mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 17:23:15 +00:00
* wip(rebuild): core reliability spine
- remove PR-babysitting (ci_autofix + ci_monitor graph + webhook wiring)
- dispatch core: agent/dispatch.py with multitask_strategy=interrupt +
durability=sync + completion webhook; reroute all webhook + plan triggers;
drop the racy in-process lock + is_thread_active busy-check
- completion webhook: agent/completion.py + /webhooks/run-complete loopback
route for failure/timeout replies (idempotent)
Co-authored-by: open-swe[bot]
* feat(rebuild): async tools, reconcile, shared http timeouts, assembly tuning
Parallel batch on top of the reliability spine:
- async-ify all 24 tools (drop asyncio.run; requests->httpx); re-implement the
http_request/fetch_url SSRF + DNS-rebinding defense httpx-natively and harden
the IP check to 'not is_global' (+ IPv4-mapped unwrap)
- reconcile.py: stale pending-run sweep (threads.search -> per-thread runs.list
-> cancel_many), wired into the scheduler graph via task='reconcile'
- shared DEFAULT_HTTP_TIMEOUT (agent/utils/http.py) on every bare
httpx.AsyncClient() across utils/dashboard/webapp/middleware
- run budget: MODEL_CALL_RECURSION_LIMIT 5000->250
- fix stale OpenAI->Anthropic fallback id (claude-opus-4-5 -> 4-8)
- drop redundant custom repair middleware (deepagents auto-adds PatchToolCalls)
- confirm tool-result eviction + summarization auto-wired via backend
- slim system prompt ~8% (full harness-profile rewrite deferred)
Co-authored-by: open-swe[bot]
* feat(rebuild): harness-profile prompt + split webhooks out of webapp
- prompt.py: own the system prompt via a registered harness profile
(OPEN_SWE_SHARED_BASE, kept neutral so the read-only reviewer/analyzer that
share it stay safe), registered across all 4 providers; per-thread values
stay in construct_system_prompt. Assembled main-agent prompt ~6.8k -> ~3.1k
tokens (~55% smaller); de-duped PR/commit/suite/force-push guidance; dropped
ALL-CAPS markers.
- webapp.py 3325 -> 1890 LOC: moved 14 per-source handlers into
agent/webhooks/{linear,slack,github}.py; webapp re-exports them for the
routes + tests; moved handlers reach shared helpers via the webapp namespace
to preserve the test suite's monkeypatch targets.
Full suite: 1168 passing, lint clean.
Co-authored-by: open-swe[bot]
* Restore MODEL_CALL_RECURSION_LIMIT to 5000 for long-running tasks
Reverts the 250 cap from the run-budget change — long-running tasks legitimately
need many model calls. The notify_step_limit_reached safety net still fires if a
run does hit the cap, so runs end with a signal either way.
Co-authored-by: open-swe[bot]
* fix: address PR review (auth, SSRF, interrupted status, redirect headers)
- completion.py: drop `interrupted` from failure statuses — with
multitask_strategy=interrupt a follow-up ends the prior run as interrupted,
which is healthy, not a failure to report. [open-swe]
- /webhooks/run-complete: shared-secret auth — dispatch appends ?token= when
RUN_COMPLETE_WEBHOOK_SECRET is set; route verifies via hmac.compare_digest.
[corridor-security]
- SSRF: extract the URL validator to agent/utils/url_safety.py and apply it
before server-side image fetches in multimodal.fetch_image_block.
[corridor-security]
- http_request: preserve caller headers/extensions across redirect hops instead
of dropping them on the first hop. [open-swe]
Co-authored-by: open-swe[bot]
* chore: remove REBUILD_PLAN.md (planning doc, not needed in the repo)
Co-authored-by: open-swe[bot]
* fix: fail closed on run-complete webhook auth when secret unset
Corridor follow-up: verify_run_complete_token returns False (not True) when
RUN_COMPLETE_WEBHOOK_SECRET is unset, so the public route is never
unauthenticated. Logs a startup warning when the secret is absent, and dispatch
skips registering the webhook when there's no secret (no rejected callbacks).
