feat(worker): add verify stage and harness closed-loop pipeline#48
Open
sawzhang wants to merge 1 commit into
Open
feat(worker): add verify stage and harness closed-loop pipeline#48sawzhang wants to merge 1 commit into
sawzhang wants to merge 1 commit into
Conversation
Add a new "verify" agent role for build/lint/type-check validation, with automatic failure redirect context passing (verify/test → code) so the coding agent can self-correct. Includes composite evaluator scoring from LLM confidence + external signals, project-level verify_commands config, tech_stack auto-detection, and a built-in "harness_pipeline" template (Code→Verify→Test with up to 3 retry loops). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Coverage report
Click to see where and how coverage changed
This report was generated by python-coverage-comment-action |
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
evaluator.py) combining LLM confidence with external signals (test pass rate, build success, lint clean) via configurable weightsverify_commandsfield with auto-detection fallback fromtech_stack_template_needs_graph()to auto-enable graph execution when template usesdepends_on/on_failureTest plan
test_evaluator.py— composite scoring, weight loading, evaluate functiontest_harness_loop.py— failure redirect context flow, template detection, verify command resolutiontest_verify_stage.py— verify role prompt/tools config, stage instructions, guardrailstest_worker_graph.py— graph execution with redirect context🤖 Generated with Claude Code