Compare commits
20
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
6a636c58e7 | ||
|
|
9301739910 | ||
|
|
d2fe0110a0 | ||
|
|
b9ba43a5bf | ||
|
|
a1e5a4af8c | ||
|
|
188e83c4d6 | ||
|
|
db5ed6042b | ||
|
|
15c75d2225 | ||
|
|
2d95e0fcc6 | ||
|
|
8ba1c5b87c | ||
|
|
a20975688d | ||
|
|
25bc2a3291 | ||
|
|
f1e4809930 | ||
|
|
c040bd4674 | ||
|
|
dc1d0e045f | ||
|
|
64b6eb5d54 | ||
|
|
f21f81f9b5 | ||
|
|
badc4e636b | ||
|
|
08061b7b8a | ||
|
|
243f52dc79 |
+13
-1
@@ -163,7 +163,19 @@ _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", "stale_dead_process", "stale_missing_worktree"})
|
_STALE_STATUSES = frozenset(
|
||||||
|
{
|
||||||
|
"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:
|
||||||
|
|||||||
@@ -46,6 +46,17 @@ _FIELD_RE = re.compile(
|
|||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def is_known_cth_type(value: str | None) -> bool:
|
||||||
|
"""True when *value* is a declared member of the :data:`CTH_TYPES` contract.
|
||||||
|
|
||||||
|
``CTH_TYPES`` is the single authority for what a CTH type may be. The
|
||||||
|
heading a comment carries is free text, so a *read* path that turns a parsed
|
||||||
|
type into something durable — a serialized field, a routing decision — must
|
||||||
|
check membership here rather than trust the parse or keep a list of its own.
|
||||||
|
"""
|
||||||
|
return (value or "").strip() in CTH_TYPES
|
||||||
|
|
||||||
|
|
||||||
def format_cth_body(
|
def format_cth_body(
|
||||||
*,
|
*,
|
||||||
cth_type: str,
|
cth_type: str,
|
||||||
@@ -60,7 +71,7 @@ def format_cth_body(
|
|||||||
) -> str:
|
) -> str:
|
||||||
"""Render a canonical CTH comment body."""
|
"""Render a canonical CTH comment body."""
|
||||||
normalized_type = (cth_type or "").strip()
|
normalized_type = (cth_type or "").strip()
|
||||||
if normalized_type not in CTH_TYPES:
|
if not is_known_cth_type(normalized_type):
|
||||||
raise ValueError(
|
raise ValueError(
|
||||||
f"unknown CTH type '{cth_type}'; expected one of {sorted(CTH_TYPES)}"
|
f"unknown CTH type '{cth_type}'; expected one of {sorted(CTH_TYPES)}"
|
||||||
)
|
)
|
||||||
@@ -101,6 +112,12 @@ def parse_cth_comment(body: str) -> dict[str, Any] | None:
|
|||||||
fields[key] = match.group(2).strip()
|
fields[key] = match.group(2).strip()
|
||||||
return {
|
return {
|
||||||
"cth_type": cth_type,
|
"cth_type": cth_type,
|
||||||
|
# The heading capture is unconstrained free text, so the parse states
|
||||||
|
# whether it satisfies the CTH_TYPES contract instead of leaving every
|
||||||
|
# reader to decide (or forget). Parsing stays total — an unknown type is
|
||||||
|
# still parsed and reported, never raised on — but a reader that turns
|
||||||
|
# the type into a durable value can now tell the two apart.
|
||||||
|
"cth_type_known": is_known_cth_type(cth_type),
|
||||||
"fields": fields,
|
"fields": fields,
|
||||||
"raw_body": text,
|
"raw_body": text,
|
||||||
}
|
}
|
||||||
@@ -119,7 +136,7 @@ def assess_cth_comment(body: str) -> dict[str, Any]:
|
|||||||
}
|
}
|
||||||
|
|
||||||
cth_type = parsed.get("cth_type") or ""
|
cth_type = parsed.get("cth_type") or ""
|
||||||
if cth_type not in CTH_TYPES:
|
if not is_known_cth_type(cth_type):
|
||||||
reasons.append(
|
reasons.append(
|
||||||
f"unknown CTH type '{cth_type}'; expected one of {sorted(CTH_TYPES)}"
|
f"unknown CTH type '{cth_type}'; expected one of {sorted(CTH_TYPES)}"
|
||||||
)
|
)
|
||||||
|
|||||||
@@ -100,6 +100,7 @@ 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`
|
||||||
|
|||||||
@@ -74,6 +74,11 @@ status, onboarding checklist state, and the fail-closed error payloads (#635).
|
|||||||
| `/api/actions/{id}/preview` | Mutation ledger preview (GET, read-only) |
|
| `/api/actions/{id}/preview` | Mutation ledger preview (GET, read-only) |
|
||||||
| `/leases` | Lease and collision visibility (#433) |
|
| `/leases` | Lease and collision visibility (#433) |
|
||||||
| `/api/leases` | JSON lease/collision export |
|
| `/api/leases` | JSON lease/collision export |
|
||||||
|
| `/sessions` | Phase 1 shell stub — session inventory (backed by #636) |
|
||||||
|
| `/inventory` | Phase 1 shell stub — unified inventory (backed by #636) |
|
||||||
|
| `/timeline` | Phase 1 shell stub — workflow event timeline |
|
||||||
|
| `/policy` | Phase 1 shell stub — capability/role policy placeholder |
|
||||||
|
| `/insights` | Phase 1 shell stub — operational insights placeholder |
|
||||||
|
|
||||||
Most routes are GET-only. POST/PUT/PATCH/DELETE return `405` with
|
Most routes are GET-only. POST/PUT/PATCH/DELETE return `405` with
|
||||||
`read-only-mvp`, except `/audit` and `/api/audit` which accept POST for
|
`read-only-mvp`, except `/audit` and `/api/audit` which accept POST for
|
||||||
@@ -233,6 +238,26 @@ 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.
|
||||||
|
|
||||||
|
## Application shell — Phase 1 (#638)
|
||||||
|
|
||||||
|
The console shell (`webui/layout.py`) renders a grouped navigation driven by a
|
||||||
|
single nav-config module, `webui/nav.py`. Nav groups follow the epic #631
|
||||||
|
Phase 1 information architecture: **Health, Traffic, Runtime/Sessions,
|
||||||
|
Projects, Inventory, Timeline, Policy** (placeholder), and **Insights**
|
||||||
|
(placeholder). Live views and Phase 1 placeholders (`stub`) are declared in one
|
||||||
|
place so the layout and the route table cannot drift.
|
||||||
|
|
||||||
|
The header carries two read-only status badges — an **environment** badge
|
||||||
|
(`local` for loopback binds, `remote` otherwise, derived from `WEBUI_HOST`) and
|
||||||
|
a **mode: read-only** badge — plus a **Docs** link to this document. No
|
||||||
|
privileged action controls are present in the Phase 1 shell.
|
||||||
|
|
||||||
|
Not-yet-implemented surfaces (`/sessions`, `/inventory`, `/timeline`,
|
||||||
|
`/policy`, `/insights`) resolve to graceful read-only stub pages instead of
|
||||||
|
404s; their backing views land in later child issues of #631 (the inventory
|
||||||
|
surfaces are backed by #636). Mutating methods on stub routes still fail closed
|
||||||
|
with `read-only-mvp`.
|
||||||
|
|
||||||
## Deployment boundary (#435)
|
## Deployment boundary (#435)
|
||||||
|
|
||||||
MVP serves on loopback by default. Binding `0.0.0.0` or `::` is **refused**
|
MVP serves on loopback by default. Binding `0.0.0.0` or `::` is **refused**
|
||||||
@@ -292,6 +317,108 @@ 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.
|
||||||
|
|
||||||
|
## Workflow-event timeline (#637)
|
||||||
|
|
||||||
|
`GET /api/v1/timeline` is a read-only, versioned aggregation of workflow
|
||||||
|
events from every available source into one normalised, filterable stream. It
|
||||||
|
is the model layer for the Phase 1 timeline console view (a later child issue
|
||||||
|
of #631); this issue ships the schema, adapters, and read API only.
|
||||||
|
|
||||||
|
### Schema (versioned)
|
||||||
|
|
||||||
|
`webui/timeline.py` declares `TIMELINE_SCHEMA_VERSION` (currently `1`) and the
|
||||||
|
frozen `WorkflowEvent` record. Every response carries `schema_version` so a
|
||||||
|
consumer can branch on shape. One event:
|
||||||
|
|
||||||
|
```json
|
||||||
|
{
|
||||||
|
"source": "control_plane",
|
||||||
|
"event_type": "lease.renew",
|
||||||
|
"event_key": "cp:1421",
|
||||||
|
"timestamp": "2026-07-23T02:00:00Z",
|
||||||
|
"actor": null,
|
||||||
|
"role": null,
|
||||||
|
"issue_number": 637,
|
||||||
|
"pr_number": null,
|
||||||
|
"session_id": null,
|
||||||
|
"tool_name": null,
|
||||||
|
"decision": null,
|
||||||
|
"message": "lease renewed",
|
||||||
|
"correlation_id": "issue#637",
|
||||||
|
"evidence_refs": [],
|
||||||
|
"sensitive": true
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
`event_key` is stable and unique per source (`cp:<event_id>`,
|
||||||
|
`cth:<kind>:<number>:<comment_id>`), so pagination and dedup are deterministic.
|
||||||
|
|
||||||
|
### Sources and field authority
|
||||||
|
|
||||||
|
| Source | Adapter | Authority |
|
||||||
|
|---|---|---|
|
||||||
|
| Control-plane `events` ⋈ `work_items` | `adapt_cp_events` | `event_type`, `message`, `timestamp`, issue/PR scope come from the CP database, read through a `mode=ro` URI (never creates the DB or runs migrations) |
|
||||||
|
| Gitea Canonical Thread Handoff comments | `adapt_cth_comments` | `actor`, `role` (next owner), `decision`, `evidence_refs`, `timestamp` come from the parsed CTH comment body (`canonical_thread_handoff`) |
|
||||||
|
|
||||||
|
Handoff comments are thread-scoped: they are only read when the request filters
|
||||||
|
by a single `issue` or `pr`. Otherwise the handoff source reports `not run`
|
||||||
|
with a reason — it is never rendered as empty-and-healthy. Each source degrades
|
||||||
|
independently: an unavailable control-plane DB or a failed comment fetch is a
|
||||||
|
`sources[]` entry with `ok:false` and a `reason`, never a dropped timeline.
|
||||||
|
|
||||||
|
### Query parameters
|
||||||
|
|
||||||
|
`issue`, `pr`, `session` (conjunctive filters); `limit` (default 50, max 500)
|
||||||
|
and `offset` for pagination; `remote`, `org`, `repo` to override the default
|
||||||
|
registry-project scope. Events sort ascending by
|
||||||
|
`(timestamp, source_rank, event_key)`; missing timestamps sort last.
|
||||||
|
|
||||||
|
### Filter authority, and refusing what cannot be answered
|
||||||
|
|
||||||
|
A filter dimension is only meaningful for a source whose records carry it.
|
||||||
|
Each source declares its own support in `_SOURCE_FILTER_SUPPORT` and reports it
|
||||||
|
per response as `supported_filters` / `unsupported_filters`:
|
||||||
|
|
||||||
|
| Source | issue | pr | session |
|
||||||
|
|---|---|---|---|
|
||||||
|
| `control_plane` | yes | yes | **no** — the `events` table is `(event_id, work_item_id, event_type, message, created_at)` and records no session |
|
||||||
|
| `gitea_handoff` | yes | yes | yes — a CTH comment declares its own `Session:` field |
|
||||||
|
|
||||||
|
`session_id` is read only from that declared CTH field. It is never inferred
|
||||||
|
from a work item, an actor, or message text, and a value that is
|
||||||
|
redaction-altering or bare-secret-shaped is dropped rather than emitted.
|
||||||
|
|
||||||
|
When **no source that ran** can carry a requested dimension, the request is
|
||||||
|
refused rather than answered: the response is `422` with `ok:false` and a
|
||||||
|
structured `error` naming `unsupported_filters` and the per-source reason. A
|
||||||
|
`200` with zero events would tell an operator that no such activity exists,
|
||||||
|
which is a stronger — and false — claim than "this cannot be answered here".
|
||||||
|
A source that *can* answer the dimension and simply matched nothing still
|
||||||
|
returns `200` with `ok:true` and an empty page.