Co-authored-by: open-swe[bot]
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
121 lines
4.2 KiB
Python
121 lines
4.2 KiB
Python
"""Reconciliation sweep: cancel runs stuck in ``pending`` past their deadline.
|
|
|
|
The durable-dispatch contract relies on the platform's completion webhook to
|
|
end every run. When that webhook never fires (crash, lost delivery), a run can
|
|
sit in ``pending`` forever and hold its thread ``busy``. This sweep is the
|
|
safety net: find busy threads, look for stale ``pending`` runs on them, and
|
|
cancel the ones older than ``max_age_seconds`` so the thread frees up.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
from datetime import UTC, datetime
|
|
from typing import Any
|
|
|
|
from .utils.thread_ops import langgraph_client
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
_SEARCH_PAGE_SIZE = 100
|
|
|
|
|
|
def _parse_created_at(value: Any) -> datetime | None:
|
|
"""Parse a run's ``created_at`` into an aware UTC datetime, or None."""
|
|
if isinstance(value, datetime):
|
|
return value if value.tzinfo else value.replace(tzinfo=UTC)
|
|
if not isinstance(value, str) or not value:
|
|
return None
|
|
text = value.strip()
|
|
if text.endswith("Z"):
|
|
text = f"{text[:-1]}+00:00"
|
|
try:
|
|
parsed = datetime.fromisoformat(text)
|
|
except ValueError:
|
|
return None
|
|
return parsed if parsed.tzinfo else parsed.replace(tzinfo=UTC)
|
|
|
|
|
|
async def reconcile_stale_runs(*, max_age_seconds: int = 1800) -> dict[str, int]:
|
|
"""Cancel ``pending`` runs older than ``max_age_seconds`` on busy threads.
|
|
|
|
Walks every ``busy`` thread (paginated), lists its ``pending`` runs, and
|
|
cancels those whose ``created_at`` is older than the cutoff. Per-thread work
|
|
is wrapped in try/except so one bad thread never aborts the sweep.
|
|
|
|
Returns counts: ``{"threads_checked", "stale_runs", "cancelled"}``.
|
|
"""
|
|
client = langgraph_client()
|
|
now = datetime.now(UTC)
|
|
|
|
threads_checked = 0
|
|
stale_runs = 0
|
|
cancelled = 0
|
|
|
|
offset = 0
|
|
while True:
|
|
try:
|
|
threads = await client.threads.search(
|
|
metadata=None,
|
|
status="busy",
|
|
limit=_SEARCH_PAGE_SIZE,
|
|
offset=offset,
|
|
)
|
|
except Exception:
|
|
logger.exception("Reconcile sweep: thread search failed at offset %d", offset)
|
|
break
|
|
if not threads:
|
|
break
|
|
|
|
for thread in threads:
|
|
thread_id = thread.get("thread_id") if isinstance(thread, dict) else None
|
|
if not thread_id:
|
|
continue
|
|
threads_checked += 1
|
|
try:
|
|
runs = await client.runs.list(thread_id, status="pending")
|
|
stale_run_ids: list[str] = []
|
|
for run in runs:
|
|
created = _parse_created_at(run.get("created_at"))
|
|
if created is None:
|
|
logger.warning(
|
|
"Reconcile sweep: unparseable created_at on run %s (thread %s)",
|
|
run.get("run_id"),
|
|
thread_id,
|
|
)
|
|
continue
|
|
if (now - created).total_seconds() <= max_age_seconds:
|
|
continue
|
|
run_id = run.get("run_id")
|
|
if run_id:
|
|
stale_run_ids.append(run_id)
|
|
|
|
if not stale_run_ids:
|
|
continue
|
|
stale_runs += len(stale_run_ids)
|
|
await client.runs.cancel_many(
|
|
thread_id=thread_id,
|
|
run_ids=stale_run_ids,
|
|
action="interrupt",
|
|
)
|
|
cancelled += len(stale_run_ids)
|
|
logger.info(
|
|
"Reconcile sweep: cancelled %d stale pending run(s) on thread %s",
|
|
len(stale_run_ids),
|
|
thread_id,
|
|
)
|
|
except Exception:
|
|
logger.exception("Reconcile sweep: failed to reconcile thread %s", thread_id)
|
|
continue
|
|
|
|
if len(threads) < _SEARCH_PAGE_SIZE:
|
|
break
|
|
offset += _SEARCH_PAGE_SIZE
|
|
|
|
counts = {
|
|
"threads_checked": threads_checked,
|
|
"stale_runs": stale_runs,
|
|
"cancelled": cancelled,
|
|
}
|
|
logger.info("Reconcile sweep complete: %s", counts)
|
|
return counts
|