository; dev/test runtimes must not mutate real "
"issues or PRs (ADR: stable control runtime vs dev runtime)"
)
with patch.object(mcp_server, "get_profile", return_value=profile), patch.object(
mcp_server, "_master_parity_block", return_value=[]
), patch.object(
mcp_server, "_runtime_mode_block", return_value=[runtime_reason]
), patch.object(
mcp_server, "_ensure_matching_profile", return_value=None
), patch.object(
mcp_server.session_ctx,
"mutation_context_audit_fields",
return_value={"session_profile": "prgs-author"},
):
blocked = mcp_server._profile_permission_block("gitea.issue.create")
self.assertIsNotNone(blocked)
assert blocked is not None
self.assertEqual(blocked.get("blocker_kind"), "runtime_mode_blocked", blocked)
self.assertNotIn("permission_report", blocked, blocked)
action = (blocked.get("exact_safe_next_action") or "").lower()
self.assertNotIn("call gitea_activate_profile with", action)
self.assertIn("stable control runtime", action)
class Issue897CreateIssueRegression(unittest.TestCase):
def test_create_issue_stale_daemon_never_missing_issue_create(self):
"""Regression AC: stale prgs-author create_issue must not claim missing create."""
profile = _profile(
"prgs-author",
"author",
[
"gitea.read",
"gitea.issue.create",
"gitea.issue.comment",
"gitea.branch.create",
"gitea.branch.push",
"gitea.pr.create",
"gitea.pr.comment",
"gitea.repo.commit",
],
[],
)
stale_reason = (
f"live remote master is {SHA_LIVE[:12]} but the MCP server started "
f"at {SHA_START[:12]}; the daemon is stale relative to live master "
"-- restart/reconnect before mutating"
)
parity = {
"in_parity": True,
"stale": False,
"restart_required": True,
"determinable": True,
"startup_head": SHA_START,
"current_head": SHA_START,
"daemon_start_head": SHA_START,
"local_head": SHA_START,
"live_remote_head": SHA_LIVE,
"live_known": True,
"live_stale": True,
"mutation_safe": False,
"reasons": [stale_reason],
}
with patch.object(mcp_server, "get_profile", return_value=profile), patch.object(
mcp_server, "_current_master_parity", return_value=parity
), patch.object(
mcp_server, "_master_parity_block", return_value=[stale_reason]
), patch.object(
mcp_server, "_runtime_mode_block", return_value=[]
), patch.object(
mcp_server, "_ensure_matching_profile", return_value=None
), patch.object(
mcp_server.session_ctx,
"mutation_context_audit_fields",
return_value={"session_profile": "prgs-author"},
), patch.object(
mcp_server, "_mutation_config_authority_block", return_value=None
), patch.object(
mcp_server, "_session_context_mutation_block", return_value=None
):
blocked = mcp_server._profile_permission_block(
"gitea.issue.create", remote="prgs"
)
self.assertIsNotNone(blocked)
assert blocked is not None
self.assertEqual(blocked.get("blocker_kind"), "runtime_reconnect_required")
self.assertNotIn("permission_report", blocked)
# Even if a caller still built a raw report, holds-check must not claim missing.
with patch.object(mcp_server, "get_profile", return_value=profile):
raw = mcp_server._permission_block_report("gitea.issue.create")
self.assertIsNone(raw.get("missing_permission"), raw)
self.assertNotEqual(raw.get("missing_permission"), "gitea.issue.create")
def test_permission_report_for_gate_reasons_skips_stale(self):
stale = (
f"live remote master is {SHA_LIVE[:12]} but the MCP server started "
f"at {SHA_START[:12]}; the daemon is stale relative to live master "
"-- restart/reconnect before mutating"
)
self.assertIsNone(
mcp_server._permission_report_for_gate_reasons(
"gitea.issue.comment", [stale]
)
)
if __name__ == "__main__":
unittest.main()
-117
View File
@@ -105,120 +105,3 @@ def test_cross_links_do_not_embed_secrets():
text = _read(path) text = _read(path)
for marker in ("ghp_", "BEGIN PRIVATE KEY", "Authorization: Bearer"): for marker in ("ghp_", "BEGIN PRIVATE KEY", "Authorization: Bearer"):
assert marker not in text, f"{path} contains {marker!r}" assert marker not in text, f"{path} contains {marker!r}"
# --- Coordinator doc stays in lock-step with the tool (#886 review blocker B2) --
#
# PR #882 moved the #661 drain-proof hard gate *into* gitea_request_mcp_restart,
# but the coordinator document still described the proof as "a separate child"
# and omitted both new parameters. Nothing referenced that document, so nothing
# caught the drift. These tests bind the prose to the real signature.
COORDINATOR_DOC = REPO_ROOT / "docs" / "mcp-restart-coordinator.md"
# Affirmative claims that were accurate before #661 landed and are now false.
# Matched against whitespace-normalized text so re-wrapping cannot hide them.
# Deliberately not the bare phrase "a separate child": the corrected prose uses
# it in a negation ("no longer a separate child operation"), and a guard that
# forbids naming the old behaviour would block explaining that it changed.
STALE_PRE_661_PHRASES = (
"gated by a drain proof (a separate child)",
"is a later child gated by a drain proof",
"mutative apply path is explicitly out of scope",
"apply is gated by a drain proof (a separate child)",
)
def _documented_signature_block() -> str:
"""The fenced signature block for the tool, as published in the doc."""
