Skip to content

Publish the reproducible specialist evaluation suite - #6

Merged
hudsonaikins merged 5 commits into
mainfrom
codex/analysis-eval-foundation
Nov 13, 2026
Merged

hudsonaikins merged 5 commits into
mainfrom
codex/analysis-eval-foundation

Conversation

@hudsonaikins

@hudsonaikins hudsonaikins commented Nov 13, 2026 •

Copy link
Copy Markdown
Contributor

Publish the reproducible four-case specialist evaluation package so a clean checkout can prepare the fixtures, run the scripted SmolVM reference suite, and compare qualified live models through LangSmith. The cases cover sales/refunds, missing-cost refusal, irregular energy and service availability; private references remain outside runtime mounts. README and roadmap point to runnable commands and distinguish measured capability from release acceptance.

Review fixes enforce declared metric IDs and cell bindings, reject negated/ambiguous missing-input explanations, and make live CLI success require complete applicable accounting and review eligibility. Numerical references and model inputs are unchanged. SQLite dataset identity is checked within each frozen environment rather than hardcoding a host-specific file encoding. Historical feedback stays intact; any revised grading is recorded separately with its evaluator identity.

Validation: the full offline suite passed 204 tests with 15 optional skips before one additional refusal-control case; the final focused suite passes 47 tests. Ruff, format, Vulture and Gitleaks checks pass. The real scripted SmolVM suite passed 4/4 with three exported bundles and no provider calls. The original two-case SmolVM integration passed 7 tests. Refreshed six-store runtime validation passed all stores, captured commit 3d61a72 and source/runner identities, used zero model calls or data reloads, and restored service state.

No runtime default or specialist prompt changes are included. Prompt guidance is isolated in stacked PR #7. One trial per case is not general reliability or release acceptance.

Tracks INT-451.

@hudsonaikins
hudsonaikins marked this pull request as ready for review November 13, 2026 04:45
@chatgpt-codex-connector

chatgpt-codex-connector Bot commented Nov 13, 2026 •

Copy link
Copy Markdown
Codex Review Summary: ✅ Completed

This comment shows the latest Codex review activity on this pull request.

Review Status Commit Review trigger
📝 Code Review ✅ Completed 2026-11-13T05:05:59.515427Z 34e27a2 New commits
🔒 Security Review ✅ Completed 2026-11-13T05:06:42.695182Z 34e27a2 New commits
ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 25f37b657c

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

Comment thread scripts/analysis_cases.py Resolved
Comment thread scripts/run_analysis_comparison.py Resolved
Comment thread results/runtime-validation-smoke.json Resolved
Comment thread scripts/analysis_cases.py Resolved
@hudsonaikins
hudsonaikins merged commit edcad7c into main Nov 13, 2026
2 checks passed
@hudsonaikins
hudsonaikins deleted the codex/analysis-eval-foundation branch November 13, 2026 05:10
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