Skip to content

fix(owasp-agent): index/router fixes (board, events, chapters, Top 10) + regression rows - #1159

Open
northdpole wants to merge 5 commits into
fix/ask-embedding-retrievalfrom
claude/fix-agent-index-80b1a2
Open

northdpole wants to merge 5 commits into
fix/ask-embedding-retrievalfrom
claude/fix-agent-index-80b1a2

Conversation

@northdpole

Copy link
Copy Markdown
Collaborator

Agent-index fixes found by the private eval and Prateek's synth_v2 files: board name parsing, indexed event lookup, metro chapter aliases, meta-lane grounding floor, compound questions, nearest-to place, whole-name project match, ambiguous first-name candidates. Regression rows added; all 187 owasp_agent tests pass. Multi-suite eval 107/190 strict in-process (baseline before deploy).

Stacked on #1155. Deploys to staging together with the comprehension branch.

🤖 Generated with Claude Code

@coderabbitai

coderabbitai Bot commented Oct 17, 2026 •

Copy link
Copy Markdown
Contributor

Important

Review skipped

Auto reviews are disabled on base/target branches other than the default branch.

🗂️ Base branches to auto review: 1
  • main

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

Run configuration

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

  • 🔍 Trigger review
  • Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands.

@northdpole
northdpole force-pushed the fix/ask-embedding-retrieval branch from 21890d0 to 1129c1f Compare October 20, 2026 08:20
@northdpole
northdpole force-pushed the claude/fix-agent-index-80b1a2 branch from 05ba4c2 to 7dd9cd2 Compare October 20, 2026 08:20
@northdpole
northdpole force-pushed the fix/ask-embedding-retrieval branch from 1129c1f to 7e37a9d Compare October 20, 2026 08:29
@northdpole
northdpole force-pushed the claude/fix-agent-index-80b1a2 branch from 7dd9cd2 to f5ba231 Compare October 20, 2026 08:29
@northdpole
northdpole force-pushed the fix/ask-embedding-retrieval branch from 7e37a9d to fdda36d Compare October 20, 2026 08:48
@northdpole
northdpole force-pushed the claude/fix-agent-index-80b1a2 branch from f5ba231 to d14089a Compare October 20, 2026 08:48
@northdpole
northdpole force-pushed the fix/ask-embedding-retrieval branch from fdda36d to 22f42fa Compare October 20, 2026 09:21
@northdpole
northdpole force-pushed the claude/fix-agent-index-80b1a2 branch from d14089a to cb51c1f Compare October 20, 2026 09:21
@northdpole
northdpole force-pushed the fix/ask-embedding-retrieval branch from 22f42fa to d6126a4 Compare October 21, 2026 23:09
@northdpole
northdpole force-pushed the claude/fix-agent-index-80b1a2 branch from cb51c1f to fe62660 Compare October 21, 2026 23:09
@northdpole
northdpole force-pushed the fix/ask-embedding-retrieval branch from d6126a4 to d2416dc Compare October 22, 2026 07:59
@northdpole
northdpole force-pushed the claude/fix-agent-index-80b1a2 branch from fe62660 to 044e610 Compare October 22, 2026 07:59
@northdpole
northdpole marked this pull request as ready for review October 22, 2026 11:17
northdpole and others added 5 commits October 25, 2026 10:31
…s and multi-suite eval

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
…prompt cap, leader noise/email

- resolve any indexed chapter/place (no hardcoded city lists), qualifier mismatch
  (Athens, Georgia) no longer answers Athens, Greece; Oakland != Oakland County
- drop template leaders (Meeting Location, Everyone, Speaker name) at sync + read
- strip email from public payloads
- refusal gate: current turn only, attack-material only (not prevent/mitigate/
  phishing-resistant), droppable injection clause in compound turns
- cap prompt at 4 KB; typo repair + 'number of' for chapter counts

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
…pter aliases

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
…est-to place

- single-entity sim cards must name the entity; counts/compares/lists/refusals never get one
- ask owasp_meta no-match returns a short 'what I can answer' fallback
- two-part prompts answer every agent-answerable clause and name the one handed back

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
…e lists candidates

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
@northdpole
northdpole force-pushed the fix/ask-embedding-retrieval branch from d2416dc to 2f9187c Compare October 25, 2026 10:35
@northdpole
northdpole force-pushed the claude/fix-agent-index-80b1a2 branch from 044e610 to f6c15e0 Compare October 25, 2026 10:35

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant