Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
f7ef719bd6 | ||
|
|
cad5e44703 | ||
|
|
c4d089f931 | ||
|
|
baf3a474df | ||
|
|
784369cc25 | ||
|
|
e0b87a0ae5 | ||
|
|
34173e079c | ||
|
|
b7a63a5579 |
+1
-13
@@ -163,19 +163,7 @@ _TERMINAL_OWNERSHIP_STATUSES = frozenset(
|
|||||||
{"released", "abandoned", "done", "blocked", "terminal", "closed"}
|
{"released", "abandoned", "done", "blocked", "terminal", "closed"}
|
||||||
)
|
)
|
||||||
_EXPIRED_STATUSES = frozenset({"expired"})
|
_EXPIRED_STATUSES = frozenset({"expired"})
|
||||||
_STALE_STATUSES = frozenset(
|
_STALE_STATUSES = frozenset({"stale", "stale_dead_process", "stale_missing_worktree"})
|
||||||
{
|
|
||||||
"stale",
|
|
||||||
"stale_dead_process",
|
|
||||||
"stale_missing_worktree",
|
|
||||||
# #790 Slice A heartbeat-lifecycle bands. Listed here so they are
|
|
||||||
# *classified* rather than falling through to the unknown-status branch;
|
|
||||||
# they still block unless the ownership record proves
|
|
||||||
# ``reclaim_allowed is True``, so the O2 fail-closed rule is unchanged.
|
|
||||||
"stale_missed_heartbeat",
|
|
||||||
"stale_absolute_cap",
|
|
||||||
}
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
def _norm_str(value: Any) -> str:
|
def _norm_str(value: Any) -> str:
|
||||||
|
|||||||
@@ -101,7 +101,6 @@ that gates each call, not which tools exist.
|
|||||||
- `gitea_get_profile`
|
- `gitea_get_profile`
|
||||||
- `gitea_get_runtime_context`
|
- `gitea_get_runtime_context`
|
||||||
- `gitea_get_shell_health`
|
- `gitea_get_shell_health`
|
||||||
- `gitea_heartbeat_issue_lock`
|
|
||||||
- `gitea_heartbeat_reviewer_pr_lease`
|
- `gitea_heartbeat_reviewer_pr_lease`
|
||||||
- `gitea_inspect_workflow_lease`
|
- `gitea_inspect_workflow_lease`
|
||||||
- `gitea_issue_irrecoverable_provenance_authorization`
|
- `gitea_issue_irrecoverable_provenance_authorization`
|
||||||
|
|||||||
@@ -349,6 +349,53 @@ health, workflow/schema SHA-256 hashes, and stale-runtime warnings when the
|
|||||||
checkout is behind merged safety-gate changes. Restart guidance links to #420;
|
checkout is behind merged safety-gate changes. Restart guidance links to #420;
|
||||||
no tokens or MCP restart actions are exposed.
|
no tokens or MCP restart actions are exposed.
|
||||||
|
|
||||||
|
## Inventory API (#636)
|
||||||
|
|
||||||
|
`GET /api/v1/inventory` returns one versioned, read-only snapshot that unifies
|
||||||
|
what the lease (#433), worktree (#432), and runtime (#430) MVP views each show
|
||||||
|
separately, so traffic-control and recovery consumers read the same source.
|
||||||
|
`GET /api/v1/inventory/{section}` returns a single section under the identical
|
||||||
|
schema (`sessions`, `leases`, `locks`, `worktrees`, `namespaces`); an unknown
|
||||||
|
section is a `404` with `error: unknown_section`. Both routes are `GET`-only.
|
||||||
|
|
||||||
|
Each section carries its own `status` (`ok` / `degraded` / `unavailable`), a
|
||||||
|
`reason` when not `ok`, and a `scan_ms`. A subsystem that cannot be read
|
||||||
|
degrades to a reasoned section; it never raises and never emits an empty list
|
||||||
|
that would read as "nothing is there".
|
||||||
|
|
||||||
|
### Field authority
|
||||||
|
|
||||||
|
Every section names where its rows came from; authorities are never blended.
|
||||||
|
|
||||||
|
| Section | Authority | Source |
|
||||||
|
|---|---|---|
|
||||||
|
| `sessions` | `control_plane_db` | #613 control-plane DB (`mode=ro`), authoritative for exclusive ownership (#600/#601) |
|
||||||
|
| `leases` | `control_plane_db` | #613 control-plane DB; degrades if the `work_items` table is absent |
|
||||||
|
| `locks` | `filesystem` | durable per-issue lock files (`issue_lock_store`) |
|
||||||
|
| `worktrees` | `filesystem` | registered git worktrees via the #432 hygiene scanner |
|
||||||
|
| `namespaces` | `filesystem` | the active profile serving this web process (others are not enumerable) |
|
||||||
|
|
||||||
|
The payload restates this map under `field_authority` for machine consumers.
|
||||||
|
|
||||||
|
### Ownership safety
|
||||||
|
|
||||||
|
`ownership_authority_complete` is true only when every ownership-bearing section
|
||||||
|
(`sessions`, `leases`, `locks`) read cleanly. While it is false, nothing is
|
||||||
|
reported as unowned and no collision is asserted from a degraded source —
|
||||||
|
absence of evidence is reported as absence of evidence, never as free work.
|
||||||
|
|
||||||
|
`collisions` surfaces detectable conflicts, each with a `kind` and `severity`:
|
||||||
|
`lock-without-worktree`, `duplicate-live-lock`, `live-lock-dead-owner` (unexpired
|
||||||
|
lease, dead pid — a #753 recovery candidate that would read as live to a naive
|
||||||
|
timestamp check), `stale-lock-dead-owner`, `expired-lock-live-owner` (the
|
||||||
|
#635/#760 daemon-pid deadlock), `concurrent-active-lease`, `active-lease-past-expiry`,
|
||||||
|
and `orphan-lease`. Collisions are emitted only from sections that read cleanly.
|
||||||
|
|
||||||
|
The control-plane DB is opened through a `mode=ro` URI so a read never creates
|
||||||
|
or migrates it; paths are collapsed against `$HOME`, URLs lose userinfo and
|
||||||
|
query strings, and credential-shaped values are redacted at the boundary. Lease
|
||||||
|
steal/release and worktree deletion are Phase 2+ and have no representation here.
|
||||||
|
|
||||||
## Workflow-event timeline (#637)
|
## Workflow-event timeline (#637)
|
||||||
|
|
||||||
`GET /api/v1/timeline` is a read-only, versioned aggregation of workflow
|
`GET /api/v1/timeline` is a read-only, versioned aggregation of workflow
|
||||||
|
|||||||
+4
-146
@@ -2065,7 +2065,6 @@ import allocator_dependencies # noqa: E402
|
|||||||
import dependency_graph # noqa: E402 # #784 durable dependency edges
|
import dependency_graph # noqa: E402 # #784 durable dependency edges
|
||||||
import control_plane_db # noqa: E402
|
import control_plane_db # noqa: E402
|
||||||
import lease_lifecycle # noqa: E402
|
import lease_lifecycle # noqa: E402
|
||||||
import lease_policy # noqa: E402
|
|
||||||
import workflow_dashboard # noqa: E402 # #605 live queue/lease dashboard
|
import workflow_dashboard # noqa: E402 # #605 live queue/lease dashboard
|
||||||
import restart_coordinator # noqa: E402 # #658 MCP restart coordinator/impact
|
import restart_coordinator # noqa: E402 # #658 MCP restart coordinator/impact
|
||||||
import incident_bridge # noqa: E402
|
import incident_bridge # noqa: E402
|
||||||
@@ -2311,6 +2310,7 @@ import canonical_comment_validator as ccv # noqa: E402
|
|||||||
# GITEA_ISSUE_LOCK_DIR, bound to the current MCP session via a per-PID pointer.
|
# GITEA_ISSUE_LOCK_DIR, bound to the current MCP session via a per-PID pointer.
|
||||||
# Legacy global path retained only for test/doc references — do not seed manually.
|
# Legacy global path retained only for test/doc references — do not seed manually.
|
||||||
ISSUE_LOCK_FILE = "/tmp/gitea_issue_lock.json"
|
ISSUE_LOCK_FILE = "/tmp/gitea_issue_lock.json"
|
||||||
|
WORK_LEASE_TTL_HOURS = 4
|
||||||
AUTHOR_ISSUE_WORK_LEASE = "author_issue_work"
|
AUTHOR_ISSUE_WORK_LEASE = "author_issue_work"
|
||||||
VALID_WORK_LEASE_OPERATIONS = frozenset({
|
VALID_WORK_LEASE_OPERATIONS = frozenset({
|
||||||
AUTHOR_ISSUE_WORK_LEASE,
|
AUTHOR_ISSUE_WORK_LEASE,
|
||||||
@@ -2625,12 +2625,7 @@ def _build_author_issue_work_lease(
|
|||||||
host: str | None,
|
host: str | None,
|
||||||
) -> dict:
|
) -> dict:
|
||||||
created = _work_lease_now()
|
created = _work_lease_now()
|
||||||
# #790 Slice A: the window comes from the central policy, not a literal here.
|
expires = created + timedelta(hours=WORK_LEASE_TTL_HOURS)
|
||||||
# It is also now a *sliding* window — the lease lives ``initial_ttl_minutes``
|
|
||||||
# past its last valid heartbeat rather than a fixed four hours past its
|
|
||||||
# creation, so an abandoned task stops holding the claim within one TTL.
|
|
||||||
policy = lease_policy.policy_for(lease_policy.TASK_CLASS_AUTHOR_ISSUE_WORK)
|
|
||||||
expires = created + timedelta(minutes=policy.initial_ttl_minutes)
|
|
||||||
return {
|
return {
|
||||||
"operation_type": AUTHOR_ISSUE_WORK_LEASE,
|
"operation_type": AUTHOR_ISSUE_WORK_LEASE,
|
||||||
"issue_number": issue_number,
|
"issue_number": issue_number,
|
||||||
@@ -2641,15 +2636,6 @@ def _build_author_issue_work_lease(
|
|||||||
"created_at": _work_lease_timestamp(created),
|
"created_at": _work_lease_timestamp(created),
|
||||||
"expires_at": _work_lease_timestamp(expires),
|
"expires_at": _work_lease_timestamp(expires),
|
||||||
"last_heartbeat_at": _work_lease_timestamp(created),
|
"last_heartbeat_at": _work_lease_timestamp(created),
|
||||||
# #790 AC-N1: the ownership key for this task. Distinct from the recorded
|
|
||||||
# PID, which is the shared daemon and identifies no individual task.
|
|
||||||
"task_session_id": issue_lock_store.mint_task_session_id(
|
|
||||||
AUTHOR_ISSUE_WORK_LEASE
|
|
||||||
),
|
|
||||||
# #790 AC-N8: the explicit lifecycle marker. Its absence — never a
|
|
||||||
# timestamp comparison — is what makes a lock legacy.
|
|
||||||
"lifecycle_version": lease_policy.LIFECYCLE_HEARTBEAT_V1,
|
|
||||||
"heartbeat_count": 1,
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
@@ -4420,135 +4406,6 @@ def gitea_lock_issue(
|
|||||||
|
|
||||||
|
|
||||||
@mcp.tool()
|
@mcp.tool()
|
||||||
def gitea_heartbeat_issue_lock(
|
|
||||||
issue_number: int,
|
|
||||||
branch_name: str,
|
|
||||||
task_session_id: str | None = None,
|
|
||||||
remote: str = "dadeschools",
|
|
||||||
host: str | None = None,
|
|
||||||
org: str | None = None,
|
|
||||||
repo: str | None = None,
|
|
||||||
worktree_path: str | None = None,
|
|
||||||
expected_generation: int | None = None,
|
|
||||||
) -> dict:
|
|
||||||
"""Prove an owned author issue lease is still active (#790 Slice A).
|
|
||||||
|
|
||||||
The task-liveness signal the lifecycle was missing. Before this, an author
|
|
||||||
lease carried a fixed four-hour expiry that nothing could shorten, and the
|
|
||||||
only liveness evidence was the recorded PID — the long-lived MCP daemon,
|
|
||||||
which stays alive across every task it serves and so proved nothing about
|
|
||||||
whether the authoring task still held the work.
|
|
||||||
|
|
||||||
Each successful call slides the lease ``initial_ttl_minutes`` past *now*
|
|
||||||
from the central policy, so an actively heartbeating session is never
|
|
||||||
evicted while an abandoned one releases its claim within one TTL.
|
|
||||||
|
|
||||||
What this tool cannot do, by construction:
|
|
||||||
|
|
||||||
* **Acquire.** It refuses when no durable lock exists.
|
|
||||||
* **Take over.** Exact issue, branch, realpath-normalized worktree,
|
|
||||||
claimant username, claimant profile, and recorded task-session identifier
|
|
||||||
must all match; a superseded session holding an older identifier is
|
|
||||||
refused.
|
|
||||||
* **Revive.** A lease already past its grace is not heartbeatable — that
|
|
||||||
would let a session restore ownership it had stopped proving. It must use
|
|
||||||
the sanctioned reclaim path, which mints a new generation.
|
|
||||||
|
|
||||||
A lock predating the heartbeat lifecycle is rebound rather than heartbeated:
|
|
||||||
its exact owner is re-verified and a genuine task-session identifier and
|
|
||||||
first heartbeat are minted (#790 AC-N8). The rebind is decided server-side
|
|
||||||
from the durable lifecycle marker; there is no caller-facing switch.
|
|
||||||
|
|
||||||
Args:
|
|
||||||
issue_number: The locked issue number.
|
|
||||||
branch_name: The branch recorded on the lock.
|
|
||||||
task_session_id: The identifier this session received when it acquired
|
|
||||||
or rebound the lock. It is a fencing token, not an ownership
|
|
||||||
assertion: it is compared against durable state and can only ever
|
|
||||||
cause a refusal, never grant anything. Omitted only when rebinding a
|
|
||||||
legacy lock, which has no identifier yet and mints one.
|
|
||||||
remote: Known instance — 'dadeschools' or 'prgs'.
|
|
||||||
host: Override the Gitea host.
|
|
||||||
org: Override the owner/organization.
|
|
||||||
repo: Override the repository name.
|
|
||||||
worktree_path: Author worktree recorded on the lock.
|
|
||||||
expected_generation: Optional fencing value. The per-issue flock already
|
|
||||||
serializes the read and the write, so this is for a caller that
|
|
||||||
wants to pin the generation it last observed across calls; a moved
|
|
||||||
generation fails closed.
|
|
||||||
|
|
||||||
Returns:
|
|
||||||
dict with 'success', 'performed', the sliding 'expires_at',
|
|
||||||
'last_heartbeat_at', 'lock_generation', 'task_session_id', the applied
|
|
||||||
'policy', and post-write 'freshness'; on refusal 'success'/'performed'
|
|
||||||
False with 'reasons' naming exactly what did not match.
|
|
||||||
"""
|
|
||||||
blocked = _profile_permission_block(
|
|
||||||
task_capability_map.required_permission("heartbeat_issue_lock"),
|
|
||||||
issue_number=issue_number,
|
|
||||||
remote=remote,
|
|
||||||
host=host,
|
|
||||||
org=org,
|
|
||||||
repo=repo,
|
|
||||||
org_explicit=org is not None,
|
|
||||||
repo_explicit=repo is not None,
|
|
||||||
)
|
|
||||||
if blocked:
|
|
||||||
return blocked
|
|
||||||
|
|
||||||
resolved_worktree = issue_lock_worktree.resolve_author_worktree_path(
|
|
||||||
worktree_path, _canonical_local_git_root()
|
|
||||||
)
|
|
||||||
h, o, r = _resolve(remote, host, org, repo)
|
|
||||||
claimant = _work_lease_claimant(h)
|
|
||||||
identity = claimant.get("username")
|
|
||||||
profile = claimant.get("profile")
|
|
||||||
|
|
||||||
existing = _load_existing_issue_lock(
|
|
||||||
remote=remote, org=o, repo=r, issue_number=issue_number
|
|
||||||
)
|
|
||||||
if not existing:
|
|
||||||
return {
|
|
||||||
"success": False,
|
|
||||||
"performed": False,
|
|
||||||
"issue_number": issue_number,
|
|
||||||
"reasons": [
|
|
||||||
f"no durable lock for issue #{issue_number}; heartbeat cannot "
|
|
||||||
"acquire a claim (fail closed)"
|
|
||||||
],
|
|
||||||
}
|
|
||||||
|
|
||||||
if issue_lock_store.is_legacy_lease(existing):
|
|
||||||
outcome = issue_lock_store.rebind_legacy_lock(
|
|
||||||
remote=remote,
|
|
||||||
org=o,
|
|
||||||
repo=r,
|
|
||||||
issue_number=issue_number,
|
|
||||||
branch_name=branch_name,
|
|
||||||
worktree_path=resolved_worktree,
|
|
||||||
identity=identity,
|
|
||||||
profile=profile,
|
|
||||||
expected_generation=expected_generation,
|
|
||||||
)
|
|
||||||
outcome["operation"] = "legacy_rebind"
|
|
||||||
return outcome
|
|
||||||
|
|
||||||
outcome = issue_lock_store.heartbeat_session_lock(
|
|
||||||
remote=remote,
|
|
||||||
org=o,
|
|
||||||
repo=r,
|
|
||||||
issue_number=issue_number,
|
|
||||||
branch_name=branch_name,
|
|
||||||
worktree_path=resolved_worktree,
|
|
||||||
identity=identity,
|
|
||||||
profile=profile,
|
|
||||||
task_session_id=str(task_session_id or ""),
|
|
||||||
expected_generation=expected_generation,
|
|
||||||
)
|
|
||||||
outcome["operation"] = "heartbeat"
|
|
||||||
return outcome
|
|
||||||
|
|
||||||
|
|
||||||
@mcp.tool()
|
@mcp.tool()
|
||||||
def gitea_recover_dirty_orphaned_issue_worktree(
|
def gitea_recover_dirty_orphaned_issue_worktree(
|
||||||
issue_number: int,
|
issue_number: int,
|
||||||
@@ -4822,7 +4679,6 @@ def gitea_recover_dirty_orphaned_issue_worktree(
|
|||||||
)
|
)
|
||||||
return result
|
return result
|
||||||
|
|
||||||
|
|
||||||
@mcp.tool()
|
@mcp.tool()
|
||||||
def gitea_rebind_dirty_same_claimant_author_session(
|
def gitea_rebind_dirty_same_claimant_author_session(
|
||||||
issue_number: int,
|
issue_number: int,
|
||||||
@@ -5079,6 +4935,8 @@ def gitea_rebind_dirty_same_claimant_author_session(
|
|||||||
}
|
}
|
||||||
return result
|
return result
|
||||||
|
|
||||||
|
return result
|
||||||
|
|
||||||
|
|
||||||
@mcp.tool()
|
@mcp.tool()
|
||||||
def gitea_assess_work_issue_duplicate(
|
def gitea_assess_work_issue_duplicate(
|
||||||
|
|||||||
+54
-579
@@ -15,27 +15,15 @@ import json
|
|||||||
import os
|
import os
|
||||||
import re
|
import re
|
||||||
import tempfile
|
import tempfile
|
||||||
import uuid
|
|
||||||
from contextlib import contextmanager
|
from contextlib import contextmanager
|
||||||
from datetime import datetime, timedelta, timezone
|
from datetime import datetime, timedelta, timezone
|
||||||
from typing import Any
|
from typing import Any
|
||||||
|
|
||||||
import lease_policy
|
|
||||||
|
|
||||||
LOCK_DIR_ENV = "GITEA_ISSUE_LOCK_DIR"
|
LOCK_DIR_ENV = "GITEA_ISSUE_LOCK_DIR"
|
||||||
DEFAULT_LOCK_DIR = os.path.expanduser("~/.cache/gitea-tools/issue-locks")
|
DEFAULT_LOCK_DIR = os.path.expanduser("~/.cache/gitea-tools/issue-locks")
|
||||||
|
WORK_LEASE_TTL_HOURS = 4
|
||||||
AUTHOR_ISSUE_WORK_LEASE = "author_issue_work"
|
AUTHOR_ISSUE_WORK_LEASE = "author_issue_work"
|
||||||
|
|
||||||
# Freshness classifications. ``STATUS_STALE`` remains the dead-PID band that
|
|
||||||
# #753 recovery keys on; the two bands below are new in #790 Slice A and apply
|
|
||||||
# only to leases minted under the heartbeat lifecycle.
|
|
||||||
STATUS_LIVE = "live"
|
|
||||||
STATUS_EXPIRED = "expired"
|
|
||||||
STATUS_ABSENT = "absent"
|
|
||||||
STATUS_STALE = "stale"
|
|
||||||
STATUS_STALE_MISSED_HEARTBEAT = "stale_missed_heartbeat"
|
|
||||||
STATUS_STALE_ABSOLUTE_CAP = "stale_absolute_cap"
|
|
||||||
|
|
||||||
_SAFE_SEGMENT_RE = re.compile(r"[^A-Za-z0-9._+-]+")
|
_SAFE_SEGMENT_RE = re.compile(r"[^A-Za-z0-9._+-]+")
|
||||||
|
|
||||||
|
|
||||||
@@ -269,331 +257,6 @@ def bind_session_lock(
|
|||||||
return path
|
return path
|
||||||
|
|
||||||
|
|
||||||
def _ownership_refusals(
|
|
||||||
lock: dict[str, Any],
|
|
||||||
*,
|
|
||||||
issue_number: int,
|
|
||||||
branch_name: str,
|
|
||||||
worktree_path: str,
|
|
||||||
identity: str | None,
|
|
||||||
profile: str | None,
|
|
||||||
) -> list[str]:
|
|
||||||
"""Exact-ownership mismatches between a durable lock and a live caller.
|
|
||||||
|
|
||||||
Shared by the heartbeat writer and the legacy rebind path so the two cannot
|
|
||||||
disagree about what "the same owner" means. Every field is compared against
|
|
||||||
durable state; nothing is taken on the caller's word beyond the identity the
|
|
||||||
server itself resolved.
|
|
||||||
"""
|
|
||||||
reasons: list[str] = []
|
|
||||||
if lock.get("issue_number") != issue_number:
|
|
||||||
reasons.append(
|
|
||||||
f"lock targets issue #{lock.get('issue_number')}, not #{issue_number}"
|
|
||||||
)
|
|
||||||
if str(lock.get("branch_name") or "") != str(branch_name or ""):
|
|
||||||
reasons.append(
|
|
||||||
f"lock branch '{lock.get('branch_name')}' does not match '{branch_name}'"
|
|
||||||
)
|
|
||||||
if not _same_realpath(str(lock.get("worktree_path") or ""), worktree_path):
|
|
||||||
reasons.append(
|
|
||||||
f"lock worktree '{lock.get('worktree_path')}' does not match "
|
|
||||||
f"'{worktree_path}'"
|
|
||||||
)
|
|
||||||
lease = lock.get("work_lease") if isinstance(lock, dict) else None
|
|
||||||
claimant = lease.get("claimant") if isinstance(lease, dict) else None
|
|
||||||
claimant = claimant if isinstance(claimant, dict) else {}
|
|
||||||
recorded_identity = str(claimant.get("username") or "").strip()
|
|
||||||
recorded_profile = str(claimant.get("profile") or "").strip()
|
|
||||||
if not recorded_identity or not recorded_profile:
|
|
||||||
reasons.append("lock does not record both a claimant username and profile")
|
|
||||||
if recorded_identity and recorded_identity != str(identity or "").strip():
|
|
||||||
reasons.append(
|
|
||||||
f"lock claimant '{recorded_identity}' does not match active identity "
|
|
||||||
f"'{str(identity or '').strip() or 'unknown'}'"
|
|
||||||
)
|
|
||||||
if recorded_profile and recorded_profile != str(profile or "").strip():
|
|
||||||
reasons.append(
|
|
||||||
f"lock profile '{recorded_profile}' does not match active profile "
|
|
||||||
f"'{str(profile or '').strip() or 'unknown'}'"
|
|
||||||
)
|
|
||||||
return reasons
|
|
||||||
|
|
||||||
|
|
||||||
def _refusal(reasons: list[str], **extra: Any) -> dict[str, Any]:
|
|
||||||
return {"success": False, "performed": False, "reasons": reasons, **extra}
|
|
||||||
|
|
||||||
|
|
||||||
def heartbeat_session_lock(
|
|
||||||
*,
|
|
||||||
remote: str,
|
|
||||||
org: str,
|
|
||||||
repo: str,
|
|
||||||
issue_number: int,
|
|
||||||
branch_name: str,
|
|
||||||
worktree_path: str,
|
|
||||||
identity: str | None,
|
|
||||||
profile: str | None,
|
|
||||||
task_session_id: str,
|
|
||||||
expected_generation: int | None = None,
|
|
||||||
lock_dir: str | None = None,
|
|
||||||
now: datetime | None = None,
|
|
||||||
) -> dict[str, Any]:
|
|
||||||
"""Slide a heartbeat-lifecycle lease forward (#790 Slice A, A4).
|
|
||||||
|
|
||||||
The write happens inside the same per-issue ``flock`` that serializes
|
|
||||||
acquisition, and under the #772 generation compare-and-swap, so a heartbeat
|
|
||||||
can never race a concurrent reclaim: whichever lands first moves the
|
|
||||||
generation and the other fails closed.
|
|
||||||
|
|
||||||
Refuses — never revives — in every ambiguous case. A lease that has already
|
|
||||||
lapsed past its grace is *not* heartbeatable: allowing that would let a
|
|
||||||
session that stopped proving liveness restore ownership retroactively, which
|
|
||||||
is precisely the revival AC-N5 forbids. Such a session must go through the
|
|
||||||
sanctioned reclaim path, which mints a fresh generation.
