Plan step C4 (docs/upstream-sync/domain-reorg/reorg-build-plan.md, approved
decisions 1-2): split the 2,590-line agent/webapp.py monolith into
agent/webhooks/common.py (shared verify/dispatch helpers), agent/api/app.py
(composition), agent/api/health.py (/health + /webhooks/run-complete), and
per-source {github,linear,slack,jira,confluence}_routes.py. Atlassian
Connect lifecycle + descriptor routes (/connect/*) fold into
confluence_routes.py; webapp.py becomes the upstream-shaped compatibility
shim (from .api.app import app). langgraph.json http.app stays
agent.webapp:app via the shim.
Fork content, upstream layout: linear/slack route files verified
content-identical to upstream 8356eb34 and taken verbatim; github_routes is
upstream + the fork's CI auto-fix trigger wiring; jira/confluence routes are
fork-only, transformed to the same common.X / service.X module-attribute
style. All signature verification (GitHub HMAC, Slack, Linear
timestamp-freshness, verify_jira_secret + opt-in HMAC/timestamp/IP
allowlist, Connect JWT/qsh), token-attribution gating, TID-COLLIDE-01 repo
binding, _is_repo_auto_review_enabled gates, and public-repo org gate move
unchanged.
Handlers rewired from webapp.X to common.X; test monkeypatch sites across
26 files + conftest.py + e2e/harness.py retargeted to
webhook_common/handler/route modules per upstream's pattern. Residual
agent.webapp importers: only the shim, langgraph.json http.app, Makefile
uvicorn target, and docs (doc-path updates land in C7).
Gates: ruff check + format, pytest --co, full unit (1637 passed), full
Playwright E2E vs real langgraph dev (9/9), residual-importer sweep.
Part of the domain-reorg adoption (build plan step C2): fork content,
upstream layout. Nine 1:1 module moves (reviewer_diff/eval_store/
findings/groups/publish/reconcile/trace_context + review_style_
collector/guidance) into agent/review/, with internal relative
imports re-wired to the new package depth. agent/review/__init__.py
mirrors upstream's thin re-export shim (one of the 21 verified "A"
structural adds).
Rewrote the 38 grep hits across importer files (agent/{analyzer,
ci_autofix,reviewer,webapp}.py, agent/dashboard/*, agent/middleware/
settle_review_check.py, agent/tools/*, agent/utils/github_feedback.py,
agent/webhooks/github.py, evals/reviewer/*, and the reviewer test
suite) to point at agent.review.*; 4 of the 38 hits were name
collisions (list_reviewer_findings, reviewer_outcomes,
_reviewer_thread_id, reviewer_thread_id — not the moved modules) and
were left untouched. tests/test_github_checks.py's module-alias
import (`from agent import reviewer_publish`) follows upstream's own
`from agent.review import publish as reviewer_publish` pattern so
downstream `reviewer_publish.*` call sites needed no changes.
agent/reviewer.py and agent/webapp.py stay in place per the hard
rule (fork content, import-only rewire) and are not part of this
package.
Gates: ruff check + ruff format --check, pytest --co -q (1637
collected), full unit suite (1637 passed), and the reviewer/findings
suite in isolation (pytest -k "review or finding", 421 passed).
* 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>
* fix(dashboard): review style prompts UX, stale runs, and OAuth refresh
Reconcile stuck "running" analysis state, add cancel/remove for style
profiles, stack the review styles UI vertically, and auto-refresh expiring
GitHub user tokens with proactive and 401-triggered rotation.
* fix(dashboard): address review feedback on style prompts PR
Restore GitHub repo access checks on create/save with token refresh,
and preserve running status when LangGraph sync fails transiently.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Hardcoded localhost:2024 caused httpx.ConnectError when starting the
review_style_analyzer graph in production. Resolve the SDK URL from
LANGGRAPH_URL / LANGGRAPH_URL_PROD like webapp, otherwise get_client().
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat: tune reviewer for precision — web/wiki tools + recalibrated prompt
Reviewer agent now has web_search, fetch_url, and http_request alongside the
finding tools, so it can verify library semantics and consult the DeepWiki
auto-generated wiki for public repos (https://deepwiki.com/<owner>/<repo>)
before flagging cross-file or architectural concerns.
Prompt rewritten to push precision over recall:
- explicit severity ladder pushing reviews toward bimodal high/low instead of
defaulting to medium
- ≤200-char description target (gold set averages ~186 chars; we were at ~436)
- mandatory docs / wiki / code lookup before flagging concurrency, security,
or perf — the three categories that dominated false positives
- "do not flag" list covering compiler/linter-catchable nits, speculative
claims without a concrete attacker/interleaving/scale, style preferences
the codebase doesn't share, and test-quality nits on non-test diffs
- smart file-selection guidance for large PRs (deprioritize generated /
vendored / pure-rename hunks)
Eval config switched to openai:gpt-5.5 + high reasoning effort for the next
benchmark run.
* trim prompt
* subagent prompting
* confidence ratings
* added medium
* enforce confidence threshold
* .
* reviewer: precision-tuned prompt + drop confidence gate
Rewrites the reviewer system prompt around a defensibility bar (anchor +
failure mode + maintainer wouldn't say "not a bug"), an explicit do-not-file
list (style nits, speculation, scope-policing, same-bug fan-out), and a
checklist of 10 bug archetypes drawn from a per-PR audit of the eval golden
set. The audit showed 145 FPs in the last eval split ~28% speculative, ~26%
style-nit, ~31% real-but-unscored (mostly same-archetype fan-out); the new
prompt targets each class directly.
Confidence is still recorded on every finding for post-hoc calibration but
no longer gates publication — the audit showed the gate was a no-op (agent
self-rated 65% of findings "high" regardless), and the prompt's defensibility
bar is the actual discipline. Drops CONFIDENCE_ORDER, CONFIDENCE_THRESHOLD,
the confidence_threshold kwarg on filter_findings_for_publish, the
confidence_filtered score_mode, and the min_confidence kwarg on the eval
target's _extract_comments — all dead once the gate is gone.
Also removes the "informational" severity tier from the Severity enum,
SEVERITY_ORDER, and all validators / tests / docstrings. It was reserved for
FYI observations the dataset never rewards.
* benchmax
* adding google provider
* slight steering
* tuning
* more tuning
* fix
* cleanup
* reducing overfitting
* Add per-repo review style profiles and inject them into the reviewer.
Dashboard users can analyze historical PR review feedback per repository,
edit the resulting style guide, and have it loaded from LangGraph Store at
reviewer runtime (including Martian eval runs) keyed by owner/name.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Fix review style job errors leaking exception details to clients.
Return generic dashboard messages while logging full stack traces server-side.
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