|
||||||
|
|
||||||
|
### Redaction
|
||||||
|
|
||||||
|
Every free-text field (event messages, decision/proof text, roles, actors) is
|
||||||
|
passed through the console redaction policy (`webui.console_redaction`, backed
|
||||||
|
by `gitea_audit.redact`) before it leaves the module, failing closed to the
|
||||||
|
placeholder. No unredacted tool arguments or secrets are ever emitted, and a
|
||||||
|
generation error never drops raw data to a caller or a log.
|
||||||
|
|
||||||
|
Redaction also runs *before* any structured value is derived from free text.
|
||||||
|
`evidence_refs` are extracted from already-redacted proof/decision text, and a
|
||||||
|
commit reference is recognised only where the text declares one (`commit`,
|
||||||
|
`head`, `base`, `sha`, …). An undeclared 40-character hex run has the exact
|
||||||
|
shape of a Gitea access token, so it is never lifted out of prose into a
|
||||||
|
structured field. Every reference is then independently revalidated against an
|
||||||
|
allowed shape and a second redaction pass immediately before serialization;
|
||||||
|
anything unproven is dropped and the event is flagged `sensitive`.
|
||||||
|
|
||||||
|
### Tests
|
||||||
|
|
||||||
|
```bash
|
||||||
|
pytest tests/test_webui_timeline.py -q
|
||||||
|
```
|
||||||
|
|
||||||
## Tests
|
## Tests
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
|
|||||||
+148
-2
@@ -2020,6 +2020,7 @@ 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 incident_bridge # noqa: E402
|
import incident_bridge # noqa: E402
|
||||||
import sentry_observability # noqa: E402 (#606 optional Sentry observability)
|
import sentry_observability # noqa: E402 (#606 optional Sentry observability)
|
||||||
@@ -2262,7 +2263,6 @@ 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,
|
||||||
@@ -2562,7 +2562,12 @@ def _build_author_issue_work_lease(
|
|||||||
host: str | None,
|
host: str | None,
|
||||||
) -> dict:
|
) -> dict:
|
||||||
created = _work_lease_now()
|
created = _work_lease_now()
|
||||||
expires = created + timedelta(hours=WORK_LEASE_TTL_HOURS)
|
# #790 Slice A: the window comes from the central policy, not a literal here.
|
||||||
|
# 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,
|
||||||
@@ -2573,6 +2578,15 @@ 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,
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
@@ -4342,6 +4356,138 @@ def gitea_lock_issue(
|
|||||||
return result
|
return result
|
||||||
|
|
||||||
|
|
||||||
|
@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):
|
||||||
|
# AC-N8 exit route one: canonical exact-owner rebinding. The other exit
|
||||||
|
# is terminal retirement, which is Slice B.
|
||||||
|
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_assess_work_issue_duplicate(
|
def gitea_assess_work_issue_duplicate(
|
||||||
issue_number: int,
|
issue_number: int,
|
||||||
|
|||||||
+553
-29
@@ -15,15 +15,27 @@ 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._+-]+")
|
||||||
|
|
||||||
|
|
||||||
@@ -253,6 +265,331 @@ 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))
|
||||||
@@ -336,6 +673,16 @@ 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
|
||||||
@@ -356,60 +703,216 @@ 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": "absent",
|
"status": STATUS_ABSENT,
|
||||||
"live": False,
|
"live": False,
|
||||||
"stale": False,
|
"stale": False,
|
||||||
"reason": "no lock record",
|
"reason": "no lock record",
|
||||||
}
|
}
|
||||||
|
|
||||||
expires_at = lease_expires_at(lock_data)
|
|
||||||
lease = lock_data.get("work_lease")
|
lease = lock_data.get("work_lease")
|
||||||
heartbeat_at = _parse_lease_timestamp(lock_data.get("last_heartbeat_at"))
|
expires_at = lease_expires_at(lock_data)
|
||||||
if heartbeat_at is None and isinstance(lease, dict):
|
heartbeat_at = _lease_heartbeat_at(lock_data)
|
||||||
heartbeat_at = _parse_lease_timestamp(lease.get("last_heartbeat_at"))
|
created_at = (
|
||||||
|
_parse_lease_timestamp(lease.get("created_at"))
|
||||||
|
if isinstance(lease, dict)
|
||||||
|
else None
|
||||||
|
)
|
||||||
|
|
||||||
pid = lock_data.get("session_pid")
|
pid = lock_data.get("session_pid")
|
||||||
if pid is None:
|
if pid is None:
|
||||||
pid = lock_data.get("pid")
|
pid = lock_data.get("pid")
|
||||||
|
# Evidence only. Never consulted to grant liveness (AC-N2).
|
||||||
pid_alive = is_process_alive(pid) if pid is not None else False
|
pid_alive = is_process_alive(pid) if pid is not None else False
|
||||||
|
|
||||||
if expires_at and expires_at <= current:
|
lifecycle = lease_lifecycle_version(lock_data)
|
||||||
return {
|
legacy = lifecycle != lease_policy.LIFECYCLE_HEARTBEAT_V1
|
||||||
"status": "expired",
|
policy = lease_policy.policy_for(lease_task_class(lock_data))
|
||||||
"live": False,
|
|
||||||
"stale": True,
|
|
||||||
"reason": f"lease expired at {expires_at.isoformat()}",
|
|
||||||
"pid_alive": pid_alive,
|
|
||||||
}
|
|
||||||
|
|
||||||
if pid is not None and not pid_alive:
|
evidence: dict[str, Any] = {
|
||||||
return {
|
|
||||||
"status": "stale",
|
|
||||||
"live": False,
|
|
||||||
"stale": True,
|
|
||||||
"reason": f"owner pid {pid} is not alive",
|
|
||||||
"pid_alive": False,
|
|
||||||
}
|
|
||||||
|
|
||||||
return {
|
|
||||||
"status": "live",
|
|
||||||
"live": True,
|
|
||||||
"stale": False,
|
|
||||||
"reason": "lock heartbeat and lease are fresh",
|
|
||||||
"pid_alive": pid_alive,
|
"pid_alive": pid_alive,
|
||||||
|
"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:
|
||||||
@@ -446,6 +949,27 @@ 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")
|
||||||
|
|||||||
+212
@@ -0,0 +1,212 @@
|
|||||||
|
"""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,
|
||||||
|
}
|
||||||
@@ -32,6 +32,15 @@ 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",
|
||||||
|
},
|
||||||
"set_issue_labels": {
|
"set_issue_labels": {
|
||||||
"permission": "gitea.issue.comment",
|
"permission": "gitea.issue.comment",
|
||||||
"role": "author",
|
"role": "author",
|
||||||
|
|||||||
@@ -0,0 +1,444 @@
|
|||||||
|
"""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()
|
||||||
@@ -0,0 +1,594 @@
|
|||||||
|
"""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()
|
||||||
@@ -0,0 +1,135 @@
|
|||||||
|
"""Tests for the Phase 1 operator console application shell (#638)."""
|
||||||
|
import sys
|
||||||
|
import unittest
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
||||||
|
|
||||||
|
from starlette.routing import Route
|
||||||
|
from starlette.testclient import TestClient
|
||||||
|
|
||||||
|
from webui import layout
|
||||||
|
from webui.app import create_app
|
||||||
|
from webui.nav import NAV_GROUPS, STUB_PAGES, nav_hrefs
|
||||||
|
|
||||||
|
|
||||||
|
class TestShellNav(unittest.TestCase):
|
||||||
|
def setUp(self):
|
||||||
|
self.client = TestClient(create_app())
|
||||||
|
|
||||||
|
def test_nav_group_labels_present(self):
|
||||||
|
text = self.client.get("/").text
|
||||||
|
for group in NAV_GROUPS:
|
||||||
|
with self.subTest(group=group.label):
|
||||||
|
self.assertIn(f">{group.label}<", text)
|
||||||
|
|
||||||
|
def test_phase1_group_labels_cover_expected_ia(self):
|
||||||
|
labels = {group.label for group in NAV_GROUPS}
|
||||||
|
for expected in (
|
||||||
|
"Health",
|
||||||
|
"Traffic",
|
||||||
|
"Runtime/Sessions",
|
||||||
|
"Projects",
|
||||||
|
"Inventory",
|
||||||
|
"Timeline",
|
||||||
|
"Policy",
|
||||||
|
"Insights",
|
||||||
|
):
|
||||||
|
with self.subTest(label=expected):
|
||||||
|
self.assertIn(expected, labels)
|
||||||
|
|
||||||
|
def test_every_nav_href_resolves_to_a_get_route(self):
|
||||||
|
app = create_app()
|
||||||
|
get_paths = {
|
||||||
|
route.path
|
||||||
|
for route in app.routes
|
||||||
|
if isinstance(route, Route) and "GET" in route.methods
|
||||||
|
}
|
||||||
|
for href in nav_hrefs():
|
||||||
|
with self.subTest(href=href):
|
||||||
|
self.assertIn(href, get_paths, f"nav href {href} has no GET route")
|
||||||
|
|
||||||
|
def test_legacy_hrefs_still_navigable(self):
|
||||||
|
text = self.client.get("/").text
|
||||||
|
for href in ("/queue", "/projects", "/prompts", "/runtime",
|
||||||
|
"/audit", "/worktrees", "/leases", "/actions"):
|
||||||
|
with self.subTest(href=href):
|
||||||
|
self.assertIn(f'href="{href}"', text)
|
||||||
|
|
||||||
|
|
||||||
|
class TestShellBadges(unittest.TestCase):
|
||||||
|
def setUp(self):
|
||||||
|
self.client = TestClient(create_app())
|
||||||
|
|
||||||
|
def test_mode_badge_present(self):
|
||||||
|
self.assertIn("mode: read-only", self.client.get("/").text)
|
||||||
|
|
||||||
|
def test_environment_badge_present(self):
|
||||||
|
self.assertIn("env:", self.client.get("/").text)
|
||||||
|
|
||||||
|
def test_default_environment_is_local(self):
|
||||||
|
self.assertEqual(layout.environment_label(), "local")
|
||||||
|
|
||||||
|
def test_remote_bind_reports_remote_environment(self):
|
||||||
|
import os
|
||||||
|
|
||||||
|
prior = os.environ.get("WEBUI_HOST")
|
||||||
|
os.environ["WEBUI_HOST"] = "10.0.0.5"
|
||||||
|
try:
|
||||||
|
self.assertEqual(layout.environment_label(), "remote")
|
||||||
|
finally:
|
||||||
|
if prior is None:
|
||||||
|
os.environ.pop("WEBUI_HOST", None)
|
||||||
|
else:
|
||||||
|
os.environ["WEBUI_HOST"] = prior
|
||||||
|
|
||||||
|
def test_docs_link_present(self):
|
||||||
|
text = self.client.get("/").text
|
||||||
|
self.assertIn(layout.DOCS_URL, text)
|
||||||
|
self.assertIn(">Docs<", text)
|
||||||
|
|
||||||
|
|
||||||
|
class TestShellStubs(unittest.TestCase):
|
||||||
|
def setUp(self):
|
||||||
|
self.client = TestClient(create_app())
|
||||||
|
|
||||||
|
def test_stub_routes_render_200(self):
|
||||||
|
for path, (title, _desc) in STUB_PAGES.items():
|
||||||
|
with self.subTest(path=path):
|
||||||
|
response = self.client.get(path)
|
||||||
|
self.assertEqual(response.status_code, 200, path)
|
||||||
|
self.assertIn(title, response.text)
|
||||||
|
self.assertIn("placeholder", response.text)
|