|
|
||||||
"""
|
|
||||||
current = _lease_now(now)
|
|
||||||
root = _ensure_lock_dir(lock_dir)
|
|
||||||
path = lock_file_path(
|
|
||||||
remote=remote, org=org, repo=repo, issue_number=issue_number, lock_dir=root
|
|
||||||
)
|
|
||||||
declared_session = str(task_session_id or "").strip()
|
|
||||||
if not declared_session:
|
|
||||||
return _refusal(["no task_session_id supplied (fail closed)"])
|
|
||||||
|
|
||||||
sentinel = flock_path(path)
|
|
||||||
try:
|
|
||||||
with _exclusive_file_lock(sentinel):
|
|
||||||
lock = read_lock_file(path)
|
|
||||||
if not lock:
|
|
||||||
return _refusal([f"no durable lock for issue #{issue_number}"])
|
|
||||||
|
|
||||||
if is_legacy_lease(lock):
|
|
||||||
return _refusal(
|
|
||||||
[
|
|
||||||
"lock predates the heartbeat lifecycle; it must be rebound "
|
|
||||||
"by its exact owner before it can be heartbeated"
|
|
||||||
],
|
|
||||||
lifecycle=lease_lifecycle_version(lock),
|
|
||||||
legacy_lease=True,
|
|
||||||
)
|
|
||||||
|
|
||||||
reasons = _ownership_refusals(
|
|
||||||
lock,
|
|
||||||
issue_number=issue_number,
|
|
||||||
branch_name=branch_name,
|
|
||||||
worktree_path=worktree_path,
|
|
||||||
identity=identity,
|
|
||||||
profile=profile,
|
|
||||||
)
|
|
||||||
recorded_session = lease_task_session_id(lock)
|
|
||||||
if not recorded_session:
|
|
||||||
reasons.append(
|
|
||||||
"lock declares the heartbeat lifecycle but records no "
|
|
||||||
"task_session_id (fail closed)"
|
|
||||||
)
|
|
||||||
elif recorded_session != declared_session:
|
|
||||||
# A superseded session holding an old identifier cannot heartbeat
|
|
||||||
# over the session that replaced it.
|
|
||||||
reasons.append(
|
|
||||||
"task_session_id does not match the session recorded on the lock"
|
|
||||||
)
|
|
||||||
if reasons:
|
|
||||||
return _refusal(reasons)
|
|
||||||
|
|
||||||
current_generation = lock_generation(lock)
|
|
||||||
if (
|
|
||||||
expected_generation is not None
|
|
||||||
and current_generation != expected_generation
|
|
||||||
):
|
|
||||||
return _refusal(
|
|
||||||
[
|
|
||||||
f"lock generation changed: expected {expected_generation}, "
|
|
||||||
f"found {current_generation}; another session reclaimed or "
|
|
||||||
"replaced this claim (fail closed)"
|
|
||||||
],
|
|
||||||
lock_generation=current_generation,
|
|
||||||
)
|
|
||||||
|
|
||||||
freshness = assess_lock_freshness(lock, now=current)
|
|
||||||
if not freshness.get("live"):
|
|
||||||
return _refusal(
|
|
||||||
[
|
|
||||||
f"lease is not live ({freshness.get('status')}): "
|
|
||||||
f"{freshness.get('reason')}; a lapsed lease must be "
|
|
||||||
"reclaimed, not heartbeated"
|
|
||||||
],
|
|
||||||
freshness=freshness,
|
|
||||||
)
|
|
||||||
|
|
||||||
policy = lease_policy.policy_for(lease_task_class(lock))
|
|
||||||
expires = current + timedelta(minutes=policy.initial_ttl_minutes)
|
|
||||||
record = dict(lock)
|
|
||||||
lease = dict(record.get("work_lease") or {})
|
|
||||||
prior_heartbeat = lease.get("last_heartbeat_at")
|
|
||||||
lease["last_heartbeat_at"] = _format_lease_timestamp(current)
|
|
||||||
lease["expires_at"] = _format_lease_timestamp(expires)
|
|
||||||
try:
|
|
||||||
lease["heartbeat_count"] = int(lease.get("heartbeat_count") or 0) + 1
|
|
||||||
except (TypeError, ValueError):
|
|
||||||
lease["heartbeat_count"] = 1
|
|
||||||
record["work_lease"] = lease
|
|
||||||
record["lock_generation"] = current_generation + 1
|
|
||||||
save_lock_file(path, record)
|
|
||||||
except LockContentionError as exc:
|
|
||||||
return _refusal([f"issue #{issue_number} lock contention: {exc} (fail closed)"])
|
|
||||||
|
|
||||||
return {
|
|
||||||
"success": True,
|
|
||||||
"performed": True,
|
|
||||||
"issue_number": issue_number,
|
|
||||||
"branch_name": branch_name,
|
|
||||||
"worktree_path": worktree_path,
|
|
||||||
"task_session_id": declared_session,
|
|
||||||
"lock_generation": record["lock_generation"],
|
|
||||||
"prior_generation": current_generation,
|
|
||||||
"prior_heartbeat_at": prior_heartbeat,
|
|
||||||
"last_heartbeat_at": lease["last_heartbeat_at"],
|
|
||||||
"expires_at": lease["expires_at"],
|
|
||||||
"heartbeat_count": lease["heartbeat_count"],
|
|
||||||
"lock_file_path": path,
|
|
||||||
"policy": lease_policy.describe(lease_task_class(record)),
|
|
||||||
"freshness": assess_lock_freshness(record, now=current),
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
def rebind_legacy_lock(
|
|
||||||
*,
|
|
||||||
remote: str,
|
|
||||||
org: str,
|
|
||||||
repo: str,
|
|
||||||
issue_number: int,
|
|
||||||
branch_name: str,
|
|
||||||
worktree_path: str,
|
|
||||||
identity: str | None,
|
|
||||||
profile: str | None,
|
|
||||||
expected_generation: int | None = None,
|
|
||||||
lock_dir: str | None = None,
|
|
||||||
now: datetime | None = None,
|
|
||||||
) -> dict[str, Any]:
|
|
||||||
"""Move a legacy lock into the heartbeat lifecycle (#790 AC-N8).
|
|
||||||
|
|
||||||
One of the two sanctioned exits from the preserved-expiry legacy state; the
|
|
||||||
other is terminal retirement, which is Slice B. Only the exact recorded
|
|
||||||
owner may rebind, and only while the legacy lock is still live under its
|
|
||||||
original absolute expiry — an already-expired legacy lease belongs to the
|
|
||||||
#760 renewal path or #601 reclaim, and this must not become a second, weaker
|
|
||||||
way to revive one.
|
|
||||||
|
|
||||||
The rebind mints a genuine task-session identifier and a genuine first
|
|
||||||
heartbeat. It does not fabricate history: the original creation and expiry
|
|
||||||
are preserved under ``legacy_origin`` for audit, and the new lifecycle's
|
|
||||||
absolute cap runs from the rebind, not from the legacy claim.
|
|
||||||
"""
|
|
||||||
current = _lease_now(now)
|
|
||||||
root = _ensure_lock_dir(lock_dir)
|
|
||||||
path = lock_file_path(
|
|
||||||
remote=remote, org=org, repo=repo, issue_number=issue_number, lock_dir=root
|
|
||||||
)
|
|
||||||
sentinel = flock_path(path)
|
|
||||||
try:
|
|
||||||
with _exclusive_file_lock(sentinel):
|
|
||||||
lock = read_lock_file(path)
|
|
||||||
if not lock:
|
|
||||||
return _refusal([f"no durable lock for issue #{issue_number}"])
|
|
||||||
if not is_legacy_lease(lock):
|
|
||||||
return _refusal(
|
|
||||||
[
|
|
||||||
"lock is already on the heartbeat lifecycle; use the "
|
|
||||||
"heartbeat path"
|
|
||||||
],
|
|
||||||
lifecycle=lease_lifecycle_version(lock),
|
|
||||||
legacy_lease=False,
|
|
||||||
)
|
|
||||||
|
|
||||||
reasons = _ownership_refusals(
|
|
||||||
lock,
|
|
||||||
issue_number=issue_number,
|
|
||||||
branch_name=branch_name,
|
|
||||||
worktree_path=worktree_path,
|
|
||||||
identity=identity,
|
|
||||||
profile=profile,
|
|
||||||
)
|
|
||||||
if reasons:
|
|
||||||
return _refusal(reasons)
|
|
||||||
|
|
||||||
current_generation = lock_generation(lock)
|
|
||||||
if (
|
|
||||||
expected_generation is not None
|
|
||||||
and current_generation != expected_generation
|
|
||||||
):
|
|
||||||
return _refusal(
|
|
||||||
[
|
|
||||||
f"lock generation changed: expected {expected_generation}, "
|
|
||||||
f"found {current_generation} (fail closed)"
|
|
||||||
],
|
|
||||||
lock_generation=current_generation,
|
|
||||||
)
|
|
||||||
|
|
||||||
freshness = assess_lock_freshness(lock, now=current)
|
|
||||||
if not freshness.get("live"):
|
|
||||||
return _refusal(
|
|
||||||
[
|
|
||||||
f"legacy lease is not live ({freshness.get('status')}): "
|
|
||||||
f"{freshness.get('reason')}; rebinding is not a recovery "
|
|
||||||
"path for a lapsed lease"
|
|
||||||
],
|
|
||||||
freshness=freshness,
|
|
||||||
)
|
|
||||||
|
|
||||||
policy = lease_policy.policy_for(lease_task_class(lock))
|
|
||||||
expires = current + timedelta(minutes=policy.initial_ttl_minutes)
|
|
||||||
session_id = mint_task_session_id(lease_task_class(lock))
|
|
||||||
record = dict(lock)
|
|
||||||
lease = dict(record.get("work_lease") or {})
|
|
||||||
legacy_origin = {
|
|
||||||
"created_at": lease.get("created_at"),
|
|
||||||
"expires_at": lease.get("expires_at"),
|
|
||||||
"last_heartbeat_at": lease.get("last_heartbeat_at"),
|
|
||||||
"lifecycle": lease_policy.LIFECYCLE_LEGACY,
|
|
||||||
}
|
|
||||||
lease["lifecycle_version"] = lease_policy.LIFECYCLE_HEARTBEAT_V1
|
|
||||||
lease["task_session_id"] = session_id
|
|
||||||
lease["created_at"] = _format_lease_timestamp(current)
|
|
||||||
lease["last_heartbeat_at"] = _format_lease_timestamp(current)
|
|
||||||
lease["expires_at"] = _format_lease_timestamp(expires)
|
|
||||||
lease["heartbeat_count"] = 1
|
|
||||||
record["work_lease"] = lease
|
|
||||||
record["legacy_rebind"] = {
|
|
||||||
"rebound_at": _format_lease_timestamp(current),
|
|
||||||
"task_session_id": session_id,
|
|
||||||
"prior_generation": current_generation,
|
|
||||||
"legacy_origin": legacy_origin,
|
|
||||||
"reason": (
|
|
||||||
"legacy lock rebound into the heartbeat lifecycle by its exact "
|
|
||||||
"recorded owner"
|
|
||||||
),
|
|
||||||
}
|
|
||||||
record["lock_generation"] = current_generation + 1
|
|
||||||
save_lock_file(path, record)
|
|
||||||
except LockContentionError as exc:
|
|
||||||
return _refusal([f"issue #{issue_number} lock contention: {exc} (fail closed)"])
|
|
||||||
|
|
||||||
return {
|
|
||||||
"success": True,
|
|
||||||
"performed": True,
|
|
||||||
"issue_number": issue_number,
|
|
||||||
"task_session_id": session_id,
|
|
||||||
"lock_generation": record["lock_generation"],
|
|
||||||
"prior_generation": current_generation,
|
|
||||||
"lifecycle": lease_policy.LIFECYCLE_HEARTBEAT_V1,
|
|
||||||
"legacy_rebind": record["legacy_rebind"],
|
|
||||||
"expires_at": lease["expires_at"],
|
|
||||||
"last_heartbeat_at": lease["last_heartbeat_at"],
|
|
||||||
"lock_file_path": path,
|
|
||||||
"freshness": assess_lock_freshness(record, now=current),
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
def read_session_issue_lock(lock_dir: str | None = None) -> dict[str, Any] | None:
|
def read_session_issue_lock(lock_dir: str | None = None) -> dict[str, Any] | None:
|
||||||
root = (lock_dir or default_lock_dir()).strip()
|
root = (lock_dir or default_lock_dir()).strip()
|
||||||
pointer = read_lock_file(session_pointer_path(root))
|
pointer = read_lock_file(session_pointer_path(root))
|
||||||
@@ -677,16 +340,6 @@ def _parse_lease_timestamp(value: str | None) -> datetime | None:
|
|||||||
return None
|
return None
|
||||||
|
|
||||||
|
|
||||||
def _format_lease_timestamp(value: datetime) -> str:
|
|
||||||
"""Serialize a lease timestamp in the durable ``...Z`` form already on disk."""
|
|
||||||
return (
|
|
||||||
value.astimezone(timezone.utc)
|
|
||||||
.replace(microsecond=0)
|
|
||||||
.isoformat()
|
|
||||||
.replace("+00:00", "Z")
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
def lease_expires_at(lock: dict[str, Any] | None) -> datetime | None:
|
def lease_expires_at(lock: dict[str, Any] | None) -> datetime | None:
|
||||||
if not lock:
|
if not lock:
|
||||||
return None
|
return None
|
||||||
@@ -707,113 +360,26 @@ def is_lease_live(lock: dict[str, Any] | None, *, now: datetime | None = None) -
|
|||||||
return assess_lock_freshness(lock, now=now)["live"]
|
return assess_lock_freshness(lock, now=now)["live"]
|
||||||
|
|
||||||
|
|
||||||
def lease_task_class(lock_data: dict[str, Any] | None) -> str:
|
|
||||||
"""Policy task class for a durable lock; author work when unrecorded."""
|
|
||||||
lease = lock_data.get("work_lease") if isinstance(lock_data, dict) else None
|
|
||||||
if isinstance(lease, dict):
|
|
||||||
recorded = str(lease.get("operation_type") or "").strip()
|
|
||||||
if recorded:
|
|
||||||
return recorded
|
|
||||||
return AUTHOR_ISSUE_WORK_LEASE
|
|
||||||
|
|
||||||
|
|
||||||
def lease_lifecycle_version(lock_data: dict[str, Any] | None) -> str:
|
|
||||||
"""Read the durable lifecycle marker (#790 AC-N8).
|
|
||||||
|
|
||||||
The marker is the *only* discriminator between a heartbeat-lifecycle lease
|
|
||||||
and a legacy one. Timestamps are deliberately not consulted: a lock minted
|
|
||||||
before this lifecycle existed has ``last_heartbeat_at == created_at``
|
|
||||||
forever, and reading that equality as "recently heartbeated" would treat
|
|
||||||
every never-heartbeated legacy lock as fresh — the precise inversion AC-N8
|
|
||||||
forbids. A newly minted heartbeat lease also has the two equal, so the
|
|
||||||
equality carries no information in either direction.
|
|
||||||
"""
|
|
||||||
lease = lock_data.get("work_lease") if isinstance(lock_data, dict) else None
|
|
||||||
if isinstance(lease, dict):
|
|
||||||
recorded = str(lease.get("lifecycle_version") or "").strip()
|
|
||||||
if recorded:
|
|
||||||
return recorded
|
|
||||||
return lease_policy.LIFECYCLE_LEGACY
|
|
||||||
|
|
||||||
|
|
||||||
def is_legacy_lease(lock_data: dict[str, Any] | None) -> bool:
|
|
||||||
"""True when a lock predates the shared heartbeat lifecycle."""
|
|
||||||
return lease_lifecycle_version(lock_data) != lease_policy.LIFECYCLE_HEARTBEAT_V1
|
|
||||||
|
|
||||||
|
|
||||||
def lease_task_session_id(lock_data: dict[str, Any] | None) -> str:
|
|
||||||
"""Recorded per-task session identifier, or empty for a legacy lock."""
|
|
||||||
lease = lock_data.get("work_lease") if isinstance(lock_data, dict) else None
|
|
||||||
if isinstance(lease, dict):
|
|
||||||
return str(lease.get("task_session_id") or "").strip()
|
|
||||||
return ""
|
|
||||||
|
|
||||||
|
|
||||||
def mint_task_session_id(task_class: str = AUTHOR_ISSUE_WORK_LEASE) -> str:
|
|
||||||
"""Mint an ownership key for one task (#790 AC-N1).
|
|
||||||
|
|
||||||
Deliberately contains no process identifier. The recorded PID belongs to the
|
|
||||||
long-lived MCP daemon, which outlives any individual task and is reused by
|
|
||||||
every task it serves, so PID digits cannot identify *which* task holds a
|
|
||||||
claim. The PID is still recorded alongside this value as evidence.
|
|
||||||
"""
|
|
||||||
prefix = _sanitize_segment(str(task_class or AUTHOR_ISSUE_WORK_LEASE))
|
|
||||||
return f"{prefix}-{uuid.uuid4().hex[:16]}"
|
|
||||||
|
|
||||||
|
|
||||||
def _lease_heartbeat_at(lock_data: dict[str, Any] | None) -> datetime | None:
|
|
||||||
lease = lock_data.get("work_lease") if isinstance(lock_data, dict) else None
|
|
||||||
heartbeat_at = None
|
|
||||||
if isinstance(lock_data, dict):
|
|
||||||
heartbeat_at = _parse_lease_timestamp(lock_data.get("last_heartbeat_at"))
|
|
||||||
if heartbeat_at is None and isinstance(lease, dict):
|
|
||||||
heartbeat_at = _parse_lease_timestamp(lease.get("last_heartbeat_at"))
|
|
||||||
return heartbeat_at
|
|
||||||
|
|
||||||
|
|
||||||
def assess_lock_freshness(
|
def assess_lock_freshness(
|
||||||
lock_data: dict[str, Any] | None,
|
lock_data: dict[str, Any] | None,
|
||||||
*,
|
*,
|
||||||
now: datetime | None = None,
|
now: datetime | None = None,
|
||||||
) -> dict[str, Any]:
|
) -> dict[str, Any]:
|
||||||
"""Classify a lock as live, expired, stale, or absent.
|
"""Classify a lock as live, expired, stale, or absent."""
|
||||||
|
|
||||||
#790 Slice A makes the heartbeat load-bearing. Before this change
|
|
||||||
``last_heartbeat_at`` was parsed and then never consulted: liveness was
|
|
||||||
decided entirely by the absolute ``expires_at`` and by PID liveness, and
|
|
||||||
since the recorded PID is the long-lived MCP daemon, an abandoned author
|
|
||||||
task stayed "live" for the full four-hour TTL.
|
|
||||||
|
|
||||||
Two rules govern the rewrite:
|
|
||||||
|
|
||||||
* **An alive PID never establishes freshness** (AC-N2). It proves the daemon
|
|
||||||
is up, nothing about the task. It is recorded as evidence and no branch
|
|
||||||
returns ``live`` because of it.
|
|
||||||
* **A dead PID still corroborates staleness.** The dead-PID band is
|
|
||||||
unchanged and still precedes every heartbeat evaluation, so #753
|
|
||||||
dead-session recovery keys on exactly the classification it always did.
|
|
||||||
|
|
||||||
Legacy leases (AC-N8) keep their recorded absolute expiry and are never
|
|
||||||
evaluated against the short heartbeat grace, so deploying this change cannot
|
|
||||||
make an existing claim instantly reclaimable.
|
|
||||||
"""
|
|
||||||
current = _lease_now(now)
|
current = _lease_now(now)
|
||||||
if not lock_data:
|
if not lock_data:
|
||||||
return {
|
return {
|
||||||
"status": STATUS_ABSENT,
|
"status": "absent",
|
||||||
"live": False,
|
"live": False,
|
||||||
"stale": False,
|
"stale": False,
|
||||||
"reason": "no lock record",
|
"reason": "no lock record",
|
||||||
}
|
}
|
||||||
|
|
||||||
lease = lock_data.get("work_lease")
|
|
||||||
expires_at = lease_expires_at(lock_data)
|
expires_at = lease_expires_at(lock_data)
|
||||||
heartbeat_at = _lease_heartbeat_at(lock_data)
|
lease = lock_data.get("work_lease")
|
||||||
created_at = (
|
heartbeat_at = _parse_lease_timestamp(lock_data.get("last_heartbeat_at"))
|
||||||
_parse_lease_timestamp(lease.get("created_at"))
|
if heartbeat_at is None and isinstance(lease, dict):
|
||||||
if isinstance(lease, dict)
|
heartbeat_at = _parse_lease_timestamp(lease.get("last_heartbeat_at"))
|
||||||
else None
|
|
||||||
)
|
|
||||||
|
|
||||||
pid = lock_data.get("session_pid")
|
pid = lock_data.get("session_pid")
|
||||||
if pid is None:
|
if pid is None:
|
||||||
@@ -831,103 +397,56 @@ def assess_lock_freshness(
|
|||||||
pid_int = None
|
pid_int = None
|
||||||
pid_alive = is_process_alive(pid_int) if pid_int is not None else False
|
pid_alive = is_process_alive(pid_int) if pid_int is not None else False
|
||||||
|
|
||||||
lifecycle = lease_lifecycle_version(lock_data)
|
if expires_at and expires_at <= current:
|
||||||
legacy = lifecycle != lease_policy.LIFECYCLE_HEARTBEAT_V1
|
return {
|
||||||
policy = lease_policy.policy_for(lease_task_class(lock_data))
|
"status": "expired",
|
||||||
|
"live": False,
|
||||||
|
"stale": True,
|
||||||
|
"reason": f"lease expired at {expires_at.isoformat()}",
|
||||||
|
"pid_alive": pid_alive,
|
||||||
|
"pid_missing": pid_missing,
|
||||||
|
}
|
||||||
|
|
||||||
evidence: dict[str, Any] = {
|
# #860: a PID-less lock must never be considered live merely because
|
||||||
|
# expiration / heartbeat fields are absent. Missing PID is insufficient
|
||||||
|
# evidence of a live owner; treat as malformed/stale so recovery routes
|
||||||
|
# can evaluate corroborating pins instead of blocking on a false live flag.
|
||||||
|
if pid_missing:
|
||||||
|
return {
|
||||||
|
"status": "malformed",
|
||||||
|
"live": False,
|
||||||
|
"stale": True,
|
||||||
|
"reason": (
|
||||||
|
"lock has no usable session pid; cannot prove live ownership "
|
||||||
|
"(PID-less locks are never live by missing expiry alone)"
|
||||||
|
),
|
||||||
|
"pid_alive": False,
|
||||||
|
"pid_missing": True,
|
||||||
|
"heartbeat_at": heartbeat_at.isoformat() if heartbeat_at else None,
|
||||||
|
"expires_at": expires_at.isoformat() if expires_at else None,
|
||||||
|
}
|
||||||
|
|
||||||
|
if pid_int is not None and not pid_alive:
|
||||||
|
return {
|
||||||
|
"status": "stale",
|
||||||
|
"live": False,
|
||||||
|
"stale": True,
|
||||||
|
"reason": f"owner pid {pid_int} is not alive",
|
||||||
|
"pid_alive": False,
|
||||||
|
"pid_missing": False,
|
||||||
|
}
|
||||||
|
|
||||||
|
return {
|
||||||
|
"status": "live",
|
||||||
|
"live": True,
|
||||||
|
"stale": False,
|
||||||
|
"reason": "lock heartbeat and lease are fresh",
|
||||||
"pid_alive": pid_alive,
|
"pid_alive": pid_alive,
|
||||||
"pid_missing": pid_missing,
|
"pid_missing": False,
|
||||||
"lifecycle": lifecycle,
|
|
||||||
"legacy_lease": legacy,
|
|
||||||
"task_session_id": lease_task_session_id(lock_data) or None,
|
|
||||||
"heartbeat_at": heartbeat_at.isoformat() if heartbeat_at else None,
|
"heartbeat_at": heartbeat_at.isoformat() if heartbeat_at else None,
|
||||||
"expires_at": expires_at.isoformat() if expires_at else None,
|
"expires_at": expires_at.isoformat() if expires_at else None,
|
||||||
}
|
}
|
||||||
|
|
||||||
def _result(status: str, *, live: bool, reason: str, **extra: Any) -> dict[str, Any]:
|
|
||||||
return {
|
|
||||||
"status": status,
|
|
||||||
"live": live,
|
|
||||||
"stale": not live and status != STATUS_ABSENT,
|
|
||||||
"reason": reason,
|
|
||||||
**evidence,
|
|
||||||
**extra,
|
|
||||||
}
|
|
||||||
|
|
||||||
if legacy:
|
|
||||||
# AC-N8: the preserved absolute expiry is the only clock for a lock
|
|
||||||
# written before task-session heartbeats existed.
|
|
||||||
if expires_at and expires_at <= current:
|
|
||||||
return _result(
|
|
||||||
STATUS_EXPIRED,
|
|
||||||
live=False,
|
|
||||||
reason=f"lease expired at {expires_at.isoformat()}",
|
|
||||||
)
|
|
||||||
if pid is not None and not pid_alive:
|
|
||||||
return _result(
|
|
||||||
STATUS_STALE, live=False, reason=f"owner pid {pid} is not alive"
|
|
||||||
)
|
|
||||||
return _result(
|
|
||||||
STATUS_LIVE,
|
|
||||||
live=True,
|
|
||||||
reason=(
|
|
||||||
"legacy lease is within its recorded absolute expiry; the "
|
|
||||||
"heartbeat grace does not apply retroactively"
|
|
||||||
),
|
|
||||||
legacy_expiry_preserved=True,
|
|
||||||
)
|
|
||||||
|
|
||||||
# ── Heartbeat lifecycle ──
|
|
||||||
if pid is not None and not pid_alive:
|
|
||||||
# Unchanged dead-PID band: #753 recovery depends on this exact status.
|
|
||||||
return _result(STATUS_STALE, live=False, reason=f"owner pid {pid} is not alive")
|
|
||||||
|
|
||||||
if heartbeat_at is None:
|
|
||||||
# Contradictory: a heartbeat lease must carry a heartbeat. Fail closed.
|
|
||||||
return _result(
|
|
||||||
STATUS_STALE_MISSED_HEARTBEAT,
|
|
||||||
live=False,
|
|
||||||
reason=(
|
|
||||||
f"lease declares lifecycle '{lifecycle}' but records no "
|
|
||||||
"last_heartbeat_at (fail closed)"
|
|
||||||
),
|
|
||||||
)
|
|
||||||
|
|
||||||
if policy.absolute_cap_hours and created_at is not None:
|
|
||||||
cap_at = created_at + timedelta(hours=policy.absolute_cap_hours)
|
|
||||||
if cap_at <= current:
|
|
||||||
return _result(
|
|
||||||
STATUS_STALE_ABSOLUTE_CAP,
|
|
||||||
live=False,
|
|
||||||
reason=(
|
|
||||||
f"lease exceeded its {policy.absolute_cap_hours}h absolute cap "
|
|
||||||
f"at {cap_at.isoformat()}; canonical re-adoption is required"
|
|
||||||
),
|
|
||||||
absolute_cap_at=cap_at.isoformat(),
|
|
||||||
)
|
|
||||||
|
|
||||||
grace_at = heartbeat_at + timedelta(minutes=policy.missed_heartbeat_grace_minutes)
|
|
||||||
if grace_at <= current or (expires_at is not None and expires_at <= current):
|
|
||||||
return _result(
|
|
||||||
STATUS_STALE_MISSED_HEARTBEAT,
|
|
||||||
live=False,
|
|
||||||
reason=(
|
|
||||||
f"no valid heartbeat since {heartbeat_at.isoformat()}; the "
|
|
||||||
f"{policy.missed_heartbeat_grace_minutes}min grace lapsed at "
|
|
||||||
f"{grace_at.isoformat()}"
|
|
||||||
),
|
|
||||||
missed_heartbeat_since=grace_at.isoformat(),
|
|
||||||
)
|
|
||||||
|
|
||||||
warning_at = heartbeat_at + timedelta(minutes=policy.stale_warning_minutes)
|
|
||||||
return _result(
|
|
||||||
STATUS_LIVE,
|
|
||||||
live=True,
|
|
||||||
reason="lease heartbeat is fresh within the configured grace",
|
|
||||||
heartbeat_warning=warning_at <= current,
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
def _same_realpath(left: str | None, right: str | None) -> bool:
|
def _same_realpath(left: str | None, right: str | None) -> bool:
|
||||||
if not left or not right:
|
if not left or not right:
|
||||||
@@ -964,27 +483,6 @@ def assess_expired_lock_reclaim(
|
|||||||
"reasons": ["lock is still live; cannot reclaim (fail closed)"],
|
"reasons": ["lock is still live; cannot reclaim (fail closed)"],
|
||||||
"freshness": freshness,
|
"freshness": freshness,
|
||||||
}
|
}
|
||||||
status = str(freshness.get("status") or "")
|
|
||||||
if status in (STATUS_STALE_MISSED_HEARTBEAT, STATUS_STALE_ABSOLUTE_CAP):
