open-swe/agent/tools/list_review_findings.py
Johannes du Plessis 209132d355
refactor: durable interrupt dispatch + completion webhook (#1621)
* 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>
2026-06-26 13:48:38 -07:00

70 lines
2.4 KiB
Python

"""Tool: ``list_review_findings``. Read the published review's findings.
The PR chat agent runs on its own thread; the findings live on the canonical
reviewer thread for the PR. The reviewer thread id is seeded into the run config
by the dashboard chat proxy.
"""
from __future__ import annotations
from typing import Any
from langgraph.config import get_config
from ..reviewer_findings import list_findings as list_findings_async
_COMPACT_FIELDS = (
"id",
"severity",
"confidence",
"category",
"title",
"description",
"suggestion",
"file",
"start_line",
"end_line",
"side",
"status",
"resolution_note",
)
def _compact(finding: dict[str, Any]) -> dict[str, Any]:
return {key: finding.get(key) for key in _COMPACT_FIELDS if finding.get(key) is not None}
async def list_review_findings(status_filter: str | None = None) -> dict[str, Any]:
"""List the findings the reviewer published for this PR.
Use this to ground answers about the review — what was flagged, the
severity/confidence, and any resolution notes. Prefer quoting these over
re-deriving issues from the diff.
Args:
status_filter: One of ``open``, ``resolved``, ``dismissed``. ``None``
(default) returns findings of every status.
Returns:
``{findings, count}``; ``{findings: [], count: 0, error}`` on failure.
"""
if status_filter is not None and status_filter not in {"open", "resolved", "dismissed"}:
return {"findings": [], "count": 0, "error": f"Invalid status_filter: {status_filter}"}
config = get_config()
configurable = config.get("configurable", {}) if isinstance(config, dict) else {}
reviewer_thread_id = (
configurable.get("reviewer_thread_id") if isinstance(configurable, dict) else None
)
if not isinstance(reviewer_thread_id, str) or not reviewer_thread_id:
return {"findings": [], "count": 0, "error": "reviewer thread unavailable"}
try:
findings = await list_findings_async(reviewer_thread_id)
except Exception as exc: # noqa: BLE001
return {"findings": [], "count": 0, "error": f"could not load findings: {exc!s}"}
if status_filter is not None:
findings = [f for f in findings if f.get("status") == status_filter]
compact = [_compact(f) for f in findings]
return {"findings": compact, "count": len(compact)}