text = _read(COORDINATOR_DOC)
marker = "gitea_request_mcp_restart("
start = text.index(marker)
end = text.index("```", start)
return text[start:end]
def test_documented_signature_matches_the_real_tool_signature():
import inspect
import gitea_mcp_server
block = _documented_signature_block()
real = inspect.signature(gitea_mcp_server.gitea_request_mcp_restart)
for name in real.parameters:
assert name in block, (
f"docs/mcp-restart-coordinator.md documents no {name!r} parameter; "
"the published signature has drifted from the tool"
)
def test_drain_proof_and_break_glass_parameters_are_documented():
block = _documented_signature_block()
for name in ("drain_proof_json", "request_break_glass"):
assert name in block, f"signature block missing {name}"
def test_restart_class_and_target_scoping_parameters_survive():
block = _documented_signature_block()
for name in ("restart_class", "target_session_id", "target_role",
"target_connector"):
assert name in block, f"signature block lost #663 parameter {name}"
def test_gate_is_documented_as_executing_inside_this_tool():
lower = _read(COORDINATOR_DOC).lower()
assert "inside this tool" in lower, (
"the coordinator doc must state that the drain-proof gate executes in "
"gitea_request_mcp_restart, not in a later child"
)
assert "no longer a separate child operation" in lower
def test_stale_pre_661_wording_cannot_return():
normalized = " ".join(_read(COORDINATOR_DOC).split()).lower()
for phrase in STALE_PRE_661_PHRASES:
assert phrase not in normalized, (
f"stale pre-#661 wording returned to the coordinator doc: {phrase!r}"
)
def test_dry_run_versus_apply_behavior_is_documented():
lower = _read(COORDINATOR_DOC).lower()
assert "dry_run=true" in lower and "dry_run=false" in lower
assert "apply_supported" in lower and "restart_performed" in lower
assert "never restarts anything" in lower
def test_authorization_ordering_and_conjunction_are_documented():
text = _read(COORDINATOR_DOC)
lower = text.lower()
assert "authorization ordering" in lower
assert "allow_restart" in text
assert "apply_authorized" in text
# The conjunction itself, and the attribution fields behind it.
assert "gate.allow and allow_restart" in text
for field in ("drain_gate_allow", "restart_class_authorized"):
assert field in text, f"doc omits apply_gate.{field}"
def test_break_glass_scope_is_documented_as_drain_proof_only():
text = _read(COORDINATOR_DOC)
lower = text.lower()
assert "break-glass" in lower
assert "drain proof only" in lower, (
"doc must state break-glass never bypasses the restart-class matrix"
)
assert "GITEA_BREAKGLASS_RESTART_AUTHORIZATION" in text
def test_fail_closed_on_apply_is_documented():
lower = _read(COORDINATOR_DOC).lower()
assert "fail closed" in lower
for condition in ("expired", "unclean", "tampered", "stale"):
assert condition in lower, f"fail-closed list omits {condition!r}"
def test_coordinator_doc_embeds_no_secrets():
text = _read(COORDINATOR_DOC)
for marker in ("ghp_", "BEGIN PRIVATE KEY", "Authorization: Bearer"):
assert marker not in text, f"{COORDINATOR_DOC} contains {marker!r}"
-232
View File
@@ -1,232 +0,0 @@
"""Permission, drain, routing, and audit matrix for restart classes (#663)."""
