feat: require agent evolver self-validation#22
Merged
StoneHanaMori merged 1 commit intomainfrom Apr 28, 2026
Merged
Conversation
There was a problem hiding this comment.
Pull request overview
Adds an “inner-loop” self-validation gate to the Agentic Evolver center harness, ensuring skills are checked (and results recorded) before they’re finalized and leave the central workspace.
Changes:
- Update
EVOLVE_AGENTS.mdto require self-validation (static checks + minimal safe smoke tests) and to record outcomes in history evidence. - Update the evolve workspace bootstrap (
AGENTS.mdtemplate inagent_workspace.py) to point agents at the new self-validation requirement. - Add tests that assert the guide and bootstrap mention the new self-validation process.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 4 comments.
| File | Description |
|---|---|
| tests/test_agent_evolver_self_validation.py | Adds doc/bootstrapping “guardrail” tests to ensure self-validation instructions stay present. |
| evolve_server/engines/agent_workspace.py | Updates the embedded AGENTS.md bootstrap template to require self-validation before finalizing skill changes. |
| evolve_server/engines/EVOLVE_AGENTS.md | Introduces a full self-validation step and reiterates validation requirements near the end of the guide. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
|
|
||
|
|
||
| def test_evolve_agents_md_requires_center_harness_self_validation(): | ||
| text = Path("evolve_server/engines/EVOLVE_AGENTS.md").read_text(encoding="utf-8") |
Comment on lines
+18
to
+22
| text = agent_workspace._EVOLVE_AGENTS_MD | ||
|
|
||
| assert "self-validation" in text | ||
| assert "EVOLVE_AGENTS.md" in text | ||
| assert "Before finalizing" in text |
| - Before finalizing any changed skill, complete the self-validation required | ||
| by `EVOLVE_AGENTS.md`; if validation fails, keep editing or revert the | ||
| change rather than leaving a known-failing skill in `skills/`. | ||
| - Record self-validation results in the paired `history/v<N>_evidence.md` file. |
Comment on lines
+398
to
+399
| - ALWAYS complete center harness self-validation before finalizing a changed | ||
| skill, and record the result in the paired `history/v<N>_evidence.md` file. |
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
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
Motivation
Previously, Skill validation mainly happened after distribution to validation clients. This PR adds an
earlier Codex / Claude Code-style quality gate inside the Agentic Evolver harness, so obvious skill issues
can be detected and fixed before the candidate skill leaves the central workspace.