Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
1be4600261 | ||
|
|
780ef0b1be | ||
|
|
a654cda058 | ||
|
|
ab1c2d7973 | ||
|
|
6a179aeb85 | ||
|
|
f20c8436aa | ||
|
|
db5d14184f | ||
|
|
10228e1c06 | ||
|
|
d8b2b8f1a7 | ||
|
|
9e1d5c5649 | ||
|
|
2429d9d2e8 | ||
|
|
16cd871fbd | ||
|
|
783ea88a01 | ||
|
|
036b78e31e | ||
|
|
08c3488d7c | ||
|
|
4f2fd9a8b1 | ||
|
|
4185ee1417 |
@@ -0,0 +1,610 @@
|
||||
"""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
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,105 @@
|
||||
# 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
|
||||
```
|
||||
@@ -0,0 +1,301 @@
|
||||
# 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 §§2–11.
|
||||
|
||||
## 14. Document history
|
||||
|
||||
| Date | Change |
|
||||
|------|--------|
|
||||
| 2026-07-09 | Initial ADR: dependency order, authority model, topology, lease migration, bridge, `incident_links`, security, non-goals |
|
||||
+936
-42
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,788 @@
|
||||
"""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")
|
||||
@@ -375,6 +375,64 @@ 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,
|
||||
*,
|
||||
@@ -405,6 +463,11 @@ 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}'. "
|
||||
|
||||
@@ -0,0 +1,723 @@
|
||||
"""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,
|
||||
}
|
||||
@@ -6,6 +6,9 @@ Runs over stdio. All tools authenticate via macOS keychain (git credential fill)
|
||||
import os
|
||||
import sys
|
||||
|
||||
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,
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
"""Stale / moot #332 review-decision lock detection and cleanup policy (#594).
|
||||
"""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
|
||||
@@ -6,6 +6,12 @@ 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.
|
||||
@@ -23,6 +29,45 @@ from typing import Any
|
||||
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:
|
||||
@@ -35,18 +80,125 @@ def last_terminal_mutation(lock: dict | None) -> dict | None:
|
||||
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,
|
||||
}
|
||||
|
||||
|
||||
@@ -56,6 +208,7 @@ def lock_summary(lock: dict | None) -> dict[str, Any] | 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"),
|
||||
@@ -67,16 +220,21 @@ def lock_summary(lock: dict | None) -> dict[str, Any] | None:
|
||||
"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"),
|
||||
}
|
||||
@@ -88,13 +246,16 @@ def assess_stale_review_decision_lock(
|
||||
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).
|
||||
"""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 and #332 hard-stop remains in force.
|
||||
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] = {
|
||||
@@ -102,6 +263,10 @@ def assess_stale_review_decision_lock(
|
||||
"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,
|
||||
@@ -141,8 +306,10 @@ def assess_stale_review_decision_lock(
|
||||
|
||||
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(
|
||||
@@ -165,25 +332,46 @@ def assess_stale_review_decision_lock(
|
||||
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"]:
|
||||
result["reasons"].append(
|
||||
f"terminal review mutation on open PR #{pr_number} is still active "
|
||||
f"({action}); #332 hard-stop remains — cleanup forbidden (#594)"
|
||||
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)"
|
||||
|
||||
@@ -139,6 +139,103 @@ 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",
|
||||
|
||||
@@ -275,7 +275,6 @@ def main():
|
||||
servers[name],
|
||||
required_tool=REQUIRED_NAMESPACE_TOOLS.get(name),
|
||||
config_path=config_path,
|
||||
probe_source="offline_spawn",
|
||||
):
|
||||
failed = True
|
||||
else:
|
||||
|
||||
@@ -0,0 +1,366 @@
|
||||
"""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()
|
||||
@@ -0,0 +1,824 @@
|
||||
"""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()
|
||||
@@ -0,0 +1,397 @@
|
||||
"""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()
|
||||
@@ -0,0 +1,345 @@
|
||||
"""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()
|
||||
@@ -103,20 +103,40 @@ 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",
|
||||
worktree_path="/tmp/other-does-not-exist-420",
|
||||
session_pid=1,
|
||||
work_lease=_lease("2000-01-01T00:00:00Z"),
|
||||
)
|
||||
incoming = _lock_record(worktree_path="/tmp/mine")
|
||||
self.assertIsNone(ils.assess_foreign_lock_overwrite(existing, incoming))
|
||||
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=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"),
|
||||
)
|
||||
self.assertIn("Recovery review is required", block or "")
|
||||
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 "")
|
||||
|
||||
def test_same_owner_lease_conflict_allows_refresh(self):
|
||||
worktree = "/tmp/wt-420"
|
||||
|
||||
@@ -0,0 +1,392 @@
|
||||
"""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()
|
||||
@@ -5,6 +5,7 @@ the MCP protocol) with mocked API responses.
|
||||
"""
|
||||
import json
|
||||
import os
|
||||
import shutil
|
||||
import sys
|
||||
import tempfile
|
||||
import unittest
|
||||
@@ -3811,7 +3812,15 @@ 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",
|
||||
@@ -3825,15 +3834,22 @@ class TestIssueLocking(unittest.TestCase):
|
||||
"remote": "prgs",
|
||||
"org": "Scaled-Tech-Consulting",
|
||||
"repo": prgs_repo,
|
||||
"worktree_path": "/tmp/other-worktree",
|
||||
"worktree_path": sticky_worktree,
|
||||
"session_pid": os.getpid(),
|
||||
"pid": os.getpid(),
|
||||
"work_lease": {
|
||||
"operation_type": "author_issue_work",
|
||||
"expires_at": "2000-01-01T00:00:00Z",
|
||||
},
|
||||
},
|
||||
)
|
||||
with self.assertRaises(RuntimeError) as ctx:
|
||||
gitea_lock_issue(issue_number=196, branch_name="feat/issue-196-mutations", remote="prgs")
|
||||
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",
|
||||
)
|
||||
self.assertIn("Recovery review is required before takeover", str(ctx.exception))
|
||||
|
||||
@patch("mcp_server.api_get_all", return_value=[])
|
||||
|
||||
Reference in New Issue
Block a user