||||||
|
|
||||||
|
def test_stub_routes_are_read_only(self):
|
||||||
|
for path in STUB_PAGES:
|
||||||
|
with self.subTest(path=path):
|
||||||
|
response = self.client.post(path)
|
||||||
|
self.assertEqual(response.status_code, 405)
|
||||||
|
self.assertEqual(response.json()["error"], "read-only-mvp")
|
||||||
|
|
||||||
|
def test_stub_pages_carry_nav_and_badges(self):
|
||||||
|
response = self.client.get("/inventory")
|
||||||
|
self.assertIn("mode: read-only", response.text)
|
||||||
|
self.assertIn('href="/queue"', response.text)
|
||||||
|
|
||||||
|
|
||||||
|
class TestShellHome(unittest.TestCase):
|
||||||
|
def setUp(self):
|
||||||
|
self.client = TestClient(create_app())
|
||||||
|
|
||||||
|
def test_home_summarizes_console(self):
|
||||||
|
text = self.client.get("/").text
|
||||||
|
self.assertIn("Operator console", text)
|
||||||
|
self.assertIn("Phase 1", text)
|
||||||
|
|
||||||
|
def test_home_links_legacy_pages(self):
|
||||||
|
text = self.client.get("/").text
|
||||||
|
self.assertIn("MVP legacy pages", text)
|
||||||
|
for href in ("/queue", "/audit", "/leases"):
|
||||||
|
with self.subTest(href=href):
|
||||||
|
self.assertIn(f'href="{href}"', text)
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
unittest.main()
|
||||||
File diff suppressed because it is too large
Load Diff
+154
-11
@@ -12,6 +12,7 @@ from starlette.routing import Route
|
|||||||
|
|
||||||
from webui.deployment_boundary import deployment_snapshot
|
from webui.deployment_boundary import deployment_snapshot
|
||||||
from webui.layout import render_page
|
from webui.layout import render_page
|
||||||
|
from webui.nav import NAV_GROUPS, STUB_PAGES
|
||||||
from webui.project_registry import (
|
from webui.project_registry import (
|
||||||
ProjectRegistry,
|
ProjectRegistry,
|
||||||
RegistryError,
|
RegistryError,
|
||||||
@@ -45,6 +46,7 @@ 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.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,
|
||||||
load_system_health,
|
load_system_health,
|
||||||
@@ -65,24 +67,62 @@ def _stub_page(title: str, description: str) -> HTMLResponse:
|
|||||||
return HTMLResponse(render_page(title=title, body_html=body))
|
return HTMLResponse(render_page(title=title, body_html=body))
|
||||||
|
|
||||||
|
|
||||||
|
_LEGACY_PAGES = (
|
||||||
|
("/queue", "Queue", "live PR and issue dashboard (#429)"),
|
||||||
|
("/projects", "Projects", "registry and onboarding (#427)"),
|
||||||
|
("/prompts", "Prompts", "canonical workflow prompt library (#428)"),
|
||||||
|
("/runtime", "Runtime", "MCP health and stale-runtime detection (#430)"),
|
||||||
|
("/audit", "Audit", "final-report paste and validator preview (#431)"),
|
||||||
|
("/worktrees", "Worktrees", "branch hygiene dashboard (#432)"),
|
||||||
|
("/leases", "Leases", "collision and lease visibility (#433)"),
|
||||||
|
("/actions", "Actions", "gated write-action framework (#434)"),
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def _render_home_nav_groups() -> str:
|
||||||
|
groups = []
|
||||||
|
for group in NAV_GROUPS:
|
||||||
|
items = "".join(
|
||||||
|
f'<li><a href="{item.href}">{item.label}</a>'
|
||||||
|
+ ("" if item.status == "live" else " <span class=\"muted\">(stub)</span>")
|
||||||
|
+ "</li>"
|
||||||
|
for item in group.items
|
||||||
|
)
|
||||||
|
groups.append(f"<h3>{group.label}</h3><ul>{items}</ul>")
|
||||||
|
return "".join(groups)
|
||||||
|
|
||||||
|
|
||||||
async def home(_request: Request) -> HTMLResponse:
|
async def home(_request: Request) -> HTMLResponse:
|
||||||
|
legacy = "".join(
|
||||||
|
f"<li><strong>{label}</strong> — {desc} "
|
||||||
|
f'(<a href="{href}">{href}</a>)</li>'
|
||||||
|
for href, label, desc in _LEGACY_PAGES
|
||||||
|
)
|
||||||
body = (
|
body = (
|
||||||
"<h2>Operator console</h2>"
|
"<h2>Operator console</h2>"
|
||||||
"<p>Local entry point for MCP Control Plane operational views.</p>"
|
"<p>Read-only home for the MCP Control Plane Phase 1 operator console. "
|
||||||
"<ul>"
|
"Gitea, MCP capability gates, and canonical workflows remain the source "
|
||||||
"<li><strong>Queue</strong> — live PR and issue dashboard (#429)</li>"
|
"of truth; this console never mutates them.</p>"
|
||||||
"<li><strong>Projects</strong> — registry and onboarding (#427)</li>"
|
"<h2>Phase 1 surfaces</h2>"
|
||||||
"<li><strong>Prompts</strong> — canonical workflow prompt library (#428)</li>"
|
+ _render_home_nav_groups()
|
||||||
"<li><strong>Runtime</strong> — MCP health and stale-runtime detection (#430)</li>"
|
+ "<h2>MVP legacy pages</h2>"
|
||||||
"<li><strong>Audit</strong> — final-report paste and validator preview (#431)</li>"
|
"<ul>" + legacy + "</ul>"
|
||||||
"<li><strong>Worktrees</strong> — branch hygiene dashboard (#432)</li>"
|
|
||||||
"<li><strong>Leases</strong> — collision and lease visibility (#433)</li>"
|
|
||||||
"<li><strong>Actions</strong> — gated write-action framework (#434)</li>"
|
|
||||||
"</ul>"
|
|
||||||
)
|
)
|
||||||
return HTMLResponse(render_page(title="Home", body_html=body))
|
return HTMLResponse(render_page(title="Home", body_html=body))
|
||||||
|
|
||||||
|
|
||||||
|
async def phase_stub(request: Request) -> HTMLResponse:
|
||||||
|
"""Graceful read-only placeholder for a not-yet-implemented Phase 1 surface."""
|
||||||
|
title, description = STUB_PAGES[request.url.path]
|
||||||
|
body = (
|
||||||
|
f"<h2>{title}</h2>"
|
||||||
|
f'<div class="stub"><p>{description}</p>'
|
||||||
|
"<p>Phase 1 shell placeholder — no write actions. Tracked under "
|
||||||
|
"epic #631.</p></div>"
|
||||||
|
)
|
||||||
|
return HTMLResponse(render_page(title=title, body_html=body))
|
||||||
|
|
||||||
|
|
||||||
async def health(_request: Request) -> JSONResponse:
|
async def health(_request: Request) -> JSONResponse:
|
||||||
"""Liveness only — deliberately cheap, runs no dependency probe (#634).
|
"""Liveness only — deliberately cheap, runs no dependency probe (#634).
|
||||||
|
|
||||||
@@ -410,6 +450,104 @@ async def api_console_security_model(_request: Request) -> JSONResponse:
|
|||||||
})
|
})
|
||||||
|
|
||||||
|
|
||||||
|
def _query_int(request: Request, key: str) -> int | None:
|
||||||
|
"""Parse an optional integer query parameter; None when absent/invalid."""
|
||||||
|
raw = request.query_params.get(key)
|
||||||
|
if raw is None or not str(raw).strip():
|
||||||
|
return None
|
||||||
|
try:
|
||||||
|
return int(str(raw).strip())
|
||||||
|
except (TypeError, ValueError):
|
||||||
|
return None
|
||||||
|
|
||||||
|
|
||||||
|
def _derive_remote(host: str) -> str:
|
||||||
|
"""Map a Gitea host to its known short remote name (control-plane scope key)."""
|
||||||
|
text = (host or "").lower()
|
||||||
|
if "prgs" in text:
|
||||||
|
return "prgs"
|
||||||
|
if "dadeschools" in text:
|
||||||
|
return "dadeschools"
|
||||||
|
return text.split(".")[0] if text else ""
|
||||||
|
|
||||||
|
|
||||||
|
def _timeline_comment_source(host: str, org: str, repo: str):
|
||||||
|
"""Build a fail-soft CTH-comment fetcher for one repo, or None when offline.
|
||||||
|
|
||||||
|
Returns a callable ``(kind, number) -> list[comment]``. Credentials or
|
||||||
|
network failures raise inside the callable so ``load_timeline`` degrades the
|
||||||
|
handoff source rather than the whole timeline. Offline test mode yields no
|
||||||
|
live source so the handoff section reports ``not run``.
|
||||||
|
"""
|
||||||
|
import os
|
||||||
|
|
||||||
|
from gitea_auth import api_fetch_page, get_auth_header, repo_api_url
|
||||||
|
|
||||||
|
offline = (os.environ.get("WEBUI_TEST_OFFLINE") or "").strip().lower() in {"1", "true", "yes"}
|
||||||
|
if offline:
|
||||||
|
return None
|
||||||
|
auth = get_auth_header(host)
|
||||||
|
if not auth:
|
||||||
|
return None
|
||||||
|
|
||||||
|
def _fetch(kind: str, number: int) -> list:
|
||||||
|
segment = "pulls" if kind == "pr" else "issues"
|
||||||
|
url = f"{repo_api_url(host, org, repo)}/{segment}/{int(number)}/comments"
|
||||||
|
comments: list = []
|
||||||
|
page = 1
|
||||||
|
while page <= 20:
|
||||||
|
raw, meta = api_fetch_page(url, auth, page=page, limit=50)
|
||||||
|
comments.extend(raw)
|
||||||
|
if bool(meta["is_final_page"]):
|
||||||
|
break
|
||||||
|
page += 1
|
||||||
|
return comments
|
||||||
|
|
||||||
|
return _fetch
|
||||||
|
|
||||||
|
|
||||||
|
async def api_v1_timeline(request: Request) -> JSONResponse:
|
||||||
|
"""Read-only workflow-event timeline (#637). Filter by issue/PR/session."""
|
||||||
|
from webui.queue_loader import _host_from_url # host normalisation helper
|
||||||
|
|
||||||
|
registry, error = _load_project_registry()
|
||||||
|
if error is not None:
|
||||||
|
return JSONResponse(error.to_dict(), status_code=500)
|
||||||
|
project = registry.projects[0] if registry.projects else None
|
||||||
|
|
||||||
|
org = request.query_params.get("org") or (project.gitea_owner if project else "")
|
||||||
|
repo = request.query_params.get("repo") or (project.repo_name if project else "")
|
||||||
|
host = _host_from_url(project.remote_host) if project else ""
|
||||||
|
remote = request.query_params.get("remote") or _derive_remote(host)
|
||||||
|
|
||||||
|
if not (remote and org and repo):
|
||||||
|
return JSONResponse(
|
||||||
|
{
|
||||||
|
"error": "timeline_scope_unresolved",
|
||||||
|
"detail": "no project in registry and no remote/org/repo query params provided",
|
||||||
|
},
|
||||||
|
status_code=400,
|
||||||
|
)
|
||||||
|
|
||||||
|
comment_source = _timeline_comment_source(host, org, repo) if (host and org and repo) else None
|
||||||
|
|
||||||
|
snapshot = load_timeline(
|
||||||
|
remote=remote,
|
||||||
|
org=org,
|
||||||
|
repo=repo,
|
||||||
|
issue=_query_int(request, "issue"),
|
||||||
|
pr=_query_int(request, "pr"),
|
||||||
|
session=(request.query_params.get("session") or None),
|
||||||
|
limit=_query_int(request, "limit"),
|
||||||
|
offset=_query_int(request, "offset"),
|
||||||
|
comment_source=comment_source,
|
||||||
|
)