|
|
||||||
# #790: under the heartbeat lifecycle the heartbeat *is* the liveness
|
|
||||||
# proof, so a session that stopped heartbeating past its grace has
|
|
||||||
# released its claim by definition. Requiring a dead PID on top of that
|
|
||||||
# would reinstate the original defect — the recorded PID is the shared
|
|
||||||
# daemon, which stays alive across every abandoned task it ever served.
|
|
||||||
#
|
|
||||||
# This band is unreachable for a legacy lease (AC-N8), so no lock
|
|
||||||
# written before this lifecycle can be reclaimed by this path.
|
|
||||||
return {
|
|
||||||
"reclaim_allowed": True,
|
|
||||||
"reasons": [
|
|
||||||
f"heartbeat-lifecycle lease is {status}: {freshness.get('reason')}"
|
|
||||||
],
|
|
||||||
"freshness": freshness,
|
|
||||||
"prior_branch": existing_lock.get("branch_name"),
|
|
||||||
"prior_worktree": existing_lock.get("worktree_path"),
|
|
||||||
"prior_pid": existing_lock.get("session_pid") or existing_lock.get("pid"),
|
|
||||||
"prior_task_session_id": lease_task_session_id(existing_lock) or None,
|
|
||||||
}
|
|
||||||
pid = existing_lock.get("session_pid")
|
pid = existing_lock.get("session_pid")
|
||||||
if pid is None:
|
if pid is None:
|
||||||
pid = existing_lock.get("pid")
|
pid = existing_lock.get("pid")
|
||||||
@@ -1059,28 +557,7 @@ def assess_same_issue_lease_conflict(
|
|||||||
)
|
)
|
||||||
if recovery_sanctioned and existing_issue == issue_number and existing_branch == branch_name:
|
if recovery_sanctioned and existing_issue == issue_number and existing_branch == branch_name:
|
||||||
return None
|
return None
|
||||||
expired = is_lease_expired(existing_lock, now=now)
|
if is_lease_expired(existing_lock, now=now):
|
||||||
# #790 review #502/#516: a heartbeat-lifecycle lease that is non-live but
|
|
||||||
# whose absolute expires_at is still in the future must enter the same
|
|
||||||
# reclaim/renewal disposition as an expired lease. This happens for
|
|
||||||
# stale_absolute_cap (a session that keeps heartbeating past the 8h cap has
|
|
||||||
# expires_at = last_heartbeat + TTL in the future) and for
|
|
||||||
# stale_missed_heartbeat under an independent TTL>grace policy. Keying this
|
|
||||||
# gate on is_lease_expired alone left assess_expired_lock_reclaim — which
|
|
||||||
# already permits exactly those bands — unreachable from the acquisition
|
|
||||||
# path, so the load-bearing heartbeat was not load-bearing for foreign
|
|
||||||
# reclaim: the precise abandonment scenario #790 exists to fix.
|
|
||||||
# assess_foreign_lock_overwrite already keys on is_lease_live; this makes the
|
|
||||||
# same-issue path consistent with it. Legacy leases keep their absolute-expiry
|
|
||||||
# clock (AC-N8): is_lease_live already decides a legacy lease from expires_at
|
|
||||||
# / dead-PID alone and is_legacy_lease excludes it here, so this widening is a
|
|
||||||
# no-op for every pre-lifecycle lock.
|
|
||||||
heartbeat_non_live_reclaimable = (
|
|
||||||
not expired
|
|
||||||
and not is_legacy_lease(existing_lock)
|
|
||||||
and not is_lease_live(existing_lock, now=now)
|
|
||||||
)
|
|
||||||
if expired or heartbeat_non_live_reclaimable:
|
|
||||||
# #760 AC1/AC2: exact-owner renewal is a different disposition from
|
# #760 AC1/AC2: exact-owner renewal is a different disposition from
|
||||||
# foreign takeover and is evaluated first. Before this, both branches
|
# foreign takeover and is evaluated first. Before this, both branches
|
||||||
# below returned unconditionally, so the same_owner allowance further
|
# below returned unconditionally, so the same_owner allowance further
|
||||||
@@ -1094,12 +571,10 @@ def assess_same_issue_lease_conflict(
|
|||||||
reclaim = assess_expired_lock_reclaim(existing_lock, now=now)
|
reclaim = assess_expired_lock_reclaim(existing_lock, now=now)
|
||||||
if reclaim.get("reclaim_allowed"):
|
if reclaim.get("reclaim_allowed"):
|
||||||
# #601: expired + dead pid / missing worktree may be reclaimed
|
# #601: expired + dead pid / missing worktree may be reclaimed
|
||||||
# through the normal lock path (sanctioned overwrite). #790: the new
|
# through the normal lock path (sanctioned overwrite).
|
||||||
# stale heartbeat bands are reclaimable here on the same evidence.
|
|
||||||
return None
|
return None
|
||||||
descriptor = "expired" if expired else "non-live"
|
|
||||||
return (
|
return (
|
||||||
f"Issue #{issue_number} has an {descriptor} {operation_type} lease on "
|
f"Issue #{issue_number} has an expired {operation_type} lease on "
|
||||||
f"branch '{existing_branch}' from worktree '{existing_worktree}'. "
|
f"branch '{existing_branch}' from worktree '{existing_worktree}'. "
|
||||||
"Recovery review is required before takeover (fail closed)"
|
"Recovery review is required before takeover (fail closed)"
|
||||||
)
|
)
|
||||||
|
|||||||
-212
@@ -1,212 +0,0 @@
|
|||||||
"""Central lease policy configuration (#790 Slice A, AC-N7).
|
|
||||||
|
|
||||||
The single authoritative source for every lease duration in the project. Before
|
|
||||||
this module the numbers were scattered: a four-hour author TTL was declared
|
|
||||||
twice (``issue_lock_store`` and ``gitea_mcp_server``), the reviewer/merger
|
|
||||||
sliding window lived in ``reviewer_pr_lease``, the conflict-fix window in
|
|
||||||
``pr_work_lease``, and the control-plane default in ``control_plane_db``.
|
|
||||||
Nothing tied them together, so tuning one class silently diverged from the
|
|
||||||
others and no reader could answer "how long does a lease live?" without
|
|
||||||
grepping four files.
|
|
||||||
|
|
||||||
AC-N7 requires that this configuration exist *before* the first heartbeat and
|
|
||||||
TTL behavior that reads from it, so it ships in Slice A rather than trailing the
|
|
||||||
code it governs.
|
|
||||||
|
|
||||||
Deliberate boundaries:
|
|
||||||
|
|
||||||
* **Declaration is not rewiring.** Every task class is declared here, but only
|
|
||||||
those with ``heartbeat_lifecycle_active`` were migrated onto the shared
|
|
||||||
heartbeat lifecycle in Slice A — currently ``author_issue_work`` alone.
|
|
||||||
Reviewer, merger, and conflict-fix leases keep their own existing behavior
|
|
||||||
until Slice C moves them; their numbers are recorded here so the two cannot
|
|
||||||
drift apart unnoticed, and ``tests/test_issue_790_lease_policy.py`` asserts
|
|
||||||
the recorded values still equal the constants those modules use.
|
|
||||||
* **No policy decision lives here.** This module answers "how long", never "may
|
|
||||||
this session proceed". Freshness, reclaim, and renewal dispositions stay in
|
|
||||||
``issue_lock_store``.
|
|
||||||
"""
|
|
||||||
|
|
||||||
from __future__ import annotations
|
|
||||||
|
|
||||||
import os
|
|
||||||
from dataclasses import dataclass
|
|
||||||
from typing import Any
|
|
||||||
|
|
||||||
# Task classes. Only the first is migrated onto the shared lifecycle in Slice A.
|
|
||||||
TASK_CLASS_AUTHOR_ISSUE_WORK = "author_issue_work"
|
|
||||||
TASK_CLASS_REVIEWER_PR = "reviewer_pr"
|
|
||||||
TASK_CLASS_MERGER_PR = "merger_pr"
|
|
||||||
TASK_CLASS_CONFLICT_FIX = "conflict_fix"
|
|
||||||
|
|
||||||
# Durable marker for a lease minted under the shared heartbeat lifecycle.
|
|
||||||
#
|
|
||||||
# #790 AC-N8: this explicit marker — never a timestamp comparison — is what
|
|
||||||
# distinguishes a heartbeat-lifecycle lease from a legacy one. A lock written
|
|
||||||
# before this lifecycle existed carries no marker and reads as
|
|
||||||
# ``LIFECYCLE_LEGACY``.
|
|
||||||
LIFECYCLE_HEARTBEAT_V1 = "heartbeat-v1"
|
|
||||||
LIFECYCLE_LEGACY = "legacy"
|
|
||||||
|
|
||||||
_ENV_PREFIX = "GITEA_LEASE_POLICY"
|
|
||||||
|
|
||||||
|
|
||||||
@dataclass(frozen=True)
|
|
||||||
class LeasePolicy:
|
|
||||||
"""Durations governing one task class.
|
|
||||||
|
|
||||||
All intervals are minutes except ``absolute_cap_hours``. ``None`` for the
|
|
||||||
cap means the class has no maximum continuous duration.
|
|
||||||
"""
|
|
||||||
|
|
||||||
task_class: str
|
|
||||||
initial_ttl_minutes: float
|
|
||||||
heartbeat_cadence_minutes: float
|
|
||||||
stale_warning_minutes: float
|
|
||||||
missed_heartbeat_grace_minutes: float
|
|
||||||
absolute_cap_hours: float | None
|
|
||||||
recovery_grace_minutes: float
|
|
||||||
terminal_race_drain_minutes: float
|
|
||||||
terminal_retirement_eligible: bool
|
|
||||||
heartbeat_lifecycle_active: bool
|
|
||||||
|
|
||||||
|
|
||||||
# Defaults. ``author_issue_work`` adopts the reviewer window proven by #747
|
|
||||||
# rather than inventing new numbers: a lease expires 10 minutes after its last
|
|
||||||
# valid heartbeat, warns at half that, and an actively heartbeating session is
|
|
||||||
# never evicted. The prior value was a fixed four hours (240 minutes) that no
|
|
||||||
# heartbeat could shorten — the defect this issue exists to correct.
|
|
||||||
_DEFAULTS: dict[str, LeasePolicy] = {
|
|
||||||
TASK_CLASS_AUTHOR_ISSUE_WORK: LeasePolicy(
|
|
||||||
task_class=TASK_CLASS_AUTHOR_ISSUE_WORK,
|
|
||||||
initial_ttl_minutes=10.0,
|
|
||||||
heartbeat_cadence_minutes=2.0,
|
|
||||||
stale_warning_minutes=5.0,
|
|
||||||
missed_heartbeat_grace_minutes=10.0,
|
|
||||||
absolute_cap_hours=8.0,
|
|
||||||
recovery_grace_minutes=10.0,
|
|
||||||
terminal_race_drain_minutes=2.0,
|
|
||||||
terminal_retirement_eligible=True,
|
|
||||||
heartbeat_lifecycle_active=True,
|
|
||||||
),
|
|
||||||
# Declared, not rewired. These mirror reviewer_pr_lease.LEASE_TTL_MINUTES
|
|
||||||
# and STALE_WARNING_MINUTES; Slice C migrates the call sites.
|
|
||||||
TASK_CLASS_REVIEWER_PR: LeasePolicy(
|
|
||||||
task_class=TASK_CLASS_REVIEWER_PR,
|
|
||||||
initial_ttl_minutes=10.0,
|
|
||||||
heartbeat_cadence_minutes=2.0,
|
|
||||||
stale_warning_minutes=5.0,
|
|
||||||
missed_heartbeat_grace_minutes=10.0,
|
|
||||||
absolute_cap_hours=None,
|
|
||||||
recovery_grace_minutes=10.0,
|
|
||||||
terminal_race_drain_minutes=2.0,
|
|
||||||
terminal_retirement_eligible=False,
|
|
||||||
heartbeat_lifecycle_active=False,
|
|
||||||
),
|
|
||||||
TASK_CLASS_MERGER_PR: LeasePolicy(
|
|
||||||
task_class=TASK_CLASS_MERGER_PR,
|
|
||||||
initial_ttl_minutes=10.0,
|
|
||||||
heartbeat_cadence_minutes=2.0,
|
|
||||||
stale_warning_minutes=5.0,
|
|
||||||
missed_heartbeat_grace_minutes=10.0,
|
|
||||||
absolute_cap_hours=None,
|
|
||||||
recovery_grace_minutes=10.0,
|
|
||||||
terminal_race_drain_minutes=2.0,
|
|
||||||
terminal_retirement_eligible=False,
|
|
||||||
heartbeat_lifecycle_active=False,
|
|
||||||
),
|
|
||||||
# Mirrors pr_work_lease.DEFAULT_CONFLICT_FIX_TTL_MINUTES. Deliberately left
|
|
||||||
# at its current window; shortening it is Slice C's call, not this slice's.
|
|
||||||
TASK_CLASS_CONFLICT_FIX: LeasePolicy(
|
|
||||||
task_class=TASK_CLASS_CONFLICT_FIX,
|
|
||||||
initial_ttl_minutes=120.0,
|
|
||||||
heartbeat_cadence_minutes=2.0,
|
|
||||||
stale_warning_minutes=5.0,
|
|
||||||
missed_heartbeat_grace_minutes=10.0,
|
|
||||||
absolute_cap_hours=None,
|
|
||||||
recovery_grace_minutes=10.0,
|
|
||||||
terminal_race_drain_minutes=2.0,
|
|
||||||
terminal_retirement_eligible=False,
|
|
||||||
heartbeat_lifecycle_active=False,
|
|
||||||
),
|
|
||||||
}
|
|
||||||
|
|
||||||
_NUMERIC_FIELDS = (
|
|
||||||
"initial_ttl_minutes",
|
|
||||||
"heartbeat_cadence_minutes",
|
|
||||||
"stale_warning_minutes",
|
|
||||||
"missed_heartbeat_grace_minutes",
|
|
||||||
"absolute_cap_hours",
|
|
||||||
"recovery_grace_minutes",
|
|
||||||
"terminal_race_drain_minutes",
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
def env_var_name(task_class: str, field: str) -> str:
|
|
||||||
"""Environment variable that overrides one field of one task class."""
|
|
||||||
return f"{_ENV_PREFIX}_{task_class.upper()}_{field.upper()}"
|
|
||||||
|
|
||||||
|
|
||||||
def _override(task_class: str, field: str, default: float | None) -> float | None:
|
|
||||||
"""Read one override, falling back to *default* on anything unusable.
|
|
||||||
|
|
||||||
A malformed or non-positive override is ignored rather than raised: a typo
|
|
||||||
in an environment variable must not be able to mint a zero-length lease that
|
|
||||||
makes every claim instantly reclaimable, nor crash the server at import.
|
|
||||||
"""
|
|
||||||
raw = (os.environ.get(env_var_name(task_class, field)) or "").strip()
|
|
||||||
if not raw:
|
|
||||||
return default
|
|
||||||
try:
|
|
||||||
value = float(raw)
|
|
||||||
except (TypeError, ValueError):
|
|
||||||
return default
|
|
||||||
if value <= 0:
|
|
||||||
return default
|
|
||||||
return value
|
|
||||||
|
|
||||||
|
|
||||||
def policy_for(task_class: str) -> LeasePolicy:
|
|
||||||
"""Return the effective policy for *task_class*.
|
|
||||||
|
|
||||||
Unknown task classes fall back to the author policy, which is the most
|
|
||||||
conservative migrated class, rather than raising — a new caller must never
|
|
||||||
be able to crash a lock write by naming a class this table has not learned.
|
|
||||||
"""
|
|
||||||
key = str(task_class or "").strip() or TASK_CLASS_AUTHOR_ISSUE_WORK
|
|
||||||
base = _DEFAULTS.get(key) or _DEFAULTS[TASK_CLASS_AUTHOR_ISSUE_WORK]
|
|
||||||
resolved = {
|
|
||||||
field: _override(base.task_class, field, getattr(base, field))
|
|
||||||
for field in _NUMERIC_FIELDS
|
|
||||||
}
|
|
||||||
if all(resolved[field] == getattr(base, field) for field in _NUMERIC_FIELDS):
|
|
||||||
return base
|
|
||||||
return LeasePolicy(
|
|
||||||
task_class=base.task_class,
|
|
||||||
terminal_retirement_eligible=base.terminal_retirement_eligible,
|
|
||||||
heartbeat_lifecycle_active=base.heartbeat_lifecycle_active,
|
|
||||||
**resolved,
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
def known_task_classes() -> tuple[str, ...]:
|
|
||||||
"""Every declared task class, migrated or not."""
|
|
||||||
return tuple(_DEFAULTS)
|
|
||||||
|
|
||||||
|
|
||||||
def describe(task_class: str) -> dict[str, Any]:
|
|
||||||
"""Serializable view of a policy, for audit records and tool payloads."""
|
|
||||||
policy = policy_for(task_class)
|
|
||||||
return {
|
|
||||||
"task_class": policy.task_class,
|
|
||||||
"initial_ttl_minutes": policy.initial_ttl_minutes,
|
|
||||||
"heartbeat_cadence_minutes": policy.heartbeat_cadence_minutes,
|
|
||||||
"stale_warning_minutes": policy.stale_warning_minutes,
|
|
||||||
"missed_heartbeat_grace_minutes": policy.missed_heartbeat_grace_minutes,
|
|
||||||
"absolute_cap_hours": policy.absolute_cap_hours,
|
|
||||||
"recovery_grace_minutes": policy.recovery_grace_minutes,
|
|
||||||
"terminal_race_drain_minutes": policy.terminal_race_drain_minutes,
|
|
||||||
"terminal_retirement_eligible": policy.terminal_retirement_eligible,
|
|
||||||
"heartbeat_lifecycle_active": policy.heartbeat_lifecycle_active,
|
|
||||||
"lifecycle_version": LIFECYCLE_HEARTBEAT_V1,
|
|
||||||
}
|
|
||||||
@@ -32,15 +32,6 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
|
|||||||
"permission": "gitea.issue.comment",
|
"permission": "gitea.issue.comment",
|
||||||
"role": "author",
|
"role": "author",
|
||||||
},
|
},
|
||||||
# #790 Slice A: prove an owned author lease is still active. Strictly
|
|
||||||
# narrower than lock_issue — it can only slide a lease this exact session
|
|
||||||
# already owns, never acquire, take over, or revive one — so it gates on the
|
|
||||||
# same authority rather than introducing an operation name that every
|
|
||||||
# already-configured author profile would be missing.
|
|
||||||
"heartbeat_issue_lock": {
|
|
||||||
"permission": "gitea.issue.comment",
|
|
||||||
"role": "author",
|
|
||||||
},
|
|
||||||
# #860: dirty orphaned same-claimant worktree recovery (explicit operation).
|
# #860: dirty orphaned same-claimant worktree recovery (explicit operation).
|
||||||
"recover_dirty_orphaned_issue_worktree": {
|
"recover_dirty_orphaned_issue_worktree": {
|
||||||
"permission": "gitea.issue.comment",
|
"permission": "gitea.issue.comment",
|
||||||
|
|||||||
@@ -1,444 +0,0 @@
|
|||||||
"""Task heartbeat through the native MCP author path (#790 Slice A, AC-N6).
|
|
||||||
|
|
||||||
Assessor-level coverage is not sufficient here, and this project has already
|
|
||||||
paid for learning that: in review #499 on PR #791 the #760 renewal waiver was
|
|
||||||
computed correctly and then *discarded* at two later gates, so every real
|
|
||||||
renewal still failed while the unit suite stayed green. AC-N6 exists because of
|
|
||||||
that, and requires driving the real tools against a real git repository and a
|
|
||||||
real durable lock file, composing the gates in production order.
|
|
||||||
|
|
||||||
These tests therefore call ``gitea_lock_issue`` and
|
|
||||||
``gitea_heartbeat_issue_lock`` themselves and assert on what lands on disk,
|
|
||||||
never on an assessor's return value alone.
|
|
||||||
"""
|
|
||||||
|
|
||||||
from __future__ import annotations
|
|
||||||
|
|
||||||
import os
|
|
||||||
import subprocess
|
|
||||||
import sys
|
|
||||||
import tempfile
|
|
||||||
import unittest
|
|
||||||
from datetime import datetime, timedelta, timezone
|
|
||||||
from unittest.mock import patch
|
|
||||||
|
|
||||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
|
||||||
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
|
|
||||||
|
|
||||||
from mutation_profile_fixture import shared_mutation_env # noqa: E402
|
|
||||||
|
|
||||||
import issue_lock_provenance # noqa: E402
|
|
||||||
import issue_lock_store # noqa: E402
|
|
||||||
import lease_policy # noqa: E402
|
|
||||||
import mcp_server # noqa: E402
|
|
||||||
|
|
||||||
ISSUE = 9791
|
|
||||||
BRANCH = f"fix/issue-{ISSUE}-heartbeat-mcp"
|
|
||||||
IDENTITY = "example-user"
|
|
||||||
PROFILE = "test-author-prgs"
|
|
||||||
ORG = "Scaled-Tech-Consulting"
|
|
||||||
REPO = "Gitea-Tools"
|
|
||||||
|
|
||||||
|
|
||||||
def _ts(moment: datetime) -> str:
|
|
||||||
return (
|
|
||||||
moment.astimezone(timezone.utc)
|
|
||||||
.replace(microsecond=0)
|
|
||||||
.isoformat()
|
|
||||||
.replace("+00:00", "Z")
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
class _HeartbeatMcpBase(unittest.TestCase):
|
|
||||||
"""Real git repo plus a real durable lock, driven through the real tools."""
|
|
||||||
|
|
||||||
def setUp(self):
|
|
||||||
self.lock_dir = tempfile.TemporaryDirectory()
|
|
||||||
self.addCleanup(self.lock_dir.cleanup)
|
|
||||||
self.repo = tempfile.mkdtemp(prefix="issue790-mcp-")
|
|
||||||
self.addCleanup(lambda: subprocess.run(["rm", "-rf", self.repo], check=False))
|
|
||||||
self._init_worktree()
|
|
||||||
self.remotes = patch.dict(
|
|
||||||
mcp_server.REMOTES,
|
|
||||||
{"prgs": {"host": "gitea.prgs.cc", "org": ORG, "repo": REPO}},
|
|
||||||
)
|
|
||||||
self.remotes.start()
|
|
||||||
self.addCleanup(patch.stopall)
|
|
||||||
mcp_server._IDENTITY_CACHE.clear()
|
|
||||||
|
|
||||||
def _git(self, *args):
|
|
||||||
return subprocess.run(
|
|
||||||
["git", "-C", self.repo, *args], capture_output=True, text=True, check=True
|
|
||||||
)
|
|
||||||
|
|
||||||
def _init_worktree(self):
|
|
||||||
self._git("init", "-q", "-b", "master")
|
|
||||||
self._git("config", "user.email", "[email protected]")
|
|
||||||
self._git("config", "user.name", "Test")
|
|
||||||
with open(os.path.join(self.repo, "seed.txt"), "w") as fh:
|
|
||||||
fh.write("seed\n")
|
|
||||||
self._git("add", "seed.txt")
|
|
||||||
self._git("commit", "-q", "-m", "seed")
|
|
||||||
self.base_sha = self._git("rev-parse", "HEAD").stdout.strip()
|
|
||||||
# A fresh claim starts base-equivalent, which is the ordinary first-lock
|
|
||||||
# shape and exercises assess_issue_lock_worktree on its normal path.
|
|
||||||
self._git("checkout", "-q", "-b", BRANCH)
|
|
||||||
self.head_sha = self.base_sha
|
|
||||||
self.worktree = os.path.realpath(self.repo)
|
|
||||||
|
|
||||||
def _lock_path(self):
|
|
||||||
return issue_lock_store.lock_file_path(
|
|
||||||
remote="prgs",
|
|
||||||
org=ORG,
|
|
||||||
repo=REPO,
|
|
||||||
issue_number=ISSUE,
|
|
||||||
lock_dir=self.lock_dir.name,
|
|
||||||
)
|
|
||||||
|
|
||||||
def _tool_env(self):
|
|
||||||
env = shared_mutation_env(
|
|
||||||
PROFILE, include_example_repo=True, GITEA_ISSUE_LOCK_DIR=self.lock_dir.name
|
|
||||||
)
|
|
||||||
env["GITEA_ISSUE_LOCK_DIR"] = self.lock_dir.name
|
|
||||||
return env
|
|
||||||
|
|
||||||
def _git_state(self, *, porcelain="", base_equivalent=True):
|
|
||||||
return {
|
|
||||||
"current_branch": BRANCH,
|
|
||||||
"porcelain_status": porcelain,
|
|
||||||
"base_equivalent": base_equivalent,
|
|
||||||
"head_sha": self.head_sha,
|
|
||||||
"inspected_git_root": self.worktree,
|
|
||||||
"base_branch": "master",
|
|
||||||
}
|
|
||||||
|
|
||||||
def run_lock_issue(
|
|
||||||
self,
|
|
||||||
*,
|
|
||||||
branch_entries=None,
|
|
||||||
open_prs=None,
|
|
||||||
git_state=None,
|
|
||||||
identity=IDENTITY,
|
|
||||||
profile=PROFILE,
|
|
||||||
):
|
|
||||||
branch_entries = branch_entries if branch_entries is not None else []
|
|
||||||
open_prs = open_prs if open_prs is not None else []
|
|
||||||
git_state = git_state or self._git_state()
|
|
||||||
env = self._tool_env()
|
|
||||||
with patch(
|
|
||||||
"mcp_server.api_get_all", return_value=list(branch_entries)
|
|
||||||
), patch(
|
|
||||||
"mcp_server._list_open_pulls", return_value=list(open_prs)
|
|
||||||
), patch(
|
|
||||||
"mcp_server.get_auth_header", return_value="token x"
|
|
||||||
), patch(
|
|
||||||
"mcp_server._work_lease_claimant",
|
|
||||||
return_value={"username": identity, "profile": profile},
|
|
||||||
), patch(
|
|
||||||
"mcp_server.issue_lock_worktree.read_worktree_git_state",
|
|
||||||
return_value=git_state,
|
|
||||||
), patch(
|
|
||||||
"mcp_server.issue_duplicate_context_fetcher",
|
|
||||||
side_effect=lambda h, o, r, auth, issue_number: (
|
|
||||||
list(open_prs),
|
|
||||||
[b.get("name") for b in branch_entries if isinstance(b, dict)],
|
|
||||||
{"status": "not_claimed"},
|
|
||||||
),
|
|
||||||
), patch.dict(os.environ, env, clear=True):
|
|
||||||
os.environ["GITEA_ISSUE_LOCK_DIR"] = self.lock_dir.name
|
|
||||||
return mcp_server.gitea_lock_issue(
|
|
||||||
issue_number=ISSUE,
|
|
||||||
branch_name=BRANCH,
|
|
||||||
remote="prgs",
|
|
||||||
worktree_path=self.worktree,
|
|
||||||
)
|
|
||||||
|
|
||||||
def run_heartbeat(
|
|
||||||
self, *, task_session_id, identity=IDENTITY, profile=PROFILE, **kwargs
|
|
||||||
):
|
|
||||||
env = self._tool_env()
|
|
||||||
with patch(
|
|
||||||
"mcp_server._work_lease_claimant",
|
|
||||||
return_value={"username": identity, "profile": profile},
|
|
||||||
), patch("mcp_server.get_auth_header", return_value="token x"), patch.dict(
|
|
||||||
os.environ, env, clear=True
|
|
||||||
):
|
|
||||||
os.environ["GITEA_ISSUE_LOCK_DIR"] = self.lock_dir.name
|
|
||||||
return mcp_server.gitea_heartbeat_issue_lock(
|
|
||||||
issue_number=ISSUE,
|
|
||||||
branch_name=kwargs.pop("branch_name", BRANCH),
|
|
||||||
task_session_id=task_session_id,
|
|
||||||
remote="prgs",
|
|
||||||
worktree_path=kwargs.pop("worktree_path", self.worktree),
|
|
||||||
**kwargs,
|
|
||||||
)
|
|
||||||
|
|
||||||
def write_legacy_lock(self, *, hours_old: float = 3.0, ttl_hours: float = 4.0):
|
|
||||||
"""A durable lock in the shape the store wrote before this slice."""
