open-swe/agent/dashboard
Adam Moussa 0d21fb8c47
fix: align reviewer eval with published findings (#1713)
* fix: make reviewer eval reflect published findings

Serialize and deduplicate finding persistence, align review calibration around the final six-finding publication, and make judge matching order-independent and auditable.

* fix: honor reviewer eval limits

Forward configured caps into publication snapshots and keep recall-at-cap bounded for diagnostic all-findings runs.

(cherry picked from commit 71e3b8183882bcc42e318f3f220c291617ebcb67)
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
2026-07-16 17:36:18 -04:00
..
__init__.py feat: port durable dispatch hardening and startup latency improvements (#160) 2026-07-09 17:11:25 -04:00
admin.py fix: allow GitHub logins for dashboard admins (#1582) 2026-06-20 09:44:12 -07:00
agent_instructions.py feat: per-repo custom instructions for the coding agent (#1460) 2026-06-09 15:46:29 -07:00
agent_overrides.py feat: author Slack/dashboard/schedule commits + PRs as the app by default (#57) (#60) 2026-06-29 14:22:33 -04:00
agent_usage.py feat: weight merged PRs above LOC in usage leaderboard sorting (#1563) 2026-06-17 10:59:42 -07:00
analyzer_cron.py feat: outcomes dataset + bootstrap/continual split via skills (#1365) 2026-06-01 13:25:12 -07:00
autofix_state.py feat: activate PR babysitting UI toggles for autofix and trigger mode (#1561) 2026-06-17 14:12:04 -07:00
enabled_repos.py feat: restructure Open SWE Review tab + wire create_prs (#1319) 2026-05-21 09:17:07 -07:00
eval_jobs.py fix: align reviewer eval with published findings (#1713) 2026-07-16 17:36:18 -04:00
notion_oauth.py feat: add user-scoped Notion MCP OAuth (#1593) 2026-06-23 12:07:13 -07:00
oauth.py feat: port plan-review & workflow-approval UX (#159) 2026-07-09 16:03:13 -04:00
options.py feat(open-swe): re-add Fable 5 behind an admin toggle (Bedrock) (#172) 2026-07-10 14:05:20 -04:00
plan_api.py feat: port plan-review & workflow-approval UX (#159) 2026-07-09 16:03:13 -04:00
plan_store.py feat: port plan-review & workflow-approval UX (#159) 2026-07-09 16:03:13 -04:00
pr_diff.py feat: render Reviews page diffs with pierre MultiFileDiff (#1517) 2026-06-12 11:03:51 -07:00
profiles.py fix: auto-recover from expired GitHub refresh tokens (#1491) 2026-06-11 12:05:27 -07:00
repo_access.py chore: sync upstream/main, defer #1621 modular webhooks (#81) 2026-06-30 16:45:19 -04:00
repo_snapshots.py feat: repo-scoped dynamic sandbox snapshots (#1595) 2026-06-23 12:24:11 -07:00
review_api.py chore: sync upstream/main, defer #1621 modular webhooks (#81) 2026-06-30 16:45:19 -04:00
review_chat_api.py feat: managed LangGraph Cloud + Vercel migration (PR2 — code fixes + docs) (#65) 2026-06-29 19:58:38 -04:00
review_style_jobs.py feat: outcomes dataset + bootstrap/continual split via skills (#1365) 2026-06-01 13:25:12 -07:00
review_styles.py feat: outcomes dataset + bootstrap/continual split via skills (#1365) 2026-06-01 13:25:12 -07:00
routes.py feat(open-swe): re-add Fable 5 behind an admin toggle (Bedrock) (#172) 2026-07-10 14:05:20 -04:00
schedules.py feat(open-swe): re-add Fable 5 behind an admin toggle (Bedrock) (#172) 2026-07-10 14:05:20 -04:00
slack_oauth.py chore: sync upstream/main, defer #1621 modular webhooks (#81) 2026-06-30 16:45:19 -04:00
team_credentials.py feat: server-side Datadog/LangSmith observability tools + team creds [closes OPE-54] (#1476) 2026-06-10 11:07:42 -07:00
team_settings.py feat(open-swe): re-add Fable 5 behind an admin toggle (Bedrock) (#172) 2026-07-10 14:05:20 -04:00
thread_api.py feat(open-swe): re-add Fable 5 behind an admin toggle (Bedrock) (#172) 2026-07-10 14:05:20 -04:00
user_credentials.py feat: add user-scoped Notion MCP OAuth (#1593) 2026-06-23 12:07:13 -07:00
user_mappings.py feat: managed LangGraph Cloud + Vercel migration (PR2 — code fixes + docs) (#65) 2026-06-29 19:58:38 -04:00
workflow_approval.py feat: port plan-review & workflow-approval UX (#159) 2026-07-09 16:03:13 -04:00
workflow_approval_api.py feat: port plan-review & workflow-approval UX (#159) 2026-07-09 16:03:13 -04:00