chore(codex): bootstrap PR for issue #481

[stranske]

Source: Issue #481

Automated Status Summary

Scope

Scope section missing from source issue.

Tasks

Issue Deduplication

• Create embedding generation for issue descriptions using OpenAI/GitHub Models
• Build FAISS vector store from existing open issues
• Implement similarity search with configurable threshold
• Post advisory comment linking similar issues

Label Matching

• Build vector store from repo labels (cache since labels rarely change)
• Replace findMatchingLabel() Levenshtein logic with semantic search
• Add fallback to Levenshtein for edge cases (very short labels)

Shared Infrastructure

• Create scripts/langchain/semantic_matcher.py for shared embeddings logic
• Add tests for both issue and label semantic similarity
• Deprecate/remove Levenshtein-based matching where applicable

Acceptance criteria

• New issues compared against existing open issues using embeddings
• High semantic similarity triggers warning comment for issues
• Label matching catches synonyms (defect→bug, improvement→enhancement)
• Related issues linked for context
• Does not block issue creation (advisory only)
• Catches "same idea, different phrasing" that Levenshtein misses

[github-actions]

🤖 Keepalive Loop Status

PR #526 | Agent: Codex | Iteration 5/5

Current State

Metric	Value
Iteration progress	[##########] 5/5
Action	stop (max-iterations-unproductive)
Gate	success
Tasks	15/16 complete
Keepalive	✅ enabled
Autofix	❌ disabled

🔍 Failure Classification

| Error type | infrastructure |
| Error category | unknown |
| Suggested recovery | Capture logs and context; retry once and escalate if the issue persists. |

⚠️ Failure Tracking

| Consecutive failures | 1/3 |
| Reason | max-iterations-unproductive |

🛑 Paused – Human Attention Required

The keepalive loop has paused due to repeated failures.

To resume:

1. Investigate the failure reason above
2. Fix any issues in the code or prompt
3. Remove the needs-human label from this PR
4. The next Gate pass will restart the loop

Or manually edit this comment to reset failure: {} in the state below.

[Copilot]

Pull request overview

This PR creates a bootstrap placeholder file for codex on issue #481, following the established pattern used throughout the repository for tracking codex-related work items.

• Adds a new markdown file in the agents/ directory with a standardized HTML comment

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[github-actions]

✅ Codex Completion Checkpoint

Iteration: 4
Commit: b24b316
Recorded: 2026-01-05T05:11:34.061Z

Acceptance Criteria Met

• New issues compared against existing open issues using embeddings
• High semantic similarity triggers warning comment for issues
• Related issues linked for context
• Does not block issue creation (advisory only)

About this comment

This comment is automatically generated to track task completions.
The Automated Status Summary reads these checkboxes to update PR progress.
Do not edit this comment manually.

[github-actions]

Status | ✅ no new diagnostics
History points | 1
Timestamp | 2026-01-05 05:23:48 UTC
Report artifact | autofix-report-pr-526
Remaining | 0
New | 0
No additional artifacts

[github-actions]

Autofix updated these files:

• scripts/langchain/semantic_matcher.py