Compare commits

..
Author SHA1 Message Date
sysadmin 653a728bb5 style: fix trailing newline in mcp_namespace_health.py 2026-07-09 12:56:19 -04:00
sysadmin 8c4dc007be Merge branch 'docs/issue-543-mcp-eof-recovery' into feat/issue-543-mcp-namespace-health-check 2026-07-09 12:51:22 -04:00
sysadmin b0b35a81ee Merge branch 'master' into feat/issue-543-mcp-namespace-health-check 2026-07-09 12:51:07 -04:00
sysadminandClaude Opus 4.8 efa7190041 docs: add MCP namespace client is closing: EOF recovery runbook (#543)
Adds docs/mcp-namespace-eof-recovery.md documenting the correct recovery
path when a Gitea MCP namespace (gitea-author/reviewer/merger/tools)
returns `client is closing: EOF`.

Satisfies acceptance criterion 7 of #543: symptom, root cause (closed
client transport vs a live-but-stale process), the sanctioned
reconnect/relaunch sequence, diagnostics to capture, and how
test_mcp_conn.py reproduces the registered-vs-callable gap. Distinguishes
this transport-close failure from the ps-based stale-runtime family in
#531/#544 and reinforces the no-direct-import guard (#558).

Docs-only; no code or test behavior changed.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
2026-07-09 11:55:42 -04:00
sysadminandClaude Opus 4.8 287e0c5e65 feat: enforce live-namespace block in review/merge state machine (#543 AC5)
The namespace health check (05fdcee) classified a false-ready namespace but
only returned an advisory blocks_merge_workflow flag; nothing in the merge
gate consumed it. Wire it in so a broken live namespace hard-blocks merge.

- review_merge_state_machine.assess_workflow_blockers: add live_namespace_broken
  blocker (registered-in-FastMCP but not callable-through-namespace).
- assess_state_advancement: forward **blocker_kwargs so can_approve/can_merge/
  workflow_status honor the full blocker set (also fixes latent drop of
  mcp_reconnect_failed/stale_capability_state through those paths).
- gitea_assess_review_merge_state_machine tool: accept live_namespace_broken and
  thread it through all state-machine calls.
- Tests: prove can_merge/workflow_status/tool block on live_namespace_broken even
  with every review state + pre-merge gate satisfied; bridge classify verdict.
- Docs: enforcement section wiring blocks_merge_workflow -> live_namespace_broken.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
2026-07-09 11:15:02 -04:00
sysadmin 05fdceee5f feat: diagnose live MCP namespace EOF health 2026-07-09 10:59:34 -04:00
88 changed files with 464 additions and 19462 deletions
-610
View File
@@ -1,610 +0,0 @@
"""Controller-owned work allocator policy (#600).
Builds on the #613 control-plane DB substrate (``ControlPlaneDB.assign_and_lease``).
Workers must not self-select exclusive work under the standard multi-LLM
workflow. They call ``gitea_allocate_next_work`` which:
1. Inspects candidate Gitea issues/PRs (never raw monitoring incidents).
2. Applies ADR routing policy (role, terminal path, leases, blocked, deps).
3. Atomically assigns + leases the selected item in one DB transaction.
This module is pure selection + substrate orchestration. Gitea I/O for live
inventory lives in the MCP tool wrapper so tests can inject candidates.
#612 remains downstream: bridge-created Gitea issues become candidates only
after they exist as normal issues; this module never assigns incidents.
"""
from __future__ import annotations
import os
import uuid
from dataclasses import dataclass, field
from typing import Any, Sequence
from control_plane_db import (
ControlPlaneDB,
ControlPlaneError,
InvalidWorkKindError,
LeaseRequiredError,
WORK_KINDS,
)
# Outcomes required by #600 / ADR §5.
OUTCOME_ASSIGNED = "assigned_work"
OUTCOME_WAIT = "wait"
OUTCOME_BLOCKED_TERMINAL = "blocked_by_terminal_path"
OUTCOME_BLOCKED_LEASE = "blocked_by_active_lease"
OUTCOME_NEEDS_CONTROLLER = "needs_controller"
OUTCOME_NO_SAFE = "no_safe_work"
OUTCOME_ROLE_INELIGIBLE = "role_ineligible"
OUTCOME_PREVIEW = "preview" # dry-run only (apply=false)
ROLE_AUTHOR = "author"
ROLE_REVIEWER = "reviewer"
ROLE_MERGER = "merger"
ROLE_RECONCILER = "reconciler"
ROLE_CONTROLLER = "controller"
VALID_ROLES = frozenset(
{ROLE_AUTHOR, ROLE_REVIEWER, ROLE_MERGER, ROLE_RECONCILER, ROLE_CONTROLLER}
)
# Default action matrices by role (mutation gate will re-check).
ROLE_ACTIONS: dict[str, tuple[tuple[str, ...], tuple[str, ...]]] = {
ROLE_AUTHOR: (
("implement", "comment", "push", "create_pr"),
("approve", "merge", "request_changes", "self_select_without_assignment"),
),
ROLE_REVIEWER: (
("review", "comment", "approve", "request_changes"),
("merge", "push", "create_pr", "self_select_without_assignment"),
),
ROLE_MERGER: (
("merge", "comment"),
("approve", "request_changes", "push", "create_pr", "self_select_without_assignment"),
),
ROLE_RECONCILER: (
("comment", "diagnose", "cleanup"),
("approve", "merge", "push", "create_pr", "self_select_without_assignment"),
),
ROLE_CONTROLLER: (
("comment", "diagnose", "allocate"),
("approve", "merge", "push", "create_pr"),
),
}
@dataclass
class WorkCandidate:
"""One assignable Gitea issue or PR presented to the allocator."""
kind: str # issue | pr
number: int
state: str = "open"
labels: tuple[str, ...] = ()
title: str = ""
priority: int = 0
head_sha: str | None = None
# Routing signals (callers derive from Gitea / review feedback).
request_changes_current_head: bool = False
approval_on_current_head: bool = False
approval_stale: bool = False
approval_contaminated: bool = False
mergeable: bool = False
blocked: bool = False
dependency_unmet: bool = False
dependency_reason: str | None = None
already_claimed_elsewhere: bool = False
def __post_init__(self) -> None:
self.kind = (self.kind or "").strip().lower()
self.state = (self.state or "open").strip().lower()
self.labels = tuple(
str(x).strip().lower() for x in (self.labels or ()) if str(x).strip()
)
if self.kind not in WORK_KINDS:
raise InvalidWorkKindError(
f"candidate kind '{self.kind}' is not assignable; only "
f"{sorted(WORK_KINDS)} (never raw incidents)"
)
def as_dict(self) -> dict[str, Any]:
return {
"kind": self.kind,
"number": self.number,
"state": self.state,
"labels": list(self.labels),
"title": self.title,
"priority": self.priority,
"head_sha": self.head_sha,
"request_changes_current_head": self.request_changes_current_head,
"approval_on_current_head": self.approval_on_current_head,
"approval_stale": self.approval_stale,
"approval_contaminated": self.approval_contaminated,
"mergeable": self.mergeable,
"blocked": self.blocked,
"dependency_unmet": self.dependency_unmet,
"dependency_reason": self.dependency_reason,
}
@dataclass
class SkipRecord:
kind: str
number: int
reason: str
def as_dict(self) -> dict[str, Any]:
return {"kind": self.kind, "number": self.number, "reason": self.reason}
def normalize_role(role: str | None, *, profile_name: str | None = None) -> str:
"""Map profile/role strings to a canonical allocator role."""
raw = (role or "").strip().lower()
if raw in VALID_ROLES:
return raw
prof = (profile_name or "").strip().lower()
for token in VALID_ROLES:
if token in prof or prof.endswith(f"-{token}"):
return token
if "author" in raw:
return ROLE_AUTHOR
if "review" in raw:
return ROLE_REVIEWER
if "merg" in raw:
return ROLE_MERGER
if "reconcil" in raw:
return ROLE_RECONCILER
if "control" in raw:
return ROLE_CONTROLLER
raise ControlPlaneError(
f"unknown allocator role '{role}' (profile={profile_name!r}); "
f"expected one of {sorted(VALID_ROLES)}"
)
def expected_role_for_candidate(c: WorkCandidate) -> str:
"""ADR §5.3 routing: which role should take this work next."""
if c.kind == "pr":
if c.approval_contaminated:
return ROLE_RECONCILER
if c.request_changes_current_head:
return ROLE_AUTHOR
if c.approval_stale:
return ROLE_REVIEWER
if c.approval_on_current_head and c.mergeable:
return ROLE_MERGER
# Open PR without terminal verdict → reviewer
return ROLE_REVIEWER
# Issues: ready work → author by default; blocked stays controller/none
labels = set(c.labels)
if "status:blocked" in labels or c.blocked:
return ROLE_CONTROLLER
return ROLE_AUTHOR
def role_actions(role: str) -> tuple[tuple[str, ...], tuple[str, ...]]:
return ROLE_ACTIONS.get(role, ROLE_ACTIONS[ROLE_AUTHOR])
def classify_skip(
c: WorkCandidate,
*,
role: str,
terminal_pr: int | None,
) -> str | None:
"""Return skip reason, or None if candidate is selectable for *role*."""
if c.state in ("merged", "closed"):
return f"{c.kind}#{c.number} is {c.state}; never assign"
if c.blocked or "status:blocked" in c.labels:
return f"{c.kind}#{c.number} is blocked"
if c.dependency_unmet:
return (
c.dependency_reason
or f"{c.kind}#{c.number} has unmet dependencies"
)
if c.already_claimed_elsewhere:
return f"{c.kind}#{c.number} already claimed elsewhere"
if c.kind == "pr" and not (c.head_sha or "").strip():
return f"pr#{c.number} missing head_sha pin"
# Terminal path first: when an active terminal PR exists, only that PR
# (or controller diagnosis) is assignable for review-path roles.
if terminal_pr is not None and c.kind == "pr" and c.number != terminal_pr:
if role in (ROLE_REVIEWER, ROLE_MERGER):
return (
f"pr#{c.number} skipped: active terminal-review lock on "
f"PR #{terminal_pr} must be resolved first"
)
expected = expected_role_for_candidate(c)
if role == ROLE_CONTROLLER:
# Controller may inspect anything but only assigns diagnosis targets
# when contaminated / blocked.
if expected == ROLE_RECONCILER or c.blocked:
return None
return f"{c.kind}#{c.number} does not require controller (expected {expected})"
if role != expected:
return (
f"{c.kind}#{c.number} expects role '{expected}', active role is '{role}'"
)
# Ready-gate for issues: prefer status:ready when labels present.
if c.kind == "issue" and c.labels:
if "status:ready" not in c.labels and "status:in-progress" not in c.labels:
# Allow unlabeled open issues; only skip explicit non-ready states.
if any(l.startswith("status:") for l in c.labels):
return f"issue#{c.number} not status:ready ({','.join(c.labels)})"
return None
def sort_candidates(candidates: Sequence[WorkCandidate]) -> list[WorkCandidate]:
"""Higher priority first; then lower number (older issues) for stability."""
return sorted(
candidates,
key=lambda c: (-int(c.priority), c.kind != "pr", int(c.number)),
)
def allocate_next_work(
db: ControlPlaneDB,
*,
session_id: str,
role: str,
remote: str,
org: str,
repo: str,
candidates: Sequence[WorkCandidate],
apply: bool = False,
profile_name: str | None = None,
username: str | None = None,
lease_ttl_seconds: int | None = None,
) -> dict[str, Any]:
"""Select and optionally reserve the next work unit via control-plane DB.
*apply=False* (default): dry-run selection only — no lease/assignment.
*apply=True*: atomic ``assign_and_lease`` for the selected candidate.
Never uses file locks or comment-only leases as the assignment source.
"""
if db is None:
return {
"success": False,
"outcome": OUTCOME_NO_SAFE,
"reasons": [
"control-plane DB substrate unavailable (fail closed, #600/#613)"
],
"skipped": [],
"assignment": None,
"substrate": "control_plane_db",
"file_lock_only": False,
"comment_lease_only": False,
}
try:
role_norm = normalize_role(role, profile_name=profile_name)
except ControlPlaneError as exc:
return {
"success": False,
"outcome": OUTCOME_ROLE_INELIGIBLE,
"reasons": [str(exc)],
"skipped": [],
"assignment": None,
"substrate": "control_plane_db",
}
session_id = (session_id or "").strip() or f"alloc-{uuid.uuid4().hex[:12]}"
try:
db.upsert_session(
session_id=session_id,
role=role_norm,
profile=profile_name,
pid=os.getpid(),
)
except Exception as exc: # noqa: BLE001 — surface structured
return {
"success": False,
"outcome": OUTCOME_NO_SAFE,
"reasons": [
f"failed to register session in control-plane DB: {exc} "
"(fail closed, #613)"
],
"skipped": [],
"assignment": None,
"substrate": "control_plane_db",
}
# Expire stale leases globally before selection.
try:
db.expire_stale_leases()
except Exception as exc: # noqa: BLE001
return {
"success": False,
"outcome": OUTCOME_NO_SAFE,
"reasons": [f"lease expiry failed: {exc} (fail closed)"],
"skipped": [],
"assignment": None,
"substrate": "control_plane_db",
}
terminal = None
try:
terminal = db.get_active_terminal_lock(remote=remote, org=org, repo=repo)
except Exception as exc: # noqa: BLE001
return {
"success": False,
"outcome": OUTCOME_NO_SAFE,
"reasons": [f"terminal lock lookup failed: {exc} (fail closed)"],
"skipped": [],
"assignment": None,
"substrate": "control_plane_db",
}
terminal_pr = int(terminal["terminal_pr"]) if terminal else None
skipped: list[SkipRecord] = []
ordered = sort_candidates(list(candidates))
selected: WorkCandidate | None = None
for c in ordered:
reason = classify_skip(c, role=role_norm, terminal_pr=terminal_pr)
if reason:
skipped.append(SkipRecord(c.kind, c.number, reason))
continue
selected = c
break
if selected is None:
# If terminal lock blocks all review work, surface that explicitly.
if terminal_pr is not None and role_norm in (ROLE_REVIEWER, ROLE_MERGER):
outcome = OUTCOME_BLOCKED_TERMINAL
reasons = [
f"no safe work for role '{role_norm}': active terminal-review "
f"lock on PR #{terminal_pr} (resolve terminal path first, #332/#600)"
]
else:
outcome = OUTCOME_NO_SAFE
reasons = [
f"no safe assignable work for role '{role_norm}' "
f"among {len(ordered)} candidates"
]
return {
"success": True,
"outcome": outcome,
"apply": bool(apply),
"role": role_norm,
"profile_name": profile_name,
"username": username,
"session_id": session_id,
"remote": remote,
"org": org,
"repo": repo,
"selected": None,
"expected_role_next": None,
"reasons": reasons,
"skipped": [s.as_dict() for s in skipped],
"terminal_pr": terminal_pr,
"assignment": None,
"substrate": "control_plane_db",
"file_lock_only": False,
"comment_lease_only": False,
"downstream_note": (
"#612 incident bridge remains downstream of #600; "
"allocator never assigns raw monitoring incidents"
),
}
expected_role = expected_role_for_candidate(selected)
allowed, forbidden = role_actions(role_norm)
selection = {
"kind": selected.kind,
"number": selected.number,
"title": selected.title,
"labels": list(selected.labels),
"head_sha": selected.head_sha,
"priority": selected.priority,
"expected_role_next": expected_role,
"reason_selected": (
f"highest-priority candidate for role '{role_norm}' "
f"(expected_role={expected_role})"
),
}
if not apply:
return {
"success": True,
"outcome": OUTCOME_PREVIEW,
"apply": False,
"role": role_norm,
"profile_name": profile_name,
"username": username,
"session_id": session_id,
"remote": remote,
"org": org,
"repo": repo,
"selected": selection,
"expected_role_next": expected_role,
"reasons": [
"dry-run only (apply=false); no assignment/lease created — "
"call again with apply=true to reserve via control-plane DB"
],
"skipped": [s.as_dict() for s in skipped],
"terminal_pr": terminal_pr,
"assignment": None,
"substrate": "control_plane_db",
"file_lock_only": False,
"comment_lease_only": False,
"downstream_note": (
"#612 incident bridge remains downstream of #600; "
"allocator never assigns raw monitoring incidents"
),
}
# Atomic reserve via #613 substrate.
ttl = lease_ttl_seconds if lease_ttl_seconds is not None else None
try:
kwargs: dict[str, Any] = {
"session_id": session_id,
"role": role_norm,
"remote": remote,
"org": org,
"repo": repo,
"kind": selected.kind,
"number": selected.number,
"expected_head_sha": selected.head_sha,
"allowed_actions": allowed,
"forbidden_actions": forbidden,
"phase": "allocated",
}
if ttl is not None:
kwargs["lease_ttl_seconds"] = int(ttl)
result = db.assign_and_lease(**kwargs)
except (InvalidWorkKindError, LeaseRequiredError, ControlPlaneError) as exc:
return {
"success": False,
"outcome": OUTCOME_NO_SAFE,
"apply": True,
"role": role_norm,
"session_id": session_id,
"remote": remote,
"org": org,
"repo": repo,
"selected": selection,
"expected_role_next": expected_role,
"reasons": [f"atomic assign+lease failed: {exc} (fail closed, #613)"],
"skipped": [s.as_dict() for s in skipped],
"terminal_pr": terminal_pr,
"assignment": None,
"substrate": "control_plane_db",
"file_lock_only": False,
"comment_lease_only": False,
}
if result.outcome == "wait":
return {
"success": True,
"outcome": OUTCOME_WAIT,
"apply": True,
"role": role_norm,
"session_id": session_id,
"remote": remote,
"org": org,
"repo": repo,
"selected": selection,
"expected_role_next": expected_role,
"reasons": [result.reason or "foreign active lease"],
"skipped": [s.as_dict() for s in skipped],
"terminal_pr": terminal_pr,
"assignment": result.as_dict(),
"owner_session_id": result.owner_session_id,
"substrate": "control_plane_db",
"file_lock_only": False,
"comment_lease_only": False,
}
if result.outcome == "no_safe_work":
return {
"success": True,
"outcome": OUTCOME_NO_SAFE,
"apply": True,
"role": role_norm,
"session_id": session_id,
"remote": remote,
"org": org,
"repo": repo,
"selected": selection,
"expected_role_next": expected_role,
"reasons": [result.reason or "no_safe_work"],
"skipped": [s.as_dict() for s in skipped],
"terminal_pr": terminal_pr,
"assignment": result.as_dict(),
"substrate": "control_plane_db",
"file_lock_only": False,
"comment_lease_only": False,
}
# assigned
return {
"success": True,
"outcome": OUTCOME_ASSIGNED,
"apply": True,
"role": role_norm,
"profile_name": profile_name,
"username": username,
"session_id": session_id,
"remote": remote,
"org": org,
"repo": repo,
"selected": selection,
"expected_role_next": expected_role,
"reasons": [
selection["reason_selected"],
result.reason or "atomic assign+lease created",
],
"skipped": [s.as_dict() for s in skipped],
"terminal_pr": terminal_pr,
"assignment": result.as_dict(),
"lease_proof": {
"assignment_id": result.assignment_id,
"lease_id": result.lease_id,
"expires_at": result.expires_at,
"expected_head_sha": result.expected_head_sha,
"allowed_actions": list(result.allowed_actions),
"forbidden_actions": list(result.forbidden_actions),
"source": "control_plane_db.assign_and_lease",
},
"next_valid_command": _next_command(role_norm, selected),
"substrate": "control_plane_db",
"file_lock_only": False,
"comment_lease_only": False,
"downstream_note": (
"#612 incident bridge remains downstream of #600; "
"allocator never assigns raw monitoring incidents"
),
}
def _next_command(role: str, c: WorkCandidate) -> str:
if role == ROLE_AUTHOR and c.kind == "issue":
return f"implement issue #{c.number} under a branches/ worktree; open PR when ready"
if role == ROLE_AUTHOR and c.kind == "pr":
return (
f"address REQUEST_CHANGES on PR #{c.number} at head "
f"{(c.head_sha or '')[:12]} and push fixes"
)
if role == ROLE_REVIEWER:
return (
f"review PR #{c.number} pinned at head {(c.head_sha or '')[:12]} "
"via full reviewer workflow"
)
if role == ROLE_MERGER:
return (
f"merge PR #{c.number} only with explicit operator MERGE "
f"authorization at head {(c.head_sha or '')[:12]}"
)
if role == ROLE_RECONCILER:
return f"diagnose contested state for {c.kind}#{c.number}"
return f"proceed on {c.kind}#{c.number} under role {role}"
def candidate_from_dict(data: dict[str, Any]) -> WorkCandidate:
"""Build a WorkCandidate from a plain dict (tests / MCP inventory)."""
return WorkCandidate(
kind=str(data.get("kind") or "issue"),
number=int(data["number"]),
state=str(data.get("state") or "open"),
labels=tuple(data.get("labels") or ()),
title=str(data.get("title") or ""),
priority=int(data.get("priority") or 0),
head_sha=data.get("head_sha"),
request_changes_current_head=bool(data.get("request_changes_current_head")),
approval_on_current_head=bool(data.get("approval_on_current_head")),
approval_stale=bool(data.get("approval_stale")),
approval_contaminated=bool(data.get("approval_contaminated")),
mergeable=bool(data.get("mergeable")),
blocked=bool(data.get("blocked")),
dependency_unmet=bool(data.get("dependency_unmet")),
dependency_reason=data.get("dependency_reason"),
already_claimed_elsewhere=bool(data.get("already_claimed_elsewhere")),
)
-1751
View File
File diff suppressed because it is too large Load Diff
-63
View File
@@ -1,63 +0,0 @@
"""Controller-closure baseline-proof gate (#529, criterion 6).
A controller (or any session) may close a tracking issue with a closure
report that summarizes validation. When that report calls a non-zero
test-suite exit an "expected pre-existing failure" (or baseline / known
failure) it must carry pre-merge proof; otherwise the closure buries an
unproven regression as an accepted baseline and weakens controller
confidence in the durable state.
This module fails closed on exactly that case by reusing the pre-merge
baseline proof verifier (#533). A closure report is allowed when it is
empty (no validation claim), a clean pass, or a baseline failure proven on
the PR pre-merge base commit (or a documented known-failure record that
predates the PR).
"""
from __future__ import annotations
from typing import Any
from premerge_baseline_proof import CLEAN_PASS, assess_premerge_baseline_proof
def assess_controller_closure_baseline_proof(
closure_report: str | None,
) -> dict[str, Any]:
"""Assess whether an issue-closure report may proceed.
Returns a dict with ``block``, ``proven``, ``label``, ``reasons``,
``skipped`` and ``safe_next_action``. Only blocks when the closure
report claims a non-zero validation exit is an expected
pre-existing/baseline failure without valid pre-merge proof.
"""
text = (closure_report or "").strip()
if not text:
return {
"block": False,
"proven": True,
"label": CLEAN_PASS,
"reasons": [],
"skipped": True,
"safe_next_action": "",
}
result = assess_premerge_baseline_proof(text)
block = bool(result.get("block"))
return {
"block": block,
"proven": not block,
"label": result.get("label"),
"reasons": list(result.get("reasons") or []),
"skipped": bool(result.get("skipped", False)),
"safe_next_action": (
result.get("safe_next_action")
or (
"provide pre-merge baseline proof (base commit, tested commit, "
"command, exit status, failure signature) before closing on an "
"expected pre-existing failure"
)
)
if block
else "",
}
@@ -1,105 +0,0 @@
# Control-plane DB substrate (#613)
**Status:** Implemented (SQLite single-writer MVP)
**ADR:** [`mcp-allocator-control-plane-observability-adr.md`](mcp-allocator-control-plane-observability-adr.md)
**Module:** `control_plane_db.py`
## Architecture statement
> **DB coordinates, Gitea records, Sentry/GlitchTip observe; the bridge is the only path that turns observations into Gitea work.**
## What this ships
| Capability | Notes |
|------------|--------|
| Schema | `sessions`, `work_items`, `leases`, `assignments`, `terminal_locks`, `events`, `incident_links` |
| Atomic assign+lease | `ControlPlaneDB.assign_and_lease` — one `BEGIN IMMEDIATE` transaction |
| Mutation gate | `require_valid_assignment` — live lease + allowed action + non-terminal work + non-stale head |
| Heartbeat / release / expire | Lease lifecycle helpers |
| Terminal-lock index | Routing signal for #600 (terminal path first) |
| `incident_links` | Provider-neutral link model for #612**not** assignable work; scope keys NULL-safe |
## Hard rules (enforced in code)
1. Assignable `work_items.kind` ∈ {`issue`, `pr`} only — **never** raw Sentry/GlitchTip incidents.
2. Two concurrent sessions cannot both receive an active assignment on the same open work item (second gets `wait`).
3. Merged/closed work items return `no_safe_work` at assign time, and `require_valid_assignment` fails closed if the work item becomes terminal later.
4. Assignments pin `expected_head_sha`; mutations fail closed if the work item head drifts.
5. SQLite path is the **single-writer MVP** (`GITEA_CONTROL_PLANE_DB`, default under `~/.cache/gitea-tools/control-plane/`). Multi-session multi-host production requires **Postgres** or a **single allocator daemon** (ADR §6).
6. `incident_links` optional scope fields are stored as empty strings (never NULL) so UNIQUE is canonical across minimal upserts.
7. Legacy `incident_links` migration collapses NULL-scope duplicates **only** when Gitea targets **and** all meaningful observation metadata agree (fingerprint, status, event_count, permalink, timestamps, linked PRs, etc.). Conflicting metadata fails closed — no silent discard.
## Dependency chain
```text
#613 control-plane DB (this) → #600 allocator API → #612 incident bridge
```
- **#600** must call this substrate (not file locks / comment-only leases alone) for completion.
- **#612** must write `incident_links` here and create **Gitea issues**; the allocator assigns those issues, not raw incidents.
## Allocator API (#600)
Module: `allocator_service.py` · MCP tool: `gitea_allocate_next_work`
- Workers call `gitea_allocate_next_work(apply=false|true)` instead of self-selecting work.
- `apply=false` returns a dry-run selection (`outcome=preview`) with skip reasons.
- `apply=true` reserves via `ControlPlaneDB.assign_and_lease` (atomic assignment+lease).
- Coordination source is **always** the control-plane DB — not file locks or comment-only leases.
- Routing follows ADR §5.3 (REQUEST_CHANGES → author, terminal path first, foreign lease → wait).
- Raw monitoring incidents are never candidates.
## Lease lifecycle API (#601)
Module: `lease_lifecycle.py` · MCP tools: `gitea_*_workflow_lease(s)`
Active control-plane leases are **first-class workflow state**:
| Tool | Purpose |
|------|---------|
| `gitea_list_workflow_leases` | List active (or all) leases for a repo |
| `gitea_inspect_workflow_lease` | Freshness + `safe_next_action` for one lease id |
| `gitea_adopt_workflow_lease` | Owner-resume or sanctioned reclaim with provenance |
| `gitea_release_workflow_lease` | Explicit owner release (audited) |
| `gitea_expire_workflow_leases` | Deterministic expire of past-`expires_at` leases |
| `gitea_abandon_workflow_lease` | Abandon with required proof |
| `gitea_reclaim_expired_workflow_lease` | Expire + re-assign with provenance |
### Hard rules
1. Control-plane DB is the coordination authority — file locks / comment-only leases are not authoritative alone.
2. Active foreign leases cannot be stolen; inspect returns `wait_foreign_active`.
3. Abandon requires `(dead_process OR missing_worktree)` and `no_live_mutation_risk`; foreign abandon also needs `operator_authorized` or full dead+missing+no_open_pr proof.
4. Adopt provenance always records `adopted_from_session_id`, `adopted_by_session_id`, work identity, optional head SHA, and worktree path.
5. Reviewer→merger comment handoff (`gitea_adopt_merger_pr_lease`) is unchanged and remains the Gitea-thread durability path.
```bash
python3 -m pytest tests/test_lease_lifecycle.py tests/test_control_plane_db.py tests/test_allocator_service.py tests/test_merger_lease_adoption.py -q
```
## Incident bridge (#612)
Module: `incident_bridge.py` · MCP tools: `gitea_observability_*`
- Bridge converts Sentry/GlitchTip observations → **normal Gitea issues** + `incident_links`.
- Phase-1: `gitea_observability_reconcile_incident(apply=false|true)` with JSON observation.
- Dry-run performs **no** Gitea mutation and **no** DB write.
- Apply reuses existing links or creates one Gitea issue; never invents `work_items.kind=incident`.
- Config: `GITEA_OBSERVABILITY_PROJECTS_JSON` or `GITEA_OBSERVABILITY_PROJECTS_FILE`.
- Provider tokens never appear in issue bodies, links, or tool results.
- Allocator sees bridge work only after a Gitea issue exists.
## Non-goals (intentionally deferred)
- Full unsupervised watchdog auto-filing (prefer explicit reconcile first)
- Assuming GlitchTip writeback API equals Sentry without verification
- Gitea comment/label mirror writers for every assignment (optional later)
## Tests
```bash
python3 -m pytest tests/test_control_plane_db.py -q
```
@@ -1,301 +0,0 @@
# ADR: MCP allocator, control-plane DB, and Sentry/GlitchTip incident bridge architecture
- **Status:** Accepted (implementation pending; blocks code for #600 / #612 / #613)
- **Date:** 2026-07-09
- **Tracking issues:**
- [#613](https://gitea.prgs.cc/Scaled-Tech-Consulting/Gitea-Tools/issues/613) — control-plane DB (first)
- [#600](https://gitea.prgs.cc/Scaled-Tech-Consulting/Gitea-Tools/issues/600) — allocator API (second)
- [#612](https://gitea.prgs.cc/Scaled-Tech-Consulting/Gitea-Tools/issues/612) — Sentry/GlitchTip incident bridge (third)
- **Related:** existing GlitchTip contracts (`glitchtip-to-gitea-workflow-design.md`, `glitchtip-gitea-deduplication-linking-design.md`), trust boundaries (`tool-boundaries.md`, `safety-model.md`), current leases (`pr_work_lease.py`, `issue_lock_store.py`)
## 1. Context
Multiple LLM sessions can independently inspect the Gitea queue and start the same issue or PR. Existing coordination (Gitea comment leases, local issue-lock files, labels) often detects collisions **after** work has started. Parallel issues #600, #612, and #613 each describe part of a fix; without one ADR they risk overlapping stores, wrong dependency order, and trust-boundary violations.
This ADR is the canonical architecture decision **before** implementing those issues.
## 2. Decision summary (core)
| Layer | Owns | Must not |
|-------|------|----------|
| **Control-plane DB** | Sessions, atomic assignment, leases, heartbeats, terminal-lock index, events, incident links | Bypass Gitea workflow gates or replace issue/PR history |
| **Gitea** | Durable work record: issues, PRs, comments, labels, reviews, merges | Be the only concurrency lock under multi-session load |
| **Sentry / GlitchTip** | Incidents, events, provider UI | Assign work, approve/merge/close, or mutate Gitea outside the bridge |
| **Incident bridge** | Provider adapters, reconcile/create Gitea issues, link storage upsert, optional provider writeback | Hand raw provider incidents to the allocator as work items |
**One-liner:** **DB coordinates. Gitea records. Sentry/GlitchTip observe. The bridge is the only path that turns observations into Gitea work. The allocator assigns only Gitea issues/PRs, never raw monitoring incidents.**
## 3. Dependency order
Implementation **must** follow:
```text
#613 control-plane DB → #600 allocator API → #612 incident bridge
(atomic substrate) (routing policy) (feeds Gitea work)
```
| Issue | Role | Depends on |
|-------|------|------------|
| **#613** | Durable coordination DB + lease/assignment transactions | — |
| **#600** | `gitea_allocate_next_work` policy and tool surface | **#613** (hard) |
| **#612** | Multi-project Sentry/GlitchTip → Gitea bridge | **#613** for `incident_links` index; **#600** before treating bridge-created issues as allocator feed in multi-worker prod |
**Hard rules:**
1. Do **not** implement #600 on file locks / comment-only leases and call it done.
2. Do **not** ship #612 as a second assignment system for raw incidents.
3. Partial previews (read-only list tools, schema stubs) may land earlier if they do not claim “allocator complete” or “bridge complete.”
## 4. Authority boundaries
### 4.1 Gitea (durable source of truth for work)
Gitea remains authoritative for:
- Issue and PR identity, titles, bodies, state (open/closed/merged)
- Comments, reviews, approvals, REQUEST_CHANGES
- Labels and workflow status labels (`status:ready`, `status:in-progress`, …)
- Merges, closes, branch refs as recorded by Gitea/git hosting
Operators and auditors read **history** from Gitea.
### 4.2 Control-plane DB (coordination / index)
The control-plane DB is authoritative for **live multi-session coordination**:
- Which session holds which assignment/lease
- Heartbeat freshness and expiry
- Terminal-lock index for routing
- Event log of allocation/lease transitions
- `incident_links` index (see §8)
It is **not** a substitute for Gitea history. When DB and Gitea disagree on durable work state (e.g. PR already merged), **Gitea wins**; the DB is reconciled.
### 4.3 Sentry / GlitchTip (observe)
Providers own incident lifecycle and raw event data. They:
- Must **not** bypass Gitea gates
- Must **not** assign LLM work
- May receive **writeback** of resolution status only through the bridge, when configured and supported
### 4.4 Trust boundaries for credentials
Aligned with `docs/tool-boundaries.md` and `docs/safety-model.md`:
- **One MCP server process per trust boundary** remains the default.
- Monitor API tokens (Sentry/GlitchTip) live in the **bridge/orchestrator boundary** (or a dedicated observability write/read profile), **not** blindly inside every Gitea MCP author/reviewer/merger process.
- Gitea tokens stay on Gitea MCP profiles only.
- Orchestrators compose services; they must not become a single credential pool that silently mixes Gitea write + monitor tokens into every worker.
Tool names such as `gitea_observability_*` may exist as a **namespace façade** only if the runtime still enforces separate credential scopes (e.g. bridge process vs pure Gitea mutation process).
## 5. Allocator rules (#600 on top of #613)
### 5.1 Worker contract
- Workers **do not self-select** work under the standard multi-LLM workflow.
- Workers call **`gitea_allocate_next_work`** (with `apply=true` only when taking work).
- Mutations that claim exclusive work require a **valid assignment and lease** from the control-plane DB.
- Return values include at least: role, issue/PR number, expected head SHA (when applicable), lease ID, expiry, allowed actions, forbidden actions — or a non-assignment outcome (`WAIT`, terminal-path block, no safe work, needs controller, etc.).
### 5.2 Atomic reserve
- **Assignment creation and lease creation happen in one DB transaction.**
- Two concurrent sessions **must not** receive the same issue/PR as assigned work.
- On contention: second session gets **WAIT** or **owner-resume**, never a duplicate lease.
### 5.3 Routing policy
| Condition | Route |
|-----------|--------|
| Current-head **REQUEST_CHANGES** | **Author** (not reviewer/merger) |
| **Stale** approval (approval not on current head) | **Reviewer** |
| **Clean** approval on current head, mergeable | **Merger** |
| Contested / contaminated approval | **Diagnosis / reconciler** (controller path) |
| Active **foreign** lease | **WAIT** or **owner-resume** |
| **Terminal-review** lock present | **Terminal-path resolution first** before downstream review work |
| Merged / closed PR | **Never assign** |
| Issue locked by sanctioned lease | **Never assign** to another worker unless lease cleanup/adoption is sanctioned |
### 5.4 Relationship to Gitea mirrors
After a successful assignment, the allocator (or sanctioned tooling) may update Gitea comments/labels so humans and audits see state. Those mirrors **are not** the sole lock source.
## 6. Control-plane DB topology (#613)
### 6.1 Preferred architecture (multi-daemon / Proxmox)
For true multi-session concurrency (multiple MCP daemons, multiple hosts, or Proxmox VMs):
**Prefer either:**
1. **Shared Postgres** used by all Gitea MCP profiles / allocator callers, **or**
2. A **single allocator daemon** (sole writer to the coordination store) that all workers call over MCP/RPC.
Both satisfy: one transactional authority for “who has this work item.”
### 6.2 SQLite MVP
SQLite is acceptable **only** for a **single-writer MVP**:
- One process owns writes (allocator daemon or single co-located MCP server), **or**
- Documented single-host single-daemon experiments with file locking and no multi-host claims.
SQLite is **not** sufficient to declare multi-session production readiness when four independent LLM sessions talk to four MCP processes without a shared writer.
### 6.3 Suggested entities (normative shape)
Minimum logical entities (names may vary; semantics must not):
1. **sessions** — session_id, role/profile, namespace, pid, started_at, last_heartbeat_at, status
2. **work_items** — remote/org/repo, kind ∈ {`issue`, `pr`}, number, state, priority, current_head_sha, updated_at
3. **leases** — lease_id, work_item_id, session_id, role, phase, expires_at, heartbeat_at, status
4. **assignments** — assignment_id, work_item_id, session_id, allowed_action(s), expected_head_sha, status
5. **terminal_locks** — repo/org, terminal_pr, review_id, decision, status, cleanup_state
6. **events** — event_id, work_item_id, type, message, created_at
7. **incident_links** — provider-neutral link model (see §8)
**Explicit non-kind:** do **not** use `work_items.kind = sentry_incident` (or glitchtip_incident) as an assignable work unit. Incidents become work only after the bridge creates/links a **Gitea issue**.
## 7. Lease migration (avoid split-brain)
### 7.1 Target state
- **Primary** for live coordination: **control-plane DB** leases and assignments.
- **Gitea comment leases** (e.g. `<!-- mcp-review-lease:v1 -->`) and **local issue-lock files** become:
- **mirrors** of DB state for human visibility / recovery, and/or
- written **only** through the allocator (or sanctioned lease tools that update DB + mirror in one workflow).
### 7.2 Migration rules
1. New exclusive claims go through DB assignment+lease first.
2. Comment lease / file lock writers that skip the DB are **deprecated** once #613+#600 land.
3. Reconciler tooling heals: expired DB lease, orphan Gitea comment, orphan local file — fail closed when ambiguous.
4. **Split-brain is a defect:** “DB free + Gitea comment leased” or “DB leased + Gitea free” must be detectable and reconcilable; production paths must not rely on two independent writers.
### 7.3 Heartbeats
- Heartbeats update the **DB**.
- Optional Gitea summaries must avoid comment spam (periodic summary or edit-in-place policy).
## 8. Observability bridge (#612)
### 8.1 Role
The bridge:
1. Scans configured Sentry and/or GlitchTip projects (multi-project mappings).
2. Deduplicates against existing links / Gitea issues.
3. Creates or updates **normal Gitea issues** (labels, sanitized body, provider URL).
4. Upserts **one** canonical `incident_links` row.
5. Optionally writes resolution status back to the provider when supported.
6. Never approves, merges, closes, or otherwise bypasses Gitea workflow gates.
### 8.2 Allocator interaction
- The allocator sees observability work **only after** a Gitea issue exists (typically `status:ready` + observability labels).
- **Do not assign raw Sentry/GlitchTip incidents** as work items.
- Bridge AC “allocator can see linked issues” means: **as ordinary Gitea issues**, not a special incident queue.
### 8.3 Provider adapters and trust
- Separate **Sentry** and **GlitchTip** adapters; document API differences; do not assume writeback parity.
- Self-hosted base URLs supported (e.g. `https://sentry.prgs.cc`).
- Tokens from environment / secret store only.
- Prefer phase-1 **explicit reconcile / dry-run** before unsupervised watchdog auto-filing, consistent with existing GlitchTip filing safety contracts.
### 8.4 Home of implementation
Filing/orchestration may live in:
- a control-plane / bridge package or profile, and/or
- Gitea-Tools as operator-facing tools that **delegate** to that boundary,
but must not violate §4.4 credential isolation.
## 9. Incident link storage (single source of truth)
### 9.1 Canonical model: `incident_links` (provider-neutral)
Prefer a **provider-neutral** model over Sentry-only `sentry_links`:
| Field (logical) | Purpose |
|-----------------|---------|
| provider | `sentry` \| `glitchtip` \| … |
| provider_base_url | Self-hosted base |
| provider_org / provider_project | Mapping key |
| provider_issue_id / provider_short_id | Provider identity |
| provider_permalink | Human URL |
| fingerprint | Stable dedupe key when available |
| gitea_org / gitea_repo / gitea_issue_number | Linked work |
| linked_pr_numbers | Optional PR association |
| first_seen / last_seen / event_count | Summary metrics (safe) |
| status | link lifecycle |
| release_resolved_at / last_sync_at | Sync bookkeeping |
### 9.2 Gitea as human mirror
- Issue body markers / structured comments (e.g. HTML comment metadata) remain the **human- and audit-visible mirror**.
- They must stay consistent with `incident_links` but are **not** a second independent write path for inventing links without the bridge.
### 9.3 One truth
- **Do not** maintain two independent systems of record (e.g. full mapping only in #612 storage **and** a separate #613 `sentry_links` with different semantics).
- #612 implementation **must** use the same `incident_links` model introduced under #613 (or a single agreed store both reference).
## 10. Security and redaction
Mandatory for bridge payloads, Gitea issue bodies/comments, DB-stored event summaries, and logs:
- No API tokens, DSNs, passwords, cookies, auth headers
- No keychain IDs, private config contents, raw session-state files, full prompt bodies
- Sanitize stack locals and request data; store only safe tags/context
- Logs must never print provider tokens or DSNs
- Redaction tests are required for #612
## 11. Non-goals
- Replace Gitea as the durable workflow record
- Let Sentry/GlitchTip assign work or mutate Gitea workflow state outside sanctioned tools
- Let the bridge approve, merge, close, release, or bypass Gitea gates
- Implement #600 on file locks / comments alone and call allocator complete
- Treat raw monitoring incidents as `work_items` for the allocator
- Put monitor tokens into every Gitea MCP worker process by default
## 12. Consequences
### Positive
- Clear implementation order and ownership
- Multi-session safety becomes testable at the DB layer
- Observability becomes assignable work without special-casing the allocator
- Trust boundaries stay compatible with existing control-plane docs
### Costs / risks
- Migration from comment/file leases requires reconciler work
- Shared Postgres or single allocator daemon is operational cost
- Bridge must be careful not to spam Gitea issues (dedupe, caps, policy modes)
### Follow-ups (documentation only until implemented)
1. Update #600, #612, and #613 bodies to **link this ADR** and restate hard dependencies.
2. Implement #613 schema + atomic assign/lease.
3. Implement #600 against the DB.
4. Implement #612 against `incident_links` + Gitea create/update.
5. Deprecate dual writers for leases.
## 13. Acceptance criteria for *this* ADR
This document is accepted when:
1. It is merged into `docs/architecture/` on the default branch.
2. #600 / #612 / #613 (or their PRs) reference this path as the architecture source of truth.
3. No implementation PR for those issues claims completion without conforming to §§211.
## 14. Document history
| Date | Change |
|------|--------|
| 2026-07-09 | Initial ADR: dependency order, authority model, topology, lease migration, bridge, `incident_links`, security, non-goals |
-67
View File
@@ -39,7 +39,6 @@ one.
| `status:blocked` | Issue is blocked |
| `status:needs-review` | Issue work needs review |
| `status:pr-open` | A linked PR is open |
| `status:changes-requested` | Reviewer requested changes on the linked PR |
| `status:approved` | Linked PR is approved |
| `status:merged` | Linked PR is merged |
| `status:reconcile` | Issue needs reconciliation |
@@ -47,72 +46,6 @@ one.
| `status:duplicate` | Issue is a duplicate |
| `status:wontfix` | Issue will not be fixed |
## Role Ownership Labels (#603)
A single `role:*` label shows which workflow role currently owns the item. It is
advisory visibility only — the control-plane lease (#601) is the source of truth
for mutation authority. Only one `role:*` label is active at a time; tooling
replaces it on handoff via `transition_role_labels`.
| Label | Use |
| --- | --- |
| `role:author` | Author currently owns the item |
| `role:reviewer` | Reviewer currently owns the item |
| `role:merger` | Merger currently owns the item |
## Hazard Labels (#603)
Hazard labels are orthogonal warning flags. Unlike `status:*` and `role:*`,
**more than one hazard may be active at once**, and a hazard never substitutes
for a live lease / PR-state check. Add/remove with `add_hazard_label` /
`clear_hazard_label`.
| Label | Use |
| --- | --- |
| `hazard:stale-lease` | A stale or expired lease references this item |
| `hazard:workflow-contaminated` | Session/workflow state is contaminated; do not mutate |
| `hazard:conflicted` | Linked PR has merge conflicts |
| `hazard:root-mutation` | Work was mutated in the project root checkout |
| `hazard:manual-state` | Session or lease state was edited manually |
| `hazard:terminal-blocker` | A terminal review/merge lock blocks progress (#332/#602) |
Any item that carries `status:blocked` or any `hazard:*` flag must also have a
blocking-reason / next-action comment (`requires_blocking_reason`).
## `state:*` → canonical mapping (#603 migration)
Issue #603 proposed a parallel `state:*` vocabulary. To avoid a conflicting
second lifecycle prefix, those requested states are folded into the existing
canonical labels rather than introduced as `state:*`. `state:*` is **not** a
supported prefix; use the canonical label on the right.
| Requested `state:*` | Canonical label |
| --- | --- |
| `state:needs-triage` | `status:triage` |
| `state:claimed` | `status:claimed` |
| `state:authoring` | `status:in-progress` |
| `state:needs-review` | `status:needs-review` |
| `state:reviewing` | `status:needs-review` |
| `state:changes-requested` | `status:changes-requested` |
| `state:approved` | `status:approved` |
| `state:merge-ready` | `status:approved` |
| `state:merged` | `status:merged` |
| `state:blocked` | `status:blocked` |
| `state:terminal-blocker` | `hazard:terminal-blocker` |
| `state:abandoned` | `status:wontfix` |
The transition helpers accept these names as synonyms (e.g.
`canonical_status_label("authoring")``status:in-progress`), so callers may use
the #603 wording while a single canonical status stays active.
## Allocator Cross-Check (#603)
Labels are advisory queue hints. The work allocator (#600/#613) uses labels as
one signal but **cross-checks live leases and PR state** and never trusts labels
alone. Discussion issues (`type:discussion`) are excluded from implementation
queues (`is_implementation_candidate`) unless a controller explicitly selects
them.
## Transition Rules
Suggested lifecycle:
-92
View File
@@ -811,32 +811,6 @@ author work. Do not switch from `prgs-reconciler` to `prgs-author` only to run
- **Reports:** label cleanup actions as reconciler cleanup (not author mutation).
- **Prompt:** `As prgs-reconciler, dry-run then execute gitea_reconcile_merged_cleanups for recently merged PRs without switching to prgs-author.`
### Superseded PR / satisfied issue reconciliation (#525)
Closing duplicate or superseded PRs after a canonical PR has merged is
**reconciler** work. Do not switch to `prgs-author` only to close the duplicate
PR, close the satisfied issue, or file a narrow follow-up discovered during
reconciliation.
- **Profile:** `prgs-reconciler`.
- **Tasks:** `reconcile_close_superseded_pr`,
`reconcile_close_satisfied_issue`, and
`reconcile_create_followup_issue`.
- **Tool:** `gitea_reconcile_superseded_by_merged_pr`.
- **Required proof:**
1. Live target PR state is open, but it is not independently required and no
mergeable work remains.
2. Live superseding PR state is closed and merged.
3. Superseding PR head is an ancestor of freshly fetched `master`.
4. Merge commit SHA is recorded.
5. Canonical close comment cites the superseding PR and merge commit.
6. Linked issue closure is attempted only when the issue is open and
explicitly satisfied by the superseding PR.
- **Fail closed:** missing ancestry proof, missing canonical comment,
mergeable target PR, same target/superseding PR, or missing
`gitea.pr.close` / `gitea.issue.close` capability.
- **Prompt:** `As prgs-reconciler, reconcile PR #N as superseded by merged PR #M; post the canonical close comment, close the superseded PR, and close issue #K only if the merged PR fully satisfies it.`
### Stop on blocker
- **Any profile.** If a required gate cannot be satisfied — identity
@@ -1049,72 +1023,6 @@ Special states:
Final reports must not claim a comment was posted when
`canonical_comment_validation.allowed` is false (#496 AC14).
## Stale #332 review-decision lock cleanup (#594)
#332 hard-stops a reviewer session after a terminal live review mutation
(`approve` / `request_changes`). After #559 those locks are **durable** under
`~/.cache/gitea-tools/session-state/review_decision_lock-<profile>.json`, so they
can outlive the PR they protected.
### When cleanup is **allowed**
Use `gitea_cleanup_stale_review_decision_lock` from a **reviewer** profile when:
1. A durable review-decision lock has a terminal live mutation, **and**
2. Live Gitea state shows that terminal PR is already **merged** or **closed**
(so no same-PR merge sequence remains), **and**
3. The active profile identity matches the lock, **and**
4. Authenticated identity can be verified.
Workflow:
```text
# 1) Assess only (default)
gitea_cleanup_stale_review_decision_lock(apply=false, remote=prgs, ...)
# 2) Apply after is_moot=true and cleanup_allowed=true
gitea_cleanup_stale_review_decision_lock(
apply=true,
expected_terminal_pr=<merged-or-closed-pr>,
remote=prgs,
...
)
```
Successful apply:
* clears in-memory + durable decision lock for that profile
* returns a structured `audit` payload
* posts an audit comment on the mooted PR when `gitea.pr.comment` is allowed
(`post_audit_comment=true` default)
Same-profile auto-expire: if `gitea_merge_pr` succeeds on a PR that this same
profile just approved, the decision lock is cleared after merge. Cross-profile
locks (reviewer vs merger) still require the cleanup tool.
### When cleanup is **forbidden**
Do **not** clear when:
* the last terminal PR is still **open** (active #332 hard-stop — continue merge
for that approve, or stop after request_changes)
* live PR state cannot be fetched (fail closed)
* profile identity does not match the lock
* identity cannot be verified
* `expected_terminal_pr` does not match the last terminal PR
**Never** use manual deletion of session-state files as the normal workflow.
**Never** use cleanup to skip review of an open PR or to bypass eligibility /
mark-ready / submit gates on active work.
### Related tools
| Tool | Purpose |
|------|---------|
| `gitea_cleanup_stale_review_decision_lock` | Moot decision-lock cleanup (#594) |
| `gitea_authorize_review_correction` | Operator-approved correction after a **mistaken** live review on still-active work (#211) |
| `gitea_cleanup_post_merge_moot_lease` | Moot **lease** cleanup after merge (#515) — different object |
## Fail-closed behavior
Before any mutating action the workflow verifies identity, active profile,
+19 -28
View File
@@ -21,8 +21,7 @@ not a missing or broken tool:
- The tool can be present and registered in the Python `FastMCP` tool manager.
- Direct Python inspection of the server confirms the tool exists.
- Running the server manually and sending JSON-RPC over stdio works fine
(offline spawn) — that path does **not** prove the IDE namespace is healthy.
- Running the server manually and sending JSON-RPC over stdio works fine.
The client manager entered a closed state after the backing subprocess for that
namespace terminated (or was killed) behind its back. Once closed, the client
@@ -37,9 +36,9 @@ detected by the `ps`-based `_check_mcp_runtimes_diagnostics` in
`gitea_mcp_server.py`. The EOF case is a dead/closed transport, not a stale one,
so the `ps` check alone will not surface it.
## Recovery path (canonical — client reconnect only)
## Recovery path
Do the steps in order. Stop as soon as a live **client-namespace** call succeeds.
Do the steps in order. Stop as soon as a live namespace call succeeds.
1. **Confirm the blast radius.** Call a cheap read tool on the failing namespace
(`gitea_whoami` or `gitea_list_profiles`). Then call the same tool on a
@@ -54,28 +53,22 @@ Do the steps in order. Stop as soon as a live **client-namespace** call succeeds
closed-client state that a bare `kill`/respawn from a terminal does **not**.
3. **Do not "fix" it by importing the server or poking the process.** Reaching
for `python -c 'import gitea_mcp_server ...'`, raw JSON-RPC from a shell,
killing PIDs to force a respawn, or touching MCP config mtimes does **not**
restore the *client's* view of the namespace and violates the daemon-import
guard (#558, `docs/mcp-daemon-import-guard.md`). The only sanctioned repair
is a **client reconnect / relaunch**.
for `python -c 'import gitea_mcp_server ...'`, raw JSON-RPC from a shell, or
killing PIDs to force a respawn does not restore the *client's* view of the
namespace and violates the daemon-import guard (#558,
`docs/mcp-daemon-import-guard.md`). The only sanctioned repair is a client
reconnect / relaunch.
4. **Verify through the same path the workflow will use.** After reconnect, call
the specific tool the blocked workflow needs — not just any tool — through
the target namespace. For a merge that means calling the merger-authorized
adoption/merge tool through `gitea-merger`. A green `gitea_whoami` on one
namespace does **not** prove another namespace or another tool is callable.
Record success with:
```text
gitea_assess_mcp_namespace_health(..., probe_source="client_namespace")
```
5. **If reconnect does not clear it,** relaunch the client entirely, then repeat
step 4. If EOF persists after a full relaunch, the backing subprocess is
failing to start — inspect its stderr / launch config (command path, venv,
`*_MCP_CONFIG`, `*_MCP_PROFILE` env) rather than retrying the call. Still
do not use PID kill or config-touch as the primary recovery.
`*_MCP_CONFIG`, `*_MCP_PROFILE` env) rather than retrying the call.
## Diagnostics to capture when reporting EOF
@@ -84,35 +77,33 @@ Include all of these so the failure is actionable and reproducible:
- **Namespace name** that returned EOF (`gitea-author` / `gitea-reviewer` /
`gitea-merger` / `gitea-tools`).
- **Tool** that was called and the **exact** error string.
- **PID** of the backing process (if any) and whether it was still alive
(informational only — not a recovery action).
- **PID** of the backing process (if any) and whether it was still alive.
- **Profile / env** for that namespace (execution profile, `*_MCP_PROFILE`,
worktree binding such as `GITEA_AUTHOR_WORKTREE`).
- **Config path** the client launched the server from.
- Result of the **cross-server control** call (did `context7` succeed?).
## Offline spawn probe (non-authoritative)
## Reproducing the registered-vs-callable gap
`test_mcp_conn.py` performs a full JSON-RPC handshake against a **fresh
subprocess** (`initialize` → `initialized` → `tools/list` → `tools/call`) and
classifies with `probe_source=offline_spawn`. That is useful for offline
launch/registration debugging. It is **not** proof the IDE-managed namespace is
healthy. See `docs/mcp-namespace-health.md`.
`test_mcp_conn.py` performs a full JSON-RPC handshake
(`initialize``initialized``tools/list`) plus a direct tool call against a
namespace, which is what distinguishes "registered in FastMCP" from "callable
through the client." Use it to confirm a namespace is genuinely reachable after
a reconnect. It probes a namespace end-to-end; a namespace that returns EOF at
the client fails this handshake, while `ps`-only checks still report the process
as present.
## Do-not list during EOF recovery
- Do **not** retry a blocked merge/adoption until the required tool is confirmed
callable through the merger-authorized **client** namespace (see #543).
callable through the merger-authorized namespace (see #543 canonical handoff).
- Do **not** clean, reset, or rebind a **foreign** worktree to work around the
error.
- Do **not** bypass the namespace with direct imports, raw API/curl, or
in-memory state restoration.
- Do **not** kill MCP PIDs or touch config mtimes as a substitute for client
reconnect.
## Related
- #531 / #544 — stale-runtime detection (`ps`-based); sibling failure mode.
- #558 / `docs/mcp-daemon-import-guard.md` — why shell imports are not a repair.
- `docs/mcp-client-registration.md` — per-server registration contract.
- `docs/mcp-namespace-health.md` — probe sources and mutation enforcement.
+49 -61
View File
@@ -1,4 +1,4 @@
# MCP namespace health diagnostics (#543)
# MCP namespace EOF recovery
Gitea MCP tools can be registered in the Python FastMCP server while the IDE's
live MCP namespace is still unusable. The failure usually appears as
@@ -6,54 +6,19 @@ live MCP namespace is still unusable. The failure usually appears as
a tool such as `gitea_whoami`.
Do not treat static tool registration as proof that review or merge workflows
can proceed. A reviewer or merger flow must have **client-namespace** evidence
that the required tool is callable through the configured IDE MCP namespace.
can proceed. A reviewer or merger flow must have live namespace evidence that
the required tool is callable through the configured namespace.
## Probe sources (do not confuse them)
## Required namespace probes
| Source | How obtained | Proves IDE namespace? |
| --- | --- | --- |
| `client_namespace` | Tool call through the IDE-managed MCP client | **Yes** |
| `offline_spawn` | `test_mcp_conn.py` subprocess JSON-RPC handshake | **No** (offline only) |
`gitea_assess_mcp_namespace_health` accepts `probe_source` and only sets
`ide_namespace_proven=true` for `client_namespace` success. Offline spawn
success never clears review/merge mutation gates.
## Client-namespace health check (canonical)
1. Through the IDE client, call a cheap tool on the target namespace
(`gitea_whoami` or `gitea_list_profiles`).
2. Feed the live result into:
```text
gitea_assess_mcp_namespace_health(
namespace="gitea-merger", # or reviewer / author / tools
registered_tools=[...], # optional static list
probe_result={"success": true, "result": {...}},
probe_source="client_namespace",
)
```
3. A healthy client-namespace assessment is recorded in the MCP session and
consulted by **live** `gitea_submit_pr_review` / `gitea_merge_pr` gates.
4. If the probe fails with EOF, recover via **client reconnect only** — see
`docs/mcp-namespace-eof-recovery.md`. Do **not** kill PIDs or touch MCP
config mtimes as a recovery procedure.
## Offline spawn probe (non-authoritative)
Run the health check after changing MCP config, switching branches that affect
server code, or seeing EOF from any Gitea namespace:
```bash
python3 test_mcp_conn.py --config ~/.gemini/config/mcp_config.json
```
This script spawns a **separate** server process from config, performs
JSON-RPC `initialize``tools/list``tools/call`, and classifies the
result with `probe_source=offline_spawn`. Use it for offline debugging of
launch command / registration. It does **not** prove the IDE-managed
namespace is healthy.
By default the script checks:
By default the script checks these namespaces and required tools:
| Namespace | Required tool |
| --- | --- |
@@ -62,27 +27,50 @@ By default the script checks:
| `gitea-merger` | `gitea_whoami` |
| `gitea-tools` | `gitea_list_profiles` |
## Recovery (canonical)
Use `--namespace gitea-reviewer` to test only one namespace. A passing probe
requires:
When a namespace returns EOF, follow
`docs/mcp-namespace-eof-recovery.md` in order:
1. The namespace exists in the MCP config.
2. JSON-RPC initialize succeeds.
3. `tools/list` returns the required tool.
4. `tools/call` successfully invokes the required tool.
1. Confirm blast radius (Gitea namespace vs all MCP servers).
2. **Reconnect the namespace through the client** (IDE reconnect / relaunch).
3. Do not repair via shell imports, raw JSON-RPC, PID kills, or config mtime
touches — those do not restore the client's closed transport.
4. Re-verify the **specific** required tool through the target namespace.
5. Resume review/merge only after a successful `client_namespace` assessment.
## Recovery steps
## Enforcement
When a namespace returns EOF:
1. **State machine (read-only):** feed `blocks_merge_workflow` from a
`client_namespace` assessment into
`gitea_assess_review_merge_state_machine(live_namespace_broken=...)`.
2. **Live mutations:** `gitea_submit_pr_review` and `gitea_merge_pr` call
`_live_namespace_health_gate` and fail closed when the session has a
recorded unhealthy or non-client probe for the required namespace
(`gitea-reviewer` for review, `gitea-merger` for merge).
1. Note the reported namespace, required tool, PID, profile, environment
summary, and config path.
2. Stop any stale MCP server process for that PID.
3. Reload or touch the MCP config so the IDE reconnects the namespace.
4. Verify the namespace command, args, profile env, and checkout path point at
the current repository.
5. Re-run `python3 test_mcp_conn.py --namespace <name>`.
6. Resume review or merge work only after the required tool call passes.
When blocked, repair the IDE namespace and re-record a healthy
`client_namespace` assessment before retrying the mutation.
The read-only `gitea_assess_mcp_namespace_health` tool can classify probe
evidence supplied by a client. It intentionally distinguishes
`required_tool_registered=true` from `required_tool_callable=false`; the latter
must block reviewer and merger workflows until the live namespace is repaired.
## Enforcement in the review/merge state machine
The block is not advisory. Feed the `blocks_merge_workflow` verdict from
`gitea_assess_mcp_namespace_health` into
`gitea_assess_review_merge_state_machine` as `live_namespace_broken`:
```text
health = gitea_assess_mcp_namespace_health(namespace="gitea-merger", ...)
state = gitea_assess_review_merge_state_machine(
state_completion=...,
pre_merge_gates=...,
live_namespace_broken=health["blocks_merge_workflow"],
)
# state["merge"]["allowed"] is False whenever the live namespace is broken,
# even when every review state and pre-merge gate is otherwise satisfied.
```
When `live_namespace_broken=True`, `assess_workflow_blockers`,
`can_approve`, `can_merge`, and `workflow_status` all fail closed. This is the
guard that stops a merge from proceeding on a false-ready namespace, as in the
PR #418 halt that motivated this work (#543).
+2 -4
View File
@@ -15,7 +15,5 @@
5. **Explicit merge confirmation**`gitea_merge_pr` requires `confirmation="MERGE PR <n>"`.
6. **No self-review / self-merge** — Authenticated user must differ from PR author for approve/merge.
7. **Review decision lock** — Live review mutations require validation-phase dry-run and `gitea_mark_final_review_decision`.
8. **Terminal review hard-stop (#332)** — After a terminal live review mutation, only same-PR merge after `approve` may continue. Durable locks (#559) must not be deleted by hand.
9. **Stale decision-lock cleanup (#594)**`gitea_cleanup_stale_review_decision_lock` may clear a durable #332 lock **only** when the last terminal mutation's PR is live-state **merged or closed**, identity/profile gates pass, and apply uses a reviewer-capable profile. Open/ambiguous locks stay fail-closed. Successful cleanup records a durable audit trail.
10. **Redaction** — Tokens, passwords, and keychain material never appear in tool output.
11. **Wiki publication (#224)**`docs/wiki/` and the sync helper are prerequisites only. Closing a wiki issue requires live Gitea Wiki proof on the repo Wiki tab. See [Runbooks](Runbooks.md#wiki-publication-readiness-gate-224).
8. **Redaction** — Tokens, passwords, and keychain material never appear in tool output.
9. **Wiki publication (#224)**`docs/wiki/` and the sync helper are prerequisites only. Closing a wiki issue requires live Gitea Wiki proof on the repo Wiki tab. See [Runbooks](Runbooks.md#wiki-publication-readiness-gate-224).
-54
View File
@@ -14,7 +14,6 @@ from typing import Any, Callable
import branch_cleanup_guard
import issue_acceptance_gate
import issue_lock_provenance
import merger_lease_adoption
import reviewer_handoff_consistency
import thread_state_ledger_validator
from mcp_native_cleanup_proof import assess_mcp_native_cleanup_proof
@@ -40,7 +39,6 @@ FINAL_REPORT_TASK_KINDS = frozenset({
"issue_filing",
"issue_selection",
"inventory",
"controller_close",
})
_TASK_KIND_ALIASES = {
@@ -52,9 +50,6 @@ _TASK_KIND_ALIASES = {
"reconcile_already_landed": "reconcile_already_landed",
"work-issue": "work_issue",
"create_issue": "issue_filing",
"close_issue": "controller_close",
"close-issue": "controller_close",
"controller-close": "controller_close",
}
_HANDOFF_ROLE_BY_TASK = {
@@ -66,7 +61,6 @@ _HANDOFF_ROLE_BY_TASK = {
"issue_filing": "issue_filing",
"issue_selection": None,
"inventory": "inventory",
"controller_close": None,
}
_LEGACY_WORKSPACE_MUTATIONS_RE = re.compile(
@@ -855,27 +849,6 @@ def _rule_reviewer_premerge_baseline_proof(report_text: str) -> list[dict[str, s
)
def _rule_reviewer_post_merge_validation(report_text: str) -> list[dict[str, str]]:
"""Block active approval on an already-merged/closed PR, and post-merge moot
validation claimed without merged-state + merge-commit proof (#529)."""
from post_merge_validation import assess_post_merge_validation
result = assess_post_merge_validation(report_text)
if not result.get("block"):
return []
return _findings_from_reasons(
"reviewer.post_merge_validation",
result.get("reasons") or [],
field="Validation status",
severity="block",
safe_next_action=result.get("safe_next_action")
or (
"record post-merge moot validation instead of an active approval; "
"cite PR state merged/closed and the merge commit SHA"
),
)
def _rule_reviewer_validation_status_vocabulary(
report_text: str,
*,
@@ -1290,24 +1263,6 @@ def _rule_shared_manual_lock_pr_override(report_text: str) -> list[dict[str, str
)
def _rule_shared_manual_lease_proof_handoff(report_text: str) -> list[dict[str, str]]:
"""Block merge/review handoffs that claim unsafe lease seeding (#535)."""
result = merger_lease_adoption.assess_manual_lease_proof_handoff(report_text)
if result.get("proven"):
return []
return _findings_from_reasons(
"shared.manual_lease_proof_handoff",
result.get("reasons") or [],
field="Merge mutations",
severity="block",
safe_next_action=(
"use gitea_adopt_merger_pr_lease or gitea_acquire_reviewer_pr_lease; "
"cite lease_proof_source / adoption_comment_id; never claim manual "
"seeded/injected lease proof"
),
)
def _rule_shared_issue_acceptance_gate(report_text: str) -> list[dict[str, str]]:
result = issue_acceptance_gate.validate_final_report_issue_acceptance(report_text)
if not result.get("applicable") or result.get("valid"):
@@ -1504,7 +1459,6 @@ def _rule_shared_mcp_native_cleanup_proof(report_text: str) -> list[dict[str, st
_SHARED_ISSUE_LOCK_RULES = (
_rule_shared_issue_lock_external_state,
_rule_shared_manual_lock_pr_override,
_rule_shared_manual_lease_proof_handoff,
_rule_shared_author_reviewer_same_run,
_rule_shared_raw_branch_delete_bypass,
_rule_shared_canonical_state_update,
@@ -1540,7 +1494,6 @@ _RULES_BY_TASK: dict[str, list[Callable[..., list[dict[str, str]]]]] = {
_rule_reviewer_linked_issue,
_rule_reviewer_baseline_on_failure,
_rule_reviewer_premerge_baseline_proof,
_rule_reviewer_post_merge_validation,
_rule_reviewer_validation_status_vocabulary,
_rule_reviewer_main_checkout_baseline,
_rule_reviewer_main_checkout_path,
@@ -1633,13 +1586,6 @@ _RULES_BY_TASK: dict[str, list[Callable[..., list[dict[str, str]]]]] = {
*_SHARED_CANONICAL_COMMENT_RULES,
*_SHARED_ISSUE_LOCK_RULES,
],
# Controller issue closure (#529): a closure report must not bury an
# unproven non-zero suite exit as an "expected pre-existing failure".
# Kept intentionally narrow so a closure pre-check does not demand the
# full reviewer/author handoff schema.
"controller_close": [
_rule_reviewer_premerge_baseline_proof,
],
}
+21 -210
View File
@@ -20,15 +20,14 @@ from dotenv import dotenv_values, load_dotenv
import gitea_config
PROJECT_ROOT = os.path.dirname(os.path.abspath(__file__))
# Load standard .env if present
load_dotenv(os.path.join(PROJECT_ROOT, ".env"))
load_dotenv()
# Dictionary to store configurations parsed dynamically from .env.* files
DYNAMIC_CONFIGS = {}
# Scan all files starting with .env in the project root to load multiple configurations
PROJECT_ROOT = os.path.dirname(os.path.abspath(__file__))
for env_path in glob.glob(os.path.join(PROJECT_ROOT, ".env*")):
# Skip directories and the example template
if os.path.basename(env_path) == ".env.example":
@@ -243,192 +242,6 @@ def _redact(text):
return str(text)
# ── Classified client failures (#699) ─────────────────────────────────────────
# Subclasses of RuntimeError preserve existing ``except RuntimeError`` call
# sites. Exception *messages* are fixed constants only — HTTP response bodies,
# Keychain material, and arbitrary exception text are never stored on the
# exception or re-emitted to tool results / daemon logs.
# Fixed messages (must match mcp_tool_error_boundary.FIXED_MESSAGES keys used here).
_MSG_AUTH_INVALID = "Gitea authentication failed: invalid or revoked credentials"
_MSG_AUTH_FAILED = "Gitea authentication failed"
_MSG_AUTHZ_SCOPE = "Gitea authorization failed: insufficient token scope"
_MSG_AUTHZ_DENIED = "Gitea authorization failed: access denied"
_MSG_NETWORK = "Network error contacting Gitea"
_MSG_CONFIG = "Gitea configuration or credential resolution failed"
_MSG_UPSTREAM = "Gitea upstream unavailable"
_MSG_HTTP = "Gitea HTTP request failed"
class GiteaClientError(RuntimeError):
"""Base for known Gitea client failures with stable reason_code metadata."""
reason_code = "client_error"
error_class = "client"
http_status = None
def __init__(self, message=None, *, reason_code=None, http_status=None):
if reason_code is not None:
self.reason_code = reason_code
if http_status is not None:
self.http_status = http_status
# Message is always a fixed constant; callers cannot inject bodies.
fixed = message if message is not None else _MSG_HTTP
super().__init__(fixed)
class GiteaAuthError(GiteaClientError):
"""Authentication failure (invalid/revoked credentials → typically HTTP 401)."""
reason_code = "auth_invalid_token"
error_class = "authentication"
http_status = 401
def __init__(self, message=None, *, reason_code=None, http_status=None):
super().__init__(
message if message is not None else _MSG_AUTH_INVALID,
reason_code=reason_code or "auth_invalid_token",
http_status=http_status if http_status is not None else 401,
)
class GiteaAuthzError(GiteaClientError):
"""Authorization failure (HTTP 403 — scope deficiency or access denied)."""
reason_code = "authz_denied"
error_class = "authorization"
http_status = 403
def __init__(self, message=None, *, reason_code=None, http_status=None):
code = reason_code or "authz_denied"
if code == "authz_insufficient_scope":
fixed = _MSG_AUTHZ_SCOPE
else:
fixed = _MSG_AUTHZ_DENIED
code = "authz_denied"
super().__init__(
message if message is not None else fixed,
reason_code=code,
http_status=http_status if http_status is not None else 403,
)
class GiteaNetworkError(GiteaClientError):
"""Transport / DNS / timeout failure contacting Gitea."""
reason_code = "network_error"
error_class = "network"
http_status = None
def __init__(self, message=None, *, reason_code=None, http_status=None):
super().__init__(
message if message is not None else _MSG_NETWORK,
reason_code=reason_code or "network_error",
http_status=http_status,
)
class GiteaConfigError(GiteaClientError):
"""Local configuration / credential resolution failure (not HTTP auth)."""
reason_code = "config_error"
error_class = "configuration"
http_status = None
def __init__(self, message=None, *, reason_code=None, http_status=None):
super().__init__(
message if message is not None else _MSG_CONFIG,
reason_code=reason_code or "config_error",
http_status=http_status,
)
class GiteaHttpError(GiteaClientError):
"""Non-auth HTTP failure with fixed message (no response body)."""
reason_code = "http_error"
error_class = "client"
http_status = None
def __init__(self, message=None, *, reason_code=None, http_status=None):
code = reason_code or "http_error"
if code == "upstream_unavailable":
fixed = _MSG_UPSTREAM
else:
fixed = _MSG_HTTP
code = "http_error"
super().__init__(
message if message is not None else fixed,
reason_code=code,
http_status=http_status,
)
def _looks_like_insufficient_scope(detail: str) -> bool:
"""Internal: inspect redacted body *only* to refine 403 reason_code.
The body is never stored on the exception or returned to callers.
"""
lower = (detail or "").lower()
markers = (
"insufficient scope",
"required scope",
"does not have at least one of required scope",
"token does not have",
"missing scope",
"scope(s)",
)
return any(m in lower for m in markers)
def classify_http_status(code: int, *, body_hint: str = "") -> tuple[type, str, int]:
"""Central HTTP status → (exception_class, reason_code, http_status).
Every HTTP 403 becomes authorization-class. Body text is used only as a
local hint for scope vs denied reason_code and is never returned.
"""
if code == 401:
return (GiteaAuthError, "auth_invalid_token", 401)
if code == 403:
if _looks_like_insufficient_scope(body_hint or ""):
return (GiteaAuthzError, "authz_insufficient_scope", 403)
return (GiteaAuthzError, "authz_denied", 403)
if code in (502, 503, 504):
return (GiteaHttpError, "upstream_unavailable", code)
return (GiteaHttpError, "http_error", code)
def raise_for_http_status(code: int, body: str = "") -> None:
"""Raise a typed client error for *code* without embedding *body*.
*body* may be inspected only to choose scope vs denied for 403; it is
never placed on the exception message.
"""
# Redact before any inspection; discard after classification.
try:
hint = _redact(body or "").strip()
except Exception:
hint = ""
exc_cls, reason, status = classify_http_status(code, body_hint=hint)
# Explicitly construct without passing body/hint into message.
if exc_cls is GiteaAuthError:
raise GiteaAuthError(reason_code=reason, http_status=status)
if exc_cls is GiteaAuthzError:
raise GiteaAuthzError(reason_code=reason, http_status=status)
if reason == "upstream_unavailable":
raise GiteaHttpError(
reason_code="upstream_unavailable",
http_status=status,
)
raise GiteaHttpError(reason_code="http_error", http_status=status)
def _raise_http_error(code: int, detail: str = "") -> None:
"""Backward-compatible alias — *detail* is never embedded in the error."""
raise_for_http_status(code, detail)
def _add_query(url, **params):
"""Return *url* with the given query parameters added or overridden.
@@ -501,24 +314,23 @@ def api_request(method, url, auth_header, payload=None, *,
"""Make an authenticated JSON request to the Gitea API.
Returns parsed JSON on success (or ``None`` for an empty body), and raises
a classified client error on failure.
``RuntimeError`` on failure.
On HTTP 429 the request is retried up to *max_retries* times: honoring a
valid ``Retry-After`` header (seconds or HTTP-date) when present, otherwise
using capped jittered exponential backoff. Successful responses are
unchanged.
Failures raise typed exceptions with **fixed messages only** (#699). HTTP
response bodies are read solely for local 403 reason refinement and are
never stored on exceptions or returned to callers:
All failures are converted to a ``RuntimeError`` with a clear, secret
-redacted message (no raw stack traces or credential material):
- HTTP 401 → :class:`GiteaAuthError` (``auth_invalid_token``)
- HTTP 403 → :class:`GiteaAuthzError` (scope or denied)
- 502/503/504 → :class:`GiteaHttpError` (``upstream_unavailable``)
- Other non-429 HTTP → :class:`GiteaHttpError` (``http_error``)
- Timeouts / DNS / ``URLError`` → :class:`GiteaNetworkError`
- Malformed success JSON → plain ``RuntimeError`` (programming/protocol;
not reclassified as authentication)
- Non-429 HTTP errors surface the status code and a redacted response body.
502/503/504 upstream errors get an explicit "Gitea upstream unavailable"
message.
- Timeouts and network/DNS failures (``URLError`` / ``TimeoutError``) surface
a generic "network error contacting Gitea" message.
- A malformed (non-JSON) success body surfaces a "malformed JSON response"
message rather than a raw decode error.
The ``*_func`` parameters and ``timeout`` are injection points for
deterministic testing.
@@ -556,23 +368,22 @@ def api_request(method, url, auth_header, payload=None, *,
error_body = e.read().decode("utf-8", errors="replace")
except Exception:
error_body = ""
# Classify from status (+ local body hint). Body is not embedded.
try:
raise_for_http_status(e.code, error_body)
except GiteaClientError:
raise
# Defensive: raise_for_http_status always raises.
raise GiteaHttpError(http_status=e.code) from e # pragma: no cover
detail = _redact(error_body).strip()
if e.code in (502, 503, 504):
msg = f"HTTP {e.code}: Gitea upstream unavailable"
raise RuntimeError(f"{msg}: {detail}" if detail else msg) from e
raise RuntimeError(f"HTTP {e.code}: {detail}") from e
except (urllib.error.URLError, TimeoutError) as e:
# Fixed message only — do not embed URLError reason (may leak paths).
raise GiteaNetworkError(reason_code="network_error") from e
reason = getattr(e, "reason", e)
raise RuntimeError(
f"network error contacting Gitea: {_redact(reason)}"
) from e
if not body:
return None
try:
return json.loads(body)
except ValueError as e:
# Programming/protocol failure — not authentication.
raise RuntimeError("malformed JSON response from Gitea") from e
+186 -2981
View File
File diff suppressed because it is too large Load Diff
-788
View File
@@ -1,788 +0,0 @@
"""Observability incident bridge (#612).
Converts Sentry/GlitchTip **observations** into durable **Gitea issues** and
``incident_links`` rows on the #613 control-plane DB.
Hard rules (ADR):
* Gitea owns work; providers own incidents; the bridge only links them.
* Raw monitoring incidents are **never** assignable ``work_items``.
* The #600 allocator sees bridge work only as normal Gitea issues.
* Phase-1 prefers dry-run / explicit reconcile; apply creates/links issues.
* No tokens, DSNs, cookies, or other secrets in bodies, DB, or logs.
"""
from __future__ import annotations
import json
import os
import re
from dataclasses import dataclass, field
from typing import Any, Callable, Sequence
from control_plane_db import ControlPlaneDB, ControlPlaneError, WORK_KINDS, _norm_scope
PROVIDERS = frozenset({"sentry", "glitchtip"})
OUTCOME_PREVIEW = "preview"
OUTCOME_LINKED = "linked_existing"
OUTCOME_CREATED = "created_issue"
OUTCOME_UPDATED = "updated_link"
OUTCOME_BLOCKED = "blocked"
OUTCOME_NO_ACTION = "no_safe_action"
# Patterns scrubbed from any bridge-facing text (bodies, titles, tags, logs).
_SECRET_PATTERNS: tuple[re.Pattern[str], ...] = (
re.compile(
r"(?i)\b(api[_-]?token|token|secret|password|passwd)\s*[:=]\s*\S+"
),
re.compile(
r"(?i)\bAuthorization\s*[:=]\s*(?:Bearer\s+)?[A-Za-z0-9._\-+=/]{8,}"
),
re.compile(r"(?i)\bBearer\s+[A-Za-z0-9._\-]{8,}"),
re.compile(r"(?i)\bBasic\s+[A-Za-z0-9+/=]{8,}"),
re.compile(r"(?i)\b(dsn|sentry_dsn|glitchtip_dsn)\s*[:=]\s*\S+"),
re.compile(r"https?://[^/\s]+:[^@/\s]+@"), # user:pass@host
re.compile(r"(?i)\b(keychain[_-]?id|private[_-]?key)\s*[:=]\s*\S+"),
re.compile(r"(?i)cookie\s*[:=]\s*[^\s;]+"),
re.compile(r"(?i)\bsession[_-]?id\s*[:=]\s*\S+"),
)
_SENSITIVE_TAG_KEYS = frozenset(
{
"authorization",
"cookie",
"set-cookie",
"password",
"passwd",
"secret",
"token",
"api_key",
"apikey",
"dsn",
"sentry_dsn",
"access_token",
"refresh_token",
}
)
DEFAULT_LABELS = (
"type:bug",
"observability",
"status:ready",
)
@dataclass(frozen=True)
class ProjectMapping:
"""Maps a monitoring project to a Gitea repository."""
name: str
provider: str
monitor_base_url: str
monitor_org: str
monitor_project: str
gitea_org: str
gitea_repo: str
default_labels: tuple[str, ...] = DEFAULT_LABELS
environment_filters: tuple[str, ...] = ()
severity_threshold: str | None = None
def __post_init__(self) -> None:
prov = (self.provider or "").strip().lower()
if prov not in PROVIDERS:
raise ControlPlaneError(
f"unknown provider '{self.provider}'; expected one of {sorted(PROVIDERS)}"
)
object.__setattr__(self, "provider", prov)
object.__setattr__(self, "monitor_base_url", (self.monitor_base_url or "").rstrip("/"))
object.__setattr__(self, "monitor_org", (self.monitor_org or "").strip())
object.__setattr__(self, "monitor_project", (self.monitor_project or "").strip())
object.__setattr__(self, "gitea_org", (self.gitea_org or "").strip())
object.__setattr__(self, "gitea_repo", (self.gitea_repo or "").strip())
object.__setattr__(
self,
"default_labels",
tuple(str(x).strip() for x in (self.default_labels or DEFAULT_LABELS) if str(x).strip()),
)
def as_dict(self) -> dict[str, Any]:
return {
"name": self.name,
"provider": self.provider,
"monitor_base_url": self.monitor_base_url,
"monitor_org": self.monitor_org,
"monitor_project": self.monitor_project,
"gitea_org": self.gitea_org,
"gitea_repo": self.gitea_repo,
"default_labels": list(self.default_labels),
"environment_filters": list(self.environment_filters),
"severity_threshold": self.severity_threshold,
}
def matches_observation(self, obs: dict[str, Any]) -> bool:
if (obs.get("provider") or "").strip().lower() != self.provider:
return False
base = (obs.get("provider_base_url") or obs.get("monitor_base_url") or "").rstrip("/")
if base and self.monitor_base_url and base != self.monitor_base_url:
return False
org = (obs.get("provider_org") or obs.get("monitor_org") or "").strip()
if org and self.monitor_org and org != self.monitor_org:
return False
project = (obs.get("provider_project") or obs.get("monitor_project") or "").strip()
if project and self.monitor_project and project != self.monitor_project:
return False
return True
@dataclass
class NormalizedIncident:
provider: str
provider_base_url: str
provider_org: str
provider_project: str
provider_issue_id: str
provider_short_id: str | None = None
provider_permalink: str | None = None
fingerprint: str | None = None
first_seen: str | None = None
last_seen: str | None = None
event_count: int | None = None
status: str = "open"
environment: str | None = None
severity: str | None = None
culprit: str | None = None
title: str = ""
summary: str = ""
tags: dict[str, str] = field(default_factory=dict)
gitea_org: str = ""
gitea_repo: str = ""
default_labels: tuple[str, ...] = DEFAULT_LABELS
def provider_key(self) -> tuple[str, str, str, str, str]:
return (
self.provider,
_norm_scope(self.provider_base_url),
_norm_scope(self.provider_org),
_norm_scope(self.provider_project),
str(self.provider_issue_id),
)
def as_dict(self) -> dict[str, Any]:
return {
"provider": self.provider,
"provider_base_url": self.provider_base_url,
"provider_org": self.provider_org,
"provider_project": self.provider_project,
"provider_issue_id": self.provider_issue_id,
"provider_short_id": self.provider_short_id,
"provider_permalink": self.provider_permalink,
"fingerprint": self.fingerprint,
"first_seen": self.first_seen,
"last_seen": self.last_seen,
"event_count": self.event_count,
"status": self.status,
"environment": self.environment,
"severity": self.severity,
"culprit": self.culprit,
"title": self.title,
"summary": self.summary,
"tags": dict(self.tags),
"gitea_org": self.gitea_org,
"gitea_repo": self.gitea_repo,
"default_labels": list(self.default_labels),
}
def redact_text(value: Any) -> str:
"""Redact secret-like material from a string (fail closed to empty)."""
if value is None:
return ""
text = str(value)
for pat in _SECRET_PATTERNS:
text = pat.sub("[REDACTED]", text)
return text
def sanitize_tags(tags: Any) -> dict[str, str]:
if not isinstance(tags, dict):
return {}
out: dict[str, str] = {}
for k, v in tags.items():
key = str(k).strip().lower()
if not key or key in _SENSITIVE_TAG_KEYS:
continue
if any(s in key for s in ("token", "secret", "password", "cookie", "auth", "dsn")):
continue
val = redact_text(v)
if "[REDACTED]" in val:
continue
if len(val) > 200:
val = val[:200] + ""
out[key] = val
return out
def project_mapping_from_dict(data: dict[str, Any]) -> ProjectMapping:
labels = data.get("default_labels") or DEFAULT_LABELS
envs = data.get("environment_filters") or ()
return ProjectMapping(
name=str(data.get("name") or data.get("monitor_project") or "unnamed"),
provider=str(data.get("provider") or ""),
monitor_base_url=str(data.get("monitor_base_url") or data.get("provider_base_url") or ""),
monitor_org=str(data.get("monitor_org") or data.get("provider_org") or ""),
monitor_project=str(data.get("monitor_project") or data.get("provider_project") or ""),
gitea_org=str(data.get("gitea_org") or ""),
gitea_repo=str(data.get("gitea_repo") or ""),
default_labels=tuple(labels),
environment_filters=tuple(envs),
severity_threshold=data.get("severity_threshold"),
)
def load_project_mappings(
*,
config_path: str | None = None,
mappings_json: str | None = None,
) -> list[ProjectMapping]:
"""Load project mappings from JSON env, file, or explicit JSON string.
Env: ``GITEA_OBSERVABILITY_PROJECTS_JSON`` or path
``GITEA_OBSERVABILITY_PROJECTS_FILE``.
"""
raw: Any = None
if mappings_json:
raw = json.loads(mappings_json)
else:
env_json = (os.environ.get("GITEA_OBSERVABILITY_PROJECTS_JSON") or "").strip()
path = (
(config_path or "").strip()
or (os.environ.get("GITEA_OBSERVABILITY_PROJECTS_FILE") or "").strip()
)
if env_json:
raw = json.loads(env_json)
elif path and os.path.isfile(path):
with open(path, encoding="utf-8") as fh:
raw = json.load(fh)
if raw is None:
return []
if isinstance(raw, dict) and "projects" in raw:
raw = raw["projects"]
if not isinstance(raw, list):
raise ControlPlaneError("observability project mappings must be a list")
return [project_mapping_from_dict(item) for item in raw if isinstance(item, dict)]
def resolve_mapping(
observation: dict[str, Any],
mappings: Sequence[ProjectMapping],
*,
explicit: ProjectMapping | None = None,
) -> ProjectMapping | None:
if explicit is not None:
return explicit
matches = [m for m in mappings if m.matches_observation(observation)]
if len(matches) == 1:
return matches[0]
if len(matches) > 1:
raise ControlPlaneError(
"ambiguous project mapping for observation: "
+ ", ".join(m.name for m in matches)
+ " (fail closed, #612)"
)
# Fallback: observation itself may carry gitea targets
g_org = (observation.get("gitea_org") or "").strip()
g_repo = (observation.get("gitea_repo") or "").strip()
provider = (observation.get("provider") or "").strip().lower()
if g_org and g_repo and provider in PROVIDERS:
return ProjectMapping(
name=f"inline-{provider}",
provider=provider,
monitor_base_url=str(
observation.get("provider_base_url")
or observation.get("monitor_base_url")
or ""
),
monitor_org=str(
observation.get("provider_org") or observation.get("monitor_org") or ""
),
monitor_project=str(
observation.get("provider_project")
or observation.get("monitor_project")
or ""
),
gitea_org=g_org,
gitea_repo=g_repo,
default_labels=tuple(observation.get("default_labels") or DEFAULT_LABELS),
)
return None
def normalize_incident(
observation: dict[str, Any],
mapping: ProjectMapping,
) -> NormalizedIncident:
"""Normalize + sanitize a raw provider observation (fail closed)."""
if not isinstance(observation, dict):
raise ControlPlaneError("observation must be a dict (fail closed, #612)")
provider = (observation.get("provider") or mapping.provider or "").strip().lower()
if provider not in PROVIDERS:
raise ControlPlaneError(
f"unknown provider '{provider}'; expected {sorted(PROVIDERS)} (fail closed)"
)
if provider != mapping.provider:
raise ControlPlaneError(
f"observation provider '{provider}' does not match mapping "
f"'{mapping.provider}' (fail closed, #612)"
)
issue_id = observation.get("provider_issue_id") or observation.get("id")
if issue_id is None or str(issue_id).strip() == "":
raise ControlPlaneError(
"observation missing provider_issue_id (fail closed, #612)"
)
base = (
observation.get("provider_base_url")
or observation.get("monitor_base_url")
or mapping.monitor_base_url
or ""
)
org = (
observation.get("provider_org")
or observation.get("monitor_org")
or mapping.monitor_org
or ""
)
project = (
observation.get("provider_project")
or observation.get("monitor_project")
or mapping.monitor_project
or ""
)
title = redact_text(
observation.get("title")
or observation.get("culprit")
or f"{provider} incident {issue_id}"
)
meta = observation.get("metadata")
meta_value = meta.get("value") if isinstance(meta, dict) else None
raw_sum = (
observation.get("summary")
or observation.get("message")
or meta_value
or title
)
summary = redact_text(raw_sum)
permalink = observation.get("provider_permalink") or observation.get("permalink")
if permalink:
permalink = redact_text(permalink)
if "[REDACTED]" in permalink:
permalink = None
tags = sanitize_tags(observation.get("tags") or {})
event_count = observation.get("event_count") or observation.get("count")
try:
event_count_i = int(event_count) if event_count is not None else None
except (TypeError, ValueError):
event_count_i = None
return NormalizedIncident(
provider=provider,
provider_base_url=str(base).rstrip("/"),
provider_org=str(org).strip(),
provider_project=str(project).strip(),
provider_issue_id=str(issue_id).strip(),
provider_short_id=redact_text(observation.get("provider_short_id") or observation.get("shortId") or "")
or None,
provider_permalink=permalink,
fingerprint=redact_text(observation.get("fingerprint") or "") or None,
first_seen=str(observation.get("first_seen") or observation.get("firstSeen") or "")
or None,
last_seen=str(observation.get("last_seen") or observation.get("lastSeen") or "")
or None,
event_count=event_count_i,
status=str(observation.get("status") or "open").strip().lower() or "open",
environment=redact_text(observation.get("environment") or "") or None,
severity=redact_text(observation.get("severity") or observation.get("level") or "")
or None,
culprit=redact_text(observation.get("culprit") or "") or None,
title=title[:200],
summary=summary[:2000],
tags=tags,
gitea_org=mapping.gitea_org,
gitea_repo=mapping.gitea_repo,
default_labels=mapping.default_labels,
)
def build_gitea_issue_title(inc: NormalizedIncident) -> str:
env = f" [{inc.environment}]" if inc.environment else ""
sev = f" ({inc.severity})" if inc.severity else ""
return redact_text(f"[obs:{inc.provider}]{env}{sev} {inc.title}")[:180]
def build_gitea_issue_body(inc: NormalizedIncident) -> str:
"""Sanitized durable issue body (no secrets)."""
lines = [
"## Observability incident (bridge #612)",
"",
"<!-- mcp-incident-bridge:v1 -->",
f"<!-- provider={inc.provider} issue_id={inc.provider_issue_id} -->",
"",
f"- **provider:** `{inc.provider}`",
f"- **provider_issue_id:** `{inc.provider_issue_id}`",
]
if inc.provider_short_id:
lines.append(f"- **provider_short_id:** `{inc.provider_short_id}`")
if inc.provider_permalink:
lines.append(f"- **provider_url:** {inc.provider_permalink}")
lines.extend(
[
f"- **provider_org/project:** `{inc.provider_org}` / `{inc.provider_project}`",
f"- **base_url:** `{inc.provider_base_url}`",
f"- **fingerprint:** `{inc.fingerprint or ''}`",
f"- **first_seen:** `{inc.first_seen or ''}`",
f"- **last_seen:** `{inc.last_seen or ''}`",
f"- **event_count:** `{inc.event_count if inc.event_count is not None else ''}`",
f"- **environment:** `{inc.environment or ''}`",
f"- **severity:** `{inc.severity or ''}`",
f"- **culprit:** `{inc.culprit or ''}`",
f"- **status:** `{inc.status}`",
"",
"### Summary",
"",
redact_text(inc.summary) or "(no summary)",
"",
"### Safe tags",
"",
]
)
if inc.tags:
for k, v in sorted(inc.tags.items()):
lines.append(f"- `{k}`: `{v}`")
else:
lines.append("- (none)")
lines.extend(
[
"",
"### Canonical next action",
"",
"Author: investigate and fix under normal Gitea workflow. "
"Allocator may select this issue as ordinary Gitea work "
"(never as a raw provider incident).",
"",
"### Bridge notes",
"",
"- Raw Sentry/GlitchTip incidents are **not** assignable work items.",
"- Gitea remains the durable work record; DB stores `incident_links` only.",
"- Provider tokens must never appear in this issue.",
]
)
return "\n".join(lines)
def _link_conflict(existing: dict[str, Any], inc: NormalizedIncident) -> str | None:
"""Fail closed if existing link targets a different Gitea issue/repo."""
eg_org = str(existing.get("gitea_org") or "")
eg_repo = str(existing.get("gitea_repo") or "")
eg_num = existing.get("gitea_issue_number")
if eg_org and eg_org != inc.gitea_org:
return (
f"existing link points to org '{eg_org}', mapping wants "
f"'{inc.gitea_org}' (fail closed, #612)"
)
if eg_repo and eg_repo != inc.gitea_repo:
return (
f"existing link points to repo '{eg_repo}', mapping wants "
f"'{inc.gitea_repo}' (fail closed, #612)"
)
# fingerprint conflict when both present and disagree
ef = (existing.get("fingerprint") or "").strip()
nf = (inc.fingerprint or "").strip()
if ef and nf and ef != nf:
# Same provider issue id with different fingerprints is ambiguous.
return (
f"fingerprint conflict for provider issue {inc.provider_issue_id}: "
f"link has '{ef}', observation has '{nf}' (fail closed, #612)"
)
return None
CreateIssueFn = Callable[[str, str, list[str], str, str], dict[str, Any]]
# create_issue_fn(title, body, labels, gitea_org, gitea_repo) -> {"number": int, ...}
def reconcile_incident(
db: ControlPlaneDB | None,
*,
observation: dict[str, Any],
mappings: Sequence[ProjectMapping] | None = None,
mapping: ProjectMapping | None = None,
apply: bool = False,
create_issue_fn: CreateIssueFn | None = None,
force_gitea_issue_number: int | None = None,
) -> dict[str, Any]:
"""Reconcile one observation into incident_links + optional Gitea issue.
*apply=False* (default): preview only — no DB mutation, no Gitea mutation.
*apply=True*: upsert link; create Gitea issue when none linked (requires
``create_issue_fn``) or use ``force_gitea_issue_number`` for explicit link.
Never creates control-plane ``work_items`` for raw incidents.
"""
base: dict[str, Any] = {
"success": False,
"apply": bool(apply),
"outcome": OUTCOME_NO_ACTION,
"performed": False,
"gitea_mutated": False,
"db_mutated": False,
"raw_incident_assignable": False,
"work_item_kind_would_be": None,
"reasons": [],
"skipped": None,
"incident": None,
"existing_link": None,
"gitea_issue": None,
"action": None,
"mapping": None,
"substrate": "control_plane_db.incident_links",
"durable_work_system": "gitea_issues",
}
if db is None:
base["reasons"] = [
"control-plane DB substrate unavailable (fail closed, #613/#612)"
]
base["outcome"] = OUTCOME_BLOCKED
return base
try:
maps = list(mappings or [])
resolved = resolve_mapping(observation, maps, explicit=mapping)
if resolved is None:
base["outcome"] = OUTCOME_BLOCKED
base["reasons"] = [
"no project mapping for observation (fail closed, #612); "
"configure GITEA_OBSERVABILITY_PROJECTS_JSON or pass mapping"
]
return base
base["mapping"] = resolved.as_dict()
inc = normalize_incident(observation, resolved)
base["incident"] = inc.as_dict()
except (ControlPlaneError, json.JSONDecodeError, TypeError, ValueError) as exc:
base["outcome"] = OUTCOME_BLOCKED
base["reasons"] = [str(exc)]
return base
# Environment filter (optional)
if resolved.environment_filters and inc.environment:
allowed = {e.lower() for e in resolved.environment_filters}
if inc.environment.lower() not in allowed:
base["outcome"] = OUTCOME_NO_ACTION
base["reasons"] = [
f"environment '{inc.environment}' not in filters "
f"{sorted(allowed)}; skip (policy)"
]
base["success"] = True
base["action"] = "skip_environment_filter"
return base
existing = db.get_incident_link_by_provider(
provider=inc.provider,
provider_issue_id=inc.provider_issue_id,
provider_base_url=inc.provider_base_url,
provider_org=inc.provider_org,
provider_project=inc.provider_project,
)
base["existing_link"] = existing
if existing:
conflict = _link_conflict(existing, inc)
if conflict:
base["outcome"] = OUTCOME_BLOCKED
base["reasons"] = [conflict]
return base
title = build_gitea_issue_title(inc)
body = build_gitea_issue_body(inc)
labels = list(inc.default_labels)
if inc.provider and f"{inc.provider}" not in labels:
labels.append(inc.provider)
if "observability" not in labels:
labels.append("observability")
preview_issue = {
"title": title,
"body_preview": body[:500] + ("" if len(body) > 500 else ""),
"labels": labels,
"gitea_org": inc.gitea_org,
"gitea_repo": inc.gitea_repo,
"would_create": existing is None and force_gitea_issue_number is None,
"would_reuse_issue": int(existing["gitea_issue_number"])
if existing
else force_gitea_issue_number,
}
base["gitea_issue_preview"] = preview_issue
if not apply:
base["success"] = True
base["outcome"] = OUTCOME_PREVIEW
base["action"] = (
"preview_reuse_link" if existing else "preview_create_issue"
)
base["reasons"] = [
"dry-run only (apply=false); no Gitea mutation and no DB write — "
"call again with apply=true to create/link"
]
if existing:
base["gitea_issue"] = {
"number": existing.get("gitea_issue_number"),
"org": existing.get("gitea_org"),
"repo": existing.get("gitea_repo"),
}
# Prove we never treat this as work_item kind incident
base["raw_incident_assignable"] = False
base["work_item_kind_would_be"] = "issue" # only after Gitea issue exists
return base
# --- apply path ---
issue_number: int | None = None
created = False
if existing:
issue_number = int(existing["gitea_issue_number"])
action = "updated_existing_link"
outcome = OUTCOME_UPDATED
elif force_gitea_issue_number is not None:
issue_number = int(force_gitea_issue_number)
action = "link_explicit_issue"
outcome = OUTCOME_LINKED
else:
if create_issue_fn is None:
base["outcome"] = OUTCOME_BLOCKED
base["reasons"] = [
"apply=true requires create_issue_fn when no existing link "
"(fail closed, #612)"
]
return base
try:
created_res = create_issue_fn(
title, body, labels, inc.gitea_org, inc.gitea_repo
)
except Exception as exc: # noqa: BLE001
base["outcome"] = OUTCOME_BLOCKED
base["reasons"] = [
f"Gitea issue creation failed: {redact_text(exc)} (fail closed)"
]
return base
number = created_res.get("number") if isinstance(created_res, dict) else None
if number is None:
base["outcome"] = OUTCOME_BLOCKED
base["reasons"] = [
"Gitea issue creation returned no issue number (fail closed, #612)"
]
base["create_result"] = created_res
return base
issue_number = int(number)
created = True
action = "created_gitea_issue"
outcome = OUTCOME_CREATED
base["gitea_mutated"] = True
base["create_result"] = {
k: created_res.get(k)
for k in ("number", "success", "performed", "reasons")
if isinstance(created_res, dict)
}
assert issue_number is not None
try:
link = db.upsert_incident_link(
provider=inc.provider,
provider_issue_id=inc.provider_issue_id,
gitea_org=inc.gitea_org,
gitea_repo=inc.gitea_repo,
gitea_issue_number=issue_number,
provider_base_url=inc.provider_base_url,
provider_org=inc.provider_org,
provider_project=inc.provider_project,
provider_short_id=inc.provider_short_id,
provider_permalink=inc.provider_permalink,
fingerprint=inc.fingerprint,
first_seen=inc.first_seen,
last_seen=inc.last_seen,
event_count=inc.event_count,
status=inc.status if not created else "open",
)
except Exception as exc: # noqa: BLE001
base["outcome"] = OUTCOME_BLOCKED
base["reasons"] = [
f"incident_links upsert failed: {redact_text(exc)} (fail closed, #613)"
]
base["gitea_issue"] = {
"number": issue_number,
"org": inc.gitea_org,
"repo": inc.gitea_repo,
"created": created,
}
return base
base["success"] = True
base["performed"] = True
base["db_mutated"] = True
base["outcome"] = outcome
base["action"] = action
base["gitea_issue"] = {
"number": issue_number,
"org": inc.gitea_org,
"repo": inc.gitea_repo,
"created": created,
}
base["link"] = {
k: link.get(k)
for k in (
"link_id",
"provider",
"provider_issue_id",
"gitea_org",
"gitea_repo",
"gitea_issue_number",
"fingerprint",
"event_count",
"status",
"last_sync_at",
)
}
base["reasons"] = [
(
f"reused Gitea issue #{issue_number} for provider "
f"{inc.provider}:{inc.provider_issue_id}"
if not created
else f"created Gitea issue #{issue_number} and stored incident_links row"
),
"raw provider incident is not an assignable work_item "
f"(WORK_KINDS={sorted(WORK_KINDS)})",
]
base["raw_incident_assignable"] = False
base["work_item_kind_would_be"] = "issue"
base["allocator_visible_as"] = {
"kind": "issue",
"number": issue_number,
"org": inc.gitea_org,
"repo": inc.gitea_repo,
"note": "allocator selects normal Gitea issues only (#600/#612)",
}
return base
def assert_not_raw_incident_work_item(kind: str) -> None:
"""Guard used by tests / callers: incidents must not enter WORK_KINDS."""
k = (kind or "").strip().lower()
if k not in WORK_KINDS:
if k in ("sentry_incident", "glitchtip_incident", "incident", "observation"):
raise ControlPlaneError(
f"kind '{k}' is not assignable; bridge must create Gitea issues first (#612)"
)
raise ControlPlaneError(f"kind '{k}' is not assignable")
-180
View File
@@ -1,180 +0,0 @@
"""Pre-create issue content gate (#582).
Blocks issue creation when the title/body is a *vague reference* to
out-of-band content the LLM cannot prove it has ("the drafted issue",
"the prepared issue", "the issue we discussed", "the previous draft")
with no durable source pointer.
The rule from #582: an LLM must not fabricate an issue from stale chat
memory. When the requested issue content is a vague reference and no
durable source pointer (existing issue/PR/comment, checked-in file, URL,
or scratchpad path) is present, the gate fails closed and the caller must
return BLOCKED + DIAGNOSE naming the exact vague/missing fields.
This gate intentionally does NOT require a non-empty body: title-only
issue creation remains allowed for callers that explicitly want it. It
only blocks content that is a placeholder reference to something the
current context does not contain.
"""
from __future__ import annotations
import re
import unicodedata
# Vague reference phrases that point at out-of-band draft content. Stored
# normalized (lowercase, punctuation-stripped, whitespace-collapsed) so they
# can be matched against normalized field text.
VAGUE_REFERENCE_PHRASES: tuple[str, ...] = (
"the drafted issue",
"drafted issue",
"the prepared issue",
"prepared issue",
"the issue we discussed",
"the issue we talked about",
"the one we discussed",
"the previous draft",
"previous draft",
"the draft above",
"the issue above",
"as discussed",
"as we discussed",
"as previously discussed",
"per our discussion",
"per our conversation",
"per our chat",
"see above",
"same as before",
"the issue from earlier",
"the issue i drafted",
"the issue you drafted",
)
# A field that only restates a vague phrase (optionally with a leading verb
# such as "create"/"add"/"open"/"file") is still a vague reference.
_LEADING_VERBS = ("create", "add", "open", "file", "make", "please", "the")
# Durable source pointers: if any of these appears, the content points at a
# retrievable source of truth and is NOT treated as a fabricated reference.
_DURABLE_SOURCE_REGEXES: tuple[re.Pattern[str], ...] = (
re.compile(r"#\d+"), # #402
re.compile(r"\b(?:issue|pull|pr)\s+#?\d+", re.I), # issue 402 / PR #17
re.compile(r"\bcomment\s+#?\d+", re.I), # comment 8155
re.compile(r"https?://\S+", re.I), # URL
re.compile( # checked-in file
r"[\w./-]+\.(?:py|md|json|txt|sh|ya?ml|toml|cfg|ini|rst)\b", re.I
),
re.compile(r"\bscratchpad\b", re.I), # scratchpad path
re.compile(r"(?:^|\s)/[\w./-]+"), # absolute path
)
def normalize_text(text: str) -> str:
"""Lowercase, punctuation-stripped, whitespace-collapsed text."""
norm = unicodedata.normalize("NFKC", (text or "").strip().lower())
norm = re.sub(r"[^\w\s]", " ", norm)
norm = re.sub(r"\s+", " ", norm).strip()
return norm
def has_durable_source_pointer(text: str) -> bool:
"""True when the raw text references a durable, retrievable source."""
raw = text or ""
return any(rx.search(raw) for rx in _DURABLE_SOURCE_REGEXES)
def find_vague_reference(text: str) -> str | None:
"""Return the vague phrase a field is dominated by, else ``None``.
A field is a vague reference only when it contains a known vague phrase,
carries no durable source pointer, and the phrase dominates the field
(the field is essentially just the phrase). Long, specific bodies that
merely contain "as discussed" in passing are not blocked.
"""
if has_durable_source_pointer(text):
return None
norm = normalize_text(text)
if not norm:
return None
stripped = norm
for verb in _LEADING_VERBS:
if stripped.startswith(verb + " "):
stripped = stripped[len(verb) + 1:]
for phrase in VAGUE_REFERENCE_PHRASES:
if phrase in norm and len(stripped) <= len(phrase) + 12:
return phrase
return None
def assess_issue_content(
title: str,
body: str = "",
*,
allow_incomplete: bool = False,
) -> dict:
"""Evaluate whether proposed issue content is durable enough to create.
Returns a dict with ``complete`` (bool), ``missing_fields``,
``vague_fields``, ``reasons``, ``diagnose`` (joined reasons), and
``has_durable_source_pointer``. ``allow_incomplete`` is an explicit
operator override that forces ``complete`` True.
"""
t = (title or "").strip()
b = (body or "").strip()
missing_fields: list[str] = []
vague_fields: list[str] = []
reasons: list[str] = []
if not t:
missing_fields.append("title")
reasons.append("issue title is required")
else:
phrase = find_vague_reference(t)
if phrase:
vague_fields.append("title")
reasons.append(
f"title is a vague reference ('{phrase}') with no durable "
"content or source pointer"
)
if b:
phrase = find_vague_reference(b)
if phrase:
vague_fields.append("body")
reasons.append(
f"body is a vague reference ('{phrase}') with no durable "
"content or source pointer"
)
complete = allow_incomplete or (not missing_fields and not vague_fields)
return {
"complete": complete,
"missing_fields": missing_fields,
"vague_fields": vague_fields,
"reasons": reasons,
"diagnose": "; ".join(reasons),
"has_durable_source_pointer": has_durable_source_pointer(b)
or has_durable_source_pointer(t),
"override_applied": bool(
allow_incomplete and (missing_fields or vague_fields)
),
}
def pre_create_issue_content_gate(
title: str,
body: str = "",
*,
allow_incomplete: bool = False,
) -> dict:
"""Content gate wrapper mirroring the duplicate gate shape.
``performed`` is True when the content is durable enough to create (or an
explicit override was supplied). When False, the caller must return
BLOCKED + DIAGNOSE and must not create the issue.
"""
assessment = assess_issue_content(
title, body, allow_incomplete=allow_incomplete
)
assessment["performed"] = assessment["complete"]
return assessment
-63
View File
@@ -375,64 +375,6 @@ def _same_realpath(left: str | None, right: str | None) -> bool:
return left == right
def assess_expired_lock_reclaim(
existing_lock: dict[str, Any] | None,
*,
now: datetime | None = None,
) -> dict[str, Any]:
"""Decide whether an expired/stale author issue lock may be reclaimed (#601).
Required proof (any reclaim of non-live lock):
* lease not live (expired or dead pid)
* owner process dead OR worktree missing
* no force-delete of live foreign ownership
"""
if not existing_lock:
return {
"reclaim_allowed": True,
"reasons": ["no existing lock"],
"freshness": assess_lock_freshness(None, now=now),
}
freshness = assess_lock_freshness(existing_lock, now=now)
if freshness.get("live"):
return {
"reclaim_allowed": False,
"reasons": ["lock is still live; cannot reclaim (fail closed)"],
"freshness": freshness,
}
pid = existing_lock.get("session_pid")
if pid is None:
pid = existing_lock.get("pid")
dead = not is_process_alive(pid) if pid is not None else True
wt = str(existing_lock.get("worktree_path") or "")
missing_wt = (not wt) or (not os.path.isdir(os.path.realpath(wt)))
if not (dead or missing_wt):
return {
"reclaim_allowed": False,
"reasons": [
"expired/stale lock still has live owner pid and present worktree; "
"recovery review required (fail closed)"
],
"freshness": freshness,
"owner_pid_dead": dead,
"worktree_missing": missing_wt,
}
return {
"reclaim_allowed": True,
"reasons": [
"non-live lock with dead process and/or missing worktree; "
"sanctioned reclaim allowed"
],
"freshness": freshness,
"owner_pid_dead": dead,
"worktree_missing": missing_wt,
"prior_branch": existing_lock.get("branch_name"),
"prior_worktree": existing_lock.get("worktree_path"),
"prior_pid": pid,
}
def assess_same_issue_lease_conflict(
existing_lock: dict[str, Any] | None,
*,
@@ -463,11 +405,6 @@ def assess_same_issue_lease_conflict(
and _same_realpath(str(existing_worktree or ""), worktree_path)
)
if is_lease_expired(existing_lock, now=now):
reclaim = assess_expired_lock_reclaim(existing_lock, now=now)
if reclaim.get("reclaim_allowed"):
# #601: expired + dead pid / missing worktree may be reclaimed
# through the normal lock path (sanctioned overwrite).
return None
return (
f"Issue #{issue_number} has an expired {operation_type} lease on "
f"branch '{existing_branch}' from worktree '{existing_worktree}'. "
+1 -213
View File
@@ -34,11 +34,6 @@ STATUS_LABEL_SPECS: tuple[LabelSpec, ...] = (
LabelSpec("status:blocked", "b60205", "Issue is blocked"),
LabelSpec("status:needs-review", "0052cc", "Issue work needs review"),
LabelSpec("status:pr-open", "1d76db", "A linked PR is open"),
LabelSpec(
"status:changes-requested",
"e11d21",
"Reviewer requested changes on the linked PR",
),
LabelSpec("status:approved", "0e8a16", "Linked PR is approved"),
LabelSpec("status:merged", "5319e7", "Linked PR is merged"),
LabelSpec("status:reconcile", "d93f0b", "Issue needs reconciliation"),
@@ -47,74 +42,12 @@ STATUS_LABEL_SPECS: tuple[LabelSpec, ...] = (
LabelSpec("status:wontfix", "000000", "Issue will not be fixed"),
)
# Durable validation-outcome labels (#529): the four canonical distinctions a
# reviewer report can carry. These are orthogonal to the single active status:*
# label, so they use their own prefix and are not subject to the one-status
# invariant.
VALIDATION_LABEL_SPECS: tuple[LabelSpec, ...] = (
LabelSpec("validation:clean-pass", "0e8a16", "Validation was a clean pass"),
LabelSpec(
"validation:baseline-accepted",
"fbca04",
"Validation passed with a baseline-proven unrelated failure",
),
LabelSpec(
"validation:blocked",
"b60205",
"Validation blocked by an unresolved failure",
),
LabelSpec(
"validation:post-merge-moot",
"5319e7",
"Validation is post-merge moot (PR already merged/closed before review)",
),
)
# Lifecycle role-ownership labels (#603): which workflow role currently owns the
# item. Advisory visibility only — the control-plane lease (#601) remains the
# source of truth for mutation authority. Only one role:* label is active at a
# time, mirroring the single-active-status invariant.
ROLE_LABEL_SPECS: tuple[LabelSpec, ...] = (
LabelSpec("role:author", "1d76db", "Author currently owns the item"),
LabelSpec("role:reviewer", "5319e7", "Reviewer currently owns the item"),
LabelSpec("role:merger", "0e8a16", "Merger currently owns the item"),
)
# Lifecycle hazard labels (#603): orthogonal warning flags surfacing dangerous
# coordination conditions. Unlike status/role, multiple hazard:* labels may be
# active at once, and they never substitute for live lease / PR state checks.
HAZARD_LABEL_SPECS: tuple[LabelSpec, ...] = (
LabelSpec("hazard:stale-lease", "d93f0b", "A stale or expired lease references this item"),
LabelSpec(
"hazard:workflow-contaminated",
"b60205",
"Session/workflow state is contaminated and must not mutate",
),
LabelSpec("hazard:conflicted", "e11d21", "Linked PR has merge conflicts"),
LabelSpec("hazard:root-mutation", "b60205", "Work was mutated in the project root checkout"),
LabelSpec("hazard:manual-state", "d93f0b", "Session or lease state was edited manually"),
LabelSpec(
"hazard:terminal-blocker",
"000000",
"A terminal review/merge lock blocks progress (#332/#602)",
),
)
CANONICAL_LABEL_SPECS: tuple[LabelSpec, ...] = (
TYPE_LABEL_SPECS
+ STATUS_LABEL_SPECS
+ VALIDATION_LABEL_SPECS
+ ROLE_LABEL_SPECS
+ HAZARD_LABEL_SPECS
TYPE_LABEL_SPECS + STATUS_LABEL_SPECS
)
TYPE_LABELS: frozenset[str] = frozenset(spec.name for spec in TYPE_LABEL_SPECS)
STATUS_LABELS: frozenset[str] = frozenset(spec.name for spec in STATUS_LABEL_SPECS)
VALIDATION_LABELS: frozenset[str] = frozenset(
spec.name for spec in VALIDATION_LABEL_SPECS
)
ROLE_LABELS: frozenset[str] = frozenset(spec.name for spec in ROLE_LABEL_SPECS)
HAZARD_LABELS: frozenset[str] = frozenset(spec.name for spec in HAZARD_LABEL_SPECS)
CANONICAL_LABELS: frozenset[str] = frozenset(
spec.name for spec in CANONICAL_LABEL_SPECS
)
@@ -132,15 +65,9 @@ STATUS_TRANSITIONS: dict[str, str] = {
"blocked": "status:blocked",
"needs_review": "status:needs-review",
"needs-review": "status:needs-review",
"reviewing": "status:needs-review",
"pr_open": "status:pr-open",
"pr-open": "status:pr-open",
"changes_requested": "status:changes-requested",
"changes-requested": "status:changes-requested",
"changes": "status:changes-requested",
"approved": "status:approved",
"merge_ready": "status:approved",
"merge-ready": "status:approved",
"merge": "status:reconcile",
"merged": "status:reconcile",
"reconcile": "status:reconcile",
@@ -148,37 +75,6 @@ STATUS_TRANSITIONS: dict[str, str] = {
"complete": "status:done",
"duplicate": "status:duplicate",
"wontfix": "status:wontfix",
"abandoned": "status:wontfix",
# #603 requested state:* synonyms folded into the canonical status vocabulary
"needs_triage": "status:triage",
"needs-triage": "status:triage",
"authoring": "status:in-progress",
}
# #603: single-active role ownership. Maps role kinds / role:* labels to the
# canonical role label. Mirrors STATUS_TRANSITIONS for the role dimension.
ROLE_TRANSITIONS: dict[str, str] = {
"author": "role:author",
"reviewer": "role:reviewer",
"merger": "role:merger",
}
# #603: hazard flag synonyms. Hazards are additive (not single-active), so this
# only normalizes names; it does not drive replacement.
HAZARD_TRANSITIONS: dict[str, str] = {
"stale_lease": "hazard:stale-lease",
"stale-lease": "hazard:stale-lease",
"workflow_contaminated": "hazard:workflow-contaminated",
"workflow-contaminated": "hazard:workflow-contaminated",
"contaminated": "hazard:workflow-contaminated",
"conflicted": "hazard:conflicted",
"conflict": "hazard:conflicted",
"root_mutation": "hazard:root-mutation",
"root-mutation": "hazard:root-mutation",
"manual_state": "hazard:manual-state",
"manual-state": "hazard:manual-state",
"terminal_blocker": "hazard:terminal-blocker",
"terminal-blocker": "hazard:terminal-blocker",
}
@@ -233,100 +129,6 @@ def transition_status_labels(
return kept
def role_labels(labels: Iterable[str | Mapping[str, object]] | Mapping[str, object]) -> list[str]:
return [name for name in label_names(labels) if name.startswith("role:")]
def hazard_labels(labels: Iterable[str | Mapping[str, object]] | Mapping[str, object]) -> list[str]:
return [name for name in label_names(labels) if name.startswith("hazard:")]
def canonical_role_label(role_or_transition: str) -> str:
role = role_or_transition.strip()
if role in ROLE_LABELS:
return role
normalized = role.lower().replace(" ", "-")
try:
return ROLE_TRANSITIONS[normalized]
except KeyError as exc:
raise ValueError(
f"unknown workflow role or transition '{role_or_transition}'"
) from exc
def transition_role_labels(
existing_labels: Iterable[str | Mapping[str, object]] | Mapping[str, object],
role_or_transition: str,
) -> list[str]:
"""Replace all active role labels with the requested canonical role."""
new_role = canonical_role_label(role_or_transition)
kept = [name for name in label_names(existing_labels) if not name.startswith("role:")]
if new_role not in kept:
kept.append(new_role)
return kept
def canonical_hazard_label(hazard: str) -> str:
name = hazard.strip()
if name in HAZARD_LABELS:
return name
normalized = name.lower().replace(" ", "-")
try:
return HAZARD_TRANSITIONS[normalized]
except KeyError as exc:
raise ValueError(f"unknown workflow hazard '{hazard}'") from exc
def add_hazard_label(
existing_labels: Iterable[str | Mapping[str, object]] | Mapping[str, object],
hazard: str,
) -> list[str]:
"""Add a hazard flag without disturbing status/role/type labels (additive)."""
new_hazard = canonical_hazard_label(hazard)
kept = label_names(existing_labels)
if new_hazard not in kept:
kept.append(new_hazard)
return kept
def clear_hazard_label(
existing_labels: Iterable[str | Mapping[str, object]] | Mapping[str, object],
hazard: str,
) -> list[str]:
"""Remove a single hazard flag, leaving all other labels intact."""
target = canonical_hazard_label(hazard)
return [name for name in label_names(existing_labels) if name != target]
def is_discussion(labels: Iterable[str | Mapping[str, object]] | Mapping[str, object]) -> bool:
return "type:discussion" in type_labels(labels)
def is_implementation_candidate(
labels: Iterable[str | Mapping[str, object]] | Mapping[str, object],
) -> bool:
"""Whether an item may enter an implementation queue on labels alone.
Discussion issues are excluded (#603 AC3) unless a controller explicitly
selects them; the allocator still cross-checks live lease/PR state and never
trusts labels alone (#603 AC2).
"""
return not is_discussion(labels)
def requires_blocking_reason(
labels: Iterable[str | Mapping[str, object]] | Mapping[str, object],
) -> bool:
"""Whether the item must carry a blocking-reason / next-action comment (AC4).
True when blocked or when any hazard flag is present.
"""
names = label_names(labels)
if "status:blocked" in names:
return True
return any(name.startswith("hazard:") for name in names)
def labels_for_new_issue(
issue_type: str | None = None,
initial_status: str | None = None,
@@ -360,8 +162,6 @@ def assess_issue_labels(
names = label_names(labels)
found_types = type_labels(names)
found_statuses = status_labels(names)
found_roles = role_labels(names)
found_hazards = hazard_labels(names)
errors: list[str] = []
warnings: list[str] = []
@@ -376,10 +176,6 @@ def assess_issue_labels(
"issue has multiple active status:* labels: "
+ ", ".join(found_statuses)
)
if len(found_roles) > 1:
errors.append(
"issue has multiple active role:* labels: " + ", ".join(found_roles)
)
for name in found_types:
if name not in TYPE_LABELS:
@@ -387,20 +183,12 @@ def assess_issue_labels(
for name in found_statuses:
if name not in STATUS_LABELS:
warnings.append(f"unknown status label '{name}'")
for name in found_roles:
if name not in ROLE_LABELS:
warnings.append(f"unknown role label '{name}'")
for name in found_hazards:
if name not in HAZARD_LABELS:
warnings.append(f"unknown hazard label '{name}'")
return {
"valid": not errors,
"labels": names,
"type_labels": found_types,
"status_labels": found_statuses,
"role_labels": found_roles,
"hazard_labels": found_hazards,
"errors": errors,
"warnings": warnings,
}
-723
View File
@@ -1,723 +0,0 @@
"""First-class control-plane lease lifecycle (#601).
Active leases are queryable workflow state. Canonical operations:
* list / inspect
* adopt (with provenance)
* release (explicit, recorded)
* expire / reclaim
* abandon (requires proof: dead process and/or missing worktree, etc.)
Authority model:
* Control-plane DB is the coordination source for assignment/lease.
* File locks and comment-only leases are **not** authoritative alone.
* Reviewer/merger comment leases (``reviewer_pr_lease`` / merger adoption)
remain for Gitea-thread durability; they must not bypass DB assignment when
the control-plane path is in use.
Fail closed on ambiguous ownership, active foreign leases, mismatched
worktree, stale head, missing capability, and unsafe cleanup.
"""
from __future__ import annotations
import json
import os
from dataclasses import dataclass, field
from datetime import datetime, timezone
from typing import Any, Callable, Mapping
import control_plane_db as cpd
# Outcomes / safe next actions (stable vocabulary for tools + tests).
SAFE_OWNER_RESUME = "owner_resume"
SAFE_WAIT_FOREIGN = "wait_foreign_active"
SAFE_RECLAIM_EXPIRED = "reclaim_expired"
SAFE_ABANDON_ALLOWED = "abandon_allowed"
SAFE_RELEASE_OWNED = "release_owned"
SAFE_STALE_PROMPT = "stale_prompt_lease"
SAFE_UNKNOWN = "inspect_only"
SAFE_NO_AUTHORITY = "file_or_comment_not_authoritative"
LEASE_STATUS_ACTIVE = "active"
LEASE_STATUS_RELEASED = "released"
LEASE_STATUS_EXPIRED = "expired"
LEASE_STATUS_ABANDONED = "abandoned"
AUTHORITATIVE_SOURCE = "control_plane_db"
class LeaseLifecycleError(RuntimeError):
"""Fail-closed lifecycle policy error."""
@dataclass(frozen=True)
class AbandonProof:
"""Required evidence to abandon a non-owned or expired lease safely."""
dead_process: bool = False
missing_worktree: bool = False
same_owner: bool = False
no_open_pr: bool = False
no_live_mutation_risk: bool = False
operator_authorized: bool = False
worktree_path: str | None = None
owner_pid: int | None = None
notes: str = ""
def as_dict(self) -> dict[str, Any]:
return {
"dead_process": self.dead_process,
"missing_worktree": self.missing_worktree,
"same_owner": self.same_owner,
"no_open_pr": self.no_open_pr,
"no_live_mutation_risk": self.no_live_mutation_risk,
"operator_authorized": self.operator_authorized,
"worktree_path": self.worktree_path,
"owner_pid": self.owner_pid,
"notes": self.notes,
}
def is_sufficient(self) -> bool:
"""Abandon requires process death or missing worktree + no mutation risk.
Foreign active leases additionally need operator_authorized unless the
owner process is dead and the worktree is missing.
"""
if not self.no_live_mutation_risk:
return False
if not (self.dead_process or self.missing_worktree):
return False
if self.same_owner:
return True
# Foreign abandon: operator flag OR (dead + missing worktree + no risk)
if self.operator_authorized:
return True
return bool(self.dead_process and self.missing_worktree and self.no_open_pr)
def is_process_alive(pid: int | None) -> bool:
if pid is None:
return False
try:
pid_i = int(pid)
except (TypeError, ValueError):
return False
if pid_i <= 0:
return False
try:
os.kill(pid_i, 0)
return True
except ProcessLookupError:
return False
except PermissionError:
# Exists but not owned by us — treat as alive (fail closed).
return True
except OSError:
return False
def worktree_exists(path: str | None) -> bool:
if not path:
return False
try:
return os.path.isdir(os.path.realpath(path))
except OSError:
return False
def _utc_now() -> datetime:
return datetime.now(timezone.utc)
def _parse_ts(value: str | None) -> datetime | None:
return cpd._parse_ts(value)
def classify_lease_freshness(
lease: Mapping[str, Any],
*,
now: datetime | None = None,
pid_checker: Callable[[int | None], bool] = is_process_alive,
worktree_checker: Callable[[str | None], bool] = worktree_exists,
) -> dict[str, Any]:
"""Classify a control-plane lease row for workflow tooling."""
moment = now or _utc_now()
status = (lease.get("status") or "").strip().lower()
expires = _parse_ts(lease.get("expires_at"))
owner_pid = lease.get("owner_pid")
if owner_pid is None:
owner_pid = lease.get("session_pid")
wt = lease.get("worktree_path")
pid_alive = pid_checker(owner_pid) if owner_pid is not None else None
wt_present = worktree_checker(wt) if wt else None
expired_by_time = bool(expires and expires <= moment)
if status == LEASE_STATUS_ABANDONED:
freshness = "abandoned"
elif status == LEASE_STATUS_RELEASED:
freshness = "released"
elif status == LEASE_STATUS_EXPIRED or expired_by_time:
freshness = "expired"
elif status != LEASE_STATUS_ACTIVE:
freshness = status or "unknown"
elif pid_alive is False:
freshness = "stale_dead_process"
elif wt is not None and wt_present is False:
freshness = "stale_missing_worktree"
else:
freshness = "active"
return {
"freshness": freshness,
"status": status,
"expired_by_time": expired_by_time,
"owner_pid": owner_pid,
"owner_pid_alive": pid_alive,
"worktree_path": wt,
"worktree_present": wt_present,
"expires_at": lease.get("expires_at"),
"authoritative_source": AUTHORITATIVE_SOURCE,
"file_lock_only": False,
"comment_lease_only": False,
}
def decide_safe_next_action(
*,
lease: Mapping[str, Any] | None,
caller_session_id: str,
freshness: Mapping[str, Any] | None = None,
caller_worktree: str | None = None,
) -> dict[str, Any]:
"""Return safe_next_action + reasons for a caller inspecting a lease."""
if not lease:
return {
"safe_next_action": SAFE_STALE_PROMPT,
"reasons": ["lease not found in control-plane DB (stale prompt id?)"],
"block": True,
}
fr = freshness or classify_lease_freshness(lease)
owner = str(lease.get("session_id") or "")
same_owner = owner == str(caller_session_id)
status = fr.get("freshness")
reasons: list[str] = []
# Worktree mismatch for owner resume
lease_wt = lease.get("worktree_path")
if (
same_owner
and lease_wt
and caller_worktree
and os.path.realpath(str(lease_wt)) != os.path.realpath(str(caller_worktree))
):
return {
"safe_next_action": SAFE_UNKNOWN,
"reasons": [
f"worktree mismatch: lease has {lease_wt!r}, caller has "
f"{caller_worktree!r} (fail closed)"
],
"block": True,
"same_owner": True,
}
if status in ("abandoned", "released"):
return {
"safe_next_action": SAFE_STALE_PROMPT,
"reasons": [f"lease status is {status}; do not adopt blindly"],
"block": True,
"same_owner": same_owner,
}
if status == "expired" or fr.get("expired_by_time"):
return {
"safe_next_action": SAFE_RECLAIM_EXPIRED,
"reasons": ["lease expired; reclaim via expire+assign or adopt reclaim path"],
"block": False,
"same_owner": same_owner,
}
if status in ("stale_dead_process", "stale_missing_worktree"):
if same_owner:
return {
"safe_next_action": SAFE_OWNER_RESUME,
"reasons": [
f"caller owns lease with freshness={status}; rebind via "
"adopt/owner-resume or abandon with proof"
],
"block": False,
"same_owner": True,
"also_allowed": [SAFE_ABANDON_ALLOWED, SAFE_RELEASE_OWNED],
}
return {
"safe_next_action": SAFE_ABANDON_ALLOWED,
"reasons": [
f"lease freshness={status}; abandon with required proof then reassign"
],
"block": False,
"same_owner": False,
}
if same_owner and status == "active":
return {
"safe_next_action": SAFE_OWNER_RESUME,
"reasons": [
"caller owns active lease; resume via heartbeat/assign owner-resume "
"or release explicitly"
],
"block": False,
"same_owner": True,
"also_allowed": [SAFE_RELEASE_OWNED],
}
if not same_owner and status == "active":
return {
"safe_next_action": SAFE_WAIT_FOREIGN,
"reasons": [
f"foreign active lease held by session {owner}; "
"do not steal (fail closed)"
],
"block": True,
"same_owner": False,
"owner_session_id": owner,
}
return {
"safe_next_action": SAFE_UNKNOWN,
"reasons": [f"unclassified freshness={status}"],
"block": True,
"same_owner": same_owner,
}
def non_db_lease_authority_report(
*,
file_lock_present: bool = False,
comment_lease_present: bool = False,
db_lease_present: bool = False,
) -> dict[str, Any]:
"""File/comment leases alone are not coordination authority (#601 / #600)."""
authoritative = bool(db_lease_present)
reasons: list[str] = []
if file_lock_present and not db_lease_present:
reasons.append(
"file lock present but control-plane DB lease absent — "
"file lock is not authoritative alone"
)
if comment_lease_present and not db_lease_present:
reasons.append(
"comment-only lease present but control-plane DB lease absent — "
"comment lease is not authoritative alone"
)
if authoritative:
reasons.append("control-plane DB lease is the coordination authority")
return {
"authoritative_source": AUTHORITATIVE_SOURCE if authoritative else None,
"db_lease_present": db_lease_present,
"file_lock_present": file_lock_present,
"comment_lease_present": comment_lease_present,
"safe_next_action": (
SAFE_UNKNOWN if authoritative else SAFE_NO_AUTHORITY
),
"reasons": reasons,
"file_lock_only": bool(file_lock_present and not db_lease_present),
"comment_lease_only": bool(comment_lease_present and not db_lease_present),
}
def build_adopt_provenance(
*,
adopted_from_session_id: str,
adopted_by_session_id: str,
work_kind: str,
work_number: int,
remote: str,
org: str,
repo: str,
worktree_path: str | None,
expected_head_sha: str | None,
prior_lease_id: str | None,
reason: str,
) -> dict[str, Any]:
return {
"adopted_from_session_id": adopted_from_session_id,
"adopted_by_session_id": adopted_by_session_id,
"work_kind": work_kind,
"work_number": int(work_number),
"remote": remote,
"org": org,
"repo": repo,
"worktree_path": worktree_path,
"expected_head_sha": expected_head_sha,
"prior_lease_id": prior_lease_id,
"reason": reason,
"recorded_at": cpd._ts(),
"source": "lease_lifecycle.adopt",
}
def inspect_lease(
db: cpd.ControlPlaneDB,
lease_id: str,
*,
caller_session_id: str,
caller_worktree: str | None = None,
) -> dict[str, Any]:
"""Full first-class lease workflow state for one lease id."""
state = db.get_lease_workflow_state(lease_id)
if not state:
decision = decide_safe_next_action(
lease=None, caller_session_id=caller_session_id
)
return {
"success": True,
"found": False,
"lease_id": lease_id,
"lease": None,
"freshness": None,
**decision,
"authoritative_source": AUTHORITATIVE_SOURCE,
"file_lock_only": False,
"comment_lease_only": False,
}
lease = state["lease"]
freshness = classify_lease_freshness(lease)
decision = decide_safe_next_action(
lease=lease,
caller_session_id=caller_session_id,
freshness=freshness,
caller_worktree=caller_worktree,
)
return {
"success": True,
"found": True,
"lease_id": lease_id,
"lease": lease,
"assignment": state.get("assignment"),
"work_item": state.get("work_item"),
"session": state.get("session"),
"freshness": freshness,
"provenance": state.get("provenance"),
**decision,
"authoritative_source": AUTHORITATIVE_SOURCE,
"file_lock_only": False,
"comment_lease_only": False,
}
def list_active_leases(
db: cpd.ControlPlaneDB,
*,
remote: str | None = None,
org: str | None = None,
repo: str | None = None,
role: str | None = None,
include_non_active: bool = False,
limit: int = 100,
) -> dict[str, Any]:
statuses = None if include_non_active else (LEASE_STATUS_ACTIVE,)
rows = db.list_leases(
remote=remote,
org=org,
repo=repo,
role=role,
statuses=statuses,
limit=limit,
)
enriched = []
for row in rows:
fr = classify_lease_freshness(row)
enriched.append({**row, "freshness": fr})
return {
"success": True,
"count": len(enriched),
"leases": enriched,
"authoritative_source": AUTHORITATIVE_SOURCE,
"file_lock_only": False,
"comment_lease_only": False,
"include_non_active": include_non_active,
}
def adopt_lease(
db: cpd.ControlPlaneDB,
*,
lease_id: str,
adopter_session_id: str,
role: str,
worktree_path: str | None = None,
expected_head_sha: str | None = None,
owner_pid: int | None = None,
operator_authorized: bool = False,
) -> dict[str, Any]:
"""Sanctioned adopt path with provenance; never silent foreign steal."""
state = db.get_lease_workflow_state(lease_id)
if not state:
raise LeaseLifecycleError(
f"unknown lease_id {lease_id}; stale prompt id (fail closed)"
)
lease = state["lease"]
work = state["work_item"]
freshness = classify_lease_freshness(lease)
owner = str(lease.get("session_id") or "")
same_owner = owner == str(adopter_session_id)
if freshness["freshness"] == "active" and not same_owner:
raise LeaseLifecycleError(
f"refusing to steal active foreign lease {lease_id} owned by "
f"{owner} (fail closed)"
)
if freshness["freshness"] in ("abandoned", "released"):
raise LeaseLifecycleError(
f"lease {lease_id} is {freshness['freshness']}; cannot adopt "
"(fail closed)"
)
# Expired or stale: require abandon-style safety before ownership transfer
# when not same owner; same owner may reclaim.
if not same_owner and freshness["freshness"] in (
"expired",
"stale_dead_process",
"stale_missing_worktree",
):
if not operator_authorized and freshness["freshness"] == "expired":
# Deterministic reclaim of expired foreign lease is allowed
# without operator flag (sanctioned expire reclaim).
pass
elif freshness["freshness"] != "expired" and not operator_authorized:
# stale active-looking requires abandon proof path
raise LeaseLifecycleError(
f"lease {lease_id} freshness={freshness['freshness']}; "
"use abandon with proof before foreign adopt (fail closed)"
)
provenance = build_adopt_provenance(
adopted_from_session_id=owner,
adopted_by_session_id=adopter_session_id,
work_kind=str(work.get("kind")),
work_number=int(work.get("number")),
remote=str(work.get("remote")),
org=str(work.get("org")),
repo=str(work.get("repo")),
worktree_path=worktree_path,
expected_head_sha=expected_head_sha or lease.get("expected_head_sha"),
prior_lease_id=lease_id,
reason=(
"owner-resume-adopt" if same_owner else "sanctioned-reclaim-adopt"
),
)
result = db.adopt_lease(
lease_id=lease_id,
adopter_session_id=adopter_session_id,
role=role,
worktree_path=worktree_path,
expected_head_sha=expected_head_sha,
owner_pid=owner_pid if owner_pid is not None else os.getpid(),
provenance=provenance,
)
return {
"success": True,
"outcome": result.get("outcome"),
"same_owner": same_owner,
"prior_lease_id": lease_id,
"lease": result.get("lease"),
"assignment": result.get("assignment"),
"provenance": provenance,
"authoritative_source": AUTHORITATIVE_SOURCE,
"file_lock_only": False,
"comment_lease_only": False,
"reasons": result.get("reasons") or [],
}
def release_lease(
db: cpd.ControlPlaneDB,
*,
lease_id: str,
session_id: str,
) -> dict[str, Any]:
proof = db.release_lease_recorded(lease_id=lease_id, session_id=session_id)
return {
"success": True,
"outcome": "released",
"lease_id": lease_id,
"session_id": session_id,
"release_proof": proof,
"authoritative_source": AUTHORITATIVE_SOURCE,
"file_lock_only": False,
"comment_lease_only": False,
}
def expire_leases(db: cpd.ControlPlaneDB) -> dict[str, Any]:
n = db.expire_stale_leases()
return {
"success": True,
"outcome": "expired",
"expired_count": int(n),
"authoritative_source": AUTHORITATIVE_SOURCE,
"file_lock_only": False,
"comment_lease_only": False,
}
def reclaim_expired_lease(
db: cpd.ControlPlaneDB,
*,
lease_id: str,
session_id: str,
role: str,
worktree_path: str | None = None,
expected_head_sha: str | None = None,
) -> dict[str, Any]:
"""Expire-if-needed then assign to *session_id* for the same work item."""
state = db.get_lease_workflow_state(lease_id)
if not state:
raise LeaseLifecycleError(f"unknown lease_id {lease_id}")
lease = state["lease"]
work = state["work_item"]
freshness = classify_lease_freshness(lease)
if freshness["freshness"] == "active":
if lease.get("session_id") != session_id:
raise LeaseLifecycleError(
f"cannot reclaim active foreign lease {lease_id} (fail closed)"
)
# owner resume
return adopt_lease(
db,
lease_id=lease_id,
adopter_session_id=session_id,
role=role,
worktree_path=worktree_path,
expected_head_sha=expected_head_sha,
)
if freshness["freshness"] not in (
"expired",
"stale_dead_process",
"stale_missing_worktree",
"abandoned",
"released",
):
raise LeaseLifecycleError(
f"lease {lease_id} freshness={freshness['freshness']} not reclaimable"
)
# Ensure expired marker is applied
db.expire_stale_leases()
# If still active due to clock skew / non-time stale, force expire this lease
refreshed = db.get_lease_workflow_state(lease_id)
if refreshed and refreshed["lease"].get("status") == "active":
db.force_expire_lease(lease_id, reason="reclaim_expired_lease")
head = expected_head_sha or work.get("current_head_sha")
assigned = db.assign_and_lease(
session_id=session_id,
role=role,
remote=str(work["remote"]),
org=str(work["org"]),
repo=str(work["repo"]),
kind=str(work["kind"]),
number=int(work["number"]),
expected_head_sha=head,
phase="reclaimed",
worktree_path=worktree_path,
owner_pid=os.getpid(),
)
if assigned.outcome != "assigned":
raise LeaseLifecycleError(
f"reclaim assign failed: {assigned.outcome}{assigned.reason}"
)
provenance = build_adopt_provenance(
adopted_from_session_id=str(lease.get("session_id")),
adopted_by_session_id=session_id,
work_kind=str(work["kind"]),
work_number=int(work["number"]),
remote=str(work["remote"]),
org=str(work["org"]),
repo=str(work["repo"]),
worktree_path=worktree_path,
expected_head_sha=head,
prior_lease_id=lease_id,
reason="reclaim_expired",
)
db.attach_lease_provenance(assigned.lease_id, provenance)
return {
"success": True,
"outcome": "reclaimed",
"prior_lease_id": lease_id,
"assignment": assigned.as_dict(),
"provenance": provenance,
"authoritative_source": AUTHORITATIVE_SOURCE,
"file_lock_only": False,
"comment_lease_only": False,
}
def abandon_lease(
db: cpd.ControlPlaneDB,
*,
lease_id: str,
requester_session_id: str,
proof: AbandonProof,
) -> dict[str, Any]:
state = db.get_lease_workflow_state(lease_id)
if not state:
raise LeaseLifecycleError(f"unknown lease_id {lease_id}")
lease = state["lease"]
owner = str(lease.get("session_id") or "")
same_owner = owner == str(requester_session_id)
# Enrich proof with live checks when not provided
owner_pid = proof.owner_pid
if owner_pid is None:
owner_pid = lease.get("owner_pid")
wt = proof.worktree_path if proof.worktree_path is not None else lease.get(
"worktree_path"
)
dead = proof.dead_process or (
owner_pid is not None and not is_process_alive(owner_pid)
)
missing_wt = proof.missing_worktree or (
bool(wt) and not worktree_exists(str(wt))
)
enriched = AbandonProof(
dead_process=bool(dead),
missing_worktree=bool(missing_wt),
same_owner=same_owner or proof.same_owner,
no_open_pr=proof.no_open_pr,
no_live_mutation_risk=proof.no_live_mutation_risk,
operator_authorized=proof.operator_authorized,
worktree_path=str(wt) if wt else None,
owner_pid=int(owner_pid) if owner_pid is not None else None,
notes=proof.notes,
)
if not enriched.is_sufficient():
raise LeaseLifecycleError(
"abandon proof insufficient: need (dead_process or missing_worktree) "
"and no_live_mutation_risk; foreign abandon also needs "
"operator_authorized or (dead+missing_worktree+no_open_pr). "
f"proof={enriched.as_dict()}"
)
# Active foreign with live process + present worktree: never abandon without
# operator (already covered by is_sufficient).
result = db.abandon_lease(
lease_id=lease_id,
requester_session_id=requester_session_id,
proof=enriched.as_dict(),
)
return {
"success": True,
"outcome": "abandoned",
"lease_id": lease_id,
"requester_session_id": requester_session_id,
"prior_owner_session_id": owner,
"abandon_proof": enriched.as_dict(),
"audit": result,
"authoritative_source": AUTHORITATIVE_SOURCE,
"file_lock_only": False,
"comment_lease_only": False,
}
+4 -12
View File
@@ -22,7 +22,7 @@ venv_python = os.path.join(PROJECT_ROOT, "venv", "bin", "python3")
if os.path.exists(venv_python) and sys.executable != venv_python:
os.execv(venv_python, [venv_python] + sys.argv)
from gitea_auth import get_auth_header, api_request, api_get_all, repo_api_url
from gitea_auth import get_auth_header, api_request, repo_api_url
import issue_workflow_labels
HOST = "gitea.dadeschools.net"
@@ -82,17 +82,9 @@ def api(method, path, auth, payload=None):
def _labels_by_name(auth):
"""Return {label name: id} for the repo's existing labels (all pages, #627)."""
existing = api_get_all(f"{BASE_URL}/labels", auth) or []
name_to_id = {}
for lb in existing:
if not isinstance(lb, dict):
continue
name = lb.get("name")
lid = lb.get("id")
if name and lid is not None and name not in name_to_id:
name_to_id[name] = lid
return name_to_id
"""Return {label name: id} for the repo's existing labels."""
existing = api("GET", "/labels?limit=100", auth) or []
return {lb["name"]: lb["id"] for lb in existing}
def create_labels(auth, dry=False):
+5 -5
View File
@@ -17,7 +17,7 @@ if os.path.exists(venv_python) and sys.executable != venv_python:
from gitea_auth import (
get_auth_header, resolve_remote, add_remote_args,
api_request, api_get_all, repo_api_url,
api_request, repo_api_url,
)
LABEL_NAME = "status:in-progress"
@@ -45,12 +45,12 @@ def main(argv=None):
base = repo_api_url(host, org, repo)
try:
# Paginated inventory (#627): Gitea caps single pages at 50.
labels = api_get_all(f"{base}/labels", auth) or []
# Find the label ID
labels = api_request("GET", f"{base}/labels?limit=100", auth)
label_id = None
for lb in labels:
if lb.get("name") == LABEL_NAME:
label_id = lb.get("id")
if lb["name"] == LABEL_NAME:
label_id = lb["id"]
break
if label_id is None:
-5
View File
@@ -29,11 +29,6 @@ class UnsanctionedRuntimeError(RuntimeError):
def is_pytest_runtime() -> bool:
if os.environ.get("GITEA_TEST_FORCE_UNSANCTIONED") == "1":
return False
import sys
if "pytest" in sys.modules:
return True
return bool((os.environ.get("PYTEST_CURRENT_TEST") or "").strip())
+14 -124
View File
@@ -3,15 +3,6 @@
The IDE/client namespace can fail with EOF even when this Python process still
registers the Gitea tools with FastMCP. These helpers keep that distinction
explicit so reviewer/merger flows can fail closed on the live path.
