Document ensemble test generation workflow (#159)#160
Merged
that-github-user merged 2 commits intomainfrom Mar 30, 2026
Merged
Conversation
- Add "Recommended workflows" section to README with two-phase pattern: generate tests via ensemble first, then implement against converged tests - Include ensemble-generated test suite (test_pathfinding_generated.py) produced by 3/5 agents, all converging on correct maze path length (9) - Add test collection wrapper script for --collect-only validation Addresses #159 (Option A: documented workflow) Also references #31 (A* showcase evidence) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This was referenced Mar 30, 2026
Closed
that-github-user
pushed a commit
that referenced
this pull request
Mar 31, 2026
- Fix exit-127 preflight test: accept both "Test command not found" and generic failure message (Linux returns 127, Windows may differ) - Add GitHub Packages publish step to release workflow: publishes as @that-github-user/thinktank-ai to npm.pkg.github.com alongside the existing npmjs.org publish - Add packages:write permission to release workflow Fixes CI failure from #160. Resolves "No packages published" on GitHub. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
that-github-user
added a commit
that referenced
this pull request
Mar 31, 2026
* Fix CI test failure and add GitHub Packages publishing - Fix exit-127 preflight test: accept both "Test command not found" and generic failure message (Linux returns 127, Windows may differ) - Add GitHub Packages publish step to release workflow: publishes as @that-github-user/thinktank-ai to npm.pkg.github.com alongside the existing npmjs.org publish - Add packages:write permission to release workflow Fixes CI failure from #160. Resolves "No packages published" on GitHub. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * Fix formatting (trailing comma) * Remove accidentally committed artifacts, update .gitignore --------- Co-authored-by: unknown <that-github-user@github.com> Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
test_pathfinding_generated.py) produced by running thinktank with 5 agents — 3/5 succeeded, all converging on correct maze path length assertionsEvidence
We ran
thinktank run "write tests for A* pathfinding" -n 5and compared the maze path length assertions:applycommand to apply selected agent's diff #1: asserted path length 9 for the main maze (correct), 13 for a different wall-maze (also correct)All 3 passing agents independently computed the same expected values. If one had disagreed, convergence analysis would have flagged it before the test became the oracle.
Test plan
npm run buildpassesnpm testpasses (250 tests)pytest --collect-onlyCloses #159
🤖 Generated with Claude Code