mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 18:33:15 +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>
90 lines
3.3 KiB
Python
90 lines
3.3 KiB
Python
"""Single durable dispatch contract behind every agent/reviewer run trigger.
|
|
|
|
Replaces the per-site ``runs.create`` calls (plus the ``is_thread_active``
|
|
busy-check and the custom store-queue) with one function that always uses:
|
|
|
|
- ``multitask_strategy="interrupt"`` — a follow-up halts the active run
|
|
(progress preserved by the sync checkpoint) and resumes the agent with full
|
|
history + the new message; on an idle thread it just starts. This is the
|
|
platform-native, cross-process replacement for the racy busy-check + queue.
|
|
- ``durability="sync"`` — checkpoint before each step so a crash/recycle
|
|
resumes from the last checkpoint instead of losing all work.
|
|
- ``webhook=COMPLETION_WEBHOOK_URL`` — the platform calls us on completion or
|
|
failure so every run ends with a signal even if the agent died.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
import os
|
|
from typing import Any
|
|
|
|
from langgraph_sdk import get_client
|
|
from langgraph_sdk.client import LangGraphClient
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
ContentBlocks = str | list[dict[str, Any]]
|
|
|
|
# Same-server FastAPI route the platform POSTs run completion/failure to. A
|
|
# relative URL loopback-posts into this app (no SSRF/loopback config needed);
|
|
# override with an absolute URL via env for split deployments. The route is
|
|
# fail-closed on RUN_COMPLETE_WEBHOOK_SECRET, so only register the webhook when
|
|
# the secret is set, appending it as ?token= so the route can verify the call
|
|
# came from us (completion.verify_run_complete_token). Unset → no webhook.
|
|
_COMPLETION_WEBHOOK_BASE = os.environ.get("COMPLETION_WEBHOOK_URL") or "/webhooks/run-complete"
|
|
_RUN_COMPLETE_SECRET = os.environ.get("RUN_COMPLETE_WEBHOOK_SECRET")
|
|
COMPLETION_WEBHOOK_URL: str | None
|
|
if not _RUN_COMPLETE_SECRET:
|
|
COMPLETION_WEBHOOK_URL = None
|
|
elif "?" in _COMPLETION_WEBHOOK_BASE:
|
|
COMPLETION_WEBHOOK_URL = _COMPLETION_WEBHOOK_BASE
|
|
else:
|
|
COMPLETION_WEBHOOK_URL = f"{_COMPLETION_WEBHOOK_BASE}?token={_RUN_COMPLETE_SECRET}"
|
|
|
|
|
|
def _langgraph_url() -> str:
|
|
return os.environ.get("LANGGRAPH_URL") or os.environ.get(
|
|
"LANGGRAPH_URL_PROD", "http://localhost:2024"
|
|
)
|
|
|
|
|
|
def dispatch_client() -> LangGraphClient:
|
|
return get_client(url=_langgraph_url())
|
|
|
|
|
|
async def dispatch_agent_run(
|
|
thread_id: str,
|
|
content: ContentBlocks,
|
|
configurable: dict[str, Any],
|
|
*,
|
|
source: str,
|
|
assistant_id: str = "agent",
|
|
metadata: dict[str, Any] | None = None,
|
|
client: LangGraphClient | None = None,
|
|
) -> dict[str, Any]:
|
|
"""Create (or interrupt-and-resume) a run for ``thread_id``.
|
|
|
|
Routes every Slack / Linear / GitHub / dashboard trigger through one
|
|
contract. ``source`` is for logging/metadata only; ``assistant_id`` selects
|
|
the graph (``"agent"`` or ``"reviewer"``).
|
|
"""
|
|
client = client or dispatch_client()
|
|
run = await client.runs.create(
|
|
thread_id,
|
|
assistant_id,
|
|
input={"messages": [{"role": "user", "content": content}]},
|
|
config={"configurable": configurable, "metadata": metadata or {}},
|
|
multitask_strategy="interrupt",
|
|
durability="sync",
|
|
webhook=COMPLETION_WEBHOOK_URL,
|
|
if_not_exists="create",
|
|
)
|
|
logger.info(
|
|
"Dispatched %s run on thread %s (source=%s, run=%s)",
|
|
assistant_id,
|
|
thread_id,
|
|
source,
|
|
run.get("run_id") if isinstance(run, dict) else None,
|
|
)
|
|
return run
|