|
||||||
|
# A filter no surviving source can carry is refused, not answered empty:
|
||||||
|
# a 200 with zero events would tell the operator no such activity exists.
|
||||||
|
status_code = 200 if snapshot.ok else 422
|
||||||
|
return JSONResponse(timeline_snapshot_to_dict(snapshot), status_code=status_code)
|
||||||
|
|
||||||
|
|
||||||
async def method_not_allowed(request: Request, _exc: Exception) -> Response:
|
async def method_not_allowed(request: Request, _exc: Exception) -> Response:
|
||||||
path = request.url.path
|
path = request.url.path
|
||||||
if path in _AUDIT_MUTATION_PATHS and request.method == "POST":
|
if path in _AUDIT_MUTATION_PATHS and request.method == "POST":
|
||||||
@@ -449,6 +587,7 @@ def create_app(*, bind_host: str | None = None) -> Starlette:
|
|||||||
Route("/api/prompts", api_prompts, methods=["GET"]),
|
Route("/api/prompts", api_prompts, methods=["GET"]),
|
||||||
Route("/runtime", runtime, methods=["GET"]),
|
Route("/runtime", runtime, methods=["GET"]),
|
||||||
Route("/api/runtime", api_runtime, methods=["GET"]),
|
Route("/api/runtime", api_runtime, methods=["GET"]),
|
||||||
|
Route("/api/v1/timeline", api_v1_timeline, methods=["GET"]),
|
||||||
Route("/audit", audit, methods=["GET", "POST"]),
|
Route("/audit", audit, methods=["GET", "POST"]),
|
||||||
Route("/api/audit", api_audit, methods=["GET", "POST"]),
|
Route("/api/audit", api_audit, methods=["GET", "POST"]),
|
||||||
Route("/worktrees", worktrees, methods=["GET"]),
|
Route("/worktrees", worktrees, methods=["GET"]),
|
||||||
@@ -472,6 +611,10 @@ def create_app(*, bind_host: str | None = None) -> Starlette:
|
|||||||
api_console_security_model,
|
api_console_security_model,
|
||||||
methods=["GET"],
|
methods=["GET"],
|
||||||
),
|
),
|
||||||
|
*[
|
||||||
|
Route(path, phase_stub, methods=["GET"])
|
||||||
|
for path in STUB_PAGES
|
||||||
|
],
|
||||||
],
|
],
|
||||||
exception_handlers={405: method_not_allowed},
|
exception_handlers={405: method_not_allowed},
|
||||||
)
|
)
|
||||||
|
|||||||
+95
-17
@@ -2,28 +2,66 @@
|
|||||||
|
|
||||||
from __future__ import annotations
|
from __future__ import annotations
|
||||||
|
|
||||||
NAV_ITEMS = (
|
import os
|
||||||
("/", "Home"),
|
|
||||||
("/queue", "Queue"),
|
from webui.nav import NAV_GROUPS
|
||||||
("/projects", "Projects"),
|
|
||||||
("/prompts", "Prompts"),
|
|
||||||
("/runtime", "Runtime"),
|
|
||||||
("/audit", "Audit"),
|
|
||||||
("/worktrees", "Worktrees"),
|
|
||||||
("/leases", "Leases"),
|
|
||||||
("/actions", "Actions"),
|
|
||||||
)
|
|
||||||
|
|
||||||
MVP_NOTICE = (
|
MVP_NOTICE = (
|
||||||
"Read-only MVP — Gitea, MCP tools, and canonical workflows remain the "
|
"Read-only MVP — Gitea, MCP tools, and canonical workflows remain the "
|
||||||
"source of truth. No mutation endpoints."
|
"source of truth. No mutation endpoints."
|
||||||
)
|
)
|
||||||
|
|
||||||
|
# Canonical docs entry point surfaced from the shell header (#638).
|
||||||
|
DOCS_URL = (
|
||||||
|
"https://gitea.prgs.cc/Scaled-Tech-Consulting/Gitea-Tools/src/branch/"
|
||||||
|
"master/docs/webui-local-dev.md"
|
||||||
|
)
|
||||||
|
|
||||||
|
_LOCAL_HOSTS = frozenset({"", "127.0.0.1", "localhost", "::1"})
|
||||||
|
|
||||||
|
|
||||||
|
def environment_label() -> str:
|
||||||
|
"""Classify the serving environment as ``local`` or ``remote`` (#638).
|
||||||
|
|
||||||
|
Derived from the same ``WEBUI_HOST`` default the app binds to; loopback
|
||||||
|
hosts are ``local``, anything else is ``remote``. Read-only signal only.
|
||||||
|
"""
|
||||||
|
host = (os.environ.get("WEBUI_HOST", "127.0.0.1") or "").strip().lower()
|
||||||
|
return "local" if host in _LOCAL_HOSTS else "remote"
|
||||||
|
|
||||||
|
|
||||||
|
def _render_nav() -> str:
|
||||||
|
groups_html = []
|
||||||
|
for group in NAV_GROUPS:
|
||||||
|
links = "".join(
|
||||||
|
f'<a href="{item.href}"'
|
||||||
|
+ (' class="nav-stub"' if item.status == "stub" else "")
|
||||||
|
+ f'>{item.label}</a>'
|
||||||
|
for item in group.items
|
||||||
|
)
|
||||||
|
groups_html.append(
|
||||||
|
'<div class="nav-group">'
|
||||||
|
f'<span class="nav-group-label">{group.label}</span>'
|
||||||
|
f'<span class="nav-group-links">{links}</span>'
|
||||||
|
"</div>"
|
||||||
|
)
|
||||||
|
return "".join(groups_html)
|
||||||
|
|
||||||
|
|
||||||
|
def _render_badges() -> str:
|
||||||
|
env = environment_label()
|
||||||
|
return (
|
||||||
|
'<div class="header-badges">'
|
||||||
|
f'<span class="badge env-badge env-{env}">env: {env}</span>'
|
||||||
|
'<span class="badge mode-badge">mode: read-only</span>'
|
||||||
|
f'<a class="badge docs-link" href="{DOCS_URL}">Docs</a>'
|
||||||
|
"</div>"
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
def render_page(*, title: str, body_html: str, extra_head: str = "") -> str:
|
def render_page(*, title: str, body_html: str, extra_head: str = "") -> str:
|
||||||
nav_links = "".join(
|
nav_links = _render_nav()
|
||||||
f'<a href="{href}">{label}</a>' for href, label in NAV_ITEMS
|
header_badges = _render_badges()
|
||||||
)
|
|
||||||
return f"""<!DOCTYPE html>
|
return f"""<!DOCTYPE html>
|
||||||
<html lang="en">
|
<html lang="en">
|
||||||
<head>
|
<head>
|
||||||
@@ -53,21 +91,58 @@ def render_page(*, title: str, body_html: str, extra_head: str = "") -> str:
|
|||||||
padding: 0.75rem 1.25rem;
|
padding: 0.75rem 1.25rem;
|
||||||
}}
|
}}
|
||||||
header h1 {{
|
header h1 {{
|
||||||
margin: 0 0 0.5rem;
|
margin: 0;
|
||||||
font-size: 1.1rem;
|
font-size: 1.1rem;
|
||||||
font-weight: 600;
|
font-weight: 600;
|
||||||
}}
|
}}
|
||||||
|
.header-top {{
|
||||||
|
display: flex;
|
||||||
|
flex-wrap: wrap;
|
||||||
|
align-items: center;
|
||||||
|
justify-content: space-between;
|
||||||
|
gap: 0.5rem 1rem;
|
||||||
|
margin-bottom: 0.6rem;
|
||||||
|
}}
|
||||||
|
.header-badges {{ display: inline-flex; flex-wrap: wrap; gap: 0.4rem; }}
|
||||||
|
.env-badge.env-local {{ color: #8fd19e; border-color: #3d6b4a; }}
|
||||||
|
.env-badge.env-remote {{ color: #e0c27a; border-color: #6b5730; }}
|
||||||
|
.mode-badge {{ color: #9ec8f0; border-color: #3d5f7a; }}
|
||||||
|
a.docs-link {{
|
||||||
|
color: var(--accent);
|
||||||
|
border-color: var(--accent);
|
||||||
|
text-decoration: none;
|
||||||
|
text-transform: none;
|
||||||
|
}}
|
||||||
|
a.docs-link:hover {{ filter: brightness(1.12); }}
|
||||||
nav {{
|
nav {{
|
||||||
display: flex;
|
display: flex;
|
||||||
flex-wrap: wrap;
|
flex-wrap: wrap;
|
||||||
gap: 0.75rem 1rem;
|
gap: 0.5rem 1.25rem;
|
||||||
}}
|
}}
|
||||||
|
.nav-group {{
|
||||||
|
display: flex;
|
||||||
|
flex-direction: column;
|
||||||
|
gap: 0.15rem;
|
||||||
|
}}
|
||||||
|
.nav-group-label {{
|
||||||
|
font-size: 0.68rem;
|
||||||
|
text-transform: uppercase;
|
||||||
|
letter-spacing: 0.04em;
|
||||||
|
color: var(--muted);
|
||||||
|
}}
|
||||||
|
.nav-group-links {{ display: inline-flex; flex-wrap: wrap; gap: 0.6rem; }}
|
||||||
nav a {{
|
nav a {{
|
||||||
color: var(--accent);
|
color: var(--accent);
|
||||||
text-decoration: none;
|
text-decoration: none;
|
||||||
font-size: 0.9rem;
|
font-size: 0.9rem;
|
||||||
}}
|
}}
|
||||||
nav a:hover {{ text-decoration: underline; }}
|
nav a:hover {{ text-decoration: underline; }}
|
||||||
|
nav a.nav-stub {{ color: var(--muted); }}
|
||||||
|
nav a.nav-stub::after {{
|
||||||
|
content: " ·stub";
|
||||||
|
font-size: 0.7rem;
|
||||||
|
color: var(--muted);
|
||||||
|
}}
|
||||||
main {{
|
main {{
|
||||||
max-width: 52rem;
|
max-width: 52rem;
|
||||||
margin: 0 auto;
|
margin: 0 auto;
|
||||||
@@ -166,7 +241,10 @@ def render_page(*, title: str, body_html: str, extra_head: str = "") -> str:
|
|||||||
</head>
|
</head>
|
||||||
<body>
|
<body>
|
||||||
<header>
|
<header>
|
||||||
<h1>MCP Control Plane</h1>
|
<div class="header-top">
|
||||||
|
<h1>MCP Control Plane</h1>
|
||||||
|
{header_badges}
|
||||||
|
</div>
|
||||||
<nav>{nav_links}</nav>
|
<nav>{nav_links}</nav>
|
||||||
</header>
|
</header>
|
||||||
<main>
|
<main>
|
||||||
|
|||||||
+111
@@ -0,0 +1,111 @@
|
|||||||
|
"""Navigation IA for the Phase 1 operator console shell (#638).
|
||||||
|
|
||||||
|
Single source of truth for the console navigation so ``webui/layout.py`` and
|
||||||
|
the ``webui/app.py`` route table stay aligned with epic #631. Read-only: every
|
||||||
|
destination is a GET view or a Phase 1 placeholder. No mutation links.
|
||||||
|
|
||||||
|
Nav groups follow the #631 Phase 1 information architecture: Health, Traffic,
|
||||||
|
Runtime/Sessions, Projects, Inventory, Timeline, Policy (placeholder), and
|
||||||
|
Insights (placeholder). Later-phase surfaces are declared as ``stub`` items and
|
||||||
|
backed by ``STUB_PAGES`` so their nav links resolve to a graceful placeholder
|
||||||
|
instead of a 404.
|
||||||
|
"""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
from dataclasses import dataclass
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class NavItem:
|
||||||
|
"""A single navigation destination.
|
||||||
|
|
||||||
|
``status`` is ``"live"`` for implemented views and ``"stub"`` for Phase 1
|
||||||
|
placeholders whose backing view lands in a later child issue.
|
||||||
|
"""
|
||||||
|
|
||||||
|
href: str
|
||||||
|
label: str
|
||||||
|
status: str = "live"
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class NavGroup:
|
||||||
|
label: str
|
||||||
|
items: tuple[NavItem, ...]
|
||||||
|
|
||||||
|
|
||||||
|
NAV_GROUPS: tuple[NavGroup, ...] = (
|
||||||
|
NavGroup("Health", (
|
||||||
|
NavItem("/health", "Liveness"),
|
||||||
|
)),
|
||||||
|
NavGroup("Traffic", (
|
||||||
|
NavItem("/queue", "Queue"),
|
||||||
|
NavItem("/leases", "Leases"),
|
||||||
|
NavItem("/actions", "Actions"),
|
||||||
|
)),
|
||||||
|
NavGroup("Runtime/Sessions", (
|
||||||
|
NavItem("/runtime", "Runtime health"),
|
||||||
|
NavItem("/sessions", "Sessions", "stub"),
|
||||||
|
)),
|
||||||
|
NavGroup("Projects", (
|
||||||
|
NavItem("/projects", "Projects"),
|
||||||
|
)),
|
||||||
|
NavGroup("Inventory", (
|
||||||
|
NavItem("/inventory", "Inventory", "stub"),
|
||||||
|
NavItem("/worktrees", "Worktrees"),
|
||||||
|
)),
|
||||||
|
NavGroup("Timeline", (
|
||||||
|
NavItem("/timeline", "Timeline", "stub"),
|
||||||
|
)),
|
||||||
|
NavGroup("Policy", (
|
||||||
|
NavItem("/policy", "Policy", "stub"),
|
||||||
|
NavItem("/prompts", "Prompts"),
|
||||||
|
)),
|
||||||
|
NavGroup("Insights", (
|
||||||
|
NavItem("/insights", "Insights", "stub"),
|
||||||
|
NavItem("/audit", "Audit"),
|
||||||
|
)),
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
# Phase 1 placeholder destinations whose backing views land in later child
|
||||||
|
# issues of epic #631. Each maps a path to (title, description). Routes are
|
||||||
|
# registered so nav links resolve to a graceful, read-only stub page.
|
||||||
|
STUB_PAGES: dict[str, tuple[str, str]] = {
|
||||||
|
"/sessions": (
|
||||||
|
"Sessions",
|
||||||
|
"Active session, capability, and role inventory. Backed by the unified "
|
||||||
|
"inventory API (#636) once it lands.",
|
||||||
|
),
|
||||||
|
"/inventory": (
|
||||||
|
"Inventory",
|
||||||
|
"Unified sessions, leases, locks, namespaces, and worktree inventory. "
|
||||||
|
"Backed by the Phase 1 inventory API (#636).",
|
||||||
|
),
|
||||||
|
"/timeline": (
|
||||||
|
"Timeline",
|
||||||
|
"Workflow event timeline across issues and PRs. A later Phase 1 surface.",
|
||||||
|
),
|
||||||
|
"/policy": (
|
||||||
|
"Policy",
|
||||||
|
"Capability and role policy surface. Placeholder until a later phase.",
|
||||||
|
),
|
||||||
|
"/insights": (
|
||||||
|
"Insights",
|
||||||
|
"Aggregate operational insights and trends. Placeholder until a later "
|
||||||
|
"phase.",
|
||||||
|
),
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
def iter_nav_items():
|
||||||
|
"""Yield every ``NavItem`` across all groups in declared order."""
|
||||||
|
for group in NAV_GROUPS:
|
||||||
|
for item in group.items:
|
||||||
|
yield item
|
||||||
|
|
||||||
|
|
||||||
|
def nav_hrefs() -> tuple[str, ...]:
|
||||||
|
"""Return every navigation href in declared order."""
|
||||||
|
return tuple(item.href for item in iter_nav_items())
|
||||||
@@ -0,0 +1,906 @@
|
|||||||
|
"""Workflow-event and conversation timeline model (#637, Phase 1).
|
||||||
|
|
||||||
|
Operators cannot browse a unified timeline of workflow events, decisions,
|
||||||
|
tool calls, and handoffs: the evidence is scattered across control-plane
|
||||||
|
events, Gitea canonical handoff comments, and local logs. This module defines
|
||||||
|
one durable, versioned event schema and per-source adapters that normalise
|
||||||
|
those scattered records into a single ``WorkflowEvent`` stream, plus a
|
||||||
|
read-only query layer (filter by issue / PR / session, stable ordering,
|
||||||
|
pagination) that the ``/api/v1/timeline`` route serves.
|
||||||
|
|
||||||
|
Design rules honoured here:
|
||||||
|
|
||||||
|
- **Read-only.** Sources are read; nothing is mutated. The control-plane
|
||||||
|
database is opened through a ``mode=ro`` URI so a missing or unwritable DB
|
||||||
|
degrades to a reason instead of creating directories or running migrations.
|
||||||
|
- **Fail-soft per source.** An unavailable source degrades to a status with a
|
||||||
|
reason rather than raising, and a source that could not run is never
|
||||||
|
rendered as an empty-and-healthy timeline.
|
||||||
|
- **Answerable filters only.** Each source declares which filter dimensions it
|
||||||
|
can actually answer. A filter dimension no source that ran can carry is
|
||||||
|
refused with an explicit reason rather than silently matching nothing: an
|
||||||
|
empty page from an unanswerable filter reads to an operator as "no such
|
||||||
|
activity", which is a different — and false — statement.
|
||||||
|
- **Redaction at the boundary, fail closed.** Every free-text field (event
|
||||||
|
messages, redacted tool arguments, decision/proof text) is run through the
|
||||||
|
console redaction policy before it leaves this module, and *before* any
|
||||||
|
structured value is derived from it — evidence references are extracted from
|
||||||
|
redacted text, then independently revalidated before serialization. An
|
||||||
|
unredactable value becomes the placeholder, and a value that cannot be proven
|
||||||
|
safe is dropped — an unredacted payload is never emitted, and a generation
|
||||||
|
error never drops raw data to a caller or a log.
|
||||||
|
- **Stable ordering.** Events sort by ``(timestamp, source_rank, event_key)``
|
||||||
|
with a deterministic tiebreak, so pagination is stable across calls and
|
||||||
|
events with equal or missing timestamps keep a fixed order.
|
||||||
|
|
||||||
|
Non-goals (from the issue): no full chat replay, no mutation of historical
|
||||||
|
events, no unredacted tool-argument storage.
|
||||||
|
"""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import re
|
||||||
|
import sqlite3
|
||||||
|
from dataclasses import dataclass, replace
|
||||||
|
from datetime import datetime, timezone
|
||||||
|
from typing import Any, Callable, Iterable
|
||||||
|
|
||||||
|
import control_plane_db
|
||||||
|
from webui import console_redaction
|
||||||
|
|
||||||
|
# The schema is versioned so consumers can branch on shape. Bump on any
|
||||||
|
# breaking change to WorkflowEvent's serialized form.
|
||||||
|
TIMELINE_SCHEMA_VERSION = 1
|
||||||
|
|
||||||
|
# Known event sources and their deterministic ordering rank. When two events
|
||||||
|
# carry the same timestamp, the source rank breaks the tie before the
|
||||||
|
# per-source event key, so a control-plane event and a handoff comment minted
|
||||||
|
# in the same second always sort in a fixed order.
|
||||||
|
SOURCE_CONTROL_PLANE = "control_plane"
|
||||||
|
SOURCE_GITEA_HANDOFF = "gitea_handoff"
|
||||||
|
_SOURCE_RANK = {
|
||||||
|
SOURCE_CONTROL_PLANE: 0,
|
||||||
|
SOURCE_GITEA_HANDOFF: 1,
|
||||||
|
}
|
||||||
|
|
||||||
|
# The filter dimensions the query layer accepts.
|
||||||
|
FILTER_ISSUE = "issue"
|
||||||
|
FILTER_PR = "pr"
|
||||||
|
FILTER_SESSION = "session"
|
||||||
|
|
||||||
|
# Which dimensions each source can actually answer. This is a property of the
|
||||||
|
# underlying records, not of the query code: the control-plane ``events`` table
|
||||||
|
# is (event_id, work_item_id, event_type, message, created_at) and carries no
|
||||||
|
# session identity at all, so no control-plane event can ever match a session
|
||||||
|
# filter. A CTH handoff comment can declare its session as a field, so the
|
||||||
|
# handoff source answers all three. Filtering on a dimension the surviving
|
||||||
|
# sources cannot carry is refused in ``load_timeline`` rather than answered
|
||||||
|
# with an empty page.
|
||||||
|
_SOURCE_FILTER_SUPPORT: dict[str, tuple[str, ...]] = {
|
||||||
|
SOURCE_CONTROL_PLANE: (FILTER_ISSUE, FILTER_PR),
|
||||||
|
SOURCE_GITEA_HANDOFF: (FILTER_ISSUE, FILTER_PR, FILTER_SESSION),
|
||||||
|
}
|
||||||
|
|
||||||
|
# Why a source cannot answer a dimension, for the refusal reason an operator reads.
|
||||||
|
_SOURCE_FILTER_LIMITS: dict[tuple[str, str], str] = {
|
||||||
|
(SOURCE_CONTROL_PLANE, FILTER_SESSION): (
|
||||||
|
"control-plane events carry no session identity "
|
||||||
|
"(the events table has no session column)"
|
||||||
|
),
|
||||||
|
}
|
||||||
|
|
||||||
|
# A timestamp far in the future so events with no parseable timestamp sort
|
||||||
|
# last (after everything real) instead of first, without raising.
|
||||||
|
_MISSING_TS_SORT = "9999-12-31T23:59:59Z"
|
||||||
|
|
||||||
|
|
||||||
|
def _parse_ts(value: str | None) -> str | None:
|
||||||
|
"""Normalise a timestamp to ``...Z`` UTC, or None when unparseable."""
|
||||||
|
if not value:
|
||||||
|
return None
|
||||||
|
text = str(value).strip()
|
||||||
|
if not text:
|
||||||
|
return None
|
||||||
|
candidate = text[:-1] + "+00:00" if text.endswith("Z") else text
|
||||||
|
try:
|
||||||
|
parsed = datetime.fromisoformat(candidate)
|
||||||
|
except ValueError:
|
||||||
|
return None
|
||||||
|
if parsed.tzinfo is None:
|
||||||
|
parsed = parsed.replace(tzinfo=timezone.utc)
|
||||||
|
return parsed.astimezone(timezone.utc).replace(microsecond=0).isoformat().replace("+00:00", "Z")
|
||||||
|
|
||||||
|
|
||||||
|
def _redact(value: Any) -> Any:
|
||||||
|
"""Redact a single free-text field, failing closed to the placeholder."""
|
||||||
|
if value is None:
|
||||||
|
return None
|
||||||
|
return console_redaction.redact_text(str(value))
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class WorkflowEvent:
|
||||||
|
"""One normalised timeline event.
|
||||||
|
|
||||||
|
Every field is optional except ``source``/``event_type``/``event_key``
|
||||||
|
because sources carry different subsets. The class is frozen so an adapted
|
||||||
|
event is an immutable record; a consumer that needs a variant builds a new
|
||||||
|
one rather than mutating history.
|
||||||
|
"""
|
||||||
|
|
||||||
|
source: str
|
||||||
|
event_type: str
|
||||||
|
event_key: str
|
||||||
|
timestamp: str | None = None
|
||||||
|
actor: str | None = None
|
||||||
|
role: str | None = None
|
||||||
|
issue_number: int | None = None
|
||||||
|
pr_number: int | None = None
|
||||||
|
session_id: str | None = None
|
||||||
|
tool_name: str | None = None
|
||||||
|
decision: str | None = None
|
||||||
|
message: str | None = None
|
||||||
|
correlation_id: str | None = None
|
||||||
|
evidence_refs: tuple[str, ...] = ()
|
||||||
|
sensitive: bool = False
|
||||||
|
|
||||||
|
def sort_key(self) -> tuple[str, int, str]:
|
||||||
|
return (
|
||||||
|
self.timestamp or _MISSING_TS_SORT,
|
||||||
|
_SOURCE_RANK.get(self.source, 99),
|
||||||
|
self.event_key,
|
||||||
|
)
|
||||||
|
|
||||||
|
def to_dict(self) -> dict[str, Any]:
|
||||||
|
return {
|
||||||
|
"source": self.source,
|
||||||
|
"event_type": self.event_type,
|
||||||
|
"event_key": self.event_key,
|
||||||
|
"timestamp": self.timestamp,
|
||||||
|
"actor": self.actor,
|
||||||
|
"role": self.role,
|
||||||
|
"issue_number": self.issue_number,
|
||||||
|
"pr_number": self.pr_number,
|
||||||
|
"session_id": self.session_id,
|
||||||
|
"tool_name": self.tool_name,
|
||||||
|
"decision": self.decision,
|
||||||
|
"message": self.message,
|
||||||
|
"correlation_id": self.correlation_id,
|
||||||
|
"evidence_refs": list(self.evidence_refs),
|
||||||
|
"sensitive": self.sensitive,
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
# --------------------------------------------------------------------------- #
|
||||||
|
# Adapters — pure functions from a source's raw records to WorkflowEvents. #
|
||||||
|
# Each is total: a malformed record is skipped, never raised on. #
|
||||||
|
# --------------------------------------------------------------------------- #
|
||||||
|
|
||||||
|
# Event types whose payload is treated as sensitive and always redaction-hard
|
||||||
|
# (they can carry lease/session provenance or tool arguments).
|
||||||
|
_SENSITIVE_EVENT_HINTS = ("lease", "capability", "token", "auth", "secret")
|
||||||
|
|
||||||
|
# Reference tokens (issue/PR/comment ids) and SHAs parsed out of proof text.
|
||||||
|
_EVIDENCE_REF_RE = re.compile(r"(?:#|PR\s*#?|issue\s*#?|comment\s*#?)(\d+)", re.IGNORECASE)
