Skip to content

Make PR-AF reviews merge-gate aware #44

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
AbirAbbas merged 26 commits into from
Jun 10, 2026
Merged

Make PR-AF reviews merge-gate aware #44

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
26 commits
Select commit Hold shift + click to select a range
1f59d21
feat: precision improvements (Phase A+B+C) and model consolidation
santoshkumarradha Mar 17, 2026
ad55cf1
feat: streaming pipeline + archei-compliant data flows
santoshkumarradha Mar 17, 2026
813b1c2
fix: use dynamic NODE_ID in webhook _fire_review instead of hardcoded…
santoshkumarradha Mar 17, 2026
38ec510
feat: parallel per-finding evidence verification
santoshkumarradha Mar 17, 2026
c9276a3
refactor: adaptive prompts + orchestrator cleanup
santoshkumarradha Mar 17, 2026
bdb97b6
feat: runtime provider/model override via review API
santoshkumarradha Mar 17, 2026
be12954
fix: model ID mapping for claude-code provider + docs update
santoshkumarradha Mar 17, 2026
dcfbbf2
fix: simplify model override — pass through to AgentField, no custom …
santoshkumarradha Mar 17, 2026
7527beb
feat: per-call provider/model via contextvars (concurrent-safe)
santoshkumarradha Mar 17, 2026
0c438da
fix: separate ai_model from harness_model for litellm compatibility
santoshkumarradha Mar 17, 2026
2595fbe
fix: add claude-agent-sdk to Dockerfile, document ai_model format
santoshkumarradha Mar 18, 2026
7cbb2f9
revert: restore original thresholds — precision gates killed recall
santoshkumarradha Mar 18, 2026
7e4ad4f
revert: restore verbose prompts from main — adaptive prompts hurt recall
santoshkumarradha Mar 18, 2026
a37c43a
feat: pass CLAUDE_CODE_OAUTH_TOKEN to harness env for claude-code pro…
santoshkumarradha Mar 19, 2026
f5e10b1
fix: inject ANTHROPIC_API_KEY for litellm when ai_model uses anthropi…
santoshkumarradha Mar 19, 2026
4baee68
fix: remove api_base override — litellm auto-detects for anthropic/ p…
santoshkumarradha Mar 19, 2026
7a13a4f
feat: install Claude Code CLI for claude-code harness provider, set a…
santoshkumarradha Mar 19, 2026
352508a
feat: add dynamic efficiency — adaptive gates, multi-tier model routi…
santoshkumarradha Mar 20, 2026
11cf818
feat: architecture redesign — research brief, cross-cluster patches, …
santoshkumarradha Mar 20, 2026
e0cac3a
chore: compress README images for faster loading
santoshkumarradha Mar 29, 2026
f50d42a
feat: parallel .ai() polish pass for inline comments before posting
santoshkumarradha May 26, 2026
adad603
feat: merge-gate — decouple "must-fix" from severity, redesign PR sum…
santoshkumarradha Jun 9, 2026
0b2e155
fix: normalize severity casing + clean stale clone dir
santoshkumarradha Jun 9, 2026
955722a
chore: clean merge gate PR artifacts
santoshkumarradha Jun 9, 2026
a88ddce
Merge origin/main into severity gating branch
santoshkumarradha Jun 9, 2026
af1b7f2
chore: trim stale gate artifacts
santoshkumarradha Jun 9, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file removed benchmark/.DS_Store
View file
Open in desktop
Binary file not shown.
90 changes: 0 additions & 90 deletions benchmark/agentfield-254/EVALUATION.md
View file
Open in desktop

This file was deleted.

Loading
Loading