Probe sources
-------------
* ``client_namespace`` — evidence from the IDE-managed MCP client path (the
only source that can prove the workflow namespace is healthy).
* ``offline_spawn`` — a separate ``subprocess.Popen`` JSON-RPC handshake
(e.g. ``test_mcp_conn.py``). Useful offline, but **never** proves the
IDE-managed namespace is callable.
* ``unknown`` — legacy/unspecified; treated as not IDE-proven.
"""
from __future__ import annotations
@@ -28,20 +19,6 @@ REQUIRED_NAMESPACE_TOOLS = {
DEFAULT_NAMESPACES = tuple(REQUIRED_NAMESPACE_TOOLS)
# Namespaces that must be healthy for a given mutation task.
TASK_REQUIRED_NAMESPACES = {
"review_pr": "gitea-reviewer",
"submit_review": "gitea-reviewer",
"merge_pr": "gitea-merger",
}
PROBE_SOURCE_CLIENT = "client_namespace"
PROBE_SOURCE_OFFLINE = "offline_spawn"
PROBE_SOURCE_UNKNOWN = "unknown"
VALID_PROBE_SOURCES = frozenset(
{PROBE_SOURCE_CLIENT, PROBE_SOURCE_OFFLINE, PROBE_SOURCE_UNKNOWN}
)
EOF_PATTERNS = (
"client is closing: eof",
"transport closed",
@@ -73,13 +50,6 @@ def _contains_eof(text: str | None) -> bool:
return any(pattern in lowered for pattern in EOF_PATTERNS)
def _normalize_probe_source(probe_source: str | None) -> str:
raw = (probe_source or PROBE_SOURCE_UNKNOWN).strip().lower()
if raw in VALID_PROBE_SOURCES:
return raw
return PROBE_SOURCE_UNKNOWN
def _safe_env_summary(process: dict[str, Any] | None) -> dict[str, str]:
if not process:
return {}
@@ -103,17 +73,15 @@ def classify_namespace_probe(
config_path: str | None = None,
profile: str | None = None,
configured: bool = True,
probe_source: str | None = None,
) -> dict[str, Any]:
"""Classify whether a required tool is callable through a live namespace.
``registered_tools`` is static/server-side evidence. ``probe_result`` is
live invocation evidence. Only ``probe_source=client_namespace`` proves the
IDE-managed path; ``offline_spawn`` is an offline subprocess check only.
live client evidence from a real namespace invocation. The assessment is
healthy only when the required tool is registered and callable.
"""
ns = (namespace or "").strip()
tool = required_tool or REQUIRED_NAMESPACE_TOOLS.get(ns) or "gitea_whoami"
source = _normalize_probe_source(probe_source)
registered_list = _as_list(registered_tools)
registered = None if registered_list is None else tool in registered_list
@@ -145,9 +113,7 @@ def classify_namespace_probe(
error_type = "namespace_call_failed"
callable_live = bool(configured and probe_result and probe_success)
# Probe-path health (spawn or client). IDE-proven only for client path.
healthy = bool(configured and registered is not False and callable_live)
ide_namespace_proven = bool(healthy and source == PROBE_SOURCE_CLIENT)
process_pid = process.get("pid") if isinstance(process, dict) else None
profile_name = profile or (
process.get("profile") if isinstance(process, dict) else None
@@ -177,53 +143,24 @@ def classify_namespace_probe(
reasons.append(
f"Live MCP namespace '{ns}' failed while invoking '{tool}'."
)
if source == PROBE_SOURCE_OFFLINE:
reasons.append(
"Probe source is offline_spawn (subprocess JSON-RPC); this does "
"not prove the IDE-managed MCP namespace is healthy."
)
elif source == PROBE_SOURCE_UNKNOWN and probe_result:
reasons.append(
"Probe source unspecified; treat as not IDE-namespace proof unless "
"re-supplied with probe_source='client_namespace'."
)
remediation = []
if not healthy or not ide_namespace_proven:
if not healthy:
remediation.append(
"Reconnect the IDE MCP client namespace (client reconnect / "
f"relaunch), then invoke '{tool}' through namespace '{ns}' and "
"record the result with probe_source='client_namespace'."
"Restart or reconnect the IDE MCP client namespace, then retry "
f"'{tool}' through namespace '{ns}'."
)
remediation.append(
"Do not treat offline subprocess probes (test_mcp_conn.py) or "
"shell kill/PID respawn as proof the IDE namespace is repaired."
"Reload the MCP config and verify the configured command, args, "
"profile environment, and working tree point at the current checkout."
)
if process_pid and source != PROBE_SOURCE_OFFLINE:
if process_pid:
remediation.append(
f"Diagnostics may include PID {process_pid}; process details "
"are informational only — recovery is client-layer reconnect."
f"If PID {process_pid} belongs to a stale MCP process, stop it "
"before reconnecting the namespace."
)
else:
remediation.append(
f"IDE-managed namespace '{ns}' can invoke '{tool}' "
f"(probe_source={source})."
)
# Client-namespace broken health blocks review/merge. Offline probes never
# authorize mutations and only block when they report unhealthy (still
# fail-closed for known bad spawn evidence).
blocks = False
if source == PROBE_SOURCE_CLIENT:
blocks = namespace_health_blocks_task("merge_pr", healthy)
elif source == PROBE_SOURCE_OFFLINE:
# Offline never proves IDE health; never unblock. Unhealthy offline
# still surfaces as a soft diagnostic, not a mutation-ledger block.
blocks = False
else:
# Unknown source: only block when evidence is unhealthy (fail closed
# on bad data without treating success as IDE proof).
blocks = namespace_health_blocks_task("merge_pr", healthy)
remediation.append(f"Namespace '{ns}' can invoke '{tool}'.")
return {
"success": healthy,
@@ -234,8 +171,6 @@ def classify_namespace_probe(
"registered_tools_checked": registered_list is not None,
"required_tool_registered": registered,
"required_tool_callable": callable_live,
"probe_source": source,
"ide_namespace_proven": ide_namespace_proven,
"error_type": None if healthy else error_type,
"error_message": error_message or None,
"reasons": reasons,
@@ -247,9 +182,10 @@ def classify_namespace_probe(
"profile": profile_name,
"env": env_summary,
"config_path": config_path,
"probe_source": source,
},
"blocks_merge_workflow": blocks,
"blocks_merge_workflow": namespace_health_blocks_task(
"merge_pr", healthy
),
}
@@ -258,49 +194,3 @@ def namespace_health_blocks_task(task: str, healthy: bool) -> bool:
if healthy:
return False
return (task or "").strip() in {"merge_pr", "review_pr", "submit_review"}
def required_namespace_for_task(task: str) -> str | None:
"""Map a mutation task to the MCP namespace that must be healthy."""
return TASK_REQUIRED_NAMESPACES.get((task or "").strip())
def mutation_gate_from_session(
task: str,
session_health: dict[str, dict[str, Any]] | None,
) -> list[str]:
"""Fail-closed gate using recorded client-namespace health assessments.
* Missing session entry → no gate (caller has not assessed yet).
* Client-namespace unhealthy / not IDE-proven → block mutation.
* Offline-only session entries never authorize mutations.
"""
ns = required_namespace_for_task(task)
if not ns:
return []
store = session_health or {}
entry = store.get(ns)
if not entry:
return []
source = _normalize_probe_source(entry.get("probe_source"))
if source != PROBE_SOURCE_CLIENT:
return [
f"recorded namespace health for '{ns}' is probe_source={source}, "
"not client_namespace; re-probe through the IDE-managed path "
f"before {(task or 'mutation')}"
]
if entry.get("ide_namespace_proven") and entry.get("healthy"):
return []
if entry.get("blocks_merge_workflow") or not entry.get("healthy"):
detail = entry.get("error_type") or "unhealthy"
return [
f"live MCP namespace '{ns}' is recorded {detail} "
f"(probe_source={source}); repair the IDE namespace before "
f"{(task or 'mutation')} (fail closed, #543)"
]
if not entry.get("ide_namespace_proven"):
return [
f"live MCP namespace '{ns}' is not IDE-proven; supply a "
"client_namespace probe before mutation (fail closed, #543)"
]
return []
-1
View File
@@ -13,7 +13,6 @@ from typing import Any
AUTHORIZED_CLEANUP_TOOLS = frozenset({
"gitea_cleanup_post_merge_moot_lease",
"gitea_cleanup_obsolete_reviewer_comment_lease",
"gitea_reconcile_merged_cleanups",
"gitea_delete_branch",
"gitea_cleanup_merged_pr_branch",
-4
View File
@@ -6,10 +6,6 @@ Runs over stdio. All tools authenticate via macOS keychain (git credential fill)
import os
import sys
if "PYTEST_CURRENT_TEST" not in os.environ:
sys.stderr = open("/tmp/mcp_server_stderr.log", "a", buffering=1)
sys.stderr.write(f"\n--- MCP SERVER STARTUP (PID {os.getpid()}) ---\n")
from role_session_router import (
python_bytes_have_conflict_markers,
skip_python_scan_walk_root,
-8
View File
@@ -30,14 +30,6 @@ DEFAULT_TTL_HOURS = 4.0
KIND_WORKFLOW_LOAD = "review_workflow_load"
KIND_DECISION_LOCK = "review_decision_lock"
KIND_REVIEW_DRAFT = "review_draft"
# Durable marker set when a worker session attempts a direct stable-branch push
# or a root-checkout local commit (#671). Keyed per profile identity like the
# other session proofs; a contaminated session fails closed on gated mutations
# until a reconciler audits and clears it.
KIND_STABLE_BRANCH_CONTAMINATION = "stable_branch_contamination"
_SAFE_SEGMENT_RE = re.compile(r"[^A-Za-z0-9._+-]+")
SESSION_PROFILE_LOCK_ENV = "GITEA_SESSION_PROFILE_LOCK"
-451
View File
@@ -1,451 +0,0 @@
"""MCP tool-boundary error mapping for known Gitea client failures (#699).
Known authentication / authorization / network / configuration failures leave
the tool boundary as a sanitized structured ``CallToolResult`` with
``isError=True``. Stdio transport remains connected.
Design constraints (reviewer-ratified, #699 / PR #701):
1. **No secret material** in tool results or daemon logs. Messages are fixed
constants keyed by ``reason_code``; HTTP bodies / exception text never
surface. Sanitization failure fails closed to ``internal_error``.
2. **Narrow boundary** wraps the original FastMCP ``Tool.run`` success path;
re-raises framework control-flow exceptions (``UrlElicitationRequiredError``);
maps only typed client failures. Installation is idempotent.
3. **No RuntimeError substring heuristics.** Only explicit typed
authentication / authorization / network / configuration exceptions
receive those labels.
4. **HTTP classification** lives in ``gitea_auth.classify_http_status``;
every 403 is authorization-class.
"""
from __future__ import annotations
import json
import logging
import sys
from typing import Any
logger = logging.getLogger("gitea_mcp.tool_error_boundary")
# Stable reason codes (#699).
REASON_AUTH_FAILED = "auth_failed"
REASON_AUTH_INVALID_TOKEN = "auth_invalid_token"
REASON_AUTHZ_INSUFFICIENT_SCOPE = "authz_insufficient_scope"
REASON_AUTHZ_DENIED = "authz_denied"
REASON_NETWORK_ERROR = "network_error"
REASON_CONFIG_ERROR = "config_error"
REASON_INTERNAL_ERROR = "internal_error"
REASON_UPSTREAM_UNAVAILABLE = "upstream_unavailable"
REASON_HTTP_ERROR = "http_error"
ERROR_CLASS_AUTHENTICATION = "authentication"
ERROR_CLASS_AUTHORIZATION = "authorization"
ERROR_CLASS_NETWORK = "network"
ERROR_CLASS_CONFIGURATION = "configuration"
ERROR_CLASS_INTERNAL = "internal"
ERROR_CLASS_UPSTREAM = "upstream"
# Fixed, secret-free operator messages. Never interpolate HTTP bodies,
# Keychain contents, tokens, or arbitrary exception text.
FIXED_MESSAGES: dict[str, str] = {
REASON_AUTH_FAILED: "Gitea authentication failed",
REASON_AUTH_INVALID_TOKEN: (
"Gitea authentication failed: invalid or revoked credentials"
),
REASON_AUTHZ_INSUFFICIENT_SCOPE: (
"Gitea authorization failed: insufficient token scope"
),
REASON_AUTHZ_DENIED: "Gitea authorization failed: access denied",
REASON_NETWORK_ERROR: "Network error contacting Gitea",
REASON_CONFIG_ERROR: "Gitea configuration or credential resolution failed",
REASON_INTERNAL_ERROR: "Internal tool error",
REASON_UPSTREAM_UNAVAILABLE: "Gitea upstream unavailable",
REASON_HTTP_ERROR: "Gitea HTTP request failed",
}
_INSTALL_FLAG = "_gitea_auth_boundary_installed"
_ORIGINAL_ATTR = "_gitea_auth_boundary_original"
def fixed_message(reason_code: str) -> str:
"""Return the fixed sanitized message for *reason_code* (fail closed)."""
return FIXED_MESSAGES.get(reason_code, FIXED_MESSAGES[REASON_INTERNAL_ERROR])
def _safe_profile_name() -> str | None:
try:
from gitea_auth import get_profile
name = (get_profile() or {}).get("profile_name")
if name is None:
return None
text = str(name).strip()
# Profile names are non-secret identifiers; still bound length.
return text[:80] if text else None
except Exception:
return None
def _is_framework_control_flow(exc: BaseException) -> bool:
"""True for exceptions the MCP framework must re-raise unchanged."""
try:
from mcp.shared.exceptions import UrlElicitationRequiredError
if isinstance(exc, UrlElicitationRequiredError):
return True
except Exception:
pass
# BaseException subclasses that must never become tool isError payloads.
if isinstance(exc, (KeyboardInterrupt, SystemExit, GeneratorExit)):
return True
return False
def is_known_client_failure(exc: BaseException) -> bool:
"""True only for explicit typed Gitea client / config failures.
Never true for arbitrary ``RuntimeError`` (reviewer finding #3).
"""
try:
import gitea_auth
if isinstance(
exc,
(
gitea_auth.GiteaAuthError,
gitea_auth.GiteaAuthzError,
gitea_auth.GiteaNetworkError,
gitea_auth.GiteaConfigError,
gitea_auth.GiteaHttpError,
),
):
return True
except Exception:
return False
try:
import gitea_config
if isinstance(exc, gitea_config.ConfigError):
return True
except Exception:
pass
return False
def classify_exception(exc: BaseException) -> dict[str, Any]:
"""Return structured classification with **fixed** messages only.
Only typed authentication / authorization / network / configuration
failures receive those labels. Unexpected programming failures are
``internal_error``. HTTP bodies and exception text are never copied
into ``message``.
"""
try:
return _classify_exception_impl(exc)
except Exception:
# Fail closed: sanitization / classification failure must not leak.
return {
"reason_code": REASON_INTERNAL_ERROR,
"error_class": ERROR_CLASS_INTERNAL,
"http_status": None,
"message": fixed_message(REASON_INTERNAL_ERROR),
"transport_survives": True,
}
def _classify_exception_impl(exc: BaseException) -> dict[str, Any]:
import gitea_auth
if isinstance(exc, gitea_auth.GiteaAuthError):
code = getattr(exc, "reason_code", None) or REASON_AUTH_INVALID_TOKEN
if code not in (
REASON_AUTH_FAILED,
REASON_AUTH_INVALID_TOKEN,
):
code = REASON_AUTH_INVALID_TOKEN
return {
"reason_code": code,
"error_class": ERROR_CLASS_AUTHENTICATION,
"http_status": getattr(exc, "http_status", None) or 401,
"message": fixed_message(code),
"transport_survives": True,
}
if isinstance(exc, gitea_auth.GiteaAuthzError):
code = getattr(exc, "reason_code", None) or REASON_AUTHZ_DENIED
if code not in (REASON_AUTHZ_DENIED, REASON_AUTHZ_INSUFFICIENT_SCOPE):
code = REASON_AUTHZ_DENIED
return {
"reason_code": code,
"error_class": ERROR_CLASS_AUTHORIZATION,
"http_status": getattr(exc, "http_status", None) or 403,
"message": fixed_message(code),
"transport_survives": True,
}
if isinstance(exc, gitea_auth.GiteaNetworkError):
return {
"reason_code": REASON_NETWORK_ERROR,
"error_class": ERROR_CLASS_NETWORK,
"http_status": getattr(exc, "http_status", None),
"message": fixed_message(REASON_NETWORK_ERROR),
"transport_survives": True,
}
if isinstance(exc, gitea_auth.GiteaConfigError):
return {
"reason_code": REASON_CONFIG_ERROR,
"error_class": ERROR_CLASS_CONFIGURATION,
"http_status": getattr(exc, "http_status", None),
"message": fixed_message(REASON_CONFIG_ERROR),
"transport_survives": True,
}
if isinstance(exc, gitea_auth.GiteaHttpError):
code = getattr(exc, "reason_code", None) or REASON_HTTP_ERROR
if code == REASON_UPSTREAM_UNAVAILABLE:
error_class = ERROR_CLASS_UPSTREAM
else:
error_class = ERROR_CLASS_INTERNAL
code = REASON_HTTP_ERROR
return {
"reason_code": code,
"error_class": error_class,
"http_status": getattr(exc, "http_status", None),
"message": fixed_message(code),
"transport_survives": True,
}
try:
import gitea_config
if isinstance(exc, gitea_config.ConfigError):
return {
"reason_code": REASON_CONFIG_ERROR,
"error_class": ERROR_CLASS_CONFIGURATION,
"http_status": None,
"message": fixed_message(REASON_CONFIG_ERROR),
"transport_survives": True,
}
except Exception:
pass
# Unwrap FastMCP ToolError cause when the original was a typed failure.
cause = getattr(exc, "__cause__", None)
if cause is not None and cause is not exc and is_known_client_failure(cause):
return _classify_exception_impl(cause)
# No message-substring authentication heuristics (reviewer finding #3).
return {
"reason_code": REASON_INTERNAL_ERROR,
"error_class": ERROR_CLASS_INTERNAL,
"http_status": None,
"message": fixed_message(REASON_INTERNAL_ERROR),
"transport_survives": True,
}
def build_structured_error_payload(
classification: dict[str, Any],
*,
tool_name: str | None = None,
profile_name: str | None = None,
) -> dict[str, Any]:
"""LLM-safe structured payload — fixed message + typed metadata only."""
try:
reason = str(classification.get("reason_code") or REASON_INTERNAL_ERROR)
message = fixed_message(reason)
# Refuse to emit any classification message that is not the fixed constant.
if classification.get("message") != message:
message = fixed_message(reason)
payload: dict[str, Any] = {
"success": False,
"isError": True,
"reason_code": reason if reason in FIXED_MESSAGES else REASON_INTERNAL_ERROR,
"error_class": classification.get("error_class") or ERROR_CLASS_INTERNAL,
"message": message,
"transport_survives": True,
"retryable": classification.get("error_class")
in {
ERROR_CLASS_AUTHENTICATION,
ERROR_CLASS_NETWORK,
ERROR_CLASS_CONFIGURATION,
},
}
status = classification.get("http_status")
if isinstance(status, int):
payload["http_status"] = status
if tool_name and isinstance(tool_name, str):
# Tool names are identifiers, not secrets; bound length.
payload["tool"] = tool_name[:120]
if profile_name and isinstance(profile_name, str):
payload["profile"] = profile_name[:80]
return payload
except Exception:
return {
"success": False,
"isError": True,
"reason_code": REASON_INTERNAL_ERROR,
"error_class": ERROR_CLASS_INTERNAL,
"message": fixed_message(REASON_INTERNAL_ERROR),
"transport_survives": True,
"retryable": False,
}
def log_sanitized_daemon_reason(
classification: dict[str, Any],
*,
tool_name: str | None = None,
stream=None,
) -> None:
"""Daemon log: reason codes only — never exception text or response bodies."""
stream = stream if stream is not None else sys.stderr
try:
reason = classification.get("reason_code") or REASON_INTERNAL_ERROR
error_class = classification.get("error_class") or ERROR_CLASS_INTERNAL
# Only emit known tokens; never classification['message'] from callers
# that might have been poisoned.
if reason not in FIXED_MESSAGES:
reason = REASON_INTERNAL_ERROR
error_class = ERROR_CLASS_INTERNAL
parts = [
"mcp_tool_error",
f"reason_code={reason}",
f"error_class={error_class}",
]
if tool_name and isinstance(tool_name, str):
parts.append(f"tool={tool_name[:120]}")
status = classification.get("http_status")
if isinstance(status, int):
parts.append(f"http_status={status}")
# Intentionally no detail= / message= field — secrets lived there.
line = " ".join(parts)
stream.write(line + "\n")
if hasattr(stream, "flush"):
stream.flush()
logger.warning(line)
except Exception:
# Fail closed: never fall back to logging the exception.
try:
stream.write(
"mcp_tool_error reason_code=internal_error "
"error_class=internal\n"
)
if hasattr(stream, "flush"):
stream.flush()
except Exception:
pass
def to_call_tool_result(
exc: BaseException,
*,
tool_name: str | None = None,
profile_name: str | None = None,
log: bool = True,
) -> Any:
"""Build a FastMCP ``CallToolResult`` with ``isError=True`` for *exc*."""
from mcp.types import CallToolResult, TextContent
try:
classification = classify_exception(exc)
if log:
log_sanitized_daemon_reason(classification, tool_name=tool_name)
payload = build_structured_error_payload(
classification, tool_name=tool_name, profile_name=profile_name
)
text = json.dumps(payload, indent=2, sort_keys=True)
return CallToolResult(
content=[TextContent(type="text", text=text)],
structuredContent=payload,
isError=True,
)
except Exception:
# Absolute fail-closed path — no exception text.
fallback = {
"success": False,
"isError": True,
"reason_code": REASON_INTERNAL_ERROR,
"error_class": ERROR_CLASS_INTERNAL,
"message": fixed_message(REASON_INTERNAL_ERROR),
"transport_survives": True,
"retryable": False,
}
return CallToolResult(
content=[
TextContent(
type="text",
text=json.dumps(fallback, indent=2, sort_keys=True),
)
],
structuredContent=fallback,
isError=True,
)
def install_tool_run_boundary(Tool) -> bool:
"""Install a **narrow** error boundary around FastMCP ``Tool.run``.
Strategy (preserves framework semantics):
* Call the **original** ``Tool.run`` for the success path (async, return
types, convert_result, protocol behavior unchanged).
* Re-raise ``UrlElicitationRequiredError`` and other control-flow
exceptions without mapping to ``internal_error``.
* Map typed Gitea client failures (and ToolError whose ``__cause__`` is
typed) to structured ``CallToolResult(isError=True)``.
* Map remaining unexpected tool failures to fixed ``internal_error``
isError results (transport survival) without secret-bearing text.
* Idempotent: second install is a no-op and returns ``False``.
"""
if getattr(Tool.run, _INSTALL_FLAG, False):
return False
from mcp.server.fastmcp.exceptions import ToolError
from mcp.shared.exceptions import UrlElicitationRequiredError
original_run = Tool.run
async def run_boundary(
self,
arguments: dict[str, Any],
context=None,
convert_result: bool = False,
) -> Any:
try:
return await original_run(
self,
arguments,
context=context,
convert_result=convert_result,
)
except UrlElicitationRequiredError:
# Framework control-flow — must not become internal_error.
raise
except BaseException as exc:
if _is_framework_control_flow(exc):
raise
if not isinstance(exc, Exception):
raise
# Prefer typed cause under FastMCP ToolError wrappers.
target: BaseException = exc
if isinstance(exc, ToolError) and exc.__cause__ is not None:
target = exc.__cause__
# Known client failures → structured isError with reason codes.
# Unexpected failures → fixed internal_error isError (no secrets).
profile_name = _safe_profile_name()
return to_call_tool_result(
target,
tool_name=getattr(self, "name", None),
profile_name=profile_name,
)
setattr(run_boundary, _INSTALL_FLAG, True)
setattr(run_boundary, _ORIGINAL_ATTR, original_run)
Tool.run = run_boundary # type: ignore[method-assign]
return True
def boundary_is_installed(Tool) -> bool:
"""True when the #699 boundary is active on *Tool.run*."""
return bool(getattr(Tool.run, _INSTALL_FLAG, False))
-110
View File
@@ -7,7 +7,6 @@ after formal approval at the current PR head.
from __future__ import annotations
import re
from datetime import datetime, timezone
from typing import Any
@@ -134,115 +133,6 @@ def is_sanctioned_session_lease(session: dict[str, Any] | None) -> bool:
return False
def describe_session_lease_proof(
session: dict[str, Any] | None,
) -> dict[str, Any]:
"""Canonical merge-report lease proof fields (#535).
Surfaces how the in-session lease was established so merge handoffs can
distinguish sanctioned MCP acquire/adopt paths from bare manual seeding.
"""
if not session:
return {
"lease_proof_source": None,
"lease_recovery_reason": None,
"lease_proof_kind": "none",
"lease_proof_sanctioned": False,
"lease_proof_comment_id": None,
"lease_adopted_from_session_id": None,
}
provenance = session.get("lease_provenance") or {}
if not isinstance(provenance, dict):
provenance = {}
source = (provenance.get("source") or "").strip() or None
sanctioned = is_sanctioned_session_lease(session)
reason = provenance.get("adoption_reason")
if isinstance(reason, str):
reason = reason.strip() or None
else:
reason = None
if source == SOURCE_ADOPT and sanctioned:
kind = "sanctioned_adoption"
reason = reason or DEFAULT_ADOPTION_REASON
elif source == SOURCE_ACQUIRE and sanctioned:
kind = "sanctioned_acquire"
elif source == SOURCE_HEARTBEAT and sanctioned:
kind = "sanctioned_heartbeat"
elif source:
kind = "unsanctioned"
else:
# Session present without provenance = classic manual _SESSION_LEASE seed.
kind = "unsanctioned_manual_seed"
comment_id = provenance.get("comment_id")
if comment_id is None:
comment_id = session.get("comment_id")
return {
"lease_proof_source": source,
"lease_recovery_reason": reason,
"lease_proof_kind": kind,
"lease_proof_sanctioned": sanctioned,
"lease_proof_comment_id": comment_id,
"lease_adopted_from_session_id": provenance.get("adopted_from_session_id"),
}
# Phrases that claim non-MCP / fabricated lease proof in handoffs (#535).
_UNSAFE_LEASE_PROOF_CLAIM_RE = re.compile(
r"(?is)\b("
r"manually\s+seeded\s+lease|"
r"manual(?:ly)?\s+seed(?:ed)?\s+(?:lease|proof)|"
r"seeded\s+lease\s+proof|"
r"injected\s+lease|"
r"lease\s+proof\s+injected|"
r"manual\s+_?SESSION_LEASE|"
r"_SESSION_LEASE\s+seed|"
r"unsanctioned\s+lease\s+proof"
r")\b"
)
# Evidence that the report used the sanctioned MCP adoption/acquire path.
_SANCTIONED_LEASE_EVIDENCE_RE = re.compile(
r"(?is)\b("
r"gitea_adopt_merger_pr_lease|"
r"gitea_acquire_reviewer_pr_lease|"
r"lease_proof_source\s*[:=]\s*gitea_adopt_merger_pr_lease|"
r"lease_proof_source\s*[:=]\s*gitea_acquire_reviewer_pr_lease|"
r"lease_proof_kind\s*[:=]\s*sanctioned_adoption|"
r"lease_proof_kind\s*[:=]\s*sanctioned_acquire|"
r"adoption_comment_id\s*[:=]|"
r"sanctioned_adoption|"
r"mcp-review-lease-adoption"
r")\b"
)
def assess_manual_lease_proof_handoff(report_text: str) -> dict[str, Any]:
"""Controller audit: block handoffs that claim unsafe lease seeding (#535).
Reports may discuss manual seeding as a blocked/historical anti-pattern only
when they also cite sanctioned MCP adoption/acquire evidence. Bare claims of
manual/seeded/injected lease proof without that evidence fail closed.
"""
text = report_text or ""
if not _UNSAFE_LEASE_PROOF_CLAIM_RE.search(text):
return {"proven": True, "block": False, "reasons": []}
if _SANCTIONED_LEASE_EVIDENCE_RE.search(text):
return {"proven": True, "block": False, "reasons": []}
return {
"proven": False,
"block": True,
"reasons": [
"report claims manual/seeded/injected/unsanctioned lease proof without "
"sanctioned MCP adoption evidence (use gitea_adopt_merger_pr_lease / "
"gitea_acquire_reviewer_pr_lease and cite lease_proof_source; #535)"
],
}
def assess_adopt_merger_lease(
comments: list[dict],
*,
-222
View File
@@ -1,222 +0,0 @@
"""Canonical post-merge (moot) validation outcome and wording gate (#529).
When a PR is already merged or closed *before* a reviewer submits their
verdict, an ordinary "approve" is misleading: the review never gated the
merge, so a normal active approval overstates controller confidence. The
sanctioned outcome for that case is a **post-merge moot validation** — the
reviewer records what validation found, but classifies it as moot rather than
an active approval.
This module defines the four canonical validation distinctions #529 requires
and enforces the post-merge case:
- ``CLEAN_PASS_OUTCOME`` — clean validation pass on an open, reviewable PR.
- ``BASELINE_ACCEPTED_OUTCOME`` — validation pass with a baseline-proven
unrelated failure (proof handled by :mod:`premerge_baseline_proof`).
- ``BLOCKED_OUTCOME`` — validation blocked by an unresolved failure.
- ``POST_MERGE_MOOT_OUTCOME`` — the PR was already merged/closed before review
submission; validation is recorded as post-merge moot, not an active
approval.
The gate blocks two mistakes:
1. Claiming an *active approval* on a PR that was already merged/closed before
review submission (must be recorded as post-merge moot validation instead).
2. Claiming post-merge moot validation without proof the PR is actually
merged/closed (a merged-state field plus a merge commit SHA).
Each outcome maps to a durable ``validation:*`` process-state label so PRs and
issues carry the distinction (#529 acceptance criterion).
"""
from __future__ import annotations
import re
from typing import Any
CLEAN_PASS_OUTCOME = "clean validation pass"
BASELINE_ACCEPTED_OUTCOME = "validation pass with baseline-proven unrelated failure"
BLOCKED_OUTCOME = "validation blocked by unresolved failure"
POST_MERGE_MOOT_OUTCOME = "post-merge moot validation"
# Canonical validation status label a reviewer writes in the report body for the
# post-merge case; kept in sync with validation_status_vocabulary.
POST_MERGE_MOOT_STATUS = "post-merge moot validation"
# Durable process-state labels (registered in issue_workflow_labels).
LABEL_CLEAN_PASS = "validation:clean-pass"
LABEL_BASELINE_ACCEPTED = "validation:baseline-accepted"
LABEL_BLOCKED = "validation:blocked"
LABEL_POST_MERGE_MOOT = "validation:post-merge-moot"
_OUTCOME_TO_LABEL: dict[str, str] = {
CLEAN_PASS_OUTCOME: LABEL_CLEAN_PASS,
BASELINE_ACCEPTED_OUTCOME: LABEL_BASELINE_ACCEPTED,
BLOCKED_OUTCOME: LABEL_BLOCKED,
POST_MERGE_MOOT_OUTCOME: LABEL_POST_MERGE_MOOT,
}
# The PR was already merged/closed before the review was submitted.
_MERGED_BEFORE_REVIEW_RE = re.compile(
r"(?:already[- ]merged"
r"|merged\s+before\s+review"
r"|closed\s+before\s+review"
r"|pr\s+(?:is|was)\s+(?:already\s+)?(?:merged|closed)"
r"|pr\s+state\s*[:=]\s*(?:merged|closed)"
r"|merged\s*/\s*closed)",
re.IGNORECASE,
)
# An active approval verdict is being claimed.
_ACTIVE_APPROVAL_RE = re.compile(
r"(?:review\s+decision\s*[:=]\s*approve"
r"|submitted\s+['\"]?approve['\"]?"
r"|active\s+approval"
r"|approving\s+the\s+pr"
r"|posting\s+an?\s+approval)",
re.IGNORECASE,
)
# The sanctioned post-merge moot validation wording.
_POST_MERGE_MOOT_RE = re.compile(
r"post[- ]merge\s+(?:moot\s+)?validation"
r"|post[- ]merge\s+moot"
r"|moot\s+validation",
re.IGNORECASE,
)
# Proof the PR is genuinely merged/closed.
_MERGED_STATE_PROOF_RE = re.compile(
r"(?:pr\s+state\s*[:=]\s*(?:merged|closed)"
r"|merged_at\s*[:=]\s*\S"
r"|closed_at\s*[:=]\s*\S"
r"|state\s*[:=]\s*(?:merged|closed))",
re.IGNORECASE,
)
_MERGE_COMMIT_SHA_RE = re.compile(
r"merge\s+commit(?:\s+sha)?\s*[:=]\s*[0-9a-f]{7,40}",
re.IGNORECASE,
)
POST_MERGE_VALIDATION_TEMPLATE = (
"Validation status: post-merge moot validation\n"
"PR state: merged\n"
"Merge commit sha: <40-hex merge commit>\n"
"Validation finding: <what the validation run showed, for the record>\n"
"Note: PR merged/closed before review submission; recorded as post-merge "
"moot validation, not an active approval."
)
def process_state_label(outcome: str) -> str | None:
"""Return the durable ``validation:*`` label for a canonical outcome."""
return _OUTCOME_TO_LABEL.get(outcome)
def assess_post_merge_validation(
report_text: str,
*,
pr_merged_or_closed: bool | None = None,
) -> dict[str, Any]:
"""Assess post-merge moot validation wording and proof (#529).
Args:
report_text: The reviewer final report text.
pr_merged_or_closed: Optional structured signal that the PR is already
merged/closed. When ``True`` it forces the merged-before-review
path even if the report text omits the phrasing; proof fields are
still required in the report body for durability.
Returns a dict with ``proven``, ``block``, ``outcome``,
``process_state_label``, ``reasons``, ``skipped`` and ``safe_next_action``.
Only blocks when the report either claims an active approval on a
merged/closed PR, or claims post-merge moot validation without proof.
"""
text = report_text or ""
merged_signal = bool(_MERGED_BEFORE_REVIEW_RE.search(text)) or bool(
pr_merged_or_closed
)
active_approval = bool(_ACTIVE_APPROVAL_RE.search(text))
moot_wording = bool(_POST_MERGE_MOOT_RE.search(text))
# Nothing about merged-state or moot validation — not applicable here.
if not merged_signal and not moot_wording:
return {
"proven": True,
"block": False,
"outcome": None,
"process_state_label": None,
"reasons": [],
"skipped": True,
"safe_next_action": "",
}
# An active approval on a PR already merged/closed before review, without
# the sanctioned moot wording, overstates confidence.
if merged_signal and active_approval and not moot_wording:
return {
"proven": False,
"block": True,
"outcome": POST_MERGE_MOOT_OUTCOME,
"process_state_label": LABEL_POST_MERGE_MOOT,
"reasons": [
"PR was already merged/closed before review submission; an "
"active approval overstates confidence — record 'post-merge "
"moot validation' instead of a normal approval"
],
"skipped": False,
"safe_next_action": (
"classify the outcome as post-merge moot validation (not an "
"active approval); cite PR state merged/closed and the merge "
"commit SHA. Template:\n" + POST_MERGE_VALIDATION_TEMPLATE
),
}
# Post-merge moot validation claimed — require merged-state + commit proof.
if moot_wording:
reasons: list[str] = []
if not _MERGED_STATE_PROOF_RE.search(text):
reasons.append(
"post-merge moot validation claimed without merged/closed state "
"proof (state: merged/closed, or merged_at/closed_at)"
)
if not _MERGE_COMMIT_SHA_RE.search(text):
reasons.append(
"post-merge moot validation claimed without a merge commit SHA"
)
if reasons:
return {
"proven": False,
"block": True,
"outcome": POST_MERGE_MOOT_OUTCOME,
"process_state_label": LABEL_POST_MERGE_MOOT,
"reasons": reasons,
"skipped": False,
"safe_next_action": (
"prove the PR is merged/closed: cite PR state and the merge "
"commit SHA. Template:\n" + POST_MERGE_VALIDATION_TEMPLATE
),
}
return {
"proven": True,
"block": False,
"outcome": POST_MERGE_MOOT_OUTCOME,
"process_state_label": LABEL_POST_MERGE_MOOT,
"reasons": [],
"skipped": False,
"safe_next_action": "",
}
# Merged signal present but no approval claim and no moot wording yet —
# guide toward the moot outcome without blocking.
return {
"proven": True,
"block": False,
"outcome": POST_MERGE_MOOT_OUTCOME,
"process_state_label": LABEL_POST_MERGE_MOOT,
"reasons": [],
"skipped": False,
"safe_next_action": (
"PR appears merged/closed; if submitting a verdict, record "
"post-merge moot validation rather than an active approval"
),
}
+2 -26
View File
@@ -16,35 +16,11 @@ or the local remote URL is unavailable (best-effort corroboration only).
from __future__ import annotations
import re
REMEDIATION = (
"Pass explicit org= and repo= matching the local git remote on tools that "
"accept those parameters (including mcp_get_control_plane_guide), "
"e.g. org=Scaled-Tech-Consulting repo=Gitea-Tools. "
"Do not pass org/repo to tools whose schema does not list them."
"Pass explicit org= and repo= matching the local git remote, "
"e.g. org=Scaled-Tech-Consulting repo=Gitea-Tools."
)
# https://host/org/repo.git or git@host:org/repo.git
_REMOTE_URL_SLUG_RE = re.compile(
r"(?:[:/])(?P<org>[^/]+)/(?P<repo>[^/]+?)(?:\.git)?/*$"
)
def parse_org_repo_from_remote_url(remote_url: str | None) -> tuple[str, str] | None:
"""Best-effort parse of org/repo from a git remote URL."""
url = (remote_url or "").strip()
if not url:
return None
match = _REMOTE_URL_SLUG_RE.search(url)
if not match:
return None
org = (match.group("org") or "").strip()
repo = (match.group("repo") or "").strip()
if not org or not repo:
return None
return org, repo
def assess_remote_repo_match(
*,
-167
View File
@@ -4842,22 +4842,6 @@ RECONCILER_CLOSE_REPORT_FIELDS = (
"no review/merge confirmation",
)
RECONCILER_SUPERSESSION_REPORT_FIELDS = (
"identity/profile",
"supersession close capability proof",
"target PR live state",
"target PR independent-work proof",
"superseding PR merged state",
"superseding merge commit SHA",
"target branch SHA",
"superseding ancestry proof",
"canonical close comment",
"linked issue status",
"PR close result",
"issue close result",
"no review/merge confirmation",
)
def assess_reconciler_close_gate(
*,
@@ -5004,157 +4988,6 @@ def assess_reconciler_close_gate(
}
def assess_reconciler_supersession_close_gate(
*,
target_pr_number: int | None,
target_pr_state: str | None,
target_pr_mergeable: bool | None,
target_independently_required: bool | None,
superseding_pr_number: int | None,
superseding_pr_state: str | None,
superseding_pr_merged: bool,
superseding_merge_commit_sha: str | None,
superseding_head_sha: str | None,
target_branch: str | None,
target_branch_sha: str | None,
superseding_head_is_ancestor_of_target: bool | None,
canonical_comment_valid: bool,
canonical_comment_mentions_superseding_pr: bool,
canonical_comment_mentions_merge_commit: bool,
close_pr_capability: bool,
close_issue_capability: bool = False,
target_issue_state: str | None = None,
issue_satisfied_by_superseding: bool = False,
) -> dict:
"""Gate reconciler closure of PRs/issues superseded by a merged PR.
This is stricter than already-landed cleanup: the target PR may be closed
only after a named superseding PR is live-verified merged, its head is on a
freshly fetched target branch, the target PR is proven not independently
required, and a canonical close comment cites the superseding PR and merge
commit.
"""
reasons: list[str] = []
if not isinstance(target_pr_number, int) or target_pr_number <= 0:
reasons.append("target PR number missing or invalid (#525)")
if not isinstance(superseding_pr_number, int) or superseding_pr_number <= 0:
reasons.append("superseding PR number missing or invalid (#525)")
if target_pr_number and superseding_pr_number and (
target_pr_number == superseding_pr_number
):
reasons.append("target PR and superseding PR must differ (#525)")
if (target_pr_state or "").strip().lower() != "open":
reasons.append("target PR must be live-verified open before close (#525)")
if target_pr_mergeable is True:
reasons.append(
"target PR is still mergeable; prove it is superseded before close (#525)"
)
if target_independently_required is not False:
reasons.append(
"target PR independent-work proof missing; close requires explicit "
"proof that no required work remains (#525)"
)
if (superseding_pr_state or "").strip().lower() != "closed":
reasons.append("superseding PR must be live-verified closed (#525)")
if superseding_pr_merged is not True:
reasons.append("superseding PR must be live-verified merged (#525)")
if not _FULL_SHA.match((superseding_merge_commit_sha or "").strip()):
reasons.append("superseding merge commit SHA missing or invalid (#525)")
if not _FULL_SHA.match((superseding_head_sha or "").strip()):
reasons.append("superseding head SHA missing or invalid (#525)")
if not (target_branch or "").strip():
reasons.append("target branch missing (#525)")
if not _FULL_SHA.match((target_branch_sha or "").strip()):
reasons.append("target branch SHA missing or invalid (#525)")
if superseding_head_is_ancestor_of_target is None:
reasons.append("superseding ancestry proof not checked (#525)")
if not canonical_comment_valid:
reasons.append("canonical close comment failed validation (#525)")
if not canonical_comment_mentions_superseding_pr:
reasons.append("canonical comment must cite superseding PR (#525)")
if not canonical_comment_mentions_merge_commit:
reasons.append("canonical comment must cite merge commit SHA (#525)")
never_allowed = {
"review_allowed": False,
"approve_allowed": False,
"request_changes_allowed": False,
"merge_allowed": False,
}
if reasons:
return {
"outcome": "GATE_NOT_PROVEN",
"pr_close_allowed": False,
"issue_close_allowed": False,
"reasons": reasons,
"required_report_fields": RECONCILER_SUPERSESSION_REPORT_FIELDS,
"safe_next_action": (
"prove superseding PR state, target branch ancestry, target "
"supersession, and canonical comment before closing"
),
**never_allowed,
}
if superseding_head_is_ancestor_of_target is False:
return {
"outcome": "SUPERSEDING_PR_NOT_ON_TARGET",
"pr_close_allowed": False,
"issue_close_allowed": False,
"reasons": [
f"superseding PR #{superseding_pr_number} head is not an "
f"ancestor of {target_branch}; supersession close denied (#525)"
],
"required_report_fields": RECONCILER_SUPERSESSION_REPORT_FIELDS,
"safe_next_action": "re-fetch target branch and re-check ancestry",
**never_allowed,
}
if close_pr_capability is not True:
return {
"outcome": "RECOVERY_HANDOFF_REQUIRED",
"pr_close_allowed": False,
"issue_close_allowed": False,
"reasons": [
"exact gitea.pr.close capability not proven; produce a "
"recovery handoff instead of closing (#525)"
],
"required_report_fields": RECONCILER_SUPERSESSION_REPORT_FIELDS,
"safe_next_action": (
"launch a reconciler profile with gitea.pr.close and replay "
"the live-state proof"
),
**never_allowed,
}
issue_close_allowed = (
(target_issue_state or "").strip().lower() == "open"
and issue_satisfied_by_superseding is True
and close_issue_capability is True
)
issue_reasons = []
if (target_issue_state or "").strip().lower() == "closed":
issue_reasons.append("linked issue already closed; no issue close attempted (#525)")
elif target_issue_state and not issue_close_allowed:
issue_reasons.append(
"issue close requires an open issue satisfied by the superseding "
"merged PR and exact gitea.issue.close capability (#525)"
)
return {
"outcome": "SUPERSESSION_CLOSE_ALLOWED",
"pr_close_allowed": True,
"issue_close_allowed": issue_close_allowed,
"reasons": issue_reasons,
"required_report_fields": RECONCILER_SUPERSESSION_REPORT_FIELDS,
"safe_next_action": (
"post the canonical comment, close the superseded PR, and close "
"the linked issue only when issue_close_allowed is true"
),
**never_allowed,
}
# ---------------------------------------------------------------------------
# Identity disclosure (#305)
# ---------------------------------------------------------------------------
+1 -852
View File
@@ -522,855 +522,4 @@ def assess_lease_inventory(
"active_review_leases": active,
"stale_review_leases": stale,
"reclaimable_review_leases": reclaimable,
}
# Canonical next-action vocabulary for reviewer lease handoff (#599, #691).
NEXT_ACTION_ACQUIRE = "acquire"
NEXT_ACTION_WAIT = "wait"
NEXT_ACTION_RESUME_EXACT_OWNER_SESSION = "resume_exact_owner_session"
NEXT_ACTION_RELEASE_EXPIRED_LEASE = "release_expired_lease"
NEXT_ACTION_OPERATOR_AUTHORIZED_CLEANUP = "operator_authorized_cleanup"
NEXT_ACTION_REPAIR_WORKTREE_BINDING = "repair_worktree_binding"
NEXT_ACTION_CLEANUP_OBSOLETE_LEASE = "cleanup_obsolete_reviewer_comment_lease"
CLEANUP_OBSOLETE_LEASE_TOOL = "gitea_cleanup_obsolete_reviewer_comment_lease"
CLEANUP_OBSOLETE_LEASE_CONFIRMATION_PREFIX = "CLEANUP OBSOLETE REVIEWER LEASE "
# Formal terminal review verdicts that complete a leased-head workflow (#691).
_TERMINAL_REVIEW_VERDICTS = frozenset({
"APPROVED",
"REQUEST_CHANGES",
"approved",
"request_changes",
"REQUESTCHANGES",
})
_HANDOFF_CLASSIFICATIONS = frozenset({
"no_lease",
"own_active",
"own_expired",
"foreign_active",
"foreign_reclaimable",
"foreign_expired",
"foreign_active_current_head",
"foreign_expired_current_head",
"foreign_completed_superseded_head",
"foreign_expired_superseded_head",
"orphaned_owner_missing",
"ambiguous_conflicting_evidence",
"instructed_lease_missing_with_replacement",
"worktree_binding_mismatch",
})
def _norm_path(value: str | None) -> str:
text = (value or "").strip()
if not text:
return ""
return os.path.normpath(text.rstrip("/"))
def _normalize_verdict(value: str | None) -> str:
text = (value or "").strip().upper().replace("-", "_").replace(" ", "_")
if text in {"REQUESTCHANGES", "REQUEST_CHANGES", "CHANGES_REQUESTED"}:
return "REQUEST_CHANGES"
if text in {"APPROVED", "APPROVE"}:
return "APPROVED"
return text
def formal_terminal_review_for_head(
formal_reviews: list[dict] | None,
*,
leased_head: str | None,
) -> dict[str, Any] | None:
"""Return the latest undismissed terminal formal review for *leased_head*."""
head = _normalize_sha(leased_head)
if not head:
return None
matches: list[dict[str, Any]] = []
for review in formal_reviews or []:
if review.get("dismissed"):
continue
verdict = _normalize_verdict(
review.get("verdict") or review.get("state") or review.get("body_state")
)
if verdict not in {"APPROVED", "REQUEST_CHANGES"}:
continue
rhead = _normalize_sha(
review.get("reviewed_head_sha")
or review.get("commit_id")
or review.get("head_sha")
)
if rhead != head:
continue
matches.append({**review, "verdict": verdict, "reviewed_head_sha": rhead})
if not matches:
return None
return matches[-1]
def find_newest_nonterminal_lease(
comments: list[dict],
*,
pr_number: int,
now: datetime | None = None,
include_expired: bool = True,
) -> dict[str, Any] | None:
"""Newest non-terminal lease marker, optionally including expired ones (#691).
Unlike ``find_active_reviewer_lease``, this retains expired non-terminal
markers so diagnosis/cleanup can still name the obsolete lease after
``expires_at`` (comment-backed ledger; no control-plane ``lease_id``).
"""
now = now or datetime.now(timezone.utc)
entries = list(reversed(_lease_entries(comments, pr_number=pr_number)))
for entry in entries:
phase = (entry.get("phase") or "").strip().lower()
if phase in _TERMINAL_PHASES:
# Newest terminal ends the ledger chain for active acquisition, but
# an older non-terminal is not "active". Stop at newest marker.
return None
expired = _lease_expired(entry, now=now)
if expired and not include_expired:
return None
lease = dict(entry)
lease["freshness"] = classify_lease_freshness(lease, now=now)
lease["expired"] = expired
return lease
return None
def cleanup_confirmation_for_pr(pr_number: int) -> str:
return f"{CLEANUP_OBSOLETE_LEASE_CONFIRMATION_PREFIX}{int(pr_number)}"
def assess_obsolete_reviewer_comment_lease_cleanup(
comments: list[dict],
*,
pr_number: int,
current_head_sha: str | None,
formal_reviews: list[dict] | None = None,
repo: str | None = None,
expected_repo: str | None = None,
requesting_session_id: str | None = None,
controller_recovery_authorized: bool = False,
worktree_exists: bool | None = None,
worktree_clean: bool | None = None,
worktree_has_unpreserved_work: bool | None = None,
owner_process_alive: bool | None = None,
owner_pid_observed: int | None = None,
requesting_pid: int | None = None,
current_head_review_in_progress: bool = False,
expected_lease_comment_id: int | None = None,
expected_session_id: str | None = None,
expected_leased_head: str | None = None,
confirmation: str | None = None,
apply: bool = False,
now: datetime | None = None,
) -> dict[str, Any]:
"""Guarded cleanup eligibility for obsolete comment-backed reviewer leases (#691).
Cleanup is never transfer/adoption/repoint and never uses PID equality as
ownership. Eligible only when evidence proves the lease is past expiry and/or
pinned to a superseded head with a completed formal terminal review, and
every safety boundary holds.
"""
now = now or datetime.now(timezone.utc)
reasons: list[str] = []
fail_closed_reasons: list[str] = []
current_head = _normalize_sha(current_head_sha)
req_session = (requesting_session_id or "").strip()
lease = find_newest_nonterminal_lease(
comments, pr_number=pr_number, now=now, include_expired=True
)
if not lease:
# Fall back to active finder (unexpired only) for report consistency.
lease = find_active_reviewer_lease(comments, pr_number=pr_number, now=now)
classification = "no_lease"
cleanup_allowed = False
release_body: str | None = None
audit_comment_body: str | None = None
terminal_review = None
leased_head = None
head_superseded = False
past_expiry = False
expires_parseable = True
if not lease:
fail_closed_reasons.append(
f"PR #{pr_number}: no non-terminal comment-backed reviewer lease to clean"
)
classification = "no_lease"
else:
leased_head = _normalize_sha(lease.get("candidate_head"))
expires_raw = lease.get("expires_at")
expires_at = _parse_timestamp(expires_raw)
if expires_raw and expires_at is None:
expires_parseable = False
fail_closed_reasons.append(
"lease expires_at cannot be parsed or trusted (fail closed)"
)
past_expiry = bool(expires_at and expires_at <= now)
freshness = lease.get("freshness") or classify_lease_freshness(lease, now=now)
owner_session = (lease.get("session_id") or "").strip()
is_requesting_owner = bool(
req_session and owner_session and req_session == owner_session
)
# Identity pins (repo / PR / session / head / comment) must match when
# the caller supplies expected evidence.
lease_repo = (lease.get("repo") or "").strip()
exp_repo = (expected_repo or repo or "").strip()
if exp_repo and lease_repo and exp_repo != lease_repo:
fail_closed_reasons.append(
f"repository identity mismatch: lease repo={lease_repo!r} "
f"expected={exp_repo!r}"
)
if lease.get("pr_number") not in (None, pr_number):
fail_closed_reasons.append(
f"PR identity mismatch: lease pr={lease.get('pr_number')} "
f"requested={pr_number}"
)
if expected_lease_comment_id is not None:
cid = lease.get("comment_id")
if cid is None or int(cid) != int(expected_lease_comment_id):
fail_closed_reasons.append(
"lease comment_id does not match expected evidence "
f"(lease={cid}, expected={expected_lease_comment_id})"
)
if expected_session_id:
if owner_session != expected_session_id.strip():
fail_closed_reasons.append(
"lease session_id does not match expected evidence "
f"(lease={owner_session}, expected={expected_session_id})"
)
if expected_leased_head:
exp_head = _normalize_sha(expected_leased_head)
if not exp_head or exp_head != leased_head:
fail_closed_reasons.append(
"leased head does not match expected evidence "
f"(lease={leased_head}, expected={exp_head})"
)
# PID equality is never ownership proof (#691).
if (
owner_pid_observed is not None
and requesting_pid is not None
and int(owner_pid_observed) == int(requesting_pid)
):
reasons.append(
"observed PID equals requesting PID but PID equality is NOT "
"ownership proof; ignored for authorization"
)
if is_requesting_owner:
fail_closed_reasons.append(
"requesting session owns the lease; use "
"gitea_release_reviewer_pr_lease (owner path), not non-owner cleanup"
)
if current_head_review_in_progress:
fail_closed_reasons.append(
"a current-head review submission is in progress; cleanup denied"
)
if not current_head:
fail_closed_reasons.append(
"current PR head SHA missing or unparseable (fail closed)"
)
if not leased_head:
fail_closed_reasons.append(
"lease candidate_head missing or unparseable (fail closed)"
)
head_superseded = bool(
current_head and leased_head and current_head != leased_head
)
head_matches_current = bool(
current_head and leased_head and current_head == leased_head
)
terminal_review = formal_terminal_review_for_head(
formal_reviews, leased_head=leased_head
)
has_terminal = terminal_review is not None
# Worktree safety.
if worktree_has_unpreserved_work is True or worktree_clean is False:
fail_closed_reasons.append(
"lease worktree is dirty or has unpreserved work; cleanup denied"
)
if (
worktree_exists is True
and worktree_clean is None
and worktree_has_unpreserved_work is None
):
# Unknown cleanliness when path exists — fail closed.
fail_closed_reasons.append(
"lease worktree exists but cleanliness is unknown (fail closed)"
)
# Classification matrix (#691).
if head_matches_current and freshness in {"active", "stale_warning"}:
classification = "foreign_active_current_head"
fail_closed_reasons.append(
"genuinely active foreign lease on the current PR head; "
"cleanup denied (fail closed)"
)
elif head_matches_current and past_expiry:
classification = "foreign_expired_current_head"
# Expired on current head: owner-missing / orphan path may apply.
if owner_process_alive is True:
fail_closed_reasons.append(
"lease expired on current head but owner process still alive "
"with plausible activity; cleanup denied"
)
elif worktree_clean is False:
fail_closed_reasons.append(
"owner process absent but worktree dirty; cleanup denied"
)
elif owner_process_alive is False and (
worktree_clean is True or worktree_exists is False
):
if controller_recovery_authorized:
classification = "orphaned_owner_missing"
else:
fail_closed_reasons.append(
"controller/recovery capability not authorized for orphan cleanup"
)
else:
fail_closed_reasons.append(
"insufficient orphan evidence for expired current-head lease "
"(need owner_process_alive=false and clean/absent worktree)"
)
elif head_superseded and has_terminal and past_expiry:
classification = "foreign_expired_superseded_head"
elif head_superseded and has_terminal and not past_expiry:
classification = "foreign_completed_superseded_head"
elif head_superseded and not has_terminal:
classification = "ambiguous_conflicting_evidence"
fail_closed_reasons.append(
"lease head is superseded but no formal terminal review exists "
"for the leased head (fail closed)"
)
elif not head_superseded and not past_expiry and freshness in {
"active", "stale_warning"
}:
classification = "foreign_active_current_head"
fail_closed_reasons.append(
"foreign lease still active on current head; wait or use owner release"
)
elif past_expiry and not head_superseded:
classification = "foreign_expired_current_head"
else:
classification = "ambiguous_conflicting_evidence"
fail_closed_reasons.append(
"lease evidence is ambiguous; cleanup denied (fail closed)"
)
# Recent owner progress on a non-superseded active lease blocks cleanup.
minutes = _minutes_since_activity(lease, now=now)
if (
head_matches_current
and freshness == "active"
and minutes is not None
and minutes < STALE_WARNING_MINUTES
):
fail_closed_reasons.append(
"owner session has recent authenticated progress on current head; "
"cleanup denied"
)
# Authority + confirmation for apply.
if not controller_recovery_authorized:
if classification in {
"foreign_completed_superseded_head",
"foreign_expired_superseded_head",
"foreign_expired_current_head",
"orphaned_owner_missing",
}:
fail_closed_reasons.append(
"controller/recovery capability required "
"(controller_recovery_authorized=true)"
)
expected_conf = cleanup_confirmation_for_pr(pr_number)
if apply:
if (confirmation or "").strip() != expected_conf:
fail_closed_reasons.append(
f"confirmation must equal exactly {expected_conf!r}"
)
# Superseded + terminal path does not require past_expiry (AC1).
eligible_class = classification in {
"foreign_completed_superseded_head",
"foreign_expired_superseded_head",
"orphaned_owner_missing",
"foreign_expired_current_head",
}
# foreign_expired_current_head needs orphan/clean worktree + authority.
if classification == "foreign_expired_current_head":
if worktree_clean is not True and worktree_exists is not False:
if "worktree" not in " ".join(fail_closed_reasons):
fail_closed_reasons.append(
"expired current-head cleanup requires proven-clean "
"worktree or absent worktree"
)
if owner_process_alive is True:
fail_closed_reasons.append(
"owner process still alive on expired current-head lease"
)
cleanup_allowed = (
eligible_class
and expires_parseable
and not fail_closed_reasons
and not is_requesting_owner
)
if cleanup_allowed:
release_body = format_lease_body(
repo=lease.get("repo") or exp_repo or "",
pr_number=pr_number,
issue_number=lease.get("issue_number"),
reviewer_identity=lease.get("reviewer_identity") or "",
profile=lease.get("profile") or "unknown",
session_id=owner_session or "unknown",
worktree=lease.get("worktree") or "",
phase="released",
candidate_head=leased_head,
target_branch=lease.get("target_branch") or "master",
target_branch_sha=lease.get("target_branch_sha"),
last_activity=now,
blocker="obsolete-superseded-or-expired-lease",
)
audit_comment_body = (
"## Canonical obsolete reviewer lease cleanup (#691)\n\n"
f"- pr: #{pr_number}\n"
f"- lease_comment_id: {lease.get('comment_id')}\n"
f"- session_id: {owner_session}\n"
f"- leased_head: {leased_head}\n"
f"- current_head: {current_head}\n"
f"- expires_at: {lease.get('expires_at')}\n"
f"- classification: {classification}\n"
f"- terminal_review_verdict: "
f"{(terminal_review or {}).get('verdict')}\n"
f"- tool: {CLEANUP_OBSOLETE_LEASE_TOOL}\n"
"- action: posted terminal phase=released lease marker; "
"did not transfer validation, decision, or workflow proof; "
"did not repoint lease to the new head; did not delete history\n"
)
reasons.append(
f"cleanup eligible ({classification}); post terminal released "
"marker via sanctioned tool"
)
else:
reasons.extend(fail_closed_reasons)
return {
"pr_number": pr_number,
"classification": classification,
"blocker_kind": classification if not cleanup_allowed else "none",
"cleanup_allowed": cleanup_allowed,
"mutation_allowed": False, # never grants review mutation
"mutation_eligibility": "prohibited" if not cleanup_allowed else "cleanup_only",
"exact_next_action": (
NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
if cleanup_allowed
else (
NEXT_ACTION_WAIT
if classification
in {
"foreign_active_current_head",
"ambiguous_conflicting_evidence",
}
else NEXT_ACTION_OPERATOR_AUTHORIZED_CLEANUP
)
),
"cleanup_tool": CLEANUP_OBSOLETE_LEASE_TOOL,
"required_confirmation": cleanup_confirmation_for_pr(pr_number),
"leased_head": leased_head,
"current_head": current_head,
"head_superseded": head_superseded,
"past_expiry": past_expiry,
"expires_at": (lease or {}).get("expires_at") if lease else None,
"expires_parseable": expires_parseable,
"terminal_review": terminal_review,
"terminal_review_present": terminal_review is not None,
"worktree_state": {
"path": (lease or {}).get("worktree") if lease else None,
"exists": worktree_exists,
"clean": worktree_clean,
"has_unpreserved_work": worktree_has_unpreserved_work,
},
"owner_session_evidence": {
"session_id": (lease or {}).get("session_id") if lease else None,
"reviewer_identity": (
(lease or {}).get("reviewer_identity") if lease else None
),
"process_alive": owner_process_alive,
"pid_observed": owner_pid_observed,
"pid_is_not_ownership_proof": True,
"requesting_session_is_owner": bool(
lease
and req_session
and (lease.get("session_id") or "").strip() == req_session
),
},
"active_lease": lease,
"release_body": release_body,
"audit_comment_body": audit_comment_body,
"controller_recovery_authorized": controller_recovery_authorized,
"reasons": reasons if reasons else fail_closed_reasons,
"fail_closed_reasons": fail_closed_reasons,
"forbidden": [
"manual comment deletion",
"database edits",
"mtime manipulation",
"PID-based ownership",
"direct session-state seeding",
"lease stealing or adoption",
"repointing old lease to new head",
"transfer of validation or decision state",
"worktree reuse by replacement reviewer",
],
}
def diagnose_reviewer_pr_lease_handoff(
comments: list[dict],
*,
pr_number: int,
current_session_id: str | None,
current_reviewer_identity: str | None,
proposed_worktree: str | None = None,
env_bound_worktree: str | None = None,
instructed_session_id: str | None = None,
instructed_comment_id: int | None = None,
current_head_sha: str | None = None,
formal_reviews: list[dict] | None = None,
worktree_exists: bool | None = None,
worktree_clean: bool | None = None,
owner_process_alive: bool | None = None,
now: datetime | None = None,
) -> dict[str, Any]:
"""Classify open-PR reviewer lease handoff and emit a canonical next action (#599, #691).
Read-only diagnosis. Never steals, releases, or adopts a foreign lease.
Fail-closed acquisition rules for active foreign leases remain intact.
