mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-10-01 10:53:14 +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>
105 lines
4 KiB
Python
105 lines
4 KiB
Python
"""Tool: ``read_repo_file``. Read repo files/dirs over the GitHub API (no sandbox).
|
|
|
|
The PR chat agent has no sandbox, so it reads source at a specific ref through
|
|
the GitHub contents API. Repo coordinates and a read-only token come from the
|
|
run config (seeded by the dashboard chat proxy).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import base64
|
|
from typing import Any
|
|
|
|
import httpx
|
|
from langgraph.config import get_config
|
|
|
|
from ..utils.github_checks import github_headers
|
|
|
|
_GITHUB_API = "https://api.github.com"
|
|
_MAX_FILE_BYTES = 256 * 1024
|
|
|
|
|
|
def _chat_repo_context() -> tuple[str, str, str | None, str | None]:
|
|
config = get_config()
|
|
configurable = config.get("configurable", {}) if isinstance(config, dict) else {}
|
|
if not isinstance(configurable, dict):
|
|
configurable = {}
|
|
owner = configurable.get("chat_repo_owner")
|
|
repo = configurable.get("chat_repo_name")
|
|
token = configurable.get("chat_github_token")
|
|
head_sha = configurable.get("chat_head_sha")
|
|
return (
|
|
owner if isinstance(owner, str) else "",
|
|
repo if isinstance(repo, str) else "",
|
|
token if isinstance(token, str) and token else None,
|
|
head_sha if isinstance(head_sha, str) and head_sha else None,
|
|
)
|
|
|
|
|
|
async def read_repo_file(path: str, ref: str | None = None) -> dict[str, Any]:
|
|
"""Read a file (or list a directory) from the PR's repository at a git ref.
|
|
|
|
Use this to inspect code beyond the diff — callers, definitions, neighboring
|
|
modules, config — at the exact commit under review. The diff itself is
|
|
already available as the virtual file ``/pr/diff.patch``.
|
|
|
|
Args:
|
|
path: Repo-relative path, e.g. ``src/app/main.py`` or ``src/app`` for a
|
|
directory listing. Leading slashes are ignored.
|
|
ref: Git ref (branch, tag, or SHA). Defaults to the PR head commit.
|
|
|
|
Returns:
|
|
For a file: ``{success, path, ref, content, truncated}``.
|
|
For a directory: ``{success, path, ref, entries}`` where each entry is
|
|
``{name, type, path}``.
|
|
On failure: ``{success: False, error}``.
|
|
"""
|
|
owner, repo, token, head_sha = _chat_repo_context()
|
|
if not owner or not repo:
|
|
return {"success": False, "error": "repository context unavailable"}
|
|
|
|
clean_path = path.strip().lstrip("/")
|
|
resolved_ref = (ref or head_sha or "").strip()
|
|
params = {"ref": resolved_ref} if resolved_ref else None
|
|
url = f"{_GITHUB_API}/repos/{owner}/{repo}/contents/{clean_path}"
|
|
headers = github_headers(token or "")
|
|
try:
|
|
async with httpx.AsyncClient(timeout=30) as client:
|
|
response = await client.get(url, headers=headers, params=params)
|
|
except httpx.HTTPError as exc:
|
|
return {"success": False, "error": f"GitHub request failed: {exc!s}"}
|
|
|
|
if response.status_code == 404:
|
|
return {"success": False, "error": f"not found: {clean_path} @ {resolved_ref or 'default'}"}
|
|
if response.status_code >= 400:
|
|
return {"success": False, "error": f"GitHub returned {response.status_code}"}
|
|
|
|
payload = response.json()
|
|
if isinstance(payload, list):
|
|
entries = [
|
|
{
|
|
"name": item.get("name"),
|
|
"type": item.get("type"),
|
|
"path": item.get("path"),
|
|
}
|
|
for item in payload
|
|
if isinstance(item, dict)
|
|
]
|
|
return {"success": True, "path": clean_path, "ref": resolved_ref, "entries": entries}
|
|
|
|
if not isinstance(payload, dict) or payload.get("type") != "file":
|
|
return {"success": False, "error": f"unsupported content type for {clean_path}"}
|
|
|
|
encoded = payload.get("content")
|
|
if not isinstance(encoded, str):
|
|
return {"success": False, "error": "file content unavailable (too large for contents API)"}
|
|
raw = base64.b64decode(encoded)
|
|
truncated = len(raw) > _MAX_FILE_BYTES
|
|
text = raw[:_MAX_FILE_BYTES].decode("utf-8", errors="replace")
|
|
return {
|
|
"success": True,
|
|
"path": clean_path,
|
|
"ref": resolved_ref,
|
|
"content": text,
|
|
"truncated": truncated,
|
|
}
|