|
||||||
|
|
||||||
|
# A commit reference is only recognised when the text *declares* it as one.
|
||||||
|
# A bare lowercase hex run is not evidence of anything: at 40 characters it is
|
||||||
|
# exactly the shape of a Gitea personal access token, and at 7 it also matches
|
||||||
|
# ordinary words such as "defaced". Requiring an anchoring keyword keeps real
|
||||||
|
# references ("commit abc1234", "at head a209756...", "base caaae9b6") usable
|
||||||
|
# while refusing to lift an undeclared secret-shaped run out of free text.
|
||||||
|
_SHA_RE = re.compile(
|
||||||
|
r"(?i:\b(?:commit|sha|head|base|parent|revision|rev|merge[- ]base)\b[\s:=@#]*)"
|
||||||
|
r"([0-9a-f]{7,40})\b"
|
||||||
|
)
|
||||||
|
|
||||||
|
# Shapes a serialized evidence reference is allowed to take. Anything else is
|
||||||
|
# dropped rather than emitted.
|
||||||
|
_REF_ISSUE_SHAPE = re.compile(r"^#[0-9]{1,9}$")
|
||||||
|
_REF_SHA_SHAPE = re.compile(r"^[0-9a-f]{7,40}$")
|
||||||
|
|
||||||
|
# A long undelimited hex run with no declaring context is treated as credential
|
||||||
|
# material wherever it appears, never as an identifier.
|
||||||
|
_BARE_SECRET_SHAPE = re.compile(r"^[0-9a-f]{32,}$")
|
||||||
|
|
||||||
|
# An event type reads like an identifier, but a stored one is externally
|
||||||
|
# influenced: any producer that writes the control-plane ``events`` table
|
||||||
|
# chooses the string. It reaches ``to_dict`` verbatim, so it is validated here
|
||||||
|
# rather than trusted because of where it came from.
|
||||||
|
_CP_EVENT_TYPE_SHAPE = re.compile(r"^[A-Za-z][A-Za-z0-9._:+-]{0,63}$")
|
||||||
|
|
||||||
|
# Emitted in place of a value that cannot be proven safe. Deliberately not a
|
||||||
|
# plausible workflow type: an unsafe value is refused, never quietly rewritten
|
||||||
|
# into a different valid-looking one that would misdescribe the record.
|
||||||
|
UNSAFE_EVENT_TYPE = "unsafe:redacted"
|
||||||
|
|
||||||
|
# Emitted for a CTH heading that is not a declared member of ``CTH_TYPES``. The
|
||||||
|
# contract is enforced on write (``format_cth_body``) and on assess; the read
|
||||||
|
# path the timeline uses enforces it too rather than assuming it was.
|
||||||
|
UNKNOWN_HANDOFF_EVENT_TYPE = "handoff:unrecognized"
|
||||||
|
|
||||||
|
# A source record id is a plain integer in both sources it comes from: the
|
||||||
|
# control-plane ``events`` primary key and a Gitea comment id. ``event_key`` is
|
||||||
|
# serialized verbatim and is the pagination tiebreak, so anything else is
|
||||||
|
# refused rather than interpolated into it.
|
||||||
|
_RECORD_ID_SHAPE = re.compile(r"^[0-9]{1,19}$")
|
||||||
|
|
||||||
|
|
||||||
|
def _kind_to_numbers(kind: str | None, number: int | None) -> tuple[int | None, int | None]:
|
||||||
|
"""Map a control-plane work-item (kind, number) to (issue_no, pr_no)."""
|
||||||
|
if number is None:
|
||||||
|
return (None, None)
|
||||||
|
if kind == "pr":
|
||||||
|
return (None, int(number))
|
||||||
|
if kind == "issue":
|
||||||
|
return (int(number), None)
|
||||||
|
return (None, None)
|
||||||
|
|
||||||
|
|
||||||
|
def _correlation_for(kind: str | None, number: int | None) -> str | None:
|
||||||
|
if number is None or kind not in ("issue", "pr"):
|
||||||
|
return None
|
||||||
|
return f"{kind}#{number}"
|
||||||
|
|
||||||
|
|
||||||
|
def _extract_evidence_refs(*texts: str | None) -> tuple[str, ...]:
|
||||||
|
"""Extract issue/PR and declared-commit references from **redacted** text.
|
||||||
|
|
||||||
|
Callers must pass text that has already been through :func:`_redact`; this
|
||||||
|
function derives a structured field from its input, so extracting ahead of
|
||||||
|
redaction would republish whatever redaction was about to remove. Every
|
||||||
|
reference is revalidated by :func:`_validated_evidence_refs` before it is
|
||||||
|
serialized.
|
||||||
|
"""
|
||||||
|
refs: list[str] = []
|
||||||
|
for text in texts:
|
||||||
|
if not text:
|
||||||
|
continue
|
||||||
|
for match in _EVIDENCE_REF_RE.finditer(text):
|
||||||
|
token = f"#{match.group(1)}"
|
||||||
|
if token not in refs:
|
||||||
|
refs.append(token)
|
||||||
|
for match in _SHA_RE.finditer(text):
|
||||||
|
token = match.group(1)
|
||||||
|
if token not in refs:
|
||||||
|
refs.append(token)
|
||||||
|
return tuple(refs)
|
||||||
|
|
||||||
|
|
||||||
|
def _validated_evidence_refs(refs: Iterable[str]) -> tuple[tuple[str, ...], bool]:
|
||||||
|
"""Independently revalidate references immediately before serialization.
|
||||||
|
|
||||||
|
Extraction is not trusted on its own. A reference survives only when it has
|
||||||
|
a known reference shape and is unchanged by a second redaction pass — a
|
||||||
|
value the redaction policy would alter is credential material that must not
|
||||||
|
be emitted as a structured field. A full 40-character SHA stays usable
|
||||||
|
because extraction only accepts a hex run the source text explicitly
|
||||||
|
declared as a commit. Returns ``(safe_refs, dropped_any)``; ``dropped_any``
|
||||||
|
marks the event sensitive so the drop is visible rather than silent.
|
||||||
|
"""
|
||||||
|
safe: list[str] = []
|
||||||
|
dropped = False
|
||||||
|
for ref in refs or ():
|
||||||
|
try:
|
||||||
|
token = str(ref).strip()
|
||||||
|
if not token:
|
||||||
|
continue
|
||||||
|
recognised = bool(_REF_ISSUE_SHAPE.match(token) or _REF_SHA_SHAPE.match(token))
|
||||||
|
if not recognised:
|
||||||
|
dropped = True
|
||||||
|
continue
|
||||||
|
if _redact(token) != token:
|
||||||
|
dropped = True
|
||||||
|
continue
|
||||||
|
if token not in safe:
|
||||||
|
safe.append(token)
|
||||||
|
except Exception:
|
||||||
|
# Fail closed: a reference that cannot be proven safe is dropped.
|
||||||
|
dropped = True
|
||||||
|
continue
|
||||||
|
return (tuple(safe), dropped)
|
||||||
|
|
||||||
|
|
||||||
|
def _safe_session_id(value: Any) -> str | None:
|
||||||
|
"""Return a session identifier only when it is safe to emit.
|
||||||
|
|
||||||
|
The value is authoritative source data — a session the record names for
|
||||||
|
itself — but it is still free text. It is dropped when redaction alters it
|
||||||
|
or when it is a bare secret-shaped hex run, so a credential parked in a
|
||||||
|
session field can never reach the payload or be echoed back by a filter.
|
||||||
|
"""
|
||||||
|
if value is None:
|
||||||
|
return None
|
||||||
|
text = str(value).strip()
|
||||||
|
if not text:
|
||||||
|
return None
|
||||||
|
if _BARE_SECRET_SHAPE.match(text):
|
||||||
|
return None
|
||||||
|
return text if _redact(text) == text else None
|
||||||
|
|
||||||
|
|
||||||
|
def _safe_record_id(value: Any) -> str | None:
|
||||||
|
"""Return a source record id only when it is a plain numeric identifier.
|
||||||
|
|
||||||
|
``event_key`` is serialized verbatim and is the deterministic pagination
|
||||||
|
tiebreak, so an id is interpolated into it only when it has the shape both
|
||||||
|
real sources actually produce. A record whose identity cannot be trusted is
|
||||||
|
refused by the caller rather than keyed on.
|
||||||
|
"""
|
||||||
|
if value is None or isinstance(value, bool):
|
||||||
|
return None
|
||||||
|
if isinstance(value, int):
|
||||||
|
return str(value)
|
||||||
|
text = str(value).strip()
|
||||||
|
return text if _RECORD_ID_SHAPE.match(text) else None
|
||||||
|
|
||||||
|
|
||||||
|
def _safe_cp_event_type(value: Any) -> tuple[str, bool]:
|
||||||
|
"""Validate a stored control-plane event type. Returns ``(type, unsafe)``.
|
||||||
|
|
||||||
|
The stored value is externally influenced — whichever producer wrote the
|
||||||
|
``events`` row chose the string — and ``to_dict`` serializes it verbatim, so
|
||||||
|
it passes a boundary of its own instead of relying on the one ``message``
|
||||||
|
passes. A value survives only when it is an ordinary identifier, is not a
|
||||||
|
bare secret-shaped hex run, and is unchanged by a redaction pass. Anything
|
||||||
|
else fails closed to :data:`UNSAFE_EVENT_TYPE`: the record stays visible as
|
||||||
|
an audit entry, but the value itself is never republished — not verbatim,
|
||||||
|
not partially sanitized, and not rewritten into some other valid-looking
|
||||||
|
type that would misdescribe what happened.
|
||||||
|
"""
|
||||||
|
text = ("" if value is None else str(value)).strip()
|
||||||
|
if not text:
|
||||||
|
return ("", False)
|
||||||
|
if _BARE_SECRET_SHAPE.match(text):
|
||||||
|
return (UNSAFE_EVENT_TYPE, True)
|
||||||
|
if not _CP_EVENT_TYPE_SHAPE.match(text):
|
||||||
|
return (UNSAFE_EVENT_TYPE, True)
|
||||||
|
if _redact(text) != text:
|
||||||
|
return (UNSAFE_EVENT_TYPE, True)
|
||||||
|
return (text, False)
|
||||||
|
|
||||||
|
|
||||||
|
def _safe_echo(value: Any) -> Any:
|
||||||
|
"""Guard a scalar that is echoed back rather than derived from a record.
|
||||||
|
|
||||||
|
Query scope and filter values are caller-supplied and are reflected in the
|
||||||
|
response so an operator can see what was asked. Reflection is still
|
||||||
|
emission: a value redaction would alter, or a bare secret-shaped hex run, is
|
||||||
|
replaced by the placeholder instead of being echoed verbatim. Ordinary
|
||||||
|
scope and filter values pass through untouched.
|
||||||
|
"""
|
||||||
|
if value is None or isinstance(value, (int, bool)):
|
||||||
|
return value
|
||||||
|
text = str(value)
|
||||||
|
if _BARE_SECRET_SHAPE.match(text.strip()):
|
||||||
|
return console_redaction.REDACTED
|
||||||
|
return _redact(text)
|
||||||
|
|
||||||
|
|
||||||
|
def adapt_cp_events(rows: Iterable[dict[str, Any]]) -> list[WorkflowEvent]:
|
||||||
|
"""Adapt control-plane ``events`` rows (joined to work_items) into events.
|
||||||
|
|
||||||
|
Each row is expected to carry ``event_id``, ``event_type``, ``message``,
|
||||||
|
``created_at`` and the joined work-item ``kind``/``number``. Rows missing
|
||||||
|
an id or type are skipped so a partially written table never raises.
|
||||||
|
"""
|
||||||
|
events: list[WorkflowEvent] = []
|
||||||
|
for row in rows or []:
|
||||||
|
try:
|
||||||
|
event_id = _safe_record_id(row.get("event_id"))
|
||||||
|
raw_event_type = (row.get("event_type") or "").strip()
|
||||||
|
if event_id is None or not raw_event_type:
|
||||||
|
continue
|
||||||
|
# The stored type is source data, not a trusted constant: validate
|
||||||
|
# it before it is serialized, exactly as `message` below is redacted
|
||||||
|
# before it is serialized.
|
||||||
|
event_type, event_type_unsafe = _safe_cp_event_type(raw_event_type)
|
||||||
|
kind = row.get("kind")
|
||||||
|
number = row.get("number")
|
||||||
|
issue_no, pr_no = _kind_to_numbers(kind, number)
|
||||||
|
sensitive = event_type_unsafe or any(
|
||||||
|
hint in raw_event_type.lower() for hint in _SENSITIVE_EVENT_HINTS
|
||||||
|
)
|
||||||
|
events.append(
|
||||||
|
WorkflowEvent(
|
||||||
|
source=SOURCE_CONTROL_PLANE,
|
||||||
|
event_type=event_type,
|
||||||
|
event_key=f"cp:{event_id}",
|
||||||
|
timestamp=_parse_ts(row.get("created_at")),
|
||||||
|
issue_number=issue_no,
|
||||||
|
pr_number=pr_no,
|
||||||
|
# No session_id: the control-plane events table is
|
||||||
|
# (event_id, work_item_id, event_type, message, created_at)
|
||||||
|
# and records no session. Inventing one from the work item
|
||||||
|
# or the message text would be a guess, so this source
|
||||||
|
# declares the session dimension unsupported instead
|
||||||
|
# (_SOURCE_FILTER_SUPPORT) and the query layer refuses a
|
||||||
|
# session filter it cannot honestly answer.
|
||||||
|
message=_redact(row.get("message")),
|
||||||
|
correlation_id=_correlation_for(kind, number),
|
||||||
|
sensitive=sensitive,
|
||||||
|
)
|
||||||
|
)
|
||||||
|
except Exception:
|
||||||
|
# A single malformed row must not sink the whole adaptation.
|
||||||
|
continue
|
||||||
|
return events
|
||||||
|
|
||||||
|
|
||||||
|
def adapt_cth_comments(
|
||||||
|
comments: Iterable[dict[str, Any]],
|
||||||
|
*,
|
||||||
|
kind: str,
|
||||||
|
number: int,
|
||||||
|
) -> list[WorkflowEvent]:
|
||||||
|
"""Adapt Gitea Canonical Thread Handoff (CTH) comments into events.
|
||||||
|
|
||||||
|
Only comments that parse as a CTH (``canonical_thread_handoff.parse_cth_comment``)
|
||||||
|
become events; ordinary comments are ignored. ``kind``/``number`` scope the
|
||||||
|
events to the issue or PR the comments belong to.
|
||||||
|
"""
|
||||||
|
# Imported lazily so this module has no import-time dependency on the
|
||||||
|
# handoff parser when only the control-plane adapter is used.
|
||||||
|
from canonical_thread_handoff import is_known_cth_type, parse_cth_comment
|
||||||
|
|
||||||
|
# ``kind``/``number`` are interpolated into event_key and correlation_id, so
|
||||||
|
# they are normalised once here. A scope this adapter cannot express is
|
||||||
|
# refused outright rather than serialized into an identifier.
|
||||||
|
kind = (kind or "").strip().lower()
|
||||||
|
if kind not in ("issue", "pr"):
|
||||||
|
return []
|
||||||
|
try:
|
||||||
|
number = int(number)
|
||||||
|
except (TypeError, ValueError):
|
||||||
|
return []
|
||||||
|
|
||||||
|
issue_no, pr_no = _kind_to_numbers(kind, number)
|
||||||
|
correlation = _correlation_for(kind, number)
|
||||||
|
events: list[WorkflowEvent] = []
|
||||||
|
for comment in comments or []:
|
||||||
|
try:
|
||||||
|
body = comment.get("body") or ""
|
||||||
|
parsed = parse_cth_comment(body)
|
||||||
|
if not parsed:
|
||||||
|
continue
|
||||||
|
fields = parsed.get("fields") or {}
|
||||||
|
cth_type = parsed.get("cth_type") or ""
|
||||||
|
comment_id = _safe_record_id(comment.get("id"))
|
||||||
|
if comment_id is None:
|
||||||
|
continue
|
||||||
|
# The CTH heading is free text: the parser accepts whatever follows
|
||||||
|
# "## CTH:", and only the write and assess paths check it against
|
||||||
|
# the contract. Check it here too — an unrecognised heading is
|
||||||
|
# reported as such rather than serialized into event_type, so
|
||||||
|
# arbitrary, malformed, or secret-shaped heading content has no way
|
||||||
|
# through. Declared types are preserved exactly.
|
||||||
|
cth_type_known = is_known_cth_type(cth_type)
|
||||||
|
# Redaction runs first, and every derived value is taken from the
|
||||||
|
# redacted text — deriving evidence refs from the raw proof would
|
||||||
|
# re-emit exactly what redaction was about to remove.
|
||||||
|
decision = _redact(fields.get("decision"))
|
||||||
|
proof = _redact(fields.get("proof"))
|
||||||
|
next_action = _redact(fields.get("next action"))
|
||||||
|
refs, refs_dropped = _validated_evidence_refs(
|
||||||
|
_extract_evidence_refs(proof, decision)
|
||||||
|
)
|
||||||
|
events.append(
|
||||||
|
WorkflowEvent(
|
||||||
|
source=SOURCE_GITEA_HANDOFF,
|
||||||
|
event_type=(
|
||||||
|
f"handoff:{cth_type.strip()}"
|
||||||
|
if cth_type_known
|
||||||
|
else UNKNOWN_HANDOFF_EVENT_TYPE
|
||||||
|
),
|
||||||
|
event_key=f"cth:{kind}:{number}:{comment_id}",
|
||||||
|
timestamp=_parse_ts(comment.get("created_at")),
|
||||||
|
actor=_redact((comment.get("user") or {}).get("login")),
|
||||||
|
role=_redact(fields.get("next owner")),
|
||||||
|
issue_number=issue_no,
|
||||||
|
pr_number=pr_no,
|
||||||
|
# A CTH names its own session when the producer records one;
|
||||||
|
# it is read from that declared field, never inferred from
|
||||||
|
# unrelated text.
|
||||||
|
session_id=_safe_session_id(fields.get("session")),
|
||||||
|
decision=decision,
|
||||||
|
message=next_action or _redact(fields.get("status")),
|
||||||
|
correlation_id=correlation,
|
||||||
|
evidence_refs=refs,
|
||||||
|
sensitive=refs_dropped or not cth_type_known,
|
||||||
|
)
|
||||||
|
)
|
||||||
|
except Exception:
|
||||||
|
continue
|
||||||
|
return events
|
||||||
|
|
||||||
|
|
||||||
|
# --------------------------------------------------------------------------- #
|
||||||
|
# Read-only control-plane event source. #
|
||||||
|
# --------------------------------------------------------------------------- #
|
||||||
|
|
||||||
|
_CP_EVENTS_QUERY = """
|
||||||
|
SELECT e.event_id AS event_id,
|
||||||
|
e.event_type AS event_type,
|
||||||
|
e.message AS message,
|
||||||
|
e.created_at AS created_at,
|
||||||
|
w.kind AS kind,
|
||||||
|
w.number AS number
|
||||||
|
FROM events e
|
||||||
|
JOIN work_items w ON e.work_item_id = w.work_item_id
|
||||||
|
WHERE w.remote = ? AND w.org = ? AND w.repo = ?
|
||||||
|
"""
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class SourceStatus:
|
||||||
|
"""Fail-soft status for one timeline source.
|
||||||
|
|
||||||
|
``supported_filters`` states which filter dimensions this source's records
|
||||||
|
can carry; ``unsupported_filters`` names the requested dimensions it cannot,
|
||||||
|
so an operator can see *why* a source contributed nothing rather than being
|
||||||
|
left to read an empty list as an absence of activity.
|
||||||
|
"""
|
||||||
|
|
||||||
|
name: str
|
||||||
|
ok: bool
|
||||||
|
reason: str | None = None
|
||||||
|
count: int = 0
|
||||||
|
supported_filters: tuple[str, ...] = ()
|
||||||
|
unsupported_filters: tuple[str, ...] = ()
|
||||||
|
|
||||||
|
def to_dict(self) -> dict[str, Any]:
|
||||||
|
return {
|
||||||
|
"name": self.name,
|
||||||
|
"ok": self.ok,
|
||||||
|
"reason": self.reason,
|
||||||
|
"count": self.count,
|
||||||
|
"supported_filters": list(self.supported_filters),
|
||||||
|
"unsupported_filters": list(self.unsupported_filters),
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
def _cp_status(*, ok: bool, reason: str | None = None, count: int = 0) -> SourceStatus:
|
||||||
|
return SourceStatus(
|
||||||
|
SOURCE_CONTROL_PLANE,
|
||||||
|
ok=ok,
|
||||||
|
# A failure reason is serialized like any other field and is often an
|
||||||
|
# exception string carrying a path or a transport error, so it crosses
|
||||||
|
# the redaction boundary too. Static reasons pass through unchanged.
|
||||||
|
reason=_redact(reason),
|
||||||
|
count=count,
|
||||||
|
supported_filters=_SOURCE_FILTER_SUPPORT[SOURCE_CONTROL_PLANE],
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def _handoff_status(*, ok: bool, reason: str | None = None, count: int = 0) -> SourceStatus:
|
||||||
|
return SourceStatus(
|
||||||
|
SOURCE_GITEA_HANDOFF,
|
||||||
|
ok=ok,
|
||||||
|
# Same boundary as the control-plane status: this reason can quote an
|
||||||
|
# error raised by a live authenticated fetch.
|
||||||
|
reason=_redact(reason),
|
||||||
|
count=count,
|
||||||
|
supported_filters=_SOURCE_FILTER_SUPPORT[SOURCE_GITEA_HANDOFF],
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def read_cp_events(
|
||||||
|
*,
|
||||||
|
remote: str,
|
||||||
|
org: str,
|
||||||
|
repo: str,
|
||||||
|
db_path: str | None = None,
|
||||||
|
) -> tuple[list[WorkflowEvent], SourceStatus]:
|
||||||
|
"""Read scoped control-plane events read-only. Never creates the DB.
|
||||||
|
|
||||||
|
Opens the SQLite file through a ``mode=ro`` URI: a health/timeline read
|
||||||
|
must never create directories or run the schema migration that
|
||||||
|
``ControlPlaneDB()`` performs on construction. A missing or unreadable DB
|
||||||
|
degrades to a status with a reason.
|
||||||
|
"""
|
||||||
|
path = (db_path or control_plane_db.default_db_path()).strip()
|
||||||
|
conn: sqlite3.Connection | None = None
|
||||||
|
try:
|
||||||
|
conn = sqlite3.connect(f"file:{path}?mode=ro", uri=True)
|
||||||
|
conn.row_factory = sqlite3.Row
|
||||||
|
cursor = conn.execute(_CP_EVENTS_QUERY, (remote, org, repo))
|
||||||
|
rows = [dict(r) for r in cursor.fetchall()]
|
||||||
|
except sqlite3.OperationalError as exc:
|
||||||
|
return ([], _cp_status(ok=False, reason=f"control-plane DB unavailable: {exc}"))
|
||||||
|
except sqlite3.Error as exc:
|
||||||
|
return ([], _cp_status(ok=False, reason=f"control-plane read failed: {exc}"))
|
||||||
|
finally:
|
||||||
|
if conn is not None:
|
||||||
|
conn.close()
|
||||||
|
events = adapt_cp_events(rows)
|
||||||
|
return (events, _cp_status(ok=True, count=len(events)))
|
||||||
|
|
||||||
|
|
||||||
|
# --------------------------------------------------------------------------- #
|
||||||
|
# Filter, sort, paginate. #
|
||||||
|
# --------------------------------------------------------------------------- #
|
||||||
|
|
||||||
|
|
||||||
|
def filter_events(
|
||||||
|
events: Iterable[WorkflowEvent],
|
||||||
|
*,
|
||||||
|
issue: int | None = None,
|
||||||
|
pr: int | None = None,
|
||||||
|
session: str | None = None,
|
||||||
|
) -> list[WorkflowEvent]:
|
||||||
|
"""Filter events by issue number, PR number, and/or session id.
|
||||||
|
|
||||||
|
Filters are conjunctive. A filter that names a dimension an event does not
|
||||||
|
carry excludes that event (an issue filter excludes PR-only events).
|
||||||
|
"""
|
||||||
|
out: list[WorkflowEvent] = []
|
||||||
|
for ev in events:
|
||||||
|
if issue is not None and ev.issue_number != issue:
|
||||||
|
continue
|
||||||
|
if pr is not None and ev.pr_number != pr:
|
||||||
|
continue
|
||||||
|
if session is not None and ev.session_id != session:
|
||||||
|
continue
|
||||||
|
out.append(ev)
|
||||||
|
return out
|
||||||
|
|
||||||
|
|
||||||
|
def sort_events(events: Iterable[WorkflowEvent]) -> list[WorkflowEvent]:
|
||||||
|
"""Return events in stable timeline order (ascending)."""
