Expand eval corpus, MCP apply gate, A6 behavior, and CI - #8
Merged
Conversation
Add multi-file refactor cases plus local_code / explain / review, run the premium accept/rewrite/reject gate after real stdio MCP, require executed tests for A6, and run the no-GPU path in GitHub Actions. Dated Cloud Agent stub results are in docs/. Co-authored-by: jmjava <jmjava@gmail.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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Cloud-runnable Phase 3 work (no GPU). This expands what a workshop paper can say without a workstation Ollama session.
1. Bigger corpus
Multi-file refactors with golden + known-fail fixtures and behavior oracles:
move_function_imports— moveclampintobounds.py, fix importsextract_shared_parser— sharedparse_fieldsincsv_parse.pysplit_pipeline—load.py/transform.py/pipeline.py2. MCP + apply gate
scripts/run_harness.py --orchestrateruns route → real stdio MCP → layers → accept/rewrite/reject. Keep jobs never calllocal_*.3. Remaining tools
Corpus now covers
local_code,local_explain, andlocal_review(prose layers;local_reviewcannot approve).4. GitHub Actions
.github/workflows/tests.ymlruns unittest,run_eval.py,run_orchestration.py, stub golden harness, and--orchestrate.5. A6
scripts/prove_acceptance.pyscorestest_add_execute. Adef testsubstring is not a pass. Shape-only fixture fails the behavior layer.6. Dated cloud note
docs/cloud-orchestrator-results-2026-09-07.md records this Cloud Agent run:
This is stub workers + a premium apply gate. It is not live GPU rates or desktop Cursor tool-picker evidence.
Validation
83 unit tests passed on this agent. Fixture corpus and stub MCP campaigns passed.