|
|
||||||
now = datetime.now(timezone.utc)
|
|
||||||
claimant = {"username": IDENTITY, "profile": PROFILE}
|
|
||||||
created = now - timedelta(hours=hours_old)
|
|
||||||
record = {
|
|
||||||
"issue_number": ISSUE,
|
|
||||||
"branch_name": BRANCH,
|
|
||||||
"remote": "prgs",
|
|
||||||
"org": ORG,
|
|
||||||
"repo": REPO,
|
|
||||||
"worktree_path": self.worktree,
|
|
||||||
"session_pid": os.getpid(),
|
|
||||||
"pid": os.getpid(),
|
|
||||||
"lock_generation": 1,
|
|
||||||
"work_lease": {
|
|
||||||
"operation_type": issue_lock_store.AUTHOR_ISSUE_WORK_LEASE,
|
|
||||||
"issue_number": ISSUE,
|
|
||||||
"pr_number": None,
|
|
||||||
"branch": BRANCH,
|
|
||||||
"worktree_path": self.worktree,
|
|
||||||
"claimant": claimant,
|
|
||||||
"created_at": _ts(created),
|
|
||||||
# The legacy signature: never advanced past creation.
|
|
||||||
"last_heartbeat_at": _ts(created),
|
|
||||||
"expires_at": _ts(created + timedelta(hours=ttl_hours)),
|
|
||||||
},
|
|
||||||
"lock_provenance": issue_lock_provenance.build_sanctioned_lock_provenance(
|
|
||||||
tool="gitea_lock_issue", claimant=claimant
|
|
||||||
),
|
|
||||||
}
|
|
||||||
path = self._lock_path()
|
|
||||||
record["lock_file_path"] = path
|
|
||||||
issue_lock_store.save_lock_file(path, record)
|
|
||||||
return record
|
|
||||||
|
|
||||||
|
|
||||||
class TestLockIssueMintsTheLifecycle(_HeartbeatMcpBase):
|
|
||||||
"""Durable lock creation and read-back through the real tool."""
|
|
||||||
|
|
||||||
def test_native_lock_writes_the_marker_and_a_task_session_id(self):
|
|
||||||
result = self.run_lock_issue()
|
|
||||||
self.assertTrue(result["success"], result)
|
|
||||||
|
|
||||||
written = issue_lock_store.read_lock_file(result["lock_file_path"])
|
|
||||||
lease = written["work_lease"]
|
|
||||||
self.assertEqual(
|
|
||||||
lease["lifecycle_version"], lease_policy.LIFECYCLE_HEARTBEAT_V1
|
|
||||||
)
|
|
||||||
self.assertTrue(lease["task_session_id"])
|
|
||||||
self.assertFalse(issue_lock_store.is_legacy_lease(written))
|
|
||||||
# AC-N1: the ownership key is not the daemon pid, which is recorded
|
|
||||||
# separately as evidence.
|
|
||||||
self.assertNotIn(str(written["session_pid"]), lease["task_session_id"])
|
|
||||||
self.assertEqual(written["session_pid"], os.getpid())
|
|
||||||
|
|
||||||
def test_native_lease_uses_the_policy_window_not_four_hours(self):
|
|
||||||
result = self.run_lock_issue()
|
|
||||||
lease = result["work_lease"]
|
|
||||||
created = datetime.fromisoformat(lease["created_at"].replace("Z", "+00:00"))
|
|
||||||
expires = datetime.fromisoformat(lease["expires_at"].replace("Z", "+00:00"))
|
|
||||||
policy = lease_policy.policy_for(lease_policy.TASK_CLASS_AUTHOR_ISSUE_WORK)
|
|
||||||
self.assertEqual(
|
|
||||||
(expires - created).total_seconds() / 60.0, policy.initial_ttl_minutes
|
|
||||||
)
|
|
||||||
|
|
||||||
def test_freshness_of_a_new_native_lock_is_live(self):
|
|
||||||
result = self.run_lock_issue()
|
|
||||||
self.assertEqual(
|
|
||||||
result["lock_freshness"]["status"], issue_lock_store.STATUS_LIVE
|
|
||||||
)
|
|
||||||
self.assertTrue(result["lock_freshness"]["live"])
|
|
||||||
|
|
||||||
|
|
||||||
class TestHeartbeatThroughTheTool(_HeartbeatMcpBase):
|
|
||||||
def _lock_and_session(self):
|
|
||||||
result = self.run_lock_issue()
|
|
||||||
self.assertTrue(result["success"], result)
|
|
||||||
return result, result["work_lease"]["task_session_id"]
|
|
||||||
|
|
||||||
def test_heartbeat_slides_the_lease_and_advances_the_generation(self):
|
|
||||||
locked, session = self._lock_and_session()
|
|
||||||
before = issue_lock_store.read_lock_file(locked["lock_file_path"])
|
|
||||||
|
|
||||||
beat = self.run_heartbeat(task_session_id=session)
|
|
||||||
|
|
||||||
self.assertTrue(beat["success"], beat)
|
|
||||||
self.assertEqual(beat["operation"], "heartbeat")
|
|
||||||
after = issue_lock_store.read_lock_file(locked["lock_file_path"])
|
|
||||||
self.assertGreater(
|
|
||||||
issue_lock_store.lock_generation(after),
|
|
||||||
issue_lock_store.lock_generation(before),
|
|
||||||
)
|
|
||||||
self.assertGreaterEqual(
|
|
||||||
after["work_lease"]["expires_at"], before["work_lease"]["expires_at"]
|
|
||||||
)
|
|
||||||
self.assertEqual(after["work_lease"]["heartbeat_count"], 2)
|
|
||||||
|
|
||||||
def test_heartbeat_evidence_survives_the_downstream_mutation_gate(self):
|
|
||||||
"""The #499 F2 lesson, applied.
|
|
||||||
|
|
||||||
A sanction that is computed and then discarded downstream is worthless.
|
|
||||||
After a heartbeat the lock must still satisfy the gate every author
|
|
||||||
mutation runs through.
|
|
||||||
"""
|
|
||||||
locked, session = self._lock_and_session()
|
|
||||||
self.run_heartbeat(task_session_id=session)
|
|
||||||
|
|
||||||
written = issue_lock_store.read_lock_file(locked["lock_file_path"])
|
|
||||||
verdict = issue_lock_store.verify_lock_for_mutation(
|
|
||||||
written,
|
|
||||||
issue_number=ISSUE,
|
|
||||||
branch_name=BRANCH,
|
|
||||||
worktree_path=self.worktree,
|
|
||||||
)
|
|
||||||
self.assertTrue(verdict["proven"], verdict)
|
|
||||||
self.assertFalse(verdict["block"])
|
|
||||||
|
|
||||||
def _duplicate_gate(self, *, open_prs, branches):
|
|
||||||
env = self._tool_env()
|
|
||||||
with patch("mcp_server.get_auth_header", return_value="token x"), patch(
|
|
||||||
"mcp_server.issue_duplicate_context_fetcher",
|
|
||||||
side_effect=lambda h, o, r, auth, issue_number: (
|
|
||||||
list(open_prs),
|
|
||||||
list(branches),
|
|
||||||
{"status": "not_claimed"},
|
|
||||||
),
|
|
||||||
), patch.dict(os.environ, env, clear=True):
|
|
||||||
os.environ["GITEA_ISSUE_LOCK_DIR"] = self.lock_dir.name
|
|
||||||
return mcp_server.gitea_assess_work_issue_duplicate(
|
|
||||||
issue_number=ISSUE, branch_name=BRANCH, remote="prgs"
|
|
||||||
)
|
|
||||||
|
|
||||||
def test_heartbeat_does_not_change_the_duplicate_gate_verdict(self):
|
|
||||||
"""The gate must be invariant under heartbeating.
|
|
||||||
|
|
||||||
The point is not that the gate passes — with a linked open PR at the
|
|
||||||
lock phase it correctly blocks (#400), heartbeat or not. The property
|
|
||||||
that matters is that sliding a lease neither loosens the gate nor
|
|
||||||
corrupts the lock state it reads: the verdict before and after a
|
|
||||||
heartbeat must be identical, for both the clear and the blocking shape.
|
|
||||||
"""
|
|
||||||
_, session = self._lock_and_session()
|
|
||||||
linked = [{"number": 4242, "head": {"ref": BRANCH, "sha": self.head_sha}}]
|
|
||||||
|
|
||||||
clear_before = self._duplicate_gate(open_prs=[], branches=[])
|
|
||||||
blocked_before = self._duplicate_gate(open_prs=linked, branches=[BRANCH])
|
|
||||||
|
|
||||||
self.assertTrue(self.run_heartbeat(task_session_id=session)["success"])
|
|
||||||
|
|
||||||
clear_after = self._duplicate_gate(open_prs=[], branches=[])
|
|
||||||
blocked_after = self._duplicate_gate(open_prs=linked, branches=[BRANCH])
|
|
||||||
|
|
||||||
self.assertEqual(clear_before["outcome"], clear_after["outcome"])
|
|
||||||
self.assertFalse(clear_after["block"])
|
|
||||||
self.assertEqual(blocked_before["outcome"], blocked_after["outcome"])
|
|
||||||
self.assertTrue(blocked_after["block"])
|
|
||||||
self.assertEqual(blocked_after["linked_open_pr"], 4242)
|
|
||||||
|
|
||||||
def test_foreign_session_id_is_refused_through_the_tool(self):
|
|
||||||
self._lock_and_session()
|
|
||||||
beat = self.run_heartbeat(task_session_id="author_issue_work-ffffffffffffffff")
|
|
||||||
self.assertFalse(beat["success"])
|
|
||||||
self.assertIn("task_session_id does not match", " ".join(beat["reasons"]))
|
|
||||||
|
|
||||||
def test_stale_generation_is_refused_through_the_tool(self):
|
|
||||||
locked, session = self._lock_and_session()
|
|
||||||
current = issue_lock_store.lock_generation(
|
|
||||||
issue_lock_store.read_lock_file(locked["lock_file_path"])
|
|
||||||
)
|
|
||||||
beat = self.run_heartbeat(
|
|
||||||
task_session_id=session, expected_generation=current + 5
|
|
||||||
)
|
|
||||||
self.assertFalse(beat["success"])
|
|
||||||
self.assertIn("generation changed", beat["reasons"][0])
|
|
||||||
|
|
||||||
def test_foreign_claimant_is_refused_through_the_tool(self):
|
|
||||||
_, session = self._lock_and_session()
|
|
||||||
beat = self.run_heartbeat(task_session_id=session, identity="someone-else")
|
|
||||||
self.assertFalse(beat["success"])
|
|
||||||
|
|
||||||
def test_heartbeat_cannot_acquire_a_missing_lock(self):
|
|
||||||
beat = self.run_heartbeat(task_session_id="author_issue_work-000000000000")
|
|
||||||
self.assertFalse(beat["success"])
|
|
||||||
self.assertIn("no durable lock", beat["reasons"][0])
|
|
||||||
|
|
||||||
def test_alive_pid_alone_does_not_keep_a_lease_live_through_the_tool(self):
|
|
||||||
"""PID-only refusal, end to end.
|
|
||||||
|
|
||||||
The recorded pid is this live process. The lock is aged past its grace
|
|
||||||
with no heartbeat, so the tool must refuse to slide it and the durable
|
|
||||||
record must classify as a missed heartbeat rather than as live.
|
|
||||||
"""
|
|
||||||
locked, session = self._lock_and_session()
|
|
||||||
record = issue_lock_store.read_lock_file(locked["lock_file_path"])
|
|
||||||
record["work_lease"]["last_heartbeat_at"] = _ts(
|
|
||||||
datetime.now(timezone.utc) - timedelta(minutes=30)
|
|
||||||
)
|
|
||||||
record["work_lease"]["expires_at"] = _ts(
|
|
||||||
datetime.now(timezone.utc) + timedelta(hours=2)
|
|
||||||
)
|
|
||||||
issue_lock_store.save_lock_file(locked["lock_file_path"], record)
|
|
||||||
|
|
||||||
self.assertTrue(issue_lock_store.is_process_alive(record["session_pid"]))
|
|
||||||
fresh = issue_lock_store.assess_lock_freshness(record)
|
|
||||||
self.assertEqual(
|
|
||||||
fresh["status"], issue_lock_store.STATUS_STALE_MISSED_HEARTBEAT
|
|
||||||
)
|
|
||||||
self.assertTrue(fresh["pid_alive"])
|
|
||||||
|
|
||||||
beat = self.run_heartbeat(task_session_id=session)
|
|
||||||
self.assertFalse(beat["success"])
|
|
||||||
self.assertIn("reclaimed", " ".join(beat["reasons"]))
|
|
||||||
|
|
||||||
|
|
||||||
class TestLegacyLocksThroughTheTool(_HeartbeatMcpBase):
|
|
||||||
"""AC-N8 end to end: protected on deployment, and rebindable."""
|
|
||||||
|
|
||||||
def test_legacy_lock_stays_protected_after_deployment(self):
|
|
||||||
record = self.write_legacy_lock(hours_old=3.0, ttl_hours=4.0)
|
|
||||||
fresh = issue_lock_store.assess_lock_freshness(record)
|
|
||||||
self.assertEqual(fresh["status"], issue_lock_store.STATUS_LIVE)
|
|
||||||
self.assertTrue(fresh["legacy_lease"])
|
|
||||||
self.assertTrue(fresh["legacy_expiry_preserved"])
|
|
||||||
# It had never heartbeated, so under the new grace alone it would be
|
|
||||||
# long gone; the preserved absolute expiry is what protects it.
|
|
||||||
self.assertEqual(
|
|
||||||
record["work_lease"]["created_at"],
|
|
||||||
record["work_lease"]["last_heartbeat_at"],
|
|
||||||
)
|
|
||||||
|
|
||||||
def test_tool_rebinds_a_legacy_lock_and_mints_a_first_heartbeat(self):
|
|
||||||
self.write_legacy_lock(hours_old=3.0, ttl_hours=4.0)
|
|
||||||
|
|
||||||
result = self.run_heartbeat(task_session_id=None)
|
|
||||||
|
|
||||||
self.assertTrue(result["success"], result)
|
|
||||||
self.assertEqual(result["operation"], "legacy_rebind")
|
|
||||||
self.assertTrue(result["task_session_id"])
|
|
||||||
|
|
||||||
written = issue_lock_store.read_lock_file(self._lock_path())
|
|
||||||
lease = written["work_lease"]
|
|
||||||
self.assertEqual(
|
|
||||||
lease["lifecycle_version"], lease_policy.LIFECYCLE_HEARTBEAT_V1
|
|
||||||
)
|
|
||||||
self.assertEqual(lease["heartbeat_count"], 1)
|
|
||||||
self.assertNotEqual(
|
|
||||||
lease["created_at"],
|
|
||||||
written["legacy_rebind"]["legacy_origin"]["created_at"],
|
|
||||||
)
|
|
||||||
self.assertFalse(issue_lock_store.is_legacy_lease(written))
|
|
||||||
|
|
||||||
def test_rebound_lock_then_heartbeats_through_the_tool(self):
|
|
||||||
self.write_legacy_lock(hours_old=3.0, ttl_hours=4.0)
|
|
||||||
rebound = self.run_heartbeat(task_session_id=None)
|
|
||||||
beat = self.run_heartbeat(task_session_id=rebound["task_session_id"])
|
|
||||||
self.assertTrue(beat["success"], beat)
|
|
||||||
self.assertEqual(beat["operation"], "heartbeat")
|
|
||||||
self.assertEqual(beat["heartbeat_count"], 2)
|
|
||||||
|
|
||||||
def test_rebind_refuses_a_foreign_owner_through_the_tool(self):
|
|
||||||
self.write_legacy_lock(hours_old=3.0, ttl_hours=4.0)
|
|
||||||
result = self.run_heartbeat(task_session_id=None, identity="someone-else")
|
|
||||||
self.assertFalse(result["success"])
|
|
||||||
self.assertEqual(result["operation"], "legacy_rebind")
|
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
|
||||||
unittest.main()
|
|
||||||
@@ -1,594 +0,0 @@
|
|||||||
"""Central lease policy and load-bearing heartbeat freshness (#790 Slice A).
|
|
||||||
|
|
||||||
Before this slice, ``issue_lock_store.assess_lock_freshness`` parsed
|
|
||||||
``last_heartbeat_at`` and then never consulted it: liveness was decided by an
|
|
||||||
absolute four-hour ``expires_at`` and by PID liveness. Because the recorded PID
|
|
||||||
is the long-lived MCP daemon rather than the authoring task, an abandoned claim
|
|
||||||
stayed "live" for the full four hours, and a claim whose work had already landed
|
|
||||||
blocked reconciliation for just as long (Issue #787 / PR #789, and again Issue
|
|
||||||
#760 / PR #791).
|
|
||||||
|
|
||||||
These tests pin the corrected semantics, including the two asymmetries that are
|
|
||||||
easy to lose in a refactor:
|
|
||||||
|
|
||||||
* an **alive** PID must never make anything live (AC-N2), while
|
|
||||||
* a **dead** PID must still mark a lease stale, because #753 dead-session
|
|
||||||
recovery keys on exactly that classification.
|
|
||||||
|
|
||||||
Durable-state helpers here write real lock files through the real flock path;
|
|
||||||
they are not mocks of the store.
|
|
||||||
"""
|
|
||||||
|
|
||||||
from __future__ import annotations
|
|
||||||
|
|
||||||
import os
|
|
||||||
import sys
|
|
||||||
import tempfile
|
|
||||||
import unittest
|
|
||||||
from datetime import datetime, timedelta, timezone
|
|
||||||
from unittest.mock import patch
|
|
||||||
|
|
||||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
|
||||||
|
|
||||||
import issue_lock_store # noqa: E402
|
|
||||||
import lease_policy # noqa: E402
|
|
||||||
import pr_work_lease # noqa: E402
|
|
||||||
import reviewer_pr_lease # noqa: E402
|
|
||||||
|
|
||||||
ISSUE = 9790
|
|
||||||
BRANCH = f"fix/issue-{ISSUE}-heartbeat"
|
|
||||||
IDENTITY = "example-user"
|
|
||||||
PROFILE = "test-author-prgs"
|
|
||||||
ORG = "Example-Org"
|
|
||||||
REPO = "Example-Repo"
|
|
||||||
REMOTE = "prgs"
|
|
||||||
DEAD_PID = 2**22 # far above any live pid on a test host
|
|
||||||
|
|
||||||
|
|
||||||
def _ts(moment: datetime) -> str:
|
|
||||||
return (
|
|
||||||
moment.astimezone(timezone.utc)
|
|
||||||
.replace(microsecond=0)
|
|
||||||
.isoformat()
|
|
||||||
.replace("+00:00", "Z")
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
class _LockFixture(unittest.TestCase):
|
|
||||||
def setUp(self):
|
|
||||||
self.lock_dir = tempfile.TemporaryDirectory()
|
|
||||||
self.addCleanup(self.lock_dir.cleanup)
|
|
||||||
self.now = datetime.now(timezone.utc)
|
|
||||||
self.worktree = os.path.realpath(tempfile.mkdtemp(prefix="issue790-"))
|
|
||||||
self.addCleanup(patch.stopall)
|
|
||||||
|
|
||||||
def _path(self):
|
|
||||||
return issue_lock_store.lock_file_path(
|
|
||||||
remote=REMOTE,
|
|
||||||
org=ORG,
|
|
||||||
repo=REPO,
|
|
||||||
issue_number=ISSUE,
|
|
||||||
lock_dir=self.lock_dir.name,
|
|
||||||
)
|
|
||||||
|
|
||||||
def write_lock(
|
|
||||||
self,
|
|
||||||
*,
|
|
||||||
lifecycle: str | None = lease_policy.LIFECYCLE_HEARTBEAT_V1,
|
|
||||||
created_delta: timedelta = timedelta(minutes=1),
|
|
||||||
heartbeat_delta: timedelta = timedelta(minutes=1),
|
|
||||||
expires_delta: timedelta = timedelta(minutes=9),
|
|
||||||
pid: int | None = None,
|
|
||||||
task_session_id: str | None = "author_issue_work-aaaabbbbccccdddd",
|
|
||||||
generation: int = 1,
|
|
||||||
identity: str = IDENTITY,
|
|
||||||
profile: str = PROFILE,
|
|
||||||
branch: str = BRANCH,
|
|
||||||
worktree: str | None = None,
|
|
||||||
) -> dict:
|
|
||||||
"""Write a real durable lock and return the record.
|
|
||||||
|
|
||||||
Deltas are relative to ``self.now``; ``expires_delta`` is added, the
|
|
||||||
others subtracted, so "in the past" reads naturally at each call site.
|
|
||||||
"""
|
|
||||||
lease: dict = {
|
|
||||||
"operation_type": issue_lock_store.AUTHOR_ISSUE_WORK_LEASE,
|
|
||||||
"issue_number": ISSUE,
|
|
||||||
"pr_number": None,
|
|
||||||
"branch": branch,
|
|
||||||
"worktree_path": worktree or self.worktree,
|
|
||||||
"claimant": {"username": identity, "profile": profile},
|
|
||||||
"created_at": _ts(self.now - created_delta),
|
|
||||||
"last_heartbeat_at": _ts(self.now - heartbeat_delta),
|
|
||||||
"expires_at": _ts(self.now + expires_delta),
|
|
||||||
}
|
|
||||||
if lifecycle is not None:
|
|
||||||
lease["lifecycle_version"] = lifecycle
|
|
||||||
if task_session_id is not None:
|
|
||||||
lease["task_session_id"] = task_session_id
|
|
||||||
pid_value = os.getpid() if pid is None else pid
|
|
||||||
record = {
|
|
||||||
"issue_number": ISSUE,
|
|
||||||
"branch_name": branch,
|
|
||||||
"remote": REMOTE,
|
|
||||||
"org": ORG,
|
|
||||||
"repo": REPO,
|
|
||||||
"worktree_path": worktree or self.worktree,
|
|
||||||
"session_pid": pid_value,
|
|
||||||
"pid": pid_value,
|
|
||||||
"lock_generation": generation,
|
|
||||||
"work_lease": lease,
|
|
||||||
}
|
|
||||||
path = self._path()
|
|
||||||
record["lock_file_path"] = path
|
|
||||||
issue_lock_store.save_lock_file(path, record)
|
|
||||||
return record
|
|
||||||
|
|
||||||
|
|
||||||
class TestPolicyIsTheSingleSource(unittest.TestCase):
|
|
||||||
"""AC-N7: one authoritative configuration source for every duration."""
|
|
||||||
|
|
||||||
def test_author_policy_carries_the_agreed_values(self):
|
|
||||||
policy = lease_policy.policy_for(lease_policy.TASK_CLASS_AUTHOR_ISSUE_WORK)
|
|
||||||
self.assertEqual(policy.initial_ttl_minutes, 10.0)
|
|
||||||
self.assertEqual(policy.heartbeat_cadence_minutes, 2.0)
|
|
||||||
self.assertEqual(policy.stale_warning_minutes, 5.0)
|
|
||||||
self.assertEqual(policy.missed_heartbeat_grace_minutes, 10.0)
|
|
||||||
self.assertEqual(policy.absolute_cap_hours, 8.0)
|
|
||||||
self.assertEqual(policy.recovery_grace_minutes, 10.0)
|
|
||||||
self.assertEqual(policy.terminal_race_drain_minutes, 2.0)
|
|
||||||
self.assertTrue(policy.terminal_retirement_eligible)
|
|
||||||
self.assertTrue(policy.heartbeat_lifecycle_active)
|
|
||||||
|
|
||||||
def test_the_four_hour_author_ttl_literal_is_gone(self):
|
|
||||||
"""The duplicated literal AC-N7 exists to remove."""
|
|
||||||
self.assertFalse(hasattr(issue_lock_store, "WORK_LEASE_TTL_HOURS"))
|
|
||||||
import gitea_mcp_server
|
|
||||||
|
|
||||||
self.assertFalse(hasattr(gitea_mcp_server, "WORK_LEASE_TTL_HOURS"))
|
|
||||||
|
|
||||||
def test_declared_reviewer_values_match_the_module_still_using_them(self):
|
|
||||||
"""Slice A declares reviewer/merger numbers without rewiring them.
|
|
||||||
|
|
||||||
Recording a value in two places is only safe if drift is detectable, so
|
|
||||||
this asserts the declaration still equals the constants #747 owns. When
|
|
||||||
Slice C migrates those call sites, this test becomes the proof the
|
|
||||||
migration changed nothing.
|
|
||||||
"""
|
|
||||||
policy = lease_policy.policy_for(lease_policy.TASK_CLASS_REVIEWER_PR)
|
|
||||||
self.assertEqual(
|
|
||||||
policy.initial_ttl_minutes, float(reviewer_pr_lease.LEASE_TTL_MINUTES)
|
|
||||||
)
|
|
||||||
self.assertEqual(
|
|
||||||
policy.stale_warning_minutes,
|
|
||||||
float(reviewer_pr_lease.STALE_WARNING_MINUTES),
|
|
||||||
)
|
|
||||||
self.assertFalse(policy.heartbeat_lifecycle_active)
|
|
||||||
|
|
||||||
def test_declared_conflict_fix_value_matches_its_module(self):
|
|
||||||
policy = lease_policy.policy_for(lease_policy.TASK_CLASS_CONFLICT_FIX)
|
|
||||||
self.assertEqual(
|
|
||||||
policy.initial_ttl_minutes,
|
|
||||||
float(pr_work_lease.DEFAULT_CONFLICT_FIX_TTL_MINUTES),
|
|
||||||
)
|
|
||||||
self.assertFalse(policy.heartbeat_lifecycle_active)
|
|
||||||
|
|
||||||
def test_environment_override_applies(self):
|
|
||||||
var = lease_policy.env_var_name(
|
|
||||||
lease_policy.TASK_CLASS_AUTHOR_ISSUE_WORK, "initial_ttl_minutes"
|
|
||||||
)
|
|
||||||
with patch.dict(os.environ, {var: "7"}):
|
|
||||||
self.assertEqual(
|
|
||||||
lease_policy.policy_for(
|
|
||||||
lease_policy.TASK_CLASS_AUTHOR_ISSUE_WORK
|
|
||||||
).initial_ttl_minutes,
|
|
||||||
7.0,
|
|
||||||
)
|
|
||||||
|
|
||||||
def test_unusable_override_falls_back_instead_of_minting_a_zero_lease(self):
|
|
||||||
"""A typo must not make every claim instantly reclaimable."""
|
|
||||||
var = lease_policy.env_var_name(
|
|
||||||
lease_policy.TASK_CLASS_AUTHOR_ISSUE_WORK, "initial_ttl_minutes"
|
|
||||||
)
|
|
||||||
for bad in ("0", "-5", "not-a-number", " "):
|
|
||||||
with self.subTest(value=bad), patch.dict(os.environ, {var: bad}):
|
|
||||||
self.assertEqual(
|
|
||||||
lease_policy.policy_for(
|
|
||||||
lease_policy.TASK_CLASS_AUTHOR_ISSUE_WORK
|
|
||||||
).initial_ttl_minutes,
|
|
||||||
10.0,
|
|
||||||
)
|
|
||||||
|
|
||||||
def test_unknown_task_class_does_not_raise(self):
|
|
||||||
policy = lease_policy.policy_for("something-new")
|
|
||||||
self.assertEqual(policy.task_class, lease_policy.TASK_CLASS_AUTHOR_ISSUE_WORK)
|
|
||||||
|
|
||||||
|
|
||||||
class TestLifecycleDiscrimination(_LockFixture):
|
|
||||||
"""AC-N8: the marker, never a timestamp, decides legacy vs heartbeat."""
|
|
||||||
|
|
||||||
def test_missing_marker_reads_as_legacy(self):
|
|
||||||
record = self.write_lock(lifecycle=None)
|
|
||||||
self.assertTrue(issue_lock_store.is_legacy_lease(record))
|
|
||||||
self.assertEqual(
|
|
||||||
issue_lock_store.lease_lifecycle_version(record),
|
|
||||||
lease_policy.LIFECYCLE_LEGACY,
|
|
||||||
)
|
|
||||||
|
|
||||||
def test_marker_present_reads_as_heartbeat_lifecycle(self):
|
|
||||||
record = self.write_lock()
|
|
||||||
self.assertFalse(issue_lock_store.is_legacy_lease(record))
|
|
||||||
|
|
||||||
def test_equal_created_and_heartbeat_never_implies_a_fresh_heartbeat(self):
|
|
||||||
"""The exact inversion AC-N8 forbids.
|
|
||||||
|
|
||||||
A legacy lock has ``last_heartbeat_at == created_at`` forever because
|
|
||||||
nothing ever advanced it. Reading that equality as "recently
|
|
||||||
heartbeated" would classify every never-heartbeated lock as fresh.
|
|
||||||
"""
|
|
||||||
legacy = self.write_lock(
|
|
||||||
lifecycle=None,
|
|
||||||
created_delta=timedelta(hours=3),
|
|
||||||
heartbeat_delta=timedelta(hours=3),
|
|
||||||
)
|
|
||||||
lease = legacy["work_lease"]
|
|
||||||
self.assertEqual(lease["created_at"], lease["last_heartbeat_at"])
|
|
||||||
self.assertTrue(issue_lock_store.is_legacy_lease(legacy))
|
|
||||||
|
|
||||||
# A brand-new heartbeat lease has them equal too, so the equality
|
|
||||||
# carries no information in either direction.
|
|
||||||
fresh = self.write_lock(
|
|
||||||
created_delta=timedelta(seconds=0), heartbeat_delta=timedelta(seconds=0)
|
|
||||||
)
|
|
||||||
self.assertEqual(
|
|
||||||
fresh["work_lease"]["created_at"],
|
|
||||||
fresh["work_lease"]["last_heartbeat_at"],
|
|
||||||
)
|
|
||||||
self.assertFalse(issue_lock_store.is_legacy_lease(fresh))
|
|
||||||
|
|
||||||
def test_minted_session_id_contains_no_pid(self):
|
|
||||||
"""AC-N1: the ownership key must not be derived from the daemon pid."""
|
|
||||||
minted = issue_lock_store.mint_task_session_id()
|
|
||||||
self.assertNotIn(str(os.getpid()), minted)
|
|
||||||
self.assertNotEqual(minted, issue_lock_store.mint_task_session_id())
|
|
||||||
|
|
||||||
|
|
||||||
class TestFreshnessIsHeartbeatDriven(_LockFixture):
|
|
||||||
"""AC-N2 and the new bands."""
|
|
||||||
|
|
||||||
def test_fresh_heartbeat_is_live(self):
|
|
||||||
record = self.write_lock(heartbeat_delta=timedelta(minutes=1))
|
|
||||||
fresh = issue_lock_store.assess_lock_freshness(record, now=self.now)
|
|
||||||
self.assertEqual(fresh["status"], issue_lock_store.STATUS_LIVE)
|
|
||||||
self.assertTrue(fresh["live"])
|
|
||||||
self.assertFalse(fresh["heartbeat_warning"])
|
|
||||||
|
|
||||||
def test_heartbeat_past_warning_is_still_live_but_flagged(self):
|
|
||||||
record = self.write_lock(heartbeat_delta=timedelta(minutes=6))
|
|
||||||
fresh = issue_lock_store.assess_lock_freshness(record, now=self.now)
|
|
||||||
self.assertEqual(fresh["status"], issue_lock_store.STATUS_LIVE)
|
|
||||||
self.assertTrue(fresh["heartbeat_warning"])
|
|
||||||
|
|
||||||
def test_missed_heartbeat_past_grace_is_classified_explicitly(self):
|
|
||||||
record = self.write_lock(
|
|
||||||
heartbeat_delta=timedelta(minutes=11),
|
|
||||||
expires_delta=timedelta(minutes=30),
|
|
||||||
)
|
|
||||||
fresh = issue_lock_store.assess_lock_freshness(record, now=self.now)
|
|
||||||
self.assertEqual(
|
|
||||||
fresh["status"], issue_lock_store.STATUS_STALE_MISSED_HEARTBEAT
|
|
||||||
)
|
|
||||||
self.assertFalse(fresh["live"])
|
|
||||||
self.assertTrue(fresh["stale"])
|
|
||||||
|
|
||||||
def test_alive_pid_never_establishes_freshness(self):
|
|
||||||
"""The defect in one assertion.
|
|
||||||
|
|
||||||
The recorded PID is this very process, so it is unambiguously alive —
|
|
||||||
and the lease is still not live, because the task stopped heartbeating.
|
|
||||||
"""
|
|
||||||
record = self.write_lock(
|
|
||||||
pid=os.getpid(),
|
|
||||||
heartbeat_delta=timedelta(hours=4),
|
|
||||||
expires_delta=timedelta(hours=4),
|
|
||||||
)
|
|
||||||
fresh = issue_lock_store.assess_lock_freshness(record, now=self.now)
|
|
||||||
self.assertTrue(fresh["pid_alive"])
|
|
||||||
self.assertFalse(fresh["live"])
|
|
||||||
self.assertEqual(
|
|
||||||
fresh["status"], issue_lock_store.STATUS_STALE_MISSED_HEARTBEAT
|
|
||||||
)
|
|
||||||
|
|
||||||
def test_dead_pid_still_marks_stale_for_issue_753(self):
|
|
||||||
"""The opposite asymmetry: dead-PID corroboration is preserved."""
|
|
||||||
record = self.write_lock(pid=DEAD_PID, heartbeat_delta=timedelta(minutes=1))
|
|
||||||
fresh = issue_lock_store.assess_lock_freshness(record, now=self.now)
|
|
||||||
self.assertEqual(fresh["status"], issue_lock_store.STATUS_STALE)
|
|
||||||
self.assertFalse(fresh["live"])
|
|
||||||
self.assertIn("not alive", fresh["reason"])
|
|
||||||
|
|
||||||
def test_absolute_cap_requires_readoption(self):
|
|
||||||
record = self.write_lock(
|
|
||||||
created_delta=timedelta(hours=9), heartbeat_delta=timedelta(minutes=1)
|
|
||||||
)
|
|
||||||
fresh = issue_lock_store.assess_lock_freshness(record, now=self.now)
|
|
||||||
self.assertEqual(fresh["status"], issue_lock_store.STATUS_STALE_ABSOLUTE_CAP)
|
|
||||||
self.assertIn("re-adoption", fresh["reason"])
|
|
||||||
|
|
||||||
def test_heartbeat_lifecycle_without_a_heartbeat_fails_closed(self):
|
|
||||||
record = self.write_lock()
|
|
||||||
del record["work_lease"]["last_heartbeat_at"]
|
|
||||||
issue_lock_store.save_lock_file(self._path(), record)
|
|
||||||
fresh = issue_lock_store.assess_lock_freshness(record, now=self.now)
|
|
||||||
self.assertEqual(
|
|
||||||
fresh["status"], issue_lock_store.STATUS_STALE_MISSED_HEARTBEAT
|
|
||||||
)
|
|
||||||
self.assertIn("fail closed", fresh["reason"])
|
|
||||||
|
|
||||||
def test_absent_lock(self):
|
|
||||||
fresh = issue_lock_store.assess_lock_freshness(None)
|
|
||||||
self.assertEqual(fresh["status"], issue_lock_store.STATUS_ABSENT)
|
|
||||||
self.assertFalse(fresh["stale"])
|
|
||||||
|
|
||||||
|
|
||||||
class TestLegacyLocksStayProtected(_LockFixture):
|
|
||||||
"""AC-N8: deployment must not retroactively shorten an existing claim."""
|
|
||||||
|
|
||||||
def test_legacy_lock_with_a_stale_heartbeat_remains_live(self):
|
|
||||||
"""The deployment-safety case.
|
|
||||||
|
|
||||||
A four-hour legacy lease minted three hours ago has not heartbeated
|
|
||||||
once. Under the new grace it would be long gone; under its preserved
|
|
||||||
absolute expiry it is still live, and must stay that way.
|
|
||||||
"""
|
|
||||||
record = self.write_lock(
|
|
||||||
lifecycle=None,
|
|
||||||
created_delta=timedelta(hours=3),
|
|
||||||
heartbeat_delta=timedelta(hours=3),
|
|
||||||
expires_delta=timedelta(hours=1),
|
|
||||||
)
|
|
||||||
fresh = issue_lock_store.assess_lock_freshness(record, now=self.now)
|
|
||||||
self.assertEqual(fresh["status"], issue_lock_store.STATUS_LIVE)
|
|
||||||
self.assertTrue(fresh["live"])
|
|
||||||
self.assertTrue(fresh["legacy_lease"])
|
|
||||||
self.assertTrue(fresh["legacy_expiry_preserved"])
|
|
||||||
|
|
||||||
def test_legacy_lock_past_its_absolute_expiry_is_expired_as_before(self):
|
|
||||||
record = self.write_lock(
|
|
||||||
lifecycle=None,
|
|
||||||
created_delta=timedelta(hours=5),
|
|
||||||
heartbeat_delta=timedelta(hours=5),
|
|
||||||
expires_delta=timedelta(hours=-1),
|
|
||||||
)
|
|
||||||
fresh = issue_lock_store.assess_lock_freshness(record, now=self.now)
|
|
||||||
self.assertEqual(fresh["status"], issue_lock_store.STATUS_EXPIRED)
|
|
||||||
|
|
||||||
def test_legacy_lock_is_never_reclaimed_by_the_heartbeat_band(self):
|
|
||||||
record = self.write_lock(
|
|
||||||
lifecycle=None,
|
|
||||||
created_delta=timedelta(hours=3),
|
|
||||||
heartbeat_delta=timedelta(hours=3),
|
|
||||||
expires_delta=timedelta(hours=1),
|
|
||||||
)
|
|
||||||
reclaim = issue_lock_store.assess_expired_lock_reclaim(record, now=self.now)
|
|
||||||
self.assertFalse(reclaim["reclaim_allowed"])
|
|
||||||
|
|
||||||
|
|
||||||
class TestReclaimAfterMissedHeartbeat(_LockFixture):
|
|
||||||
def test_missed_heartbeat_makes_ownership_reclaimable(self):
|
|
||||||
record = self.write_lock(
|
|
||||||
pid=os.getpid(),
|
|
||||||
heartbeat_delta=timedelta(minutes=15),
|
|
||||||
expires_delta=timedelta(hours=3),
|
|
||||||
)
|
|
||||||
reclaim = issue_lock_store.assess_expired_lock_reclaim(record, now=self.now)
|
|
||||||
self.assertTrue(reclaim["reclaim_allowed"])
|
|
||||||
self.assertIn("stale_missed_heartbeat", reclaim["reasons"][0])
|
|
||||||
|
|
||||||
def test_live_lease_is_never_reclaimable(self):
|
|
||||||
record = self.write_lock(heartbeat_delta=timedelta(minutes=1))
|
|
||||||
reclaim = issue_lock_store.assess_expired_lock_reclaim(record, now=self.now)
|
|
||||||
self.assertFalse(reclaim["reclaim_allowed"])
|
|
||||||
|
|
||||||
def test_dead_pid_reclaim_path_is_unchanged(self):
|
|
||||||
"""#753 must keep working through its original conditions."""
|
|
||||||
record = self.write_lock(pid=DEAD_PID, heartbeat_delta=timedelta(minutes=1))
|
|
||||||
reclaim = issue_lock_store.assess_expired_lock_reclaim(record, now=self.now)
|
|
||||||
self.assertTrue(reclaim["reclaim_allowed"])
|
|
||||||
self.assertTrue(reclaim["owner_pid_dead"])
|
|
||||||
|
|
||||||
|
|
||||||
class TestHeartbeatWriter(_LockFixture):
|
|
||||||
"""A4: flock + CAS + exact verification, and no revival path."""
|
|
||||||
|
|
||||||
def _heartbeat(self, **kwargs):
|
|
||||||
params = {
|
|
||||||
"remote": REMOTE,
|
|
||||||
"org": ORG,
|
|
||||||
"repo": REPO,
|
|
||||||
"issue_number": ISSUE,
|
|
||||||
"branch_name": BRANCH,
|
|
||||||
"worktree_path": self.worktree,
|
|
||||||
"identity": IDENTITY,
|
|
||||||
"profile": PROFILE,
|
|
||||||
"task_session_id": "author_issue_work-aaaabbbbccccdddd",
|
|
||||||
"lock_dir": self.lock_dir.name,
|
|
||||||
"now": self.now,
|
|
||||||
}
|
|
||||||
params.update(kwargs)
|
|
||||||
return issue_lock_store.heartbeat_session_lock(**params)
|
|
||||||
|
|
||||||
def test_heartbeat_slides_expiry_and_advances_generation(self):
|
|
||||||
self.write_lock(heartbeat_delta=timedelta(minutes=4), generation=5)
|
|
||||||
result = self._heartbeat()
|
|
||||||
self.assertTrue(result["success"], result)
|
|
||||||
self.assertEqual(result["prior_generation"], 5)
|
|
||||||
self.assertEqual(result["lock_generation"], 6)
|
|
||||||
self.assertEqual(result["heartbeat_count"], 1)
|
|
||||||
self.assertEqual(result["last_heartbeat_at"], _ts(self.now))
|
|
||||||
self.assertEqual(result["expires_at"], _ts(self.now + timedelta(minutes=10)))
|
|
||||||
self.assertTrue(result["freshness"]["live"])
|
|
||||||
|
|
||||||
def test_heartbeat_is_durable_and_repeatable(self):
|
|
||||||
self.write_lock(heartbeat_delta=timedelta(minutes=4))
|
|
||||||
self._heartbeat()
|
|
||||||
second = self._heartbeat(now=self.now + timedelta(minutes=1))
|
|
||||||
self.assertTrue(second["success"], second)
|
|
||||||
self.assertEqual(second["heartbeat_count"], 2)
|
|
||||||
written = issue_lock_store.read_lock_file(self._path())
|
|
||||||
self.assertEqual(written["work_lease"]["heartbeat_count"], 2)
|
|
||||||
|
|
||||||
def test_stale_generation_is_refused(self):
|
|
||||||
self.write_lock(generation=5)
|
|
||||||
result = self._heartbeat(expected_generation=4)
|
|
||||||
self.assertFalse(result["success"])
|
|
||||||
self.assertIn("generation changed", result["reasons"][0])
|
|
||||||
|
|
||||||
def test_foreign_session_is_refused(self):
|
|
||||||
self.write_lock()
|
|
||||||
result = self._heartbeat(task_session_id="author_issue_work-ffffffffffffffff")
|
|
||||||
self.assertFalse(result["success"])
|
|
||||||
self.assertIn("task_session_id does not match", " ".join(result["reasons"]))
|
|
||||||
|
|
||||||
def test_missing_session_id_is_refused(self):
|
|
||||||
self.write_lock()
|
|
||||||
result = self._heartbeat(task_session_id="")
|
|
||||||
self.assertFalse(result["success"])
|
|
||||||
|
|
||||||
def test_foreign_claimant_is_refused(self):
|
|
||||||
self.write_lock()
|
|
||||||
for field, value in (
|
|
||||||
("identity", "someone-else"),
|
|
||||||
("profile", "other-profile"),
|
|
||||||
):
|
|
||||||
with self.subTest(field=field):
|
|
||||||
result = self._heartbeat(**{field: value})
|
|
||||||
self.assertFalse(result["success"])
|
|
||||||
|
|
||||||
def test_branch_and_worktree_mismatch_are_refused(self):
|
|
||||||
self.write_lock()
|
|
||||||
wrong_branch = self._heartbeat(branch_name=f"fix/issue-{ISSUE}-other")
|
|
||||||
self.assertFalse(wrong_branch["success"])
|
|
||||||
wrong_worktree = self._heartbeat(worktree_path="/tmp/not-the-worktree")
|
|
||||||
self.assertFalse(wrong_worktree["success"])
|
|
||||||
|
|
||||||
def test_lapsed_lease_cannot_be_heartbeated_back_to_life(self):
|
|
||||||
"""No revival path (A4).
|
|
||||||
|
|
||||||
A session that stopped proving liveness must reclaim under a fresh
|
|
||||||
generation, not restore ownership retroactively.
|
|
||||||
"""
|
|
||||||
self.write_lock(
|
|
||||||
heartbeat_delta=timedelta(minutes=30), expires_delta=timedelta(hours=1)
|
|
||||||
)
|
|
||||||
result = self._heartbeat()
|
|
||||||
self.assertFalse(result["success"])
|
|
||||||
self.assertIn("reclaimed", " ".join(result["reasons"]))
|
|
||||||
|
|
||||||
def test_absent_lock_cannot_be_created_by_heartbeat(self):
|
|
||||||
result = self._heartbeat()
|
|
||||||
self.assertFalse(result["success"])
|
|
||||||
self.assertIn("no durable lock", result["reasons"][0])
|
|
||||||
|
|
||||||
def test_legacy_lock_is_refused_until_rebound(self):
|
|
||||||
self.write_lock(lifecycle=None)
|
|
||||||
result = self._heartbeat()
|
|
||||||
self.assertFalse(result["success"])
|
|
||||||
self.assertTrue(result["legacy_lease"])
|
|
||||||
self.assertIn("rebound", " ".join(result["reasons"]))
|
|
||||||
|
|
||||||
|
|
||||||
class TestLegacyRebind(_LockFixture):
|
|
||||||
"""AC-N8 exit route: canonical exact-owner rebinding."""
|
|
||||||
|
|
||||||
def _rebind(self, **kwargs):
|
|
||||||
params = {
|
|
||||||
"remote": REMOTE,
|
|
||||||
"org": ORG,
|
|
||||||
"repo": REPO,
|
|
||||||
"issue_number": ISSUE,
|
|
||||||
"branch_name": BRANCH,
|
|
||||||
"worktree_path": self.worktree,
|
|
||||||
"identity": IDENTITY,
|
|
||||||
"profile": PROFILE,
|
|
||||||
"lock_dir": self.lock_dir.name,
|
|
||||||
"now": self.now,
|
|
||||||
}
|
|
||||||
params.update(kwargs)
|
|
||||||
return issue_lock_store.rebind_legacy_lock(**params)
|
|
||||||
|
|
||||||
def test_rebind_mints_a_session_and_a_genuine_first_heartbeat(self):
|
|
||||||
self.write_lock(
|
|
||||||
lifecycle=None,
|
|
||||||
created_delta=timedelta(hours=3),
|
|
||||||
heartbeat_delta=timedelta(hours=3),
|
|
||||||
expires_delta=timedelta(hours=1),
|
|
||||||
generation=2,
|
|
||||||
)
|
|
||||||
result = self._rebind()
|
|
||||||
self.assertTrue(result["success"], result)
|
|
||||||
self.assertTrue(result["task_session_id"])
|
|
||||||
self.assertEqual(result["lock_generation"], 3)
|
|
||||||
|
|
||||||
written = issue_lock_store.read_lock_file(self._path())
|
|
||||||
lease = written["work_lease"]
|
|
||||||
self.assertEqual(
|
|
||||||
lease["lifecycle_version"], lease_policy.LIFECYCLE_HEARTBEAT_V1
|
|
||||||
)
|
|
||||||
self.assertEqual(lease["last_heartbeat_at"], _ts(self.now))
|
|
||||||
self.assertEqual(lease["expires_at"], _ts(self.now + timedelta(minutes=10)))
|
|
||||||
self.assertFalse(issue_lock_store.is_legacy_lease(written))
|
|
||||||
# The original claim is preserved for audit rather than overwritten.
|
|
||||||
origin = written["legacy_rebind"]["legacy_origin"]
|
|
||||||
self.assertTrue(origin["created_at"])
|
|
||||||
self.assertEqual(origin["lifecycle"], lease_policy.LIFECYCLE_LEGACY)
|
|
||||||
|
|
||||||
def test_rebound_lock_can_then_heartbeat(self):
|
|
||||||
self.write_lock(
|
|
||||||
lifecycle=None,
|
|
||||||
created_delta=timedelta(hours=3),
|
|
||||||
heartbeat_delta=timedelta(hours=3),
|
|
||||||
expires_delta=timedelta(hours=1),
|
|
||||||
)
|
|
||||||
rebound = self._rebind()
|
|
||||||
beat = issue_lock_store.heartbeat_session_lock(
|
|
||||||
remote=REMOTE,
|
|
||||||
org=ORG,
|
|
||||||
repo=REPO,
|
|
||||||
issue_number=ISSUE,
|
|
||||||
branch_name=BRANCH,
|
|
||||||
worktree_path=self.worktree,
|
|
||||||
identity=IDENTITY,
|
|
||||||
profile=PROFILE,
|
|
||||||
task_session_id=rebound["task_session_id"],
|
|
||||||
lock_dir=self.lock_dir.name,
|
|
||||||
now=self.now + timedelta(minutes=1),
|
|
||||||
)
|
|
||||||
self.assertTrue(beat["success"], beat)
|
|
||||||
|
|
||||||
def test_rebind_refuses_a_foreign_owner(self):
|
|
||||||
self.write_lock(lifecycle=None, expires_delta=timedelta(hours=1))
|
|
||||||
result = self._rebind(identity="someone-else")
|
|
||||||
self.assertFalse(result["success"])
|
|
||||||
|
|
||||||
def test_rebind_refuses_a_lock_already_on_the_lifecycle(self):
|
|
||||||
self.write_lock()
|
|
||||||
result = self._rebind()
|
|
||||||
self.assertFalse(result["success"])
|
|
||||||
self.assertFalse(result["legacy_lease"])
|
|
||||||
|
|
||||||
def test_rebind_is_not_a_recovery_path_for_a_lapsed_legacy_lease(self):
|
|
||||||
"""An expired legacy lease belongs to #760 renewal or #601 reclaim."""
|
|
||||||
self.write_lock(
|
|
||||||
lifecycle=None,
|
|
||||||
created_delta=timedelta(hours=5),
|
|
||||||
heartbeat_delta=timedelta(hours=5),
|
|
||||||
expires_delta=timedelta(hours=-1),
|
|
||||||
)
|
|
||||||
result = self._rebind()
|
|
||||||
self.assertFalse(result["success"])
|
|
||||||
self.assertIn("not a recovery path", " ".join(result["reasons"]))
|
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
|
||||||
unittest.main()
|
|
||||||
@@ -1,193 +0,0 @@
|
|||||||
"""Conflict gate honors heartbeat-lifecycle non-live reclaim bands (#790 review #502/#516).
|
|
||||||
|
|
||||||
``assess_expired_lock_reclaim`` already permits reclaim for the heartbeat-lifecycle
|
|
||||||
stale bands (``stale_missed_heartbeat``, ``stale_absolute_cap``) without a dead PID.
|
|
||||||
But ``assess_same_issue_lease_conflict`` used to enter that reclaim branch only under
|
|
||||||
``is_lease_expired`` (``expires_at <= now``). For a heartbeat-lifecycle lease that is
|
|
||||||
non-live yet whose ``expires_at`` is still in the future, the acquisition gate fell
|
|
||||||
through to the foreign "already has an active lease" block and never consulted the
|
|
||||||
reclaim assessor — so the load-bearing heartbeat was not load-bearing for foreign
|
|
||||||
reclaim, the exact abandonment scenario #790 exists to fix.
|
|
||||||
|
|
||||||
Two future-``expires_at`` non-live shapes are reachable:
|
|
||||||
|
|
||||||
* ``stale_absolute_cap`` — a session that keeps heartbeating past the 8h absolute cap
|
|
||||||
has ``expires_at = last_heartbeat + TTL`` in the future (default policy).
|
|
||||||
* ``stale_missed_heartbeat`` — under an independent TTL>grace policy the heartbeat
|
|
||||||
grace lapses while ``expires_at`` is still ahead.
|
|
||||||
|
|
||||||
These tests pin: both reclaim from a foreign acquirer; a live lease still blocks a
|
|
||||||
foreign acquirer; the same owner may reclaim its own abandoned heartbeat lease; and a
|
|
||||||
legacy (pre-lifecycle) lock keeps its absolute-``expires_at`` clock — a non-expired
|
|
||||||
legacy lock with a dead PID is *not* reclaimable through this path.
