Skip to content

Add Codex Reliability Gap Map #01#43

Merged
yangfei222666-9 merged 1 commit into
mainfrom
codex-reliability-gap-map-01-clean
Jun 24, 2026
Merged

Add Codex Reliability Gap Map #01#43
yangfei222666-9 merged 1 commit into
mainfrom
codex-reliability-gap-map-01-clean

Conversation

@yangfei222666-9

Copy link
Copy Markdown
Owner

Summary

  • Add Codex Reliability Gap Map [codex] add 30s HUD demo script #1 as a clean-scope research proof.
  • Include a deterministic 30-issue public GitHub issue sample with explicit cannot_claim boundaries.
  • Add a validator and tests that keep the research table, JSON sample, failure-mode mapping, and limitations aligned.

Validation

  • python3 scripts/check_codex_gap_map.py
  • ~/.venvs/taiji-py312/bin/python -m pytest tests/test_codex_gap_map.py -q

Scope Boundaries

  • This PR intentionally contains only the Gap Map research files.
  • This is a scoped review of public user reports, not a prevalence study.
  • Open issues are treated as reported symptoms, not confirmed product defects.
  • Provider/model output is not used as canonical truth.

Related

@yangfei222666-9 yangfei222666-9 marked this pull request as ready for review June 24, 2026 17:18
@yangfei222666-9 yangfei222666-9 merged commit 44dee65 into main Jun 24, 2026
8 checks passed
@yangfei222666-9 yangfei222666-9 deleted the codex-reliability-gap-map-01-clean branch June 24, 2026 17:20
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