mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 12:43:16 +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>
60 lines
2.1 KiB
Python
60 lines
2.1 KiB
Python
from __future__ import annotations
|
|
|
|
import pathlib
|
|
|
|
from deepagents.middleware.skills import _parse_skill_metadata
|
|
|
|
from agent.dashboard.review_style_jobs import (
|
|
build_continual_run_configurable,
|
|
build_continual_run_input,
|
|
)
|
|
from agent.utils.analyzer_skills import (
|
|
ANALYZER_MODES,
|
|
SKILLS_DIR,
|
|
build_skill_files,
|
|
skill_path_for_mode,
|
|
)
|
|
|
|
|
|
def test_build_skill_files_stripped_keys_and_valid_file_data() -> None:
|
|
files = build_skill_files()
|
|
assert set(files) == {
|
|
"/bootstrap-repo-analysis/SKILL.md",
|
|
"/continual-learning/SKILL.md",
|
|
}
|
|
for entry in files.values():
|
|
assert entry["encoding"] == "utf-8"
|
|
assert isinstance(entry["content"], str) and entry["content"].strip()
|
|
assert "created_at" in entry and "modified_at" in entry
|
|
|
|
|
|
def test_skill_path_for_mode() -> None:
|
|
assert skill_path_for_mode("bootstrap") == "/skills/bootstrap-repo-analysis/SKILL.md"
|
|
assert skill_path_for_mode("continual") == "/skills/continual-learning/SKILL.md"
|
|
# Unknown modes fall back to bootstrap.
|
|
assert skill_path_for_mode("whatever") == "/skills/bootstrap-repo-analysis/SKILL.md"
|
|
|
|
|
|
def test_bundled_skill_md_parse() -> None:
|
|
for skill in ANALYZER_MODES.values():
|
|
path = SKILLS_DIR / skill / "SKILL.md"
|
|
meta = _parse_skill_metadata(path.read_text(), str(path), path.parent.name)
|
|
assert meta["name"] == skill
|
|
assert meta["description"].strip()
|
|
|
|
|
|
def test_skills_dir_resolves() -> None:
|
|
assert SKILLS_DIR.name == "skills"
|
|
assert (SKILLS_DIR / "bootstrap-repo-analysis" / "SKILL.md").exists()
|
|
assert isinstance(SKILLS_DIR, pathlib.Path)
|
|
|
|
|
|
def test_continual_run_payload_carries_mode_and_skill_files() -> None:
|
|
configurable = build_continual_run_configurable("o/r")
|
|
assert configurable["analyzer_mode"] == "continual"
|
|
assert configurable["review_style_full_name"] == "o/r"
|
|
assert configurable.get("thread_id")
|
|
|
|
run_input = build_continual_run_input("o/r")
|
|
assert "/continual-learning/SKILL.md" in run_input["files"]
|
|
assert run_input["messages"][0]["role"] == "user"
|