|
|
||||||
"""
|
|
||||||
|
|
||||||
from __future__ import annotations
|
|
||||||
|
|
||||||
import os
|
|
||||||
import sys
|
|
||||||
import unittest
|
|
||||||
from datetime import datetime, timedelta, timezone
|
|
||||||
from unittest import mock
|
|
||||||
|
|
||||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
|
||||||
|
|
||||||
import issue_lock_store as ils # noqa: E402
|
|
||||||
import lease_policy # noqa: E402
|
|
||||||
|
|
||||||
ISSUE = 790
|
|
||||||
OWNER_BRANCH = f"fix/issue-{ISSUE}-slice-a-heartbeat-policy"
|
|
||||||
OWNER_WORKTREE = "/tmp/wt-790-owner"
|
|
||||||
FOREIGN_BRANCH = f"fix/issue-{ISSUE}-foreign-attempt"
|
|
||||||
FOREIGN_WORKTREE = "/tmp/wt-790-foreign"
|
|
||||||
|
|
||||||
|
|
||||||
def _ts(moment: datetime) -> str:
|
|
||||||
return (
|
|
||||||
moment.astimezone(timezone.utc)
|
|
||||||
.replace(microsecond=0)
|
|
||||||
.isoformat()
|
|
||||||
.replace("+00:00", "Z")
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
class _ConflictGateBase(unittest.TestCase):
|
|
||||||
def setUp(self):
|
|
||||||
self.now = datetime(2026, 7, 23, 12, 0, 0, tzinfo=timezone.utc)
|
|
||||||
|
|
||||||
def _lock(
|
|
||||||
self,
|
|
||||||
*,
|
|
||||||
lifecycle: str | None,
|
|
||||||
created_ago: timedelta,
|
|
||||||
heartbeat_ago: timedelta,
|
|
||||||
expires_in: timedelta,
|
|
||||||
pid: int,
|
|
||||||
) -> dict:
|
|
||||||
lease: dict = {
|
|
||||||
"operation_type": ils.AUTHOR_ISSUE_WORK_LEASE,
|
|
||||||
"issue_number": ISSUE,
|
|
||||||
"branch": OWNER_BRANCH,
|
|
||||||
"worktree_path": OWNER_WORKTREE,
|
|
||||||
"created_at": _ts(self.now - created_ago),
|
|
||||||
"last_heartbeat_at": _ts(self.now - heartbeat_ago),
|
|
||||||
"expires_at": _ts(self.now + expires_in),
|
|
||||||
}
|
|
||||||
if lifecycle is not None:
|
|
||||||
lease["lifecycle_version"] = lifecycle
|
|
||||||
lease["task_session_id"] = "author_issue_work-deadbeefdeadbeef"
|
|
||||||
return {
|
|
||||||
"issue_number": ISSUE,
|
|
||||||
"branch_name": OWNER_BRANCH,
|
|
||||||
"remote": "prgs",
|
|
||||||
"org": "Scaled-Tech-Consulting",
|
|
||||||
"repo": "Gitea-Tools",
|
|
||||||
"worktree_path": OWNER_WORKTREE,
|
|
||||||
"session_pid": pid,
|
|
||||||
"pid": pid,
|
|
||||||
"work_lease": lease,
|
|
||||||
}
|
|
||||||
|
|
||||||
def _foreign_conflict(self, existing: dict) -> str | None:
|
|
||||||
return ils.assess_same_issue_lease_conflict(
|
|
||||||
existing,
|
|
||||||
issue_number=ISSUE,
|
|
||||||
branch_name=FOREIGN_BRANCH,
|
|
||||||
worktree_path=FOREIGN_WORKTREE,
|
|
||||||
now=self.now,
|
|
||||||
)
|
|
||||||
|
|
||||||
def _same_owner_conflict(self, existing: dict) -> str | None:
|
|
||||||
return ils.assess_same_issue_lease_conflict(
|
|
||||||
existing,
|
|
||||||
issue_number=ISSUE,
|
|
||||||
branch_name=OWNER_BRANCH,
|
|
||||||
worktree_path=OWNER_WORKTREE,
|
|
||||||
now=self.now,
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
class TestHeartbeatNonLiveFutureExpiresReclaim(_ConflictGateBase):
|
|
||||||
def test_stale_absolute_cap_future_expires_allows_foreign_reclaim(self):
|
|
||||||
# Created >8h ago, heartbeated one minute ago, expires 9 min in the FUTURE,
|
|
||||||
# owner PID alive: freshness = stale_absolute_cap, live=False, not expired.
|
|
||||||
existing = self._lock(
|
|
||||||
lifecycle=lease_policy.LIFECYCLE_HEARTBEAT_V1,
|
|
||||||
created_ago=timedelta(hours=9),
|
|
||||||
heartbeat_ago=timedelta(minutes=1),
|
|
||||||
expires_in=timedelta(minutes=9),
|
|
||||||
pid=os.getpid(),
|
|
||||||
)
|
|
||||||
freshness = ils.assess_lock_freshness(existing, now=self.now)
|
|
||||||
self.assertEqual(freshness["status"], ils.STATUS_STALE_ABSOLUTE_CAP)
|
|
||||||
self.assertFalse(freshness["live"])
|
|
||||||
self.assertFalse(ils.is_lease_expired(existing, now=self.now))
|
|
||||||
with mock.patch.object(ils, "is_process_alive", return_value=True):
|
|
||||||
self.assertIsNone(self._foreign_conflict(existing))
|
|
||||||
|
|
||||||
def test_missed_heartbeat_ttl_gt_grace_future_expires_allows_foreign_reclaim(self):
|
|
||||||
# Heartbeat grace (default 10 min) lapsed 5 min ago, but a TTL>grace policy
|
|
||||||
# leaves expires_at 20 min in the FUTURE: stale_missed_heartbeat, not expired.
|
|
||||||
existing = self._lock(
|
|
||||||
lifecycle=lease_policy.LIFECYCLE_HEARTBEAT_V1,
|
|
||||||
created_ago=timedelta(minutes=30),
|
|
||||||
heartbeat_ago=timedelta(minutes=15),
|
|
||||||
expires_in=timedelta(minutes=20),
|
|
||||||
pid=os.getpid(),
|
|
||||||
)
|
|
||||||
freshness = ils.assess_lock_freshness(existing, now=self.now)
|
|
||||||
self.assertEqual(freshness["status"], ils.STATUS_STALE_MISSED_HEARTBEAT)
|
|
||||||
self.assertFalse(freshness["live"])
|
|
||||||
self.assertFalse(ils.is_lease_expired(existing, now=self.now))
|
|
||||||
with mock.patch.object(ils, "is_process_alive", return_value=True):
|
|
||||||
self.assertIsNone(self._foreign_conflict(existing))
|
|
||||||
|
|
||||||
def test_same_owner_may_reclaim_its_own_abandoned_heartbeat_lease(self):
|
|
||||||
existing = self._lock(
|
|
||||||
lifecycle=lease_policy.LIFECYCLE_HEARTBEAT_V1,
|
|
||||||
created_ago=timedelta(hours=9),
|
|
||||||
heartbeat_ago=timedelta(minutes=1),
|
|
||||||
expires_in=timedelta(minutes=9),
|
|
||||||
pid=os.getpid(),
|
|
||||||
)
|
|
||||||
with mock.patch.object(ils, "is_process_alive", return_value=True):
|
|
||||||
self.assertIsNone(self._same_owner_conflict(existing))
|
|
||||||
|
|
||||||
|
|
||||||
class TestLiveAndLegacyStillBlockForeign(_ConflictGateBase):
|
|
||||||
def test_live_heartbeat_lease_still_blocks_foreign(self):
|
|
||||||
existing = self._lock(
|
|
||||||
lifecycle=lease_policy.LIFECYCLE_HEARTBEAT_V1,
|
|
||||||
created_ago=timedelta(minutes=5),
|
|
||||||
heartbeat_ago=timedelta(minutes=1),
|
|
||||||
expires_in=timedelta(minutes=9),
|
|
||||||
pid=os.getpid(),
|
|
||||||
)
|
|
||||||
freshness = ils.assess_lock_freshness(existing, now=self.now)
|
|
||||||
self.assertTrue(freshness["live"])
|
|
||||||
with mock.patch.object(ils, "is_process_alive", return_value=True):
|
|
||||||
block = self._foreign_conflict(existing)
|
|
||||||
self.assertIn("already has an active", block or "")
|
|
||||||
|
|
||||||
def test_legacy_lease_future_expires_dead_pid_is_not_reclaimed_here(self):
|
|
||||||
# AC-N8: a legacy lock keeps its absolute expires_at clock. Non-expired +
|
|
||||||
# dead PID is non-live, but the widened band excludes legacy, so the
|
|
||||||
# foreign acquirer is still blocked rather than silently reclaiming.
|
|
||||||
existing = self._lock(
|
|
||||||
lifecycle=None,
|
|
||||||
created_ago=timedelta(hours=9),
|
|
||||||
heartbeat_ago=timedelta(hours=9),
|
|
||||||
expires_in=timedelta(hours=2),
|
|
||||||
pid=4_194_304, # far above any live pid on a test host
|
|
||||||
)
|
|
||||||
with mock.patch.object(ils, "is_process_alive", return_value=False):
|
|
||||||
freshness = ils.assess_lock_freshness(existing, now=self.now)
|
|
||||||
self.assertTrue(freshness["legacy_lease"])
|
|
||||||
self.assertFalse(freshness["live"])
|
|
||||||
self.assertFalse(ils.is_lease_expired(existing, now=self.now))
|
|
||||||
block = self._foreign_conflict(existing)
|
|
||||||
self.assertIn("already has an active", block or "")
|
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
|
||||||
unittest.main()
|
|
||||||
@@ -0,0 +1,468 @@
|
|||||||
|
"""Tests for the unified web-console inventory API (#636).
|
||||||
|
|
||||||
|
Covers the four cases the issue names — empty, populated, partial failure, and
|
||||||
|
the no-false-unowned invariant — plus redaction, collision detection, the
|
||||||
|
resource-split routes, and read-only guarantees against a real control-plane
|
||||||
|
database and real durable lock files.
|
||||||
|
"""
|
||||||
|
import json
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
import tempfile
|
||||||
|
import unittest
|
||||||
|
from datetime import datetime, timedelta, timezone
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
||||||
|
|
||||||
|
from starlette.testclient import TestClient
|
||||||
|
|
||||||
|
import control_plane_db
|
||||||
|
from webui.app import create_app
|
||||||
|
from webui import inventory
|
||||||
|
|
||||||
|
|
||||||
|
def _iso(dt: datetime) -> str:
|
||||||
|
return dt.astimezone(timezone.utc).isoformat()
|
||||||
|
|
||||||
|
|
||||||
|
def _write_lock(lock_dir: str, name: str, payload: dict) -> str:
|
||||||
|
path = os.path.join(lock_dir, name)
|
||||||
|
with open(path, "w", encoding="utf-8") as handle:
|
||||||
|
json.dump(payload, handle)
|
||||||
|
return path
|
||||||
|
|
||||||
|
|
||||||
|
def _live_lock_payload(
|
||||||
|
*,
|
||||||
|
issue_number: int,
|
||||||
|
branch: str,
|
||||||
|
worktree_path: str,
|
||||||
|
pid: int,
|
||||||
|
username: str = "jcwalker3",
|
||||||
|
profile: str = "prgs-author",
|
||||||
|
) -> dict:
|
||||||
|
now = datetime.now(timezone.utc)
|
||||||
|
future = now + timedelta(hours=2)
|
||||||
|
return {
|
||||||
|
"branch_name": branch,
|
||||||
|
"issue_number": issue_number,
|
||||||
|
"org": "Scaled-Tech-Consulting",
|
||||||
|
"repo": "Gitea-Tools",
|
||||||
|
"remote": "prgs",
|
||||||
|
"pid": pid,
|
||||||
|
"session_pid": pid,
|
||||||
|
"lock_generation": 1,
|
||||||
|
"worktree_path": worktree_path,
|
||||||
|
"claimant": {"username": username, "profile": profile},
|
||||||
|
"work_lease": {
|
||||||
|
"branch": branch,
|
||||||
|
"issue_number": issue_number,
|
||||||
|
"operation_type": "author_issue_work",
|
||||||
|
"created_at": _iso(now),
|
||||||
|
"expires_at": _iso(future),
|
||||||
|
"last_heartbeat_at": _iso(now),
|
||||||
|
"claimant": {"username": username, "profile": profile},
|
||||||
|
},
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
class _FixtureMixin(unittest.TestCase):
|
||||||
|
def setUp(self) -> None:
|
||||||
|
self._tmp = tempfile.TemporaryDirectory()
|
||||||
|
self.tmp = self._tmp.name
|
||||||
|
self.lock_dir = os.path.join(self.tmp, "locks")
|
||||||
|
os.makedirs(self.lock_dir, mode=0o700)
|
||||||
|
self.db_path = os.path.join(self.tmp, "control_plane.db")
|
||||||
|
self.addCleanup(self._tmp.cleanup)
|
||||||
|
|
||||||
|
def _seed_db(self) -> control_plane_db.ControlPlaneDB:
|
||||||
|
db = control_plane_db.ControlPlaneDB(self.db_path)
|
||||||
|
db.upsert_session(
|
||||||
|
session_id="prgs-author-1",
|
||||||
|
role="author",
|
||||||
|
profile="prgs-author",
|
||||||
|
namespace="gitea-author",
|
||||||
|
pid=os.getpid(),
|
||||||
|
)
|
||||||
|
db.upsert_work_item(
|
||||||
|
remote="prgs",
|
||||||
|
org="Scaled-Tech-Consulting",
|
||||||
|
repo="Gitea-Tools",
|
||||||
|
kind="issue",
|
||||||
|
number=636,
|
||||||
|
)
|
||||||
|
db.assign_and_lease(
|
||||||
|
session_id="prgs-author-1",
|
||||||
|
role="author",
|
||||||
|
remote="prgs",
|
||||||
|
org="Scaled-Tech-Consulting",
|
||||||
|
repo="Gitea-Tools",
|
||||||
|
kind="issue",
|
||||||
|
number=636,
|
||||||
|
)
|
||||||
|
return db
|
||||||
|
|
||||||
|
|
||||||
|
class TestRedaction(unittest.TestCase):
|
||||||
|
def test_redact_path_collapses_home(self):
|
||||||
|
home = os.path.expanduser("~")
|
||||||
|
self.assertEqual(
|
||||||
|
inventory.redact_path(f"{home}/Development/Gitea-Tools"),
|
||||||
|
"~/Development/Gitea-Tools",
|
||||||
|
)
|
||||||
|
|
||||||
|
def test_redact_url_strips_userinfo_and_query(self):
|
||||||
|
self.assertEqual(
|
||||||
|
inventory.redact_url("https://user:[email protected]/api?token=abc"),
|
||||||
|
"https://gitea.prgs.cc/api",
|
||||||
|
)
|
||||||
|
|
||||||
|
def test_scrub_drops_credential_keys(self):
|
||||||
|
scrubbed = inventory.scrub(
|
||||||
|
{"token": "abc123", "api_key": "k", "profile": "prgs-author"}
|
||||||
|
)
|
||||||
|
self.assertEqual(scrubbed["token"], "[redacted]")
|
||||||
|
self.assertEqual(scrubbed["api_key"], "[redacted]")
|
||||||
|
self.assertEqual(scrubbed["profile"], "prgs-author")
|
||||||
|
|
||||||
|
def test_scrub_is_recursive_and_never_raises(self):
|
||||||
|
class Weird:
|
||||||
|
def __repr__(self) -> str:
|
||||||
|
return "weird-obj"
|
||||||
|
|
||||||
|
out = inventory.scrub({"nested": [{"password": "p", "obj": Weird()}]})
|
||||||
|
self.assertEqual(out["nested"][0]["password"], "[redacted]")
|
||||||
|
self.assertEqual(out["nested"][0]["obj"], "weird-obj")
|
||||||
|
|
||||||
|
|
||||||
|
class TestEmptyInventory(_FixtureMixin):
|
||||||
|
def test_empty_db_and_locks_degrade_without_raising(self):
|
||||||
|
# No DB file, no locks: sessions/leases unavailable, locks ok+empty.
|
||||||
|
snap = inventory.load_inventory_snapshot(
|
||||||
|
db_path=self.db_path,
|
||||||
|
lock_dir=self.lock_dir,
|
||||||
|
load_hygiene=lambda: _StubHygiene(entries=()),
|
||||||
|
)
|
||||||
|
sessions = snap.section("sessions")
|
||||||
|
leases = snap.section("leases")
|
||||||
|
locks = snap.section("locks")
|
||||||
|
self.assertEqual(sessions.status, inventory.STATUS_UNAVAILABLE)
|
||||||
|
self.assertEqual(leases.status, inventory.STATUS_UNAVAILABLE)
|
||||||
|
self.assertEqual(locks.status, inventory.STATUS_OK)
|
||||||
|
self.assertEqual(len(locks.items), 0)
|
||||||
|
# Ownership authority is incomplete because the DB is missing.
|
||||||
|
self.assertFalse(snap.ownership_authority_complete)
|
||||||
|
self.assertEqual(snap.collisions, ())
|
||||||
|
|
||||||
|
def test_empty_db_present_but_unpopulated(self):
|
||||||
|
control_plane_db.ControlPlaneDB(self.db_path) # creates schema, no rows
|
||||||
|
snap = inventory.load_inventory_snapshot(
|
||||||
|
db_path=self.db_path,
|
||||||
|
lock_dir=self.lock_dir,
|
||||||
|
load_hygiene=lambda: _StubHygiene(entries=()),
|
||||||
|
)
|
||||||
|
self.assertEqual(snap.section("sessions").status, inventory.STATUS_OK)
|
||||||
|
self.assertEqual(len(snap.section("sessions").items), 0)
|
||||||
|
self.assertEqual(snap.section("leases").status, inventory.STATUS_OK)
|
||||||
|
self.assertTrue(snap.ownership_authority_complete)
|
||||||
|
|
||||||
|
|
||||||
|
class TestPopulatedInventory(_FixtureMixin):
|
||||||
|
def test_sections_populated_and_correlated(self):
|
||||||
|
self._seed_db()
|
||||||
|
wt = f"{self.tmp}/branches/issue-636-inventory-api"
|
||||||
|
_write_lock(
|
||||||
|
self.lock_dir,
|
||||||
|
"prgs-Scaled-Tech-Consulting-Gitea-Tools-636.json",
|
||||||
|
_live_lock_payload(
|
||||||
|
issue_number=636,
|
||||||
|
branch="feat/issue-636-inventory-api",
|
||||||
|
worktree_path=wt,
|
||||||
|
pid=os.getpid(),
|
||||||
|
),
|
||||||
|
)
|
||||||
|
hygiene = _StubHygiene(
|
||||||
|
entries=(
|
||||||
|
_StubEntry(
|
||||||
|
rel_path="branches/issue-636-inventory-api",
|
||||||
|
branch="feat/issue-636-inventory-api",
|
||||||
|
classification="active-issue",
|
||||||
|
),
|
||||||
|
)
|
||||||
|
)
|
||||||
|
snap = inventory.load_inventory_snapshot(
|
||||||
|
db_path=self.db_path,
|
||||||
|
lock_dir=self.lock_dir,
|
||||||
|
load_hygiene=lambda: hygiene,
|
||||||
|
)
|
||||||
|
self.assertTrue(snap.ownership_authority_complete)
|
||||||
|
self.assertEqual(len(snap.section("sessions").items), 1)
|
||||||
|
self.assertEqual(len(snap.section("leases").items), 1)
|
||||||
|
self.assertEqual(len(snap.section("locks").items), 1)
|
||||||
|
self.assertEqual(len(snap.section("worktrees").items), 1)
|
||||||
|
|
||||||
|
# The lease, lock, and worktree for #636 correlate onto one row.
|
||||||
|
row = next(r for r in snap.correlations if r["issue_number"] == 636)
|
||||||
|
self.assertEqual(row["branch"], "feat/issue-636-inventory-api")
|
||||||
|
self.assertTrue(row["lock_live"])
|
||||||
|
self.assertEqual(row["worktree_classification"], "active-issue")
|
||||||
|
self.assertEqual(len(row["lease_ids"]), 1)
|
||||||
|
# No collision: live lock, live pid, matching worktree.
|
||||||
|
self.assertEqual(snap.collisions, ())
|
||||||
|
|
||||||
|
def test_serialized_payload_declares_field_authority(self):
|
||||||
|
self._seed_db()
|
||||||
|
snap = inventory.load_inventory_snapshot(
|
||||||
|
db_path=self.db_path,
|
||||||
|
lock_dir=self.lock_dir,
|
||||||
|
load_hygiene=lambda: _StubHygiene(entries=()),
|
||||||
|
)
|
||||||
|
payload = inventory.snapshot_to_dict(snap)
|
||||||
|
self.assertEqual(payload["api_version"], "v1")
|
||||||
|
self.assertEqual(payload["schema_version"], 1)
|
||||||
|
self.assertEqual(payload["field_authority"]["sessions"], "control_plane_db")
|
||||||
|
self.assertEqual(payload["field_authority"]["locks"], "filesystem")
|
||||||
|
self.assertIn("sessions", payload["sections"])
|
||||||
|
|
||||||
|
|
||||||
|
class TestPartialFailure(_FixtureMixin):
|
||||||
|
def test_worktree_scan_failure_degrades_only_that_section(self):
|
||||||
|
self._seed_db()
|
||||||
|
|
||||||
|
def _boom():
|
||||||
|
raise RuntimeError("git worktree list exploded")
|
||||||
|
|
||||||
|
snap = inventory.load_inventory_snapshot(
|
||||||
|
db_path=self.db_path,
|
||||||
|
lock_dir=self.lock_dir,
|
||||||
|
load_hygiene=_boom,
|
||||||
|
)
|
||||||
|
self.assertEqual(
|
||||||
|
snap.section("worktrees").status, inventory.STATUS_UNAVAILABLE
|
||||||
|
)
|
||||||
|
self.assertIn("exploded", snap.section("worktrees").reason)
|
||||||
|
# DB-backed sections still healthy.
|
||||||
|
self.assertEqual(snap.section("sessions").status, inventory.STATUS_OK)
|
||||||
|
self.assertIn("worktrees", snap.degraded_sections)
|
||||||
|
|
||||||
|
def test_degraded_ownership_suppresses_unowned_claim(self):
|
||||||
|
# DB absent → sessions/leases unavailable → ownership incomplete even
|
||||||
|
# though a lock exists and could look "unclaimed" by the DB alone.
|
||||||
|
_write_lock(
|
||||||
|
self.lock_dir,
|
||||||
|
"prgs-Scaled-Tech-Consulting-Gitea-Tools-636.json",
|
||||||
|
_live_lock_payload(
|
||||||
|
issue_number=636,
|
||||||
|
branch="feat/issue-636-inventory-api",
|
||||||
|
worktree_path=f"{self.tmp}/wt",
|
||||||
|
pid=os.getpid(),
|
||||||
|
),
|
||||||
|
)
|
||||||
|
snap = inventory.load_inventory_snapshot(
|
||||||
|
db_path=self.db_path,
|
||||||
|
lock_dir=self.lock_dir,
|
||||||
|
load_hygiene=lambda: _StubHygiene(entries=()),
|
||||||
|
)
|
||||||
|
self.assertFalse(snap.ownership_authority_complete)
|
||||||
|
payload = inventory.snapshot_to_dict(snap)
|
||||||
|
self.assertIn("may be treated as unowned", payload["ownership_note"])
|
||||||
|
|
||||||
|
|
||||||
|
class TestCollisionDetection(_FixtureMixin):
|
||||||
|
def test_live_lock_dead_owner_flagged(self):
|
||||||
|
_write_lock(
|
||||||
|
self.lock_dir,
|
||||||
|
"prgs-Scaled-Tech-Consulting-Gitea-Tools-700.json",
|
||||||
|
_live_lock_payload(
|
||||||
|
issue_number=700,
|
||||||
|
branch="feat/issue-700-x",
|
||||||
|
worktree_path=f"{self.tmp}/wt700",
|
||||||
|
pid=999_999_999, # not a running pid
|
||||||
|
),
|
||||||
|
)
|
||||||
|
control_plane_db.ControlPlaneDB(self.db_path) # empty but present
|
||||||
|
snap = inventory.load_inventory_snapshot(
|
||||||
|
db_path=self.db_path,
|
||||||
|
lock_dir=self.lock_dir,
|
||||||
|
load_hygiene=lambda: _StubHygiene(entries=()),
|
||||||
|
)
|
||||||
|
kinds = {c.kind for c in snap.collisions}
|
||||||
|
self.assertIn("live-lock-dead-owner", kinds)
|
||||||
|
# Also lock-without-worktree, since no worktree carries the branch.
|
||||||
|
self.assertIn("lock-without-worktree", kinds)
|
||||||
|
|
||||||
|
def test_duplicate_live_lock_on_same_branch(self):
|
||||||
|
for issue in (800, 801):
|
||||||
|
_write_lock(
|
||||||
|
self.lock_dir,
|
||||||
|
f"prgs-Scaled-Tech-Consulting-Gitea-Tools-{issue}.json",
|
||||||
|
_live_lock_payload(
|
||||||
|
issue_number=issue,
|
||||||
|
branch="feat/issue-800-shared",
|
||||||
|
worktree_path=f"{self.tmp}/wt{issue}",
|
||||||
|
pid=os.getpid(),
|
||||||
|
),
|
||||||
|
)
|
||||||
|
control_plane_db.ControlPlaneDB(self.db_path)
|
||||||
|
snap = inventory.load_inventory_snapshot(
|
||||||
|
db_path=self.db_path,
|
||||||
|
lock_dir=self.lock_dir,
|
||||||
|
load_hygiene=lambda: _StubHygiene(entries=()),
|
||||||
|
)
|
||||||
|
self.assertIn(
|
||||||
|
"duplicate-live-lock", {c.kind for c in snap.collisions}
|
||||||
|
)
|
||||||
|
|
||||||
|
def test_no_collision_when_sections_degraded(self):
|
||||||
|
# locks ok but worktrees unavailable → lock-without-worktree must NOT
|
||||||
|
# be asserted (a missing scan is not a missing worktree).
|
||||||
|
_write_lock(
|
||||||
|
self.lock_dir,
|
||||||
|
"prgs-Scaled-Tech-Consulting-Gitea-Tools-636.json",
|
||||||
|
_live_lock_payload(
|
||||||
|
issue_number=636,
|
||||||
|
branch="feat/issue-636-inventory-api",
|
||||||
|
worktree_path=f"{self.tmp}/wt",
|
||||||
|
pid=os.getpid(),
|
||||||
|
),
|
||||||
|
)
|
||||||
|
control_plane_db.ControlPlaneDB(self.db_path)
|
||||||
|
|
||||||
|
def _boom():
|
||||||
|
raise RuntimeError("scan down")
|
||||||
|
|
||||||
|
snap = inventory.load_inventory_snapshot(
|
||||||
|
db_path=self.db_path,
|
||||||
|
lock_dir=self.lock_dir,
|
||||||
|
load_hygiene=_boom,
|
||||||
|
)
|
||||||
|
self.assertNotIn(
|
||||||
|
"lock-without-worktree", {c.kind for c in snap.collisions}
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
class TestSectionInclude(_FixtureMixin):
|
||||||
|
def test_include_restricts_scanned_sections(self):
|
||||||
|
self._seed_db()
|
||||||
|
snap = inventory.load_inventory_snapshot(
|
||||||
|
db_path=self.db_path,
|
||||||
|
lock_dir=self.lock_dir,
|
||||||
|
include=("locks",),
|
||||||
|
)
|
||||||
|
self.assertIsNotNone(snap.section("locks"))
|
||||||
|
self.assertIsNone(snap.section("sessions"))
|
||||||
|
self.assertIsNone(snap.section("worktrees"))
|
||||||
|
|
||||||
|
|
||||||
|
class TestRoutes(_FixtureMixin):
|
||||||
|
def setUp(self) -> None:
|
||||||
|
super().setUp()
|
||||||
|
# Point the loaders at the fixture DB and lock dir via env, and stub
|
||||||
|
# the worktree scan so the route does not shell out to git.
|
||||||
|
self._prev_env = {
|
||||||
|
"GITEA_CONTROL_PLANE_DB": os.environ.get("GITEA_CONTROL_PLANE_DB"),
|
||||||
|
"GITEA_ISSUE_LOCK_DIR": os.environ.get("GITEA_ISSUE_LOCK_DIR"),
|
||||||
|
"WEBUI_TEST_OFFLINE": os.environ.get("WEBUI_TEST_OFFLINE"),
|
||||||
|
}
|
||||||
|
os.environ["GITEA_CONTROL_PLANE_DB"] = self.db_path
|
||||||
|
os.environ["GITEA_ISSUE_LOCK_DIR"] = self.lock_dir
|
||||||
|
os.environ["WEBUI_TEST_OFFLINE"] = "1"
|
||||||
|
self._seed_db()
|
||||||
|
self.client = TestClient(create_app())
|
||||||
|
|
||||||
|
def tearDown(self) -> None:
|
||||||
|
for key, value in self._prev_env.items():
|
||||||
|
if value is None:
|
||||||
|
os.environ.pop(key, None)
|
||||||
|
else:
|
||||||
|
os.environ[key] = value
|
||||||
|
|
||||||
|
def test_inventory_route_returns_versioned_payload(self):
|
||||||
|
resp = self.client.get("/api/v1/inventory")
|
||||||
|
self.assertEqual(resp.status_code, 200)
|
||||||
|
body = resp.json()
|
||||||
|
self.assertEqual(body["api_version"], "v1")
|
||||||
|
self.assertIn("sessions", body["sections"])
|
||||||
|
self.assertIn("field_authority", body)
|
||||||
|
|
||||||
|
def test_section_route_restricts_and_labels(self):
|
||||||
|
resp = self.client.get("/api/v1/inventory/locks")
|
||||||
|
self.assertEqual(resp.status_code, 200)
|
||||||
|
body = resp.json()
|
||||||
|
self.assertEqual(body["requested_section"], "locks")
|
||||||
|
self.assertIn("locks", body["sections"])
|
||||||
|
self.assertNotIn("sessions", body["sections"])
|
||||||
|
|
||||||
|
def test_unknown_section_is_404(self):
|
||||||
|
resp = self.client.get("/api/v1/inventory/bogus")
|
||||||
|
self.assertEqual(resp.status_code, 404)
|
||||||
|
self.assertEqual(resp.json()["error"], "unknown_section")
|
||||||
|
|
||||||
|
def test_inventory_route_rejects_post(self):
|
||||||
|
resp = self.client.post("/api/v1/inventory")
|
||||||
|
self.assertEqual(resp.status_code, 405)
|
||||||
|
|
||||||
|
|
||||||
|
class TestReadOnly(_FixtureMixin):
|
||||||
|
def test_snapshot_does_not_create_db_file(self):
|
||||||
|
missing = os.path.join(self.tmp, "does-not-exist.db")
|
||||||
|
inventory.load_inventory_snapshot(
|
||||||
|
db_path=missing,
|
||||||
|
lock_dir=self.lock_dir,
|
||||||
|
load_hygiene=lambda: _StubHygiene(entries=()),
|
||||||
|
)
|
||||||
|
self.assertFalse(os.path.exists(missing))
|
||||||
|
|
||||||
|
def test_readonly_connection_refuses_write(self):
|
||||||
|
self._seed_db()
|
||||||
|
conn = inventory._open_readonly(self.db_path)
|
||||||
|
try:
|
||||||
|
with self.assertRaises(Exception):
|
||||||
|
conn.execute(
|
||||||
|
"INSERT INTO sessions(session_id, role, started_at, "
|
||||||
|
"last_heartbeat_at, status) VALUES ('x','author',"
|
||||||
|
"'t','t','active')"
|
||||||
|
)
|
||||||
|
conn.commit()
|
||||||
|
finally:
|
||||||
|
conn.close()
|
||||||
|
|
||||||
|
|
||||||
|
# ── lightweight stand-ins for the #432 hygiene snapshot ──────────────────────
|
||||||
|
|
||||||
|
|
||||||
|
class _StubEntry:
|
||||||
|
def __init__(
|
||||||
|
self,
|
||||||
|
*,
|
||||||
|
rel_path: str,
|
||||||
|
branch: str | None = None,
|
||||||
|
classification: str = "stale-clean",
|
||||||
|
head_sha: str | None = "abc123",
|
||||||
|
dirty_tracked: int = 0,
|
||||||
|
dirty_untracked: bool = False,
|
||||||
|
detached: bool = False,
|
||||||
|
registered_worktree: bool = True,
|
||||||
|
notes: str = "",
|
||||||
|
) -> None:
|
||||||
|
self.rel_path = rel_path
|
||||||
|
self.folder_name = rel_path.split("/", 1)[-1]
|
||||||
|
self.branch = branch
|
||||||
|
self.classification = classification
|
||||||
|
self.head_sha = head_sha
|
||||||
|
self.dirty_tracked = dirty_tracked
|
||||||
|
self.dirty_untracked = dirty_untracked
|
||||||
|
self.detached = detached
|
||||||
|
self.registered_worktree = registered_worktree
|
||||||
|
self.notes = notes
|
||||||
|
|
||||||
|
|
||||||
|
class _StubHygiene:
|
||||||
|
def __init__(self, *, entries=(), scan_error=None) -> None:
|
||||||
|
self.entries = tuple(entries)
|
||||||
|
self.scan_error = scan_error
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
unittest.main()
|
||||||
@@ -46,6 +46,11 @@ from webui.worktree_scanner import load_hygiene_snapshot, snapshot_to_dict as wo
|
|||||||
from webui.worktree_views import render_worktrees_page
|
from webui.worktree_views import render_worktrees_page
|
||||||
from webui.runtime_health import load_runtime_snapshot, snapshot_to_dict as runtime_snapshot_to_dict
|
from webui.runtime_health import load_runtime_snapshot, snapshot_to_dict as runtime_snapshot_to_dict
|
||||||
from webui.runtime_views import render_runtime_page
|
from webui.runtime_views import render_runtime_page
|
||||||
|
from webui.inventory import (
|
||||||
|
SECTION_NAMES as _INVENTORY_SECTIONS,
|
||||||
|
load_inventory_snapshot,
|
||||||
|
snapshot_to_dict as inventory_snapshot_to_dict,
|
||||||
|
)
|
||||||
from webui.timeline import load_timeline, snapshot_to_dict as timeline_snapshot_to_dict
|
from webui.timeline import load_timeline, snapshot_to_dict as timeline_snapshot_to_dict
|
||||||
from webui.system_health import (
|
from webui.system_health import (
|
||||||
API_PATH as SYSTEM_HEALTH_API_PATH,
|
API_PATH as SYSTEM_HEALTH_API_PATH,
|
||||||
@@ -460,6 +465,30 @@ async def api_action_attempt(request: Request) -> JSONResponse:
|
|||||||
return JSONResponse(result, status_code=status)
|
return JSONResponse(result, status_code=status)
|
||||||
|
|
||||||
|
|
||||||
|
async def api_inventory(_request: Request) -> JSONResponse:
|
||||||
|
"""Unified read-only session/lease/lock/worktree inventory (#636)."""
|
||||||
|
snapshot = load_inventory_snapshot()
|
||||||
|
return JSONResponse(inventory_snapshot_to_dict(snapshot))
|
||||||
|
|
||||||
|
|
||||||
|
async def api_inventory_section(request: Request) -> JSONResponse:
|
||||||
|
"""Resource-split view: one inventory section under the shared schema."""
|
||||||
|
section = request.path_params["section"]
|
||||||
|
if section not in _INVENTORY_SECTIONS:
|
||||||
|
return JSONResponse(
|
||||||
|
{
|
||||||
|
"error": "unknown_section",
|
||||||
|
"detail": f"no inventory section named {section!r}",
|
||||||
|
"available": sorted(_INVENTORY_SECTIONS),
|
||||||
|
},
|
||||||
|
status_code=404,
|
||||||
|
)
|
||||||
|
snapshot = load_inventory_snapshot(include=(section,))
|
||||||
|
payload = inventory_snapshot_to_dict(snapshot)
|
||||||
|
payload["requested_section"] = section
|
||||||
|
return JSONResponse(payload)
|
||||||
|
|
||||||
|
|
||||||
async def api_console_security_model(_request: Request) -> JSONResponse:
|
async def api_console_security_model(_request: Request) -> JSONResponse:
|
||||||
"""Read-only publication of the #633 authorization/redaction/audit model."""
|
"""Read-only publication of the #633 authorization/redaction/audit model."""
|
||||||
return JSONResponse({
|
return JSONResponse({
|
||||||
@@ -626,6 +655,12 @@ def create_app(*, bind_host: str | None = None) -> Starlette:
|
|||||||
methods=["POST"],
|
methods=["POST"],
|
||||||
),
|
),
|
||||||
Route("/api/leases", api_leases, methods=["GET"]),
|
Route("/api/leases", api_leases, methods=["GET"]),
|
||||||
|
Route("/api/v1/inventory", api_inventory, methods=["GET"]),
|
||||||
|
Route(
|
||||||
|
"/api/v1/inventory/{section}",
|
||||||
|
api_inventory_section,
|
||||||
|
methods=["GET"],
|
||||||
|
),
|
||||||
Route(
|
Route(
|
||||||
"/api/console/security-model",
|
"/api/console/security-model",
|
||||||
api_console_security_model,
|
api_console_security_model,
|
||||||
|
|||||||
@@ -0,0 +1,952 @@
|
|||||||
|
"""Unified session/lease/lock/worktree inventory for the web console (#636).
|
||||||
|
|
||||||
|
Leases (#433), worktrees (#432), and runtime (#430) each ship their own MVP
|
||||||
|
view, each with its own shape and its own idea of what "owned" means. A
|
||||||
|
traffic-control or recovery operator has to read all three and correlate them
|
||||||
|
by hand, which is exactly the step that goes wrong under collision pressure.
|
||||||
|
|
||||||
|
This module aggregates them into one versioned, read-only snapshot so the
|
||||||
|
console, and any worker asking "what is safe to do next", read the same
|
||||||
|
inventory from the same authority.
|
||||||
|
|
||||||
|
Field authority is explicit and never blended. Every section declares where its
|
||||||
|
rows came from:
|
||||||
|
|
||||||
|
* ``control_plane_db`` — the #613 substrate: sessions, leases, assignments.
|
||||||
|
Authoritative for *exclusive ownership* (#600/#601).
|
||||||
|
* ``filesystem`` — durable per-issue lock files (:mod:`issue_lock_store`) and
|
||||||
|
registered git worktrees. Authoritative for *what exists on this machine*.
|
||||||
|
* ``gitea`` — remote issue/PR state, reached only through existing loaders.
|
||||||
|
|
||||||
|
Safety invariants:
|
||||||
|
|
||||||
|
* **Read-only.** The control-plane database is opened through a ``mode=ro``
|
||||||
|
URI. :class:`control_plane_db.ControlPlaneDB` creates directories and runs
|
||||||
|
migrations in its constructor, which an inventory read must never do, so this
|
||||||
|
module talks to sqlite directly rather than through that class.
|
||||||
|
* **Fail-soft, never fail-silent.** A subsystem that cannot be read degrades to
|
||||||
|
a section carrying ``status`` and ``reason``. It never raises, and it never
|
||||||
|
produces an empty list that reads like "nothing is there".
|
||||||
|
* **Never invent active ownership.** This is the invariant that matters most.
|
||||||
|
A degraded ownership source sets ``ownership_authority_complete`` false, and
|
||||||
|
while that flag is false no work item is reported unowned and no collision is
|
||||||
|
asserted. Absence of evidence is reported as absence of evidence.
|
||||||
|
* **Redaction at the boundary.** Absolute paths are collapsed against the home
|
||||||
|
directory, URLs lose userinfo and query strings, and no credential-shaped
|
||||||
|
value is emitted. No session token exists in these sources and none is read.
|
||||||
|
|
||||||
|
Phase 1 is read-only. Lease steal/release and worktree deletion are Phase 2+
|
||||||
|
and deliberately have no representation here, not even a disabled one.
|
||||||
|
"""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import os
|
||||||
|
import re
|
||||||
|
import sqlite3
|
||||||
|
import time
|
||||||
|
from dataclasses import dataclass, field
|
||||||
|
from datetime import datetime, timezone
|
||||||
|
from typing import Any, Callable
|
||||||
|
from urllib.parse import urlparse
|
||||||
|
|
||||||
|
import control_plane_db
|
||||||
|
import issue_lock_store
|
||||||
|
|
||||||
|
SCHEMA_VERSION = 1
|
||||||
|
API_VERSION = "v1"
|
||||||
|
|
||||||
|
#: Sections whose absence would make an ownership claim unprovable. If any of
|
||||||
|
#: these is not ``ok``, the snapshot refuses to describe anything as unowned.
|
||||||
|
OWNERSHIP_SECTIONS = ("sessions", "leases", "locks")
|
||||||
|
|
||||||
|
SECTION_NAMES = ("sessions", "leases", "locks", "worktrees", "namespaces")
|
||||||
|
|
||||||
|
STATUS_OK = "ok"
|
||||||
|
STATUS_DEGRADED = "degraded"
|
||||||
|
STATUS_UNAVAILABLE = "unavailable"
|
||||||
|
|
||||||
|
AUTHORITY_CONTROL_PLANE_DB = "control_plane_db"
|
||||||
|
AUTHORITY_FILESYSTEM = "filesystem"
|
||||||
|
AUTHORITY_GITEA = "gitea"
|
||||||
|
|
||||||
|
_CREDENTIAL_KEY_RE = re.compile(
|
||||||
|
r"(token|secret|password|passwd|api[_-]?key|authorization|bearer|credential)",
|
||||||
|
re.IGNORECASE,
|
||||||
|
)
|
||||||
|
_REDACTED = "[redacted]"
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class InventorySection:
|
||||||
|
"""One subsystem's contribution, with its authority and health."""
|
||||||
|
|
||||||
|
name: str
|
||||||
|
authority: str
|
||||||
|
status: str
|
||||||
|
items: tuple[dict[str, Any], ...] = ()
|
||||||
|
reason: str | None = None
|
||||||
|
scan_ms: float | None = None
|
||||||
|
|
||||||
|
@property
|
||||||
|
def ok(self) -> bool:
|
||||||
|
return self.status == STATUS_OK
|
||||||
|
|
||||||
|
def to_dict(self) -> dict[str, Any]:
|
||||||
|
return {
|
||||||
|
"name": self.name,
|
||||||
|
"authority": self.authority,
|
||||||
|
"status": self.status,
|
||||||
|
"count": len(self.items),
|
||||||
|
"reason": self.reason,
|
||||||
|
"scan_ms": self.scan_ms,
|
||||||
|
"items": [dict(item) for item in self.items],
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class CollisionSignal:
|
||||||
|
"""A detected conflict between two ownership records."""
|
||||||
|
|
||||||
|
kind: str
|
||||||
|
message: str
|
||||||
|
severity: str = "warning"
|
||||||
|
issue_number: int | None = None
|
||||||
|
branch: str | None = None
|
||||||
|
worktree_path: str | None = None
|
||||||
|
session_ids: tuple[str, ...] = ()
|
||||||
|
|
||||||
|
def to_dict(self) -> dict[str, Any]:
|
||||||
|
return {
|
||||||
|
"kind": self.kind,
|
||||||
|
"severity": self.severity,
|
||||||
|
"message": self.message,
|
||||||
|
"issue_number": self.issue_number,
|
||||||
|
"branch": self.branch,
|
||||||
|
"worktree_path": self.worktree_path,
|
||||||
|
"session_ids": list(self.session_ids),
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class InventorySnapshot:
|
||||||
|
"""Versioned aggregate of every inventory section."""
|
||||||
|
|
||||||
|
generated_at: str
|
||||||
|
sections: tuple[InventorySection, ...]
|
||||||
|
collisions: tuple[CollisionSignal, ...] = ()
|
||||||
|
correlations: tuple[dict[str, Any], ...] = ()
|
||||||
|
schema_version: int = SCHEMA_VERSION
|
||||||
|
api_version: str = API_VERSION
|
||||||
|
scan_ms: float | None = None
|
||||||
|
_section_index: dict[str, InventorySection] = field(
|
||||||
|
default_factory=dict, repr=False, compare=False
|
||||||
|
)
|
||||||
|
|
||||||
|
def section(self, name: str) -> InventorySection | None:
|
||||||
|
return self._section_index.get(name)
|
||||||
|
|
||||||
|
@property
|
||||||
|
def degraded_sections(self) -> tuple[str, ...]:
|
||||||
|
return tuple(s.name for s in self.sections if not s.ok)
|
||||||
|
|
||||||
|
@property
|
||||||
|
def ownership_authority_complete(self) -> bool:
|
||||||
|
"""True only when every ownership-bearing section read cleanly.
|
||||||
|
|
||||||
|
While this is false the snapshot must not describe any work item as
|
||||||
|
unowned: a lease the reader could not load is not an absent lease.
|
||||||
|
"""
|
||||||
|
for name in OWNERSHIP_SECTIONS:
|
||||||
|
section = self._section_index.get(name)
|
||||||
|
if section is None or not section.ok:
|
||||||
|
return False
|
||||||
|
return True
|
||||||
|
|
||||||
|
@property
|
||||||
|
def status(self) -> str:
|
||||||
|
if all(s.ok for s in self.sections):
|
||||||
|
return STATUS_OK
|
||||||
|
return STATUS_DEGRADED
|
||||||
|
|
||||||
|
|
||||||
|
# ── redaction ────────────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
|
||||||
|
def redact_path(path: str | None) -> str | None:
|
||||||
|
"""Collapse an absolute path against ``$HOME`` for browser display."""
|
||||||
|
if not path:
|
||||||
|
return path
|
||||||
|
text = str(path)
|
||||||
|
home = os.path.expanduser("~")
|
||||||
|
if home and home != "/" and text.startswith(home):
|
||||||
|
return "~" + text[len(home) :]
|
||||||
|
return text
|
||||||
|
|
||||||
|
|
||||||
|
def redact_url(value: str | None) -> str | None:
|
||||||
|
"""Strip userinfo and query string from a URL."""
|
||||||
|
if not value:
|
||||||
|
return value
|
||||||
|
text = str(value)
|
||||||
|
try:
|
||||||
|
parsed = urlparse(text)
|
||||||
|
except ValueError:
|
||||||
|
return _REDACTED
|
||||||
|
if not parsed.scheme or not parsed.netloc:
|
||||||
|
return text
|
||||||
|
netloc = parsed.hostname or ""
|
||||||
|
if parsed.port:
|
||||||
|
netloc = f"{netloc}:{parsed.port}"
|
||||||
|
rebuilt = f"{parsed.scheme}://{netloc}{parsed.path}"
|
||||||
|
return rebuilt.rstrip("/") or rebuilt
|
||||||
|
|
||||||
|
|
||||||
|
def scrub(value: Any, *, key: str | None = None) -> Any:
|
||||||
|
"""Recursively drop credential-shaped values and redact paths/URLs.
|
||||||
|
|
||||||
|
Never raises: an unexpected object degrades to its ``repr`` rather than
|
||||||
|
propagating out of a read-only view.
|
||||||
|
"""
|
||||||
|
if key and _CREDENTIAL_KEY_RE.search(key):
|
||||||
|
return _REDACTED
|
||||||
|
if isinstance(value, dict):
|
||||||
|
return {str(k): scrub(v, key=str(k)) for k, v in value.items()}
|
||||||
|
if isinstance(value, (list, tuple)):
|
||||||
|
return [scrub(v, key=key) for v in value]
|
||||||
|
if isinstance(value, str):
|
||||||
|
if value.startswith(("http://", "https://")):
|
||||||
|
return redact_url(value)
|
||||||
|
if value.startswith("/") or value.startswith("~"):
|
||||||
|
return redact_path(value)
|
||||||
|
return value
|
||||||
|
if isinstance(value, (int, float, bool)) or value is None:
|
||||||
|
return value
|
||||||
|
return repr(value)
|
||||||
|
|
||||||
|
|
||||||
|
# ── control-plane database (read-only) ───────────────────────────────────────
|
||||||
|
|
||||||
|
|
||||||
|
def _open_readonly(db_path: str) -> sqlite3.Connection:
|
||||||
|
"""Open the control-plane DB without creating or migrating anything."""
|
||||||
|
conn = sqlite3.connect(f"file:{db_path}?mode=ro", uri=True, timeout=5)
|
||||||
|
conn.row_factory = sqlite3.Row
|
||||||
|
return conn
|
||||||
|
|
||||||
|
|
||||||
|
def _table_names(conn: sqlite3.Connection) -> set[str]:
|
||||||
|
rows = conn.execute(
|
||||||
|
"SELECT name FROM sqlite_master WHERE type = 'table'"
|
||||||
|
).fetchall()
|
||||||
|
return {str(row[0]) for row in rows}
|
||||||
|
|
||||||
|
|
||||||
|
def _load_cp_db_sections(
|
||||||
|
*,
|
||||||
|
db_path: str | None = None,
|
||||||
|
limit: int = 200,
|
||||||
|
) -> tuple[InventorySection, InventorySection]:
|
||||||
|
"""Return the ``sessions`` and ``leases`` sections from the #613 DB."""
|
||||||
|
path = (db_path or control_plane_db.default_db_path()).strip()
|
||||||
|
|
||||||
|
def _both_unavailable(reason: str) -> tuple[InventorySection, InventorySection]:
|
||||||
|
return (
|
||||||
|
InventorySection(
|
||||||
|
name="sessions",
|
||||||
|
authority=AUTHORITY_CONTROL_PLANE_DB,
|
||||||
|
status=STATUS_UNAVAILABLE,
|
||||||
|
reason=reason,
|
||||||
|
),
|
||||||
|
InventorySection(
|
||||||
|
name="leases",
|
||||||
|
authority=AUTHORITY_CONTROL_PLANE_DB,
|
||||||
|
status=STATUS_UNAVAILABLE,
|
||||||
|
reason=reason,
|
||||||
|
),
|
||||||
|
)
|
||||||
|
|
||||||
|
if not path:
|
||||||
|
return _both_unavailable("control-plane database path is not configured")
|
||||||
|
if not os.path.exists(path):
|
||||||
|
return _both_unavailable(
|
||||||
|
f"control-plane database not present at {redact_path(path)}; "
|
||||||
|
"no session or lease authority available"
|
||||||
|
)
|
||||||
|
|
||||||
|
started = time.perf_counter()
|
||||||
|
try:
|
||||||
|
conn = _open_readonly(path)
|
||||||
|
except sqlite3.Error as exc:
|
||||||
|
return _both_unavailable(f"control-plane database could not be opened: {exc}")
|
||||||
|
|
||||||
|
try:
|
||||||
|
tables = _table_names(conn)
|
||||||
|
if "sessions" not in tables or "leases" not in tables:
|
||||||
|
missing = sorted({"sessions", "leases"} - tables)
|
||||||
|
return _both_unavailable(
|
||||||
|
"control-plane database is missing required tables: "
|
||||||
|
+ ", ".join(missing)
|
||||||
|
)
|
||||||
|
|
||||||
|
session_rows = [
|
||||||
|
dict(row)
|
||||||
|
for row in conn.execute(
|
||||||
|
"SELECT session_id, role, profile, namespace, pid, started_at,"
|
||||||
|
" last_heartbeat_at, status FROM sessions"
|
||||||
|
" ORDER BY last_heartbeat_at DESC LIMIT ?",
|
||||||
|
(max(1, int(limit)),),
|
||||||
|
).fetchall()
|
||||||
|
]
|
||||||
|
|
||||||
|
has_work_items = "work_items" in tables
|
||||||
|
if has_work_items:
|
||||||
|
lease_sql = (
|
||||||
|
"SELECT l.lease_id, l.session_id, l.role, l.phase, l.status,"
|
||||||
|
" l.expires_at, w.remote, w.org, w.repo, w.kind AS work_kind,"
|
||||||
|
" w.number AS work_number, w.state AS work_state,"
|
||||||
|
" s.pid AS session_pid, s.profile AS session_profile,"
|
||||||
|
" s.namespace AS session_namespace, s.status AS session_status"
|
||||||
|
" FROM leases l"
|
||||||
|
" JOIN work_items w ON w.work_item_id = l.work_item_id"
|
||||||
|
" LEFT JOIN sessions s ON s.session_id = l.session_id"
|
||||||
|
" ORDER BY l.expires_at DESC LIMIT ?"
|
||||||
|
)
|
||||||
|
else:
|
||||||
|
lease_sql = (
|
||||||
|
"SELECT l.lease_id, l.session_id, l.role, l.phase, l.status,"
|
||||||
|
" l.expires_at FROM leases l"
|
||||||
|
" ORDER BY l.expires_at DESC LIMIT ?"
