mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 06:53:14 +00:00
4a55145bb1
* fix: reset stale sandbox creation sentinel Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com> * fix: treat SANDBOX_CREATING as a timestamped cross-process lock Only reset the sentinel when proven stale (older than the creation timeout); otherwise wait for the worker that holds the lock so a concurrent run does not create a duplicate sandbox. * feat(analyzer): outcomes dataset + bootstrap/continual split via skills Rename the review_style_analyzer graph to `analyzer` and split it into two modes, plus capture reviewer finding outcomes for continual learning. - Outcomes dataset: upsert resolved-by-commit (positive), dismissed (false positive), and GitHub/Slack thumbs findings into a single LangSmith dataset (openswe-reviewer-outcomes), keyed deterministically per finding+source. Emit points wired into update_finding, resolve_finding_thread, and the GitHub/Slack reaction handlers. - Two playbooks delivered as deepagents skills (bootstrap-repo-analysis, continual-learning), served as virtual files via a CompositeBackend /skills/ route + StateBackend (seeded into the run files channel at invoke time, never written to the sandbox). Mode is set by the launcher; continual runs fall back to the GitHub App installation token. - Split launcher into start_bootstrap_analysis + start_continual_run; register a per-repo nightly continual-learning cron when bootstrap completes. - New read_finding_outcomes tool feeds confirmed/dismissed findings back to the continual playbook. Tests for outcome label mapping, skills helper, and cron idempotency. * fix(analyzer): anchor continual cron runs to a real thread_id The nightly continual-learning cron is threadless, and get_analyzer early-returns an empty agent when configurable.thread_id is missing — so every cron-launched run no-op'd before reading outcomes or saving a refined prompt. Include the repo's deterministic analyzer thread_id in the continual run configurable so the run executes; the threadless run carries no message history, so nightly runs don't accumulate context. * refactor(analyzer): move cron lifecycle calls out of the review-styles store Drop the inline `analyzer_cron` imports from review_styles.py (added only to dodge a circular import) by relocating the cron-trigger calls to the layer above the store: registration to the save_review_style tool (after a prompt is saved) and removal to the dashboard delete route. review_styles.py is now a pure store again with top-level imports only. * refactor: hoist reviewer_outcomes imports to module level Move the two inline emit_finding_status_outcome imports introduced in this PR (update_finding, resolve_finding_thread) to top-level imports. reviewer_outcomes only depends on langsmith, so there is no circular import to avoid. --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
71 lines
2.7 KiB
Python
71 lines
2.7 KiB
Python
"""Tool: persist synthesized per-repo review style prompt."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import logging
|
|
from typing import Any
|
|
|
|
from langgraph.config import get_config
|
|
|
|
from ..dashboard.analyzer_cron import ensure_continual_cron
|
|
from ..dashboard.review_styles import mark_analysis_completed, mark_analysis_failed
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
async def _complete_and_register(full_name: str, **completed_kwargs: Any) -> dict[str, Any]:
|
|
"""Persist the prompt, then ensure the repo's nightly continual cron exists.
|
|
|
|
Cron registration is idempotent, so continual runs completing later don't
|
|
re-register it; it just guarantees a cron once a prompt first exists.
|
|
"""
|
|
record = await mark_analysis_completed(full_name, **completed_kwargs)
|
|
try:
|
|
await ensure_continual_cron(full_name)
|
|
except Exception:
|
|
logger.exception("Failed to ensure continual cron for %s", full_name)
|
|
return record
|
|
|
|
|
|
def save_review_style_prompt(
|
|
custom_prompt: str,
|
|
analysis_summary: str = "",
|
|
top_reviewers: str = "",
|
|
prs_sampled: int = 0,
|
|
reviews_sampled: int = 0,
|
|
) -> dict[str, Any]:
|
|
"""Save the synthesized repository-specific review style prompt.
|
|
|
|
Call this once at the end of style analysis with the final prompt text
|
|
that should be injected into the reviewer agent for this repository.
|
|
"""
|
|
config = get_config()
|
|
configurable = config.get("configurable") or {}
|
|
full_name = configurable.get("review_style_full_name")
|
|
if not isinstance(full_name, str) or "/" not in full_name:
|
|
return {"ok": False, "error": "review_style_full_name missing from config"}
|
|
|
|
reviewers_from_args = [r.strip() for r in top_reviewers.split(",") if r.strip()]
|
|
reviewers_from_config = configurable.get("review_style_top_reviewers") or []
|
|
merged_reviewers = reviewers_from_args or (
|
|
list(reviewers_from_config) if isinstance(reviewers_from_config, list) else []
|
|
)
|
|
prs_count = prs_sampled or int(configurable.get("review_style_prs_sampled") or 0)
|
|
reviews_count = reviews_sampled or int(configurable.get("review_style_reviews_sampled") or 0)
|
|
|
|
if not custom_prompt.strip():
|
|
asyncio.run(mark_analysis_failed(full_name, "custom_prompt was empty"))
|
|
return {"ok": False, "error": "custom_prompt cannot be empty"}
|
|
|
|
record = asyncio.run(
|
|
_complete_and_register(
|
|
full_name,
|
|
custom_prompt=custom_prompt.strip(),
|
|
analysis_summary=analysis_summary.strip(),
|
|
top_reviewers=merged_reviewers,
|
|
prs_sampled=prs_count,
|
|
reviews_sampled=reviews_count,
|
|
)
|
|
)
|
|
return {"ok": True, "full_name": full_name, "status": record.get("status")}
|