* fix: resolve reviewer head_sha from thread metadata, not frozen run config
A push that lands while a reviewer run is in flight is delivered as a
queued message into that run. The run's configurable is frozen at
creation, so its head_sha still names the commit the run was created for
— not the commit just pushed. publish_review then anchored the GitHub
review to the stale commit and regressed last_reviewed_sha to it, and
add_finding/update_finding stamped findings with the stale SHA.
Persist the current head in thread metadata at every reviewer dispatch
(both the ready-for-review and push paths, before they branch to create
a run or queue a message), and add resolve_review_head_sha() which
prefers the metadata head over the run config. Wire it into
publish_review (review commit_id + last_reviewed_sha), add_finding
(first_seen_sha) and update_finding (last_confirmed_sha). Falls back to
the run config when metadata carries no head (first review, eval, tests).
* fix: persist head_sha in manual review dispatch (trigger_pr_review_from_ref)
resolve_review_head_sha prefers metadata[head_sha] over the run config,
and the push/ready dispatchers write it — but trigger_pr_review_from_ref
(Slack/GitHub @open-swe review, request_pr_review tool) created a run
with a freshly-fetched config head while leaving metadata's head stale
from a prior dispatch. A manual re-review at a newer commit would then
resolve to the old head and publish/advance findings against it.
Persist head_sha in that dispatch's metadata write too, so every
run-creating reviewer dispatch keeps metadata in sync with the head its
run targets. Caught by the Open SWE reviewer on this PR.
* 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>
* feat: reconcile reviewer findings with PR threads
* fix: harden reviewer finding reply handling
* fix: queue reviewer finding reply body
Ensure review-comment replies that arrive during an active reviewer run include the sanitized reply body in the queued reassessment prompt.
* fix: apply reviewer reply formatting
Apply the repository formatter so the reviewer reply handling fix passes CI format checks.
* 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>
* feat(open-swe): cap reviewer suggestions at 4 lines
Long suggestion blocks read as the reviewer rewriting the code rather
than flagging an issue, which clutters PR comments. Steer the reviewer
toward description-only findings for non-trivial fixes, and enforce the
cap in `add_finding` / `update_finding` so suggestions over 4 lines are
dropped (the finding itself still publishes).
* fix(open-swe): don't clobber prior suggestion on over-cap update
`update_finding` was setting `suggestion=None` whenever clip_suggestion
dropped the input, which silently wiped any existing suggestion on the
finding. Distinguish the three cases: empty string clears, valid value
sets, over-cap value is rejected without touching the stored field.
* feat: implement reviewer findings, publish_review, and watch mode
Build out the reviewer agent end-to-end against the design in
REVIEWER_DESIGN.md:
- Findings as first-class state on the reviewer thread metadata
(`agent/reviewer_findings.py`): Finding TypedDict with start_line/end_line
ranges, suggestion text for ```suggestion blocks, github_review_comment_id
for cross-run reconciliation, diff_hunk for UI rendering. Thread-level
metadata gets `kind=reviewer`, `pr`, `last_reviewed_sha`, `watch` so a
future frontend can list reviewer threads via the langgraph SDK.
- Diff utilities (`agent/reviewer_diff.py`): parse_unified_diff,
compute_diff_line_set for in-diff validation, extract_diff_hunk for
caching the hunk on a Finding, compute_diff_in_sandbox for SHA-to-SHA
diffs against the prepped repo.
- Tools: `add_finding` (validates against the diff line set so out-of-diff
ranges fail at creation, not at GitHub-publish), `update_finding`,
`list_findings`, `publish_review`. The reviewer agent's tool list is
swapped from `[]` (direct shell `gh api` calls) to these four.
- Publish path (`agent/reviewer_publish.py` + `agent/tools/publish_review.py`):
one POST /reviews call with body + inline comments + ```suggestion blocks,
per-comment IDs stored back on findings, GraphQL `resolveReviewThread`
fired for findings transitioning open->resolved on a re-review.
- Reviewer graph: deterministic clone-or-fetch + checkout in the factory
before the agent's first model call (warm- and cold-path symmetric);
computed diff and in-diff line set passed via runnable config; system
prompt rewritten for the single-evolving-findings model, severity ladder,
in-diff-only discipline, and watch-mode reconciliation flow.
- Watch mode in webapp.py: `push` event + `pull_request` closed/reopened
added to supported events. New `process_github_push_event` resolves the
open PR for the pushed branch, gates on the reviewer thread's `watch`
flag, builds a re-review configurable, and triggers a run on the same
canonical thread. `process_github_pr_close` toggles watch on
closed/reopened. `set_reviewer_thread_metadata` is called on first
review to install `kind=reviewer` + PR identity + watch=True.
- Eval harness: target.py now extracts `add_finding` calls (mapped to the
legacy {file, line, body, severity} shape the judge expects) and passes
the right configurable so the prep step has base/head SHAs.
- Tests: new unit suites for findings helpers, diff parsing, finding tools,
publish rendering + GraphQL resolve, and watch-mode webhook handlers
(push triggers re-review only when watching, idempotent on unchanged
head SHA, PR close disables watch). Updated existing reviewer-webhook
tests to mock `set_reviewer_thread_metadata`.
- REVIEWER_EVAL_PLAN.md removed per user request; folded relevant context
into REVIEWER_DESIGN.md.
* fix(reviewer): correct git diff flags, scope, dedup, and review-comments URL
Address PR #1253 review findings:
- compute_diff_in_sandbox dropped the invalid `--no-prefix=false` flag
(`option no-prefix takes no value` — every prep run was failing
silently and the agent saw an empty diff).
- compute_diff_in_sandbox grew a `merge_base` flag. First-review path
now uses three-dot `base...head` (the merge-base diff GitHub renders
on Files-changed) so we don't pick up changes that landed on the base
branch after the PR diverged. Re-review delta keeps two-dot
`last_reviewed_sha..head` since that's exactly the new commits.
- publish_review skips findings that already carry
`github_review_comment_id`. Without this, watched re-reviews
re-posted every previously surfaced finding, and only the most-recent
duplicate's id would later resolve when the issue got addressed.
- fetch_review_comments URL now includes `{pull_number}` —
`/repos/{owner}/{repo}/pulls/{pr_number}/reviews/{review_id}/comments`
is the canonical endpoint; the old form 404s, so comment ids were
never stored and watch-mode resolution couldn't run.
Three new tests cover: three-dot vs two-dot wiring, no `--no-prefix`
flag in the executed command, and that publish_review does not re-post
findings whose `github_review_comment_id` is set.
* fix(reviewer): default publish cap from 15 to 4
A clean PR with one critical issue padded out by three lower-severity
findings is fine; fifteen is review spam. The agent can override per
call when a PR genuinely warrants more.