|
||||||
|
)
|
||||||
|
lease_rows = [
|
||||||
|
dict(row)
|
||||||
|
for row in conn.execute(lease_sql, (max(1, int(limit)),)).fetchall()
|
||||||
|
]
|
||||||
|
except sqlite3.Error as exc:
|
||||||
|
return _both_unavailable(f"control-plane database read failed: {exc}")
|
||||||
|
finally:
|
||||||
|
conn.close()
|
||||||
|
|
||||||
|
elapsed = (time.perf_counter() - started) * 1000.0
|
||||||
|
now = datetime.now(timezone.utc)
|
||||||
|
|
||||||
|
sessions = tuple(
|
||||||
|
scrub(
|
||||||
|
{
|
||||||
|
"session_id": row.get("session_id"),
|
||||||
|
"role": row.get("role"),
|
||||||
|
"profile": row.get("profile"),
|
||||||
|
"namespace": row.get("namespace"),
|
||||||
|
"pid": row.get("pid"),
|
||||||
|
"pid_alive": issue_lock_store.is_process_alive(row.get("pid")),
|
||||||
|
"started_at": row.get("started_at"),
|
||||||
|
"last_heartbeat_at": row.get("last_heartbeat_at"),
|
||||||
|
"status": row.get("status"),
|
||||||
|
}
|
||||||
|
)
|
||||||
|
for row in session_rows
|
||||||
|
)
|
||||||
|
|
||||||
|
leases = tuple(
|
||||||
|
scrub(
|
||||||
|
{
|
||||||
|
"lease_id": row.get("lease_id"),
|
||||||
|
"session_id": row.get("session_id"),
|
||||||
|
"role": row.get("role"),
|
||||||
|
"phase": row.get("phase"),
|
||||||
|
"status": row.get("status"),
|
||||||
|
"expires_at": row.get("expires_at"),
|
||||||
|
"expired": _is_expired(row.get("expires_at"), now=now),
|
||||||
|
"remote": row.get("remote"),
|
||||||
|
"org": row.get("org"),
|
||||||
|
"repo": row.get("repo"),
|
||||||
|
"work_kind": row.get("work_kind"),
|
||||||
|
"work_number": row.get("work_number"),
|
||||||
|
"work_state": row.get("work_state"),
|
||||||
|
"session_pid": row.get("session_pid"),
|
||||||
|
"session_profile": row.get("session_profile"),
|
||||||
|
"session_namespace": row.get("session_namespace"),
|
||||||
|
"session_status": row.get("session_status"),
|
||||||
|
}
|
||||||
|
)
|
||||||
|
for row in lease_rows
|
||||||
|
)
|
||||||
|
|
||||||
|
degraded_reason = (
|
||||||
|
None
|
||||||
|
if has_work_items
|
||||||
|
else "work_items table absent; lease rows carry no work linkage"
|
||||||
|
)
|
||||||
|
lease_status = STATUS_OK if has_work_items else STATUS_DEGRADED
|
||||||
|
|
||||||
|
return (
|
||||||
|
InventorySection(
|
||||||
|
name="sessions",
|
||||||
|
authority=AUTHORITY_CONTROL_PLANE_DB,
|
||||||
|
status=STATUS_OK,
|
||||||
|
items=sessions,
|
||||||
|
scan_ms=round(elapsed, 3),
|
||||||
|
),
|
||||||
|
InventorySection(
|
||||||
|
name="leases",
|
||||||
|
authority=AUTHORITY_CONTROL_PLANE_DB,
|
||||||
|
status=lease_status,
|
||||||
|
items=leases,
|
||||||
|
reason=degraded_reason,
|
||||||
|
scan_ms=round(elapsed, 3),
|
||||||
|
),
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def _is_expired(expires_at: str | None, *, now: datetime) -> bool | None:
|
||||||
|
if not expires_at:
|
||||||
|
return None
|
||||||
|
text = str(expires_at).strip().replace("Z", "+00:00")
|
||||||
|
try:
|
||||||
|
parsed = datetime.fromisoformat(text)
|
||||||
|
except ValueError:
|
||||||
|
return None
|
||||||
|
if parsed.tzinfo is None:
|
||||||
|
parsed = parsed.replace(tzinfo=timezone.utc)
|
||||||
|
return parsed <= now
|
||||||
|
|
||||||
|
|
||||||
|
# ── durable issue locks (filesystem) ─────────────────────────────────────────
|
||||||
|
|
||||||
|
|
||||||
|
def _load_locks_section(*, lock_dir: str | None = None) -> InventorySection:
|
||||||
|
started = time.perf_counter()
|
||||||
|
try:
|
||||||
|
paths = issue_lock_store.iter_lock_files(lock_dir)
|
||||||
|
except OSError as exc:
|
||||||
|
return InventorySection(
|
||||||
|
name="locks",
|
||||||
|
authority=AUTHORITY_FILESYSTEM,
|
||||||
|
status=STATUS_UNAVAILABLE,
|
||||||
|
reason=f"issue lock directory could not be listed: {exc}",
|
||||||
|
)
|
||||||
|
|
||||||
|
items: list[dict[str, Any]] = []
|
||||||
|
unreadable = 0
|
||||||
|
for path in paths:
|
||||||
|
try:
|
||||||
|
record = issue_lock_store.read_lock_file(path)
|
||||||
|
except (OSError, ValueError):
|
||||||
|
unreadable += 1
|
||||||
|
continue
|
||||||
|
if not record:
|
||||||
|
unreadable += 1
|
||||||
|
continue
|
||||||
|
try:
|
||||||
|
freshness = issue_lock_store.assess_lock_freshness(record)
|
||||||
|
except Exception: # noqa: BLE001 — a read-only view never raises
|
||||||
|
freshness = {"status": "unknown", "live": False, "stale": False}
|
||||||
|
claimant = record.get("claimant") or (
|
||||||
|
(record.get("work_lease") or {}).get("claimant") or {}
|
||||||
|
)
|
||||||
|
items.append(
|
||||||
|
scrub(
|
||||||
|
{
|
||||||
|
"issue_number": record.get("issue_number"),
|
||||||
|
"branch_name": record.get("branch_name"),
|
||||||
|
"remote": record.get("remote"),
|
||||||
|
"org": record.get("org"),
|
||||||
|
"repo": record.get("repo"),
|
||||||
|
"worktree_path": record.get("worktree_path"),
|
||||||
|
"pid": record.get("session_pid") or record.get("pid"),
|
||||||
|
"pid_alive": issue_lock_store.is_process_alive(
|
||||||
|
record.get("session_pid") or record.get("pid")
|
||||||
|
),
|
||||||
|
"claimant_username": (claimant or {}).get("username"),
|
||||||
|
"claimant_profile": (claimant or {}).get("profile"),
|
||||||
|
"lock_generation": record.get("lock_generation"),
|
||||||
|
"freshness_status": freshness.get("status"),
|
||||||
|
"live": bool(freshness.get("live")),
|
||||||
|
"stale": bool(freshness.get("stale")),
|
||||||
|
"freshness_reason": freshness.get("reason"),
|
||||||
|
"lock_path": record.get("lock_file_path") or path,
|
||||||
|
}
|
||||||
|
)
|
||||||
|
)
|
||||||
|
|
||||||
|
elapsed = (time.perf_counter() - started) * 1000.0
|
||||||
|
reason = (
|
||||||
|
f"{unreadable} lock file(s) were unreadable and are not represented"
|
||||||
|
if unreadable
|
||||||
|
else None
|
||||||
|
)
|
||||||
|
return InventorySection(
|
||||||
|
name="locks",
|
||||||
|
authority=AUTHORITY_FILESYSTEM,
|
||||||
|
status=STATUS_DEGRADED if unreadable else STATUS_OK,
|
||||||
|
items=tuple(items),
|
||||||
|
reason=reason,
|
||||||
|
scan_ms=round(elapsed, 3),
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
# ── worktrees (filesystem, via the #432 scanner) ─────────────────────────────
|
||||||
|
|
||||||
|
|
||||||
|
def _load_worktrees_section(
|
||||||
|
*, load_hygiene: Callable[[], Any] | None = None
|
||||||
|
) -> InventorySection:
|
||||||
|
started = time.perf_counter()
|
||||||
|
try:
|
||||||
|
loader = load_hygiene
|
||||||
|
if loader is None:
|
||||||
|
from webui.worktree_scanner import load_hygiene_snapshot
|
||||||
|
|
||||||
|
loader = load_hygiene_snapshot
|
||||||
|
snapshot = loader()
|
||||||
|
except Exception as exc: # noqa: BLE001 — fail soft, never fail the request
|
||||||
|
return InventorySection(
|
||||||
|
name="worktrees",
|
||||||
|
authority=AUTHORITY_FILESYSTEM,
|
||||||
|
status=STATUS_UNAVAILABLE,
|
||||||
|
reason=f"worktree scan failed: {exc}",
|
||||||
|
)
|
||||||
|
|
||||||
|
items = tuple(
|
||||||
|
scrub(
|
||||||
|
{
|
||||||
|
"rel_path": entry.rel_path,
|
||||||
|
"folder_name": entry.folder_name,
|
||||||
|
"classification": entry.classification,
|
||||||
|
"branch": entry.branch,
|
||||||
|
"head_sha": entry.head_sha,
|
||||||
|
"dirty_tracked": entry.dirty_tracked,
|
||||||
|
"dirty_untracked": entry.dirty_untracked,
|
||||||
|
"detached": entry.detached,
|
||||||
|
"registered_worktree": entry.registered_worktree,
|
||||||
|
"notes": entry.notes,
|
||||||
|
}
|
||||||
|
)
|
||||||
|
for entry in snapshot.entries
|
||||||
|
)
|
||||||
|
scan_error = getattr(snapshot, "scan_error", None)
|
||||||
|
elapsed = (time.perf_counter() - started) * 1000.0
|
||||||
|
return InventorySection(
|
||||||
|
name="worktrees",
|
||||||
|
authority=AUTHORITY_FILESYSTEM,
|
||||||
|
status=STATUS_DEGRADED if scan_error else STATUS_OK,
|
||||||
|
items=items,
|
||||||
|
reason=scan_error,
|
||||||
|
scan_ms=round(elapsed, 3),
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
# ── namespaces / capability summary ──────────────────────────────────────────
|
||||||
|
|
||||||
|
|
||||||
|
def _load_namespaces_section() -> InventorySection:
|
||||||
|
started = time.perf_counter()
|
||||||
|
try:
|
||||||
|
from gitea_auth import get_profile
|
||||||
|
|
||||||
|
profile = get_profile() or {}
|
||||||
|
except Exception as exc: # noqa: BLE001
|
||||||
|
return InventorySection(
|
||||||
|
name="namespaces",
|
||||||
|
authority=AUTHORITY_FILESYSTEM,
|
||||||
|
status=STATUS_UNAVAILABLE,
|
||||||
|
reason=f"active profile could not be resolved: {exc}",
|
||||||
|
)
|
||||||
|
|
||||||
|
allowed = list(profile.get("allowed_operations") or [])
|
||||||
|
forbidden = list(profile.get("forbidden_operations") or [])
|
||||||
|
profile_name = str(profile.get("profile_name") or "")
|
||||||
|
|
||||||
|
namespace = None
|
||||||
|
try:
|
||||||
|
import role_namespace_gate
|
||||||
|
|
||||||
|
namespace = role_namespace_gate.infer_mcp_namespace(profile_name)
|
||||||
|
except Exception: # noqa: BLE001 — namespace inference is advisory
|
||||||
|
namespace = None
|
||||||
|
|
||||||
|
item = scrub(
|
||||||
|
{
|
||||||
|
"profile_name": profile_name,
|
||||||
|
"role": profile.get("role"),
|
||||||
|
"mcp_namespace": namespace,
|
||||||
|
"allowed_operations": sorted(allowed),
|
||||||
|
"forbidden_operations": sorted(forbidden),
|
||||||
|
"capability_summary": {
|
||||||
|
"can_author": "gitea.pr.create" in allowed,
|
||||||
|
"can_review": "gitea.pr.approve" in allowed,
|
||||||
|
"can_merge": "gitea.pr.merge" in allowed,
|
||||||
|
"can_close_pr": "gitea.pr.close" in allowed,
|
||||||
|
},
|
||||||
|
"active": True,
|
||||||
|
}
|
||||||
|
)
|
||||||
|
elapsed = (time.perf_counter() - started) * 1000.0
|
||||||
|
return InventorySection(
|
||||||
|
name="namespaces",
|
||||||
|
authority=AUTHORITY_FILESYSTEM,
|
||||||
|
status=STATUS_OK,
|
||||||
|
items=(item,),
|
||||||
|
reason=(
|
||||||
|
"only the profile serving this web process is observable; other "
|
||||||
|
"namespaces are not enumerable from here"
|
||||||
|
),
|
||||||
|
scan_ms=round(elapsed, 3),
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
# ── correlation and collision detection ──────────────────────────────────────
|
||||||
|
|
||||||
|
|
||||||
|
def _issue_from_branch(branch: str | None) -> int | None:
|
||||||
|
match = re.search(r"issue-(\d+)", str(branch or ""), re.IGNORECASE)
|
||||||
|
return int(match.group(1)) if match else None
|
||||||
|
|
||||||
|
|
||||||
|
def correlate(
|
||||||
|
*,
|
||||||
|
leases: InventorySection,
|
||||||
|
locks: InventorySection,
|
||||||
|
worktrees: InventorySection,
|
||||||
|
sessions: InventorySection,
|
||||||
|
) -> tuple[tuple[dict[str, Any], ...], tuple[CollisionSignal, ...]]:
|
||||||
|
"""Join lease owner ↔ lock ↔ worktree ↔ namespace where evidence allows.
|
||||||
|
|
||||||
|
Correlation rows are emitted from whatever sections did load. Collision
|
||||||
|
signals are only emitted from sections that are ``ok``: a conflict inferred
|
||||||
|
from a partially-read source would be a false accusation.
|
||||||
|
"""
|
||||||
|
correlations: list[dict[str, Any]] = []
|
||||||
|
collisions: list[CollisionSignal] = []
|
||||||
|
|
||||||
|
worktree_by_branch: dict[str, dict[str, Any]] = {}
|
||||||
|
for entry in worktrees.items:
|
||||||
|
branch = (entry.get("branch") or "").strip()
|
||||||
|
if branch:
|
||||||
|
worktree_by_branch.setdefault(branch, entry)
|
||||||
|
|
||||||
|
session_by_id = {
|
||||||
|
str(s.get("session_id")): s for s in sessions.items if s.get("session_id")
|
||||||
|
}
|
||||||
|
|
||||||
|
# Lock-centred rows: a durable lock names an issue, a branch, and a worktree.
|
||||||
|
for lock in locks.items:
|
||||||
|
branch = (lock.get("branch_name") or "").strip()
|
||||||
|
worktree = worktree_by_branch.get(branch)
|
||||||
|
matching_leases = [
|
||||||
|
lease
|
||||||
|
for lease in leases.items
|
||||||
|
if lease.get("work_kind") == "issue"
|
||||||
|
and lease.get("work_number") == lock.get("issue_number")
|
||||||
|
]
|
||||||
|
correlations.append(
|
||||||
|
{
|
||||||
|
"issue_number": lock.get("issue_number"),
|
||||||
|
"branch": branch or None,
|
||||||
|
"lock_live": bool(lock.get("live")),
|
||||||
|
"lock_claimant": lock.get("claimant_profile"),
|
||||||
|
"lock_pid": lock.get("pid"),
|
||||||
|
"lock_pid_alive": lock.get("pid_alive"),
|
||||||
|
"worktree_rel_path": (worktree or {}).get("rel_path"),
|
||||||
|
"worktree_classification": (worktree or {}).get("classification"),
|
||||||
|
"worktree_registered": (worktree or {}).get("registered_worktree"),
|
||||||
|
"lease_ids": [
|
||||||
|
lease.get("lease_id")
|
||||||
|
for lease in matching_leases
|
||||||
|
if lease.get("lease_id")
|
||||||
|
],
|
||||||
|
"lease_sessions": [
|
||||||
|
lease.get("session_id")
|
||||||
|
for lease in matching_leases
|
||||||
|
if lease.get("session_id")
|
||||||
|
],
|
||||||
|
}
|
||||||
|
)
|
||||||
|
|
||||||
|
if locks.ok and worktrees.ok:
|
||||||
|
# A claim whose lease window is still open but has no registered
|
||||||
|
# worktree is an anomaly regardless of whether its pid is alive; a
|
||||||
|
# fully time-expired lease is on its way out and is not flagged.
|
||||||
|
if (
|
||||||
|
lock.get("freshness_status") != "expired"
|
||||||
|
and branch
|
||||||
|
and worktree is None
|
||||||
|
):
|
||||||
|
collisions.append(
|
||||||
|
CollisionSignal(
|
||||||
|
kind="lock-without-worktree",
|
||||||
|
severity="warning",
|
||||||
|
issue_number=lock.get("issue_number"),
|
||||||
|
branch=branch,
|
||||||
|
worktree_path=lock.get("worktree_path"),
|
||||||
|
message=(
|
||||||
|
f"Live lock on issue #{lock.get('issue_number')} names "
|
||||||
|
f"branch {branch!r} but no registered worktree carries "
|
||||||
|
"that branch (#404)"
|
||||||
|
),
|
||||||
|
)
|
||||||
|
)
|
||||||
|
|
||||||
|
if locks.ok:
|
||||||
|
# A lock whose recorded pid is gone is held by nobody: a clean #753
|
||||||
|
# dead-session recovery candidate. Subclassify by the lease window,
|
||||||
|
# because the two cases need different operator urgency. When the
|
||||||
|
# window is still open the lock would read as live to a naive
|
||||||
|
# timestamp check even though the owner is dead — the more dangerous
|
||||||
|
# case — so it is flagged distinctly from a fully time-expired lease.
|
||||||
|
if lock.get("pid_alive") is False and lock.get("stale"):
|
||||||
|
if lock.get("freshness_status") == "expired":
|
||||||
|
collisions.append(
|
||||||
|
CollisionSignal(
|
||||||
|
kind="stale-lock-dead-owner",
|
||||||
|
severity="warning",
|
||||||
|
issue_number=lock.get("issue_number"),
|
||||||
|
branch=branch or None,
|
||||||
|
message=(
|
||||||
|
f"Lock on issue #{lock.get('issue_number')} is stale "
|
||||||
|
f"and its recorded pid {lock.get('pid')} is not running "
|
||||||
|
"(#753 dead-session recovery candidate)"
|
||||||
|
),
|
||||||
|
)
|
||||||
|
)
|
||||||
|
else:
|
||||||
|
collisions.append(
|
||||||
|
CollisionSignal(
|
||||||
|
kind="live-lock-dead-owner",
|
||||||
|
severity="warning",
|
||||||
|
issue_number=lock.get("issue_number"),
|
||||||
|
branch=branch or None,
|
||||||
|
message=(
|
||||||
|
f"Lock on issue #{lock.get('issue_number')} has an "
|
||||||
|
"unexpired lease but its recorded pid "
|
||||||
|
f"{lock.get('pid')} is not running; it would read as "
|
||||||
|
"live to a timestamp check (#753 dead-session recovery "
|
||||||
|
"candidate)"
|
||||||
|
),
|
||||||
|
)
|
||||||
|
)
|
||||||
|
# The #635 trap: the lease has expired but the recorded pid is a
|
||||||
|
# still-running daemon, so neither dead-pid reclaim nor exact-owner
|
||||||
|
# renewal applies. This is the collision an operator must see.
|
||||||
|
elif (
|
||||||
|
lock.get("freshness_status") == "expired"
|
||||||
|
and lock.get("pid_alive") is True
|
||||||
|
):
|
||||||
|
collisions.append(
|
||||||
|
CollisionSignal(
|
||||||
|
kind="expired-lock-live-owner",
|
||||||
|
severity="error",
|
||||||
|
issue_number=lock.get("issue_number"),
|
||||||
|
branch=branch or None,
|
||||||
|
message=(
|
||||||
|
f"Lock on issue #{lock.get('issue_number')} has an expired "
|
||||||
|
f"lease but its recorded pid {lock.get('pid')} is still "
|
||||||
|
"running (daemon-pid deadlock; needs an operator decision, "
|
||||||
|
"#635/#760)"
|
||||||
|
),
|
||||||
|
)
|
||||||
|
)
|
||||||
|
|
||||||
|
# Two live locks on one branch, or two active leases on one work item.
|
||||||
|
if locks.ok:
|
||||||
|
by_branch: dict[str, list[dict[str, Any]]] = {}
|
||||||
|
for lock in locks.items:
|
||||||
|
if not lock.get("live"):
|
||||||
|
continue
|
||||||
|
branch = (lock.get("branch_name") or "").strip()
|
||||||
|
if branch:
|
||||||
|
by_branch.setdefault(branch, []).append(lock)
|
||||||
|
for branch, entries in sorted(by_branch.items()):
|
||||||
|
if len(entries) > 1:
|
||||||
|
collisions.append(
|
||||||
|
CollisionSignal(
|
||||||
|
kind="duplicate-live-lock",
|
||||||
|
severity="error",
|
||||||
|
branch=branch,
|
||||||
|
message=(
|
||||||
|
f"{len(entries)} live locks name branch {branch!r}: "
|
||||||
|
"issues "
|
||||||
|
+ ", ".join(
|
||||||
|
f"#{e.get('issue_number')}" for e in entries
|
||||||
|
)
|
||||||
|
),
|
||||||
|
)
|
||||||
|
)
|
||||||
|
|
||||||
|
if leases.ok:
|
||||||
|
by_work: dict[tuple[str, int], list[dict[str, Any]]] = {}
|
||||||
|
for lease in leases.items:
|
||||||
|
if str(lease.get("status") or "").lower() != "active":
|
||||||
|
continue
|
||||||
|
kind = str(lease.get("work_kind") or "").strip().lower()
|
||||||
|
number = lease.get("work_number")
|
||||||
|
if not kind or number is None:
|
||||||
|
continue
|
||||||
|
by_work.setdefault((kind, int(number)), []).append(lease)
|
||||||
|
for (kind, number), entries in sorted(by_work.items()):
|
||||||
|
sessions_held = {
|
||||||
|
str(e.get("session_id")) for e in entries if e.get("session_id")
|
||||||
|
}
|
||||||
|
if len(sessions_held) > 1:
|
||||||
|
collisions.append(
|
||||||
|
CollisionSignal(
|
||||||
|
kind="concurrent-active-lease",
|
||||||
|
severity="error",
|
||||||
|
issue_number=number if kind == "issue" else None,
|
||||||
|
session_ids=tuple(sorted(sessions_held)),
|
||||||
|
message=(
|
||||||
|
f"{len(sessions_held)} sessions hold an active lease on "
|
||||||
|
f"{kind} #{number}"
|
||||||
|
),
|
||||||
|
)
|
||||||
|
)
|
||||||
|
for entry in entries:
|
||||||
|
if entry.get("expired") is True:
|
||||||
|
collisions.append(
|
||||||
|
CollisionSignal(
|
||||||
|
kind="active-lease-past-expiry",
|
||||||
|
severity="warning",
|
||||||
|
issue_number=number if kind == "issue" else None,
|
||||||
|
session_ids=(
|
||||||
|
(str(entry.get("session_id")),)
|
||||||
|
if entry.get("session_id")
|
||||||
|
else ()
|
||||||
|
),
|
||||||
|
message=(
|
||||||
|
f"Lease {entry.get('lease_id')} on {kind} #{number} "
|
||||||
|
"is still marked active past its expiry"
|
||||||
|
),
|
||||||
|
)
|
||||||
|
)
|
||||||
|
|
||||||
|
# A lease whose owning session is gone is an orphan, not free work.
|
||||||
|
if leases.ok and sessions.ok:
|
||||||
|
for lease in leases.items:
|
||||||
|
if str(lease.get("status") or "").lower() != "active":
|
||||||
|
continue
|
||||||
|
session_id = str(lease.get("session_id") or "")
|
||||||
|
if session_id and session_id not in session_by_id:
|
||||||
|
collisions.append(
|
||||||
|
CollisionSignal(
|
||||||
|
kind="orphan-lease",
|
||||||
|
severity="error",
|
||||||
|
session_ids=(session_id,),
|
||||||
|
message=(
|
||||||
|
f"Active lease {lease.get('lease_id')} names session "
|
||||||
|
f"{session_id}, which has no session record"
|
||||||
|
),
|
||||||
|
)
|
||||||
|
)
|
||||||
|
|
||||||
|
return tuple(correlations), tuple(collisions)
|
||||||
|
|
||||||
|
|
||||||
|
# ── snapshot assembly ────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
|
||||||
|
def load_inventory_snapshot(
|
||||||
|
*,
|
||||||
|
db_path: str | None = None,
|
||||||
|
lock_dir: str | None = None,
|
||||||
|
load_hygiene: Callable[[], Any] | None = None,
|
||||||
|
include: tuple[str, ...] | None = None,
|
||||||
|
) -> InventorySnapshot:
|
||||||
|
"""Build the unified inventory snapshot.
|
||||||
|
|
||||||
|
Every section is loaded independently and fails soft. *include* restricts
|
||||||
|
the sections that are scanned; omitted sections are simply absent rather
|
||||||
|
than reported as empty, so a resource-split request cannot be mistaken for
|
||||||
|
a whole-inventory answer.
|
||||||
|
"""
|
||||||
|
started = time.perf_counter()
|
||||||
|
wanted = tuple(include) if include else SECTION_NAMES
|
||||||
|
|
||||||
|
sections: list[InventorySection] = []
|
||||||
|
sessions_section: InventorySection | None = None
|
||||||
|
leases_section: InventorySection | None = None
|
||||||
|
|
||||||
|
if "sessions" in wanted or "leases" in wanted:
|
||||||
|
sessions_section, leases_section = _load_cp_db_sections(db_path=db_path)
|
||||||
|
if "sessions" in wanted:
|
||||||
|
sections.append(sessions_section)
|
||||||
|
if "leases" in wanted:
|
||||||
|
sections.append(leases_section)
|
||||||
|
|
||||||
|
locks_section = (
|
||||||
|
_load_locks_section(lock_dir=lock_dir)
|
||||||
|
if "locks" in wanted
|
||||||
|
else _empty_section("locks", AUTHORITY_FILESYSTEM)
|
||||||
|
)
|
||||||
|
if "locks" in wanted:
|
||||||
|
sections.append(locks_section)
|
||||||
|
|
||||||
|
worktrees_section = (
|
||||||
|
_load_worktrees_section(load_hygiene=load_hygiene)
|
||||||
|
if "worktrees" in wanted
|
||||||
|
else _empty_section("worktrees", AUTHORITY_FILESYSTEM)
|
||||||
|
)
|
||||||
|
if "worktrees" in wanted:
|
||||||
|
sections.append(worktrees_section)
|
||||||
|
|
||||||
|
if "namespaces" in wanted:
|
||||||
|
sections.append(_load_namespaces_section())
|
||||||
|
|
||||||
|
correlations, collisions = correlate(
|
||||||
|
leases=leases_section or _empty_section("leases", AUTHORITY_CONTROL_PLANE_DB),
|
||||||
|
locks=locks_section,
|
||||||
|
worktrees=worktrees_section,
|
||||||
|
sessions=sessions_section
|
||||||
|
or _empty_section("sessions", AUTHORITY_CONTROL_PLANE_DB),
|
||||||
|
)
|
||||||
|
|
||||||
|
elapsed = (time.perf_counter() - started) * 1000.0
|
||||||
|
index = {section.name: section for section in sections}
|
||||||
|
return InventorySnapshot(
|
||||||
|
generated_at=datetime.now(timezone.utc).isoformat(),
|
||||||
|
sections=tuple(sections),
|
||||||
|
collisions=collisions,
|
||||||
|
correlations=correlations,
|
||||||
|
scan_ms=round(elapsed, 3),
|
||||||
|
_section_index=index,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def _empty_section(name: str, authority: str) -> InventorySection:
|
||||||
|
"""A section that was not requested — never a claim that it is empty."""
|
||||||
|
return InventorySection(
|
||||||
|
name=name,
|
||||||
|
authority=authority,
|
||||||
|
status=STATUS_UNAVAILABLE,
|
||||||
|
reason="section not requested in this scan",
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def snapshot_to_dict(snapshot: InventorySnapshot) -> dict[str, Any]:
|
||||||
|
"""Serialize the snapshot for the versioned API."""
|
||||||
|
return {
|
||||||
|
"api_version": snapshot.api_version,
|
||||||
|
"schema_version": snapshot.schema_version,
|
||||||
|
"generated_at": snapshot.generated_at,
|
||||||
|
"status": snapshot.status,
|
||||||
|
"scan_ms": snapshot.scan_ms,
|
||||||
|
"ownership_authority_complete": snapshot.ownership_authority_complete,
|
||||||
|
"ownership_note": (
|
||||||
|
"Every ownership source read cleanly; an item absent from leases "
|
||||||
|
"and locks is genuinely unclaimed."
|
||||||
|
if snapshot.ownership_authority_complete
|
||||||
|
else "One or more ownership sources are degraded; nothing in this "
|
||||||
|
"snapshot may be treated as unowned. Collisions are reported only "
|
||||||
|
"from sections that read cleanly."
|
||||||
|
),
|
||||||
|
"degraded_sections": list(snapshot.degraded_sections),
|
||||||
|
"field_authority": {
|
||||||
|
"sessions": AUTHORITY_CONTROL_PLANE_DB,
|
||||||
|
"leases": AUTHORITY_CONTROL_PLANE_DB,
|
||||||
|
"locks": AUTHORITY_FILESYSTEM,
|
||||||
|
"worktrees": AUTHORITY_FILESYSTEM,
|
||||||
|
"namespaces": AUTHORITY_FILESYSTEM,
|
||||||
|
},
|
||||||
|
"sections": {section.name: section.to_dict() for section in snapshot.sections},
|
||||||
|
"correlations": [dict(row) for row in snapshot.correlations],
|
||||||
|
"collisions": [signal.to_dict() for signal in snapshot.collisions],
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user