|
||||||
|
return sorted(events, key=lambda ev: ev.sort_key())
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class TimelinePage:
|
||||||
|
"""One page of the sorted, filtered timeline."""
|
||||||
|
|
||||||
|
events: tuple[WorkflowEvent, ...]
|
||||||
|
total: int
|
||||||
|
limit: int
|
||||||
|
offset: int
|
||||||
|
|
||||||
|
@property
|
||||||
|
def next_offset(self) -> int | None:
|
||||||
|
nxt = self.offset + len(self.events)
|
||||||
|
return nxt if nxt < self.total else None
|
||||||
|
|
||||||
|
def to_dict(self) -> dict[str, Any]:
|
||||||
|
return {
|
||||||
|
"events": [ev.to_dict() for ev in self.events],
|
||||||
|
"pagination": {
|
||||||
|
"total": self.total,
|
||||||
|
"limit": self.limit,
|
||||||
|
"offset": self.offset,
|
||||||
|
"returned": len(self.events),
|
||||||
|
"next_offset": self.next_offset,
|
||||||
|
"has_more": self.next_offset is not None,
|
||||||
|
},
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
_MAX_LIMIT = 500
|
||||||
|
_DEFAULT_LIMIT = 50
|
||||||
|
|
||||||
|
|
||||||
|
def _coerce_bounds(limit: int | None, offset: int | None) -> tuple[int, int]:
|
||||||
|
try:
|
||||||
|
lim = int(limit) if limit is not None else _DEFAULT_LIMIT
|
||||||
|
except (TypeError, ValueError):
|
||||||
|
lim = _DEFAULT_LIMIT
|
||||||
|
try:
|
||||||
|
off = int(offset) if offset is not None else 0
|
||||||
|
except (TypeError, ValueError):
|
||||||
|
off = 0
|
||||||
|
lim = max(1, min(lim, _MAX_LIMIT))
|
||||||
|
off = max(0, off)
|
||||||
|
return (lim, off)
|
||||||
|
|
||||||
|
|
||||||
|
def paginate(events: list[WorkflowEvent], *, limit: int | None, offset: int | None) -> TimelinePage:
|
||||||
|
lim, off = _coerce_bounds(limit, offset)
|
||||||
|
window = events[off : off + lim]
|
||||||
|
return TimelinePage(events=tuple(window), total=len(events), limit=lim, offset=off)
|
||||||
|
|
||||||
|
|
||||||
|
# --------------------------------------------------------------------------- #
|
||||||
|
# Composition — load_timeline aggregates all sources, fail-soft. #
|
||||||
|
# --------------------------------------------------------------------------- #
|
||||||
|
|
||||||
|
# A comment source is a callable that, given (kind, number), returns the raw
|
||||||
|
# Gitea comment list for that issue/PR. The route supplies a live fail-soft
|
||||||
|
# fetcher; tests supply a fixture. When None, the handoff source is reported as
|
||||||
|
# not-run (never silently empty-and-healthy).
|
||||||
|
CommentSource = Callable[[str, int], list[dict[str, Any]]]
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass(frozen=True)
|
||||||
|
class TimelineSnapshot:
|
||||||
|
"""One answered timeline query.
|
||||||
|
|
||||||
|
``ok`` is False when the query could not be answered as asked — currently
|
||||||
|
when a requested filter dimension no surviving source can carry was
|
||||||
|
supplied. The page is then empty *and* the snapshot says so, because an
|
||||||
|
``ok`` empty page is a claim that no such activity exists.
|
||||||
|
"""
|
||||||
|
|
||||||
|
schema_version: int
|
||||||
|
remote: str
|
||||||
|
org: str
|
||||||
|
repo: str
|
||||||
|
filters: dict[str, Any]
|
||||||
|
page: TimelinePage
|
||||||
|
sources: tuple[SourceStatus, ...]
|
||||||
|
ok: bool = True
|
||||||
|
error: dict[str, Any] | None = None
|
||||||
|
|
||||||
|
def to_dict(self) -> dict[str, Any]:
|
||||||
|
return {
|
||||||
|
"ok": self.ok,
|
||||||
|
"error": self.error,
|
||||||
|
"schema_version": self.schema_version,
|
||||||
|
# Scope and filters are echoed caller input, not derived record
|
||||||
|
# data. Reflecting a value is still emitting it, so both cross the
|
||||||
|
# same boundary; ordinary scope and filter values are unchanged.
|
||||||
|
"scope": {
|
||||||
|
"remote": _safe_echo(self.remote),
|
||||||
|
"org": _safe_echo(self.org),
|
||||||
|
"repo": _safe_echo(self.repo),
|
||||||
|
},
|
||||||
|
"filters": {key: _safe_echo(value) for key, value in self.filters.items()},
|
||||||
|
"sources": [s.to_dict() for s in self.sources],
|
||||||
|
**self.page.to_dict(),
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
def _unanswerable_reasons(
|
||||||
|
statuses: Iterable[SourceStatus], unanswerable: Iterable[str]
|
||||||
|
) -> list[dict[str, str]]:
|
||||||
|
"""Explain, per source, why each unanswerable dimension went unanswered."""
|
||||||
|
out: list[dict[str, str]] = []
|
||||||
|
for status in statuses:
|
||||||
|
for dim in unanswerable:
|
||||||
|
if dim not in status.supported_filters:
|
||||||
|
reason = _SOURCE_FILTER_LIMITS.get(
|
||||||
|
(status.name, dim), f"this source's records carry no {dim} identity"
|
||||||
|
)
|
||||||
|
elif not status.ok:
|
||||||
|
reason = (
|
||||||
|
f"this source can carry {dim} but did not run: "
|
||||||
|
f"{status.reason or 'unavailable'}"
|
||||||
|
)
|
||||||
|
else:
|
||||||
|
continue
|
||||||
|
out.append({"source": status.name, "filter": dim, "reason": reason})
|
||||||
|
return out
|
||||||
|
|
||||||
|
|
||||||
|
def load_timeline(
|
||||||
|
*,
|
||||||
|
remote: str,
|
||||||
|
org: str,
|
||||||
|
repo: str,
|
||||||
|
issue: int | None = None,
|
||||||
|
pr: int | None = None,
|
||||||
|
session: str | None = None,
|
||||||
|
limit: int | None = None,
|
||||||
|
offset: int | None = None,
|
||||||
|
db_path: str | None = None,
|
||||||
|
comment_source: CommentSource | None = None,
|
||||||
|
) -> TimelineSnapshot:
|
||||||
|
"""Aggregate every timeline source into one filtered, paginated snapshot.
|
||||||
|
|
||||||
|
Sources are read independently and fail soft: an unavailable source
|
||||||
|
contributes a ``SourceStatus`` with ``ok=False`` and a reason, and never
|
||||||
|
collapses the whole timeline. The handoff source only runs when a specific
|
||||||
|
issue or PR is requested (a handoff comment belongs to one thread) and a
|
||||||
|
``comment_source`` is available; otherwise it is reported as ``not run``
|
||||||
|
rather than as an empty-and-healthy source.
|
||||||
|
|
||||||
|
A filter dimension that no surviving source can carry — a ``session``
|
||||||
|
filter when the only source that ran is the control plane, whose events
|
||||||
|
record no session — is refused with ``ok=False`` and a structured error
|
||||||
|
instead of being answered with an empty page.
|
||||||
|
"""
|
||||||
|
all_events: list[WorkflowEvent] = []
|
||||||
|
statuses: list[SourceStatus] = []
|
||||||
|
|
||||||
|
cp_events, cp_status = read_cp_events(remote=remote, org=org, repo=repo, db_path=db_path)
|
||||||
|
all_events.extend(cp_events)
|
||||||
|
statuses.append(cp_status)
|
||||||
|
|
||||||
|
# Gitea handoff comments are thread-scoped: only fetch when the caller
|
||||||
|
# narrowed to one issue or PR, and only when a source was provided.
|
||||||
|
handoff_target: tuple[str, int] | None = None
|
||||||
|
if pr is not None:
|
||||||
|
handoff_target = ("pr", pr)
|
||||||
|
elif issue is not None:
|
||||||
|
handoff_target = ("issue", issue)
|
||||||
|
|
||||||
|
if handoff_target is None:
|
||||||
|
statuses.append(
|
||||||
|
_handoff_status(
|
||||||
|
ok=False,
|
||||||
|
reason="not run: handoff comments are thread-scoped; filter by issue or pr to include them",
|
||||||
|
)
|
||||||
|
)
|
||||||
|
elif comment_source is None:
|
||||||
|
statuses.append(
|
||||||
|
_handoff_status(
|
||||||
|
ok=False,
|
||||||
|
reason="not run: no comment source configured for this timeline read",
|
||||||
|
)
|
||||||
|
)
|
||||||
|
else:
|
||||||
|
kind, number = handoff_target
|
||||||
|
try:
|
||||||
|
comments = comment_source(kind, number) or []
|
||||||
|
handoff_events = adapt_cth_comments(comments, kind=kind, number=number)
|
||||||
|
all_events.extend(handoff_events)
|
||||||
|
statuses.append(_handoff_status(ok=True, count=len(handoff_events)))
|
||||||
|
except Exception as exc: # fail soft: a fetch/parse error degrades this source only
|
||||||
|
statuses.append(_handoff_status(ok=False, reason=f"handoff source failed: {exc}"))
|
||||||
|
|
||||||
|
requested = tuple(
|
||||||
|
name
|
||||||
|
for name, value in ((FILTER_ISSUE, issue), (FILTER_PR, pr), (FILTER_SESSION, session))
|
||||||
|
if value is not None
|
||||||
|
)
|
||||||
|
statuses = [
|
||||||
|
replace(
|
||||||
|
status,
|
||||||
|
unsupported_filters=tuple(
|
||||||
|
dim for dim in requested if dim not in status.supported_filters
|
||||||
|
),
|
||||||
|
)
|
||||||
|
for status in statuses
|
||||||
|
]
|
||||||
|
filters = {"issue": issue, "pr": pr, "session": session}
|
||||||
|
|
||||||
|
# A dimension is answerable only if a source that actually ran can carry it.
|
||||||
|
# If none can, refuse: an empty page would assert "no such activity", which
|
||||||
|
# is a claim this timeline is not in a position to make.
|
||||||
|
answerable: set[str] = set()
|
||||||
|
for status in statuses:
|
||||||
|
if status.ok:
|
||||||
|
answerable.update(status.supported_filters)
|
||||||
|
unanswerable = tuple(dim for dim in requested if dim not in answerable)
|
||||||
|
|
||||||
|
if unanswerable:
|
||||||
|
return TimelineSnapshot(
|
||||||
|
schema_version=TIMELINE_SCHEMA_VERSION,
|
||||||
|
remote=remote,
|
||||||
|
org=org,
|
||||||
|
repo=repo,
|
||||||
|
filters=filters,
|
||||||
|
page=paginate([], limit=limit, offset=offset),
|
||||||
|
sources=tuple(statuses),
|
||||||
|
ok=False,
|
||||||
|
error={
|
||||||
|
"code": "filter_not_supported",
|
||||||
|
"unsupported_filters": list(unanswerable),
|
||||||
|
"detail": (
|
||||||
|
"no timeline source that ran can answer "
|
||||||
|
+ ", ".join(f"'{dim}'" for dim in unanswerable)
|
||||||
|
+ "; the result is refused rather than returned empty"
|
||||||
|
),
|
||||||
|
"sources": _unanswerable_reasons(statuses, unanswerable),
|
||||||
|
},
|
||||||
|
)
|
||||||
|
|
||||||
|
filtered = filter_events(all_events, issue=issue, pr=pr, session=session)
|
||||||
|
ordered = sort_events(filtered)
|
||||||
|
page = paginate(ordered, limit=limit, offset=offset)
|
||||||
|
|
||||||
|
return TimelineSnapshot(
|
||||||
|
schema_version=TIMELINE_SCHEMA_VERSION,
|
||||||
|
remote=remote,
|
||||||
|
org=org,
|
||||||
|
repo=repo,
|
||||||
|
filters=filters,
|
||||||
|
page=page,
|
||||||
|
sources=tuple(statuses),
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def snapshot_to_dict(snapshot: TimelineSnapshot) -> dict[str, Any]:
|
||||||
|
return snapshot.to_dict()
|
||||||
Reference in New Issue
Block a user