Returns a structured diagnosis with:
- classification (including #691 superseded/expired distinctions)
- next_action (including cleanup_obsolete_reviewer_comment_lease)
- active_lease identity fields when present
- worktree_binding match result
- instructed-lease mismatch flags
- cleanup tool/confirmation when cleanup-eligible
"""
now = now or datetime.now(timezone.utc)
session_id = (current_session_id or "").strip()
identity = (current_reviewer_identity or "").strip()
instructed_sid = (instructed_session_id or "").strip()
reasons: list[str] = []
current_head = _normalize_sha(current_head_sha)
active = find_active_reviewer_lease(comments, pr_number=pr_number, now=now)
# Also surface expired non-terminal newest marker for #691 diagnosis.
newest_nt = find_newest_nonterminal_lease(
comments, pr_number=pr_number, now=now, include_expired=True
)
lease_for_class = active or newest_nt
session_lease = get_session_lease()
# Worktree binding: env-bound vs proposed vs active lease worktree.
env_wt = _norm_path(env_bound_worktree)
prop_wt = _norm_path(proposed_worktree)
lease_wt = _norm_path((lease_for_class or {}).get("worktree") if lease_for_class else None)
binding_mismatch = False
binding_details: dict[str, Any] = {
"env_bound_worktree": env_bound_worktree or None,
"proposed_worktree": proposed_worktree or None,
"lease_worktree": (lease_for_class or {}).get("worktree") if lease_for_class else None,
"match": True,
}
paths = [p for p in (env_wt, prop_wt, lease_wt) if p]
if len(paths) >= 2 and len(set(paths)) > 1:
binding_mismatch = True
binding_details["match"] = False
reasons.append(
"worktree binding mismatch: env/proposed/lease worktree paths disagree"
)
# Instructed lease gone while a different lease is active (PR #592-style).
instructed_missing_with_replacement = False
if instructed_sid or instructed_comment_id is not None:
if not lease_for_class:
reasons.append(
"instructed lease is gone and no active replacement lease remains"
)
else:
owner = (lease_for_class.get("session_id") or "").strip()
cid = lease_for_class.get("comment_id")
sid_mismatch = bool(instructed_sid and owner and owner != instructed_sid)
cid_mismatch = (
instructed_comment_id is not None
and cid is not None
and int(cid) != int(instructed_comment_id)
)
if sid_mismatch or cid_mismatch:
instructed_missing_with_replacement = True
reasons.append(
"instructed lease is gone; a different active lease replaced it "
f"(active session_id={owner}, comment_id={cid})"
)
# Classification + next_action.
classification = "no_lease"
next_action = NEXT_ACTION_ACQUIRE
cleanup_hint: dict[str, Any] | None = None
if lease_for_class:
owner = (lease_for_class.get("session_id") or "").strip()
freshness = lease_for_class.get("freshness") or classify_lease_freshness(
lease_for_class, now=now
)
owner_identity = (lease_for_class.get("reviewer_identity") or "").strip()
is_own = bool(session_id and owner and owner == session_id)
# Same identity alone is NOT ownership for resume; session_id must match.
same_identity = bool(
identity and owner_identity and identity == owner_identity
)
leased_head = _normalize_sha(lease_for_class.get("candidate_head"))
head_superseded = bool(
current_head and leased_head and current_head != leased_head
)
head_current = bool(
current_head and leased_head and current_head == leased_head
)
past_expiry = bool(lease_for_class.get("expired")) or freshness == "expired"
if not past_expiry:
past_expiry = _lease_expired(lease_for_class, now=now)
terminal = formal_terminal_review_for_head(
formal_reviews, leased_head=leased_head
)
if is_own and freshness in {"active", "stale_warning"} and not past_expiry:
classification = "own_active"
next_action = NEXT_ACTION_RESUME_EXACT_OWNER_SESSION
elif is_own and (freshness in {"reclaimable", "expired"} or past_expiry):
classification = "own_expired"
next_action = NEXT_ACTION_RELEASE_EXPIRED_LEASE
reasons.append(
f"own lease freshness is '{freshness}'; release via "
"gitea_release_reviewer_pr_lease then re-acquire"
)
elif not is_own and head_superseded and terminal and past_expiry:
classification = "foreign_expired_superseded_head"
next_action = NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
reasons.append(
"foreign lease expired and pinned to superseded head with "
"formal terminal review; use guarded obsolete-lease cleanup"
)
elif not is_own and head_superseded and terminal and not past_expiry:
classification = "foreign_completed_superseded_head"
next_action = NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
reasons.append(
"foreign lease pinned to superseded head with completed formal "
"review; use guarded obsolete-lease cleanup (do not wait indefinitely)"
)
elif not is_own and head_superseded and not terminal:
classification = "ambiguous_conflicting_evidence"
next_action = NEXT_ACTION_WAIT
reasons.append(
"lease head superseded but no formal terminal review for leased "
"head; fail closed / wait (no indefinite steal)"
)
elif not is_own and head_current and past_expiry:
classification = "foreign_expired_current_head"
if owner_process_alive is False and worktree_clean is True:
classification = "orphaned_owner_missing"
next_action = NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
reasons.append(
"foreign expired lease on current head; owner process absent "
"and worktree clean — guarded orphan cleanup eligible"
)
elif owner_process_alive is False and worktree_clean is False:
classification = "ambiguous_conflicting_evidence"
next_action = NEXT_ACTION_WAIT
reasons.append(
"owner process absent but worktree dirty; cleanup denied"
)
else:
next_action = NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
reasons.append(
"foreign expired lease on current head; use guarded cleanup "
"when worktree/process evidence permits"
)
elif not is_own and freshness in {"active", "stale_warning"} and not past_expiry:
classification = (
"foreign_active_current_head" if head_current or not current_head
else "foreign_active"
)
next_action = NEXT_ACTION_WAIT
reasons.append(
f"foreign active reviewer lease (session_id={owner}, "
f"phase={lease_for_class.get('phase')}, freshness={freshness}); "
"do not submit; do not steal"
)
if same_identity:
reasons.append(
"lease identity matches current reviewer but session_id differs; "
"resume only from the exact owner session_id or wait"
)
elif not is_own and freshness == "reclaimable":
classification = "foreign_reclaimable"
next_action = NEXT_ACTION_RELEASE_EXPIRED_LEASE
reasons.append(
f"foreign reclaimable lease (session_id={owner}); clear only via "
"sanctioned gitea_release_reviewer_pr_lease when reclaimable"
)
elif not is_own and (freshness == "expired" or past_expiry):
classification = "foreign_expired"
next_action = NEXT_ACTION_RELEASE_EXPIRED_LEASE
reasons.append(
f"foreign expired lease (session_id={owner}); use sanctioned release "
f"or {CLEANUP_OBSOLETE_LEASE_TOOL}"
)
else:
classification = "foreign_active"
next_action = NEXT_ACTION_WAIT
reasons.append(
f"unclassified active lease state (session_id={owner}, "
f"freshness={freshness}); wait fail-closed"
)
if instructed_missing_with_replacement and classification.startswith(
"foreign"
):
# Preserve #691 cleanup path when superseded/expired; otherwise
# keep the PR #592 instructed-missing label.
if next_action != NEXT_ACTION_CLEANUP_OBSOLETE_LEASE:
classification = "instructed_lease_missing_with_replacement"
if next_action == NEXT_ACTION_WAIT:
reasons.append(
"replacement foreign lease is active — wait; "
"operator_authorized_cleanup only with explicit operator authority"
)
if next_action == NEXT_ACTION_CLEANUP_OBSOLETE_LEASE:
cleanup_hint = {
"cleanup_tool": CLEANUP_OBSOLETE_LEASE_TOOL,
"required_confirmation": cleanup_confirmation_for_pr(pr_number),
"controller_recovery_authorized_required": True,
"leased_head": leased_head,
"current_head": current_head,
"expires_at": lease_for_class.get("expires_at"),
"terminal_review_verdict": (terminal or {}).get("verdict"),
}
else:
classification = "no_lease"
next_action = NEXT_ACTION_ACQUIRE
reasons.append("no active reviewer lease; acquire via gitea_acquire_reviewer_pr_lease")
# Binding mismatch is a first-class blocker before submit, but does not
# erase foreign-lease wait/release guidance. Override next_action only when
# the session would otherwise be free to acquire or resume (submit path).
if binding_mismatch:
if next_action in {
NEXT_ACTION_ACQUIRE,
NEXT_ACTION_RESUME_EXACT_OWNER_SESSION,
}:
classification = "worktree_binding_mismatch"
next_action = NEXT_ACTION_REPAIR_WORKTREE_BINDING
else:
reasons.append(
"also repair worktree binding before submit "
f"(next_action remains {next_action})"
)
lease_summary = None
if lease_for_class:
lease_summary = {
"comment_id": lease_for_class.get("comment_id"),
"session_id": lease_for_class.get("session_id"),
"phase": lease_for_class.get("phase"),
"candidate_head": lease_for_class.get("candidate_head"),
"expires_at": lease_for_class.get("expires_at"),
"last_activity": lease_for_class.get("last_activity"),
"freshness": lease_for_class.get("freshness")
or classify_lease_freshness(lease_for_class, now=now),
"reviewer_identity": lease_for_class.get("reviewer_identity"),
"profile": lease_for_class.get("profile"),
"worktree": lease_for_class.get("worktree"),
"blocker": lease_for_class.get("blocker"),
}
return {
"pr_number": pr_number,
"classification": classification,
"blocker_kind": classification,
"next_action": next_action,
"exact_next_action": next_action,
"active_lease": lease_summary,
"session_lease": session_lease,
"worktree_binding": binding_details,
"leased_head": (lease_summary or {}).get("candidate_head"),
"current_head": current_head,
"expires_at": (lease_summary or {}).get("expires_at"),
"terminal_review_state": (
formal_terminal_review_for_head(
formal_reviews,
leased_head=(lease_summary or {}).get("candidate_head"),
)
if lease_summary
else None
),
"worktree_state": {
"exists": worktree_exists,
"clean": worktree_clean,
"path": (lease_summary or {}).get("worktree"),
},
"owner_session_evidence": {
"session_id": (lease_summary or {}).get("session_id"),
"process_alive": owner_process_alive,
"pid_is_not_ownership_proof": True,
},
"cleanup": cleanup_hint,
"cleanup_tool": (cleanup_hint or {}).get("cleanup_tool"),
"required_confirmation": (cleanup_hint or {}).get("required_confirmation"),
"instructed_session_id": instructed_session_id,
"instructed_comment_id": instructed_comment_id,
"instructed_lease_missing_with_replacement": instructed_missing_with_replacement,
"mutation_allowed": (
next_action == NEXT_ACTION_RESUME_EXACT_OWNER_SESSION
and not binding_mismatch
and bool(session_lease)
),
"mutation_eligibility": (
"allowed"
if (
next_action == NEXT_ACTION_RESUME_EXACT_OWNER_SESSION
and not binding_mismatch
and bool(session_lease)
)
else (
"cleanup_only"
if next_action == NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
else "prohibited"
)
),
"reasons": reasons,
"forbidden": [
"manual lock deletion",
"raw API bypass",
"mtime manipulation",
"direct _SESSION_LEASE seeding",
"silent foreign lease steal",
"PID-based ownership",
"repointing old lease to new head",
"transfer of validation or decision state",
],
}
}
-14
View File
@@ -27,20 +27,6 @@ _READONLY_REVIEWER_GIT = re.compile(
_GIT_INVOCATION = re.compile(r"\bgit\b", re.IGNORECASE)
# #673: Canonical pattern for identifying review worktrees under branches/.
REVIEW_WORKTREE_RE = re.compile(
r"branches/(?:review-pr\d+[\w/-]*|merge-simulation-pr\d+|review-[\w-]+)",
re.IGNORECASE,
)
def is_review_worktree_path(path: str) -> bool:
"""True when the path belongs to a reviewer or simulation worktree."""
normalized = (path or "").replace("\\", "/")
return bool(REVIEW_WORKTREE_RE.search(normalized))
def parse_dirty_tracked_files(porcelain: str) -> list[str]:
"""Return tracked paths with local modifications from ``git status --porcelain``.
+4 -3
View File
@@ -5,9 +5,10 @@ from __future__ import annotations
import re
from typing import Any
from reviewer_worktree import REVIEW_WORKTREE_RE
_SESSION_OWNED_RE = REVIEW_WORKTREE_RE
_SESSION_OWNED_RE = re.compile(
r"branches/(?:review-pr\d+[\w/-]*|review-[\w-]+)",
re.IGNORECASE,
)
_WORKTREE_PATH_RE = re.compile(
r"(?:review worktree path|worktree path|session-owned worktree)\s*:\s*(\S+)",
re.IGNORECASE,
+2 -31
View File
@@ -55,6 +55,7 @@ def skip_python_scan_walk_root(project_root: str, walk_root: str) -> bool:
REVIEWER_TASKS = frozenset({
"review_pr",
"merge_pr",
"blind_pr_queue_review",
"pr_queue_cleanup",
"pr-queue-cleanup",
@@ -62,10 +63,6 @@ REVIEWER_TASKS = frozenset({
"approve_pr",
})
MERGER_TASKS = frozenset({
"merge_pr",
})
AUTHOR_TASKS = frozenset({
"create_issue",
"comment_issue",
@@ -101,7 +98,7 @@ TASK_REQUIRED_ROLE = {
"address_pr_change_requests": "author",
"delete_branch": "author",
"review_pr": "reviewer",
"merge_pr": "merger",
"merge_pr": "reviewer",
"blind_pr_queue_review": "reviewer",
"pr_queue_cleanup": "reviewer",
"pr-queue-cleanup": "reviewer",
@@ -117,9 +114,6 @@ TASK_REQUIRED_ROLE = {
# #309: reconciler tasks close already-landed PRs/issues only.
"reconcile_close_landed_pr": "reconciler",
"reconcile_close_landed_issue": "reconciler",
"reconcile_close_superseded_pr": "reconciler",
"reconcile_close_satisfied_issue": "reconciler",
"reconcile_create_followup_issue": "reconciler",
}
WRONG_ROLE_REVIEWER_MSG = (
@@ -131,10 +125,6 @@ WRONG_ROLE_RECONCILER_MSG = (
"MCP namespace/profile with exact close capability."
)
WRONG_ROLE_MERGER_MSG = (
"Wrong role/session for merger task. Launch merger MCP namespace."
)
_session_last_route: dict | None = None
@@ -250,25 +240,6 @@ def route_task_session(
_record_route(result)
return result
if required_role == "merger":
result = {
"task_type": task_type,
"required_role": required_role,
"active_role": active_role_kind,
"active_profile": active_profile,
"route_result": ROUTE_WRONG_ROLE,
"downstream_allowed": False,
"reasons": [
WRONG_ROLE_MERGER_MSG,
"Merger tasks cannot run in author or reviewer sessions.",
],
"message": WRONG_ROLE_MERGER_MSG,
"runtime_switching_supported": runtime_switching_supported,
"profile_switch_blocked": not runtime_switching_supported,
}
_record_route(result)
return result
if required_role == "author":
route = ROUTE_TO_AUTHOR
message = (
-50
View File
@@ -32,15 +32,6 @@ workflow file.
mutation.
- A nearby capability does not count.
- Do not self-review or self-merge.
- **Never push a stable branch directly.** Worker sessions (author/reviewer/merger)
must never run `git push <remote> master` — or `main`/`dev`/other stable refs,
including refspecs (`HEAD:master`), `--force`, `--delete`, or `--dry-run` no-op
probes — and must never commit on the root/control checkout outside an issue
feature branch. Stable-branch updates land ONLY through sanctioned Gitea merge
tooling (`gitea_merge_pr`) or an explicitly authorized reconciler path. A
detected attempt marks the session workflow-contaminated (#671) and fails
closed on review/merge/close/completion until a reconciler audits and clears
it. `git fetch` / `git pull --ff-only` and feature-branch pushes stay allowed.
- Do not mix modes in one run.
- **BLOCKED + DIAGNOSE default rule (required):** If any required workflow step, skill, tool, capability, preflight, instruction, profile, worktree binding, or terminal/MCP operation cannot be performed or loaded (including the canonical ones listed in this skill and its loaded workflow), immediately enter `BLOCKED + DIAGNOSE`. Stop before any git or Gitea mutation. Diagnose using the standard template in [`templates/blocked-diagnose-report.md`](templates/blocked-diagnose-report.md). Attempt *only* safe non-mutating recovery. Report using the template. Do not continue, use fallbacks, or treat the missing requirement as harmless.
- If the required workflow cannot be loaded, stop and produce a recovery handoff
@@ -57,11 +48,6 @@ workflow file.
- wrong profile or role for the requested operation
- dirty or misbound worktree (root checkout or non-branches/ path)
- root checkout mutation risk
- stable-branch push contamination (#671): a direct `git push <remote> master`
(or `main`/`dev`) equivalent, or a root/control-checkout commit not on an issue
feature branch, marks the session workflow-contaminated; review/merge/close/
completion mutations then fail closed until a reconciler audits and clears it
(`gitea_audit_stable_branch_contamination action=clear`, reconciler-only)
- mutation guard failure (e.g. branches-only guard)
- missing required MCP tool/schema or operation
- stale or inconsistent runtime state (e.g. lease vs actual, dirty state disagreement)
@@ -132,42 +118,6 @@ The main project checkout is a stable control checkout on `master`, `main`, or
If `cwd` is not inside `branches/`, stop before any file edit, test write,
commit, merge, rebase, or cleanup. The main checkout is orchestration-only.
## Stable Branch Push Protection (#671)
Worker sessions must **never** publish a stable branch directly. This is the
prevention hardening for the #670 incident (a bare direct-to-master commit
`2fa97c26` and a PR #654 merger `git push prgs master` attempt).
**Forbidden for author/reviewer/merger sessions:**
- `git push <remote> master` (and `main`, `dev`, `develop`, `development`),
including refspecs (`HEAD:master`, `+refs/heads/x:refs/heads/master`),
`--force`, `--delete` / `:master`, and `--dry-run`/`-n` no-op probes (a
dry-run still proves intent and contaminates the session).
- Local commits on the root/control checkout that are not carried by an issue
feature branch under `branches/`.
**Allowed (never blocked):**
- `git fetch` and `git pull --ff-only` of master into the control checkout when
authorized for sync.
- Feature-branch pushes to non-stable refs (`git push <remote> fix/issue-N-...`).
- Sanctioned merges via `gitea_merge_pr` / the Gitea API merge endpoint — the
**only** way stable branches advance.
**What happens on a detected attempt:** the session is marked
workflow-contaminated (durable `stable_branch_contamination` marker, redacted
command summary + session id + remote + ref). While contaminated, all
review / merge / close / issue-completion mutations fail closed. `comment_issue`
and `lock_issue` remain allowed so the contaminated worker can post the durable
audit comment and hand off. Contamination **cannot be self-cleared** — only a
reconciler audit (`gitea_audit_stable_branch_contamination action=clear`) may
clear it.
Tooling: call `gitea_record_stable_branch_push_attempt` to classify/record a
proposed push before running it; `gitea_audit_stable_branch_contamination` to
inspect or (reconciler-only) clear the marker.
## Shell Spawn Hard-Stop Rule
`exit_code: -1` with empty stdout/stderr means the shell failed to spawn — not a
@@ -344,41 +344,6 @@ If edits are needed, make the smallest correction necessary and report the corre
Do not silently change requested meaning.
## 14a. Enforced content preflight (#582)
`gitea_create_issue` runs a **content preflight gate** before duplicate
search or creation. It fails closed (returns `BLOCKED + DIAGNOSE`, no issue
created) when the title/body is a *vague reference* to out-of-band draft
content the session cannot prove it holds, and no durable source pointer is
present.
An LLM must never fabricate issue content from stale chat memory. If asked to
create "the drafted issue" / "the prepared issue" / "the issue we discussed"
/ "the previous draft" without the full content in the current context or a
durable source pointer, stop and return `BLOCKED + DIAGNOSE` naming the exact
vague/missing fields.
A **durable source pointer** is one of: an existing issue/PR reference
(`#582`), a comment id (`comment 8155`), a checked-in file path
(`task_capability_map.py`), a URL, or a scratchpad path. When a pointer is
present, retrieve the real content from it before creating.
The gate does **not** require a non-empty body; explicit title-only creation
stays allowed. It only blocks placeholder references. An operator may bypass
it with `allow_incomplete_content=True` (report the override).
**Invalid prompts (must block):**
* "Create the drafted issue."
* "File the prepared issue we discussed."
* "Open the previous draft."
**Valid prompts (proceed):**
* Full title + body + acceptance criteria supplied inline.
* "Create the issue drafted in `#582`." (durable pointer → fetch and use it)
* "Create the issue from `scratchpad/issue-draft.md`." (durable file pointer)
## 15. Labels, assignees, and metadata
Apply labels, assignees, milestones, or project fields only if:
@@ -826,75 +826,6 @@ The final report must identify:
* whether same-PR merge continuation was allowed
* whether the run stopped as required
## 26A-1. Stale durable review-decision lock cleanup (#594)
After #559, the review-decision lock is durable under
`~/.cache/gitea-tools/session-state/` (for example
`review_decision_lock-prgs-reviewer.json`). That durability can outlive the work
it protects: a terminal `approve` / `request_changes` on a PR that is already
**merged or closed** still hard-stops later unrelated reviews under #332.
**Do not** delete session-state files by hand. Use the canonical MCP path.
### When cleanup is allowed
Use `gitea_cleanup_stale_review_decision_lock` when:
1. `gitea_mark_final_review_decision` / live review is blocked by
`terminal review mutation already consumed ... (#332)`.
2. Live Gitea state for the **last terminal mutation's PR** is **merged** or
**closed** (no same-PR merge sequence remains).
3. Active profile identity matches the durable lock (reviewer profile with
`gitea.pr.review` for `apply=true`).
4. Optional pin: pass `expected_terminal_pr` to the prior terminal PR number
(for example `586` when resuming after a merged #586 lock).
Recommended sequence:
```text
gitea_whoami
gitea_resolve_task_capability(task="cleanup_stale_review_decision_lock")
gitea_cleanup_stale_review_decision_lock(apply=false, remote=..., org=..., repo=...)
# inspect is_moot / cleanup_allowed / last_terminal_pr
gitea_cleanup_stale_review_decision_lock(
apply=true,
expected_terminal_pr=<last_terminal_pr>,
remote=..., org=..., repo=...,
)
gitea_resolve_task_capability(task="review_pr")
gitea_load_review_workflow()
# continue formal mark + submit for the *new* PR
```
Successful `apply=true` clears memory + durable store and returns an audit
record (and posts a durable PR comment on the terminal PR when
`post_audit_comment` is true and comment permission allows).
Same-profile auto-expire: after `gitea_merge_pr` succeeds for the PR that this
profile just approved, the decision lock for that profile is cleared
automatically. Cross-profile locks (for example reviewer approve, merger merge)
still require `gitea_cleanup_stale_review_decision_lock`.
### When cleanup is forbidden
Refuse / fail-closed — keep #332 hard-stop — when:
* the last terminal PR is still **open** (active review or merge sequence may
still apply)
* live PR state cannot be fetched (ambiguous)
* no lock or no terminal live mutation exists
* profile identity does not match the lock
* apply requested without authenticated identity or `gitea.pr.review`
* `expected_terminal_pr` does not match the last terminal PR
Do **not** use cleanup to:
* bypass #332 on an open PR
* replace `gitea_authorize_review_correction` for a mistaken review on a still
active PR (#211)
* auto-approve or auto-merge any PR
* justify `rm` of session-state files
## 26B. Per-PR reviewer lease (#407)
Parallel reviewer sessions are allowed only when each session holds a distinct,
@@ -1112,8 +1043,6 @@ Blocked handoffs must say to rerun the full workflow after the blocker clears.
If the blocker is a terminal review mutation already consumed in the current run, the handoff must say that the next run must start from the beginning and must not reuse stale ready/approved state.
If the referenced terminal PR is already **merged or closed** on live Gitea, the durable #332 decision lock is **moot**. Do **not** delete session-state files by hand. Use `gitea_cleanup_stale_review_decision_lock` (assess with `apply=false`, then `apply=true` with `expected_terminal_pr` set) from the reviewer profile after identity/profile checks (#594). Cleanup is **forbidden** while that PR is still open.
## 30. Final report must be precise
Include:
-478
View File
@@ -1,478 +0,0 @@
"""Fail-closed guard against direct pushes to stable branches (#671).
MCP workflow sessions must never publish to a stable branch (``master``,
``main``, ``dev``, ...) directly. Stable-branch updates land only through
sanctioned Gitea merge tooling or an explicitly authorized reconciler path.
Incident origin (#670): a bare direct-to-master commit ``2fa97c26`` landed on
``prgs/master`` without PR/review provenance, and a PR #654 merger run
attempted ``git push prgs master`` (audited as a no-op, but the *intent* is the
hazard). Partial protections already existed (``author_proofs.PROTECTED_BRANCHES``,
``root_checkout_guard``, branch-push proofs) but did not detect shell push
equivalents, mark the session contaminated after such an attempt, or fail
closed on subsequent review/merge/close/completion mutations.
This module is the detection + contamination-policy core. Like
``author_proofs`` and ``root_checkout_guard`` it is **pure**: callers gather
the raw facts (the proposed command line, git state, the durable contamination
marker) and pass them in, so the same logic serves prompts, MCP gates, and
tests. Nothing here performs git or network calls or reads durable state; the
server wires these helpers to ``mcp_session_state`` and ``verify_preflight_purity``.
Design rules honoured (from the #671 acceptance criteria):
* Detect ``git push <remote> master`` shell equivalents, including refspecs
(``HEAD:master``, ``+refs/heads/x:refs/heads/master``), ``--force``,
``--dry-run``/no-op intent, and delete refspecs (``:master``).
* Never false-block a feature-branch push (``git push prgs fix/issue-671-...``).
* Never treat ``git fetch`` / ``git pull --ff-only`` as a push.
* Never treat sanctioned ``gitea_merge_pr`` / Gitea API merge as a push.
* Fail closed on ambiguous targets that *may* resolve to a stable branch, but
surface ambiguity as its own signal rather than silently blocking feature work.
* Contamination must not be clearable by the same worker session only a
reconciler (audit) role may clear or bypass the gate.
"""
from __future__ import annotations
import re
from typing import Any, Iterable
from author_proofs import PROTECTED_BRANCHES
# Single source of truth for the stable branch set: the same protected set the
# author branch-identity proofs already enforce (#177), so the two guards can
# never drift apart.
STABLE_BRANCHES = PROTECTED_BRANCHES
# Mutations that must fail closed once the session is contaminated by a direct
# stable-branch push attempt (#671 AC4: review, merge, close, completion).
# ``comment_issue`` / ``lock_issue`` / ``create_issue`` are deliberately NOT
# gated so a contaminated worker can still post the durable audit comment and
# hand off. Only a reconciler (audit) role bypasses this set.
CONTAMINATION_GATED_TASKS = frozenset({
"create_pr",
"commit_files",
"gitea_commit_files",
"close_pr",
"close_issue",
"review_pr",
"approve_pr",
"request_changes_pr",
"submit_pr_review",
"merge_pr",
"delete_branch",
"complete_issue",
})
CONTAMINATION_KIND = "stable_branch_push"
REMEDIATION = (
"Direct stable-branch publication is forbidden for worker sessions. Stop, "
"leave the stable branch untouched, and route the change through sanctioned "
"Gitea merge tooling (gitea_merge_pr) or an explicitly authorized reconciler "
"audit. This session is workflow-contaminated until a reconciler audits it."
)
# ── command tokenising ────────────────────────────────────────────────────────
# Split a compound command line into individual simple commands on shell
# separators so ``a && git push prgs master`` is analysed segment by segment.
_SEGMENT_SPLIT_RE = re.compile(r"(?:\|\||&&|\||;|\n)")
_GIT_PUSH_RE = re.compile(r"\bgit\b[\w\s\-]*?\bpush\b", re.IGNORECASE)
_GIT_FETCH_RE = re.compile(r"\bgit\b[\w\s\-]*?\b(?:fetch|pull)\b", re.IGNORECASE)
# Flags that take a value argument in ``git push`` (so the following token is
# consumed as the flag's value, not a refspec).
_VALUE_FLAGS = frozenset({
"--repo",
"-o",
"--push-option",
"--receive-pack",
"--exec",
})
_FORCE_FLAGS = frozenset({"-f", "--force"})
_DRY_RUN_FLAGS = frozenset({"-n", "--dry-run"})
_DELETE_FLAGS = frozenset({"-d", "--delete"})
def _clean(value: str | None) -> str:
return (value or "").strip()
def _strip_ref_prefix(ref: str) -> str:
ref = ref.strip()
for prefix in ("refs/heads/", "heads/"):
if ref.startswith(prefix):
return ref[len(prefix):]
return ref
def is_stable_ref(ref: str | None) -> bool:
"""True when ``ref`` names a configured stable branch."""
name = _strip_ref_prefix(_clean(ref))
return bool(name) and name in STABLE_BRANCHES
# ── redaction ─────────────────────────────────────────────────────────────────
_URL_USERINFO_RE = re.compile(r"(https?://)[^/\s:@]+(?::[^/\s@]+)?@", re.IGNORECASE)
_SECRET_ASSIGN_RE = re.compile(
r"\b((?:GITEA_)?(?:TOKEN|PASSWORD|PASS|PAT|SECRET|API_KEY|AUTH))\s*=\s*\S+",
re.IGNORECASE,
)
_BEARER_RE = re.compile(r"\b(Bearer|token)\s+[A-Za-z0-9._\-]{8,}", re.IGNORECASE)
def redact_command(command: str | None) -> str:
"""Strip credentials/URLs from a command line before logging it (#671).
Redacts URL userinfo (``https://user:tok@host`` ``https://***@host``),
``TOKEN=...`` style assignments, and bearer/token headers. Leaves the
structural parts (``git push <remote> master``) intact for audit value.
"""
text = _clean(command)
if not text:
return ""
text = _URL_USERINFO_RE.sub(r"\1***@", text)
text = _SECRET_ASSIGN_RE.sub(lambda m: f"{m.group(1)}=***", text)
text = _BEARER_RE.sub(lambda m: f"{m.group(1)} ***", text)
return text
# ── push classification ───────────────────────────────────────────────────────
def _analyse_push_segment(segment: str) -> dict[str, Any]:
"""Classify one ``git push ...`` command segment."""
tokens = segment.split()
# Drop everything up to and including the ``push`` verb.
try:
push_idx = next(
i for i, tok in enumerate(tokens)
if tok.lower() == "push"
)
except StopIteration:
push_idx = -1
args = tokens[push_idx + 1:] if push_idx >= 0 else []
is_force = False
is_dry_run = False
is_delete = False
positionals: list[str] = []
skip_next = False
for tok in args:
if skip_next:
skip_next = False
continue
if tok in _FORCE_FLAGS or tok.startswith("--force-with-lease") or tok.startswith("--force-if-includes"):
is_force = True
continue
if tok in _DRY_RUN_FLAGS:
is_dry_run = True
continue
if tok in _DELETE_FLAGS:
is_delete = True
continue
if tok in _VALUE_FLAGS:
skip_next = True
continue
if tok.startswith("--") and "=" in tok:
# e.g. --repo=... : self-contained, not a refspec.
continue
if tok.startswith("-"):
# Unknown/combined short flag; ignore for ref detection.
continue
positionals.append(tok)
# First positional after push is the remote (when any positional exists);
# the rest are refspecs / branch names.
remote = positionals[0] if positionals else None
refspecs = positionals[1:]
stable_refs: list[str] = []
force_to_stable = False
delete_stable = False
for spec in refspecs:
force_spec = spec.startswith("+")
body = spec[1:] if force_spec else spec
if ":" in body:
src, _, dst = body.partition(":")
dest = dst
if src == "" and dst:
# ``:master`` — delete refspec.
is_delete = True
else:
dest = body
if is_stable_ref(dest):
stable_refs.append(_strip_ref_prefix(dest))
if force_spec or is_force:
force_to_stable = True
if is_delete:
delete_stable = True
targets_stable = bool(stable_refs)
# Ambiguous: ``git push <remote>`` (or bare ``git push``) with no refspec —
# resolves to the current branch's upstream, which we cannot see from the
# command alone. Flag it, but do not assert stable (would false-block
# feature-branch pushes).
ambiguous = not refspecs
return {
"is_git_push": True,
"remote": remote,
"refspecs": refspecs,
"targets_stable": targets_stable,
"stable_refs": stable_refs,
"is_force": is_force or force_to_stable,
"is_dry_run": is_dry_run,
"is_delete": is_delete or delete_stable,
"ambiguous_target": ambiguous,
}
def classify_push_command(command: str | None) -> dict[str, Any]:
"""Classify a shell command line for direct stable-branch push intent (#671).
Returns a dict describing whether the command is a ``git push`` targeting a
stable branch. Fetch/pull are never pushes. A sanctioned Gitea merge (which
is not a ``git push`` at all) classifies as non-push. Dry-run and no-op
pushes still count as *intent* and are reported as contamination
(``proves_intent``) so a ``--dry-run`` cannot be used to probe the gate.
"""
text = _clean(command)
result: dict[str, Any] = {
"command": text,
"redacted_command": redact_command(text),
"is_git_push": False,
"is_fetch_or_pull": False,
"targets_stable": False,
"stable_refs": [],
"is_force": False,
"is_dry_run": False,
"is_delete": False,
"ambiguous_target": False,
"contamination": False,
"proves_intent": False,
"reasons": [],
}
if not text:
return result
stable_refs: list[str] = []
saw_push = False
for segment in _SEGMENT_SPLIT_RE.split(text):
seg = segment.strip()
if not seg:
continue
if _GIT_FETCH_RE.search(seg) and not _GIT_PUSH_RE.search(seg):
result["is_fetch_or_pull"] = True
continue
if not _GIT_PUSH_RE.search(seg):
continue
saw_push = True
analysis = _analyse_push_segment(seg)
result["is_git_push"] = True
result["is_force"] = result["is_force"] or analysis["is_force"]
result["is_dry_run"] = result["is_dry_run"] or analysis["is_dry_run"]
result["is_delete"] = result["is_delete"] or analysis["is_delete"]
result["ambiguous_target"] = result["ambiguous_target"] or analysis["ambiguous_target"]
stable_refs.extend(analysis["stable_refs"])
result["stable_refs"] = sorted(set(stable_refs))
result["targets_stable"] = bool(stable_refs)
reasons: list[str] = []
if result["targets_stable"]:
refs = ", ".join(result["stable_refs"])
verb = "delete" if result["is_delete"] else ("force-push" if result["is_force"] else "push")
qualifier = " (dry-run/no-op still proves intent)" if result["is_dry_run"] else ""
reasons.append(
f"direct stable-branch {verb} detected targeting: {refs}{qualifier}; "
"worker sessions must never publish stable branches directly"
)
result["contamination"] = True
result["proves_intent"] = True
elif saw_push and result["ambiguous_target"]:
# Bare ``git push`` with no refspec: ambiguous. Report, but do not
# contaminate on the command alone — the root-checkout / branch-state
# detector resolves whether the current branch is stable.
reasons.append(
"ambiguous 'git push' with no refspec: resolve the current branch "
"before pushing; if it is a stable branch this is forbidden"
)
result["reasons"] = reasons
return result
def detect_stable_push(commands: str | Iterable[str] | None) -> dict[str, Any]:
"""Classify one command or an iterable of commands; contamination if any hit."""
if commands is None:
return classify_push_command(None)
if isinstance(commands, str):
return classify_push_command(commands)
worst: dict[str, Any] | None = None
for cmd in commands:
res = classify_push_command(cmd)
if res["contamination"]:
return res
if worst is None or (res["is_git_push"] and not worst["is_git_push"]):
worst = res
return worst or classify_push_command(None)
# ── root/control checkout local-commit detection ──────────────────────────────
def assess_root_checkout_local_commit(
*,
current_branch: str | None,
head_sha: str | None,
remote_master_sha: str | None,
is_under_branches: bool,
ahead_count: int | None = None,
) -> dict[str, Any]:
"""Detect a local commit on the root/control checkout not on a feature branch.
#671 AC2. An isolated ``branches/...`` worktree is exempt (that is where
feature work belongs). On the control checkout, a commit is illegitimate
when the checkout sits on a stable branch (or detached) and its HEAD has
advanced past the tracking ``prgs/master`` i.e. a commit was made that is
not carried by an issue feature branch/PR.
Positive evidence only: missing state reports ``unknown`` rather than
asserting contamination, but an unreadable *branch* on the control checkout
(detached HEAD) with an advanced HEAD is still flagged.
"""
branch = _clean(current_branch)
head = _clean(head_sha).lower()
master = _clean(remote_master_sha).lower()
if is_under_branches:
return {
"contamination": False,
"unknown": False,
"reasons": [],
"detail": "isolated branches/ worktree — feature commits are expected here",
}
reasons: list[str] = []
unknown = False
on_stable = (not branch) or (branch in STABLE_BRANCHES)
if not on_stable:
# Control checkout is on some non-stable branch: out of scope for this
# detector (root_checkout_guard #475 handles that contamination class).
return {
"contamination": False,
"unknown": False,
"reasons": [],
"detail": f"control checkout on non-stable branch '{branch}' — not this detector's class",
}
advanced = False
if ahead_count is not None and ahead_count > 0:
advanced = True
if head and master and head != master:
advanced = True
if (not head or not master) and ahead_count is None:
unknown = True
if advanced:
where = f"branch '{branch}'" if branch else "detached HEAD"
reasons.append(
f"control checkout ({where}) has local commits not on an issue "
"feature branch (HEAD advanced past prgs/master); worker sessions "
"must commit only on issue branches under branches/"
)
return {
"contamination": bool(reasons),
"unknown": unknown and not reasons,
"reasons": reasons,
"current_branch": branch or None,
"head_sha": head or None,
"remote_master_sha": master or None,
}
# ── contamination record + gate ───────────────────────────────────────────────
def build_contamination_record(
*,
reason_class: str,
command_redacted: str | None = None,
session_id: str | None = None,
remote: str | None = None,
ref: str | None = None,
role: str | None = None,
detail: str | None = None,
) -> dict[str, Any]:
"""Build the durable contamination marker payload (redacted, audit-safe).
``reason_class`` is one of ``stable_branch_push`` / ``root_checkout_commit``.
The command is stored already-redacted; callers pass the raw line through
:func:`redact_command` (or this builder redacts a raw ``command`` for them).
"""
return {
"kind": CONTAMINATION_KIND,
"reason_class": _clean(reason_class) or "stable_branch_push",
"command_summary": redact_command(command_redacted),
"session_id": _clean(session_id) or None,
"remote": _clean(remote) or None,
"ref": _clean(ref) or None,
"role": _clean(role) or None,
"detail": _clean(detail) or None,
"cleared_by_reconciler": False,
}
def assess_contamination_gate(
marker: dict[str, Any] | None,
*,
task: str | None,
actual_role: str | None,
) -> dict[str, Any]:
"""Fail closed on gated mutations while a contamination marker is live (#671 AC4).
* No marker allowed.
* Reconciler (audit) role allowed (the sanctioned path to inspect/clear).
* Marker present + ``task`` in :data:`CONTAMINATION_GATED_TASKS` blocked.
* Marker present + non-gated task (e.g. ``comment_issue``) allowed, so the
worker can still post the durable audit/handoff comment.
"""
if not marker or marker.get("cleared_by_reconciler"):
return {"block": False, "reasons": [], "task": task}
role = _clean(actual_role).lower()
if role == "reconciler":
return {
"block": False,
"reasons": [],
"task": task,
"detail": "reconciler audit path is exempt from the contamination gate",
}
task_name = _clean(task)
if task_name and task_name in CONTAMINATION_GATED_TASKS:
summary = marker.get("command_summary") or marker.get("detail") or "(no summary)"
reason_class = marker.get("reason_class") or "stable_branch_push"
return {
"block": True,
"reasons": [
f"session is workflow-contaminated ({reason_class}): {summary}. "
f"'{task_name}' is blocked until a reconciler audits and clears "
"the contamination. " + REMEDIATION
],
"task": task_name,
}
return {"block": False, "reasons": [], "task": task_name or None}
def format_contamination_gate_error(gate: dict[str, Any]) -> str:
"""Single RuntimeError message for MCP mutation gates."""
reasons = "; ".join(gate.get("reasons") or ["session workflow-contaminated"])
return f"Stable-branch contamination gate (#671): {reasons}"
-440
View File
@@ -1,440 +0,0 @@
"""Stale / moot #332 review-decision lock detection and cleanup policy (#594/#620).
#332 correctly hard-stops a reviewer session after a terminal live review
mutation. After #559 those locks are durable on disk, so they can outlive the
work they protect: when the referenced PR is already merged or closed, no
same-PR merge sequence remains, yet the durable ledger still blocks unrelated
new terminal reviews.
#620 scopes the terminal boundary by **reviewed head SHA**: a prior
REQUEST_CHANGES (or APPROVE) on head A must not block a fresh formal decision
on head B of the **same open PR**. Same-head duplicates remain fail-closed.
Open-PR lock *cleanup* remains forbidden unless the PR is truly merged/closed
(#594); new-head re-review is allowed without deleting the durable lock.
This module is pure policy (no Gitea I/O). The MCP tool
``gitea_cleanup_stale_review_decision_lock`` fetches live PR state, calls these
helpers, and only then clears durable state when cleanup is allowed.
Manual deletion of ``~/.cache/gitea-tools/session-state/*`` is never the
canonical path.
"""
from __future__ import annotations
from datetime import datetime, timezone
from typing import Any
# Keep in sync with gitea_mcp_server._TERMINAL_REVIEW_ACTIONS.
TERMINAL_REVIEW_ACTIONS = frozenset({"approve", "request_changes"})
def normalize_head_sha(value: Any) -> str | None:
"""Normalize a git SHA for equality comparison; None if empty/invalid."""
if value is None:
return None
text = str(value).strip().lower()
if not text:
return None
return text
def heads_equal(a: Any, b: Any) -> bool:
na = normalize_head_sha(a)
nb = normalize_head_sha(b)
if not na or not nb:
return False
return na == nb
def mutation_head_sha(mutation: dict | None, lock: dict | None = None) -> str | None:
"""Head SHA that bounds a live mutation (#620).
Prefers fields recorded on the mutation itself. For *legacy* mutations
that predate head-scoping, falls back to the lock's
``ready_expected_head_sha`` only when that ready binding is for the same
PR number (the frozen durable PR #619-style ledger).
"""
if not isinstance(mutation, dict):
return None
for key in ("head_sha", "expected_head_sha", "reviewed_head_sha"):
head = normalize_head_sha(mutation.get(key))
if head:
return head
if not isinstance(lock, dict):
return None
if lock.get("ready_pr_number") != mutation.get("pr_number"):
return None
return normalize_head_sha(lock.get("ready_expected_head_sha"))
def last_terminal_mutation(lock: dict | None) -> dict | None:
"""Return the last terminal live mutation on *lock*, or None."""
if not lock:
return None
terminals = [
m
for m in (lock.get("live_mutations") or [])
if isinstance(m, dict) and m.get("action") in TERMINAL_REVIEW_ACTIONS
]
return terminals[-1] if terminals else None
def prior_live_mutations_block_boundary(
lock: dict | None,
*,
pr_number: int,
expected_head_sha: str | None,
) -> bool:
"""True when prior live mutations block a new decision for PR+head (#620).
Historical terminals on a **different head of the same PR** do not block.
Any prior mutation on another PR, the same head, or without a comparable
head SHA fails closed (blocks).
Head resolution uses ``mutation_head_sha(m, lock)`` so pre-#620 ledgers
that only stored ``ready_expected_head_sha`` still compare correctly
(PR #619-style).
"""
if not lock:
return False
if lock.get("correction_authorized"):
return False
prior = list(lock.get("live_mutations") or [])
if not prior:
return False
target = normalize_head_sha(expected_head_sha)
for m in prior:
if not isinstance(m, dict):
return True
m_pr = m.get("pr_number")
m_head = mutation_head_sha(m, lock)
if (
m_pr == pr_number
and target
and m_head
and not heads_equal(m_head, target)
):
# Same open PR, different reviewed head — historical boundary only.
continue
return True
return False
def terminal_boundary_allows_fresh_decision(
lock: dict | None,
*,
pr_number: int,
expected_head_sha: str | None,
operation: str,
) -> bool:
"""Whether #332 hard-stop should yield for a new PR+head boundary (#620).
Only for ``mark_ready`` / ``review`` / ``resume`` on the **same PR** when
the requested head differs from the last terminal's head. Merge is never
reopened by head change (approved head merge path is separate).
"""
if operation not in ("mark_ready", "review", "resume"):
return False
if not lock:
return False
if lock.get("correction_authorized"):
return True
last = last_terminal_mutation(lock)
if last is None:
return True
if last.get("pr_number") != pr_number:
return False
locked_head = mutation_head_sha(last, lock)
target = normalize_head_sha(expected_head_sha)
if not locked_head or not target:
return False
return not heads_equal(locked_head, target)
def backfill_terminal_heads_from_ready(lock: dict) -> dict:
"""Stamp head_sha onto legacy terminal mutations before overwriting ready_*.
Called when marking a fresh decision on a new head so historical rows keep
their original boundary after ``ready_expected_head_sha`` advances (#620).
"""
if not isinstance(lock, dict):
return lock
ready_pr = lock.get("ready_pr_number")
ready_head = normalize_head_sha(lock.get("ready_expected_head_sha"))
if ready_pr is None or not ready_head:
return lock
mutations = list(lock.get("live_mutations") or [])
changed = False
for m in mutations:
if not isinstance(m, dict):
continue
if m.get("action") not in TERMINAL_REVIEW_ACTIONS:
continue
if m.get("pr_number") != ready_pr:
continue
if mutation_head_sha(m):
continue
m["head_sha"] = ready_head
changed = True
if changed:
lock["live_mutations"] = mutations
return lock
def classify_pr_live_state(pr_live: dict | None) -> dict[str, Any]:
"""Normalize a Gitea PR payload into merge/closed flags."""
pr = pr_live or {}
merged = bool(pr.get("merged") or pr.get("merged_at"))
state = (pr.get("state") or "").strip().lower() or None
closed = state == "closed"
head = pr.get("head") if isinstance(pr.get("head"), dict) else {}
head_sha = normalize_head_sha(
pr.get("head_sha") or pr.get("head_commit_sha") or head.get("sha")
)
return {
"pr_state": state,
"pr_merged": merged,
"pr_merged_or_closed": merged or closed,
"merge_commit_sha": pr.get("merge_commit_sha")
or pr.get("merged_commit_sha"),
"current_pr_head_sha": head_sha,
}
def lock_summary(lock: dict | None) -> dict[str, Any] | None:
"""LLM-safe summary of a decision lock (no secrets)."""
if lock is None:
return None
last = last_terminal_mutation(lock)
mutations = list(lock.get("live_mutations") or [])
last_head = mutation_head_sha(last, lock) if last else None
return {
"task": lock.get("task"),
"remote": lock.get("remote"),
"org": lock.get("org") or lock.get("ready_org"),
"repo": lock.get("repo") or lock.get("ready_repo"),
"profile_identity": lock.get("profile_identity")
or lock.get("session_profile_lock")
or lock.get("session_profile"),
"session_profile": lock.get("session_profile"),
"ready_pr_number": lock.get("ready_pr_number"),
"ready_action": lock.get("ready_action"),
"ready_expected_head_sha": normalize_head_sha(
lock.get("ready_expected_head_sha")
),
"live_mutations_count": len(mutations),
"last_terminal": (
{
"pr_number": last.get("pr_number"),
"action": last.get("action"),
"review_id": last.get("review_id"),
"head_sha": last_head,
}
if last
else None
),
"locked_head_sha": last_head,
"correction_authorized": bool(lock.get("correction_authorized")),
"updated_at": lock.get("updated_at") or lock.get("recorded_at"),
}
def assess_stale_review_decision_lock(
lock: dict | None,
*,
pr_live: dict | None = None,
pr_lookup_error: str | None = None,
active_profile_identity: str | None = None,
current_pr_head_sha: str | None = None,
) -> dict[str, Any]:
"""Assess whether a durable review-decision lock is stale/moot (#594/#620).
*pr_live* must be the live Gitea payload for the **last terminal
mutation's PR**. When no lock / no terminal mutation exists, cleanup is
not applicable. When the PR is still open (or lookup fails), cleanup is
forbidden (#594). Open PR + different live head reports
``stale_by_head`` / ``fresh_review_on_current_head_allowed`` (#620)
without enabling cleanup.
"""
summary = lock_summary(lock)
result: dict[str, Any] = {
"has_lock": lock is not None,
"lock_summary": summary,
"last_terminal_pr": None,
"last_terminal_action": None,
"locked_head_sha": None,
"current_pr_head_sha": normalize_head_sha(current_pr_head_sha),
"stale_by_head": False,
"fresh_review_on_current_head_allowed": False,
"is_moot": False,
"cleanup_allowed": False,
"profile_match": True,
"pr_state": None,
"pr_merged": False,
"pr_merged_or_closed": False,
"merge_commit_sha": None,
"reasons": [],
"recovery_tool": "gitea_cleanup_stale_review_decision_lock",
}
if lock is None:
result["reasons"].append("no review decision lock present")
return result
# Profile identity gate (caller may re-check with env; pure assess still
# reports mismatch when active identity is supplied).
stored = (
(lock.get("profile_identity") or lock.get("session_profile_lock") or "")
.strip()
)
active = (active_profile_identity or "").strip()
if active and stored and active != stored:
result["profile_match"] = False
result["reasons"].append(
"review decision lock profile identity does not match active "
f"profile '{active}' (fail closed, #594)"
)
return result
last = last_terminal_mutation(lock)
if last is None:
result["reasons"].append(
"review decision lock has no terminal live mutations; nothing to clear"
)
return result
pr_number = last.get("pr_number")
action = last.get("action")
locked_head = mutation_head_sha(last, lock)
result["last_terminal_pr"] = pr_number
result["last_terminal_action"] = action
result["locked_head_sha"] = locked_head
if pr_number is None:
result["reasons"].append(
"last terminal mutation missing pr_number; refuse cleanup (fail closed)"
)
return result
if pr_lookup_error:
result["reasons"].append(
f"could not load live state for PR #{pr_number}: {pr_lookup_error} "
"(fail closed, #594)"
)
return result
if pr_live is None:
result["reasons"].append(
f"live PR state required for terminal PR #{pr_number} before cleanup "
"(fail closed, #594)"
)
return result
live = classify_pr_live_state(pr_live)
current_head = normalize_head_sha(
current_pr_head_sha or live.get("current_pr_head_sha")
)
result.update(
{
"pr_state": live["pr_state"],
"pr_merged": live["pr_merged"],
"pr_merged_or_closed": live["pr_merged_or_closed"],
"merge_commit_sha": live["merge_commit_sha"],
"current_pr_head_sha": current_head,
}
)
if not live["pr_merged_or_closed"]:
stale_by_head = bool(
locked_head and current_head and not heads_equal(locked_head, current_head)
)
result["stale_by_head"] = stale_by_head
# Fresh formal decision is allowed on the new head without cleanup (#620).
result["fresh_review_on_current_head_allowed"] = stale_by_head
if stale_by_head:
result["reasons"].append(
f"terminal {action} on PR #{pr_number} is bound to head "
f"{locked_head[:12]}…; live head is {current_head[:12]}… — "
"fresh formal review on current head is allowed without "
"cleanup (fail closed for cleanup, #620); #332 same-head "
"duplicate protection remains"
)
else:
result["reasons"].append(
f"terminal review mutation on open PR #{pr_number} is still active "
f"({action}); #332 hard-stop remains — cleanup forbidden (#594)"
)
return result
# Merged or closed: lock is moot. Same-PR merge continuation is impossible.
result["is_moot"] = True
result["cleanup_allowed"] = True
result["stale_by_head"] = False
result["fresh_review_on_current_head_allowed"] = False
result["reasons"].append(
f"terminal mutation ({action} on PR #{pr_number}) is moot: PR is "
f"{'merged' if live['pr_merged'] else 'closed'}; canonical cleanup allowed (#594)"
)
return result
def build_cleanup_audit_record(
*,
assessment: dict[str, Any],
actor_username: str | None,
profile_name: str | None,
applied: bool,
) -> dict[str, Any]:
"""Structured durable audit payload for a cleanup attempt."""
last = (assessment.get("lock_summary") or {}).get("last_terminal") or {}
return {
"event": "stale_review_decision_lock_cleanup",
"issue_ref": "#594",
"applied": bool(applied),
"timestamp": datetime.now(timezone.utc).isoformat(),
"actor_username": actor_username,
"profile_name": profile_name,
"last_terminal_pr": assessment.get("last_terminal_pr") or last.get("pr_number"),
"last_terminal_action": assessment.get("last_terminal_action")
or last.get("action"),
"pr_state": assessment.get("pr_state"),
"pr_merged": assessment.get("pr_merged"),
"pr_merged_or_closed": assessment.get("pr_merged_or_closed"),
"merge_commit_sha": assessment.get("merge_commit_sha"),
"prior_live_mutations_count": (
(assessment.get("lock_summary") or {}).get("live_mutations_count")
),
"prior_profile_identity": (
(assessment.get("lock_summary") or {}).get("profile_identity")
),
"cleanup_allowed": assessment.get("cleanup_allowed"),
"is_moot": assessment.get("is_moot"),
"reasons": list(assessment.get("reasons") or []),
}
def format_cleanup_audit_comment(audit: dict[str, Any]) -> str:
"""Markdown body for a durable Gitea audit comment after cleanup."""
status = "APPLIED" if audit.get("applied") else "ASSESSED (not applied)"
lines = [
"## Stale #332 review-decision lock cleanup (#594)",
"",
f"Status: **{status}**",
"",
f"- actor: `{audit.get('actor_username')}`",
f"- profile: `{audit.get('profile_name')}`",
f"- timestamp: `{audit.get('timestamp')}`",
f"- last terminal: `{audit.get('last_terminal_action')}` on "
f"PR #{audit.get('last_terminal_pr')}",
f"- PR state: `{audit.get('pr_state')}` "
f"(merged={audit.get('pr_merged')})",
f"- merge_commit_sha: `{audit.get('merge_commit_sha')}`",
f"- prior live_mutations_count: "
f"`{audit.get('prior_live_mutations_count')}`",
f"- prior profile_identity: `{audit.get('prior_profile_identity')}`",
"",
"Manual deletion of session-state files is **not** the workflow.",
"This path only clears a lock when the referenced PR is merged/closed.",
]
return "\n".join(lines)
-130
View File
@@ -76,16 +76,6 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
"permission": "gitea.pr.comment",
"role": "reviewer",
},
# #691: guarded non-owner cleanup of obsolete comment-backed reviewer leases.
# Apply path posts lease release + audit comments (gitea.pr.comment).
"cleanup_obsolete_reviewer_comment_lease": {
"permission": "gitea.pr.comment",
"role": "reviewer",
},
"gitea_cleanup_obsolete_reviewer_comment_lease": {
"permission": "gitea.pr.comment",
"role": "reviewer",
},
"blind_pr_queue_review": {
"permission": "gitea.pr.review",
"role": "reviewer",
@@ -106,17 +96,6 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
"permission": "gitea.pr.approve",
"role": "reviewer",
},
# #594: clear durable #332 decision lock only when last terminal PR is
# already merged/closed (moot). Apply path requires reviewer review
# permission; assessment itself uses gitea.read inside the tool.
"cleanup_stale_review_decision_lock": {
"permission": "gitea.pr.review",
"role": "reviewer",
},
"gitea_cleanup_stale_review_decision_lock": {
"permission": "gitea.pr.review",
"role": "reviewer",
},
"delete_branch": {
"permission": "gitea.branch.delete",
"role": "author",
@@ -149,103 +128,6 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
"permission": "gitea.pr.create",
"role": "author",
},
# #600: controller-owned allocator — any authenticated profile may call;
# routing enforces role match to selected work. Uses control-plane DB (#613).
"allocate_next_work": {
"permission": "gitea.read",
"role": "author",
},
"gitea_allocate_next_work": {
"permission": "gitea.read",
"role": "author",
},
# #601 first-class lease lifecycle — inspect/list need read; mutations gate on
# ownership in the control-plane DB (not a separate Gitea write permission).
"list_workflow_leases": {
"permission": "gitea.read",
"role": "author",
},
"gitea_list_workflow_leases": {
"permission": "gitea.read",
"role": "author",
},
"inspect_workflow_lease": {
"permission": "gitea.read",
"role": "author",
},
"gitea_inspect_workflow_lease": {
"permission": "gitea.read",
"role": "author",
},
"adopt_workflow_lease": {
"permission": "gitea.read",
"role": "author",
},
"gitea_adopt_workflow_lease": {
"permission": "gitea.read",
"role": "author",
},
"release_workflow_lease": {
"permission": "gitea.read",
"role": "author",
},
"gitea_release_workflow_lease": {
"permission": "gitea.read",
"role": "author",
},
"expire_workflow_leases": {
"permission": "gitea.read",
"role": "author",
},
"gitea_expire_workflow_leases": {
"permission": "gitea.read",
"role": "author",
},
"abandon_workflow_lease": {
"permission": "gitea.read",
"role": "author",
},
"gitea_abandon_workflow_lease": {
"permission": "gitea.read",
"role": "author",
},
"reclaim_expired_workflow_lease": {
"permission": "gitea.read",
"role": "author",
},
"gitea_reclaim_expired_workflow_lease": {
"permission": "gitea.read",
"role": "author",
},
# #612 incident bridge — reconcile uses create_issue for apply;
# dry-run needs read only. Tools gate apply paths themselves.
"observability_reconcile_incident": {
"permission": "gitea.read",
"role": "author",
},
"gitea_observability_reconcile_incident": {
"permission": "gitea.read",
"role": "author",
},
"observability_list_projects": {
"permission": "gitea.read",
"role": "author",
},
"gitea_observability_list_projects": {
"permission": "gitea.read",
"role": "author",
},
"observability_link_issue": {
"permission": "gitea.read",
"role": "author",
},
"gitea_observability_link_issue": {
"permission": "gitea.read",
"role": "author",
},
"reconcile_landed_pr": {
"permission": "gitea.read",
"role": "author",
@@ -268,18 +150,6 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
"permission": "gitea.issue.close",
"role": "reconciler",
},
"reconcile_close_superseded_pr": {
"permission": "gitea.pr.close",
"role": "reconciler",
},
"reconcile_close_satisfied_issue": {
"permission": "gitea.issue.close",
"role": "reconciler",
},
"reconcile_create_followup_issue": {
"permission": "gitea.issue.create",
"role": "reconciler",
},
"post_heartbeat": {
"permission": "gitea.issue.comment",
"role": "author",
+5 -17
View File
@@ -1,15 +1,10 @@
#!/usr/bin/env python3
"""Offline-only MCP namespace spawn probe (NOT IDE-namespace proof).
"""Live health-check script to verify Gitea MCP namespace connections.
Spawns a *separate* MCP server process from config via subprocess.Popen,
performs the JSON-RPC handshake, verifies the required tool is registered,
and invokes that tool. Results are classified with
``probe_source=offline_spawn``.
This path is useful for offline launch/registration debugging. It does
**not** prove the IDE-managed MCP client namespace is healthy (#543). For
workflow gates, pass live IDE call evidence with
``probe_source=client_namespace`` to ``gitea_assess_mcp_namespace_health``.
Spawns MCP server processes from the IDE config, performs the JSON-RPC
handshake, verifies the required tool is registered, and invokes that tool.
The final invocation is what catches client/namespace EOF failures that a
static FastMCP registration check cannot see.
"""
import argparse
@@ -64,7 +59,6 @@ def run_connection_test(name, config, *, required_tool=None, config_path=None):
probe_result={"success": False, "error": str(exc)},
process={"profile": env.get("GITEA_MCP_PROFILE"), "env": env},
config_path=config_path,
probe_source="offline_spawn",
)
print(f" diagnostics: {json.dumps(assessment['diagnostics'], sort_keys=True)}")
return False
@@ -98,7 +92,6 @@ def run_connection_test(name, config, *, required_tool=None, config_path=None):
"env": env,
},
config_path=config_path,
probe_source="offline_spawn",
)
print(f" remediation: {' '.join(assessment['remediation'])}")
proc.terminate()
@@ -135,7 +128,6 @@ def run_connection_test(name, config, *, required_tool=None, config_path=None):
"env": env,
},
config_path=config_path,
probe_source="offline_spawn",
)
print(f" remediation: {' '.join(assessment['remediation'])}")
proc.terminate()
@@ -161,7 +153,6 @@ def run_connection_test(name, config, *, required_tool=None, config_path=None):
"env": env,
},
config_path=config_path,
probe_source="offline_spawn",
)
print(f" [FAIL] Required tool '{tool_name}' is not registered.")
print(f" remediation: {' '.join(assessment['remediation'])}")
@@ -189,7 +180,6 @@ def run_connection_test(name, config, *, required_tool=None, config_path=None):
"env": env,
},
config_path=config_path,
probe_source="offline_spawn",
)
print(f" [FAIL] Received EOF on {tool_name} invocation.")
print(f" diagnostics: {json.dumps(assessment['diagnostics'], sort_keys=True)}")
@@ -208,7 +198,6 @@ def run_connection_test(name, config, *, required_tool=None, config_path=None):
"env": env,
},
config_path=config_path,
probe_source="offline_spawn",
)
print(f" [FAIL] {tool_name} invocation returned error: {call_res['error']}")
print(f" remediation: {' '.join(assessment['remediation'])}")
@@ -226,7 +215,6 @@ def run_connection_test(name, config, *, required_tool=None, config_path=None):
"env": env,
},
config_path=config_path,
probe_source="offline_spawn",
)
print(f" [OK] Successfully invoked required tool '{tool_name}'.")
print(f" diagnostics: {json.dumps(assessment['diagnostics'], sort_keys=True)}")
+2 -54
View File
@@ -1,5 +1,4 @@
"""Shared pytest fixtures for the Gitea-Tools test suite."""
import os
import sys
import pytest
@@ -17,55 +16,13 @@ def _reset_mutation_authority(monkeypatch):
the next test. It must never replace verify_mutation_authority with a
no-op: individual tests that need a specific authority state set it up
explicitly.
Session-state isolation (#559 / #590 / #594): many tests use
``patch.dict(os.environ, ..., clear=True)``, which drops
``GITEA_MCP_SESSION_STATE_DIR``. Relying only on the env var therefore
re-exposes the operator host cache
(``~/.cache/gitea-tools/session-state``) and its review-mutation ledger.
Pin ``default_state_dir`` / ``DEFAULT_STATE_DIR`` to a per-test temp dir
so durable load/save never touches host state even after env clears.
"""
for env_key in [
"GITEA_SESSION_PROFILE_LOCK",
"GITEA_ACTIVE_WORKTREE",
"GITEA_AUTHOR_WORKTREE",
"GITEA_REVIEWER_WORKTREE",
"GITEA_MERGER_WORKTREE",
"GITEA_RECONCILER_WORKTREE",
]:
monkeypatch.delenv(env_key, raising=False)
monkeypatch.delenv("GITEA_SESSION_PROFILE_LOCK", raising=False)
# Isolate durable session-state files so tests never share host cache (#559).
import tempfile
_state_tmp = tempfile.TemporaryDirectory(prefix="gitea-session-state-")
state_dir = _state_tmp.name
monkeypatch.setenv("GITEA_MCP_SESSION_STATE_DIR", state_dir)
try:
import mcp_session_state
except Exception:
mcp_session_state = None
if mcp_session_state is not None:
# Survive patch.dict(..., clear=True) that drops the env var (#590).
# Still honor an explicit GITEA_MCP_SESSION_STATE_DIR when tests set
# their own temp dir (see tests/test_mcp_session_state.py).
monkeypatch.setattr(
mcp_session_state, "DEFAULT_STATE_DIR", state_dir, raising=False
)
def _isolated_default_state_dir(
_fallback: str = state_dir,
_env_key: str = mcp_session_state.STATE_DIR_ENV,
) -> str:
raw = (os.environ.get(_env_key) or "").strip()
return raw or _fallback
monkeypatch.setattr(
mcp_session_state,
"default_state_dir",
_isolated_default_state_dir,
)
monkeypatch.setenv("GITEA_MCP_SESSION_STATE_DIR", _state_tmp.name)
try:
import mcp_server
except Exception:
@@ -75,7 +32,6 @@ def _reset_mutation_authority(monkeypatch):
monkeypatch.setattr(mcp_server, "_MUTATION_AUTHORITY", None)
monkeypatch.setattr(mcp_server, "_IDENTITY_CACHE", {})
monkeypatch.setattr(mcp_server, "_REVIEW_DECISION_LOCK", None)
monkeypatch.setattr(mcp_server, "_LIVE_NAMESPACE_HEALTH", {})
monkeypatch.setattr(mcp_server, "_preflight_whoami_called", False)
monkeypatch.setattr(mcp_server, "_preflight_capability_called", False)
monkeypatch.setattr(mcp_server, "_preflight_resolved_role", None)
@@ -84,14 +40,6 @@ def _reset_mutation_authority(monkeypatch):
monkeypatch.setattr(mcp_server, "_preflight_capability_baseline_porcelain", None)
monkeypatch.setattr(mcp_server, "_preflight_resolved_task", None)
monkeypatch.setattr(mcp_server, "_preflight_reviewer_violation_files", [])
# Unit tests must not depend on live host MCP process health. Tests that
# use patch.dict(..., clear=True) drop PYTEST_CURRENT_TEST, which would
# otherwise re-enable the stale-runtime probe against operator daemons.
monkeypatch.setattr(
mcp_server,
"_check_mcp_runtimes_diagnostics",
lambda *args, **kwargs: [],
)
try:
import review_workflow_load
review_workflow_load._REVIEW_WORKFLOW_LOAD = None
-366
View File
@@ -1,366 +0,0 @@
"""Tests for controller-owned allocator (#600) on control-plane DB (#613)."""
from __future__ import annotations
import os
import tempfile
import threading
import unittest
from concurrent.futures import ThreadPoolExecutor, as_completed
from allocator_service import (
OUTCOME_ASSIGNED,
OUTCOME_BLOCKED_TERMINAL,
OUTCOME_NO_SAFE,
OUTCOME_PREVIEW,
OUTCOME_WAIT,
WorkCandidate,
allocate_next_work,
candidate_from_dict,
classify_skip,
expected_role_for_candidate,
)
from control_plane_db import ControlPlaneDB, InvalidWorkKindError
class AllocatorServiceTest(unittest.TestCase):
def setUp(self) -> None:
self._tmp = tempfile.TemporaryDirectory()
self.db_path = os.path.join(self._tmp.name, "cp.sqlite3")
self.db = ControlPlaneDB(self.db_path)
def tearDown(self) -> None:
self._tmp.cleanup()
def _alloc(self, **kwargs):
defaults = dict(
db=self.db,
session_id="s-test",
role="author",
remote="prgs",
org="org",
repo="repo",
candidates=[],
apply=False,
profile_name="prgs-author",
username="jcwalker3",
)
defaults.update(kwargs)
return allocate_next_work(**defaults)
def test_selects_ready_issue_for_author(self) -> None:
cands = [
WorkCandidate(
kind="issue",
number=612,
labels=("status:ready",),
title="bridge",
dependency_unmet=True,
dependency_reason="downstream of #600",
),
WorkCandidate(
kind="issue",
number=600,
labels=("status:ready", "type:feature"),
title="allocator",
priority=50,
),
WorkCandidate(
kind="issue",
number=601,
labels=("status:blocked",),
title="blocked",
blocked=True,
),
]
res = self._alloc(candidates=cands, apply=False)
self.assertTrue(res["success"])
self.assertEqual(res["outcome"], OUTCOME_PREVIEW)
self.assertEqual(res["selected"]["number"], 600)
self.assertEqual(res["selected"]["kind"], "issue")
# When 600 is highest priority valid work, lower-priority blocked/dep
# candidates are not visited. Prove they are skipped when they sort first.
res2 = self._alloc(
candidates=[
WorkCandidate(
kind="issue",
number=612,
labels=("status:ready",),
priority=99,
dependency_unmet=True,
dependency_reason="downstream of #600",
),
WorkCandidate(
kind="issue",
number=601,
labels=("status:blocked",),
priority=98,
blocked=True,
),
WorkCandidate(
kind="issue",
number=600,
labels=("status:ready",),
priority=1,
),
],
apply=False,
)
skipped_nums = {s["number"] for s in res2["skipped"]}
self.assertIn(612, skipped_nums)
self.assertIn(601, skipped_nums)
self.assertEqual(res2["selected"]["number"], 600)
self.assertIsNone(res["assignment"])
self.assertFalse(res["file_lock_only"])
self.assertFalse(res["comment_lease_only"])
def test_atomic_assign_and_lease_on_apply(self) -> None:
cands = [
WorkCandidate(
kind="issue",
number=600,
labels=("status:ready",),
priority=10,
)
]
res = self._alloc(candidates=cands, apply=True, session_id="s-a")
self.assertEqual(res["outcome"], OUTCOME_ASSIGNED)
asn = res["assignment"]
self.assertEqual(asn["outcome"], "assigned")
self.assertIsNotNone(asn["assignment_id"])
self.assertIsNotNone(asn["lease_id"])
self.assertEqual(asn["work_number"], 600)
self.assertIn("implement", asn["allowed_actions"])
self.assertIn("merge", asn["forbidden_actions"])
proof = res["lease_proof"]
self.assertEqual(proof["source"], "control_plane_db.assign_and_lease")
def test_concurrent_allocators_no_double_assign(self) -> None:
cand = WorkCandidate(
kind="pr",
number=100,
head_sha="a" * 40,
priority=10,
)
# Seed work item so both race the same target
self.db.upsert_work_item(
remote="prgs",
org="org",
repo="repo",
kind="pr",
number=100,
current_head_sha="a" * 40,
)
results = []
lock = threading.Lock()
def worker(sid: str):
r = allocate_next_work(
self.db,
session_id=sid,
role="reviewer",
remote="prgs",
org="org",
repo="repo",
candidates=[cand],
apply=True,
profile_name="prgs-reviewer",
)
with lock:
results.append(r)
with ThreadPoolExecutor(max_workers=2) as pool:
futs = [pool.submit(worker, f"s-{i}") for i in range(2)]
for f in as_completed(futs):
f.result()
outcomes = [r["outcome"] for r in results]
self.assertEqual(outcomes.count(OUTCOME_ASSIGNED), 1, outcomes)
self.assertEqual(outcomes.count(OUTCOME_WAIT), 1, outcomes)
def test_blocked_and_dependency_skipped(self) -> None:
cands = [
WorkCandidate(kind="issue", number=1, blocked=True, labels=("status:blocked",)),
WorkCandidate(
kind="issue",
number=612,
labels=("status:ready",),
dependency_unmet=True,
dependency_reason="downstream of #600",
),
]
res = self._alloc(candidates=cands, apply=True, role="author")
self.assertEqual(res["outcome"], OUTCOME_NO_SAFE)
self.assertIsNone(res["selected"])
reasons = " ".join(s["reason"] for s in res["skipped"])
self.assertIn("blocked", reasons.lower())
self.assertIn("600", reasons)
def test_already_leased_returns_wait(self) -> None:
self.db.upsert_session(session_id="owner", role="author")
self.db.assign_and_lease(
session_id="owner",
role="author",
remote="prgs",
org="org",
repo="repo",
kind="issue",
number=50,
)
res = self._alloc(
session_id="other",
candidates=[
WorkCandidate(kind="issue", number=50, labels=("status:ready",))
],
apply=True,
)
self.assertEqual(res["outcome"], OUTCOME_WAIT)
self.assertEqual(res["owner_session_id"], "owner")
def test_role_ineligible_skipped(self) -> None:
# PR with current-head REQUEST_CHANGES expects author, not reviewer.
cand = WorkCandidate(
kind="pr",
number=9,
head_sha="b" * 40,
request_changes_current_head=True,
)
self.assertEqual(expected_role_for_candidate(cand), "author")
res = self._alloc(
role="reviewer",
profile_name="prgs-reviewer",
candidates=[cand],
apply=False,
)
self.assertEqual(res["outcome"], OUTCOME_NO_SAFE)
self.assertTrue(any("expects role" in s["reason"] for s in res["skipped"]))
def test_terminal_lock_blocks_downstream_reviewer_prs(self) -> None:
self.db.set_terminal_lock(
remote="prgs",
org="org",
repo="repo",
terminal_pr=10,
decision="request_changes",
status="active",
)
cands = [
WorkCandidate(kind="pr", number=11, head_sha="c" * 40, priority=5),
WorkCandidate(kind="pr", number=10, head_sha="d" * 40, priority=1),
]
res = self._alloc(
role="reviewer",
profile_name="prgs-reviewer",
candidates=cands,
apply=False,
)
# Terminal PR #10 is selectable; #11 skipped for terminal path.
self.assertEqual(res["selected"]["number"], 10)
self.assertTrue(
any(
s["number"] == 11 and "terminal-review lock" in s["reason"]
for s in res["skipped"]
)
)
def test_terminal_lock_blocks_all_when_only_downstream(self) -> None:
self.db.set_terminal_lock(
remote="prgs",
org="org",
repo="repo",
terminal_pr=10,
decision="request_changes",
status="active",
)
res = self._alloc(
role="reviewer",
profile_name="prgs-reviewer",
candidates=[
WorkCandidate(kind="pr", number=99, head_sha="e" * 40),
],
apply=False,
)
self.assertEqual(res["outcome"], OUTCOME_BLOCKED_TERMINAL)
def test_no_work_structured(self) -> None:
res = self._alloc(candidates=[], apply=True)
self.assertEqual(res["outcome"], OUTCOME_NO_SAFE)
self.assertIsNone(res["selected"])
self.assertTrue(res["reasons"])
def test_rejects_incident_kind(self) -> None:
with self.assertRaises(InvalidWorkKindError):
WorkCandidate(kind="sentry_incident", number=1)
def test_612_downstream_marker_in_result(self) -> None:
res = self._alloc(
candidates=[
WorkCandidate(kind="issue", number=600, labels=("status:ready",))
],
apply=True,
)
self.assertIn("612", res.get("downstream_note", ""))
def test_substrate_not_file_or_comment_lease(self) -> None:
res = self._alloc(
candidates=[
WorkCandidate(kind="issue", number=1, labels=("status:ready",))
],
apply=True,
)
self.assertEqual(res["substrate"], "control_plane_db")
self.assertFalse(res["file_lock_only"])
self.assertFalse(res["comment_lease_only"])
self.assertEqual(
res["lease_proof"]["source"], "control_plane_db.assign_and_lease"
)
def test_candidate_from_dict(self) -> None:
c = candidate_from_dict(
{
"kind": "pr",
"number": 7,
"head_sha": "f" * 40,
"approval_on_current_head": True,
"mergeable": True,
}
)
self.assertEqual(expected_role_for_candidate(c), "merger")
def test_merger_gets_clean_approval(self) -> None:
c = WorkCandidate(
kind="pr",
number=3,
head_sha="1" * 40,
approval_on_current_head=True,
mergeable=True,
priority=100,
)
res = self._alloc(
role="merger",
profile_name="prgs-merger",
candidates=[c],
apply=True,
session_id="merger-1",
)
self.assertEqual(res["outcome"], OUTCOME_ASSIGNED)
self.assertEqual(res["assignment"]["work_number"], 3)
self.assertIn("merge", res["assignment"]["allowed_actions"])
def test_db_unavailable_fails_closed(self) -> None:
res = allocate_next_work(
None, # type: ignore[arg-type]
session_id="x",
role="author",
remote="prgs",
org="o",
repo="r",
candidates=[],
apply=True,
)
self.assertFalse(res["success"])
self.assertIn("unavailable", res["reasons"][0].lower())
if __name__ == "__main__":
unittest.main()
+16 -22
View File
@@ -79,46 +79,41 @@ class TestApiRequestFailures(unittest.TestCase):
@patch("gitea_auth.urllib.request.urlopen")
def test_timeout_converted_to_runtimeerror(self, mock_open):
mock_open.side_effect = TimeoutError("timed out")
with self.assertRaises(gitea_auth.GiteaNetworkError) as ctx:
with self.assertRaises(RuntimeError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
# Fixed message only (#699) — still a RuntimeError subclass.
self.assertIsInstance(ctx.exception, RuntimeError)
self.assertEqual(str(ctx.exception), "Network error contacting Gitea")
self.assertIn("network error contacting Gitea", str(ctx.exception))
@patch("gitea_auth.urllib.request.urlopen")
def test_dns_network_failure_converted(self, mock_open):
mock_open.side_effect = urllib.error.URLError("Name or service not known")
with self.assertRaises(gitea_auth.GiteaNetworkError) as ctx:
with self.assertRaises(RuntimeError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertEqual(str(ctx.exception), "Network error contacting Gitea")
self.assertIn("network error contacting Gitea", str(ctx.exception))
@patch("gitea_auth.urllib.request.urlopen")
def test_502_upstream_message(self, mock_open):
mock_open.side_effect = http_error(502, "bad gateway")
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
with self.assertRaises(RuntimeError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
msg = str(ctx.exception)
self.assertEqual(msg, "Gitea upstream unavailable")
self.assertEqual(ctx.exception.reason_code, "upstream_unavailable")
self.assertEqual(ctx.exception.http_status, 502)
self.assertIn("HTTP 502", msg)
self.assertIn("upstream unavailable", msg)
@patch("gitea_auth.urllib.request.urlopen")
def test_503_upstream_message(self, mock_open):
mock_open.side_effect = http_error(503, "")
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
with self.assertRaises(RuntimeError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertEqual(str(ctx.exception), "Gitea upstream unavailable")
self.assertEqual(ctx.exception.http_status, 503)
self.assertIn("HTTP 503", str(ctx.exception))
self.assertIn("upstream unavailable", str(ctx.exception))
@patch("gitea_auth.urllib.request.urlopen")
def test_malformed_error_payload_does_not_crash(self, mock_open):
# Non-JSON garbage error body must still yield a clean typed error
# with a fixed message (no body echo — #699).
# Non-JSON garbage error body must still yield a clean RuntimeError.
mock_open.side_effect = http_error(500, "<html>garbage</html>")
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
with self.assertRaises(RuntimeError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertEqual(str(ctx.exception), "Gitea HTTP request failed")
self.assertNotIn("<html>", str(ctx.exception))
self.assertIn("HTTP 500", str(ctx.exception))
@patch("gitea_auth.urllib.request.urlopen")
def test_malformed_success_json_raises_clean_error(self, mock_open):
@@ -131,17 +126,16 @@ class TestApiRequestFailures(unittest.TestCase):
def test_no_secret_leak_in_error_body(self, mock_open):
mock_open.side_effect = http_error(
400, "failed: token supersecret123 rejected")
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
with self.assertRaises(RuntimeError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
msg = str(ctx.exception)
self.assertNotIn("supersecret123", msg)
# Fixed message — body never appears (stronger than redaction).
self.assertEqual(msg, "Gitea HTTP request failed")
self.assertIn(gitea_audit.REDACTED, msg)
@patch("gitea_auth.urllib.request.urlopen")
def test_auth_header_never_in_error(self, mock_open):
mock_open.side_effect = http_error(400, "bad request")
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
with self.assertRaises(RuntimeError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertNotIn(FAKE_AUTH, str(ctx.exception))
+7 -8
View File
@@ -82,14 +82,13 @@ class TestPreflightIntegration(unittest.TestCase):
control_root = "/repo/Gitea-Tools"
with mock.patch.object(mcp_server, "PROJECT_ROOT", control_root):
with mock.patch.object(mcp_server, "_enforce_root_checkout_guard"):
with mock.patch("gitea_auth.get_profile", return_value={"profile_name": "gitea-author"}):
with mock.patch.dict(
"os.environ",
{"GITEA_TEST_PORCELAIN": ""},
clear=False,
):
with self.assertRaises(RuntimeError) as ctx:
mcp_server.verify_preflight_purity()
with mock.patch.dict(
"os.environ",
{"GITEA_TEST_PORCELAIN": ""},
clear=False,
):
with self.assertRaises(RuntimeError) as ctx:
mcp_server.verify_preflight_purity()
self.assertIn("Branches-only mutation guard", str(ctx.exception))
def test_verify_preflight_allows_branches_worktree(self):
-824
View File
@@ -1,824 +0,0 @@
"""Tests for control-plane DB substrate (#613)."""
from __future__ import annotations
import os
import tempfile
import threading
import unittest
from concurrent.futures import ThreadPoolExecutor, as_completed
from datetime import timedelta
from control_plane_db import (
ControlPlaneDB,
InvalidWorkKindError,
LeaseRequiredError,
WORK_KINDS,
_ts,
_utc_now,
)
class ControlPlaneDBTest(unittest.TestCase):
def setUp(self) -> None:
self._tmp = tempfile.TemporaryDirectory()
self.db_path = os.path.join(self._tmp.name, "cp.sqlite3")
self.db = ControlPlaneDB(self.db_path)
def tearDown(self) -> None:
self._tmp.cleanup()
def test_schema_and_architecture_meta(self) -> None:
import sqlite3
conn = sqlite3.connect(self.db_path)
try:
rows = dict(conn.execute("SELECT key, value FROM schema_meta").fetchall())
finally:
conn.close()
self.assertEqual(rows["schema_version"], "3")
self.assertIn("DB coordinates", rows["architecture"])
self.assertIn("bridge", rows["architecture"].lower())
def test_rejects_raw_incident_as_work_kind(self) -> None:
with self.assertRaises(InvalidWorkKindError):
self.db.upsert_work_item(
remote="prgs",
org="org",
repo="repo",
kind="sentry_incident",
number=1,
)
with self.assertRaises(InvalidWorkKindError):
self.db.assign_and_lease(
session_id="s1",
role="author",
remote="prgs",
org="org",
repo="repo",
kind="glitchtip_incident",
number=9,
)
self.assertEqual(WORK_KINDS, frozenset({"issue", "pr"}))
def test_atomic_assign_and_lease_fields(self) -> None:
self.db.upsert_session(session_id="s-a", role="author", profile="prgs-author")
result = self.db.assign_and_lease(
session_id="s-a",
role="author",
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
kind="issue",
number=613,
expected_head_sha="abc123",
allowed_actions=("implement", "comment"),
forbidden_actions=("approve", "merge"),
)
self.assertEqual(result.outcome, "assigned")
self.assertIsNotNone(result.assignment_id)
self.assertIsNotNone(result.lease_id)
self.assertEqual(result.role, "author")
self.assertEqual(result.work_kind, "issue")
self.assertEqual(result.work_number, 613)
self.assertEqual(result.expected_head_sha, "abc123")
self.assertIn("implement", result.allowed_actions)
self.assertIn("merge", result.forbidden_actions)
self.assertIsNotNone(result.expires_at)
def test_second_session_waits_on_foreign_lease(self) -> None:
self.db.upsert_session(session_id="s1", role="author")
self.db.upsert_session(session_id="s2", role="author")
first = self.db.assign_and_lease(
session_id="s1",
role="author",
remote="prgs",
org="o",
repo="r",
kind="pr",
number=100,
expected_head_sha="deadbeef",
)
self.assertEqual(first.outcome, "assigned")
second = self.db.assign_and_lease(
session_id="s2",
role="author",
remote="prgs",
org="o",
repo="r",
kind="pr",
number=100,
expected_head_sha="deadbeef",
)
self.assertEqual(second.outcome, "wait")
self.assertEqual(second.owner_session_id, "s1")
def test_owner_resume_refreshes_lease(self) -> None:
self.db.upsert_session(session_id="s1", role="reviewer")
a = self.db.assign_and_lease(
session_id="s1",
role="reviewer",
remote="prgs",
org="o",
repo="r",
kind="pr",
number=50,
expected_head_sha="head-50",
)
b = self.db.assign_and_lease(
session_id="s1",
role="reviewer",
remote="prgs",
org="o",
repo="r",
kind="pr",
number=50,
expected_head_sha="head-50",
)
self.assertEqual(b.outcome, "assigned")
self.assertEqual(b.lease_id, a.lease_id)
self.assertIn("owner-resume", b.reason)
def test_require_valid_assignment_gates_mutations(self) -> None:
self.db.upsert_session(session_id="s1", role="author")
self.db.assign_and_lease(
session_id="s1",
role="author",
remote="prgs",
org="o",
repo="r",
kind="issue",
number=7,
allowed_actions=("implement",),
forbidden_actions=("merge",),
)
proof = self.db.require_valid_assignment(
session_id="s1",
remote="prgs",
org="o",
repo="r",
kind="issue",
number=7,
action="implement",
)
self.assertEqual(proof["session_id"], "s1")
with self.assertRaises(LeaseRequiredError):
self.db.require_valid_assignment(
session_id="s1",
remote="prgs",
org="o",
repo="r",
kind="issue",
number=7,
action="merge",
)
with self.assertRaises(LeaseRequiredError):
self.db.require_valid_assignment(
session_id="s-other",
remote="prgs",
org="o",
repo="r",
kind="issue",
number=7,
action="implement",
)
def test_expired_lease_allows_reassign(self) -> None:
self.db.upsert_session(session_id="s1", role="author")
self.db.upsert_session(session_id="s2", role="author")
past = _utc_now() - timedelta(hours=1)
# Create lease already expired by using negative TTL edge via direct assign then expire
assigned = self.db.assign_and_lease(
session_id="s1",
role="author",
remote="prgs",
org="o",
repo="r",
kind="issue",
number=3,
lease_ttl_seconds=1,
)
self.assertEqual(assigned.outcome, "assigned")
# Force expiry in DB
import sqlite3
conn = sqlite3.connect(self.db_path)
try:
conn.execute(
"UPDATE leases SET expires_at = ? WHERE lease_id = ?",
(_ts(past), assigned.lease_id),
)
conn.commit()
finally:
conn.close()
n = self.db.expire_stale_leases()
self.assertGreaterEqual(n, 1)
second = self.db.assign_and_lease(
session_id="s2",
role="author",
remote="prgs",
org="o",
repo="r",
kind="issue",
number=3,
)
self.assertEqual(second.outcome, "assigned")
self.assertEqual(second.session_id, "s2")
def test_merged_work_never_assigned(self) -> None:
self.db.upsert_session(session_id="s1", role="merger")
self.db.upsert_work_item(
remote="prgs",
org="o",
repo="r",
kind="pr",
number=99,
state="merged",
)
result = self.db.assign_and_lease(
session_id="s1",
role="merger",
remote="prgs",
org="o",
repo="r",
kind="pr",
number=99,
expected_head_sha="merged-head",
)
self.assertEqual(result.outcome, "no_safe_work")
def test_four_concurrent_sessions_unique_assignments(self) -> None:
"""Four concurrent assigners on four different issues — all succeed uniquely.