from __future__ import annotations
import os
from datetime import datetime, timezone
import restart_coordinator as rc
NOW = datetime(2026, 7, 24, 20, 0, tzinfo=timezone.utc)
def _inventory() -> dict:
return {
"inventory_complete": True,
"sessions": [
{
"session_id": "requester",
"role": "author",
"profile": "prgs-author",
"pid": os.getpid(),
"status": "active",
"last_heartbeat_at": NOW.isoformat(),
},
{
"session_id": "reviewer",
"role": "reviewer",
"profile": "prgs-reviewer",
"pid": os.getpid(),
"status": "active",
"last_heartbeat_at": NOW.isoformat(),
},
],
"leases": [
{
"lease_id": "review-lease",
"session_id": "reviewer",
"role": "reviewer",
"phase": "reviewing",
"work_kind": "pr",
"work_number": 900,
"worktree_path": "/tmp/review-900",
"freshness": {"freshness": "active"},
}
],
}
def _evaluate(
restart_class: rc.RestartClass,
*,
role: str = "controller",
permissions: tuple[str, ...] | None = None,
approved: bool = True,
operator: bool = True,
**targets,
):
return rc.evaluate_restart_impact(
_inventory(),
now=NOW,
requesting_session_id="requester",
restart_class=restart_class,
requester_role=role,
requester_permissions=(
permissions if permissions is not None
else rc.permissions_for_role(role)
),
controller_approved=approved,
operator_authorized=operator,
**targets,
)
def test_policy_table_covers_exactly_all_nine_classes():
assert set(rc.RESTART_CLASS_POLICIES) == set(rc.RestartClass)
assert len(rc.RESTART_CLASS_POLICIES) == 9
for restart_class, policy in rc.RESTART_CLASS_POLICIES.items():
assert policy.restart_class is restart_class
assert policy.required_permission
assert policy.expected_blast_radius in {
rc.BLAST_NONE, rc.BLAST_LOW, rc.BLAST_MEDIUM, rc.BLAST_HIGH
}
assert policy.drain_requirement
assert policy.approval_requirement
assert policy.audit_requirement
assert policy.recovery_behavior
def test_permission_matrix_allows_each_class_with_exact_permission():
targets = {
rc.RestartClass.WORKER_RESTART: {"target_session_id": "reviewer"},
rc.RestartClass.ROLE_RUNTIME_RESTART: {"target_role": "reviewer"},
rc.RestartClass.CONNECTOR_RESTART: {"target_connector": "github"},
}
for restart_class, policy in rc.RESTART_CLASS_POLICIES.items():
report = _evaluate(
restart_class,
permissions=(policy.required_permission,),
**targets.get(restart_class, {}),
)
assert report.permission_authorized, restart_class
assert report.role_authorized, restart_class
assert report.approval_satisfied, restart_class
assert report.audit_record["restart_class"] == restart_class.value
assert (
report.audit_record["required_permission"]
== policy.required_permission
)
def test_missing_or_nearby_permission_denies():
report = _evaluate(
rc.RestartClass.ROLE_RUNTIME_RESTART,
permissions=("mcp.restart.worker.request",),
target_role="reviewer",
)
assert report.verdict == rc.VERDICT_UNSAFE
assert not report.allow_restart
assert not report.permission_authorized
assert any("missing required permission" in r for r in report.reasons)
def test_unknown_restart_class_denies_fail_closed():
report = rc.evaluate_restart_impact(
_inventory(),
now=NOW,
restart_class="surprise_reboot",
requester_role="admin",
requester_permissions=("mcp.restart.host.request",),
controller_approved=True,
operator_authorized=True,
)
assert report.verdict == rc.VERDICT_UNSAFE
assert not report.allow_restart
assert report.restart_policy == {}
assert any("unknown restart class" in r for r in report.reasons)
def test_worker_roles_cannot_request_full_or_host_restart():
for role in rc.WORKER_ROLES:
granted = rc.permissions_for_role(role)
assert "mcp.restart.full.request" not in granted
assert "mcp.restart.host.request" not in granted
report = _evaluate(
rc.RestartClass.FULL_MCP_RESTART,
role=role,
permissions=granted,
)
assert not report.role_authorized
assert not report.allow_restart
def test_controller_approval_is_independent_of_permission():
report = _evaluate(
rc.RestartClass.WORKER_RESTART,
approved=False,
target_session_id="reviewer",
)
assert report.permission_authorized
assert not report.approval_satisfied
assert not report.allow_restart
def test_narrow_classes_do_not_inherit_full_drain_or_peer_lease_block():
for restart_class in (
rc.RestartClass.CLIENT_RECONNECT,
rc.RestartClass.SESSION_RECONNECT,
rc.RestartClass.CONFIGURATION_RELOAD,
):
report = _evaluate(restart_class)
assert not report.restart_policy["full_drain_required"]
assert report.counts["leases_disruptive"] == 0
assert report.counts["sessions_live_other"] == 0
assert report.counts["critical_sections"] == 0
assert report.counts["mutations"] == 0