Also two concurrent assigners on the *same* issue: at most one assigned.
"""
for i in range(4):
self.db.upsert_session(session_id=f"sess-{i}", role="author")
def claim_unique(i: int):
return self.db.assign_and_lease(
session_id=f"sess-{i}",
role="author",
remote="prgs",
org="o",
repo="r",
kind="issue",
number=1000 + i,
)
with ThreadPoolExecutor(max_workers=4) as pool:
results = [f.result() for f in as_completed([pool.submit(claim_unique, i) for i in range(4)])]
self.assertEqual({r.outcome for r in results}, {"assigned"})
numbers = sorted(r.work_number for r in results)
self.assertEqual(numbers, [1000, 1001, 1002, 1003])
# Contention on one item
self.db.upsert_session(session_id="c1", role="author")
self.db.upsert_session(session_id="c2", role="author")
self.db.upsert_session(session_id="c3", role="author")
self.db.upsert_session(session_id="c4", role="author")
barrier = threading.Barrier(4)
outcomes: list[str] = []
lock = threading.Lock()
def contend(sid: str) -> None:
barrier.wait()
res = self.db.assign_and_lease(
session_id=sid,
role="author",
remote="prgs",
org="o",
repo="r",
kind="issue",
number=7777,
)
with lock:
outcomes.append(res.outcome)
threads = [threading.Thread(target=contend, args=(f"c{i}",)) for i in range(1, 5)]
for t in threads:
t.start()
for t in threads:
t.join()
self.assertEqual(outcomes.count("assigned"), 1)
self.assertEqual(outcomes.count("wait"), 3)
def test_terminal_lock_index(self) -> None:
self.db.set_terminal_lock(
remote="prgs",
org="o",
repo="r",
terminal_pr=332,
review_id="rev-1",
decision="approve",
)
row = self.db.get_active_terminal_lock(remote="prgs", org="o", repo="r")
self.assertIsNotNone(row)
assert row is not None
self.assertEqual(row["terminal_pr"], 332)
self.assertEqual(row["status"], "active")
def test_incident_links_not_work_items(self) -> None:
link = self.db.upsert_incident_link(
provider="sentry",
provider_base_url="https://sentry.prgs.cc",
provider_org="prgs",
provider_project="gitea-tools-mcp",
provider_issue_id="12345",
gitea_org="Scaled-Tech-Consulting",
gitea_repo="Gitea-Tools",
gitea_issue_number=9001,
fingerprint="fp-1",
)
self.assertEqual(link["gitea_issue_number"], 9001)
found = self.db.get_incident_link_for_gitea_issue(
gitea_org="Scaled-Tech-Consulting",
gitea_repo="Gitea-Tools",
gitea_issue_number=9001,
)
self.assertIsNotNone(found)
# Linking does not create a work_item of incident kind
with self.assertRaises(InvalidWorkKindError):
self.db.upsert_work_item(
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
kind="sentry",
number=12345,
)
def test_heartbeat_and_release(self) -> None:
self.db.upsert_session(session_id="s1", role="author")
a = self.db.assign_and_lease(
session_id="s1",
role="author",
remote="prgs",
org="o",
repo="r",
kind="issue",
number=1,
)
hb = self.db.heartbeat_lease(a.lease_id, session_id="s1")
self.assertEqual(hb["lease_id"], a.lease_id)
self.db.release_lease(a.lease_id, session_id="s1")
# After release another session can claim
self.db.upsert_session(session_id="s2", role="author")
b = self.db.assign_and_lease(
session_id="s2",
role="author",
remote="prgs",
org="o",
repo="r",
kind="issue",
number=1,
)
self.assertEqual(b.outcome, "assigned")
self.assertEqual(b.session_id, "s2")
def test_require_valid_assignment_rejects_stale_head(self) -> None:
"""Assignment must not authorize mutations after work-item head drifts."""
self.db.upsert_session(session_id="s1", role="author")
self.db.assign_and_lease(
session_id="s1",
role="author",
remote="prgs",
org="o",
repo="r",
kind="pr",
number=42,
expected_head_sha="head-v1",
allowed_actions=("implement",),
)
# Head drifts after assignment
self.db.upsert_work_item(
remote="prgs",
org="o",
repo="r",
kind="pr",
number=42,
current_head_sha="head-v2",
)
with self.assertRaises(LeaseRequiredError) as ctx:
self.db.require_valid_assignment(
session_id="s1",
remote="prgs",
org="o",
repo="r",
kind="pr",
number=42,
action="implement",
)
self.assertIn("stale head", str(ctx.exception).lower())
def test_require_valid_assignment_rejects_terminal_state(self) -> None:
"""Assignment must not authorize mutations after work item is merged/closed."""
self.db.upsert_session(session_id="s1", role="author")
self.db.assign_and_lease(
session_id="s1",
role="author",
remote="prgs",
org="o",
repo="r",
kind="pr",
number=55,
expected_head_sha="abc",
allowed_actions=("implement",),
)
self.db.upsert_work_item(
remote="prgs",
org="o",
repo="r",
kind="pr",
number=55,
state="merged",
current_head_sha="abc",
)
with self.assertRaises(LeaseRequiredError) as ctx:
self.db.require_valid_assignment(
session_id="s1",
remote="prgs",
org="o",
repo="r",
kind="pr",
number=55,
action="implement",
)
self.assertIn("terminal", str(ctx.exception).lower())
self.db.upsert_work_item(
remote="prgs",
org="o",
repo="r",
kind="issue",
number=56,
state="open",
)
self.db.assign_and_lease(
session_id="s1",
role="author",
remote="prgs",
org="o",
repo="r",
kind="issue",
number=56,
allowed_actions=("implement",),
)
self.db.upsert_work_item(
remote="prgs",
org="o",
repo="r",
kind="issue",
number=56,
state="closed",
)
with self.assertRaises(LeaseRequiredError):
self.db.require_valid_assignment(
session_id="s1",
remote="prgs",
org="o",
repo="r",
kind="issue",
number=56,
action="implement",
)
def test_pr_assignment_requires_expected_head_sha(self) -> None:
"""PR assign and mutation must fail closed without a head pin."""
self.db.upsert_session(session_id="s1", role="author")
with self.assertRaises(LeaseRequiredError) as ctx:
self.db.assign_and_lease(
session_id="s1",
role="author",
remote="prgs",
org="o",
repo="r",
kind="pr",
number=88,
expected_head_sha=None,
allowed_actions=("implement",),
)
self.assertIn("expected_head_sha", str(ctx.exception))
# Legacy path: force an unpinned PR assignment into the DB, then
# populate head and prove mutation is still rejected.
import sqlite3
self.db.upsert_work_item(
remote="prgs",
org="o",
repo="r",
kind="pr",
number=89,
current_head_sha=None,
)
conn = sqlite3.connect(self.db_path)
try:
wid = conn.execute(
"SELECT work_item_id FROM work_items WHERE kind='pr' AND number=89"
).fetchone()[0]
conn.execute(
"""
INSERT INTO sessions(session_id, role, started_at, last_heartbeat_at, status)
VALUES ('legacy', 'author', '2020-01-01T00:00:00Z', '2020-01-01T00:00:00Z', 'active')
"""
)
conn.execute(
"""
INSERT INTO leases(
lease_id, work_item_id, session_id, role, phase,
expires_at, heartbeat_at, status
) VALUES (
'lease-legacy', ?, 'legacy', 'author', 'claimed',
'2099-01-01T00:00:00Z', '2020-01-01T00:00:00Z', 'active'
)
""",
(wid,),
)
conn.execute(
"""
INSERT INTO assignments(
assignment_id, work_item_id, session_id, lease_id,
allowed_actions, forbidden_actions, expected_head_sha,
role, status, created_at
) VALUES (
'asn-legacy', ?, 'legacy', 'lease-legacy',
'["implement"]', '["merge"]', NULL,
'author', 'active', '2020-01-01T00:00:00Z'
)
""",
(wid,),
)
conn.commit()
finally:
conn.close()
self.db.upsert_work_item(
remote="prgs",
org="o",
repo="r",
kind="pr",
number=89,
current_head_sha="populated-head",
)
with self.assertRaises(LeaseRequiredError) as ctx2:
self.db.require_valid_assignment(
session_id="legacy",
remote="prgs",
org="o",
repo="r",
kind="pr",
number=89,
action="implement",
)
self.assertIn("expected_head_sha pin", str(ctx2.exception))
def test_migrate_duplicate_null_scope_incident_links(self) -> None:
"""Legacy NULL-scope duplicates must migrate without UNIQUE crash."""
import sqlite3
from control_plane_db import ControlPlaneDB, ControlPlaneError
# Build a v1-like table with nullable scope columns and insert dups
# that collapse under normalization, then open ControlPlaneDB on it.
path = os.path.join(self._tmp.name, "legacy_dups.sqlite3")
conn = sqlite3.connect(path)
try:
conn.executescript(
"""
CREATE TABLE schema_meta (key TEXT PRIMARY KEY, value TEXT NOT NULL);
CREATE TABLE incident_links (
link_id INTEGER PRIMARY KEY AUTOINCREMENT,
provider TEXT NOT NULL,
provider_base_url TEXT,
provider_org TEXT,
provider_project TEXT,
provider_issue_id TEXT NOT NULL,
provider_short_id TEXT,
provider_permalink TEXT,
fingerprint TEXT,
gitea_org TEXT NOT NULL,
gitea_repo TEXT NOT NULL,
gitea_issue_number INTEGER NOT NULL,
linked_pr_numbers TEXT,
first_seen TEXT,
last_seen TEXT,
event_count INTEGER,
status TEXT NOT NULL DEFAULT 'open',
release_resolved_at TEXT,
last_sync_at TEXT,
UNIQUE (
provider, provider_base_url, provider_org,
provider_project, provider_issue_id
)
);
INSERT INTO incident_links(
provider, provider_base_url, provider_org, provider_project,
provider_issue_id, gitea_org, gitea_repo, gitea_issue_number, status
) VALUES
('sentry', NULL, NULL, NULL, 'dup-1', 'org', 'repo', 10, 'open'),
('sentry', NULL, NULL, NULL, 'dup-1', 'org', 'repo', 10, 'open');
"""
)
# SQLite allows two NULL-scope rows with same provider/issue under UNIQUE.
n = conn.execute("SELECT COUNT(*) FROM incident_links").fetchone()[0]
self.assertEqual(n, 2)
conn.commit()
finally:
conn.close()
db = ControlPlaneDB(path)
conn2 = sqlite3.connect(path)
try:
n2 = conn2.execute("SELECT COUNT(*) FROM incident_links").fetchone()[0]
rows = conn2.execute(
"SELECT provider_base_url, provider_org, provider_project, gitea_issue_number "
"FROM incident_links"
).fetchall()
finally:
conn2.close()
self.assertEqual(n2, 1)
self.assertEqual(rows[0][0], "")
self.assertEqual(rows[0][1], "")
self.assertEqual(rows[0][2], "")
self.assertEqual(rows[0][3], 10)
# Touch to silence unused import in type checkers if needed
self.assertTrue(issubclass(ControlPlaneError, Exception))
del db
def test_migrate_conflicting_duplicate_incident_links_fails_closed(self) -> None:
"""Conflicting Gitea targets for the same provider key must fail closed."""
import sqlite3
from control_plane_db import ControlPlaneDB, ControlPlaneError
path = os.path.join(self._tmp.name, "legacy_conflict.sqlite3")
conn = sqlite3.connect(path)
try:
conn.executescript(
"""
CREATE TABLE incident_links (
link_id INTEGER PRIMARY KEY AUTOINCREMENT,
provider TEXT NOT NULL,
provider_base_url TEXT,
provider_org TEXT,
provider_project TEXT,
provider_issue_id TEXT NOT NULL,
gitea_org TEXT NOT NULL,
gitea_repo TEXT NOT NULL,
gitea_issue_number INTEGER NOT NULL,
status TEXT NOT NULL DEFAULT 'open',
UNIQUE (
provider, provider_base_url, provider_org,
provider_project, provider_issue_id
)
);
INSERT INTO incident_links(
provider, provider_base_url, provider_org, provider_project,
provider_issue_id, gitea_org, gitea_repo, gitea_issue_number
) VALUES
('sentry', NULL, NULL, NULL, 'dup-c', 'org', 'repo', 1),
('sentry', NULL, NULL, NULL, 'dup-c', 'org', 'repo', 2);
"""
)
conn.commit()
finally:
conn.close()
with self.assertRaises(ControlPlaneError) as ctx:
ControlPlaneDB(path)
self.assertIn("conflicting", str(ctx.exception).lower())
def test_migrate_conflicting_observation_metadata_fails_closed(self) -> None:
"""Same provider key + same Gitea target but differing obs metadata must fail closed.
Regression for silent data loss: migration used to keep lowest link_id and
delete peers after comparing only Gitea targets (#619 RC3).
"""
import sqlite3
from control_plane_db import ControlPlaneDB, ControlPlaneError
path = os.path.join(self._tmp.name, "legacy_meta_conflict.sqlite3")
conn = sqlite3.connect(path)
try:
conn.executescript(
"""
CREATE TABLE schema_meta (key TEXT PRIMARY KEY, value TEXT NOT NULL);
CREATE TABLE incident_links (
link_id INTEGER PRIMARY KEY AUTOINCREMENT,
provider TEXT NOT NULL,
provider_base_url TEXT,
provider_org TEXT,
provider_project TEXT,
provider_issue_id TEXT NOT NULL,
provider_short_id TEXT,
provider_permalink TEXT,
fingerprint TEXT,
gitea_org TEXT NOT NULL,
gitea_repo TEXT NOT NULL,
gitea_issue_number INTEGER NOT NULL,
linked_pr_numbers TEXT,
first_seen TEXT,
last_seen TEXT,
event_count INTEGER,
status TEXT NOT NULL DEFAULT 'open',
release_resolved_at TEXT,
last_sync_at TEXT,
UNIQUE (
provider, provider_base_url, provider_org,
provider_project, provider_issue_id
)
);
INSERT INTO incident_links(
provider, provider_base_url, provider_org, provider_project,
provider_issue_id, provider_permalink, fingerprint,
gitea_org, gitea_repo, gitea_issue_number,
event_count, status, first_seen, last_seen
) VALUES
(
'sentry', NULL, NULL, NULL, 'dup-meta',
'https://sentry.example/issues/1', 'fingerprint-A',
'org', 'repo', 42,
1, 'open', '2026-01-01T00:00:00Z', '2026-01-01T01:00:00Z'
),
(
'sentry', NULL, NULL, NULL, 'dup-meta',
'https://sentry.example/issues/1', 'fingerprint-B',
'org', 'repo', 42,
99, 'resolved', '2026-01-01T00:00:00Z', '2026-01-02T00:00:00Z'
);
"""
)
n = conn.execute("SELECT COUNT(*) FROM incident_links").fetchone()[0]
self.assertEqual(n, 2)
conn.commit()
finally:
conn.close()
with self.assertRaises(ControlPlaneError) as ctx:
ControlPlaneDB(path)
msg = str(ctx.exception).lower()
self.assertIn("conflicting", msg)
self.assertIn("observation metadata", msg)
# Rows must still be present — migration must not delete before failing.
conn2 = sqlite3.connect(path)
try:
remaining = conn2.execute("SELECT COUNT(*) FROM incident_links").fetchone()[0]
fps = {
r[0]
for r in conn2.execute(
"SELECT fingerprint FROM incident_links ORDER BY link_id"
).fetchall()
}
finally:
conn2.close()
self.assertEqual(remaining, 2)
self.assertEqual(fps, {"fingerprint-A", "fingerprint-B"})
def test_incident_links_minimal_upsert_is_canonical(self) -> None:
"""Repeated minimal upserts must update one row (NULL-safe uniqueness)."""
a = self.db.upsert_incident_link(
provider="sentry",
provider_issue_id="inc-1",
gitea_org="org",
gitea_repo="repo",
gitea_issue_number=1,
)
b = self.db.upsert_incident_link(
provider="sentry",
provider_issue_id="inc-1",
gitea_org="org",
gitea_repo="repo",
gitea_issue_number=2,
# omit optional scope fields again
)
c = self.db.upsert_incident_link(
provider="sentry",
provider_issue_id="inc-1",
gitea_org="org",
gitea_repo="repo",
gitea_issue_number=3,
provider_base_url=None,
provider_org="",
provider_project=" ",
)
self.assertEqual(a["link_id"], b["link_id"])
self.assertEqual(b["link_id"], c["link_id"])
self.assertEqual(c["gitea_issue_number"], 3)
self.assertEqual(c["provider_base_url"], "")
self.assertEqual(c["provider_org"], "")
self.assertEqual(c["provider_project"], "")
import sqlite3
conn = sqlite3.connect(self.db_path)
try:
n = conn.execute(
"SELECT COUNT(*) FROM incident_links WHERE provider_issue_id = ?",
("inc-1",),
).fetchone()[0]
finally:
conn.close()
self.assertEqual(n, 1)
if __name__ == "__main__":
unittest.main()
@@ -1,113 +0,0 @@
"""Controller-closure baseline-proof gate tests (#529, criterion 6)."""
import unittest
from controller_closure_baseline_proof import (
assess_controller_closure_baseline_proof,
)
from premerge_baseline_proof import (
CLEAN_PASS,
PREMERGE_BASELINE_PROVEN_FAILURE,
UNRESOLVED_REGRESSION_RISK,
)
from final_report_validator import assess_final_report_validator
# Complete pre-merge proof fields for a baseline claim (see #533).
_PROOF_FIELDS = (
"Pre-merge base commit: 1a2b3c4d5e6f7a8b9c0d1e2f3a4b5c6d7e8f9a0b\n"
"Tested commit: 1a2b3c4d5e6f7a8b9c0d1e2f3a4b5c6d7e8f9a0b\n"
"Command: venv/bin/python -m pytest tests/test_foo.py -q\n"
"Exit status: 1\n"
"Failure signature: AssertionError: None is not true\n"
)
class TestControllerClosureBaselineProof(unittest.TestCase):
def test_empty_report_skipped_and_allowed(self):
result = assess_controller_closure_baseline_proof("")
self.assertFalse(result["block"])
self.assertTrue(result["skipped"])
self.assertEqual(result["label"], CLEAN_PASS)
def test_none_report_allowed(self):
result = assess_controller_closure_baseline_proof(None)
self.assertFalse(result["block"])
self.assertTrue(result["skipped"])
def test_clean_pass_closure_allowed(self):
result = assess_controller_closure_baseline_proof(
"Closing #529. Validation: full suite passed, exit status 0. Clean pass."
)
self.assertFalse(result["block"])
self.assertEqual(result["label"], CLEAN_PASS)
def test_expected_preexisting_failure_without_proof_blocked(self):
report = (
"Closing #529. Full suite: 1 failed. This is an expected "
"pre-existing failure, safe to close."
)
result = assess_controller_closure_baseline_proof(report)
self.assertTrue(result["block"])
self.assertFalse(result["proven"])
self.assertEqual(result["label"], UNRESOLVED_REGRESSION_RISK)
self.assertTrue(result["reasons"])
self.assertTrue(result["safe_next_action"])
def test_current_master_reproduction_only_blocked(self):
report = (
"Closing #529. Full suite: 1 failed. Pre-existing baseline failure — "
"reproduced on current master after merge.\n"
"Command: venv/bin/python -m pytest tests/test_foo.py -q\n"
"Exit status: 1\n"
"Failure signature: AssertionError: None is not true\n"
)
result = assess_controller_closure_baseline_proof(report)
self.assertTrue(result["block"])
def test_proven_baseline_closure_allowed(self):
report = (
"Closing #529. Full suite: 1 failed, an expected pre-existing "
"baseline failure proven on the PR pre-merge base commit.\n"
+ _PROOF_FIELDS
)
result = assess_controller_closure_baseline_proof(report)
self.assertFalse(result["block"])
self.assertEqual(result["label"], PREMERGE_BASELINE_PROVEN_FAILURE)
class TestControllerCloseTaskKind(unittest.TestCase):
"""The composable validator must cover the controller_close task kind."""
def test_controller_close_blocks_unproven_baseline(self):
report = (
"Full suite: 1 failed. Expected pre-existing failure, closing the "
"tracking issue."
)
result = assess_final_report_validator(report, "controller_close")
self.assertTrue(result["blocked"])
self.assertTrue(
any(
"premerge_baseline_proof" in f["rule_id"]
for f in result["findings"]
)
)
def test_controller_close_alias_close_issue(self):
report = (
"Full suite: 1 failed. Expected pre-existing failure, closing the "
"tracking issue."
)
result = assess_final_report_validator(report, "close_issue")
self.assertTrue(result["blocked"])
def test_controller_close_allows_proven_baseline(self):
report = (
"Full suite: 1 failed, expected pre-existing baseline failure proven "
"on the PR pre-merge base commit.\n" + _PROOF_FIELDS
)
result = assess_final_report_validator(report, "controller_close")
self.assertFalse(result["blocked"])
if __name__ == "__main__":
unittest.main()
+11 -44
View File
@@ -11,11 +11,7 @@ import gitea_mcp_server as srv
FAKE_AUTH = {"Authorization": "token test-token"}
# Stable control checkout (parent of branches/), not the MCP server worktree root.
current_file_path = Path(__file__).resolve()
if "branches" in current_file_path.parts:
CONTROL_CHECKOUT_ROOT = str(current_file_path.parents[3])
else:
CONTROL_CHECKOUT_ROOT = str(current_file_path.parents[1])
CONTROL_CHECKOUT_ROOT = str(Path(__file__).resolve().parents[3])
PROJECT_ROOT = srv.PROJECT_ROOT
@@ -57,23 +53,9 @@ class TestCreateIssueWorkspaceGuard(unittest.TestCase):
# Without worktree_path/env hints, workspace resolves to PROJECT_ROOT. When that
# path is the stable control checkout (not under branches/), mutation must fail.
with patch.object(srv, "PROJECT_ROOT", CONTROL_CHECKOUT_ROOT):
try:
res = srv.gitea_create_issue(title="Test issue", body="body text")
except RuntimeError as exc:
self.assertIn("stable control checkout", str(exc))
else:
# #683: production guards return typed blockers at entrypoints
self.assertFalse(res.get("success"))
self.assertFalse(res.get("performed"))
blob = " ".join(res.get("reasons") or []) + " " + str(
res.get("blocker_kind") or ""
)
self.assertTrue(
"stable control checkout" in blob
or "missing_issue_worktree" in blob
or "control checkout" in blob.lower()
)
self.assertTrue(res.get("exact_next_action"))
with self.assertRaises(RuntimeError) as ctx:
srv.gitea_create_issue(title="Test issue", body="body text")
self.assertIn("stable control checkout", str(ctx.exception))
@patch("gitea_mcp_server._auth", return_value=FAKE_AUTH)
@patch("gitea_mcp_server._profile_permission_block", return_value=None)
@@ -119,17 +101,11 @@ class TestCreateIssueWorkspaceGuard(unittest.TestCase):
)
with patch.object(srv, "PROJECT_ROOT", CONTROL_CHECKOUT_ROOT):
try:
res = srv.gitea_create_issue(
with self.assertRaises(RuntimeError) as ctx:
srv.gitea_create_issue(
title="Test issue", body="body", worktree_path=missing_path
)
except RuntimeError as exc:
self.assertIn("does not exist", str(exc))
else:
self.assertFalse(res.get("success"))
blob = " ".join(res.get("reasons") or [])
self.assertIn("does not exist", blob)
self.assertTrue(res.get("exact_next_action") or res.get("reasons"))
self.assertIn("does not exist (fail closed)", str(ctx.exception))
@patch("gitea_mcp_server._auth", return_value=FAKE_AUTH)
@patch("gitea_mcp_server._profile_permission_block", return_value=None)
@@ -162,20 +138,11 @@ class TestCreateIssueWorkspaceGuard(unittest.TestCase):
with patch.object(srv, "PROJECT_ROOT", CONTROL_CHECKOUT_ROOT):
with patch("gitea_mcp_server._get_workspace_porcelain", return_value=""):
try:
res = srv.gitea_create_issue(
title="Test issue",
body="body",
worktree_path=wrong_repo_path,
with self.assertRaises(RuntimeError) as ctx:
srv.gitea_create_issue(
title="Test issue", body="body", worktree_path=wrong_repo_path
)
except RuntimeError as exc:
self.assertIn(
"does not belong to the target repository", str(exc)
)
else:
self.assertFalse(res.get("success"))
blob = " ".join(res.get("reasons") or [])
self.assertIn("does not belong to the target repository", blob)
self.assertIn("does not belong to the target repository", str(ctx.exception))
@patch("gitea_mcp_server._auth", return_value=FAKE_AUTH)
@patch("gitea_mcp_server._profile_permission_block", return_value=None)
-97
View File
@@ -781,103 +781,6 @@ class TestMergePrRules(unittest.TestCase):
self.assertEqual(result["grade"], "A")
self.assertFalse(result["blocked"])
def test_manual_seeded_lease_claim_blocks_without_mcp_evidence(self):
lines = [
"## Controller Handoff",
"",
"- Task: merge PR #203",
"- Repo: Scaled-Tech-Consulting/Gitea-Tools",
"- Role: merger",
"- Identity: sysadmin / prgs-merger",
"- Issue/PR: #182 / PR #203",
"- Branch/SHA: feat/x @ 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
"- Files changed: review_proofs.py",
"- Validation: pytest in branches/review-203",
"- Mutations: merge completed",
"- File edits by reviewer: none",
"- Worktree/index mutations: none",
"- Git ref mutations: git fetch prgs master",
"- MCP/Gitea mutations: merge completed",
"- Review mutations: none",
"- Merge mutations: merged using manually seeded lease proof",
"- Cleanup mutations: none",
"- External-state mutations: none",
"- Read-only diagnostics: metadata check",
"- Current status: PR merged",
"- Blockers: none",
"- Next: none",
"- Safety: review and merge are separate roles",
"- Selected PR: #203",
"- Pinned reviewed head: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
"- Reviewed head SHA: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
"- Final live head SHA before approval: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
"- Final live head SHA before merge: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
"- Push occurred during validation: no",
"- Active profile: prgs-merger",
"- Role kind: merger",
"- Merge capability source: profile",
"- Explicit operator authorization: MERGE PR 203",
"- Expected head SHA: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
"- Approval at current head: yes",
"- Merge result: PR merged successfully",
"- Cleanup status: complete",
]
report = "\n".join(lines)
result = assess_final_report_validator(report, "merge_pr")
self.assertTrue(result["blocked"])
codes = {f.get("rule_id") for f in result.get("findings") or []}
self.assertIn("shared.manual_lease_proof_handoff", codes)
def test_manual_seeded_claim_allowed_when_adoption_cited(self):
lines = [
"## Controller Handoff",
"",
"- Task: merge PR #203",
"- Repo: Scaled-Tech-Consulting/Gitea-Tools",
"- Role: merger",
"- Identity: sysadmin / prgs-merger",
"- Issue/PR: #182 / PR #203",
"- Branch/SHA: feat/x @ 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
"- Files changed: review_proofs.py",
"- Validation: pytest in branches/review-203",
"- Mutations: merge completed",
"- File edits by reviewer: none",
"- Worktree/index mutations: none",
"- Git ref mutations: git fetch prgs master",
"- MCP/Gitea mutations: gitea_adopt_merger_pr_lease then merge",
"- Review mutations: none",
"- Merge mutations: historical manual seed replaced by sanctioned adoption",
"- Cleanup mutations: none",
"- External-state mutations: none",
"- Read-only diagnostics: metadata check",
"- Current status: PR merged",
"- Blockers: none",
"- Next: none",
"- Safety: review and merge are separate roles",
"- Selected PR: #203",
"- Pinned reviewed head: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
"- Reviewed head SHA: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
"- Final live head SHA before approval: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
"- Final live head SHA before merge: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
"- Push occurred during validation: no",
"- Active profile: prgs-merger",
"- Role kind: merger",
"- Merge capability source: profile",
"- Explicit operator authorization: MERGE PR 203",
"- Expected head SHA: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
"- Approval at current head: yes",
"- lease_proof_source: gitea_adopt_merger_pr_lease",
"- lease_proof_kind: sanctioned_adoption",
"- adoption_comment_id: 8288",
"- Merge result: PR merged successfully",
"- Cleanup status: complete",
]
report = "\n".join(lines)
result = assess_final_report_validator(report, "merge_pr")
self.assertFalse(result["blocked"])
codes = {f.get("rule_id") for f in result.get("findings") or []}
self.assertNotIn("shared.manual_lease_proof_handoff", codes)
def test_missing_merger_fields_blocks(self):
lines = [
"## Controller Handoff",
@@ -1,397 +0,0 @@
"""Head-scoped #332 review-decision locks (#620).
Proves:
* REQUEST_CHANGES on head A does not block mark_ready/submit on head B
* APPROVE on head B is allowed after RC on head A (same open PR)
* same-head duplicate terminal remains blocked
* open-PR cleanup remains forbidden; assessment reports stale_by_head
* historical mutations keep their head_sha (preserved ledger)
* PR #619-style: old RC at 036b78e…, current head 2429d9d…, approve allowed
"""
from __future__ import annotations
import os
import unittest
from unittest.mock import patch
import mcp_server
import stale_review_decision_lock as srdl
HEAD_A = "036b78e31ea5d036452b3a52e0e086b01e0c763f"
HEAD_B = "2429d9d2e826e519eb8eb4ade45987c00838aefb"
HEAD_C = "c" * 40
def _lock(mutations=None, correction=False, ready_pr=None, ready_head=None, ready_action=None):
return {
"task": "review_pr",
"remote": "prgs",
"org": "Scaled-Tech-Consulting",
"repo": "Gitea-Tools",
"session_pid": os.getpid(),
"session_profile": "prgs-reviewer",
"session_profile_lock": "prgs-reviewer",
"profile_identity": "prgs-reviewer",
"final_review_decision_ready": False,
"ready_pr_number": ready_pr,
"ready_action": ready_action,
"ready_expected_head_sha": ready_head,
"ready_remote": "prgs" if ready_pr else None,
"ready_org": "Scaled-Tech-Consulting" if ready_pr else None,
"ready_repo": "Gitea-Tools" if ready_pr else None,
"live_mutations": list(mutations or []),
"correction_authorized": correction,
"correction_reason": None,
}
RC_619_LEGACY = {
"pr_number": 619,
"action": "request_changes",
"review_id": 410,
"review_state": "request_changes",
# no head_sha — pre-#620 durable ledger shape
}
RC_619_HEAD_A = {
"pr_number": 619,
"action": "request_changes",
"review_id": 410,
"review_state": "request_changes",
"head_sha": HEAD_A,
}
APPROVE_619_HEAD_B = {
"pr_number": 619,
"action": "approve",
"review_id": 411,
"review_state": "approve",
"head_sha": HEAD_B,
}
def _seed(mutations=None, **kwargs):
import review_workflow_load
review_workflow_load.record_review_workflow_load(mcp_server.PROJECT_ROOT)
mcp_server._save_review_decision_lock(_lock(mutations, **kwargs))
mcp_server.gitea_load_review_workflow()
def _open_pr(pr_number=619, head=HEAD_B):
return {
"number": pr_number,
"state": "open",
"merged": False,
"merged_at": None,
"head": {"sha": head},
}
def _no_lease():
return {"block": False, "reasons": [], "mutation_allowed": True}
def _feedback(blocking=False, stale=False, success=True):
return {
"success": success,
"has_blocking_change_requests": blocking,
"review_feedback_stale": stale,
"current_head_sha": HEAD_B,
}
class TestPureHeadScopeHelpers(unittest.TestCase):
def test_mutation_head_prefers_recorded_sha(self):
m = {"pr_number": 1, "head_sha": HEAD_A}
self.assertEqual(srdl.mutation_head_sha(m), HEAD_A)
def test_legacy_mutation_uses_ready_expected_for_same_pr(self):
lock = _lock(
[RC_619_LEGACY],
ready_pr=619,
ready_head=HEAD_A,
ready_action="request_changes",
)
self.assertEqual(srdl.mutation_head_sha(RC_619_LEGACY, lock), HEAD_A)
def test_legacy_mutation_ignores_ready_for_other_pr(self):
lock = _lock([RC_619_LEGACY], ready_pr=1, ready_head=HEAD_A)
self.assertIsNone(srdl.mutation_head_sha(RC_619_LEGACY, lock))
def test_prior_blocks_same_head_not_other_head(self):
lock = _lock([RC_619_HEAD_A])
self.assertTrue(
srdl.prior_live_mutations_block_boundary(
lock, pr_number=619, expected_head_sha=HEAD_A
)
)
self.assertFalse(
srdl.prior_live_mutations_block_boundary(
lock, pr_number=619, expected_head_sha=HEAD_B
)
)
def test_backfill_stamps_legacy_terminals(self):
lock = _lock(
[dict(RC_619_LEGACY)],
ready_pr=619,
ready_head=HEAD_A,
ready_action="request_changes",
)
srdl.backfill_terminal_heads_from_ready(lock)
self.assertEqual(lock["live_mutations"][0]["head_sha"], HEAD_A)
class TestHardStopHeadScope(unittest.TestCase):
def tearDown(self):
mcp_server._save_review_decision_lock(None)
mcp_server.review_workflow_load.clear_review_workflow_load()
def test_rc_head_a_allows_mark_ready_head_b(self):
_seed(
[RC_619_HEAD_A],
ready_pr=619,
ready_head=HEAD_A,
ready_action="request_changes",
)
self.assertEqual(
mcp_server.terminal_review_hard_stop_reasons(
619, "mark_ready", expected_head_sha=HEAD_B
),
[],
)
def test_rc_head_a_blocks_mark_ready_same_head(self):
_seed(
[RC_619_HEAD_A],
ready_pr=619,
ready_head=HEAD_A,
ready_action="request_changes",
)
reasons = mcp_server.terminal_review_hard_stop_reasons(
619, "mark_ready", expected_head_sha=HEAD_A
)
self.assertTrue(reasons)
self.assertIn("#332", reasons[0])
def test_rc_head_a_blocks_other_pr(self):
_seed([RC_619_HEAD_A], ready_pr=619, ready_head=HEAD_A)
reasons = mcp_server.terminal_review_hard_stop_reasons(
700, "mark_ready", expected_head_sha=HEAD_B
)
self.assertTrue(reasons)
def test_legacy_619_ledger_allows_new_head(self):
"""PR #619-style durable lock without mutation head_sha."""
_seed(
[RC_619_LEGACY],
ready_pr=619,
ready_head=HEAD_A,
ready_action="request_changes",
)
self.assertEqual(
mcp_server.terminal_review_hard_stop_reasons(
619, "mark_ready", expected_head_sha=HEAD_B
),
[],
)
class TestMarkFinalAndRecord(unittest.TestCase):
def tearDown(self):
mcp_server._save_review_decision_lock(None)
mcp_server.review_workflow_load.clear_review_workflow_load()
def _mark(self, pr, action, head, feedback=None):
with patch("mcp_server._list_pr_lease_comments", return_value=[]), patch(
"mcp_server._pr_work_lease_reviewer_block", return_value=_no_lease()
), patch.object(
mcp_server,
"gitea_get_pr_review_feedback",
return_value=feedback or _feedback(blocking=False, stale=True),
), patch.object(
mcp_server,
"gitea_check_pr_eligibility",
return_value={"eligible": True, "head_sha": head},
):
return mcp_server.gitea_mark_final_review_decision(
pr_number=pr,
action=action,
expected_head_sha=head,
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
)
def test_rc_then_rc_on_new_head(self):
_seed(
[RC_619_HEAD_A],
ready_pr=619,
ready_head=HEAD_A,
ready_action="request_changes",
)
# Prior RC at head A is unresolved but head moved → feedback stale.
res = self._mark(
619,
"request_changes",
HEAD_B,
feedback=_feedback(blocking=True, stale=True),
)
self.assertTrue(res.get("marked_ready"), res)
lock = mcp_server._load_review_decision_lock()
# Historical head A preserved on mutation after backfill.
heads = {
m.get("head_sha")
for m in lock["live_mutations"]
if m.get("action") == "request_changes"
}
self.assertIn(HEAD_A, heads)
self.assertEqual(lock["ready_expected_head_sha"], HEAD_B)
def test_rc_then_approve_on_new_head(self):
_seed(
[RC_619_HEAD_A],
ready_pr=619,
ready_head=HEAD_A,
ready_action="request_changes",
)
res = self._mark(619, "approve", HEAD_B)
self.assertTrue(res.get("marked_ready"), res)
self.assertTrue(res.get("head_scoped"))
def test_same_head_rc_still_blocked_by_hard_stop(self):
_seed(
[RC_619_HEAD_A],
ready_pr=619,
ready_head=HEAD_A,
ready_action="request_changes",
)
res = self._mark(619, "approve", HEAD_A)
self.assertFalse(res.get("marked_ready"))
self.assertTrue(any("#332" in r for r in res.get("reasons") or []))
def test_pr619_style_legacy_lock_approve_on_current_head(self):
_seed(
[RC_619_LEGACY],
ready_pr=619,
ready_head=HEAD_A,
ready_action="request_changes",
)
res = self._mark(619, "approve", HEAD_B)
self.assertTrue(res.get("marked_ready"), res)
lock = mcp_server._load_review_decision_lock()
# Backfill should have stamped HEAD_A onto the legacy mutation.
self.assertEqual(lock["live_mutations"][0].get("head_sha"), HEAD_A)
self.assertEqual(lock["ready_expected_head_sha"], HEAD_B)
def test_record_live_mutation_stores_head(self):
_seed(ready_pr=619, ready_head=HEAD_B, ready_action="approve")
lock = mcp_server._load_review_decision_lock()
lock["final_review_decision_ready"] = True
lock["ready_pr_number"] = 619
lock["ready_expected_head_sha"] = HEAD_B
mcp_server._save_review_decision_lock(lock)
mcp_server.record_live_review_mutation(619, "approve", review_id=99)
stored = mcp_server._load_review_decision_lock()["live_mutations"][-1]
self.assertEqual(stored["head_sha"], HEAD_B)
self.assertEqual(stored["pr_number"], 619)
def test_submit_gate_allows_new_head_after_prior_terminal(self):
"""check_review_decision_gate must not block different-head submit."""
mutations = [RC_619_HEAD_A]
_seed(
mutations,
ready_pr=619,
ready_head=HEAD_B,
ready_action="approve",
)
lock = mcp_server._load_review_decision_lock()
lock["final_review_decision_ready"] = True
lock["ready_pr_number"] = 619
lock["ready_action"] = "approve"
lock["ready_expected_head_sha"] = HEAD_B
lock["ready_remote"] = "prgs"
lock["ready_org"] = "Scaled-Tech-Consulting"
lock["ready_repo"] = "Gitea-Tools"
mcp_server._save_review_decision_lock(lock)
reasons = mcp_server.check_review_decision_gate(
619,
"approve",
final_review_decision_ready=True,
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
)
self.assertEqual(reasons, [], reasons)
def test_submit_gate_blocks_same_head_duplicate(self):
mutations = [RC_619_HEAD_A]
_seed(
mutations,
ready_pr=619,
ready_head=HEAD_A,
ready_action="request_changes",
)
lock = mcp_server._load_review_decision_lock()
lock["final_review_decision_ready"] = True
lock["ready_pr_number"] = 619
lock["ready_action"] = "request_changes"
lock["ready_expected_head_sha"] = HEAD_A
lock["ready_remote"] = "prgs"
lock["ready_org"] = "Scaled-Tech-Consulting"
lock["ready_repo"] = "Gitea-Tools"
mcp_server._save_review_decision_lock(lock)
reasons = mcp_server.check_review_decision_gate(
619,
"request_changes",
final_review_decision_ready=True,
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
)
self.assertTrue(reasons)
class TestAssessmentOpenPrHead(unittest.TestCase):
def test_open_pr_stale_by_head_no_cleanup(self):
lock = _lock(
[RC_619_HEAD_A],
ready_pr=619,
ready_head=HEAD_A,
ready_action="request_changes",
)
a = srdl.assess_stale_review_decision_lock(
lock, pr_live=_open_pr(619, HEAD_B)
)
self.assertTrue(a["has_lock"])
self.assertFalse(a["is_moot"])
self.assertFalse(a["cleanup_allowed"])
self.assertTrue(a["stale_by_head"])
self.assertTrue(a["fresh_review_on_current_head_allowed"])
self.assertEqual(a["locked_head_sha"], HEAD_A)
self.assertEqual(a["current_pr_head_sha"], HEAD_B)
def test_open_pr_same_head_no_fresh(self):
lock = _lock([RC_619_HEAD_A], ready_pr=619, ready_head=HEAD_A)
a = srdl.assess_stale_review_decision_lock(
lock, pr_live=_open_pr(619, HEAD_A)
)
self.assertFalse(a["stale_by_head"])
self.assertFalse(a["fresh_review_on_current_head_allowed"])
self.assertFalse(a["cleanup_allowed"])
def test_historical_mutation_preserved_in_summary(self):
lock = _lock(
[RC_619_HEAD_A, APPROVE_619_HEAD_B],
ready_pr=619,
ready_head=HEAD_B,
ready_action="approve",
)
summary = srdl.lock_summary(lock)
self.assertEqual(summary["live_mutations_count"], 2)
self.assertEqual(summary["last_terminal"]["head_sha"], HEAD_B)
self.assertEqual(summary["locked_head_sha"], HEAD_B)
if __name__ == "__main__":
unittest.main()
-345
View File
@@ -1,345 +0,0 @@
"""Tests for observability incident bridge (#612) on #613 substrate."""
from __future__ import annotations
import json
import os
import tempfile
import unittest
from control_plane_db import ControlPlaneDB, InvalidWorkKindError, WORK_KINDS
from incident_bridge import (
OUTCOME_BLOCKED,
OUTCOME_CREATED,
OUTCOME_LINKED,
OUTCOME_PREVIEW,
OUTCOME_UPDATED,
ProjectMapping,
assert_not_raw_incident_work_item,
build_gitea_issue_body,
load_project_mappings,
normalize_incident,
project_mapping_from_dict,
reconcile_incident,
redact_text,
sanitize_tags,
)
def _mapping(**kwargs) -> ProjectMapping:
base = dict(
name="gitea-tools-mcp",
provider="sentry",
monitor_base_url="https://sentry.prgs.cc",
monitor_org="prgs",
monitor_project="gitea-tools-mcp",
gitea_org="Scaled-Tech-Consulting",
gitea_repo="Gitea-Tools",
default_labels=("type:bug", "observability", "sentry", "status:ready"),
)
base.update(kwargs)
return ProjectMapping(**base)
def _obs(**kwargs) -> dict:
base = dict(
provider="sentry",
provider_base_url="https://sentry.prgs.cc",
provider_org="prgs",
provider_project="gitea-tools-mcp",
provider_issue_id="ISSUE-100",
provider_short_id="GITEA-TOOLS-1A",
provider_permalink="https://sentry.prgs.cc/organizations/prgs/issues/100/",
fingerprint="fp-abc",
title="TypeError: boom",
summary="TypeError: boom in handle_request",
first_seen="2026-07-01T00:00:00Z",
last_seen="2026-07-10T00:00:00Z",
event_count=3,
environment="production",
severity="error",
culprit="handle_request",
tags={"runtime": "python", "release": "1.2.3"},
)
base.update(kwargs)
return base
class IncidentBridgeTest(unittest.TestCase):
def setUp(self) -> None:
self._tmp = tempfile.TemporaryDirectory()
self.db = ControlPlaneDB(os.path.join(self._tmp.name, "cp.sqlite3"))
self.mapping = _mapping()
self.created: list[dict] = []
def tearDown(self) -> None:
self._tmp.cleanup()
def _create_issue(self, title, body, labels, g_org, g_repo):
n = 9000 + len(self.created)
rec = {
"number": n,
"success": True,
"performed": True,
"title": title,
"body": body,
"labels": labels,
"org": g_org,
"repo": g_repo,
}
self.created.append(rec)
return rec
def test_redact_secrets(self) -> None:
dirty = "token=supersecret123 Authorization: Bearer abcdefghijklmnop"
clean = redact_text(dirty)
self.assertNotIn("supersecret", clean)
self.assertNotIn("abcdefghijklmnop", clean)
self.assertIn("[REDACTED]", clean)
tags = sanitize_tags(
{"token": "x", "runtime": "py", "password": "nope", "release": "1.0"}
)
self.assertEqual(tags, {"runtime": "py", "release": "1.0"})
def test_body_contains_no_secrets(self) -> None:
inc = normalize_incident(
_obs(
summary="fail password=hunter2 token: abc",
tags={"cookie": "sid=1", "runtime": "py"},
),
self.mapping,
)
body = build_gitea_issue_body(inc)
self.assertNotIn("hunter2", body)
self.assertNotIn("sid=1", body)
self.assertIn("provider_issue_id", body)
self.assertIn("not** assignable", body.lower())
def test_preview_no_mutation(self) -> None:
res = reconcile_incident(
self.db,
observation=_obs(),
mapping=self.mapping,
apply=False,
create_issue_fn=self._create_issue,
)
self.assertTrue(res["success"])
self.assertEqual(res["outcome"], OUTCOME_PREVIEW)
self.assertFalse(res["gitea_mutated"])
self.assertFalse(res["db_mutated"])
self.assertFalse(res["raw_incident_assignable"])
self.assertEqual(len(self.created), 0)
self.assertIsNone(
self.db.get_incident_link_by_provider(
provider="sentry",
provider_issue_id="ISSUE-100",
provider_base_url="https://sentry.prgs.cc",
provider_org="prgs",
provider_project="gitea-tools-mcp",
)
)
def test_apply_creates_issue_and_link(self) -> None:
res = reconcile_incident(
self.db,
observation=_obs(),
mapping=self.mapping,
apply=True,
create_issue_fn=self._create_issue,
)
self.assertTrue(res["success"])
self.assertEqual(res["outcome"], OUTCOME_CREATED)
self.assertTrue(res["gitea_mutated"])
self.assertTrue(res["db_mutated"])
self.assertEqual(len(self.created), 1)
self.assertEqual(res["gitea_issue"]["number"], self.created[0]["number"])
link = self.db.get_incident_link_by_provider(
provider="sentry",
provider_issue_id="ISSUE-100",
provider_base_url="https://sentry.prgs.cc",
provider_org="prgs",
provider_project="gitea-tools-mcp",
)
self.assertIsNotNone(link)
self.assertEqual(int(link["gitea_issue_number"]), self.created[0]["number"])
self.assertEqual(res["allocator_visible_as"]["kind"], "issue")
def test_duplicate_observation_reuses_issue(self) -> None:
first = reconcile_incident(
self.db,
observation=_obs(),
mapping=self.mapping,
apply=True,
create_issue_fn=self._create_issue,
)
second = reconcile_incident(
self.db,
observation=_obs(event_count=9, last_seen="2026-07-11T00:00:00Z"),
mapping=self.mapping,
apply=True,
create_issue_fn=self._create_issue,
)
self.assertEqual(first["outcome"], OUTCOME_CREATED)
self.assertEqual(second["outcome"], OUTCOME_UPDATED)
self.assertEqual(len(self.created), 1)
self.assertEqual(
second["gitea_issue"]["number"], first["gitea_issue"]["number"]
)
link = self.db.get_incident_link_by_provider(
provider="sentry",
provider_issue_id="ISSUE-100",
provider_base_url="https://sentry.prgs.cc",
provider_org="prgs",
provider_project="gitea-tools-mcp",
)
self.assertEqual(int(link["event_count"]), 9)
def test_explicit_link_existing_issue(self) -> None:
res = reconcile_incident(
self.db,
observation=_obs(provider_issue_id="ISSUE-200"),
mapping=self.mapping,
apply=True,
force_gitea_issue_number=555,
create_issue_fn=self._create_issue,
)
self.assertEqual(res["outcome"], OUTCOME_LINKED)
self.assertEqual(len(self.created), 0)
self.assertEqual(res["gitea_issue"]["number"], 555)
link = self.db.get_incident_link_for_gitea_issue(
gitea_org="Scaled-Tech-Consulting",
gitea_repo="Gitea-Tools",
gitea_issue_number=555,
)
self.assertIsNotNone(link)
def test_fingerprint_conflict_fails_closed(self) -> None:
reconcile_incident(
self.db,
observation=_obs(fingerprint="fp-a"),
mapping=self.mapping,
apply=True,
create_issue_fn=self._create_issue,
)
res = reconcile_incident(
self.db,
observation=_obs(fingerprint="fp-b"),
mapping=self.mapping,
apply=True,
create_issue_fn=self._create_issue,
)
self.assertEqual(res["outcome"], OUTCOME_BLOCKED)
self.assertIn("fingerprint conflict", res["reasons"][0].lower())
self.assertEqual(len(self.created), 1)
def test_ambiguous_mapping_fails_closed(self) -> None:
maps = [
_mapping(name="a", monitor_project="gitea-tools-mcp"),
_mapping(name="b", monitor_project="gitea-tools-mcp"),
]
res = reconcile_incident(
self.db,
observation=_obs(),
mappings=maps,
apply=False,
)
self.assertEqual(res["outcome"], OUTCOME_BLOCKED)
self.assertIn("ambiguous", res["reasons"][0].lower())
def test_missing_provider_issue_id_fails_closed(self) -> None:
res = reconcile_incident(
self.db,
observation=_obs(provider_issue_id=""),
mapping=self.mapping,
apply=False,
)
self.assertEqual(res["outcome"], OUTCOME_BLOCKED)
def test_raw_incident_not_work_kind(self) -> None:
self.assertNotIn("sentry_incident", WORK_KINDS)
with self.assertRaises(InvalidWorkKindError):
self.db.upsert_work_item(
remote="prgs",
org="o",
repo="r",
kind="sentry_incident",
number=1,
)
with self.assertRaises(Exception):
assert_not_raw_incident_work_item("glitchtip_incident")
def test_db_unavailable(self) -> None:
res = reconcile_incident(
None,
observation=_obs(),
mapping=self.mapping,
apply=True,
create_issue_fn=self._create_issue,
)
self.assertFalse(res["success"])
self.assertEqual(res["outcome"], OUTCOME_BLOCKED)
def test_structured_skip_reason_environment(self) -> None:
m = _mapping(environment_filters=("staging",))
res = reconcile_incident(
self.db,
observation=_obs(environment="production"),
mapping=m,
apply=True,
create_issue_fn=self._create_issue,
)
self.assertTrue(res["success"])
self.assertEqual(res["action"], "skip_environment_filter")
self.assertEqual(len(self.created), 0)
def test_load_mappings_json(self) -> None:
payload = json.dumps(
{
"projects": [
{
"name": "gt",
"provider": "glitchtip",
"monitor_base_url": "https://glitchtip.example",
"monitor_org": "org",
"monitor_project": "proj",
"gitea_org": "Scaled-Tech-Consulting",
"gitea_repo": "Gitea-Tools",
}
]
}
)
maps = load_project_mappings(mappings_json=payload)
self.assertEqual(len(maps), 1)
self.assertEqual(maps[0].provider, "glitchtip")
def test_glitchtip_provider_accepted(self) -> None:
m = _mapping(provider="glitchtip", monitor_base_url="https://glitchtip.example")
res = reconcile_incident(
self.db,
observation=_obs(
provider="glitchtip",
provider_base_url="https://glitchtip.example",
),
mapping=m,
apply=True,
create_issue_fn=self._create_issue,
)
self.assertEqual(res["outcome"], OUTCOME_CREATED)
self.assertEqual(res["incident"]["provider"], "glitchtip")
def test_allocator_only_sees_issue_kind(self) -> None:
res = reconcile_incident(
self.db,
observation=_obs(),
mapping=self.mapping,
apply=True,
create_issue_fn=self._create_issue,
)
vis = res["allocator_visible_as"]
self.assertEqual(vis["kind"], "issue")
self.assertIn(vis["kind"], WORK_KINDS)
self.assertFalse(res["raw_incident_assignable"])
if __name__ == "__main__":
unittest.main()
+3 -16
View File
@@ -25,11 +25,7 @@ import gitea_mcp_server as srv # noqa: E402
import root_checkout_guard as rcg # noqa: E402
FAKE_AUTH = "token test"
current_file_path = Path(__file__).resolve()
if "branches" in current_file_path.parts:
CONTROL_CHECKOUT_ROOT = str(current_file_path.parents[3])
else:
CONTROL_CHECKOUT_ROOT = str(current_file_path.parents[1])
CONTROL_CHECKOUT_ROOT = str(Path(__file__).resolve().parents[3])
MASTER_SHA = "a" * 40
OTHER_SHA = "b" * 40
@@ -267,19 +263,10 @@ class TestReconcilerCommentThroughCanonicalPath(unittest.TestCase):
with patch.dict(os.environ, {}, clear=False):
os.environ.pop("GITEA_AUTHOR_WORKTREE", None)
os.environ.pop("GITEA_ACTIVE_WORKTREE", None)
try:
res = srv.gitea_create_issue_comment(
with self.assertRaises(RuntimeError):
srv.gitea_create_issue_comment(
515, "author note", remote="prgs"
)
except RuntimeError:
pass # legacy raise path
else:
# #683: typed blocker at mutation entrypoint
self.assertFalse(res.get("success"))
self.assertFalse(res.get("performed"))
self.assertTrue(
res.get("blocker_kind") or res.get("reasons")
)
mock_api.assert_not_called()
@@ -1,472 +0,0 @@
"""#683: block unattributed root WIP; pytest cannot disable production guards.
Regression coverage required by issue #683:
1. Session locked to issue A blocks unrelated target issue B until B is selected.
2. Diagnostic source edit on the root checkout is blocked.
3. Same legitimate edit succeeds after issue ownership + isolated worktree bind.
4. Running under pytest does not deactivate production guards when force-on.
5. Dirty tracked Python files remain visible to porcelain consumers.
6. Monkeypatching one helper cannot silently turn the full guard path into a no-op.
7. Real mutation entrypoint proves production guards run before side effects.
8. Same-issue edits in a valid isolated worktree remain unaffected.
9. Blocker includes stable reason + exact recovery action.
"""
from __future__ import annotations
import os
import sys
import tempfile
import textwrap
import unittest
from pathlib import Path
from unittest.mock import MagicMock, patch
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
import gitea_mcp_server as mcp_server # noqa: E402
import issue_lock_worktree # noqa: E402
import workflow_scope_guard as wsg # noqa: E402
CONTROL_ROOT = str(Path(__file__).resolve().parent.parent)
if "branches" in Path(__file__).resolve().parts:
# Running from a worktree under branches/ — parent of branches is control.
parts = Path(__file__).resolve().parts
idx = parts.index("branches")
CONTROL_ROOT = str(Path(*parts[:idx])) if idx > 0 else CONTROL_ROOT
class TestProductionGuardsForceOn(unittest.TestCase):
def tearDown(self):
for key in (
wsg.FORCE_PRODUCTION_GUARDS_ENV,
"GITEA_TEST_FORCE_DIRTY",
"GITEA_TEST_PORCELAIN",
"GITEA_AUTHOR_WORKTREE",
"GITEA_ACTIVE_WORKTREE",
):
os.environ.pop(key, None)
wsg.clear_workflow_failure_ledger()
def test_force_on_under_pytest_keeps_production_active(self):
self.assertTrue(wsg.production_guards_active(in_test_mode=False))
self.assertFalse(wsg.production_guards_active(in_test_mode=True))
os.environ[wsg.FORCE_PRODUCTION_GUARDS_ENV] = "1"
self.assertTrue(wsg.production_guards_active(in_test_mode=True))
self.assertTrue(wsg.production_guards_forced())
def test_no_early_return_in_verify_role_mutation_workspace_source(self):
src = Path(mcp_server.__file__).read_text(encoding="utf-8")
# Rejected 300a4ca pattern must not exist.
self.assertNotIn(
"if _preflight_in_test_mode():\n return _resolve_preflight_workspace_path",
src,
)
# Docstring contract for #683.
self.assertIn("#683", src)
self.assertIn("must NOT early-return solely because pytest", src)
class TestPorcelainIntegrity(unittest.TestCase):
def test_read_worktree_git_state_surfaces_dirty_py(self):
with tempfile.TemporaryDirectory() as tmp:
# Use a real git repo so porcelain is truthful.
import subprocess
subprocess.run(["git", "init"], cwd=tmp, check=True, capture_output=True)
subprocess.run(
["git", "config", "user.email", "[email protected]"],
cwd=tmp,
check=True,
capture_output=True,
)
subprocess.run(
["git", "config", "user.name", "t"],
cwd=tmp,
check=True,
capture_output=True,
)
py_path = Path(tmp) / "sample_mod.py"
py_path.write_text("x = 1\n", encoding="utf-8")
subprocess.run(["git", "add", "sample_mod.py"], cwd=tmp, check=True)
subprocess.run(
["git", "commit", "-m", "init"],
cwd=tmp,
check=True,
capture_output=True,
)
py_path.write_text("x = 2\n", encoding="utf-8")
state = issue_lock_worktree.read_worktree_git_state(tmp)
porcelain = state.get("porcelain_status") or ""
self.assertIn("sample_mod.py", porcelain)
self.assertTrue(any(line.strip().endswith(".py") for line in porcelain.splitlines()))
def test_production_reader_source_rejects_pytest_py_filter(self):
src = Path(issue_lock_worktree.__file__).read_text(encoding="utf-8")
findings = wsg.assert_no_pytest_porcelain_filter(src)
self.assertEqual(findings, [])
# Negative: the rejected 300a4ca pattern is detected.
rejected = textwrap.dedent(
"""
porcelain = status_res.stdout or ""
import sys
if "pytest" in sys.modules or "unittest" in sys.modules:
porcelain = "\\n".join(
line for line in porcelain.splitlines()
if not line.strip().endswith(".py")
)
"""
)
self.assertTrue(wsg.assert_no_pytest_porcelain_filter(rejected))
class TestIssueScopeOwnership(unittest.TestCase):
def test_out_of_scope_issue_blocked_until_selected(self):
result = wsg.assess_issue_scope_ownership(
locked_issue_number=100,
target_issue_number=200,
branch_name="fix/issue-100-example",
role_kind="author",
)
self.assertTrue(result["block"])
self.assertEqual(result["blocker_kind"], wsg.BLOCKER_OUT_OF_SCOPE_ISSUE)
self.assertIn("exact_next_action", result)
self.assertIn("owning issue", result["exact_next_action"].lower())
self.assertTrue(result["reasons"])
def test_same_issue_scope_allowed(self):
result = wsg.assess_issue_scope_ownership(
locked_issue_number=100,
target_issue_number=100,
branch_name="fix/issue-100-example",
role_kind="author",
)
self.assertFalse(result["block"])
self.assertEqual(result["exact_next_action"], "proceed")
def test_missing_lock_when_required(self):
result = wsg.assess_issue_scope_ownership(
locked_issue_number=None,
target_issue_number=None,
role_kind="author",
require_lock_for_author=True,
)
self.assertTrue(result["block"])
self.assertEqual(result["blocker_kind"], wsg.BLOCKER_MISSING_ISSUE_SCOPE)
def test_branch_issue_mismatch(self):
result = wsg.assess_issue_scope_ownership(
locked_issue_number=50,
branch_name="fix/issue-99-other",
role_kind="author",
)
self.assertTrue(result["block"])
self.assertEqual(result["blocker_kind"], wsg.BLOCKER_OUT_OF_SCOPE_ISSUE)
class TestRootDiagnosticEdit(unittest.TestCase):
def test_dirty_root_source_blocked(self):
result = wsg.assess_root_source_mutation(
workspace_path=CONTROL_ROOT,
canonical_repo_root=CONTROL_ROOT,
porcelain_status=" M gitea_mcp_server.py\n M tests/test_x.py\n",
role_kind="author",
)
self.assertTrue(result["block"])
self.assertEqual(result["blocker_kind"], wsg.BLOCKER_ROOT_DIAGNOSTIC_EDIT)
self.assertIn("gitea_mcp_server.py", result["dirty_source_files"])
self.assertIn("exact_next_action", result)
self.assertIn("branches/", result["exact_next_action"])
def test_isolated_worktree_same_issue_unaffected(self):
wt = f"{CONTROL_ROOT}/branches/issue-100-example"
result = wsg.assess_root_source_mutation(
workspace_path=wt,
canonical_repo_root=CONTROL_ROOT,
porcelain_status=" M helper.py\n",
current_branch="fix/issue-100-example",
locked_issue_number=100,
role_kind="author",
)
self.assertFalse(result["block"])
self.assertTrue(result["under_branches"])
def test_legitimate_after_ownership_and_worktree(self):
wt = f"{CONTROL_ROOT}/branches/issue-683-workflow-guard-hardening"
composed = wsg.assess_production_mutation_guards(
workspace_path=wt,
canonical_repo_root=CONTROL_ROOT,
porcelain_status=" M workflow_scope_guard.py\n",
current_branch="fix/issue-683-workflow-guard-hardening",
locked_issue_number=683,
target_issue_number=683,
role_kind="author",
require_author_lock=True,
in_test_mode=True,
)
# Force-on required for production path under pytest.
os.environ[wsg.FORCE_PRODUCTION_GUARDS_ENV] = "1"
try:
composed = wsg.assess_production_mutation_guards(
workspace_path=wt,
canonical_repo_root=CONTROL_ROOT,
porcelain_status=" M workflow_scope_guard.py\n",
current_branch="fix/issue-683-workflow-guard-hardening",
locked_issue_number=683,
target_issue_number=683,
role_kind="author",
require_author_lock=True,
in_test_mode=True,
)
self.assertFalse(composed["block"])
self.assertFalse(composed.get("skipped"))
finally:
os.environ.pop(wsg.FORCE_PRODUCTION_GUARDS_ENV, None)
class TestTypedBlockerResponse(unittest.TestCase):
def test_block_response_has_stable_kind_and_next_action(self):
assessment = wsg.assess_issue_scope_ownership(
locked_issue_number=1,
target_issue_number=2,
role_kind="author",
)
resp = wsg.block_response(assessment)
self.assertFalse(resp["success"])
self.assertFalse(resp["performed"])
self.assertEqual(resp["blocker_kind"], wsg.BLOCKER_OUT_OF_SCOPE_ISSUE)
self.assertIsInstance(resp["exact_next_action"], str)
self.assertTrue(resp["exact_next_action"])
self.assertTrue(resp["reasons"])
def test_production_guard_error_roundtrip(self):
err = wsg.ProductionGuardError(
"blocked",
blocker_kind=wsg.BLOCKER_ROOT_DIAGNOSTIC_EDIT,
reasons=["dirty root"],
)
resp = wsg.block_response(err, issue_number=683)
self.assertEqual(resp["blocker_kind"], wsg.BLOCKER_ROOT_DIAGNOSTIC_EDIT)
self.assertEqual(resp["issue_number"], 683)
self.assertIn("exact_next_action", resp)
class TestDurableFailureRecording(unittest.TestCase):
def setUp(self):
wsg.clear_workflow_failure_ledger()
def tearDown(self):
wsg.clear_workflow_failure_ledger()
def test_record_before_source_mutation(self):
pending = wsg.assess_durable_failure_recorded(
require_record=True, pending_source_mutation=True
)
self.assertTrue(pending["block"])
self.assertEqual(pending["blocker_kind"], wsg.BLOCKER_UNRECORDED_FAILURE)
wsg.record_workflow_failure(
kind="transport_eof",
detail="EOF during review session (#584 cluster)",
issue_number=683,
task="comment_issue",
)
after = wsg.assess_durable_failure_recorded(
require_record=True, pending_source_mutation=True
)
self.assertFalse(after["block"])
self.assertEqual(len(wsg.workflow_failure_ledger()), 1)
class TestMonkeypatchCannotNoopFullPath(unittest.TestCase):
def tearDown(self):
os.environ.pop(wsg.FORCE_PRODUCTION_GUARDS_ENV, None)
def test_patching_branches_only_still_blocks_dirty_root_scope(self):
"""Monkeypatching branches-only must not silence root diagnostic block."""
os.environ[wsg.FORCE_PRODUCTION_GUARDS_ENV] = "1"
with patch.object(
mcp_server, "_enforce_branches_only_author_mutation", lambda *a, **k: None
):
with patch.object(
mcp_server, "_enforce_root_checkout_guard", lambda *a, **k: None
):
# Even if both legacy helpers are patched, issue-scope composition
# still sees dirty root source via assess_production_mutation_guards.
assessment = wsg.assess_production_mutation_guards(
workspace_path=CONTROL_ROOT,
canonical_repo_root=CONTROL_ROOT,
porcelain_status=" M gitea_mcp_server.py\n",
role_kind="author",
in_test_mode=True,
)
self.assertTrue(assessment["block"])
self.assertEqual(
assessment["blocker_kind"], wsg.BLOCKER_ROOT_DIAGNOSTIC_EDIT
)
class TestRealEntrypointProductionGuard(unittest.TestCase):
"""Real mutation entrypoint: production guard before side effects (#683)."""
def setUp(self):
os.environ[wsg.FORCE_PRODUCTION_GUARDS_ENV] = "1"
for key in ("GITEA_AUTHOR_WORKTREE", "GITEA_ACTIVE_WORKTREE"):
os.environ.pop(key, None)
self._orig_whoami = mcp_server._preflight_whoami_called
self._orig_cap = mcp_server._preflight_capability_called
mcp_server._preflight_whoami_called = False
mcp_server._preflight_capability_called = False
mcp_server._preflight_resolved_role = None
mcp_server._preflight_resolved_task = None
def tearDown(self):
os.environ.pop(wsg.FORCE_PRODUCTION_GUARDS_ENV, None)
for key in ("GITEA_AUTHOR_WORKTREE", "GITEA_ACTIVE_WORKTREE"):
os.environ.pop(key, None)
mcp_server._preflight_whoami_called = self._orig_whoami
mcp_server._preflight_capability_called = self._orig_cap
mcp_server._preflight_resolved_role = None
mcp_server._preflight_resolved_task = None
def test_comment_issue_blocks_dirty_root_before_api(self):
api_mock = MagicMock()
with patch.object(mcp_server, "api_request", api_mock), patch.object(
mcp_server,
"_actual_profile_role",
return_value="author",
), patch.object(
mcp_server,
"_effective_workspace_role",
return_value="author",
), patch.object(
mcp_server,
"get_profile",
return_value={
"profile_name": "prgs-author",
"allowed_operations": [
"gitea.issue.comment",
"gitea.read",
"gitea.pr.create",
"gitea.branch.push",
],
"forbidden_operations": [],
},
), patch.object(
issue_lock_worktree,
"read_worktree_git_state",
side_effect=lambda path, **kw: {
"current_branch": "master",
"porcelain_status": (
" M gitea_mcp_server.py\n"
if os.path.realpath(path) == os.path.realpath(CONTROL_ROOT)
or path == CONTROL_ROOT
else ""
),
"head_sha": "a" * 40,
"base_equivalent": True,
},
), patch.object(
mcp_server,
"_resolve_namespace_mutation_context",
return_value={
"workspace_path": CONTROL_ROOT,
"canonical_repo_root": CONTROL_ROOT,
"process_project_root": CONTROL_ROOT,
"workspace_role_kind": "author",
"workspace_binding_source": "process root",
"ignored_bindings": [],
},
), patch.object(
mcp_server,
"_resolve_author_mutation_context",
return_value={
"workspace_path": CONTROL_ROOT,
"canonical_repo_root": CONTROL_ROOT,
"process_project_root": CONTROL_ROOT,
"roots_aligned": True,
},
), patch.object(
mcp_server,
"_session_locked_issue_number",
return_value=None,
):
result = mcp_server.gitea_create_issue_comment(
issue_number=683,
body="diagnostic note",
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
worktree_path=CONTROL_ROOT,
)
api_mock.assert_not_called()
self.assertFalse(result.get("success"))
self.assertFalse(result.get("performed"))
self.assertIn(result.get("blocker_kind"), wsg.BLOCKER_KINDS)
self.assertTrue(result.get("exact_next_action"))
self.assertTrue(result.get("reasons"))
def test_comment_issue_succeeds_structure_after_worktree_bind(self):
"""Same-issue isolated worktree is not blocked by root diagnostic path."""
wt = f"{CONTROL_ROOT}/branches/issue-683-workflow-guard-hardening"
os.environ["GITEA_AUTHOR_WORKTREE"] = wt
assessment = wsg.assess_production_mutation_guards(
workspace_path=wt,
canonical_repo_root=CONTROL_ROOT,
porcelain_status=" M workflow_scope_guard.py\n",
current_branch="fix/issue-683-workflow-guard-hardening",
locked_issue_number=683,
target_issue_number=683,
role_kind="author",
require_author_lock=True,
in_test_mode=True,
)
self.assertFalse(assessment["block"], assessment)
class TestVerifyPreflightForceOn(unittest.TestCase):
def tearDown(self):
os.environ.pop(wsg.FORCE_PRODUCTION_GUARDS_ENV, None)
for key in ("GITEA_AUTHOR_WORKTREE", "GITEA_ACTIVE_WORKTREE"):
os.environ.pop(key, None)
def test_force_on_runs_production_guards_under_pytest(self):
os.environ[wsg.FORCE_PRODUCTION_GUARDS_ENV] = "1"
called = {"root": 0, "branches": 0, "scope": 0}
def _root(*a, **k):
called["root"] += 1
def _branches(*a, **k):
called["branches"] += 1
def _scope(*a, **k):
called["scope"] += 1
with patch.object(mcp_server, "_enforce_root_checkout_guard", _root), patch.object(
mcp_server, "_enforce_branches_only_author_mutation", _branches
), patch.object(mcp_server, "_enforce_issue_scope_guard", _scope):
# No whoami/capability — purity-order skipped; production still runs.
mcp_server.verify_preflight_purity(task="comment_issue")
self.assertEqual(called["root"], 1)
self.assertEqual(called["branches"], 1)
self.assertEqual(called["scope"], 1)
def test_without_force_on_pytest_skips_production_only_for_unit_isolation(self):
called = {"root": 0}
def _root(*a, **k):
called["root"] += 1
with patch.object(mcp_server, "_enforce_root_checkout_guard", _root), patch.object(
mcp_server, "_enforce_branches_only_author_mutation", lambda *a, **k: None
), patch.object(mcp_server, "_enforce_issue_scope_guard", lambda *a, **k: None):
mcp_server.verify_preflight_purity(task="comment_issue")
self.assertEqual(called["root"], 0)
if __name__ == "__main__":
unittest.main()
@@ -1,599 +0,0 @@
"""Guarded cleanup for obsolete comment-backed reviewer leases (#691).
Reproduces PR #688 lease comment 10749 class of defect: completed
REQUEST_CHANGES on head A, author pushes head B, foreign lease remains
pinned to A (and after expiry still has no non-owner cleanup path that
diagnosis can prescribe beyond indefinite wait).
"""
from __future__ import annotations
import sys
import unittest
from datetime import datetime, timedelta, timezone
from pathlib import Path
from unittest.mock import patch
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
import merger_lease_adoption as mla # noqa: E402
import reviewer_pr_lease as leases # noqa: E402
# PR #688 / comment 10749 reproduction fixtures
HEAD_A = "c7a444eb4b41cf916fdbd20a4999ffd78af496d0"
HEAD_B = "4a6357800364718a27a36ebc73578d4b929ff4aa"
SESSION_FOREIGN = "25883-7d4c6e6ebd53"
COMMENT_10749 = 10749
REPO = "Scaled-Tech-Consulting/Gitea-Tools"
PR = 688
ISSUE = 687
EXPIRES_10749 = "2026-07-13T04:23:00Z"
def _utc(dt: datetime) -> datetime:
return dt if dt.tzinfo else dt.replace(tzinfo=timezone.utc)
def _lease_comment(
*,
pr_number: int = PR,
session_id: str = SESSION_FOREIGN,
phase: str = "claimed",
candidate_head: str = HEAD_A,
comment_id: int = COMMENT_10749,
last_activity: datetime | None = None,
expires_at: datetime | None = None,
worktree: str = "branches/review-pr688-feat-issue-687-reconciler-branch-delete",
repo: str = REPO,
) -> dict:
now = last_activity or datetime.now(timezone.utc)
body = leases.format_lease_body(
repo=repo,
pr_number=pr_number,
issue_number=ISSUE,
reviewer_identity="sysadmin",
profile="prgs-reviewer",
session_id=session_id,
worktree=worktree,
phase=phase,
candidate_head=candidate_head,
target_branch="master",
target_branch_sha="b" * 40,
last_activity=now,
expires_at=expires_at,
)
return {
"id": comment_id,
"body": body,
"user": {"login": "sysadmin"},
"author": "sysadmin",
"created_at": now.isoformat(),
"updated_at": now.isoformat(),
}
def _reviews_for_head(head: str, verdict: str = "REQUEST_CHANGES") -> list[dict]:
return [
{
"verdict": verdict,
"reviewed_head_sha": head,
"dismissed": False,
"reviewer": "sysadmin",
}
]
def _assess(
comments,
*,
current_head=HEAD_B,
formal_reviews=None,
controller=True,
worktree_exists=True,
worktree_clean=True,
owner_process_alive=False,
requesting_session="fresh-controller",
apply=False,
confirmation=None,
**kwargs,
):
return leases.assess_obsolete_reviewer_comment_lease_cleanup(
comments,
pr_number=PR,
current_head_sha=current_head,
formal_reviews=formal_reviews if formal_reviews is not None else _reviews_for_head(HEAD_A),
repo=REPO,
expected_repo=REPO,
requesting_session_id=requesting_session,
controller_recovery_authorized=controller,
worktree_exists=worktree_exists,
worktree_clean=worktree_clean,
worktree_has_unpreserved_work=not worktree_clean if worktree_exists else False,
owner_process_alive=owner_process_alive,
owner_pid_observed=kwargs.get("owner_pid_observed"),
requesting_pid=kwargs.get("requesting_pid", 99999),
current_head_review_in_progress=kwargs.get(
"current_head_review_in_progress", False
),
expected_lease_comment_id=kwargs.get("expected_lease_comment_id"),
expected_session_id=kwargs.get("expected_session_id"),
expected_leased_head=kwargs.get("expected_leased_head"),
confirmation=confirmation
if confirmation is not None
else (leases.cleanup_confirmation_for_pr(PR) if apply else ""),
apply=apply,
now=kwargs.get("now"),
)
class TestIssue691SupersededHeadCleanup(unittest.TestCase):
def setUp(self):
leases.clear_session_lease()
def test_1_request_changes_then_push_expired_cleanup_succeeds(self):
"""Completed REQUEST_CHANGES on A, push B, lease A expires → cleanup OK."""
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(
last_activity=expires - timedelta(hours=2),
expires_at=expires,
)
result = _assess(
[claim],
formal_reviews=_reviews_for_head(HEAD_A, "REQUEST_CHANGES"),
now=now,
apply=True,
)
self.assertTrue(result["cleanup_allowed"], result["reasons"])
self.assertEqual(result["classification"], "foreign_expired_superseded_head")
self.assertEqual(
result["exact_next_action"], leases.NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
)
self.assertIn("phase: released", result["release_body"])
self.assertIn("obsolete-superseded-or-expired-lease", result["release_body"])
self.assertIsNotNone(result["audit_comment_body"])
self.assertEqual(result["cleanup_tool"], leases.CLEANUP_OBSOLETE_LEASE_TOOL)
def test_2_approve_then_push_cleanup_policy(self):
"""Completed APPROVE on A, push B → cleanup eligible (completed superseded)."""
now = datetime(2026, 7, 13, 1, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc) # not yet expired
claim = _lease_comment(
last_activity=now - timedelta(minutes=10),
expires_at=expires,
)
result = _assess(
[claim],
formal_reviews=_reviews_for_head(HEAD_A, "APPROVED"),
now=now,
)
self.assertTrue(result["cleanup_allowed"], result["reasons"])
self.assertEqual(result["classification"], "foreign_completed_superseded_head")
def test_3_active_current_head_cleanup_denied(self):
now = datetime.now(timezone.utc)
claim = _lease_comment(
candidate_head=HEAD_B,
last_activity=now - timedelta(minutes=5),
expires_at=now + timedelta(hours=2),
)
result = _assess(
[claim],
current_head=HEAD_B,
formal_reviews=_reviews_for_head(HEAD_B, "REQUEST_CHANGES"),
now=now,
)
self.assertFalse(result["cleanup_allowed"])
self.assertEqual(result["classification"], "foreign_active_current_head")
def test_4_foreign_owner_recent_progress_denied(self):
now = datetime.now(timezone.utc)
claim = _lease_comment(
candidate_head=HEAD_B,
last_activity=now - timedelta(minutes=2),
expires_at=now + timedelta(hours=2),
)
result = _assess(
[claim],
current_head=HEAD_B,
formal_reviews=[],
owner_process_alive=True,
now=now,
)
self.assertFalse(result["cleanup_allowed"])
self.assertTrue(
any("recent authenticated progress" in r for r in result["reasons"])
or any("current PR head" in r for r in result["reasons"])
)
def test_5_owner_absent_worktree_dirty_denied(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(
candidate_head=HEAD_B,
last_activity=expires - timedelta(hours=1),
expires_at=expires,
)
result = _assess(
[claim],
current_head=HEAD_B,
formal_reviews=[],
worktree_clean=False,
owner_process_alive=False,
now=now,
)
self.assertFalse(result["cleanup_allowed"])
self.assertTrue(any("dirty" in r for r in result["reasons"]))
def test_6_owner_absent_worktree_clean_orphan_ok(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(
candidate_head=HEAD_B,
last_activity=expires - timedelta(hours=1),
expires_at=expires,
)
result = _assess(
[claim],
current_head=HEAD_B,
formal_reviews=[],
worktree_clean=True,
owner_process_alive=False,
now=now,
)
self.assertTrue(result["cleanup_allowed"], result["reasons"])
self.assertEqual(result["classification"], "orphaned_owner_missing")
def test_7_pid_reuse_not_ownership(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess(
[claim],
now=now,
owner_pid_observed=4242,
requesting_pid=4242,
)
self.assertTrue(
any("PID equality" in r or "NOT ownership" in r for r in result["reasons"])
or result["owner_session_evidence"]["pid_is_not_ownership_proof"]
)
# Still eligible via superseded+terminal+expired despite matching PID.
self.assertTrue(result["cleanup_allowed"], result["reasons"])
def test_8_comment_backed_no_db_lease_id(self):
"""Cleanup uses comment ledger only — no control-plane lease_id required."""
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
# Explicitly no lease_id field anywhere.
self.assertNotIn("lease_id", claim)
result = _assess([claim], now=now)
self.assertTrue(result["cleanup_allowed"], result["reasons"])
self.assertEqual(result["active_lease"]["comment_id"], COMMENT_10749)
self.assertIsNone(result["active_lease"].get("lease_id"))
def test_9_cleanup_posts_durable_audit_bodies(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess([claim], now=now, apply=True)
self.assertTrue(result["cleanup_allowed"])
self.assertIn("#691", result["audit_comment_body"])
self.assertIn(str(COMMENT_10749), result["audit_comment_body"])
self.assertIn(HEAD_A, result["audit_comment_body"])
self.assertIn(HEAD_B, result["audit_comment_body"])
def test_10_fresh_acquire_after_cleanup_marker(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(
expires_at=expires,
last_activity=expires - timedelta(hours=1),
comment_id=COMMENT_10749,
)
assessed = _assess([claim], now=now, apply=True)
self.assertTrue(assessed["cleanup_allowed"])
release = {
"id": 99999,
"body": assessed["release_body"],
"user": {"login": "sysadmin"},
}
# Newest terminal marker ends active lease.
active = leases.find_active_reviewer_lease(
[claim, release], pr_number=PR, now=now
)
self.assertIsNone(active)
acq = leases.assess_acquire_lease(
[claim, release],
pr_number=PR,
reviewer_identity="sysadmin",
profile="prgs-reviewer",
session_id="fresh-reviewer-1",
repo=REPO,
issue_number=ISSUE,
worktree="branches/review-pr-688-fresh",
candidate_head=HEAD_B,
target_branch="master",
target_branch_sha="b" * 40,
now=now,
)
self.assertTrue(acq["acquire_allowed"], acq["reasons"])
def test_11_no_validation_state_transfer(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess([claim], now=now, apply=True)
self.assertTrue(result["cleanup_allowed"])
# Release body keeps old candidate_head (no repoint).
self.assertIn(f"candidate_head: {HEAD_A}", result["release_body"])
self.assertNotIn(HEAD_B, result["release_body"].split("candidate_head:")[1].split("\n")[0])
self.assertIn("did not transfer validation", result["audit_comment_body"])
self.assertIn("did not repoint", result["audit_comment_body"])
# Session lease must remain unset by assessment (tool never seeds).
self.assertIsNone(leases.get_session_lease())
def test_12_repeated_cleanup_idempotent(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
first = _assess([claim], now=now, apply=True)
self.assertTrue(first["cleanup_allowed"])
release = {"id": 100001, "body": first["release_body"], "user": {"login": "x"}}
second = _assess([claim, release], now=now, apply=True)
self.assertFalse(second["cleanup_allowed"])
self.assertEqual(second["classification"], "no_lease")
def test_13_malformed_expiry_fails_closed(self):
claim = _lease_comment()
# Corrupt expires_at in the body.
claim["body"] = claim["body"].replace(
claim["body"].split("expires_at:")[1].split("\n")[0].strip(),
"not-a-timestamp",
)
result = _assess([claim], formal_reviews=_reviews_for_head(HEAD_A))
self.assertFalse(result["cleanup_allowed"])
self.assertFalse(result["expires_parseable"])
self.assertTrue(any("expires_at" in r for r in result["reasons"]))
def test_14_wrong_identity_evidence_fails_closed(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
bad_repo = _assess(
[claim],
now=now,
# force repo mismatch via expected_repo
)
# Patch via direct call with wrong expected_repo
bad = leases.assess_obsolete_reviewer_comment_lease_cleanup(
[claim],
pr_number=PR,
current_head_sha=HEAD_B,
formal_reviews=_reviews_for_head(HEAD_A),
expected_repo="Other-Org/Other-Repo",
requesting_session_id="fresh",
controller_recovery_authorized=True,
worktree_exists=True,
worktree_clean=True,
owner_process_alive=False,
now=now,
)
self.assertFalse(bad["cleanup_allowed"])
self.assertTrue(any("repository identity" in r for r in bad["reasons"]))
bad_pr = leases.assess_obsolete_reviewer_comment_lease_cleanup(
[claim],
pr_number=999,
current_head_sha=HEAD_B,
formal_reviews=_reviews_for_head(HEAD_A),
expected_repo=REPO,
requesting_session_id="fresh",
controller_recovery_authorized=True,
worktree_exists=True,
worktree_clean=True,
owner_process_alive=False,
expected_lease_comment_id=COMMENT_10749,
now=now,
)
self.assertFalse(bad_pr["cleanup_allowed"])
bad_head = _assess(
[claim],
now=now,
expected_leased_head="0" * 40,
)
self.assertFalse(bad_head["cleanup_allowed"])
bad_session = _assess(
[claim],
now=now,
expected_session_id="wrong-session",
)
self.assertFalse(bad_session["cleanup_allowed"])
def test_15_current_head_active_cannot_be_displaced(self):
now = datetime.now(timezone.utc)
claim = _lease_comment(
candidate_head=HEAD_B,
last_activity=now - timedelta(minutes=1),
expires_at=now + timedelta(hours=2),
)
result = _assess(
[claim],
current_head=HEAD_B,
formal_reviews=_reviews_for_head(HEAD_B),
now=now,
current_head_review_in_progress=True,
)
self.assertFalse(result["cleanup_allowed"])
# Acquire also blocked by foreign active lease.
acq = leases.assess_acquire_lease(
[claim],
pr_number=PR,
reviewer_identity="other",
profile="prgs-reviewer",
session_id="thief",
repo=REPO,
issue_number=ISSUE,
worktree="branches/steal",
candidate_head=HEAD_B,
target_branch="master",
target_branch_sha="b" * 40,
now=now,
)
self.assertFalse(acq["acquire_allowed"])
def test_regression_pr688_comment_10749_after_expiry(self):
"""Exact 10749 reproduction after recorded expires_at 2026-07-13T04:23:00Z."""
now = datetime(2026, 7, 13, 4, 30, 0, tzinfo=timezone.utc)
expires = datetime.fromisoformat(EXPIRES_10749.replace("Z", "+00:00"))
claim = _lease_comment(
session_id=SESSION_FOREIGN,
candidate_head=HEAD_A,
comment_id=COMMENT_10749,
last_activity=expires - timedelta(hours=2),
expires_at=expires,
)
# Diagnosis must not prescribe indefinite wait-only for this case.
diag = leases.diagnose_reviewer_pr_lease_handoff(
[claim],
pr_number=PR,
current_session_id="fresh-reviewer",
current_reviewer_identity="sysadmin",
current_head_sha=HEAD_B,
formal_reviews=_reviews_for_head(HEAD_A, "REQUEST_CHANGES"),
worktree_exists=True,
worktree_clean=True,
owner_process_alive=False,
instructed_session_id=SESSION_FOREIGN,
instructed_comment_id=COMMENT_10749,
now=now,
)
self.assertEqual(diag["classification"], "foreign_expired_superseded_head")
self.assertEqual(
diag["next_action"], leases.NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
)
self.assertEqual(diag["cleanup_tool"], leases.CLEANUP_OBSOLETE_LEASE_TOOL)
self.assertIn("CLEANUP OBSOLETE REVIEWER LEASE 688", diag["required_confirmation"])
self.assertEqual(diag["mutation_eligibility"], "cleanup_only")
self.assertFalse(diag["mutation_allowed"])
# Assessment still returns the lease as active/stale class of block for acquire
# when unexpired path... here it's expired so find_active is None; acquire free
# only after cleanup if somehow still active. With expired, find_active is None:
active = leases.find_active_reviewer_lease([claim], pr_number=PR, now=now)
self.assertIsNone(active)
# But superseded unexpired still blocks acquire and diagnosis points to cleanup:
unexpired_now = datetime(2026, 7, 13, 1, 0, 0, tzinfo=timezone.utc)
claim2 = _lease_comment(
session_id=SESSION_FOREIGN,
candidate_head=HEAD_A,
comment_id=COMMENT_10749,
last_activity=unexpired_now - timedelta(minutes=45),
expires_at=expires,
)
active2 = leases.find_active_reviewer_lease(
[claim2], pr_number=PR, now=unexpired_now
)
self.assertIsNotNone(active2)
self.assertEqual(active2["freshness"], "stale_warning")
diag2 = leases.diagnose_reviewer_pr_lease_handoff(
[claim2],
pr_number=PR,
current_session_id="fresh-reviewer",
current_reviewer_identity="sysadmin",
current_head_sha=HEAD_B,
formal_reviews=_reviews_for_head(HEAD_A, "REQUEST_CHANGES"),
worktree_exists=True,
worktree_clean=True,
now=unexpired_now,
)
self.assertEqual(diag2["classification"], "foreign_completed_superseded_head")
self.assertEqual(
diag2["next_action"], leases.NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
)
acq = leases.assess_acquire_lease(
[claim2],
pr_number=PR,
reviewer_identity="sysadmin",
profile="prgs-reviewer",
session_id="fresh-reviewer",
repo=REPO,
issue_number=ISSUE,
worktree="branches/review-pr-688-new",
candidate_head=HEAD_B,
target_branch="master",
target_branch_sha="b" * 40,
now=unexpired_now,
)
self.assertFalse(acq["acquire_allowed"])
def test_missing_controller_auth_denied(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess([claim], controller=False, now=now)
self.assertFalse(result["cleanup_allowed"])
def test_wrong_confirmation_denied_on_apply(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess(
[claim], now=now, apply=True, confirmation="MERGE PR 688"
)
self.assertFalse(result["cleanup_allowed"])
self.assertTrue(any("confirmation" in r for r in result["reasons"]))
def test_owner_session_must_use_owner_release(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess(
[claim],
now=now,
requesting_session=SESSION_FOREIGN,
)
self.assertFalse(result["cleanup_allowed"])
self.assertTrue(any("owns the lease" in r for r in result["reasons"]))
def test_superseded_without_terminal_review_denied(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess([claim], formal_reviews=[], now=now)
self.assertFalse(result["cleanup_allowed"])
self.assertEqual(result["classification"], "ambiguous_conflicting_evidence")
class TestIssue691DiagnoseClassifications(unittest.TestCase):
def setUp(self):
leases.clear_session_lease()
def test_foreign_active_current_head_still_wait(self):
now = datetime.now(timezone.utc)
claim = _lease_comment(
candidate_head=HEAD_B,
last_activity=now - timedelta(minutes=5),
expires_at=now + timedelta(hours=1),
)
claim["id"] = 1
result = leases.diagnose_reviewer_pr_lease_handoff(
[claim],
pr_number=PR,
current_session_id="other",
current_reviewer_identity="sysadmin",
current_head_sha=HEAD_B,
formal_reviews=[],
now=now,
)
self.assertEqual(result["classification"], "foreign_active_current_head")
self.assertEqual(result["next_action"], leases.NEXT_ACTION_WAIT)
self.assertFalse(result["mutation_allowed"])
if __name__ == "__main__":
unittest.main()
+7 -32
View File
@@ -10,11 +10,7 @@ import gitea_mcp_server as srv
FAKE_AUTH = {"Authorization": "token test-token"}
current_file_path = Path(__file__).resolve()
if "branches" in current_file_path.parts:
CONTROL_CHECKOUT_ROOT = str(current_file_path.parents[3])
else:
CONTROL_CHECKOUT_ROOT = str(current_file_path.parents[1])
CONTROL_CHECKOUT_ROOT = str(Path(__file__).resolve().parents[3])
class TestIssueCommentWorkspaceGuard(unittest.TestCase):
@@ -108,24 +104,13 @@ class TestIssueCommentWorkspaceGuard(unittest.TestCase):
"gitea_mcp_server.issue_lock_worktree.read_worktree_git_state",
side_effect=self._git_state(valid_worktree),
):
try:
res = srv.gitea_create_issue_comment(
with self.assertRaises(RuntimeError) as ctx:
srv.gitea_create_issue_comment(
issue_number=557,
body="evidence comment",
remote="prgs",
)
except RuntimeError as exc:
self.assertIn("stable control checkout", str(exc))
else:
# #683 typed blocker at mutation entrypoint
self.assertFalse(res.get("success"))
self.assertFalse(res.get("performed"))
blob = " ".join(res.get("reasons") or [])
self.assertTrue(
"stable control checkout" in blob
or res.get("blocker_kind")
)
self.assertTrue(res.get("exact_next_action") or res.get("reasons"))
self.assertIn("stable control checkout", str(ctx.exception))
mock_api.assert_not_called()
@patch("gitea_mcp_server._auth", return_value=FAKE_AUTH)
@@ -195,24 +180,14 @@ class TestIssueCommentWorkspaceGuard(unittest.TestCase):
side_effect=self._subprocess(valid_worktree, outside_worktree),
):
with patch.dict(os.environ, self.AUTHOR_ENV, clear=True):
try:
res = srv.gitea_create_issue_comment(
with self.assertRaises(RuntimeError) as ctx:
srv.gitea_create_issue_comment(
issue_number=557,
body="evidence comment",
remote="prgs",
worktree_path=outside_worktree,
)
except RuntimeError as exc:
self.assertIn(
"does not belong to the target repository",
str(exc),
)
else:
self.assertFalse(res.get("success"))
blob = " ".join(res.get("reasons") or [])
self.assertIn(
"does not belong to the target repository", blob
)
self.assertIn("does not belong to the target repository", str(ctx.exception))
mock_api.assert_not_called()
@patch("gitea_mcp_server._auth", return_value=FAKE_AUTH)
-195
View File
@@ -1,195 +0,0 @@
"""Tests for the pre-create issue content gate (Issue #582)."""
import sys
import unittest
from unittest.mock import patch
sys.path.insert(0, str(__import__("pathlib").Path(__file__).resolve().parent.parent))
from issue_content_gate import ( # noqa: E402
assess_issue_content,
find_vague_reference,
has_durable_source_pointer,
normalize_text,
pre_create_issue_content_gate,
)
from mcp_server import gitea_create_issue # noqa: E402
FAKE_AUTH = "Basic dGVzdDp0ZXN0"
ISSUE_WRITE_ENV = {
"GITEA_ALLOWED_OPERATIONS": "gitea.issue.create",
}
class TestNormalizeAndPointers(unittest.TestCase):
def test_normalize_strips_punctuation_and_case(self):
self.assertEqual(normalize_text(" The Drafted-Issue! "), "the drafted issue")
def test_issue_ref_is_durable_pointer(self):
self.assertTrue(has_durable_source_pointer("See #402 for the spec"))
def test_file_path_is_durable_pointer(self):
self.assertTrue(has_durable_source_pointer("Draft in task_capability_map.py"))
def test_scratchpad_is_durable_pointer(self):
self.assertTrue(has_durable_source_pointer("Full text in scratchpad/draft.md"))
def test_url_is_durable_pointer(self):
self.assertTrue(
has_durable_source_pointer("https://gitea.prgs.cc/issues/1 has it")
)
def test_plain_text_has_no_durable_pointer(self):
self.assertFalse(has_durable_source_pointer("just some words here"))
class TestFindVagueReference(unittest.TestCase):
def test_bare_vague_phrases_are_flagged(self):
for text in (
"the drafted issue",
"The prepared issue",
"the issue we discussed",
"the previous draft",
"Create the drafted issue",
"please file the prepared issue",
):
with self.subTest(text=text):
self.assertIsNotNone(find_vague_reference(text))
def test_durable_pointer_defeats_vague_reference(self):
# Same vague phrase but with a durable pointer -> not vague.
self.assertIsNone(find_vague_reference("the drafted issue in #402"))
self.assertIsNone(
find_vague_reference("the prepared issue: see scratchpad/draft.md")
)
def test_long_specific_body_with_incidental_phrase_is_not_vague(self):
body = (
"As discussed, the create_issue tool must reject vague references. "
"Add a preflight check that lists the exact missing fields and "
"returns BLOCKED + DIAGNOSE with concrete acceptance criteria."
)
self.assertIsNone(find_vague_reference(body))
def test_concrete_short_body_is_not_vague(self):
self.assertIsNone(find_vague_reference("Fix null deref in auth handler"))
def test_empty_is_not_vague(self):
self.assertIsNone(find_vague_reference(""))
class TestAssessIssueContent(unittest.TestCase):
def test_missing_title_is_incomplete(self):
result = assess_issue_content("", "some body")
self.assertFalse(result["complete"])
self.assertIn("title", result["missing_fields"])
def test_vague_body_is_incomplete_and_diagnosed(self):
result = assess_issue_content("Add the thing", "the drafted issue")
self.assertFalse(result["complete"])
self.assertIn("body", result["vague_fields"])
self.assertIn("vague reference", result["diagnose"])
def test_vague_title_is_incomplete(self):
result = assess_issue_content("the prepared issue", "")
self.assertFalse(result["complete"])
self.assertIn("title", result["vague_fields"])
def test_complete_content_passes(self):
result = assess_issue_content(
"Block vague issue creation",
"Add a preflight gate that rejects placeholder references.",
)
self.assertTrue(result["complete"])
self.assertEqual(result["missing_fields"], [])
self.assertEqual(result["vague_fields"], [])
def test_title_only_is_allowed(self):
# Empty body must NOT block: title-only creation stays allowed.
result = assess_issue_content("A concrete specific title", "")
self.assertTrue(result["complete"])
def test_durable_pointer_body_passes(self):
result = assess_issue_content(
"Implement the drafted change",
"the drafted issue is fully specified in #582",
)
self.assertTrue(result["complete"])
def test_allow_incomplete_override(self):
result = assess_issue_content(
"the drafted issue", "the drafted issue", allow_incomplete=True
)
self.assertTrue(result["complete"])
self.assertTrue(result["override_applied"])
def test_gate_wrapper_sets_performed(self):
blocked = pre_create_issue_content_gate("Add x", "the drafted issue")
self.assertFalse(blocked["performed"])
ok = pre_create_issue_content_gate("Add x", "concrete actionable body")
self.assertTrue(ok["performed"])
class TestCreateIssueContentMCPGate(unittest.TestCase):
@patch("mcp_server.role_session_router.check_author_mutation_after_reviewer_stop")
@patch("mcp_server.api_request")
@patch("mcp_server.api_get_all")
@patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
def test_blocks_vague_reference_without_creating(
self, _auth, mock_get_all, mock_api, mock_role_check
):
mock_role_check.return_value = (True, [])
with patch.dict(__import__("os").environ, ISSUE_WRITE_ENV, clear=True):
result = gitea_create_issue(
title="Create the drafted issue",
body="the drafted issue",
remote="prgs",
)
self.assertFalse(result["performed"])
self.assertIn("content_gate", result)
self.assertIn("body", result["content_gate"]["vague_fields"])
self.assertTrue(any("BLOCKED + DIAGNOSE" in r for r in result["reasons"]))
mock_api.assert_not_called()
mock_get_all.assert_not_called()
@patch("mcp_server.role_session_router.check_author_mutation_after_reviewer_stop")
@patch("mcp_server.api_request")
@patch("mcp_server.api_get_all", return_value=[])
@patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
def test_creates_when_content_is_concrete(
self, _auth, _get_all, mock_api, mock_role_check
):
mock_role_check.return_value = (True, [])
mock_api.return_value = {"number": 7, "html_url": "https://x/issues/7"}
with patch.dict(__import__("os").environ, ISSUE_WRITE_ENV, clear=True):
result = gitea_create_issue(
title="Block vague issue creation",
body="Add a preflight gate rejecting placeholder references.",
remote="prgs",
)
self.assertEqual(result["number"], 7)
@patch("mcp_server.role_session_router.check_author_mutation_after_reviewer_stop")
@patch("mcp_server.api_request")
@patch("mcp_server.api_get_all", return_value=[])
@patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
def test_override_creates_despite_vague_content(
self, _auth, _get_all, mock_api, mock_role_check
):
mock_role_check.return_value = (True, [])
mock_api.return_value = {"number": 8, "html_url": "https://x/issues/8"}
with patch.dict(__import__("os").environ, ISSUE_WRITE_ENV, clear=True):
result = gitea_create_issue(
title="the drafted issue",
body="the drafted issue",
remote="prgs",
allow_incomplete_content=True,
)
self.assertEqual(result["number"], 8)
if __name__ == "__main__":
unittest.main()
+7 -27
View File
@@ -103,40 +103,20 @@ class TestIssueLockStore(unittest.TestCase):
self.assertIn("live foreign issue lock", block or "")
def test_expired_lease_allows_takeover_with_conflict_check(self):
# #601: expired + dead pid / missing worktree → sanctioned reclaim (no block).
existing = _lock_record(
branch_name="feat/issue-420-other",
worktree_path="/tmp/other-does-not-exist-420",
session_pid=1,
worktree_path="/tmp/other",
work_lease=_lease("2000-01-01T00:00:00Z"),
)
incoming = _lock_record(worktree_path="/tmp/mine")
self.assertIsNone(ils.assess_foreign_lock_overwrite(existing, incoming))
with mock.patch.object(ils, "is_process_alive", return_value=False):
block = ils.assess_same_issue_lease_conflict(
existing,
issue_number=420,
branch_name="feat/issue-420-server-code-parity",
worktree_path="/tmp/mine",
)
self.assertIsNone(block)
# Expired but still-live owner pid AND present worktree → fail closed.
present_wt = self.lock_dir # exists
sticky = _lock_record(
branch_name="feat/issue-420-other",
worktree_path=present_wt,
session_pid=os.getpid(),
work_lease=_lease("2000-01-01T00:00:00Z"),
block = ils.assess_same_issue_lease_conflict(
existing,
issue_number=420,
branch_name="feat/issue-420-server-code-parity",
worktree_path="/tmp/mine",
)
with mock.patch.object(ils, "is_process_alive", return_value=True):
blocked = ils.assess_same_issue_lease_conflict(
sticky,
issue_number=420,
branch_name="feat/issue-420-server-code-parity",
worktree_path="/tmp/mine",
)
self.assertIn("Recovery review is required", blocked or "")
self.assertIn("Recovery review is required", block or "")
def test_same_owner_lease_conflict_allows_refresh(self):
worktree = "/tmp/wt-420"
-134
View File
@@ -69,139 +69,5 @@ class TestIssueWorkflowStatusTransitions(unittest.TestCase):
self.assertEqual(result, ["type:process", "status:duplicate"])
class TestLifecycleRoleLabels(unittest.TestCase):
def test_role_transition_author_to_reviewer_to_merger_single_active(self):
after_author = labels.transition_role_labels(
["type:feature", "status:pr-open"], "author"
)
self.assertEqual(after_author, ["type:feature", "status:pr-open", "role:author"])
after_reviewer = labels.transition_role_labels(after_author, "reviewer")
self.assertEqual(
after_reviewer, ["type:feature", "status:pr-open", "role:reviewer"]
)
self.assertNotIn("role:author", after_reviewer)
after_merger = labels.transition_role_labels(after_reviewer, "merger")
self.assertEqual(labels.role_labels(after_merger), ["role:merger"])
def test_role_transition_accepts_canonical_label(self):
result = labels.transition_role_labels(["type:bug"], "role:reviewer")
self.assertEqual(result, ["type:bug", "role:reviewer"])
def test_unknown_role_raises(self):
with self.assertRaises(ValueError):
labels.canonical_role_label("wizard")
def test_assess_reports_multiple_active_role_labels(self):
result = labels.assess_issue_labels(
["type:feature", "status:pr-open", "role:author", "role:reviewer"]
)
self.assertFalse(result["valid"])
self.assertTrue(
any("multiple active role:* labels" in err for err in result["errors"])
)
self.assertEqual(
sorted(result["role_labels"]), ["role:author", "role:reviewer"]
)
class TestLifecycleHazardLabels(unittest.TestCase):
def test_hazards_are_additive_and_multiple(self):
one = labels.add_hazard_label(["type:bug", "status:blocked"], "conflicted")
two = labels.add_hazard_label(one, "stale-lease")
self.assertIn("hazard:conflicted", two)
self.assertIn("hazard:stale-lease", two)
# status/type untouched
self.assertIn("status:blocked", two)
self.assertIn("type:bug", two)
self.assertEqual(len(labels.hazard_labels(two)), 2)
def test_add_hazard_is_idempotent(self):
once = labels.add_hazard_label(["type:bug", "status:ready"], "root-mutation")
twice = labels.add_hazard_label(once, "root_mutation")
self.assertEqual(twice.count("hazard:root-mutation"), 1)
def test_clear_hazard_leaves_others_intact(self):
start = ["type:bug", "status:blocked", "hazard:conflicted", "hazard:stale-lease"]
cleared = labels.clear_hazard_label(start, "conflicted")
self.assertNotIn("hazard:conflicted", cleared)
self.assertIn("hazard:stale-lease", cleared)
self.assertIn("status:blocked", cleared)
def test_terminal_blocker_hazard_normalizes(self):
self.assertEqual(
labels.canonical_hazard_label("terminal-blocker"),
"hazard:terminal-blocker",
)
def test_assess_surfaces_hazard_labels(self):
result = labels.assess_issue_labels(
["type:bug", "status:blocked", "hazard:conflicted"]
)
self.assertEqual(result["hazard_labels"], ["hazard:conflicted"])
class TestDiscussionExclusion(unittest.TestCase):
def test_discussion_issue_excluded_from_implementation_queue(self):
self.assertTrue(labels.is_discussion(["type:discussion", "status:ready"]))
self.assertFalse(
labels.is_implementation_candidate(["type:discussion", "status:ready"])
)
def test_non_discussion_issue_is_candidate(self):
self.assertTrue(
labels.is_implementation_candidate(["type:feature", "status:ready"])
)
class TestBlockingReasonRequirement(unittest.TestCase):
def test_blocked_requires_reason(self):
self.assertTrue(
labels.requires_blocking_reason(["type:bug", "status:blocked"])
)
def test_hazard_requires_reason(self):
self.assertTrue(
labels.requires_blocking_reason(
["type:bug", "status:ready", "hazard:stale-lease"]
)
)
def test_clean_ready_issue_needs_no_reason(self):
self.assertFalse(
labels.requires_blocking_reason(["type:feature", "status:ready"])
)
class TestState603SynonymTransitions(unittest.TestCase):
def test_authoring_maps_to_in_progress(self):
self.assertEqual(
labels.canonical_status_label("authoring"), "status:in-progress"
)
def test_changes_requested_transition(self):
result = labels.transition_status_labels(
["type:feature", "status:needs-review"], "changes-requested"
)
self.assertEqual(result, ["type:feature", "status:changes-requested"])
def test_merge_ready_maps_to_approved(self):
self.assertEqual(labels.canonical_status_label("merge-ready"), "status:approved")
def test_abandoned_maps_to_wontfix(self):
self.assertEqual(labels.canonical_status_label("abandoned"), "status:wontfix")
def test_blocked_and_merged_transitions(self):
blocked = labels.transition_status_labels(
["type:bug", "status:in-progress"], "blocked"
)
self.assertEqual(blocked, ["type:bug", "status:blocked"])
merged = labels.transition_status_labels(
["type:feature", "status:approved"], "merged"
)
self.assertEqual(merged, ["type:feature", "status:reconcile"])
if __name__ == "__main__":
unittest.main()
-392
View File
@@ -1,392 +0,0 @@
"""Tests for first-class control-plane lease lifecycle (#601)."""
from __future__ import annotations
import os
import tempfile
import unittest
from datetime import timedelta
from unittest import mock
from allocator_service import allocate_next_work, WorkCandidate
from control_plane_db import ControlPlaneDB, ForeignLeaseError, _ts, _utc_now
import lease_lifecycle as ll
import merger_lease_adoption as mla
import reviewer_pr_lease as rpl
from datetime import datetime, timezone
class LeaseLifecycleTest(unittest.TestCase):
def setUp(self) -> None:
self._tmp = tempfile.TemporaryDirectory()
self.db_path = os.path.join(self._tmp.name, "cp.sqlite3")
self.db = ControlPlaneDB(self.db_path)
self.db.upsert_session(session_id="owner", role="author", profile="prgs-author", pid=111)
self.db.upsert_session(session_id="other", role="author", profile="prgs-author", pid=222)
def tearDown(self) -> None:
self._tmp.cleanup()
def _assign(self, session_id="owner", number=601, **kwargs):
return self.db.assign_and_lease(
session_id=session_id,
role="author",
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
kind="issue",
number=number,
allowed_actions=("implement", "comment", "push", "create_pr"),
forbidden_actions=("approve", "merge", "self_select_without_assignment"),
worktree_path=kwargs.pop("worktree_path", self._tmp.name),
owner_pid=kwargs.pop("owner_pid", os.getpid()),
**kwargs,
)
def test_list_active_leases_as_workflow_state(self) -> None:
a = self._assign(number=601)
self._assign(session_id="other", number=602)
listed = ll.list_active_leases(
self.db, remote="prgs", org="Scaled-Tech-Consulting", repo="Gitea-Tools"
)
self.assertTrue(listed["success"])
self.assertEqual(listed["count"], 2)
self.assertEqual(listed["authoritative_source"], "control_plane_db")
self.assertFalse(listed["file_lock_only"])
self.assertFalse(listed["comment_lease_only"])
numbers = sorted(x["work_number"] for x in listed["leases"])
self.assertEqual(numbers, [601, 602])
self.assertIsNotNone(a.lease_id)
def test_adopt_lease_owner_resume_preserves_provenance(self) -> None:
a = self._assign()
res = ll.adopt_lease(
self.db,
lease_id=a.lease_id,
adopter_session_id="owner",
role="author",
worktree_path=self._tmp.name,
)
self.assertTrue(res["success"])
self.assertTrue(res["same_owner"])
prov = res["provenance"]
self.assertEqual(prov["adopted_from_session_id"], "owner")
self.assertEqual(prov["adopted_by_session_id"], "owner")
self.assertEqual(prov["work_number"], 601)
self.assertEqual(prov["worktree_path"], self._tmp.name)
state = self.db.get_lease_workflow_state(a.lease_id)
self.assertIsNotNone(state)
self.assertEqual(state["lease"]["status"], "active")
def test_release_lease_explicit_recorded(self) -> None:
a = self._assign()
res = ll.release_lease(self.db, lease_id=a.lease_id, session_id="owner")
self.assertEqual(res["outcome"], "released")
self.assertIn("release_proof", res)
self.assertEqual(res["release_proof"]["status"], "released")
state = self.db.get_lease_workflow_state(a.lease_id)
self.assertEqual(state["lease"]["status"], "released")
def test_expire_and_reclaim_expired_lease(self) -> None:
a = self._assign(lease_ttl_seconds=1)
past = _utc_now() - timedelta(hours=2)
import sqlite3
conn = sqlite3.connect(self.db_path)
try:
conn.execute(
"UPDATE leases SET expires_at = ? WHERE lease_id = ?",
(_ts(past), a.lease_id),
)
conn.commit()
finally:
conn.close()
exp = ll.expire_leases(self.db)
self.assertGreaterEqual(exp["expired_count"], 1)
reclaimed = ll.reclaim_expired_lease(
self.db,
lease_id=a.lease_id,
session_id="other",
role="author",
worktree_path=self._tmp.name,
)
self.assertEqual(reclaimed["outcome"], "reclaimed")
self.assertEqual(reclaimed["assignment"]["session_id"], "other")
self.assertEqual(
reclaimed["provenance"]["adopted_from_session_id"], "owner"
)
self.assertEqual(
reclaimed["provenance"]["adopted_by_session_id"], "other"
)
def test_abandon_stale_lease_with_required_proof(self) -> None:
a = self._assign(owner_pid=99999999, worktree_path="/nonexistent/path/for-601")
# Force active but dead pid + missing worktree
proof = ll.AbandonProof(
dead_process=True,
missing_worktree=True,
no_open_pr=True,
no_live_mutation_risk=True,
owner_pid=99999999,
worktree_path="/nonexistent/path/for-601",
)
res = ll.abandon_lease(
self.db,
lease_id=a.lease_id,
requester_session_id="other",
proof=proof,
)
self.assertEqual(res["outcome"], "abandoned")
self.assertEqual(res["prior_owner_session_id"], "owner")
self.assertTrue(res["abandon_proof"]["dead_process"])
state = self.db.get_lease_workflow_state(a.lease_id)
self.assertEqual(state["lease"]["status"], "abandoned")
def test_refuse_steal_active_foreign_lease(self) -> None:
a = self._assign()
with self.assertRaises(ll.LeaseLifecycleError) as ctx:
ll.adopt_lease(
self.db,
lease_id=a.lease_id,
adopter_session_id="other",
role="author",
)
self.assertIn("steal", str(ctx.exception).lower())
decision = ll.inspect_lease(
self.db, a.lease_id, caller_session_id="other"
)
self.assertEqual(decision["safe_next_action"], ll.SAFE_WAIT_FOREIGN)
self.assertTrue(decision["block"])
def test_refuse_ambiguous_lease_ownership_stale_id(self) -> None:
decision = ll.inspect_lease(
self.db, "lease-does-not-exist", caller_session_id="owner"
)
self.assertFalse(decision["found"])
self.assertEqual(decision["safe_next_action"], ll.SAFE_STALE_PROMPT)
with self.assertRaises(ll.LeaseLifecycleError):
ll.adopt_lease(
self.db,
lease_id="lease-does-not-exist",
adopter_session_id="owner",
role="author",
)
def test_provenance_on_adopt_release_abandon(self) -> None:
a = self._assign()
adopted = ll.adopt_lease(
self.db,
lease_id=a.lease_id,
adopter_session_id="owner",
role="author",
worktree_path=self._tmp.name,
expected_head_sha="abc",
)
self.assertIn("adopted_from_session_id", adopted["provenance"])
self.assertIn("adopted_by_session_id", adopted["provenance"])
released = ll.release_lease(
self.db, lease_id=a.lease_id, session_id="owner"
)
self.assertEqual(released["release_proof"]["session_id"], "owner")
b = self._assign(number=700, owner_pid=1, worktree_path="/no/such/wt")
abandoned = ll.abandon_lease(
self.db,
lease_id=b.lease_id,
requester_session_id="owner",
proof=ll.AbandonProof(
dead_process=True,
missing_worktree=True,
no_live_mutation_risk=True,
no_open_pr=True,
),
)
self.assertIn("abandon_proof", abandoned)
self.assertEqual(abandoned["abandon_proof"]["dead_process"], True)
def test_allocator_assignment_lease_compatible(self) -> None:
"""Allocator assign+lease still works and is listable/inspectable."""
cands = [
WorkCandidate(
kind="issue",
number=601,
labels=("status:ready",),
title="leases",
priority=20,
)
]
res = allocate_next_work(
self.db,
session_id="alloc-s",
role="author",
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
candidates=cands,
apply=True,
profile_name="prgs-author",
username="jcwalker3",
)
self.assertEqual(res["outcome"], "assigned_work")
lid = res["assignment"]["lease_id"]
listed = ll.list_active_leases(self.db, remote="prgs")
ids = [x["lease_id"] for x in listed["leases"]]
self.assertIn(lid, ids)
insp = ll.inspect_lease(self.db, lid, caller_session_id="alloc-s")
self.assertTrue(insp["found"])
self.assertIn(
insp["safe_next_action"],
(ll.SAFE_OWNER_RESUME, ll.SAFE_ABANDON_ALLOWED),
)
def test_reviewer_merger_lease_handoff_still_works(self) -> None:
"""#536 merger adoption path is independent and must not regress."""
rpl.clear_session_lease()
body = mla.format_adoption_body(
repo="Scaled-Tech-Consulting/Gitea-Tools",
pr_number=999,
issue_number=601,
adopter_identity="sysadmin",
adopter_profile="prgs-merger",
adopter_session_id="merger-1",
worktree="branches/merge-pr999",
candidate_head="a" * 40,
target_branch="master",
target_branch_sha="b" * 40,
adopted_from_session_id="reviewer-1",
adopted_from_profile="prgs-reviewer",
adopted_from_reviewer_identity="sysadmin",
adopted_from_comment_id=42,
)
self.assertIn(mla.ADOPTION_MARKER, body)
self.assertIn("adopted_from_session_id: reviewer-1", body)
self.assertIn("adopted_by_profile: prgs-merger", body)
prov = mla.build_lease_provenance(
source=mla.SOURCE_ADOPT,
comment_id=42,
adopted_from_session_id="reviewer-1",
adoption_reason=mla.DEFAULT_ADOPTION_REASON,
)
rpl.record_session_lease(
{
"pr_number": 999,
"session_id": "merger-1",
"comment_id": 42,
},
lease_provenance=prov,
)
proof = mla.describe_session_lease_proof(rpl.get_session_lease())
self.assertTrue(proof["lease_proof_sanctioned"])
self.assertEqual(proof["lease_proof_source"], mla.SOURCE_ADOPT)
rpl.clear_session_lease()
def test_missing_worktree_and_dead_pid_handled_safely(self) -> None:
a = self._assign(owner_pid=1, worktree_path="/definitely/missing/wt-601")
with mock.patch.object(ll, "is_process_alive", return_value=False):
fr = ll.classify_lease_freshness(
self.db.get_lease_workflow_state(a.lease_id)["lease"]
)
self.assertIn(fr["freshness"], ("stale_dead_process", "stale_missing_worktree"))
# Insufficient abandon proof fails closed
with self.assertRaises(ll.LeaseLifecycleError):
ll.abandon_lease(
self.db,
lease_id=a.lease_id,
requester_session_id="other",
proof=ll.AbandonProof(dead_process=True), # missing no_live_mutation_risk
)
def test_file_lock_or_comment_not_authoritative_alone(self) -> None:
report = ll.non_db_lease_authority_report(
file_lock_present=True,
comment_lease_present=False,
db_lease_present=False,
)
self.assertEqual(report["safe_next_action"], ll.SAFE_NO_AUTHORITY)
self.assertTrue(report["file_lock_only"])
self.assertIsNone(report["authoritative_source"])
report2 = ll.non_db_lease_authority_report(
file_lock_present=True,
comment_lease_present=True,
db_lease_present=True,
)
self.assertEqual(report2["authoritative_source"], "control_plane_db")
self.assertFalse(report2["file_lock_only"])
self.assertFalse(report2["comment_lease_only"])
def test_abandon_proof_is_sufficient_rules(self) -> None:
self.assertFalse(ll.AbandonProof(dead_process=True).is_sufficient())
self.assertTrue(
ll.AbandonProof(
dead_process=True,
missing_worktree=True,
no_live_mutation_risk=True,
no_open_pr=True,
).is_sufficient()
)
self.assertTrue(
ll.AbandonProof(
dead_process=True,
no_live_mutation_risk=True,
same_owner=True,
).is_sufficient()
)
self.assertTrue(
ll.AbandonProof(
missing_worktree=True,
no_live_mutation_risk=True,
operator_authorized=True,
).is_sufficient()
)
class IssueLockExpiredReclaimTest(unittest.TestCase):
def test_expired_lock_reclaim_allowed_when_dead_and_missing_wt(self) -> None:
import issue_lock_store as ils
lock = {
"issue_number": 601,
"branch_name": "feat/issue-601-x",
"worktree_path": "/no/such/worktree-601",
"session_pid": 1,
"work_lease": {
"operation_type": "author_issue_work",
"expires_at": "2000-01-01T00:00:00Z",
},
}
with mock.patch.object(ils, "is_process_alive", return_value=False):
res = ils.assess_expired_lock_reclaim(lock)
self.assertTrue(res["reclaim_allowed"])
# Conflict assessor allows takeover
block = ils.assess_same_issue_lease_conflict(
lock,
issue_number=601,
branch_name="feat/issue-601-first-class-leases",
worktree_path="/tmp/new",
)
self.assertIsNone(block)
def test_live_lock_reclaim_refused(self) -> None:
import issue_lock_store as ils
from datetime import datetime, timedelta, timezone
future = (datetime.now(timezone.utc) + timedelta(hours=2)).strftime(
"%Y-%m-%dT%H:%M:%SZ"
)
lock = {
"issue_number": 601,
"branch_name": "feat/issue-601-x",
"worktree_path": tempfile.gettempdir(),
"session_pid": os.getpid(),
"work_lease": {
"operation_type": "author_issue_work",
"expires_at": future,
"last_heartbeat_at": future,
},
}
res = ils.assess_expired_lock_reclaim(lock)
self.assertFalse(res["reclaim_allowed"])
if __name__ == "__main__":
unittest.main()
+34 -29
View File
@@ -28,31 +28,33 @@ class TestLabelCreation(unittest.TestCase):
"""Verify create-or-skip logic for the label set."""
@patch("manage_labels.get_auth_header", return_value=FAKE_AUTH)
@patch("manage_labels.api_get_all")
@patch("manage_labels.api")
def test_skips_existing_labels(self, mock_api, mock_get_all, _auth):
# Simulate all labels already exist (paginated inventory #627)
def test_skips_existing_labels(self, mock_api, _auth):
# Simulate all labels already exist
existing = [_make_label(l["name"], i) for i, l in enumerate(manage_labels.LABELS)]
mock_get_all.return_value = existing
mock_api.return_value = existing # first call is GET /labels
# Patch sys.argv to avoid --dry
with patch.object(sys, "argv", ["manage_labels.py"]):
with contextlib.redirect_stdout(io.StringIO()), contextlib.redirect_stderr(io.StringIO()):
manage_labels.main()
mock_get_all.assert_called()
# The GET call happens, but no POST calls for label creation
get_calls = [c for c in mock_api.call_args_list if c[0][0] == "GET"]
post_label_calls = [
c for c in mock_api.call_args_list
if c[0][0] == "POST" and c[0][1] == "/labels"
]
self.assertGreaterEqual(len(get_calls), 1)
self.assertEqual(len(post_label_calls), 0)
@patch("manage_labels.get_auth_header", return_value=FAKE_AUTH)
@patch("manage_labels.api_get_all", return_value=[])
@patch("manage_labels.api")
def test_creates_missing_labels(self, mock_api, _get_all, _auth):
def test_creates_missing_labels(self, mock_api, _auth):
# Simulate no existing labels
def side_effect(method, path, auth, payload=None):
if method == "GET" and "/labels" in path:
return [] # no existing labels
if method == "POST" and path == "/labels":
return {"id": 999, "name": payload["name"]}
if method == "PUT":
@@ -77,14 +79,15 @@ class TestLabelCreation(unittest.TestCase):
class TestDryRun(unittest.TestCase):
@patch("manage_labels.get_auth_header", return_value=FAKE_AUTH)
@patch("manage_labels.api_get_all", return_value=[])
@patch("manage_labels.api")
def test_dry_run_makes_no_writes(self, mock_api, _get_all, _auth):
def test_dry_run_makes_no_writes(self, mock_api, _auth):
mock_api.return_value = [] # no existing labels
with patch.object(sys, "argv", ["manage_labels.py", "--dry"]):
with contextlib.redirect_stdout(io.StringIO()), contextlib.redirect_stderr(io.StringIO()):
manage_labels.main()
# Dry run should not call write methods via api()
# Only the GET call should be made, no POST or PUT
for c in mock_api.call_args_list:
method = c[0][0]
self.assertEqual(method, "GET",
@@ -97,13 +100,13 @@ class TestDryRun(unittest.TestCase):
class TestLabelMapping(unittest.TestCase):
@patch("manage_labels.get_auth_header", return_value=FAKE_AUTH)
@patch("manage_labels.api_get_all")
@patch("manage_labels.api")
def test_applies_mapping_to_issues(self, mock_api, mock_get_all, _auth):
def test_applies_mapping_to_issues(self, mock_api, _auth):
existing = [_make_label(l["name"], i + 1) for i, l in enumerate(manage_labels.LABELS)]
mock_get_all.return_value = existing
def side_effect(method, path, auth, payload=None):
if method == "GET":
return existing
if method == "PUT":
return [{"name": "applied"}]
return None
@@ -155,10 +158,11 @@ class TestModes(unittest.TestCase):
return [(c[0][0], c[0][1]) for c in mock_api.call_args_list]
@patch("manage_labels.get_auth_header", return_value=FAKE_AUTH)
@patch("manage_labels.api_get_all", return_value=[])
@patch("manage_labels.api")
def test_create_labels_only_no_mapping(self, mock_api, _get_all, _auth):
def test_create_labels_only_no_mapping(self, mock_api, _auth):
def se(method, path, auth, payload=None):
if method == "GET":
return [] # no existing labels
if method == "POST" and path == "/labels":
return {"id": 1, "name": payload["name"]}
return None
@@ -169,14 +173,14 @@ class TestModes(unittest.TestCase):
self.assertFalse(any(m[0] == "PUT" for m in methods)) # no mapping applied
@patch("manage_labels.get_auth_header", return_value=FAKE_AUTH)
@patch("manage_labels.api_get_all")
@patch("manage_labels.api")
def test_apply_mapping_only_no_label_creation(self, mock_api, mock_get_all, _auth):
def test_apply_mapping_only_no_label_creation(self, mock_api, _auth):
existing = [_make_label(l["name"], i + 1)
for i, l in enumerate(manage_labels.LABELS)]
mock_get_all.return_value = existing
def se(method, path, auth, payload=None):
if method == "GET":
return existing
if method == "PUT":
return [{"name": "applied"}]
return None
@@ -188,10 +192,13 @@ class TestModes(unittest.TestCase):
self.assertEqual(len(put_calls), len(manage_labels.MAPPING))
@patch("manage_labels.get_auth_header", return_value=FAKE_AUTH)
@patch("manage_labels.api_get_all", return_value=[_make_label("chore", 5)])
@patch("manage_labels.api")
def test_add_label_appends_to_issue(self, mock_api, _get_all, _auth):
def test_add_label_appends_to_issue(self, mock_api, _auth):
existing = [_make_label("chore", 5)]
def se(method, path, auth, payload=None):
if method == "GET":
return existing
if method == "POST":
return [{"name": "chore"}]
return None
@@ -205,21 +212,19 @@ class TestModes(unittest.TestCase):
self.assertFalse(any(c[0][0] == "PUT" for c in mock_api.call_args_list))
@patch("manage_labels.get_auth_header", return_value=FAKE_AUTH)
@patch("manage_labels.api_get_all", return_value=[])
@patch("manage_labels.api")
def test_add_label_unknown_makes_no_write(self, mock_api, _get_all, _auth):
def test_add_label_unknown_makes_no_write(self, mock_api, _auth):
mock_api.side_effect = lambda *a, **k: [] if a[0] == "GET" else None
manage_labels.main(["--add-label", "42", "ghost"])
# No write via api() for an undefined label.
self.assertTrue(all(c[0][0] == "GET" for c in mock_api.call_args_list)
or len(mock_api.call_args_list) == 0)
# Only the GET label lookup; no POST/PUT for an undefined label.
self.assertTrue(all(c[0][0] == "GET" for c in mock_api.call_args_list))
@patch("manage_labels.get_auth_header", return_value=FAKE_AUTH)
@patch("manage_labels.api_get_all", return_value=[_make_label("chore", 5)])
@patch("manage_labels.api")
def test_add_label_dry_makes_no_write(self, mock_api, _get_all, _auth):
def test_add_label_dry_makes_no_write(self, mock_api, _auth):
mock_api.side_effect = lambda *a, **k: [_make_label("chore", 5)] if a[0] == "GET" else None
manage_labels.main(["--dry", "--add-label", "42", "chore"])
self.assertTrue(all(c[0][0] == "GET" for c in mock_api.call_args_list)
or len(mock_api.call_args_list) == 0)
self.assertTrue(all(c[0][0] == "GET" for c in mock_api.call_args_list))
@patch("manage_labels.get_auth_header", return_value=FAKE_AUTH)
@patch("manage_labels.api")
-3
View File
@@ -17,7 +17,6 @@ class TestMcpDaemonGuard(unittest.TestCase):
mcp_daemon_guard.ALLOW_DIRECT_IMPORT_ENV,
"PYTEST_CURRENT_TEST",
}}
env["GITEA_TEST_FORCE_UNSANCTIONED"] = "1"
with patch.dict(os.environ, env, clear=True):
with self.assertRaises(mcp_daemon_guard.UnsanctionedRuntimeError):
mcp_daemon_guard.assert_sanctioned_mutation_runtime("test")
@@ -44,7 +43,6 @@ class TestMcpDaemonGuard(unittest.TestCase):
"PYTEST_CURRENT_TEST",
}
}
env["GITEA_TEST_FORCE_UNSANCTIONED"] = "1"
with patch.dict(os.environ, env, clear=True):
with self.assertRaises(mcp_daemon_guard.UnsanctionedRuntimeError):
mcp_daemon_guard.assert_keychain_access_allowed()
@@ -60,7 +58,6 @@ class TestMcpDaemonGuard(unittest.TestCase):
"PYTEST_CURRENT_TEST",
}
}
env["GITEA_TEST_FORCE_UNSANCTIONED"] = "1"
with patch.dict(os.environ, env, clear=True):
with self.assertRaises(mcp_daemon_guard.UnsanctionedRuntimeError):
gitea_auth.get_auth_header("gitea.prgs.cc")
+2 -55
View File
@@ -6,9 +6,6 @@ import review_merge_state_machine as rmsm
class TestMcpNamespaceHealth(unittest.TestCase):
def setUp(self):
gitea_mcp_server._LIVE_NAMESPACE_HEALTH.clear()
def test_registered_tool_but_live_eof_blocks_merge(self):
result = mcp_namespace_health.classify_namespace_probe(
"gitea-reviewer",
@@ -27,7 +24,6 @@ class TestMcpNamespaceHealth(unittest.TestCase):
},
},
config_path="/Users/jasonwalker/.gemini/config/mcp_config.json",
probe_source="client_namespace",
)
self.assertFalse(result["healthy"])
@@ -35,8 +31,6 @@ class TestMcpNamespaceHealth(unittest.TestCase):
self.assertTrue(result["required_tool_registered"])
self.assertFalse(result["required_tool_callable"])
self.assertTrue(result["blocks_merge_workflow"])
self.assertFalse(result["ide_namespace_proven"])
self.assertEqual(result["probe_source"], "client_namespace")
self.assertEqual(result["diagnostics"]["process_pid"], 4321)
self.assertEqual(result["diagnostics"]["profile"], "prgs-reviewer")
self.assertEqual(
@@ -47,44 +41,26 @@ class TestMcpNamespaceHealth(unittest.TestCase):
self.assertIn("gitea-reviewer", result["reasons"][0])
self.assertIn("gitea_whoami", result["reasons"][0])
def test_successful_client_namespace_invocation_is_ide_proven(self):
def test_successful_live_invocation_is_healthy(self):
result = mcp_namespace_health.classify_namespace_probe(
"gitea-author",
registered_tools=["gitea_whoami"],
probe_result={"success": True, "result": {"authenticated": True}},
process={"pid": 1234, "profile": "prgs-author"},
config_path="/tmp/mcp_config.json",
probe_source="client_namespace",
)
self.assertTrue(result["healthy"])
self.assertTrue(result["required_tool_registered"])
self.assertTrue(result["required_tool_callable"])
self.assertTrue(result["ide_namespace_proven"])
self.assertFalse(result["blocks_merge_workflow"])
self.assertIsNone(result["error_type"])
def test_offline_spawn_success_is_not_ide_proof(self):
result = mcp_namespace_health.classify_namespace_probe(
"gitea-merger",
registered_tools=["gitea_whoami"],
probe_result={"success": True, "result": {}},
process={"pid": 99, "profile": "prgs-merger"},
probe_source="offline_spawn",
)
self.assertTrue(result["healthy"])
self.assertFalse(result["ide_namespace_proven"])
self.assertFalse(result["blocks_merge_workflow"])
self.assertTrue(
any("offline_spawn" in r for r in result["reasons"])
)
def test_registered_missing_required_tool_fails_before_probe_success(self):
result = mcp_namespace_health.classify_namespace_probe(
"gitea-tools",
registered_tools=["gitea_whoami"],
probe_result={"success": True, "result": {}},
probe_source="client_namespace",
)
self.assertFalse(result["healthy"])
@@ -92,31 +68,23 @@ class TestMcpNamespaceHealth(unittest.TestCase):
self.assertFalse(result["required_tool_registered"])
self.assertEqual(result["error_type"], "tool_missing")
def test_server_tool_exposes_same_assessment_and_records_session(self):
def test_server_tool_exposes_same_assessment(self):
result = gitea_mcp_server.gitea_assess_mcp_namespace_health(
"gitea-merger",
registered_tools=["gitea_whoami"],
probe_result={"success": False, "error": "transport closed"},
process={"pid": 9876, "profile": "prgs-merger"},
probe_source="client_namespace",
)
self.assertFalse(result["success"])
self.assertEqual(result["error_type"], "namespace_eof")
self.assertEqual(result["namespace"], "gitea-merger")
self.assertEqual(result["diagnostics"]["process_pid"], 9876)
self.assertIn("gitea-merger", gitea_mcp_server._LIVE_NAMESPACE_HEALTH)
gate = gitea_mcp_server._live_namespace_health_gate("merge_pr")
self.assertTrue(gate)
self.assertTrue(any("gitea-merger" in r for r in gate))
class TestLiveNamespaceBlocksMerge(unittest.TestCase):
"""AC5: a broken live namespace must hard-block the review/merge state machine."""
def setUp(self):
gitea_mcp_server._LIVE_NAMESPACE_HEALTH.clear()
def _merge_ready_completion(self):
# Completion through PRE_MERGE_RECHECK is the state where a clean merge
# is otherwise allowed (see test_merge_allowed_with_pre_merge_gates).
@@ -173,7 +141,6 @@ class TestLiveNamespaceBlocksMerge(unittest.TestCase):
registered_tools=["gitea_whoami", "gitea_adopt_merger_pr_lease"],
probe_result={"success": False, "error": "client is closing: EOF"},
process={"pid": 555, "profile": "prgs-merger"},
probe_source="client_namespace",
)
self.assertTrue(verdict["blocks_merge_workflow"])
blocked = rmsm.can_merge(
@@ -183,26 +150,6 @@ class TestLiveNamespaceBlocksMerge(unittest.TestCase):
)
self.assertFalse(blocked["allowed"])
def test_offline_spawn_does_not_authorize_mutation_gate(self):
gitea_mcp_server.gitea_assess_mcp_namespace_health(
"gitea-merger",
registered_tools=["gitea_whoami"],
probe_result={"success": True, "result": {}},
probe_source="offline_spawn",
)
gate = gitea_mcp_server._live_namespace_health_gate("merge_pr")
self.assertTrue(gate)
self.assertTrue(any("offline_spawn" in r or "client_namespace" in r for r in gate))
def test_client_namespace_healthy_clears_mutation_gate(self):
gitea_mcp_server.gitea_assess_mcp_namespace_health(
"gitea-merger",
registered_tools=["gitea_whoami"],
probe_result={"success": True, "result": {}},
probe_source="client_namespace",
)
self.assertEqual(gitea_mcp_server._live_namespace_health_gate("merge_pr"), [])
if __name__ == "__main__":
unittest.main()
+6 -152
View File
@@ -5,7 +5,6 @@ the MCP protocol) with mocked API responses.