assert report.allow_restart, (restart_class, report.reasons)
def test_client_reconnect_does_not_wait_for_unrelated_terminal_lock():
inventory = _inventory()
inventory["terminal_lock"] = {"terminal_pr": 901}
report = rc.evaluate_restart_impact(
inventory,
now=NOW,
requesting_session_id="requester",
restart_class=rc.RestartClass.CLIENT_RECONNECT,
requester_role="author",
requester_permissions=rc.permissions_for_role("author"),
)
assert report.allow_restart
assert report.terminal_lock is None
def test_scoped_restart_only_counts_named_target():
report = _evaluate(
rc.RestartClass.ROLE_RUNTIME_RESTART,
target_role="author",
)
assert report.counts["leases_disruptive"] == 0
assert report.affected_prs == []
assert report.allow_restart
reviewer = _evaluate(
rc.RestartClass.ROLE_RUNTIME_RESTART,
target_role="reviewer",
)
assert reviewer.counts["leases_disruptive"] == 1
assert reviewer.affected_prs == [900]
assert not reviewer.allow_restart
def test_missing_scoped_target_denies_instead_of_widening():
for restart_class in (
rc.RestartClass.WORKER_RESTART,
rc.RestartClass.ROLE_RUNTIME_RESTART,
rc.RestartClass.CONNECTOR_RESTART,
):
report = _evaluate(restart_class)
assert not report.allow_restart
assert any("target required" in r for r in report.reasons)
def test_only_full_and_host_classes_require_full_drain():
requiring_full = {
restart_class
for restart_class, policy in rc.RESTART_CLASS_POLICIES.items()
if policy.full_drain_required
}
assert requiring_full == {
rc.RestartClass.FULL_MCP_RESTART,
rc.RestartClass.HOST_RESTART,
}
File diff suppressed because it is too large Load Diff
-6
View File
@@ -444,12 +444,6 @@ class TestAuditEmission(unittest.TestCase):
) )
self.assertEqual(record["target"]["namespace"], NAMESPACE) self.assertEqual(record["target"]["namespace"], NAMESPACE)
self.assertEqual(record["target"]["mode"], "restart") self.assertEqual(record["target"]["mode"], "restart")
self.assertEqual(
record["target"]["restart_class"], "role_runtime_restart"
)
self.assertEqual(
record["metadata"]["restart_class"], "role_runtime_restart"
)
self.assertEqual(record["result"], console_audit.RESULT_ALLOWED) self.assertEqual(record["result"], console_audit.RESULT_ALLOWED)
self.assertEqual(record["actor"]["subject"], "[email protected]") self.assertEqual(record["actor"]["subject"], "[email protected]")
self.assertFalse(record["metadata"]["process_kill_executed"]) self.assertFalse(record["metadata"]["process_kill_executed"])
-116
View File
@@ -67,8 +67,6 @@ from webui.system_health import (
snapshot_to_dict as system_health_to_dict, snapshot_to_dict as system_health_to_dict,
) )
from webui.system_health_views import render_system_health_page from webui.system_health_views import render_system_health_page
from webui import request_service
from webui.request_views import render_requests_page
_READ_ONLY_METHODS = frozenset({"GET", "HEAD", "OPTIONS"}) _READ_ONLY_METHODS = frozenset({"GET", "HEAD", "OPTIONS"})
_AUDIT_MUTATION_PATHS = frozenset({"/audit", "/api/audit"}) _AUDIT_MUTATION_PATHS = frozenset({"/audit", "/api/audit"})
@@ -724,109 +722,6 @@ async def api_v1_analytics_ingest(request: Request) -> JSONResponse:
) )
def _default_request_scope() -> dict[str, str]:
"""Resolve remote/org/repo from the project registry for request forms.
Returns an empty mapping when the registry cannot be read, which makes
``parse_request`` reject a request that did not name its own scope rather
than letting it default to some other repository.
"""
from webui.queue_loader import _host_from_url # host normalisation helper
registry, error = _load_project_registry()
if error is not None or not registry.projects:
return {}
project = registry.projects[0]
host = _host_from_url(project.remote_host)
return {
"remote": _derive_remote(host),
"org": project.gitea_owner or "",
"repo": project.repo_name or "",
}
async def _request_payload(request: Request) -> dict[str, object]:
"""Read a request body as JSON or form-encoded. Never raises."""
content_type = (request.headers.get("content-type") or "").lower()
if "application/json" in content_type:
try:
body = await request.json()
except Exception:
return {}
return dict(body) if isinstance(body, dict) else {}
try:
form = await request.form()
except Exception:
return {}
return {key: form[key] for key in form}
async def requests_page(request: Request) -> HTMLResponse:
"""Operator request form and intent preview (#643).
POST here only ever *previews*. Initiation is a separate confirmed call to
``/api/v1/requests/apply`` so that submitting this form cannot reserve
work as a side effect.
"""
submitted: dict[str, object] = {}
preview = None
error = None
if request.method == "POST":
submitted = await _request_payload(request)
work_request, error = request_service.parse_request(
submitted, default_scope=_default_request_scope()
)
if work_request is not None:
preview = request_service.preview_request(
work_request,
principal=resolve_principal(headers=dict(request.headers)),
)
return HTMLResponse(
render_requests_page(
preview=preview, error=error, submitted=submitted
)
)
async def api_v1_request_preview(request: Request) -> JSONResponse:
"""Dry-run authorization and intent preview for a work request (#643)."""
payload = await _request_payload(request)
work_request, error = request_service.parse_request(
payload, default_scope=_default_request_scope()
)
if work_request is None:
return JSONResponse(error.to_dict(), status_code=400)
preview = request_service.preview_request(
work_request,
principal=resolve_principal(headers=dict(request.headers)),
)
return JSONResponse(
preview.to_dict(), status_code=200 if preview.authorized else 403
)
async def api_v1_request_apply(request: Request) -> JSONResponse:
"""Initiate a previewed work request through the allocator (#643).
Fail-closed at every step: unauthorized, unconfirmed, not-next-safe, and
already-claimed all return without attempting an assignment.
"""
payload = await _request_payload(request)
work_request, error = request_service.parse_request(
payload, default_scope=_default_request_scope()
)
if work_request is None:
return JSONResponse(error.to_dict(), status_code=400)
confirm = _truthy_flag(str(payload.get("confirm") or ""))
result = request_service.apply_request(
work_request,
principal=resolve_principal(headers=dict(request.headers)),
confirm=confirm,
)
status = int(result.pop("status_code", 403))
return JSONResponse(result, status_code=status)
async def method_not_allowed(request: Request, _exc: Exception) -> Response: async def method_not_allowed(request: Request, _exc: Exception) -> Response:
path = request.url.path path = request.url.path
if path in _AUDIT_MUTATION_PATHS and request.method == "POST": if path in _AUDIT_MUTATION_PATHS and request.method == "POST":
@@ -891,17 +786,6 @@ def create_app(*, bind_host: str | None = None) -> Starlette:
api_action_attempt, api_action_attempt,
methods=["POST"], methods=["POST"],
), ),
Route("/requests", requests_page, methods=["GET", "POST"]),
Route(
"/api/v1/requests/preview",
api_v1_request_preview,
methods=["POST"],
),
Route(
"/api/v1/requests/apply",
api_v1_request_apply,
methods=["POST"],
),
Route("/api/leases", api_leases, methods=["GET"]), Route("/api/leases", api_leases, methods=["GET"]),
Route("/api/v1/inventory", api_inventory, methods=["GET"]), Route("/api/v1/inventory", api_inventory, methods=["GET"]),
Route( Route(
+8 -71
View File
@@ -115,12 +115,6 @@ class ConsoleAction:
break_glass: bool break_glass: bool
phase: int phase: int
summary: str summary: str
# Opt-in switch for an action whose execution path is genuinely wired
# ahead of its phase becoming globally active (#643). Naming a variable
# here enables nothing on its own: the variable must also be set in the
# environment. An action that leaves this ``None`` can only execute once
# ACTIVE_PHASE reaches its phase, exactly as before.
execution_env_flag: str | None = None
@property @property
def mcp_permission(self) -> str: def mcp_permission(self) -> str:
@@ -283,27 +277,6 @@ _ACTION_SPECS: tuple[ConsoleAction, ...] = (
phase=2, phase=2,
summary="Restart one MCP namespace via the host supervisor.", summary="Restart one MCP namespace via the host supervisor.",
), ),
# #643: submit a work request — desired role, issue/PR, intent — and let
# the allocator reserve it. This is the one Phase 2 action whose execution
# path is actually implemented (``webui.request_service``), so it carries
# the opt-in flag; it stays denied until an operator sets that variable.
# Authority is operator-class because the outcome is a claim, not a Gitea
# verdict: initiating reviewer or merger *work* does not grant the right
# to approve or merge, which stays with the MCP role profile.
ConsoleAction(
action_id="initiate_workflow",
task_key="allocate_next_work",
action_class=CLASS_WRITE,
minimum_role=OPERATOR,
requires_confirmation=True,
dual_control=False,
break_glass=False,
phase=2,
summary=(
"Preview and initiate allocator-owned workflow work for a role."
),
execution_env_flag="WEBUI_REQUESTS_EXECUTION",
),
) )
ACTIONS: dict[str, ConsoleAction] = {a.action_id: a for a in _ACTION_SPECS} ACTIONS: dict[str, ConsoleAction] = {a.action_id: a for a in _ACTION_SPECS}
@@ -457,33 +430,6 @@ ALLOW_PREVIEW = "allowed_preview_only"
# gated on this model landing; nothing here enables it. # gated on this model landing; nothing here enables it.
ACTIVE_PHASE = 1 ACTIVE_PHASE = 1
_TRUTHY = frozenset({"1", "true", "yes", "on"})
def execution_wired(
action: ConsoleAction | None, env: dict[str, str] | None = None
) -> bool:
"""Whether *action* has a live execution path right now.
Two ways to be wired, and only two. The action's phase is active, or the
action declares an opt-in environment variable *and* that variable is set.
Everything else including every action that never declares a flag is
unwired, so the default across the registry stays deny.
Bumping ``ACTIVE_PHASE`` would enable execution for every action of that
phase at once. The per-action flag exists so a single implemented action
can go live without dragging its unimplemented phase-mates with it.
"""
if action is None:
return False
if action.phase <= ACTIVE_PHASE:
return True
flag = (action.execution_env_flag or "").strip()
if not flag:
return False
source = env if env is not None else os.environ
return (source.get(flag) or "").strip().lower() in _TRUTHY
@dataclass(frozen=True) @dataclass(frozen=True)
class AuthorizationDecision: class AuthorizationDecision:
@@ -523,19 +469,16 @@ def authorize(
principal: Principal | None = None, principal: Principal | None = None,
*, *,
for_execution: bool = False, for_execution: bool = False,
env: dict[str, str] | None = None,
) -> AuthorizationDecision: ) -> AuthorizationDecision:
"""Decide whether *principal* may invoke *action_id*. Deny by default. """Decide whether *principal* may invoke *action_id*. Deny by default.
``for_execution`` distinguishes a read-only preview from a real invocation. ``for_execution`` distinguishes a read-only preview from a real invocation.
``execution_enabled`` reports whether the action has a live execution path Even an allowed decision reports ``execution_enabled=False`` while the
at all (:func:`execution_wired`) for every action without an explicit console is in Phase 1, so no caller can read an allow as permission to
opt-in flag that stays ``False`` while the console is in Phase 1, so no mutate.
caller can read an allow as permission to mutate.
""" """
who = principal if principal is not None else ANONYMOUS who = principal if principal is not None else ANONYMOUS
action = get_action(action_id) action = get_action(action_id)
wired = execution_wired(action, env)
if action is None: if action is None:
return AuthorizationDecision( return AuthorizationDecision(
@@ -554,7 +497,7 @@ def authorize(
"requires_confirmation": action.requires_confirmation, "requires_confirmation": action.requires_confirmation,
"dual_control": action.dual_control, "dual_control": action.dual_control,
"break_glass": action.break_glass, "break_glass": action.break_glass,
"execution_enabled": wired, "execution_enabled": False,
} }
if not who.authenticated: if not who.authenticated:
@@ -587,19 +530,13 @@ def authorize(
**base, **base,
) )
if for_execution and not wired: if for_execution and action.phase > ACTIVE_PHASE:
return AuthorizationDecision( return AuthorizationDecision(
allowed=False, allowed=False,
reason_code=DENY_PHASE_NOT_ACTIVE, reason_code=DENY_PHASE_NOT_ACTIVE,
detail=( detail=(
f"Action {action_id!r} belongs to phase {action.phase}; the " f"Action {action_id!r} belongs to phase {action.phase}; the "
f"console is in phase {ACTIVE_PHASE}" f"console is in phase {ACTIVE_PHASE}. Execution is not wired."
+ (
f" and {action.execution_env_flag} is not set"
if action.execution_env_flag
else ""
)
+ ". Execution is not wired."
), ),
**base, **base,
) )
@@ -608,8 +545,8 @@ def authorize(
allowed=True, allowed=True,
reason_code=ALLOW_PREVIEW, reason_code=ALLOW_PREVIEW,
detail=( detail=(
"Principal holds the required role. Execution proceeds only for an " "Principal holds the required role. Preview only — execution "
"action with a wired execution path; everything else is preview." "remains disabled until the Phase 2 action framework ships."
), ),
**base, **base,
) )
-1
View File
@@ -45,7 +45,6 @@ NAV_GROUPS: tuple[NavGroup, ...] = (
NavItem("/queue", "Queue"), NavItem("/queue", "Queue"),
NavItem("/leases", "Leases"), NavItem("/leases", "Leases"),
NavItem("/actions", "Actions"), NavItem("/actions", "Actions"),
NavItem("/requests", "Requests"),
)), )),
NavGroup("Runtime/Sessions", ( NavGroup("Runtime/Sessions", (
NavItem("/runtime", "Runtime health"), NavItem("/runtime", "Runtime health"),
File diff suppressed because it is too large Load Diff
-164
View File
@@ -1,164 +0,0 @@
"""HTML views for the operator request surface (#643).
The form is deliberately a *preview* form. It has no initiate button, because
initiating requires a confirmed POST to ``/api/v1/requests/apply`` and a stray
form submission must not be able to produce one by accident.
Nothing rendered here is trusted input: every interpolated value is escaped,
and the page renders only values the service already produced rather than
echoing a raw request body back.
"""
from __future__ import annotations
import html
import json
from typing import Any
from webui.layout import render_page
from webui.request_service import (
REQUESTABLE_ROLES,
WORK_KINDS,
RequestError,
RequestPreview,
)
REQUESTS_PATH = "/requests"
PREVIEW_API_PATH = "/api/v1/requests/preview"
APPLY_API_PATH = "/api/v1/requests/apply"
def _escape(text: Any) -> str:
return html.escape(str(text if text is not None else ""), quote=True)
REQUEST_PAGE_STYLES = """
<style>
.request-form { display: grid; gap: 0.75rem; max-width: 44rem; }
.request-form label { display: grid; gap: 0.25rem; font-size: 0.9rem; }
.request-check { margin: 0.35rem 0; }
.request-check .verdict-ok { color: var(--accent); }
.request-check .verdict-fail { color: #d14; }
.request-prohibited code { margin-right: 0.4rem; }
</style>
"""
def _options(values: tuple[str, ...], selected: Any) -> str:
return "".join(
f"<option value='{_escape(value)}'"
+ (" selected" if selected == value else "")
+ f">{_escape(value)}</option>"
for value in values
)
def _form(values: dict[str, Any] | None = None) -> str:
current = dict(values or {})
number = current.get("work_number")
return (
f"<form class='request-form' method='post' action='{REQUESTS_PATH}'>"
"<label>Desired role<select name='desired_role'>"
f"{_options(REQUESTABLE_ROLES, current.get('desired_role'))}"
"</select></label>"
"<label>Work kind<select name='work_kind'>"
f"{_options(WORK_KINDS, current.get('work_kind'))}"
"</select></label>"
"<label>Issue or PR number"
"<input type='number' name='work_number' min='1' required "
f"value='{_escape(number) if number else ''}'></label>"
"<label>Intent summary"
"<input type='text' name='intent_summary' maxlength='500' required "
f"value='{_escape(current.get('intent_summary'))}'></label>"
"<label>Expected head SHA <span class='muted'>(PR work only)</span>"
"<input type='text' name='expected_head_sha' "
f"value='{_escape(current.get('expected_head_sha'))}'></label>"
"<button type='submit' class='copy-btn'>Preview request</button>"
"<p class='muted meta'>Preview is read-only and creates no assignment. "
f"Initiating requires a confirmed POST to <code>{APPLY_API_PATH}</code>."
"</p>"
"</form>"
)
def _checks_block(preview: RequestPreview) -> str:
rows = []
for check in preview.checks:
verdict = "PASS" if check.ok else "FAIL"
css = "verdict-ok" if check.ok else "verdict-fail"
rows.append(
"<li class='request-check'>"
f"<span class='{css}'><strong>{verdict}</strong></span> "
f"<code>{_escape(check.name)}</code> — {_escape(check.detail)} "
f"<span class='muted meta'>({_escape(check.reason_code)})</span>"
"</li>"
)
return "<ul>" + "".join(rows) + "</ul>"
def _preview_block(preview: RequestPreview) -> str:
verdict = "AUTHORIZED" if preview.authorized else "DENIED"
prohibited = "".join(
f"<code>{_escape(action)}</code>" for action in preview.prohibited_actions
)
request = preview.request
evidence = json.dumps(preview.allocator_evidence, indent=2, default=str)
return (
"<h3>Intent preview</h3>"
f"<p><strong>{verdict}</strong> — {_escape(preview.detail)}</p>"
"<p class='meta'>"
f"Role <code>{_escape(request.desired_role)}</code> · "
f"{_escape(request.work_kind)} <code>{_escape(request.display_ref)}</code>"
f" · profile <code>{_escape(preview.required_profile)}</code> · "
f"namespace <code>{_escape(preview.required_namespace)}</code> · "
f"permission <code>{_escape(preview.required_permission)}</code>"
"</p>"
f"<p>Intent: {_escape(request.intent_summary)}</p>"
f"{_checks_block(preview)}"
f"<p><strong>Next safe action:</strong> "
f"{_escape(preview.next_safe_action)}</p>"
"<p class='request-prohibited'><strong>Prohibited for this role:</strong> "
+ (prohibited or "<span class='muted'>none declared</span>")
+ "</p>"
"<p class='muted meta'>Correlation id "
f"<code>{_escape(preview.correlation_id)}</code></p>"
"<details><summary>Allocator evidence</summary>"
f"<pre class='prompt-text'>{_escape(evidence)}</pre>"
"</details>"
)
def _error_block(error: RequestError) -> str:
field = (
f"<p class='meta'>Field: <code>{_escape(error.field_name)}</code></p>"
if error.field_name
else ""
)
return (
"<h3>Request rejected</h3>"
f"<p><strong>{_escape(error.reason_code)}</strong> — "
f"{_escape(error.detail)}</p>{field}"
)
def render_requests_page(
*,
preview: RequestPreview | None = None,
error: RequestError | None = None,
submitted: dict[str, Any] | None = None,
) -> str:
"""Render the request form, plus a preview or rejection when one exists."""