"""
import json
import os
import shutil
import sys
import tempfile
import unittest
@@ -48,22 +47,6 @@ import gitea_config # noqa: E402
import mcp_server
import issue_lock_store
import gitea_auth
_orig_api_request = gitea_auth.api_request
def mockable_api_request(*args, **kwargs):
import mcp_server
return mcp_server.api_request(*args, **kwargs)
def setUpModule():
gitea_auth.api_request = mockable_api_request
patch("mcp_server._enforce_root_checkout_guard").start()
patch("mcp_server._enforce_branches_only_author_mutation").start()
def tearDownModule():
gitea_auth.api_request = _orig_api_request
patch.stopall()
FAKE_AUTH = "Basic dGVzdDp0ZXN0"
FULL_HEAD_SHA = "a" * 40
@@ -791,9 +774,6 @@ class TestMergePR(unittest.TestCase):
def setUp(self):
import reviewer_pr_lease
# Clean ledger each merge test so residual/host durable #332 state
# cannot short-circuit eligibility gates (#590 / #594).
mcp_server._save_review_decision_lock(None)
mcp_server.gitea_load_review_workflow()
self._lease_patch = _install_owned_reviewer_lease(8)
self._lease_patch.start()
@@ -1023,64 +1003,6 @@ class TestMergePR(unittest.TestCase):
r["reasons"])
self._assert_no_merge_call(mock_api)
@patch("mcp_server.api_request")
@patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
def test_env_clear_does_not_adopt_host_review_mutation_ledger(
self, _auth, mock_api
):
"""#590: patch.dict(clear=True) must not load host terminal mutations.
Simulates a dirty host session-state file for profile gitea-default
(the profile active when env is fully cleared). Isolation must keep
the #332 hard-stop ledger clean so the empty-profile gate fires.
"""
import tempfile
import mcp_session_state
poison_dir = tempfile.mkdtemp(prefix="gitea-host-poison-")
mcp_session_state.save_state(
kind=mcp_session_state.KIND_DECISION_LOCK,
profile_identity="gitea-default",
state_dir=poison_dir,
payload={
"task": "review_pr",
"remote": "prgs",
"final_review_decision_ready": True,
"ready_pr_number": 8,
"ready_action": "request_changes",
"live_mutations": [
{
"pr_number": 8,
"action": "request_changes",
"review_id": 99,
"review_state": "request_changes",
}
],
},
)
# If isolation only used the env var, clear=True would fall back to
# DEFAULT_STATE_DIR and adopt this poison ledger.
mcp_server._REVIEW_DECISION_LOCK = None
mock_api.side_effect = [{"login": "merger-bot"}, self._pr("author-bot")]
with patch.object(mcp_session_state, "DEFAULT_STATE_DIR", poison_dir):
with patch.dict(os.environ, {}, clear=True):
r = gitea_merge_pr(
pr_number=8,
confirmation=self._confirm(8),
remote="prgs",
)
self.assertFalse(r["performed"])
self.assertIn(
"profile has no configured allowed operations (fail closed)",
r["reasons"],
)
self.assertFalse(
any("terminal review mutation already consumed" in x for x in r["reasons"]),
msg=f"host ledger leaked into reasons: {r['reasons']}",
)
self._assert_no_merge_call(mock_api)
@patch("mcp_server.api_request")
@patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
def test_profile_without_merge_permission_blocks(self, _auth, mock_api):
@@ -1380,11 +1302,11 @@ class TestReviewPR(unittest.TestCase):
self.assertIn("Review/Merge Blocked", result["message"])
self.assertIn("Author profile", result["message"])
@patch("mcp_server.api_fetch_page")
@patch("mcp_server.api_get_all")
@patch("mcp_server.api_request")
@patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
@patch("mcp_server.get_profile")
def test_legacy_review_pr_self_approval_blocked(self, mock_get_profile, _auth, mock_api, mock_fetch):
def test_legacy_review_pr_self_approval_blocked(self, mock_get_profile, _auth, mock_api, mock_get_all):
mock_get_profile.return_value = {
"profile_name": "gitea-reviewer",
"allowed_operations": ["read", "approve"],
@@ -1392,10 +1314,7 @@ class TestReviewPR(unittest.TestCase):
"base_url": None,
}
head_sha = FULL_HEAD_SHA
mock_fetch.return_value = (
[{"number": 1, "title": "PR 1", "state": "open", "head": {"ref": "branch1", "sha": head_sha}, "base": {"ref": "master"}, "mergeable": True, "user": {"login": "jcwalker3"}}],
{"page": 1, "per_page": 50, "returned_count": 1, "has_more": False, "next_page": None, "is_final_page": True}
)
mock_get_all.return_value = [{"number": 1, "title": "PR 1", "state": "open", "head": {"ref": "branch1", "sha": head_sha}, "base": {"ref": "master"}, "mergeable": True, "user": {"login": "jcwalker3"}}]
# mock_api responses: 1) /user (inventory), 2) /user (eligibility), 3) /pulls/1 (eligibility)
mock_api.side_effect = [
{"login": "jcwalker3"}, # /api/v1/user (inventory)
@@ -2753,56 +2672,6 @@ class TestTrackerHygieneCleanup(unittest.TestCase):
self.assertTrue(res["success"])
self.assertEqual(res["cleanup_status"].get(1), "not present")
def test_close_issue_blocks_unproven_expected_preexisting_failure(self):
# #529: a closure report calling a non-zero suite exit an "expected
# pre-existing failure" without pre-merge proof must fail closed and
# never PATCH the issue state.
patched = []
def api_side_effect(method, url, auth, payload=None):
if method == "PATCH":
patched.append(url)
return {}
self.mock_api.side_effect = api_side_effect
res = gitea_close_issue(
issue_number=1,
closure_report=(
"Full suite: 1 failed. Expected pre-existing failure, safe to close."
),
)
self.assertFalse(res["success"])
self.assertTrue(res.get("blocked"))
self.assertTrue(res.get("reasons"))
self.assertFalse(
patched, "must not PATCH issue state when the closure gate blocks"
)
def test_close_issue_allows_proven_baseline_closure(self):
def api_side_effect(method, url, auth, payload=None):
if method == "PATCH" and "issues/1" in url:
return {"state": "closed"}
if method == "GET" and "labels" in url and "issues" not in url:
return [{"name": "bug", "id": 2}]
if method == "GET" and "issues/1" in url:
return {"labels": [{"name": "bug"}]}
return {}
self.mock_api.side_effect = api_side_effect
res = gitea_close_issue(
issue_number=1,
closure_report=(
"Full suite: 1 failed, expected pre-existing baseline failure "
"proven on the PR pre-merge base commit.\n"
"Pre-merge base commit: 1a2b3c4d5e6f7a8b9c0d1e2f3a4b5c6d7e8f9a0b\n"
"Tested commit: 1a2b3c4d5e6f7a8b9c0d1e2f3a4b5c6d7e8f9a0b\n"
"Command: venv/bin/python -m pytest -q\n"
"Exit status: 1\n"
"Failure signature: AssertionError: None is not true\n"
),
)
self.assertTrue(res["success"])
def test_merge_pr_with_closes_removes_label(self):
import reviewer_pr_lease
@@ -3831,15 +3700,7 @@ class TestIssueLocking(unittest.TestCase):
@patch("mcp_server.api_get_all", return_value=[])
@patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
def test_lock_issue_blocks_expired_same_operation_lease_for_recovery(self, _auth, _api, _git_state):
"""#601: expired lease still blocks takeover when owner pid is live AND worktree exists.
Dead-pid / missing-worktree reclaim is covered by issue_lock_store unit tests.
This MCP path must remain fail-closed for sticky expired foreign ownership.
"""
prgs_repo = mcp_server.REMOTES["prgs"]["repo"]
# Present worktree + live pid => reclaim_allowed=False even though expires_at is past.
sticky_worktree = tempfile.mkdtemp(prefix="gitea-sticky-lease-")
self.addCleanup(lambda: shutil.rmtree(sticky_worktree, ignore_errors=True))
issue_lock_store.save_lock_file(
issue_lock_store.lock_file_path(
remote="prgs",
@@ -3853,22 +3714,15 @@ class TestIssueLocking(unittest.TestCase):
"remote": "prgs",
"org": "Scaled-Tech-Consulting",
"repo": prgs_repo,
"worktree_path": sticky_worktree,
"session_pid": os.getpid(),
"pid": os.getpid(),
"worktree_path": "/tmp/other-worktree",
"work_lease": {
"operation_type": "author_issue_work",
"expires_at": "2000-01-01T00:00:00Z",
},
},
)
with patch.object(issue_lock_store, "is_process_alive", return_value=True):
with self.assertRaises(RuntimeError) as ctx:
gitea_lock_issue(
issue_number=196,
branch_name="feat/issue-196-mutations",
remote="prgs",
)
with self.assertRaises(RuntimeError) as ctx:
gitea_lock_issue(issue_number=196, branch_name="feat/issue-196-mutations", remote="prgs")
self.assertIn("Recovery review is required before takeover", str(ctx.exception))
@patch("mcp_server.api_get_all", return_value=[])
-61
View File
@@ -67,66 +67,5 @@ class TestMcpStaleRuntime(unittest.TestCase):
# But does NOT contain missing author profile error
self.assertFalse(any("None of the matching profiles for task" in r for r in reasons_author))
@patch("subprocess.run")
@patch("os.path.getmtime")
@patch("os.path.exists")
@patch("os.getpid")
@patch.dict("os.environ", {"GITEA_FORCE_MCP_RUNTIME_CHECK": "1"})
def test_git_head_change_triggers_staleness(self, mock_getpid, mock_exists, mock_getmtime, mock_run):
# Set boot SHA to FAKE1 and current to FAKE2
gitea_mcp_server._process_boot_head_sha = "FAKE1"
mock_getpid.return_value = 12345
mock_exists.return_value = True
# Code time is in the past (fresh process chronologically)
code_time = datetime(2026, 7, 8, 11, 0, 0)
mock_getmtime.return_value = code_time.timestamp()
ps_output = (
" PID LSTART COMMAND\n"
"12345 Wed Jul 8 12:00:00 2026 /path/to/python mcp_server.py\n"
)
mock_run_ps = MagicMock()
mock_run_ps.stdout = ps_output
mock_run_env = MagicMock()
mock_run_env.stdout = "GITEA_MCP_PROFILE=prgs-author"
mock_run_git = MagicMock()
mock_run_git.stdout = "FAKE2" # different SHA
def side_effect(args, **kwargs):
if args[0] == "ps" and "eww" in args:
return mock_run_env
elif args[0] == "ps":
return mock_run_ps
elif args[0] == "git" and "rev-parse" in args:
return mock_run_git
raise ValueError(f"Unexpected: {args}")
mock_run.side_effect = side_effect
# Stale even though process started AFTER code mtime, because git HEAD changed
reasons = gitea_mcp_server._check_mcp_runtimes_diagnostics("create_issue", ["prgs-author"])
self.assertTrue(any("stale-runtime: The active Gitea MCP server process is stale" in r for r in reasons))
@patch("threading.Thread")
@patch("os.utime")
@patch("os.path.exists")
@patch.dict("os.environ", {"MCP_CONFIG_PATH": "/tmp/mcp_config.json"})
def test_auto_restart_trigger_touches_and_spawns(self, mock_exists, mock_utime, mock_thread):
mock_exists.return_value = True
gitea_mcp_server._restart_triggered = False
# Ensure we are not skipped in test mode for testing purposes
with patch("gitea_mcp_server._preflight_in_test_mode", return_value=False):
gitea_mcp_server._trigger_mcp_auto_restart()
mock_utime.assert_called_once_with("/tmp/mcp_config.json", None)
mock_thread.assert_called_once()
self.assertTrue(gitea_mcp_server._restart_triggered)
if __name__ == "__main__":
unittest.main()
-90
View File
@@ -42,96 +42,6 @@ def _lease_comment(
HEAD = "f" * 40
class TestDescribeSessionLeaseProof(unittest.TestCase):
def setUp(self):
leases.clear_session_lease()
def test_empty_session_is_none_kind(self):
proof = mla.describe_session_lease_proof(None)
self.assertIsNone(proof["lease_proof_source"])
self.assertEqual(proof["lease_proof_kind"], "none")
self.assertFalse(proof["lease_proof_sanctioned"])
def test_manual_seed_without_provenance(self):
leases.record_session_lease({
"pr_number": 536,
"session_id": "manual",
"comment_id": 1,
})
proof = mla.describe_session_lease_proof(leases.get_session_lease())
self.assertIsNone(proof["lease_proof_source"])
self.assertEqual(proof["lease_proof_kind"], "unsanctioned_manual_seed")
self.assertFalse(proof["lease_proof_sanctioned"])
def test_sanctioned_adopt_fields(self):
leases.record_session_lease(
{
"pr_number": 536,
"session_id": "merger-sess",
"comment_id": 700,
},
lease_provenance=mla.build_lease_provenance(
source=mla.SOURCE_ADOPT,
comment_id=700,
adopted_from_session_id="reviewer-sess",
adoption_reason=mla.DEFAULT_ADOPTION_REASON,
),
)
proof = mla.describe_session_lease_proof(leases.get_session_lease())
self.assertEqual(proof["lease_proof_source"], mla.SOURCE_ADOPT)
self.assertEqual(proof["lease_proof_kind"], "sanctioned_adoption")
self.assertTrue(proof["lease_proof_sanctioned"])
self.assertEqual(
proof["lease_recovery_reason"], mla.DEFAULT_ADOPTION_REASON
)
self.assertEqual(proof["lease_proof_comment_id"], 700)
self.assertEqual(proof["lease_adopted_from_session_id"], "reviewer-sess")
def test_sanctioned_acquire_fields(self):
leases.record_session_lease(
{
"pr_number": 536,
"session_id": "rev",
"comment_id": 50,
},
lease_provenance=mla.build_lease_provenance(
source=mla.SOURCE_ACQUIRE,
comment_id=50,
),
)
proof = mla.describe_session_lease_proof(leases.get_session_lease())
self.assertEqual(proof["lease_proof_source"], mla.SOURCE_ACQUIRE)
self.assertEqual(proof["lease_proof_kind"], "sanctioned_acquire")
self.assertTrue(proof["lease_proof_sanctioned"])
class TestManualLeaseProofHandoffAudit(unittest.TestCase):
def test_clean_merge_report_passes(self):
text = (
"Merged via gitea_merge_pr after gitea_adopt_merger_pr_lease. "
"lease_proof_source: gitea_adopt_merger_pr_lease"
)
result = mla.assess_manual_lease_proof_handoff(text)
self.assertTrue(result["proven"])
self.assertFalse(result["block"])
def test_manual_seeded_claim_without_mcp_evidence_blocks(self):
text = "Merged using manually seeded lease proof from prior session."
result = mla.assess_manual_lease_proof_handoff(text)
self.assertFalse(result["proven"])
self.assertTrue(result["block"])
self.assertTrue(any("#535" in r for r in result["reasons"]))
def test_historical_manual_mention_allowed_with_adoption_evidence(self):
text = (
"Historical incident used manually seeded lease; this merge used "
"gitea_adopt_merger_pr_lease with adoption_comment_id: 8288."
)
result = mla.assess_manual_lease_proof_handoff(text)
self.assertTrue(result["proven"])
self.assertFalse(result["block"])
class TestSanctionedProvenance(unittest.TestCase):
def setUp(self):
leases.clear_session_lease()
-15
View File
@@ -88,21 +88,6 @@ class TestControlPlaneGuide(GuideTestBase):
blob = " ".join(g["guidance"]).lower()
self.assertIn("forbidden", blob)
self.assertIn("review", blob)
self.assertIn("resolved_repository", g)
@patch("mcp_server.api_request", return_value={"login": "author-bot"})
@patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
def test_guide_explicit_org_repo_parameters(self, _auth, _api):
with patch.dict(os.environ, AUTHOR_ENV, clear=True):
g = mcp_get_control_plane_guide(
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
)
self.assertEqual(
g["resolved_repository"],
{"org": "Scaled-Tech-Consulting", "repo": "Gitea-Tools"},
)
@patch("mcp_server.api_request", return_value={"login": "reviewer-bot"})
@patch("mcp_server.get_auth_header", return_value=FAKE_AUTH)
-119
View File
@@ -1,119 +0,0 @@
"""Post-merge moot validation wording + label tests (#529, criteria 1/4/5)."""
import unittest
from post_merge_validation import (
BASELINE_ACCEPTED_OUTCOME,
BLOCKED_OUTCOME,
CLEAN_PASS_OUTCOME,
LABEL_BASELINE_ACCEPTED,
LABEL_BLOCKED,
LABEL_CLEAN_PASS,
LABEL_POST_MERGE_MOOT,
POST_MERGE_MOOT_OUTCOME,
assess_post_merge_validation,
process_state_label,
)
from final_report_validator import assess_final_report_validator
from issue_workflow_labels import CANONICAL_LABELS, VALIDATION_LABELS
_MOOT_PROOF = (
"Validation status: post-merge moot validation\n"
"PR state: merged\n"
"Merge commit sha: 1a2b3c4d5e6f7a8b9c0d1e2f3a4b5c6d7e8f9a0b\n"
"Validation finding: full suite passed, for the record.\n"
)
class TestPostMergeValidation(unittest.TestCase):
def test_not_applicable_when_no_merged_or_moot_signal(self):
result = assess_post_merge_validation(
"Review decision: approve. Validation: full suite passed."
)
self.assertFalse(result["block"])
self.assertTrue(result["skipped"])
def test_active_approval_on_merged_pr_blocked(self):
report = (
"PR is already merged. Review decision: approve. "
"Validation: full suite passed."
)
result = assess_post_merge_validation(report)
self.assertTrue(result["block"])
self.assertEqual(result["outcome"], POST_MERGE_MOOT_OUTCOME)
self.assertEqual(result["process_state_label"], LABEL_POST_MERGE_MOOT)
def test_active_approval_on_merged_pr_via_structured_signal_blocked(self):
report = "Review decision: approve. Validation: full suite passed."
result = assess_post_merge_validation(report, pr_merged_or_closed=True)
self.assertTrue(result["block"])
def test_moot_wording_without_proof_blocked(self):
report = "Recording post-merge moot validation for this PR."
result = assess_post_merge_validation(report)
self.assertTrue(result["block"])
self.assertTrue(result["reasons"])
def test_moot_wording_with_full_proof_allowed(self):
result = assess_post_merge_validation(_MOOT_PROOF)
self.assertFalse(result["block"])
self.assertEqual(result["outcome"], POST_MERGE_MOOT_OUTCOME)
def test_merged_signal_only_guides_without_blocking(self):
result = assess_post_merge_validation(
"PR was already merged before review; recording findings."
)
self.assertFalse(result["block"])
self.assertTrue(result["safe_next_action"])
def test_process_state_label_mapping(self):
self.assertEqual(process_state_label(CLEAN_PASS_OUTCOME), LABEL_CLEAN_PASS)
self.assertEqual(
process_state_label(BASELINE_ACCEPTED_OUTCOME), LABEL_BASELINE_ACCEPTED
)
self.assertEqual(process_state_label(BLOCKED_OUTCOME), LABEL_BLOCKED)
self.assertEqual(
process_state_label(POST_MERGE_MOOT_OUTCOME), LABEL_POST_MERGE_MOOT
)
self.assertIsNone(process_state_label("nonsense"))
class TestValidationLabelsRegistered(unittest.TestCase):
def test_validation_labels_are_canonical(self):
for label in (
LABEL_CLEAN_PASS,
LABEL_BASELINE_ACCEPTED,
LABEL_BLOCKED,
LABEL_POST_MERGE_MOOT,
):
self.assertIn(label, VALIDATION_LABELS)
self.assertIn(label, CANONICAL_LABELS)
class TestPostMergeValidationWiredIntoReview(unittest.TestCase):
def test_review_pr_blocks_active_approval_on_merged_pr(self):
report = (
"PR is already merged. Review decision: approve. "
"Validation: full suite passed."
)
result = assess_final_report_validator(report, "review_pr")
self.assertTrue(result["blocked"])
self.assertTrue(
any(
f["rule_id"] == "reviewer.post_merge_validation"
for f in result["findings"]
)
)
def test_review_pr_allows_proven_post_merge_moot(self):
result = assess_final_report_validator(_MOOT_PROOF, "review_pr")
self.assertFalse(
any(
f["rule_id"] == "reviewer.post_merge_validation"
for f in result["findings"]
)
)
if __name__ == "__main__":
unittest.main()
+3 -7
View File
@@ -76,17 +76,13 @@ class TestPreflightReadSurvival(unittest.TestCase):
self.assertIn("task mismatch", str(ctx.exception))
def test_capability_consumed_after_mutation_gate(self):
# Use reconciler/close_pr so this purity-order test does not require a
# branches/ worktree (author create_issue would hit #274/#683 guards).
# Test isolation stays explicit; production author guards remain live
# under force-on (see tests/test_issue_683_workflow_scope_guards.py).
mcp_server.record_preflight_check("whoami")
mcp_server.record_preflight_check(
"capability", resolved_role="reconciler", resolved_task="close_pr"
"capability", resolved_role="author", resolved_task="create_issue"
)
mcp_server.verify_preflight_purity(task="close_pr")
mcp_server.verify_preflight_purity(task="create_issue")
with self.assertRaises(RuntimeError) as ctx:
mcp_server.verify_preflight_purity(task="close_pr")
mcp_server.verify_preflight_purity(task="create_issue")
self.assertIn("has not been resolved", str(ctx.exception))
def test_whoami_recovery_after_violation_clears_capability(self):
+24 -15
View File
@@ -64,45 +64,54 @@ class TestMarkIssueCLI(unittest.TestCase):
with self.assertRaises(SystemExit):
mark_issue.main(["10", "bogus_action"])
@patch("mark_issue.api_get_all", return_value=[{"id": 101, "name": "status:in-progress"}])
@patch("mark_issue.api_request")
@patch("mark_issue.get_auth_header", return_value=FAKE_AUTH)
def test_successful_start(self, _auth, mock_api, mock_get_all):
mock_api.return_value = [{"name": "status:in-progress"}]
def test_successful_start(self, _auth, mock_api):
# First call is GET labels, second is POST label
mock_api.side_effect = [
[{"id": 101, "name": "status:in-progress"}],
[{"name": "status:in-progress"}],
]
with contextlib.redirect_stdout(io.StringIO()), contextlib.redirect_stderr(io.StringIO()):
rc = mark_issue.main(["15", "start"])
self.assertEqual(rc, 0)
mock_get_all.assert_called()
self.assertIn("/labels", mock_get_all.call_args[0][0])
self.assertEqual(mock_api.call_count, 2)
# Verify GET labels call
get_call = mock_api.call_args_list[0]
self.assertEqual(get_call[0][0], "GET")
self.assertIn("/labels?limit=100", get_call[0][1])
# Verify POST labels call
post_call = mock_api.call_args_list[0]
post_call = mock_api.call_args_list[1]
self.assertEqual(post_call[0][0], "POST")
self.assertIn("/issues/15/labels", post_call[0][1])
self.assertEqual(post_call[0][3], {"labels": [101]})
@patch("mark_issue.api_get_all", return_value=[{"id": 101, "name": "status:in-progress"}])
@patch("mark_issue.api_request")
@patch("mark_issue.get_auth_header", return_value=FAKE_AUTH)
def test_successful_done(self, _auth, mock_api, _get_all):
mock_api.return_value = None
def test_successful_done(self, _auth, mock_api):
# First call is GET labels, second is DELETE label
mock_api.side_effect = [
[{"id": 101, "name": "status:in-progress"}],
None,
]
rc = mark_issue.main(["15", "done"])
self.assertEqual(rc, 0)
self.assertEqual(mock_api.call_count, 1)
self.assertEqual(mock_api.call_count, 2)
# Verify DELETE labels call
delete_call = mock_api.call_args_list[0]
delete_call = mock_api.call_args_list[1]
self.assertEqual(delete_call[0][0], "DELETE")
self.assertIn("/issues/15/labels/101", delete_call[0][1])
@patch("mark_issue.api_get_all", return_value=[{"id": 1, "name": "bug"}])
@patch("mark_issue.api_request")
@patch("mark_issue.get_auth_header", return_value=FAKE_AUTH)
def test_label_not_found(self, _auth, mock_api, _get_all):
# Paginated inventory returns no status:in-progress label
def test_label_not_found(self, _auth, mock_api):
# GET labels returns no status:in-progress label
mock_api.return_value = [{"id": 1, "name": "bug"}]
rc = mark_issue.main(["15", "start"])
self.assertEqual(rc, 1)
mock_api.assert_not_called()
if __name__ == "__main__":
+5 -20
View File
@@ -10,11 +10,8 @@ sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
import gitea_mcp_server as srv
FAKE_AUTH = "token test"
current_file_path = Path(__file__).resolve()
if "branches" in current_file_path.parts:
CONTROL_CHECKOUT_ROOT = str(current_file_path.parents[3])
else:
CONTROL_CHECKOUT_ROOT = str(current_file_path.parents[1])
CONTROL_CHECKOUT_ROOT = str(Path(__file__).resolve().parents[3])
RECONCILER_PROFILE = {
"profile_name": "prgs-reconciler",
"allowed_operations": ["gitea.read", "gitea.pr.close", "gitea.pr.comment"],
@@ -86,21 +83,9 @@ class TestReconcilerCloseWorkspaceGuard(unittest.TestCase):
):
srv._preflight_resolved_role = "author"
with patch.object(srv, "PROJECT_ROOT", CONTROL_CHECKOUT_ROOT):
try:
res = srv.gitea_create_issue(title="Test", body="body")
except RuntimeError as exc:
self.assertIn("stable control checkout", str(exc))
else:
# #683 typed blocker at mutation entrypoint
self.assertFalse(res.get("success"))
blob = " ".join(res.get("reasons") or []) + str(
res.get("blocker_kind") or ""
)
self.assertTrue(
"stable control checkout" in blob
or "missing_issue_worktree" in blob
or "control checkout" in blob.lower()
)
with self.assertRaises(RuntimeError) as ctx:
srv.gitea_create_issue(title="Test", body="body")
self.assertIn("stable control checkout", str(ctx.exception))
if __name__ == "__main__":
-245
View File
@@ -1,245 +0,0 @@
"""Issue #525: reconciler supersession close path."""
import sys
import unittest
from unittest.mock import patch
sys.path.insert(0, str(__import__("pathlib").Path(__file__).resolve().parent.parent))
import mcp_server # noqa: E402
import role_session_router # noqa: E402
import task_capability_map # noqa: E402
from review_proofs import assess_reconciler_supersession_close_gate # noqa: E402
HEAD = "0fdc8f582026b72a229d59a172c0a63ac4aaeaf9"
MERGE = "1111111111111111111111111111111111111111"
TARGET = "2222222222222222222222222222222222222222"
def _target_pr(mergeable=False):
return {
"number": 490,
"state": "open",
"mergeable": mergeable,
"head": {"sha": "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"},
}
def _superseding_pr():
return {
"number": 502,
"state": "closed",
"merged": True,
"merge_commit_sha": MERGE,
"head": {"sha": HEAD},
}
class TestReconcilerSupersessionCapabilityMap(unittest.TestCase):
def test_supersession_tasks_route_to_reconciler(self):
self.assertEqual(
task_capability_map.required_permission(
"reconcile_close_superseded_pr"),
"gitea.pr.close",
)
self.assertEqual(
task_capability_map.required_role("reconcile_close_superseded_pr"),
"reconciler",
)
self.assertEqual(
task_capability_map.required_permission(
"reconcile_close_satisfied_issue"),
"gitea.issue.close",
)
self.assertEqual(
task_capability_map.required_role("reconcile_create_followup_issue"),
"reconciler",
)
def test_author_session_cannot_route_supersession_close(self):
result = role_session_router.route_task_session(
"reconcile_close_superseded_pr",
active_profile="prgs-author",
active_role_kind="author",
allowed_in_current_session=False,
)
self.assertEqual(result["route_result"], "wrong_role_stop")
self.assertFalse(result["downstream_allowed"])
class TestReconcilerSupersessionCloseGate(unittest.TestCase):
def _gate(self, **overrides):
kwargs = {
"target_pr_number": 490,
"target_pr_state": "open",
"target_pr_mergeable": False,
"target_independently_required": False,
"superseding_pr_number": 502,
"superseding_pr_state": "closed",
"superseding_pr_merged": True,
"superseding_merge_commit_sha": MERGE,
"superseding_head_sha": HEAD,
"target_branch": "master",
"target_branch_sha": TARGET,
"superseding_head_is_ancestor_of_target": True,
"canonical_comment_valid": True,
"canonical_comment_mentions_superseding_pr": True,
"canonical_comment_mentions_merge_commit": True,
"close_pr_capability": True,
"close_issue_capability": True,
"target_issue_state": "open",
"issue_satisfied_by_superseding": True,
}
kwargs.update(overrides)
return assess_reconciler_supersession_close_gate(**kwargs)
def test_supersession_close_allowed_with_full_proof(self):
result = self._gate()
self.assertEqual(result["outcome"], "SUPERSESSION_CLOSE_ALLOWED")
self.assertTrue(result["pr_close_allowed"])
self.assertTrue(result["issue_close_allowed"])
self.assertFalse(result["review_allowed"])
self.assertFalse(result["merge_allowed"])
def test_mergeable_target_still_blocks(self):
result = self._gate(target_pr_mergeable=True)
self.assertEqual(result["outcome"], "GATE_NOT_PROVEN")
self.assertFalse(result["pr_close_allowed"])
self.assertTrue(any("mergeable" in r for r in result["reasons"]))
def test_requires_canonical_comment_with_merge_commit(self):
result = self._gate(canonical_comment_mentions_merge_commit=False)
self.assertEqual(result["outcome"], "GATE_NOT_PROVEN")
self.assertFalse(result["pr_close_allowed"])
self.assertTrue(any("merge commit" in r for r in result["reasons"]))
def test_superseding_head_must_be_on_target_branch(self):
result = self._gate(superseding_head_is_ancestor_of_target=False)
self.assertEqual(result["outcome"], "SUPERSEDING_PR_NOT_ON_TARGET")
self.assertFalse(result["pr_close_allowed"])
def test_close_capability_required(self):
result = self._gate(close_pr_capability=False)
self.assertEqual(result["outcome"], "RECOVERY_HANDOFF_REQUIRED")
self.assertFalse(result["pr_close_allowed"])
class TestReconcilerSupersessionMcpTool(unittest.TestCase):
def _comment(self):
return f"""## Canonical PR State
STATE: superseded
NEXT_ACTION: Close superseded PR #490 and issue #470; PR #502 is canonical.
NEXT_ACTOR: prgs-reconciler
SUMMARY: PR #490 is superseded by merged PR #502 at merge commit {MERGE}.
CANONICAL_ITEM: PR #502
SUPERSEDED_ITEM: PR #490
CLOSE_OR_KEEP_OPEN: close superseded PR #490 and satisfied issue #470
"""
@patch("mcp_server.verify_preflight_purity")
@patch("mcp_server._canonical_comment_gate")
@patch("already_landed_reconcile.is_head_ancestor_of_ref", return_value=True)
@patch("already_landed_reconcile.fetch_target_branch")
@patch("mcp_server._profile_operation_gate", return_value=[])
@patch("mcp_server._auth", return_value="token test")
@patch("mcp_server.api_request")
def test_tool_posts_comment_and_closes_superseded_pr_issue(
self,
api,
_auth,
_profile_gate,
fetch_target,
_ancestor,
canonical_gate,
verify_preflight,
):
fetch_target.return_value = {
"success": True,
"target_branch": "master",
"target_ref": "prgs/master",
"target_branch_sha": TARGET,
}
canonical_gate.return_value = {
"blocked": False,
"canonical_comment_validation": {"valid": True},
}
api.side_effect = [
_target_pr(),
_superseding_pr(),
{"number": 470, "state": "open"},
{"id": 123},
{"state": "closed"},
{"state": "closed"},
]
result = mcp_server.gitea_reconcile_superseded_by_merged_pr(
target_pr_number=490,
superseding_pr_number=502,
target_issue_number=470,
target_independently_required=False,
issue_satisfied_by_superseding=True,
close_pr=True,
close_issue=True,
post_comment=True,
comment_body=self._comment(),
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
)
self.assertTrue(result["success"])
self.assertTrue(result["performed"])
self.assertTrue(result["pr_comment_posted"])
self.assertTrue(result["pr_closed"])
self.assertTrue(result["issue_closed"])
verify_preflight.assert_called_once_with(
"prgs", task="reconcile_close_superseded_pr")
@patch("mcp_server.verify_preflight_purity")
@patch("mcp_server._canonical_comment_gate")
@patch("already_landed_reconcile.is_head_ancestor_of_ref", return_value=True)
@patch("already_landed_reconcile.fetch_target_branch")
@patch("mcp_server._profile_operation_gate", return_value=[])
@patch("mcp_server._auth", return_value="token test")
@patch("mcp_server.api_request")
def test_tool_does_not_mutate_when_target_still_mergeable(
self,
api,
_auth,
_profile_gate,
fetch_target,
_ancestor,
canonical_gate,
verify_preflight,
):
fetch_target.return_value = {
"success": True,
"target_branch": "master",
"target_ref": "prgs/master",
"target_branch_sha": TARGET,
}
canonical_gate.return_value = {
"blocked": False,
"canonical_comment_validation": {"valid": True},
}
api.side_effect = [_target_pr(mergeable=True), _superseding_pr()]
result = mcp_server.gitea_reconcile_superseded_by_merged_pr(
target_pr_number=490,
superseding_pr_number=502,
target_independently_required=False,
close_pr=True,
post_comment=True,
comment_body=self._comment(),
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
)
self.assertFalse(result["success"])
self.assertFalse(result["performed"])
self.assertFalse(result["pr_closed"])
self.assertFalse(result["pr_comment_posted"])
verify_preflight.assert_not_called()
self.assertEqual(api.call_count, 2)
-93
View File
@@ -111,23 +111,6 @@ class TestAssessRemoteRepoMatch(unittest.TestCase):
self.assertIn("Gitea-Tools", message)
self.assertIn("org=", message)
self.assertIn("repo=", message)
# Recovery text must name a tool that actually accepts org/repo (#530 follow-up).
self.assertIn("mcp_get_control_plane_guide", message)
self.assertIn("schema does not list", message)
def test_parse_org_repo_from_https_url(self):
parsed = remote_repo_guard.parse_org_repo_from_remote_url(LOCAL_GITEA_TOOLS_URL)
self.assertEqual(parsed, ("Scaled-Tech-Consulting", "Gitea-Tools"))
def test_parse_org_repo_from_ssh_url(self):
parsed = remote_repo_guard.parse_org_repo_from_remote_url(
"[email protected]:Scaled-Tech-Consulting/Gitea-Tools.git"
)
self.assertEqual(parsed, ("Scaled-Tech-Consulting", "Gitea-Tools"))
def test_parse_org_repo_empty(self):
self.assertIsNone(remote_repo_guard.parse_org_repo_from_remote_url(None))
self.assertIsNone(remote_repo_guard.parse_org_repo_from_remote_url(""))
class TestResolveServerWiring(unittest.TestCase):
@@ -190,82 +173,6 @@ class TestResolveServerWiring(unittest.TestCase):
with self.assertRaises(RuntimeError):
self.server.gitea_view_issue(issue_number=1, remote="prgs")
def test_control_plane_guide_accepts_explicit_gitea_tools(self):
"""Guide schema accepts org/repo and resolves Gitea-Tools, not Timesheet."""
self._set_prgs_default_repo("Timesheet")
with mock.patch.object(
self.server, "api_request", return_value={"login": "guide-bot"}
), mock.patch.object(
self.server, "get_auth_header", return_value="Basic dGVzdA=="
), mock.patch.dict(
os.environ,
{
"GITEA_PROFILE_NAME": "author-test",
"GITEA_ALLOWED_OPERATIONS": "gitea.read",
"GITEA_FORBIDDEN_OPERATIONS": "gitea.pr.merge",
},
clear=False,
):
guide = self.server.mcp_get_control_plane_guide(
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
)
self.assertTrue(guide["read_only"])
self.assertEqual(
guide["resolved_repository"],
{"org": "Scaled-Tech-Consulting", "repo": "Gitea-Tools"},
)
self.assertNotEqual(guide["resolved_repository"]["repo"], "Timesheet")
def test_control_plane_guide_bare_remote_aligns_to_local_gitea_tools(self):
"""Bare remote=prgs in a Gitea-Tools worktree must not stay on Timesheet."""
self._set_prgs_default_repo("Timesheet")
with mock.patch.object(
self.server, "api_request", return_value={"login": "guide-bot"}
), mock.patch.object(
self.server, "get_auth_header", return_value="Basic dGVzdA=="
), mock.patch.dict(
os.environ,
{
"GITEA_PROFILE_NAME": "author-test",
"GITEA_ALLOWED_OPERATIONS": "gitea.read",
"GITEA_FORBIDDEN_OPERATIONS": "gitea.pr.merge",
},
clear=False,
):
guide = self.server.mcp_get_control_plane_guide(remote="prgs")
self.assertEqual(guide["resolved_repository"]["repo"], "Gitea-Tools")
self.assertEqual(
guide["resolved_repository"]["org"], "Scaled-Tech-Consulting"
)
def test_control_plane_guide_wrong_default_fails_closed_without_local(self):
"""Without local remote context, mismatched defaults still fail closed."""
self._set_prgs_default_repo("Timesheet")
with mock.patch.object(
self.server, "_local_git_remote_url", return_value=None
):
# No local URL → preference cannot recover; bare resolve uses Timesheet
# and guard is skipped only because local URL is missing (best-effort).
host, org, repo = self.server._resolve_control_plane_guide_target(
"prgs", None, None, None
)
self.assertEqual(repo, "Timesheet")
def test_control_plane_guide_schema_recovery_matches_parameters(self):
"""Remediation must only recommend parameters the guide actually accepts."""
import inspect
sig = inspect.signature(self.server.mcp_get_control_plane_guide)
self.assertIn("org", sig.parameters)
self.assertIn("repo", sig.parameters)
self.assertIn("remote", sig.parameters)
remediation = remote_repo_guard.REMEDIATION
self.assertIn("mcp_get_control_plane_guide", remediation)
self.assertIn("org=", remediation)
self.assertIn("repo=", remediation)
if __name__ == "__main__":
unittest.main()
-43
View File
@@ -287,49 +287,6 @@ class TestResolveTaskCapability(unittest.TestCase):
self.assertEqual(res["required_operation_permission"], "gitea.pr.merge")
self.assertEqual(res["required_role_kind"], "merger")
@patch("mcp_server.api_request", return_value={"login": "reviewer-user"})
@patch("mcp_server.get_auth_header", return_value="token reviewer-pass")
def test_reviewer_role_with_merge_permission_still_cannot_merge(self, _auth, _api):
# #539: exact permission alone is insufficient. The active profile
# role must also be merger for merge_pr.
config = json.loads(json.dumps(CONFIG_RESOLVER))
config["profiles"]["reviewer-with-merge"] = {
"enabled": True,
"context": "ctx",
"role": "reviewer",
"username": "reviewer-user",
"auth": {"type": "env", "name": "GITEA_TOKEN_REVIEWER"},
"allowed_operations": [
"gitea.read", "gitea.pr.review", "gitea.pr.approve",
"gitea.pr.merge",
],
"forbidden_operations": ["gitea.pr.create", "gitea.branch.push"],
"execution_profile": "reviewer-with-merge",
}
self._write_config(config)
with patch.dict(os.environ, self._env("reviewer-with-merge")):
res = mcp_server.gitea_resolve_task_capability(
task="merge_pr", remote="prgs"
)
self.assertEqual(res["required_role_kind"], "merger")
self.assertEqual(res["active_role_kind"], "reviewer")
self.assertTrue(res["active_profile_permission_allowed"])
self.assertFalse(res["allowed_in_current_session"])
self.assertTrue(res["stop_required"])
self.assertIn("cannot perform merger task", " ".join(res["task_role_guidance"]))
@patch("mcp_server.api_request", return_value={"login": "merger-user"})
@patch("mcp_server.get_auth_header", return_value="token merger-pass")
def test_merger_profile_can_resolve_merge_task(self, _auth, _api):
with patch.dict(os.environ, self._env("merger-profile")):
res = mcp_server.gitea_resolve_task_capability(
task="merge_pr", remote="prgs"
)
self.assertEqual(res["required_role_kind"], "merger")
self.assertEqual(res["active_role_kind"], "merger")
self.assertTrue(res["allowed_in_current_session"])
self.assertFalse(res["stop_required"])
@patch("mcp_server.api_request")
def test_self_review_blocked_structured(self, mock_api):
# Test that self-approve (self-review gate) is blocked and returns structured reasons
+4 -9
View File
@@ -122,11 +122,9 @@ class TestApiRequestRetry(unittest.TestCase):
sleep.assert_not_called()
def test_non_429_error_raises_immediately(self):
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
with self.assertRaises(RuntimeError) as ctx:
_call([_http_error(500, body=b"boom")])
# Fixed message only (#699) — no response body echo.
self.assertEqual(str(ctx.exception), "Gitea HTTP request failed")
self.assertEqual(ctx.exception.http_status, 500)
self.assertIn("HTTP 500", str(ctx.exception))
def test_non_429_error_does_not_sleep(self):
sleep = MagicMock()
@@ -173,12 +171,9 @@ class TestApiRequestRetry(unittest.TestCase):
# max_retries=3 -> 3 sleeps, then the 4th failure raises.
errors = [_http_error(429, retry_after="1") for _ in range(4)]
sleep = MagicMock()
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
with self.assertRaises(RuntimeError) as ctx:
_call(errors, sleep_func=sleep, max_retries=3)
# After retries are exhausted, 429 is a typed HTTP error with fixed
# message (#699); status metadata carries 429.
self.assertEqual(str(ctx.exception), "Gitea HTTP request failed")
self.assertEqual(ctx.exception.http_status, 429)
self.assertIn("HTTP 429", str(ctx.exception))
self.assertEqual(sleep.call_count, 3)
def test_no_infinite_loop_when_always_429(self):
-287
View File
@@ -1,287 +0,0 @@
"""Tests for preserving and resuming prepared Gitea review drafts (#609)."""
from __future__ import annotations
import os
import sys
import tempfile
import unittest
from pathlib import Path
from unittest.mock import patch, MagicMock
sys_path_root = str(Path(__file__).resolve().parent.parent)
if sys_path_root not in sys.path:
sys.path.insert(0, sys_path_root)
import mcp_session_state
import gitea_mcp_server
import reviewer_pr_lease
class TestReviewDrafts(unittest.TestCase):
def setUp(self):
self._tmpdir = tempfile.TemporaryDirectory()
self.state_dir = self._tmpdir.name
self._env = patch.dict(
os.environ,
{
mcp_session_state.STATE_DIR_ENV: self.state_dir,
mcp_session_state.SESSION_PROFILE_LOCK_ENV: "prgs-reviewer",
"GITEA_MCP_PROFILE": "prgs-reviewer",
"GITEA_PROFILE_NAME": "prgs-reviewer",
"PYTEST_CURRENT_TEST": "1", # skip runtime stale checks
},
clear=False,
)
self._env.start()
# Mock workspace binding to pass in test context
self._nwb_patch = patch(
"gitea_mcp_server.nwb.assess_namespace_mutation_workspace",
return_value={"block": False, "mutation_workspace": "/tmp/test-worktree"},
)
self._nwb_patch.start()
# Mock authentication headers
self._auth_patch = patch(
"gitea_mcp_server.get_auth_header",
return_value="Bearer mock-token",
)
self._auth_patch.start()
self._username_patch = patch(
"gitea_mcp_server._authenticated_username",
return_value="sysadmin",
)
self._username_patch.start()
# Clear/Mock local session lease in-memory state
reviewer_pr_lease.clear_session_lease()
def tearDown(self):
self._username_patch.stop()
self._auth_patch.stop()
self._nwb_patch.stop()
self._env.stop()
self._tmpdir.cleanup()
reviewer_pr_lease.clear_session_lease()
@patch("gitea_mcp_server.api_request")
def test_save_draft_success(self, mock_api):
print("GITEA_MCP_SERVER FILE:", gitea_mcp_server.__file__)
print("DIR OF GITEA_MCP_SERVER:", dir(gitea_mcp_server))
mock_api.return_value = {
"head": {"sha": "headsha1234567890"},
"base": {"ref": "master", "sha": "basesha0987654321"},
}
res = gitea_mcp_server.gitea_save_review_draft(
pr_number=587,
action="approve",
body="Good changes",
expected_head_sha="headsha1234567890",
validation_commands="pytest tests/",
validation_results="all pass",
blocker_reason="stale daemon",
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
worktree_path="/tmp/test-worktree",
)
self.assertTrue(res.get("success"))
self.assertEqual(res.get("head_sha"), "headsha1234567890")
# Load draft and verify fields
draft = mcp_session_state.load_state(
kind=mcp_session_state.KIND_REVIEW_DRAFT,
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
profile_identity="prgs-reviewer",
)
self.assertIsNotNone(draft)
self.assertEqual(draft.get("pr_number"), 587)
self.assertEqual(draft.get("action"), "approve")
self.assertEqual(draft.get("body"), "Good changes")
self.assertEqual(draft.get("validation_commands"), "pytest tests/")
self.assertEqual(draft.get("validation_results"), "all pass")
self.assertEqual(draft.get("blocker_reason"), "stale daemon")
self.assertEqual(os.path.realpath(draft.get("worktree_path")), os.path.realpath("/tmp/test-worktree"))
@patch("gitea_mcp_server.api_request")
@patch("gitea_mcp_server._fetch_pr_comments")
@patch("gitea_mcp_server.gitea_submit_pr_review")
def test_resume_draft_and_submit_success(self, mock_submit, mock_comments, mock_api):
# 1. Save draft
mock_api.return_value = {
"state": "open",
"head": {"sha": "headsha1234567890"},
"base": {"ref": "master", "sha": "basesha0987654321"},
}
gitea_mcp_server.gitea_save_review_draft(
pr_number=587,
action="approve",
body="Good changes",
expected_head_sha="headsha1234567890",
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
worktree_path="/tmp/test-worktree",
)
# Seed local session lease
reviewer_pr_lease.record_session_lease({
"pr_number": 587,
"session_id": "session-1234",
})
# Mock Gitea comments to return active reviewer lease owned by us
mock_comments.return_value = [
{
"id": 1,
"user": {"username": "sysadmin"},
"body": (
"<!-- mcp-review-lease:v1 -->\n"
"repo: Scaled-Tech-Consulting/Gitea-Tools\n"
"pr: #587\n"
"reviewer_identity: sysadmin\n"
"profile: prgs-reviewer\n"
"session_id: session-1234\n"
"phase: claimed\n"
),
}
]
mock_submit.return_value = {"performed": True, "success": True}
# 2. Resume draft
res = gitea_mcp_server.gitea_resume_review_draft(
pr_number=587,
submit=True,
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
worktree_path="/tmp/test-worktree",
)
self.assertTrue(res.get("success"))
self.assertTrue(res.get("marked_ready"))
self.assertTrue(res.get("submitted"))
mock_submit.assert_called_once()
# Verify draft was deleted after successful submit
draft = mcp_session_state.load_state(
kind=mcp_session_state.KIND_REVIEW_DRAFT,
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
profile_identity="prgs-reviewer",
)
self.assertIsNone(draft)
@patch("gitea_mcp_server.api_request")
@patch("gitea_mcp_server._fetch_pr_comments")
def test_resume_draft_fails_checks(self, mock_comments, mock_api):
# Save a draft
mock_api.return_value = {
"state": "open",
"head": {"sha": "headsha1234567890"},
"base": {"ref": "master", "sha": "basesha0987654321"},
}
gitea_mcp_server.gitea_save_review_draft(
pr_number=587,
action="approve",
body="Good changes",
expected_head_sha="headsha1234567890",
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
worktree_path="/tmp/test-worktree",
)
# Seed local session lease
reviewer_pr_lease.record_session_lease({
"pr_number": 587,
"session_id": "session-1234",
})
# Mock Gitea comments to return active reviewer lease owned by us
mock_comments.return_value = [
{
"id": 1,
"user": {"username": "sysadmin"},
"body": (
"<!-- mcp-review-lease:v1 -->\n"
"repo: Scaled-Tech-Consulting/Gitea-Tools\n"
"pr: #587\n"
"reviewer_identity: sysadmin\n"
"profile: prgs-reviewer\n"
"session_id: session-1234\n"
"phase: claimed\n"
),
}
]
# Case A: PR closed
mock_api.return_value = {
"state": "closed",
"head": {"sha": "headsha1234567890"},
"base": {"ref": "master", "sha": "basesha0987654321"},
}
res = gitea_mcp_server.gitea_resume_review_draft(
pr_number=587,
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
worktree_path="/tmp/test-worktree",
)
self.assertFalse(res.get("success"))
self.assertIn("PR #587 is not open", res.get("reasons")[0])
# Case B: Head changed
mock_api.return_value = {
"state": "open",
"head": {"sha": "headsha_NEW"},
"base": {"ref": "master", "sha": "basesha0987654321"},
}
res = gitea_mcp_server.gitea_resume_review_draft(
pr_number=587,
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
worktree_path="/tmp/test-worktree",
)
self.assertFalse(res.get("success"))
self.assertIn("PR head SHA changed", res.get("reasons")[0])
# Case C: Target branch changed
mock_api.return_value = {
"state": "open",
"head": {"sha": "headsha1234567890"},
"base": {"ref": "master", "sha": "basesha_NEW"},
}
res = gitea_mcp_server.gitea_resume_review_draft(
pr_number=587,
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
worktree_path="/tmp/test-worktree",
)
self.assertFalse(res.get("success"))
self.assertIn("target branch SHA changed", res.get("reasons")[0])
# Case D: Worktree mismatch
mock_api.return_value = {
"state": "open",
"head": {"sha": "headsha1234567890"},
"base": {"ref": "master", "sha": "basesha0987654321"},
}
res = gitea_mcp_server.gitea_resume_review_draft(
pr_number=587,
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
worktree_path="/tmp/different-worktree",
)
self.assertFalse(res.get("success"))
self.assertIn("worktree binding mismatch", res.get("reasons")[0])
-108
View File
@@ -237,113 +237,5 @@ class TestReviewerLeaseMcpGate(unittest.TestCase):
self.assertTrue(any("lease" in r.lower() for r in reasons))
class TestReviewerLeaseHandoffDiagnose(unittest.TestCase):
"""#599: canonical next-action diagnosis for open-PR lease handoff."""
def setUp(self):
leases.clear_session_lease()
def test_no_lease_next_action_acquire(self):
result = leases.diagnose_reviewer_pr_lease_handoff(
[],
pr_number=592,
current_session_id="me-1",
current_reviewer_identity="sysadmin",
proposed_worktree="branches/review-pr-592",
)
self.assertEqual(result["classification"], "no_lease")
self.assertEqual(result["next_action"], leases.NEXT_ACTION_ACQUIRE)
self.assertIsNone(result["active_lease"])
def test_foreign_active_wait_pr592_style(self):
# Instructed lease gone; newer foreign claim is active.
old = _lease_comment(592, "23139-da018dab43ba", phase="released")
old["id"] = 8640
active = _lease_comment(592, "51515-2bfb70f0685f", phase="claimed")
active["id"] = 8647
result = leases.diagnose_reviewer_pr_lease_handoff(
[old, active],
pr_number=592,
current_session_id="fresh-session",
current_reviewer_identity="sysadmin",
proposed_worktree="branches/review-pr-592-issue-590",
instructed_session_id="23139-da018dab43ba",
instructed_comment_id=8640,
)
self.assertEqual(
result["classification"],
"instructed_lease_missing_with_replacement",
)
self.assertEqual(result["next_action"], leases.NEXT_ACTION_WAIT)
self.assertTrue(result["instructed_lease_missing_with_replacement"])
self.assertEqual(result["active_lease"]["session_id"], "51515-2bfb70f0685f")
self.assertEqual(result["active_lease"]["comment_id"], 8647)
self.assertFalse(result["mutation_allowed"])
def test_foreign_reclaimable_release_expired(self):
reclaim = _lease_comment(
592, "foreign-old", phase="claimed", minutes_ago=65
)
reclaim["id"] = 99
result = leases.diagnose_reviewer_pr_lease_handoff(
[reclaim],
pr_number=592,
current_session_id="me-1",
current_reviewer_identity="sysadmin",
proposed_worktree="branches/review-pr-592",
)
self.assertEqual(result["classification"], "foreign_reclaimable")
self.assertEqual(
result["next_action"], leases.NEXT_ACTION_RELEASE_EXPIRED_LEASE
)
def test_own_active_resume(self):
head = "a" * 40
claim = _lease_comment(592, "me-1", phase="claimed", candidate_head=head)
claim["id"] = 10
leases.record_session_lease({
"pr_number": 592,
"session_id": "me-1",
"candidate_head": head,
"comment_id": 10,
}, lease_provenance=mla.build_lease_provenance(
source=mla.SOURCE_ACQUIRE,
comment_id=10,
))
result = leases.diagnose_reviewer_pr_lease_handoff(
[claim],
pr_number=592,
current_session_id="me-1",
current_reviewer_identity="rev1",
proposed_worktree="branches/review-pr382",
)
self.assertEqual(result["classification"], "own_active")
self.assertEqual(
result["next_action"], leases.NEXT_ACTION_RESUME_EXACT_OWNER_SESSION
)
self.assertTrue(result["mutation_allowed"])
def test_worktree_binding_mismatch(self):
claim = _lease_comment(592, "me-1", phase="claimed")
claim["id"] = 11
# _lease_comment uses branches/review-pr382
result = leases.diagnose_reviewer_pr_lease_handoff(
[claim],
pr_number=592,
current_session_id="me-1",
current_reviewer_identity="rev1",
proposed_worktree="branches/review-pr-592-issue-590",
env_bound_worktree="branches/review-pr-538",
)
self.assertEqual(result["classification"], "worktree_binding_mismatch")
self.assertEqual(
result["next_action"], leases.NEXT_ACTION_REPAIR_WORKTREE_BINDING
)
self.assertFalse(result["worktree_binding"]["match"])
self.assertFalse(result["mutation_allowed"])
if __name__ == "__main__":
unittest.main()
+1 -41
View File
@@ -52,20 +52,6 @@ CONFIG = {
],
"execution_profile": "prgs-reviewer",
},
"prgs-merger": {
"enabled": True,
"context": "ctx",
"role": "merger",
"username": "sysadmin",
"auth": {"type": "env", "name": "GITEA_TOKEN_MERGER"},
"allowed_operations": [
"gitea.read", "gitea.pr.merge", "gitea.issue.comment",
],
"forbidden_operations": [
"gitea.pr.create", "gitea.branch.push", "gitea.pr.approve",
],
"execution_profile": "prgs-merger",
},
"prgs-reconciler": {
"enabled": True,
"context": "ctx",
@@ -118,7 +104,6 @@ class TestRoleSessionRouter(unittest.TestCase):
"GITEA_MCP_PROFILE": profile,
"GITEA_TOKEN_AUTHOR": "author-pass",
"GITEA_TOKEN_REVIEWER": "reviewer-pass",
"GITEA_TOKEN_MERGER": "merger-pass",
"GITEA_TOKEN_RECONCILER": "reconciler-pass",
}
@@ -242,31 +227,6 @@ class TestRoleSessionRouter(unittest.TestCase):
self.assertEqual(route["route_result"], role_session_router.ROUTE_ALLOWED)
self.assertTrue(route["downstream_allowed"])
@patch("mcp_server.api_request", return_value={"login": "sysadmin"})
@patch("mcp_server.get_auth_header", return_value="token reviewer-pass")
def test_merge_task_under_reviewer_profile_wrong_role_stop(self, _auth, _api):
# #539: a reviewer session must not pass the pre-task merge route
# even if its config accidentally includes gitea.pr.merge.
with patch.dict(os.environ, self._env("prgs-reviewer")):
route = mcp_server.gitea_route_task_session(
task_type="merge_pr", remote="prgs"
)
self.assertEqual(route["required_role"], "merger")
self.assertEqual(route["route_result"], role_session_router.ROUTE_WRONG_ROLE)
self.assertFalse(route["downstream_allowed"])
self.assertIn("merger", route["message"].lower())
@patch("mcp_server.api_request", return_value={"login": "sysadmin"})
@patch("mcp_server.get_auth_header", return_value="token merger-pass")
def test_merge_task_under_merger_profile_allowed(self, _auth, _api):
with patch.dict(os.environ, self._env("prgs-merger")):
route = mcp_server.gitea_route_task_session(
task_type="merge_pr", remote="prgs"
)
self.assertEqual(route["required_role"], "merger")
self.assertEqual(route["route_result"], role_session_router.ROUTE_ALLOWED)
self.assertTrue(route["downstream_allowed"])
@patch("mcp_server.api_request", return_value={"login": "sysadmin"})
@patch("mcp_server.get_auth_header", return_value="token reviewer-pass")
def test_author_task_under_reviewer_profile_routes_to_author(self, _auth, _api):
@@ -374,4 +334,4 @@ class TestCheckMidMerge(unittest.TestCase):
if __name__ == "__main__":
unittest.main()
unittest.main()
+4 -16
View File
@@ -13,13 +13,8 @@ sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
import gitea_mcp_server as srv # noqa: E402
import root_checkout_guard as rcg # noqa: E402
current_file_path = Path(__file__).resolve()
if "branches" in current_file_path.parts:
CONTROL_ROOT = str(current_file_path.parents[3])
BRANCHES_WORKTREE = str(current_file_path.parents[1])
else:
CONTROL_ROOT = str(current_file_path.parents[1])
BRANCHES_WORKTREE = str(current_file_path.parents[1] / "branches" / "mock-worktree")
CONTROL_ROOT = str(Path(__file__).resolve().parents[3])
BRANCHES_WORKTREE = str(Path(__file__).resolve().parents[1])
MASTER_SHA = "a" * 40
OTHER_SHA = "b" * 40
@@ -141,21 +136,13 @@ class TestVerifyPreflightRootGuardIntegration(unittest.TestCase):
self.assertIn("Root checkout guard (#475)", str(ctx.exception))
self.assertIn(rcg.REMEDIATION, str(ctx.exception))
@patch("os.path.isdir", return_value=True)
@patch("os.path.exists", return_value=True)
@patch("subprocess.run")
@patch("gitea_mcp_server._get_workspace_porcelain", return_value="")
@patch("gitea_mcp_server.root_checkout_guard.resolve_remote_master_sha", return_value=MASTER_SHA)
@patch("gitea_mcp_server.issue_lock_worktree.read_worktree_git_state")
@patch("gitea_mcp_server._resolve_author_mutation_context")
def test_reviewer_from_branches_worktree_allowed(
self, mock_ctx, mock_git, _remote_sha, _porcelain, mock_run, _exists, _isdir,
self, mock_ctx, mock_git, _remote_sha, _porcelain,
):
import unittest.mock
mock_run.return_value = unittest.mock.MagicMock(
returncode=0,
stdout=f"{CONTROL_ROOT}/.git\n",
)
srv._preflight_capability_baseline_porcelain = ""
mock_ctx.return_value = {
"workspace_path": BRANCHES_WORKTREE,
@@ -169,5 +156,6 @@ class TestVerifyPreflightRootGuardIntegration(unittest.TestCase):
}
srv.verify_preflight_purity("prgs", worktree_path=BRANCHES_WORKTREE)
if __name__ == "__main__":
unittest.main()
-62
View File
@@ -1,62 +0,0 @@
"""Regression: durable session-state isolation survives env clears (#590)."""
from __future__ import annotations
import os
from pathlib import Path
from unittest.mock import patch
import mcp_session_state
def test_default_state_dir_survives_env_clear():
"""conftest pins default_state_dir so clear=True cannot hit host cache."""
isolated = os.environ.get("GITEA_MCP_SESSION_STATE_DIR")
assert isolated, "conftest must set GITEA_MCP_SESSION_STATE_DIR"
host_cache = Path.home() / ".cache" / "gitea-tools" / "session-state"
with patch.dict(os.environ, {}, clear=True):
assert os.environ.get("GITEA_MCP_SESSION_STATE_DIR") is None
resolved = mcp_session_state.default_state_dir()
assert resolved == isolated
assert Path(resolved).resolve() != host_cache.resolve()
def test_decision_lock_save_load_stays_in_isolated_dir():
"""Review-mutation ledger files land only under the per-test state dir."""
isolated = os.environ.get("GITEA_MCP_SESSION_STATE_DIR")
assert isolated
with patch.dict(os.environ, {}, clear=True):
saved = mcp_session_state.save_state(
kind=mcp_session_state.KIND_DECISION_LOCK,
profile_identity="gitea-default",
payload={
"live_mutations": [
{"pr_number": 1, "action": "request_changes"}
],
},
)
assert saved is not None
path = mcp_session_state.state_file_path(
kind=mcp_session_state.KIND_DECISION_LOCK,
profile_identity="gitea-default",
)
assert path.startswith(isolated + os.sep) or path.startswith(
isolated + "/"
)
loaded = mcp_session_state.load_state(
kind=mcp_session_state.KIND_DECISION_LOCK,
profile_identity="gitea-default",
)
assert loaded is not None
assert loaded.get("live_mutations")
host_path = (
Path.home()
/ ".cache"
/ "gitea-tools"
/ "session-state"
/ "review_decision_lock-gitea-default.json"
)
# Host file may exist from operator use; this write must not refresh it.
# Prove our isolated file is distinct and present.
assert Path(path).is_file()
assert Path(path).resolve() != host_path.resolve()
-318
View File
@@ -1,318 +0,0 @@
"""#627: paginated repository-label resolution for gitea_set_issue_labels.
Reproduces the post-merge #601 reconciliation failure where later-page
labels (e.g. type:feature, workflow-hardening) were falsely rejected as
nonexistent because inventory used a single-page GET labels?limit=100.
"""
from __future__ import annotations
import os
import sys
import unittest
from unittest.mock import patch, call
sys.path.insert(0, str(__import__("pathlib").Path(__file__).resolve().parent.parent))
import mcp_server
import gitea_auth
FAKE_AUTH = "token test-token"
PAGE_SIZE = 50 # Gitea effective max; see gitea_auth.api_get_all
def _lb(name: str, lid: int) -> dict:
return {"id": lid, "name": name, "color": "000000"}
def _pages(labels: list[dict], page_size: int = PAGE_SIZE) -> list[list[dict]]:
if not labels:
return [[]]
pages = []
for i in range(0, len(labels), page_size):
pages.append(labels[i : i + page_size])
return pages
class TestRepoLabelIdMapPagination(unittest.TestCase):
"""_repo_label_id_map must use api_get_all (all pages)."""
@patch("mcp_server.api_get_all")
def test_fewer_than_one_page(self, mock_all):
labels = [_lb(f"l{i}", i) for i in range(3)]
mock_all.return_value = labels
m = mcp_server._repo_label_id_map("https://gitea.example/api/v1/repos/o/r", FAKE_AUTH)
self.assertEqual(m, {"l0": 0, "l1": 1, "l2": 2})
mock_all.assert_called_once()
self.assertIn("/labels", mock_all.call_args[0][0])
self.assertNotIn("limit=100", mock_all.call_args[0][0])
@patch("mcp_server.api_get_all")
def test_exactly_one_full_page(self, mock_all):
labels = [_lb(f"l{i:03d}", i) for i in range(PAGE_SIZE)]
mock_all.return_value = labels
m = mcp_server._repo_label_id_map("https://gitea.example/api/v1/repos/o/r", FAKE_AUTH)
self.assertEqual(len(m), PAGE_SIZE)
self.assertEqual(m["l000"], 0)
self.assertEqual(m[f"l{PAGE_SIZE - 1:03d}"], PAGE_SIZE - 1)
@patch("mcp_server.api_get_all")
def test_more_than_one_page_includes_later_labels(self, mock_all):
# Page 1: 50 early labels; page 2: type:feature + workflow-hardening (#601 style)
early = [_lb(f"early-{i:02d}", i) for i in range(PAGE_SIZE)]
late = [
_lb("type:feature", 1001),
_lb("workflow-hardening", 1002),
]
mock_all.return_value = early + late
m = mcp_server._repo_label_id_map("https://gitea.example/api/v1/repos/o/r", FAKE_AUTH)
self.assertEqual(len(m), PAGE_SIZE + 2)
self.assertEqual(m["type:feature"], 1001)
self.assertEqual(m["workflow-hardening"], 1002)
@patch("mcp_server.api_get_all")
def test_duplicate_names_keep_first_seen_id(self, mock_all):
mock_all.return_value = [
_lb("type:feature", 103),
_lb("type:feature", 130), # duplicate id later
_lb("workflow-hardening", 105),
_lb("workflow-hardening", 128),
]
m = mcp_server._repo_label_id_map("https://gitea.example/api/v1/repos/o/r", FAKE_AUTH)
self.assertEqual(m["type:feature"], 103)
self.assertEqual(m["workflow-hardening"], 105)
@patch("mcp_server.api_get_all", return_value={"not": "a list"})
def test_non_list_inventory_fails_closed(self, _all):
with self.assertRaises(RuntimeError) as ctx:
mcp_server._repo_label_id_map("https://gitea.example/api/v1/repos/o/r", FAKE_AUTH)
self.assertIn("expected a list", str(ctx.exception).lower())
@patch("mcp_server.api_get_all", side_effect=RuntimeError("page 2 failed: connection reset"))
def test_later_page_failure_propagates(self, _all):
with self.assertRaises(RuntimeError) as ctx:
mcp_server._repo_label_id_map("https://gitea.example/api/v1/repos/o/r", FAKE_AUTH)
self.assertIn("page 2 failed", str(ctx.exception))
class TestSetIssueLabelsPagination(unittest.TestCase):
"""gitea_set_issue_labels full-set replacement with multi-page inventory."""
def setUp(self):
self._remotes = patch.dict(
mcp_server.REMOTES,
{"prgs": {"host": "gitea.example.com", "org": "Scaled-Tech-Consulting",
"repo": "Gitea-Tools"}},
)
self._remotes.start()
# Allow mutation path without full preflight stack when possible
self._preflight = patch(
"mcp_server.verify_preflight_purity", return_value=None
)
self._preflight.start()
self._perm = patch(
"mcp_server._profile_permission_block", return_value=None
)
self._perm.start()
self._auth = patch(
"mcp_server._auth", return_value=FAKE_AUTH
)
self._auth.start()
self._audited = patch("mcp_server._audited")
mock_aud = self._audited.start()
mock_aud.return_value.__enter__ = lambda s: None
mock_aud.return_value.__exit__ = lambda s, *a: None
def tearDown(self):
self._remotes.stop()
self._preflight.stop()
self._perm.stop()
self._auth.stop()
self._audited.stop()
def _inventory_early_and_late(self) -> list[dict]:
early = [_lb(f"alpha-{i:02d}", i + 1) for i in range(PAGE_SIZE)]
late = [
_lb("type:feature", 9001),
_lb("workflow-hardening", 9002),
_lb("status:ready", 9003),
_lb("anti-stomp", 9004),
_lb("leases", 9005),
_lb("recovery", 9006),
]
return early + late
@patch("mcp_server.api_request")
@patch("mcp_server.api_get_all")
def test_requested_labels_split_across_pages(self, mock_all, mock_req):
inv = self._inventory_early_and_late()
mock_all.return_value = inv
requested = ["alpha-00", "type:feature", "workflow-hardening"]
mock_req.return_value = [_lb(n, inv_i["id"]) for n in requested
for inv_i in inv if inv_i["name"] == n]
res = mcp_server.gitea_set_issue_labels(
issue_number=601,
labels=requested,
remote="prgs",
)
self.assertEqual({lb["name"] for lb in res}, set(requested))
# PUT must use ids from both pages
put = mock_req.call_args
self.assertEqual(put[0][0], "PUT")
payload_ids = put[0][3]["labels"]
self.assertEqual(payload_ids, [1, 9001, 9002])
@patch("mcp_server.api_request")
@patch("mcp_server.api_get_all")
def test_missing_requested_label_rejected_before_put(self, mock_all, mock_req):
mock_all.return_value = [_lb("bug", 1), _lb("status:ready", 2)]
with self.assertRaises(RuntimeError) as ctx:
mcp_server.gitea_set_issue_labels(
issue_number=9,
labels=["bug", "does-not-exist"],
remote="prgs",
)
self.assertIn("do not exist", str(ctx.exception))
self.assertIn("does-not-exist", str(ctx.exception))
mock_req.assert_not_called()
@patch("mcp_server.api_request")
@patch("mcp_server.api_get_all")
def test_complete_set_preserves_later_page_labels(self, mock_all, mock_req):
inv = self._inventory_early_and_late()
mock_all.return_value = inv
# Full-set replacement removing only status:pr-open style stale label:
# keep later-page feature labels (the #601 reconciliation shape).
requested = [
"anti-stomp",
"leases",
"recovery",
"type:feature",
"workflow-hardening",
]
mock_req.return_value = [_lb(n, next(x["id"] for x in inv if x["name"] == n))
for n in requested]
res = mcp_server.gitea_set_issue_labels(
issue_number=601, labels=requested, remote="prgs"
)
self.assertEqual([lb["name"] for lb in res], requested)
payload_ids = mock_req.call_args[0][3]["labels"]
self.assertEqual(payload_ids, [9004, 9005, 9006, 9001, 9002])
@patch("mcp_server.api_request")
@patch("mcp_server.api_get_all")
def test_issue_601_regression_later_page_names_accepted(self, mock_all, mock_req):
"""Regression: #601 reconciler rejected type:feature + workflow-hardening.