body = (
"<h2>Requests</h2>"
"<p>Submit a work request — desired role, issue or PR, and intent — "
"and see whether it would be authorized before anything is reserved. "
"Initiation goes through the allocator (#600/#613); this console never "
"self-selects work, never approves, and never merges.</p>"
+ _form(submitted)
+ (_error_block(error) if error is not None else "")
+ (_preview_block(preview) if preview is not None else "")
+ f"<p class='meta'><a href='{PREVIEW_API_PATH}'>Preview API</a> · "
"<a href='/api/console/security-model'>RBAC model</a></p>"
+ REQUEST_PAGE_STYLES
)
return render_page(title="Requests", body_html=body)
+1 -19
View File
@@ -38,7 +38,6 @@ from dataclasses import asdict, dataclass
from typing import Any from typing import Any
import mcp_namespace_health import mcp_namespace_health
import restart_coordinator
import runtime_recovery_guard import runtime_recovery_guard
from webui import console_audit, console_authz from webui import console_audit, console_authz
@@ -100,14 +99,6 @@ def _clean(value: Any) -> str:
return str(value or "").strip() return str(value or "").strip()
def restart_class_for_mode(mode: str) -> str:
"""Map the existing namespace controls onto the #663 class taxonomy."""
if _clean(mode) == MODE_RELOAD:
return restart_coordinator.RestartClass.CONFIGURATION_RELOAD.value
return restart_coordinator.RestartClass.ROLE_RUNTIME_RESTART.value
# --- Mutation ledger -------------------------------------------------------- # --- Mutation ledger --------------------------------------------------------
@@ -265,7 +256,6 @@ def build_restart_preview(
return { return {
"action_id": action_id, "action_id": action_id,
"restart_class": restart_class_for_mode(md),
"namespace": ns, "namespace": ns,
"mode": md, "mode": md,
"scope_valid": scope_error is None, "scope_valid": scope_error is None,
@@ -319,7 +309,6 @@ def assess_restart_request(
"reason_code": reason_code, "reason_code": reason_code,
"detail": detail, "detail": detail,
"action_id": action_id, "action_id": action_id,
"restart_class": restart_class_for_mode(md),
"namespace": ns, "namespace": ns,
"mode": md, "mode": md,
"preview": preview, "preview": preview,
@@ -404,7 +393,6 @@ def assess_restart_request(
"process." "process."
), ),
"action_id": action_id, "action_id": action_id,
"restart_class": restart_class_for_mode(md),
"namespace": ns, "namespace": ns,
"mode": md, "mode": md,
"preview": preview, "preview": preview,
@@ -453,11 +441,7 @@ def execute_restart(
else console_audit.RESULT_DENIED else console_audit.RESULT_DENIED
), ),
principal=principal, principal=principal,
target={ target={"namespace": assessment["namespace"], "mode": assessment["mode"]},
"namespace": assessment["namespace"],
"mode": assessment["mode"],
"restart_class": assessment["restart_class"],
},
reason_code=assessment["reason_code"], reason_code=assessment["reason_code"],
detail=assessment["detail"], detail=assessment["detail"],
request_id=request_id, request_id=request_id,
@@ -466,7 +450,6 @@ def execute_restart(
"gates_passed": assessment["gates_passed"], "gates_passed": assessment["gates_passed"],
"process_kill_executed": False, "process_kill_executed": False,
"post_restart_verification_required": True, "post_restart_verification_required": True,
"restart_class": assessment["restart_class"],
}, },
) )
@@ -480,7 +463,6 @@ def execute_restart(
"namespace": assessment["namespace"], "namespace": assessment["namespace"],
"mode": assessment["mode"], "mode": assessment["mode"],
"action_id": action_id, "action_id": action_id,
"restart_class": assessment["restart_class"],
"process_kill_executed": False, "process_kill_executed": False,
"host_hook": assessment["preview"]["restart_hook"], "host_hook": assessment["preview"]["restart_hook"],
"next_action": ( "next_action": (
-10
View File
@@ -201,16 +201,6 @@ def _candidates_from_queue_snapshot(q_snap: QueueSnapshot) -> list[WorkCandidate
return candidates return candidates
def candidates_from_queue_snapshot(q_snap: QueueSnapshot) -> list[WorkCandidate]:
"""Public alias for :func:`_candidates_from_queue_snapshot` (#643).
The request-initiation service ranks the same candidate set this view
renders, so both must agree on how a queue row becomes a candidate. One
construction, two callers not two that can drift apart.
"""
return _candidates_from_queue_snapshot(q_snap)
def _claim_lease_records(inventory: dict[str, Any] | None) -> list[dict[str, Any]]: def _claim_lease_records(inventory: dict[str, Any] | None) -> list[dict[str, Any]]:
"""Normalize ``build_claim_inventory`` entries into lease records. """Normalize ``build_claim_inventory`` entries into lease records.