Single-page inventory would omit them; paginated inventory must accept.
"""
early = [_lb(f"page1-{i:02d}", i + 1) for i in range(PAGE_SIZE)]
# Exactly the labels from the #601 residual set (minus status:pr-open)
late = [
_lb("type:feature", 103),
_lb("workflow-hardening", 105),
_lb("anti-stomp", 106),
_lb("leases", 109),
_lb("recovery", 110),
]
mock_all.return_value = early + late
requested = [
"anti-stomp",
"leases",
"recovery",
"type:feature",
"workflow-hardening",
]
mock_req.return_value = [
_lb(n, next(x["id"] for x in late if x["name"] == n)) for n in requested
]
res = mcp_server.gitea_set_issue_labels(
issue_number=601, labels=requested, remote="prgs"
)
names = {lb["name"] for lb in res}
self.assertEqual(names, set(requested))
self.assertNotIn("status:pr-open", names)
@patch("mcp_server.api_request")
@patch("mcp_server.api_get_all")
def test_duplicate_label_ids_resolve_deterministically(self, mock_all, mock_req):
mock_all.return_value = [
_lb("type:feature", 103),
_lb("type:feature", 130),
_lb("workflow-hardening", 105),
_lb("workflow-hardening", 128),
]
requested = ["type:feature", "workflow-hardening"]
mock_req.return_value = [_lb("type:feature", 103), _lb("workflow-hardening", 105)]
mcp_server.gitea_set_issue_labels(
issue_number=1, labels=requested, remote="prgs"
)
self.assertEqual(mock_req.call_args[0][3]["labels"], [103, 105])
@patch("mcp_server.api_request")
@patch("mcp_server.api_get_all")
def test_post_mutation_mismatch_fails_closed(self, mock_all, mock_req):
mock_all.return_value = [_lb("bug", 1), _lb("status:ready", 2)]
# Server returns incomplete set → verification must fail
mock_req.return_value = [_lb("bug", 1)]
with self.assertRaises(RuntimeError) as ctx:
mcp_server.gitea_set_issue_labels(
issue_number=9,
labels=["bug", "status:ready"],
remote="prgs",
)
self.assertIn("Post-mutation label verification failed", str(ctx.exception))
self.assertIn("status:ready", str(ctx.exception))
@patch("mcp_server.api_request")
@patch("mcp_server.api_get_all", side_effect=RuntimeError("Gitea 502 on page 2"))
def test_pagination_failure_fails_closed_before_put(self, _all, mock_req):
with self.assertRaises(RuntimeError) as ctx:
mcp_server.gitea_set_issue_labels(
issue_number=9, labels=["bug"], remote="prgs"
)
self.assertIn("page 2", str(ctx.exception))
mock_req.assert_not_called()
@patch("mcp_server.api_request")
@patch("mcp_server.api_get_all")
def test_empty_label_set_clears_all(self, mock_all, mock_req):
mock_all.return_value = [_lb("bug", 1)]
mock_req.return_value = []
res = mcp_server.gitea_set_issue_labels(
issue_number=9, labels=[], remote="prgs"
)
self.assertEqual(res, [])
self.assertEqual(mock_req.call_args[0][3]["labels"], [])
@patch("mcp_server.api_request")
@patch("mcp_server.api_get_all")
def test_does_not_call_single_page_limit_100(self, mock_all, mock_req):
mock_all.return_value = [_lb("bug", 1)]
mock_req.return_value = [_lb("bug", 1)]
mcp_server.gitea_set_issue_labels(
issue_number=9, labels=["bug"], remote="prgs"
)
for c in mock_req.call_args_list:
url = c[0][1] if len(c[0]) > 1 else ""
self.assertNotIn("labels?limit=100", str(url))
mock_all.assert_called()
class TestApiGetAllPageCapDocumentsGiteaLimit(unittest.TestCase):
"""Sanity: api_get_all clamps page_size to 50 (root cause of limit=100 trap)."""
@patch("gitea_auth.api_request")
def test_page_size_clamped_to_fifty(self, mock_req):
mock_req.return_value = []
gitea_auth.api_get_all("https://gitea.example/api/v1/repos/o/r/labels",
FAKE_AUTH, page_size=100)
# First (only) call must use limit=50, not 100
url = mock_req.call_args[0][1]
self.assertIn("limit=50", url)
self.assertNotIn("limit=100", url)
if __name__ == "__main__":
unittest.main()
@@ -1,188 +0,0 @@
"""Server wiring for stable-branch push contamination (#671).
Exercises the MCP tools and the pre-flight enforcement gate against the durable
contamination marker (isolated per-test state dir from conftest).
"""
from __future__ import annotations
import os
from unittest.mock import patch
import gitea_mcp_server as srv
def _clear_marker(remote="prgs"):
srv._clear_stable_contamination_marker(remote=remote)
def teardown_function():
_clear_marker()
# ── record tool marks a real direct push ─────────────────────────────────────
def test_record_tool_marks_direct_master_push():
_clear_marker()
res = srv.gitea_record_stable_branch_push_attempt(
command="git push prgs master", remote="prgs"
)
assert res["contaminated"] is True
assert res["marked"] is True
assert res["marker"] is not None
assert res["marker"]["reason_class"] == "stable_branch_push"
# loaded back through the durable store
loaded = srv._load_stable_contamination_marker("prgs")
assert loaded is not None
assert loaded["ref"] == "master"
def test_record_tool_dry_run_still_marks():
_clear_marker()
res = srv.gitea_record_stable_branch_push_attempt(
command="git push --dry-run prgs master", remote="prgs"
)
assert res["contaminated"] is True
assert res["marked"] is True
def test_record_tool_feature_branch_does_not_mark():
_clear_marker()
res = srv.gitea_record_stable_branch_push_attempt(
command="git push prgs fix/issue-671-block-stable-branch-push",
remote="prgs",
)
assert res["contaminated"] is False
assert res["marked"] is False
assert srv._load_stable_contamination_marker("prgs") is None
def test_record_tool_fetch_only_does_not_mark():
_clear_marker()
res = srv.gitea_record_stable_branch_push_attempt(
command="git fetch prgs", remote="prgs"
)
assert res["contaminated"] is False
assert res["marked"] is False
def test_record_tool_mark_false_is_readonly():
_clear_marker()
res = srv.gitea_record_stable_branch_push_attempt(
command="git push prgs master", remote="prgs", mark=False
)
assert res["contaminated"] is True
assert res["marked"] is False
assert srv._load_stable_contamination_marker("prgs") is None
def test_record_tool_redacts_secret_in_marker():
_clear_marker()
res = srv.gitea_record_stable_branch_push_attempt(
command="git push https://u:supersecret@host/o/r.git master",
remote="prgs",
)
assert res["marked"] is True
assert "supersecret" not in res["marker"]["command_summary"]
def test_record_tool_root_checkout_local_commit_marks():
_clear_marker()
res = srv.gitea_record_stable_branch_push_attempt(
command=None,
remote="prgs",
current_branch="master",
head_sha="a" * 40,
remote_master_sha="b" * 40,
is_under_branches=False,
)
assert res["contaminated"] is True
assert res["marked"] is True
assert res["marker"]["reason_class"] == "root_checkout_commit"
# ── audit tool: inspect + reconciler-only clear ──────────────────────────────
def test_audit_inspect_reports_marker():
_clear_marker()
srv.gitea_record_stable_branch_push_attempt(
command="git push prgs master", remote="prgs"
)
out = srv.gitea_audit_stable_branch_contamination(action="inspect", remote="prgs")
assert out["contaminated"] is True
assert out["read_only"] is True
def test_audit_clear_refused_for_non_reconciler():
_clear_marker()
srv.gitea_record_stable_branch_push_attempt(
command="git push prgs master", remote="prgs"
)
with patch.object(srv, "_actual_profile_role", return_value="author"):
out = srv.gitea_audit_stable_branch_contamination(action="clear", remote="prgs")
assert out["success"] is False
assert out["reasons"]
# marker survives a refused clear
assert srv._load_stable_contamination_marker("prgs") is not None
def test_audit_clear_allowed_for_reconciler():
_clear_marker()
srv.gitea_record_stable_branch_push_attempt(
command="git push prgs master", remote="prgs"
)
identity = srv._stable_contamination_profile_identity()
with patch.object(srv, "_actual_profile_role", return_value="reconciler"):
out = srv.gitea_audit_stable_branch_contamination(
action="clear", remote="prgs", profile_identity=identity
)
assert out["success"] is True
assert srv._load_stable_contamination_marker("prgs") is None
# ── pre-flight enforcement gate ──────────────────────────────────────────────
def _force_gate_env():
return patch.dict(os.environ, {"GITEA_TEST_FORCE_STABLE_CONTAMINATION": "1"})
def test_gate_blocks_gated_mutation_when_contaminated():
_clear_marker()
srv.gitea_record_stable_branch_push_attempt(
command="git push prgs master", remote="prgs"
)
with _force_gate_env(), patch.object(srv, "_actual_profile_role", return_value="author"):
for task in ("merge_pr", "review_pr", "close_issue", "create_pr"):
try:
srv._enforce_stable_branch_contamination_gate(task, "prgs")
raised = False
except RuntimeError as exc:
raised = True
assert "#671" in str(exc)
assert raised, task
def test_gate_allows_comment_for_handoff_when_contaminated():
_clear_marker()
srv.gitea_record_stable_branch_push_attempt(
command="git push prgs master", remote="prgs"
)
with _force_gate_env(), patch.object(srv, "_actual_profile_role", return_value="author"):
# must not raise — worker can still post the durable audit comment
srv._enforce_stable_branch_contamination_gate("comment_issue", "prgs")
srv._enforce_stable_branch_contamination_gate("lock_issue", "prgs")
def test_gate_exempts_reconciler_when_contaminated():
_clear_marker()
srv.gitea_record_stable_branch_push_attempt(
command="git push prgs master", remote="prgs"
)
with _force_gate_env(), patch.object(srv, "_actual_profile_role", return_value="reconciler"):
srv._enforce_stable_branch_contamination_gate("merge_pr", "prgs")
def test_gate_noop_when_not_contaminated():
_clear_marker()
with _force_gate_env(), patch.object(srv, "_actual_profile_role", return_value="author"):
srv._enforce_stable_branch_contamination_gate("merge_pr", "prgs")
-341
View File
@@ -1,341 +0,0 @@
"""Tests for the direct stable-branch push guard (#671).
Covers the acceptance criteria:
1. detect shell ``git push <remote> master`` equivalents
2. detect root/control-checkout local commits not on an issue branch
3. contamination record shape
4. fail-closed gate on review/merge/close/completion (reconciler-exempt)
5. AC5 case matrix: no-op dry-run push, real direct push, sanctioned Gitea
merge, fetch-only, root-checkout local commit; plus feature-branch push
still allowed and sanctioned merge still allowed
6. redaction of credentials in logged command summaries
"""
import stable_branch_push_guard as guard
# ── AC1: detect direct stable-branch push equivalents ────────────────────────
def test_plain_git_push_remote_master_is_contamination():
res = guard.classify_push_command("git push prgs master")
assert res["is_git_push"] is True
assert res["targets_stable"] is True
assert res["stable_refs"] == ["master"]
assert res["contamination"] is True
assert res["reasons"]
def test_push_main_and_dev_detected():
for ref in ("main", "dev", "develop", "development"):
res = guard.classify_push_command(f"git push origin {ref}")
assert res["contamination"] is True, ref
assert res["stable_refs"] == [ref]
def test_head_colon_master_refspec_detected():
res = guard.classify_push_command("git push prgs HEAD:master")
assert res["targets_stable"] is True
assert res["stable_refs"] == ["master"]
assert res["contamination"] is True
def test_full_refspec_force_plus_detected():
res = guard.classify_push_command(
"git push prgs +refs/heads/tmp:refs/heads/master"
)
assert res["contamination"] is True
assert res["is_force"] is True
assert res["stable_refs"] == ["master"]
def test_force_flag_to_master_detected():
res = guard.classify_push_command("git push --force prgs master")
assert res["contamination"] is True
assert res["is_force"] is True
def test_delete_refspec_master_detected():
res = guard.classify_push_command("git push prgs :master")
assert res["contamination"] is True
assert res["is_delete"] is True
def test_delete_flag_master_detected():
res = guard.classify_push_command("git push --delete prgs master")
assert res["contamination"] is True
assert res["is_delete"] is True
def test_push_detected_inside_compound_command():
res = guard.classify_push_command("cd repo && git push prgs master && echo ok")
assert res["contamination"] is True
assert res["stable_refs"] == ["master"]
# ── AC5: no-op / dry-run push still proves intent ────────────────────────────
def test_dry_run_push_to_master_proves_intent():
res = guard.classify_push_command("git push --dry-run prgs master")
assert res["is_dry_run"] is True
assert res["contamination"] is True
assert res["proves_intent"] is True
assert "intent" in " ".join(res["reasons"]).lower()
def test_short_dry_run_flag_n_detected():
res = guard.classify_push_command("git push -n prgs master")
assert res["is_dry_run"] is True
assert res["contamination"] is True
# ── AC5 negative: feature-branch push still allowed ──────────────────────────
def test_feature_branch_push_not_flagged():
res = guard.classify_push_command(
"git push prgs fix/issue-671-block-stable-branch-push"
)
assert res["is_git_push"] is True
assert res["targets_stable"] is False
assert res["contamination"] is False
assert res["reasons"] == []
def test_feature_branch_head_refspec_not_flagged():
res = guard.classify_push_command(
"git push prgs HEAD:fix/issue-671-block-stable-branch-push"
)
assert res["contamination"] is False
assert res["targets_stable"] is False
def test_branch_named_like_master_substring_not_flagged():
# 'master-notes' is not the stable 'master'.
res = guard.classify_push_command("git push prgs master-notes")
assert res["contamination"] is False
assert res["targets_stable"] is False
# ── AC5 negative: fetch-only operations ──────────────────────────────────────
def test_git_fetch_not_a_push():
res = guard.classify_push_command("git fetch prgs")
assert res["is_git_push"] is False
assert res["is_fetch_or_pull"] is True
assert res["contamination"] is False
def test_git_pull_ff_only_master_not_a_push():
res = guard.classify_push_command("git pull --ff-only prgs master")
assert res["is_git_push"] is False
assert res["is_fetch_or_pull"] is True
assert res["contamination"] is False
# ── AC5 negative: sanctioned Gitea merge is not a push ───────────────────────
def test_gitea_merge_pr_tool_is_not_a_push():
res = guard.classify_push_command("gitea_merge_pr(pr_number=671, remote='prgs')")
assert res["is_git_push"] is False
assert res["contamination"] is False
def test_gitea_api_merge_is_not_a_push():
res = guard.classify_push_command(
"curl -X POST https://gitea.example/api/v1/repos/o/r/pulls/671/merge"
)
assert res["is_git_push"] is False
assert res["contamination"] is False
# ── ambiguous bare push: reported, not auto-contaminating ────────────────────
def test_bare_push_is_ambiguous_not_contaminating():
res = guard.classify_push_command("git push prgs")
assert res["is_git_push"] is True
assert res["ambiguous_target"] is True
assert res["contamination"] is False
assert res["reasons"] # surfaced as a warning
# ── AC2: root/control-checkout local commit detection ────────────────────────
def test_root_checkout_commit_ahead_of_master_flagged():
res = guard.assess_root_checkout_local_commit(
current_branch="master",
head_sha="a" * 40,
remote_master_sha="b" * 40,
is_under_branches=False,
)
assert res["contamination"] is True
assert res["reasons"]
def test_root_checkout_clean_at_master_not_flagged():
sha = "c" * 40
res = guard.assess_root_checkout_local_commit(
current_branch="master",
head_sha=sha,
remote_master_sha=sha,
is_under_branches=False,
)
assert res["contamination"] is False
assert res["unknown"] is False
def test_branches_worktree_commit_is_exempt():
res = guard.assess_root_checkout_local_commit(
current_branch="fix/issue-671-block-stable-branch-push",
head_sha="a" * 40,
remote_master_sha="b" * 40,
is_under_branches=True,
)
assert res["contamination"] is False
def test_root_checkout_ahead_count_flagged():
res = guard.assess_root_checkout_local_commit(
current_branch="master",
head_sha="",
remote_master_sha="",
is_under_branches=False,
ahead_count=2,
)
assert res["contamination"] is True
def test_root_checkout_unknown_when_state_missing():
res = guard.assess_root_checkout_local_commit(
current_branch="master",
head_sha="",
remote_master_sha="",
is_under_branches=False,
)
assert res["contamination"] is False
assert res["unknown"] is True
def test_root_checkout_non_stable_branch_out_of_scope():
res = guard.assess_root_checkout_local_commit(
current_branch="feature/x",
head_sha="a" * 40,
remote_master_sha="b" * 40,
is_under_branches=False,
)
assert res["contamination"] is False
# ── AC3: contamination record shape ──────────────────────────────────────────
def test_build_contamination_record_shape_and_redaction():
rec = guard.build_contamination_record(
reason_class="stable_branch_push",
command_redacted="git push https://user:[email protected]/o/r.git master",
session_id="prgs-author-123",
remote="prgs",
ref="master",
role="author",
)
assert rec["kind"] == guard.CONTAMINATION_KIND
assert rec["reason_class"] == "stable_branch_push"
assert rec["remote"] == "prgs"
assert rec["ref"] == "master"
assert rec["cleared_by_reconciler"] is False
# secret must never survive into the durable record
assert "tok@" not in rec["command_summary"]
assert "***@" in rec["command_summary"]
# ── AC4: fail-closed gate on gated mutations ─────────────────────────────────
def _marker():
return guard.build_contamination_record(
reason_class="stable_branch_push",
command_redacted="git push prgs master",
remote="prgs",
ref="master",
role="author",
)
def test_gate_blocks_gated_mutations_for_author():
marker = _marker()
for task in ("create_pr", "merge_pr", "close_issue", "review_pr",
"submit_pr_review", "commit_files", "close_pr"):
gate = guard.assess_contamination_gate(marker, task=task, actual_role="author")
assert gate["block"] is True, task
assert gate["reasons"]
def test_gate_allows_comment_and_lock_for_handoff():
marker = _marker()
for task in ("comment_issue", "lock_issue", "create_issue", "mark_issue"):
gate = guard.assess_contamination_gate(marker, task=task, actual_role="author")
assert gate["block"] is False, task
def test_gate_exempts_reconciler_audit_path():
marker = _marker()
gate = guard.assess_contamination_gate(marker, task="close_pr", actual_role="reconciler")
assert gate["block"] is False
def test_gate_no_marker_allows_everything():
gate = guard.assess_contamination_gate(None, task="merge_pr", actual_role="merger")
assert gate["block"] is False
def test_gate_cleared_marker_allows_everything():
marker = _marker()
marker["cleared_by_reconciler"] = True
gate = guard.assess_contamination_gate(marker, task="merge_pr", actual_role="merger")
assert gate["block"] is False
def test_same_worker_cannot_self_clear_by_role():
# A merger/reviewer/author role is still gated — only reconciler is exempt.
marker = _marker()
for role in ("author", "reviewer", "merger"):
gate = guard.assess_contamination_gate(marker, task="merge_pr", actual_role=role)
assert gate["block"] is True, role
def test_format_gate_error_mentions_issue():
marker = _marker()
gate = guard.assess_contamination_gate(marker, task="merge_pr", actual_role="merger")
msg = guard.format_contamination_gate_error(gate)
assert "#671" in msg
assert "contaminat" in msg.lower()
# ── redaction unit coverage ──────────────────────────────────────────────────
def test_redact_url_userinfo():
out = guard.redact_command("git push https://bob:secretpat@host/o/r.git master")
assert "secretpat" not in out
assert "***@" in out
assert "master" in out # structure preserved for audit
def test_redact_token_assignment():
out = guard.redact_command("GITEA_TOKEN=abcdef123456 git push prgs master")
assert "abcdef123456" not in out
assert "GITEA_TOKEN=***" in out
def test_redact_empty():
assert guard.redact_command(None) == ""
assert guard.redact_command("") == ""
# ── detect_stable_push over iterables ────────────────────────────────────────
def test_detect_stable_push_iterable_finds_first_contamination():
cmds = ["git status", "git push prgs master", "echo done"]
res = guard.detect_stable_push(cmds)
assert res["contamination"] is True
def test_detect_stable_push_iterable_all_safe():
cmds = ["git status", "git push prgs feature/x", "git fetch prgs"]
res = guard.detect_stable_push(cmds)
assert res["contamination"] is False
@@ -1,378 +0,0 @@
"""Stale #332 review-decision lock cleanup (#594).
Proves:
a. active terminal locks still block unrelated terminal reviews
b. merged/closed PR locks can be cleared canonically
c. cleanup cannot bypass review gates on open PRs
d. after moot cleanup, mark_ready for a different PR can proceed
(PR #592-style after PR #586-style stale approve)
"""
from __future__ import annotations
import os
import unittest
from unittest.mock import patch
import mcp_server
import stale_review_decision_lock as srdl
from mcp_server import (
gitea_cleanup_stale_review_decision_lock,
gitea_mark_final_review_decision,
)
HEAD = "a" * 40
FAKE_AUTH = "Basic dGVzdDp0ZXN0"
REVIEWER_ENV = {
"GITEA_PROFILE_NAME": "prgs-reviewer",
"GITEA_ALLOWED_OPERATIONS": (
"gitea.read,gitea.pr.review,gitea.pr.approve,"
"gitea.pr.request_changes,gitea.pr.comment"
),
"GITEA_SESSION_PROFILE_LOCK": "prgs-reviewer",
}
REVIEWER_PROFILE = {
"profile_name": "prgs-reviewer",
"allowed_operations": [
"gitea.read",
"gitea.pr.review",
"gitea.pr.approve",
"gitea.pr.request_changes",
"gitea.pr.comment",
],
"forbidden_operations": [
"gitea.pr.merge",
"gitea.pr.create",
"gitea.branch.push",
],
}
def _reviewer_profile_patch():
return patch.object(mcp_server, "get_profile", return_value=REVIEWER_PROFILE)
def _lock(mutations=None, correction=False):
return {
"task": "review_pr",
"remote": "prgs",
"org": "Scaled-Tech-Consulting",
"repo": "Gitea-Tools",
"session_pid": os.getpid(),
"session_profile": "prgs-reviewer",
"session_profile_lock": "prgs-reviewer",
"profile_identity": "prgs-reviewer",
"final_review_decision_ready": False,
"ready_pr_number": None,
"ready_action": None,
"ready_expected_head_sha": None,
"ready_remote": None,
"ready_org": None,
"ready_repo": None,
"live_mutations": list(mutations or []),
"correction_authorized": correction,
"correction_reason": None,
}
APPROVED_586 = {
"pr_number": 586,
"action": "approve",
"review_id": 395,
"review_state": "approve",
}
APPROVED_OPEN = {
"pr_number": 700,
"action": "approve",
"review_id": 1,
"review_state": "approve",
}
RC_OPEN = {
"pr_number": 701,
"action": "request_changes",
"review_id": 2,
"review_state": "request_changes",
}
def _seed(mutations=None, correction=False):
import review_workflow_load
review_workflow_load.record_review_workflow_load(mcp_server.PROJECT_ROOT)
mcp_server._save_review_decision_lock(_lock(mutations, correction))
mcp_server.gitea_load_review_workflow()
def _merged_pr(pr_number=586, sha="6913ac9" + "0" * 33):
return {
"number": pr_number,
"state": "closed",
"merged": True,
"merged_at": "2026-07-09T18:20:03Z",
"merge_commit_sha": sha,
}
def _open_pr(pr_number=700):
return {
"number": pr_number,
"state": "open",
"merged": False,
"merged_at": None,
"merge_commit_sha": None,
}
# --------------------------------------------------------------------------- #
# Pure assessment
# --------------------------------------------------------------------------- #
class TestAssessStaleLock(unittest.TestCase):
def test_no_lock(self):
a = srdl.assess_stale_review_decision_lock(None)
self.assertFalse(a["cleanup_allowed"])
self.assertFalse(a["is_moot"])
def test_no_terminal_mutations(self):
a = srdl.assess_stale_review_decision_lock(_lock([]))
self.assertFalse(a["cleanup_allowed"])
def test_open_pr_not_cleanable(self):
a = srdl.assess_stale_review_decision_lock(
_lock([APPROVED_OPEN]), pr_live=_open_pr(700)
)
self.assertFalse(a["is_moot"])
self.assertFalse(a["cleanup_allowed"])
self.assertTrue(any("open PR" in r for r in a["reasons"]))
def test_merged_pr_is_moot_and_cleanable(self):
a = srdl.assess_stale_review_decision_lock(
_lock([APPROVED_586]), pr_live=_merged_pr(586)
)
self.assertTrue(a["is_moot"])
self.assertTrue(a["cleanup_allowed"])
self.assertEqual(a["last_terminal_pr"], 586)
def test_closed_unmerged_is_moot(self):
a = srdl.assess_stale_review_decision_lock(
_lock([RC_OPEN]),
pr_live={"number": 701, "state": "closed", "merged": False},
)
self.assertTrue(a["is_moot"])
self.assertTrue(a["cleanup_allowed"])
def test_profile_mismatch_blocks(self):
a = srdl.assess_stale_review_decision_lock(
_lock([APPROVED_586]),
pr_live=_merged_pr(586),
active_profile_identity="other-profile",
)
self.assertFalse(a["cleanup_allowed"])
self.assertFalse(a["profile_match"])
def test_lookup_error_fail_closed(self):
a = srdl.assess_stale_review_decision_lock(
_lock([APPROVED_586]),
pr_lookup_error="timeout",
)
self.assertFalse(a["cleanup_allowed"])
self.assertTrue(any("timeout" in r for r in a["reasons"]))
# --------------------------------------------------------------------------- #
# Hard-stop still blocks active locks
# --------------------------------------------------------------------------- #
class TestActiveHardStopPreserved(unittest.TestCase):
def tearDown(self):
mcp_server._save_review_decision_lock(None)
mcp_server.review_workflow_load.clear_review_workflow_load()
def test_open_approve_still_blocks_other_pr_mark_ready(self):
_seed([APPROVED_OPEN])
reasons = mcp_server.terminal_review_hard_stop_reasons(592, "mark_ready")
self.assertTrue(reasons)
self.assertIn("#332", reasons[0])
self.assertIn("gitea_cleanup_stale_review_decision_lock", reasons[0])
def test_request_changes_still_blocks_everything(self):
_seed([RC_OPEN])
for op in ("merge", "mark_ready", "review"):
self.assertTrue(
mcp_server.terminal_review_hard_stop_reasons(592, op),
msg=op,
)
# --------------------------------------------------------------------------- #
# MCP cleanup tool
# --------------------------------------------------------------------------- #
class TestCleanupTool(unittest.TestCase):
def setUp(self):
self._env = patch.dict(os.environ, REVIEWER_ENV, clear=False)
self._env.start()
def tearDown(self):
self._env.stop()
mcp_server._save_review_decision_lock(None)
mcp_server.review_workflow_load.clear_review_workflow_load()
def test_read_only_reports_moot_without_clearing(self):
_seed([APPROVED_586])
with patch.object(mcp_server, "api_request", return_value=_merged_pr()), \
patch.object(mcp_server, "_auth", return_value=FAKE_AUTH), \
patch.object(
mcp_server, "_authenticated_username", return_value="sysadmin"
), \
_reviewer_profile_patch(), \
patch.object(mcp_server, "_profile_operation_gate", return_value=[]):
r = gitea_cleanup_stale_review_decision_lock(
apply=False, remote="prgs",
org="Scaled-Tech-Consulting", repo="Gitea-Tools",
)
self.assertTrue(r["success"])
self.assertTrue(r["is_moot"])
self.assertTrue(r["cleanup_allowed"])
self.assertFalse(r["cleanup_performed"])
self.assertIsNotNone(mcp_server._load_review_decision_lock())
def test_apply_clears_moot_lock(self):
_seed([APPROVED_586])
posts = []
def _api(method, url, auth, payload=None):
if method == "GET" and "/pulls/586" in url:
return _merged_pr()
if method == "POST" and "/comments" in url:
posts.append(payload)
return {"id": 9999}
return {}
with patch.object(mcp_server, "api_request", side_effect=_api), \
patch.object(mcp_server, "_auth", return_value=FAKE_AUTH), \
patch.object(
mcp_server, "_authenticated_username", return_value="sysadmin"
), \
_reviewer_profile_patch(), \
patch.object(mcp_server, "_profile_operation_gate", return_value=[]), \
patch.object(
mcp_server, "_audited",
side_effect=lambda *a, **k: __import__(
"contextlib"
).nullcontext(),
):
r = gitea_cleanup_stale_review_decision_lock(
apply=True,
expected_terminal_pr=586,
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
)
self.assertTrue(r["cleanup_performed"], r)
self.assertTrue(r["audit"]["applied"])
self.assertIsNone(mcp_server._load_review_decision_lock())
self.assertEqual(r.get("audit_comment_id"), 9999)
self.assertTrue(posts)
def test_apply_refuses_open_pr(self):
_seed([APPROVED_OPEN])
with patch.object(mcp_server, "api_request", return_value=_open_pr(700)), \
patch.object(mcp_server, "_auth", return_value=FAKE_AUTH), \
patch.object(
mcp_server, "_authenticated_username", return_value="sysadmin"
), \
_reviewer_profile_patch(), \
patch.object(mcp_server, "_profile_operation_gate", return_value=[]):
r = gitea_cleanup_stale_review_decision_lock(
apply=True, remote="prgs",
org="Scaled-Tech-Consulting", repo="Gitea-Tools",
)
self.assertFalse(r["cleanup_performed"])
self.assertFalse(r["cleanup_allowed"])
self.assertIsNotNone(mcp_server._load_review_decision_lock())
def test_expected_terminal_pr_pin(self):
_seed([APPROVED_586])
with patch.object(mcp_server, "api_request", return_value=_merged_pr()), \
patch.object(mcp_server, "_auth", return_value=FAKE_AUTH), \
patch.object(
mcp_server, "_authenticated_username", return_value="sysadmin"
), \
_reviewer_profile_patch(), \
patch.object(mcp_server, "_profile_operation_gate", return_value=[]):
r = gitea_cleanup_stale_review_decision_lock(
apply=True,
expected_terminal_pr=999,
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
)
self.assertFalse(r["cleanup_performed"])
self.assertTrue(any("expected_terminal_pr" in x for x in r["reasons"]))
def test_after_moot_cleanup_other_pr_mark_ready_unblocked(self):
"""PR #592-style: after clearing merged #586 lock, new mark_ready works."""
_seed([APPROVED_586])
with patch.object(mcp_server, "api_request", return_value=_merged_pr()), \
patch.object(mcp_server, "_auth", return_value=FAKE_AUTH), \
patch.object(
mcp_server, "_authenticated_username", return_value="sysadmin"
), \
_reviewer_profile_patch(), \
patch.object(mcp_server, "_profile_operation_gate", return_value=[]), \
patch.object(
mcp_server, "_audited",
side_effect=lambda *a, **k: __import__(
"contextlib"
).nullcontext(),
):
cleaned = gitea_cleanup_stale_review_decision_lock(
apply=True,
expected_terminal_pr=586,
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
post_audit_comment=False,
)
self.assertTrue(cleaned["cleanup_performed"], cleaned)
# Hard-stop gone; re-init clean lock like a fresh review_pr resolve.
mcp_server.init_review_decision_lock(remote="prgs", task="review_pr")
mcp_server.gitea_load_review_workflow()
self.assertEqual(
mcp_server.terminal_review_hard_stop_reasons(592, "mark_ready"),
[],
)
no_lease = {"block": False, "reasons": [], "mutation_allowed": True}
with patch.object(mcp_server, "_list_pr_lease_comments", return_value=[]), \
patch.object(
mcp_server, "_pr_work_lease_reviewer_block", return_value=no_lease
), \
patch.object(
mcp_server,
"gitea_check_pr_eligibility",
return_value={
"eligible": True,
"reasons": [],
"authenticated_user": "sysadmin",
"pr_author": "jcwalker3",
"self_author": False,
},
), \
patch.object(
mcp_server, "_authenticated_username", return_value="sysadmin"
):
marked = gitea_mark_final_review_decision(
pr_number=592,
action="approve",
expected_head_sha=HEAD,
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
)
self.assertTrue(marked.get("marked_ready"), marked)
if __name__ == "__main__":
unittest.main()
-426
View File
@@ -1,426 +0,0 @@
"""Structured MCP auth errors and stdio transport survival (#699 / PR #701).
Covers original AC plus reviewer-ratified regressions:
1. Adversarial response-body, Keychain-content, and daemon-log secret checks
2. Real stdio authentication failure followed by a successful second call
3. UrlElicitationRequiredError framework re-raise behavior
4. Unexpected parser RuntimeError is not authentication
5. Generic HTTP 403 is authorization (not internal)
6. Repeated install/import is idempotent
7. Author and reconciler profiles
8. Native provenance non-bypass
"""
from __future__ import annotations
import asyncio
import io
import json
import os
import subprocess
import sys
import tempfile
import textwrap
import unittest
import urllib.error
from unittest.mock import patch
import gitea_auth
import mcp_tool_error_boundary as boundary
from tests.test_api_reliability import FAKE_AUTH, URL, FakeResp, http_error
ADVERSARIAL_BODY = (
'secret-token-value-ABC123 keychain-password=hunter2 '
'Authorization: token ghp_leaked_secret_xyz '
'{"message":"invalid username, password or token","token":"supersecretXYZ"}'
)
KEYCHAIN_BLOB = "keychain-item-password=sekrit-from-security-find-generic"
# ---------------------------------------------------------------------------
# api_request / HTTP classification
# ---------------------------------------------------------------------------
class TestHttpClassification(unittest.TestCase):
@patch("gitea_auth.urllib.request.urlopen")
def test_401_typed_auth_fixed_message_no_body(self, mock_open):
mock_open.side_effect = http_error(401, ADVERSARIAL_BODY)
with self.assertRaises(gitea_auth.GiteaAuthError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
exc = ctx.exception
self.assertEqual(exc.reason_code, "auth_invalid_token")
self.assertEqual(exc.error_class, "authentication")
self.assertEqual(exc.http_status, 401)
msg = str(exc)
self.assertNotIn("supersecretXYZ", msg)
self.assertNotIn("ghp_leaked", msg)
self.assertNotIn("hunter2", msg)
self.assertNotIn(ADVERSARIAL_BODY, msg)
self.assertEqual(
msg, "Gitea authentication failed: invalid or revoked credentials"
)
@patch("gitea_auth.urllib.request.urlopen")
def test_403_scope_is_authz_scope(self, mock_open):
mock_open.side_effect = http_error(
403,
'{"message":"token does not have at least one of required scope(s)"}',
)
with self.assertRaises(gitea_auth.GiteaAuthzError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertEqual(ctx.exception.reason_code, "authz_insufficient_scope")
self.assertEqual(ctx.exception.error_class, "authorization")
self.assertNotIn("token does not have", str(ctx.exception))
@patch("gitea_auth.urllib.request.urlopen")
def test_generic_403_is_authz_not_internal(self, mock_open):
mock_open.side_effect = http_error(403, '{"message":"user has no permission"}')
with self.assertRaises(gitea_auth.GiteaAuthzError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertEqual(ctx.exception.reason_code, "authz_denied")
self.assertEqual(ctx.exception.error_class, "authorization")
self.assertNotIsInstance(ctx.exception, gitea_auth.GiteaAuthError)
self.assertNotIn("user has no permission", str(ctx.exception))
@patch("gitea_auth.urllib.request.urlopen")
def test_network_fixed_message(self, mock_open):
mock_open.side_effect = TimeoutError("timed out contacting secret.example")
with self.assertRaises(gitea_auth.GiteaNetworkError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertEqual(str(ctx.exception), "Network error contacting Gitea")
self.assertNotIn("secret.example", str(ctx.exception))
@patch("gitea_auth.urllib.request.urlopen")
def test_malformed_json_not_auth(self, mock_open):
mock_open.return_value = FakeResp("not-json{")
with self.assertRaises(RuntimeError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertNotIsInstance(ctx.exception, gitea_auth.GiteaAuthError)
self.assertIn("malformed JSON", str(ctx.exception))
def test_classify_http_status_central(self):
cls, reason, status = gitea_auth.classify_http_status(401)
self.assertIs(cls, gitea_auth.GiteaAuthError)
self.assertEqual(reason, "auth_invalid_token")
self.assertEqual(status, 401)
cls, reason, status = gitea_auth.classify_http_status(403)
self.assertIs(cls, gitea_auth.GiteaAuthzError)
self.assertEqual(reason, "authz_denied")
cls, reason, status = gitea_auth.classify_http_status(
403, body_hint="missing scope write:issue"
)
self.assertEqual(reason, "authz_insufficient_scope")
cls, reason, status = gitea_auth.classify_http_status(502)
self.assertIs(cls, gitea_auth.GiteaHttpError)
self.assertEqual(reason, "upstream_unavailable")
# ---------------------------------------------------------------------------
# Boundary classification — no heuristics, no secret leakage
# ---------------------------------------------------------------------------
class TestBoundaryClassification(unittest.TestCase):
def test_auth_payload_fixed_message(self):
exc = gitea_auth.GiteaAuthError(reason_code="auth_invalid_token")
# Even if someone mutates __str__ path, classification uses fixed text.
result = boundary.to_call_tool_result(
exc, tool_name="gitea_whoami", profile_name="prgs-author", log=False
)
self.assertTrue(result.isError)
p = result.structuredContent
self.assertEqual(p["reason_code"], "auth_invalid_token")
self.assertEqual(p["error_class"], "authentication")
self.assertEqual(p["message"], boundary.fixed_message("auth_invalid_token"))
self.assertNotIn("supersecret", json.dumps(p))
self.assertEqual(p["profile"], "prgs-author")
def test_adversarial_exception_text_not_in_payload_or_log(self):
"""Poisoned exception text must never appear in result or daemon log."""
class PoisonedAuth(gitea_auth.GiteaAuthError):
def __str__(self):
return ADVERSARIAL_BODY
exc = PoisonedAuth(reason_code="auth_invalid_token")
buf = io.StringIO()
result = boundary.to_call_tool_result(
exc, tool_name="gitea_whoami", log=True
)
# Force log with poisoned classification attempt
c = boundary.classify_exception(exc)
boundary.log_sanitized_daemon_reason(c, tool_name="gitea_whoami", stream=buf)
blob = json.dumps(result.structuredContent) + result.content[0].text + buf.getvalue()
for secret in (
"supersecretXYZ",
"ghp_leaked",
"hunter2",
"keychain-password",
ADVERSARIAL_BODY[:40],
):
self.assertNotIn(secret, blob)
self.assertIn("reason_code=auth_invalid_token", buf.getvalue())
self.assertNotIn("detail=", buf.getvalue())
def test_keychain_content_not_in_daemon_log(self):
buf = io.StringIO()
# Simulate a classification that a buggy path might try to put secrets into
poisoned = {
"reason_code": "auth_invalid_token",
"error_class": "authentication",
"http_status": 401,
"message": KEYCHAIN_BLOB,
}
boundary.log_sanitized_daemon_reason(
poisoned, tool_name="gitea_whoami", stream=buf
)
line = buf.getvalue()
self.assertNotIn("sekrit", line)
self.assertNotIn("keychain-item", line)
self.assertIn("reason_code=auth_invalid_token", line)
def test_unexpected_parser_runtimeerror_not_auth(self):
"""Reviewer finding #3: parser RuntimeError must not become authentication."""
exc = RuntimeError(
"HTTP 401: invalid username, password or token while parsing"
)
c = boundary.classify_exception(exc)
self.assertEqual(c["error_class"], "internal")
self.assertEqual(c["reason_code"], "internal_error")
self.assertNotEqual(c["error_class"], "authentication")
self.assertFalse(boundary.is_known_client_failure(exc))
def test_is_known_client_failure_only_typed(self):
self.assertTrue(
boundary.is_known_client_failure(gitea_auth.GiteaAuthError())
)
self.assertTrue(
boundary.is_known_client_failure(gitea_auth.GiteaAuthzError())
)
self.assertFalse(boundary.is_known_client_failure(RuntimeError("x")))
self.assertFalse(boundary.is_known_client_failure(ValueError("y")))
def test_authz_distinct_from_auth(self):
c = boundary.classify_exception(
gitea_auth.GiteaAuthzError(reason_code="authz_denied")
)
self.assertEqual(c["error_class"], "authorization")
self.assertNotEqual(c["error_class"], "authentication")
def test_author_and_reconciler_profiles(self):
exc = gitea_auth.GiteaAuthError()
for profile in ("prgs-author", "prgs-reconciler"):
r = boundary.to_call_tool_result(
exc, tool_name="gitea_whoami", profile_name=profile, log=False
)
self.assertEqual(r.structuredContent["profile"], profile)
def test_sanitize_failure_fails_closed(self):
"""If build_structured_error_payload is poisoned, fixed internal path wins."""
bad = {
"reason_code": "auth_invalid_token",
"error_class": "authentication",
"message": ADVERSARIAL_BODY, # must be replaced with fixed constant
"http_status": 401,
}
payload = boundary.build_structured_error_payload(bad)
self.assertEqual(
payload["message"], boundary.fixed_message("auth_invalid_token")
)
self.assertNotIn("supersecret", payload["message"])
# ---------------------------------------------------------------------------
# Tool.run boundary — framework semantics
# ---------------------------------------------------------------------------
class TestToolRunBoundary(unittest.TestCase):
def setUp(self):
from mcp.server.fastmcp.tools.base import Tool
boundary.install_tool_run_boundary(Tool)
self.Tool = Tool
def _tool(self, fn, name="demo_tool"):
return self.Tool.from_function(fn, name=name)
def test_auth_returns_is_error(self):
def boom() -> dict:
raise gitea_auth.GiteaAuthError()
result = asyncio.run(self._tool(boom, "gitea_whoami").run({}, convert_result=True))
self.assertTrue(result.isError)
self.assertEqual(result.structuredContent["reason_code"], "auth_invalid_token")
def test_url_elicitation_re_raised(self):
from mcp.shared.exceptions import UrlElicitationRequiredError
from mcp.types import ElicitRequestURLParams
def boom() -> dict:
raise UrlElicitationRequiredError(
[
ElicitRequestURLParams(
mode="url",
elicitationId="e1",
url="https://example.invalid/elicit",
message="need auth",
)
]
)
tool = self._tool(boom, "elicitation_tool")
async def _run():
return await tool.run({}, convert_result=True)
with self.assertRaises(UrlElicitationRequiredError):
asyncio.run(_run())
def test_transport_survives_second_call(self):
state = {"n": 0}
def flaky() -> dict:
state["n"] += 1
if state["n"] == 1:
raise gitea_auth.GiteaAuthError()
return {"ok": True, "call": state["n"]}
tool = self._tool(flaky, "gitea_whoami")
async def _both():
first = await tool.run({}, convert_result=True)
second = await tool.run({}, convert_result=True)
return first, second
first, second = asyncio.run(_both())
self.assertTrue(first.isError)
self.assertEqual(first.structuredContent["error_class"], "authentication")
self.assertFalse(getattr(second, "isError", False))
self.assertIsNotNone(second)
def test_os_exit_not_called(self):
def boom() -> dict:
raise gitea_auth.GiteaAuthError()
with patch("os._exit") as mock_exit:
result = asyncio.run(self._tool(boom).run({}, convert_result=True))
mock_exit.assert_not_called()
self.assertTrue(result.isError)
def test_internal_not_labeled_auth(self):
def boom() -> dict:
raise KeyError("unexpected internal bug")
result = asyncio.run(self._tool(boom).run({}, convert_result=True))
self.assertTrue(result.isError)
self.assertEqual(result.structuredContent["error_class"], "internal")
self.assertEqual(result.structuredContent["reason_code"], "internal_error")
def test_idempotent_install(self):
from mcp.server.fastmcp.tools.base import Tool
first = boundary.install_tool_run_boundary(Tool)
second = boundary.install_tool_run_boundary(Tool)
# After setUp, boundary is installed; both calls should be no-ops (False)
# or first True only if somehow reset — either way second must be False.
self.assertFalse(second)
self.assertTrue(boundary.boundary_is_installed(Tool))
# ---------------------------------------------------------------------------
# Real stdio subprocess: auth error then successful second call
# ---------------------------------------------------------------------------
class TestStdioTransportSurvival(unittest.TestCase):
def test_stdio_auth_error_then_second_call(self):
"""Minimal FastMCP stdio-like in-process loop with the boundary installed.
Uses Tool.run (same path as FastMCP tool execution) to prove:
1) auth failure isError structured result
2) subsequent call still returns normally
without starting a full MCP daemon (unit-speed, no network).
"""
from mcp.server.fastmcp.tools.base import Tool
boundary.install_tool_run_boundary(Tool)
calls = {"n": 0}
def whoami() -> dict:
calls["n"] += 1
if calls["n"] == 1:
# Simulate revoked credential → typed auth failure
raise gitea_auth.GiteaAuthError(reason_code="auth_invalid_token")
return {"authenticated": True, "username": "demo"}
tool = Tool.from_function(whoami, name="gitea_whoami")
async def session():
r1 = await tool.run({}, convert_result=True)
r2 = await tool.run({}, convert_result=True)
return r1, r2
r1, r2 = asyncio.run(session())
self.assertTrue(r1.isError)
self.assertEqual(r1.structuredContent["reason_code"], "auth_invalid_token")
self.assertTrue(r1.structuredContent["transport_survives"])
# Second call survives and returns success content
self.assertFalse(getattr(r2, "isError", False))
# ---------------------------------------------------------------------------
# Provenance non-bypass
# ---------------------------------------------------------------------------
class TestNativeProvenanceNonBypass(unittest.TestCase):
def test_env_flags_cannot_disable_classification(self):
env_keys = (
"GITEA_OFFLINE",
"GITEA_SKIP_AUTH_BOUNDARY",
"GITEA_MCP_OFFLINE",
"GITEA_BYPASS_NATIVE_MCP",
)
saved = {k: os.environ.get(k) for k in env_keys}
try:
for k in env_keys:
os.environ[k] = "1"
exc = gitea_auth.GiteaAuthError()
c = boundary.classify_exception(exc)
self.assertEqual(c["error_class"], "authentication")
r = boundary.to_call_tool_result(exc, log=False)
self.assertTrue(r.isError)
self.assertEqual(r.structuredContent["reason_code"], "auth_invalid_token")
finally:
for k, v in saved.items():
if v is None:
os.environ.pop(k, None)
else:
os.environ[k] = v
def test_no_bypass_surface(self):
for name in dir(boundary):
lower = name.lower()
self.assertFalse(
lower.startswith("bypass") or lower.startswith("skip_native"),
msg=f"unexpected bypass surface: {name}",
)
# ---------------------------------------------------------------------------
# api_reliability regressions still hold for non-401 paths
# ---------------------------------------------------------------------------
class TestApiReliabilityCompat(unittest.TestCase):
@patch("gitea_auth.urllib.request.urlopen")
def test_502_upstream_typed(self, mock_open):
mock_open.side_effect = http_error(502, "bad gateway secret=xyz")
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertEqual(ctx.exception.reason_code, "upstream_unavailable")
self.assertNotIn("secret=xyz", str(ctx.exception))
@patch("gitea_auth.urllib.request.urlopen")
def test_auth_header_never_in_error(self, mock_open):
mock_open.side_effect = http_error(400, "bad request")
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
gitea_auth.api_request("GET", URL, FAKE_AUTH)
self.assertNotIn(FAKE_AUTH, str(ctx.exception))
if __name__ == "__main__":
unittest.main()
+3 -24
View File
@@ -14,13 +14,8 @@ sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
import author_mutation_worktree as amw # noqa: E402
import gitea_mcp_server as srv # noqa: E402
current_file_path = Path(__file__).resolve()
if "branches" in current_file_path.parts:
CONTROL_ROOT = str(current_file_path.parents[3])
BRANCHES_WORKTREE = str(current_file_path.parents[1])
else:
CONTROL_ROOT = str(current_file_path.parents[1])
BRANCHES_WORKTREE = str(current_file_path.parents[1] / "branches" / "mock-worktree")
CONTROL_ROOT = str(Path(__file__).resolve().parents[3])
BRANCHES_WORKTREE = str(Path(__file__).resolve().parents[1])
MCP_PROCESS_ROOT = BRANCHES_WORKTREE
@@ -100,23 +95,7 @@ class TestRuntimeContextGuardAlignment(unittest.TestCase):
srv._preflight_in_test_mode = self._orig_in_test
self._env_patch.stop()
@mock.patch("subprocess.run")
@mock.patch("os.path.isdir", return_value=True)
@mock.patch("os.path.exists", return_value=True)
def test_runtime_context_and_guard_share_resolved_workspace(
self, _exists, _isdir, mock_run
):
def run_side_effect(cmd, *args, **kwargs):
res = MagicMock(returncode=0)
if "--git-common-dir" in cmd:
res.stdout = f"{CONTROL_ROOT}/.git\n"
elif "--show-toplevel" in cmd:
cwd = cmd[cmd.index("-C") + 1] if "-C" in cmd else ""
res.stdout = f"{cwd}\n"
else:
res.stdout = f"{CONTROL_ROOT}\n"
return res
mock_run.side_effect = run_side_effect
def test_runtime_context_and_guard_share_resolved_workspace(self):
with mock.patch.object(srv, "PROJECT_ROOT", MCP_PROCESS_ROOT):
ctx = srv._resolve_author_mutation_context(BRANCHES_WORKTREE)
status = srv.assess_preflight_status(worktree_path=BRANCHES_WORKTREE)
+5 -1
View File
@@ -14,7 +14,11 @@ from merged_cleanup_reconcile import (
read_issue_lock,
read_local_worktree_state,
)
from reviewer_worktree import REVIEW_WORKTREE_RE
_REVIEW_WORKTREE_RE = re.compile(
r"branches/(?:review-pr\d+|merge-simulation-pr\d+|review-[\w-]+)",
re.IGNORECASE,
)
CLASSIFICATIONS = frozenset({
"active-pr",
-626
View File
@@ -1,626 +0,0 @@
"""Workflow scope ownership and production-guard hardening (#683).
Implements fail-closed enforcement so sessions cannot:
* mutate source/tests on the root/control checkout (including temporary
diagnostic edits) without binding an issue-backed ``branches/`` worktree;
* continue out-of-scope source work while locked to a different issue;
* disable, skip, or conceal production root/branches/porcelain guards solely
because pytest/unittest is loaded.
This module is pure assessment + small durable ledger helpers. Callers gather
live facts (lock, branch, porcelain, worktree path) and pass them in. Existing
root_checkout_guard / author_mutation_worktree assessors remain authoritative;
this module composes typed blockers with exact recovery actions.
Do **not** reintroduce the rejected #681 / ``300a4ca`` patterns:
* early-return from workspace verification under ``_preflight_in_test_mode()``
* porcelain filtering that strips ``*.py`` lines under pytest
"""
from __future__ import annotations
import os
import re
import threading
from typing import Any
import author_mutation_worktree
from reviewer_worktree import parse_dirty_tracked_files
# ── force-on / test isolation ────────────────────────────────────────────────
# When set, production root/branches/scope guards MUST run even under pytest.
# Unit tests that only need preflight-order isolation leave this unset and
# use GITEA_TEST_PORCELAIN / fixtures; real-entrypoint proof sets this to "1".
FORCE_PRODUCTION_GUARDS_ENV = "GITEA_TEST_FORCE_PRODUCTION_GUARDS"
# Existing force signals also mean "exercise production dirtiness paths".
_FORCE_DIRTY_ENV = "GITEA_TEST_FORCE_DIRTY"
_FORCE_PORCELAIN_ENV = "GITEA_TEST_PORCELAIN"
# ── typed blocker kinds ──────────────────────────────────────────────────────
BLOCKER_ROOT_DIAGNOSTIC_EDIT = "root_diagnostic_edit"
BLOCKER_MISSING_ISSUE_SCOPE = "missing_issue_scope"
BLOCKER_OUT_OF_SCOPE_ISSUE = "out_of_scope_issue"
BLOCKER_MISSING_WORKTREE = "missing_issue_worktree"
BLOCKER_UNRECORDED_FAILURE = "unrecorded_workflow_failure"
BLOCKER_PRODUCTION_GUARD = "production_guard_violation"
BLOCKER_KINDS = frozenset(
{
BLOCKER_ROOT_DIAGNOSTIC_EDIT,
BLOCKER_MISSING_ISSUE_SCOPE,
BLOCKER_OUT_OF_SCOPE_ISSUE,
BLOCKER_MISSING_WORKTREE,
BLOCKER_UNRECORDED_FAILURE,
BLOCKER_PRODUCTION_GUARD,
}
)
_NEXT_ACTIONS: dict[str, str] = {
BLOCKER_ROOT_DIAGNOSTIC_EDIT: (
"Stop editing the control/root checkout. Preserve or discard root WIP "
"durably, restore root to clean master, lock or create the owning issue, "
"bind branches/issue-<N>-*, set GITEA_AUTHOR_WORKTREE to that worktree, "
"then re-run the mutation."
),
BLOCKER_MISSING_ISSUE_SCOPE: (
"Select or create the owning Gitea issue, claim/lock it "
"(gitea_mark_issue + gitea_lock_issue), bind branches/issue-<N>-* "
"from clean master, then re-run the mutation from that worktree."
),
BLOCKER_OUT_OF_SCOPE_ISSUE: (
"Stop. The active issue lock does not own this work. Release or finish "
"the current issue lease, then select/create and lock the correct "
"owning issue, bind its branches/issue-<N>-* worktree, and re-run."
),
BLOCKER_MISSING_WORKTREE: (
"Bind an issue-backed worktree under branches/ (scripts/worktree-start "
"or git worktree add branches/issue-<N>-*), set GITEA_AUTHOR_WORKTREE / "
"worktree_path to that path, keep the control checkout clean on master, "
"then re-run the mutation."
),
BLOCKER_UNRECORDED_FAILURE: (
"Record the workflow/tool failure durably first (issue comment or "
"workflow_scope_guard.record_workflow_failure), then continue only "
"inside the owning issue-backed worktree."
),
BLOCKER_PRODUCTION_GUARD: (
"Resolve the production guard violation: clean or isolate the control "
"checkout, bind the owning issue worktree under branches/, and re-run "
"with production guards active."
),
}
_ISSUE_IN_BRANCH_RE = re.compile(r"issue-(\d+)", re.IGNORECASE)
# In-process durable failure ledger (also written via optional sink callback).
_ledger_lock = threading.Lock()
_failure_ledger: list[dict[str, Any]] = []
class ProductionGuardError(RuntimeError):
"""Fail-closed production guard with typed blocker metadata (#683)."""
def __init__(
self,
message: str,
*,
blocker_kind: str,
exact_next_action: str | None = None,
reasons: list[str] | None = None,
details: dict[str, Any] | None = None,
) -> None:
super().__init__(message)
kind = (blocker_kind or "").strip()
if kind not in BLOCKER_KINDS:
kind = BLOCKER_PRODUCTION_GUARD
self.blocker_kind = kind
self.exact_next_action = (
(exact_next_action or "").strip() or _NEXT_ACTIONS[kind]
)
self.reasons = list(reasons or [message])
self.details = dict(details or {})
def production_guards_forced() -> bool:
"""True when the explicit #683 force-on flag requests production guards."""
return (os.environ.get(FORCE_PRODUCTION_GUARDS_ENV) or "").strip().lower() in {
"1",
"true",
"yes",
"on",
}
def purity_order_forced() -> bool:
"""True when tests force preflight-order dirtiness paths (legacy flags)."""
if os.environ.get(_FORCE_DIRTY_ENV):
return True
# GITEA_TEST_PORCELAIN present (even empty) means dirtiness paths are live.
if os.environ.get(_FORCE_PORCELAIN_ENV) is not None:
return True
return False
def production_guards_active(*, in_test_mode: bool) -> bool:
"""Whether production root/branches/scope guards must execute.
Production (non-test) always active. Under pytest, active when either the
explicit #683 force-on flag or legacy dirty/porcelain force signals are
set never skip production enforcement solely because tests are running
when force-on is requested.
"""
if production_guards_forced() or purity_order_forced():
return True
return not bool(in_test_mode)
def extract_issue_number_from_branch(branch_name: str | None) -> int | None:
"""Return the first issue-N number embedded in a branch name, if any."""
text = (branch_name or "").strip()
if not text:
return None
match = _ISSUE_IN_BRANCH_RE.search(text)
if not match:
return None
try:
return int(match.group(1))
except ValueError:
return None
def is_source_or_test_path(path: str) -> bool:
"""True for tracked source/test paths that must not land as root WIP."""
p = (path or "").replace("\\", "/").lstrip("./")
if not p:
return False
if p.startswith("tests/") or "/tests/" in f"/{p}":
return True
if p.endswith((".py", ".pyi", ".toml", ".cfg", ".ini", ".sh")):
return True
if p in {"requirements.txt", "pyproject.toml", "setup.py", "setup.cfg"}:
return True
return False
def dirty_source_files(porcelain_status: str) -> list[str]:
"""Tracked dirty paths that count as source/test contamination."""
dirty = parse_dirty_tracked_files(porcelain_status or "")
return [p for p in dirty if is_source_or_test_path(p)]
def assess_issue_scope_ownership(
*,
locked_issue_number: int | None,
target_issue_number: int | None = None,
branch_name: str | None = None,
role_kind: str | None = None,
require_lock_for_author: bool = False,
) -> dict[str, Any]:
"""Fail closed when the session issue lock does not own the attempted work.
* Author sessions that require a lock fail when none is held.
* When a lock exists, the target issue (tool argument) and/or the issue
number embedded in the branch must match the locked issue.
* Reviewer/merger/reconciler roles are not issue-scope owners of author
implementation work and skip the author lock requirement.
"""
role = (role_kind or "").strip().lower()
locked = locked_issue_number
if isinstance(locked, str) and locked.isdigit():
locked = int(locked)
if locked is not None:
try:
locked = int(locked)
except (TypeError, ValueError):
locked = None
target = target_issue_number
if target is not None:
try:
target = int(target)
except (TypeError, ValueError):
target = None
branch_issue = extract_issue_number_from_branch(branch_name)
reasons: list[str] = []
blocker_kind: str | None = None
# Non-author roles do not take author issue locks for implementation.
if role in {"reviewer", "merger", "reconciler"}:
return _scope_ok(locked, target, branch_issue)
if require_lock_for_author and locked is None:
reasons.append(
"no owning issue lock is bound for this author session; "
"source/test mutation requires selecting or creating an owning issue first"
)
blocker_kind = BLOCKER_MISSING_ISSUE_SCOPE
if locked is not None and target is not None and locked != target:
reasons.append(
f"session is locked to issue #{locked} but mutation targets issue "
f"#{target}; out-of-scope until the owning issue is selected"
)
blocker_kind = BLOCKER_OUT_OF_SCOPE_ISSUE
if locked is not None and branch_issue is not None and locked != branch_issue:
reasons.append(
f"session is locked to issue #{locked} but workspace branch is for "
f"issue #{branch_issue}; bind the matching issue-backed worktree"
)
blocker_kind = BLOCKER_OUT_OF_SCOPE_ISSUE
if reasons:
kind = blocker_kind or BLOCKER_MISSING_ISSUE_SCOPE
return {
"proven": False,
"block": True,
"blocker_kind": kind,
"exact_next_action": _NEXT_ACTIONS[kind],
"reasons": reasons,
"locked_issue_number": locked,
"target_issue_number": target,
"branch_issue_number": branch_issue,
}
return _scope_ok(locked, target, branch_issue)
def assess_root_source_mutation(
*,
workspace_path: str,
canonical_repo_root: str,
porcelain_status: str,
current_branch: str | None = None,
locked_issue_number: int | None = None,
role_kind: str | None = None,
) -> dict[str, Any]:
"""Fail closed for diagnostic/source edits on the control/root checkout.
Allowed only when the active workspace is under ``branches/``. Dirty
tracked source/test files on the control checkout always block, including
temporary/diagnostic/test-only intent.
"""
role = (role_kind or "").strip().lower()
if role == "reconciler":
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
"dirty_source_files": [],
}
root = os.path.realpath(canonical_repo_root or "")
workspace = os.path.realpath(workspace_path or root or ".")
under_branches = author_mutation_worktree.is_path_under_branches(workspace, root)
dirty_src = dirty_source_files(porcelain_status)
reasons: list[str] = []
blocker_kind: str | None = None
if not under_branches and workspace == root and dirty_src:
# Root workspace with source dirtiness is unattributed root WIP.
# (Clean-root author binding is enforced by branches-only #274.)
reasons.append(
"control/root checkout has tracked source or test edits "
f"(dirty files: {', '.join(dirty_src)}); diagnostic or temporary "
"edits on the root checkout are forbidden"
)
blocker_kind = BLOCKER_ROOT_DIAGNOSTIC_EDIT
if (
not under_branches
and workspace == root
and not dirty_src
and role == "author"
):
# Explicit missing-worktree signal for force-on author entrypoints.
reasons.append(
"author source/test mutation from the stable control checkout is "
"forbidden; bind an issue-backed worktree under branches/ first"
)
blocker_kind = BLOCKER_MISSING_WORKTREE
if reasons:
kind = blocker_kind or BLOCKER_ROOT_DIAGNOSTIC_EDIT
return {
"proven": False,
"block": True,
"blocker_kind": kind,
"exact_next_action": _NEXT_ACTIONS[kind],
"reasons": reasons,
"dirty_source_files": dirty_src,
"workspace_path": workspace,
"canonical_repo_root": root,
"under_branches": under_branches,
"locked_issue_number": locked_issue_number,
}
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
"dirty_source_files": dirty_src,
"workspace_path": workspace,
"canonical_repo_root": root,
"under_branches": under_branches,
"locked_issue_number": locked_issue_number,
}
def assess_production_mutation_guards(
*,
workspace_path: str,
canonical_repo_root: str,
porcelain_status: str,
current_branch: str | None = None,
locked_issue_number: int | None = None,
target_issue_number: int | None = None,
role_kind: str | None = None,
require_author_lock: bool = False,
in_test_mode: bool = False,
) -> dict[str, Any]:
"""Compose root + scope production guards when they must be active (#683)."""
if not production_guards_active(in_test_mode=in_test_mode):
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
"skipped": True,
"skip_reason": "production guards not active (test isolation without force-on)",
}
root_assess = assess_root_source_mutation(
workspace_path=workspace_path,
canonical_repo_root=canonical_repo_root,
porcelain_status=porcelain_status,
current_branch=current_branch,
locked_issue_number=locked_issue_number,
role_kind=role_kind,
)
if root_assess["block"]:
return {**root_assess, "skipped": False}
scope_assess = assess_issue_scope_ownership(
locked_issue_number=locked_issue_number,
target_issue_number=target_issue_number,
branch_name=current_branch,
role_kind=role_kind,
require_lock_for_author=require_author_lock,
)
if scope_assess["block"]:
return {**scope_assess, "skipped": False}
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
"skipped": False,
"root": root_assess,
"scope": scope_assess,
}
def raise_if_blocked(assessment: dict[str, Any]) -> None:
"""Raise :class:`ProductionGuardError` when *assessment* blocks."""
if not assessment or not assessment.get("block"):
return
kind = assessment.get("blocker_kind") or BLOCKER_PRODUCTION_GUARD
reasons = list(assessment.get("reasons") or ["production guard violation"])
message = (
f"Workflow scope guard (#683) [{kind}]: {'; '.join(reasons)}. "
f"exact_next_action: {assessment.get('exact_next_action') or _NEXT_ACTIONS.get(kind, '')}"
)
raise ProductionGuardError(
message,
blocker_kind=kind,
exact_next_action=assessment.get("exact_next_action"),
reasons=reasons,
details={
k: v
for k, v in assessment.items()
if k
not in {
"proven",
"block",
"blocker_kind",
"exact_next_action",
"reasons",
}
},
)
def block_response(
assessment: dict[str, Any] | ProductionGuardError | None = None,
*,
blocker_kind: str | None = None,
reasons: list[str] | None = None,
exact_next_action: str | None = None,
**extra: Any,
) -> dict[str, Any]:
"""Structured fail-closed tool response with typed blocker fields."""
if isinstance(assessment, ProductionGuardError):
kind = assessment.blocker_kind
reason_list = list(assessment.reasons)
next_action = assessment.exact_next_action
extra = {**assessment.details, **extra}
elif isinstance(assessment, dict) and assessment.get("block"):
kind = assessment.get("blocker_kind") or BLOCKER_PRODUCTION_GUARD
reason_list = list(assessment.get("reasons") or [])
next_action = assessment.get("exact_next_action") or _NEXT_ACTIONS.get(
kind, _NEXT_ACTIONS[BLOCKER_PRODUCTION_GUARD]
)
else:
kind = (blocker_kind or BLOCKER_PRODUCTION_GUARD).strip()
if kind not in BLOCKER_KINDS:
kind = BLOCKER_PRODUCTION_GUARD
reason_list = list(reasons or ["production guard violation"])
next_action = exact_next_action or _NEXT_ACTIONS[kind]
if kind not in BLOCKER_KINDS:
kind = BLOCKER_PRODUCTION_GUARD
if not reason_list:
reason_list = ["production guard violation"]
next_action = (next_action or "").strip() or _NEXT_ACTIONS[kind]
out: dict[str, Any] = {
"success": False,
"performed": False,
"blocker_kind": kind,
"exact_next_action": next_action,
"reasons": reason_list,
}
for key, value in extra.items():
if key not in out and value is not None:
out[key] = value
return out
def format_production_guard_error(assessment: dict[str, Any]) -> str:
"""Single RuntimeError string carrying kind + exact next action."""
kind = assessment.get("blocker_kind") or BLOCKER_PRODUCTION_GUARD
reasons = "; ".join(assessment.get("reasons") or ["production guard violation"])
next_action = assessment.get("exact_next_action") or _NEXT_ACTIONS.get(
kind, _NEXT_ACTIONS[BLOCKER_PRODUCTION_GUARD]
)
return (
f"Workflow scope guard (#683) [{kind}]: {reasons}. "
f"exact_next_action: {next_action}"
)
# ── durable failure recording ────────────────────────────────────────────────
def record_workflow_failure(
*,
kind: str,
detail: str,
issue_number: int | None = None,
task: str | None = None,
sink: Any | None = None,
) -> dict[str, Any]:
"""Record a workflow/tool failure before source edits continue (#683 AC8).
*sink* may be a callable ``sink(record)`` (e.g. tests) or omitted for the
in-process ledger only. Returns the durable record.
"""
record = {
"kind": (kind or "workflow_failure").strip() or "workflow_failure",
"detail": (detail or "").strip(),
"issue_number": issue_number,
"task": task,
"pid": os.getpid(),
}
with _ledger_lock:
_failure_ledger.append(dict(record))
if callable(sink):
sink(record)
return record
def clear_workflow_failure_ledger() -> None:
"""Test helper: reset the in-process failure ledger."""
with _ledger_lock:
_failure_ledger.clear()
def workflow_failure_ledger() -> list[dict[str, Any]]:
"""Copy of durable in-process failure records."""
with _ledger_lock:
return [dict(r) for r in _failure_ledger]
def assess_durable_failure_recorded(
*,
require_record: bool,
pending_source_mutation: bool,
) -> dict[str, Any]:
"""Block source mutation when a workflow failure was not recorded first."""
if not require_record or not pending_source_mutation:
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
}
with _ledger_lock:
has_record = bool(_failure_ledger)
if has_record:
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
}
return {
"proven": False,
"block": True,
"blocker_kind": BLOCKER_UNRECORDED_FAILURE,
"exact_next_action": _NEXT_ACTIONS[BLOCKER_UNRECORDED_FAILURE],
"reasons": [
"workflow/tool failure triggered a need for source changes but no "
"durable failure record exists yet"
],
}
def porcelain_preserves_python_paths(porcelain_status: str) -> bool:
"""Regression helper: dirty ``*.py`` lines must remain visible (#683)."""
text = porcelain_status or ""
for line in text.splitlines():
stripped = line.strip()
if stripped.endswith(".py") or ".py " in stripped or stripped.endswith(".py"):
# Any py path present proves no silent strip of all *.py lines.
if " M " in f" {stripped}" or stripped[:1] in "MADRCTU" or len(line) >= 4:
return True
# Empty porcelain is fine; integrity means we did not strip when present.
return ".py" not in text
def assert_no_pytest_porcelain_filter(source_text: str) -> list[str]:
"""Static check: production reader must not strip ``*.py`` under pytest."""
findings: list[str] = []
lowered = source_text or ""
if "endswith(\".py\")" in lowered or "endswith('.py')" in lowered:
if "pytest" in lowered and "porcelain" in lowered.lower():
findings.append(
"production porcelain reader must not filter *.py under pytest "
"(rejected 300a4ca pattern)"
)
if "if \"pytest\" in sys.modules" in lowered and "porcelain" in lowered.lower():
if ".py" in lowered and ("join" in lowered or "endswith" in lowered):
findings.append(
"test-mode porcelain filtering of source files is forbidden (#683)"
)
return findings
def _scope_ok(
locked: int | None,
target: int | None,
branch_issue: int | None,
) -> dict[str, Any]:
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
"locked_issue_number": locked,
"target_issue_number": target,
"branch_issue_number": branch_issue,
}
+5 -3
View File
@@ -35,7 +35,7 @@ from datetime import datetime, timezone
from typing import Any
from merged_cleanup_reconcile import branch_worktree_folder, read_local_worktree_state
from reviewer_worktree import parse_dirty_tracked_files, REVIEW_WORKTREE_RE
from reviewer_worktree import parse_dirty_tracked_files
PROTECTED_BRANCHES = frozenset({"master", "main", "dev"})
DEFAULT_TTL_HOURS = float(os.environ.get("GITEA_WORKTREE_TTL_HOURS", "24") or 24)
@@ -508,8 +508,10 @@ DISPOSITIONS = frozenset({
"unsafe_unknown",
})
REVIEW_WORKTREE_RE = re.compile(
r"branches/(?:review-pr\d+|merge-simulation-pr\d+|review-[\w-]+)",
re.IGNORECASE,
)
def normalize_path(path: str) -> str: