Conversation
Co-authored-by: Maximilian Sören Pollak <maximilian.pollak@qorix.com> Signed-off-by: Frank Scholter Peres(MBTI) <145544737+FScholPer@users.noreply.github.com>
Co-authored-by: Andreas Zwinkau <95761648+a-zw@users.noreply.github.com> Signed-off-by: Frank Scholter Peres(MBTI) <145544737+FScholPer@users.noreply.github.com>
Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <copilot@github.com>
- Add outer loop with both metrics_json and needs_json task modes - Add lightweight candidate validation and query tooling - Add baseline + rule-retrieval harness candidates - Add provenance metadata and responsibility model for audit compliance - Add tool safety restrictions and compliance documentation - Create executable seed corpus (4 tasks) Addresses eclipse-score/score#2850, eclipse-score/score#2856 Part of eclipse-score/score#2852
- Log validation failures to validation_failures.jsonl - Instruct LLM proposer to read failure log first (SKILL.md Step 1) - Document learning mechanism in SELF_HEALING.md - Enables system to learn from linting/type/interface mistakes - Auto-logs failures in outer_loop.py when validation fails Self-healing allows the proposer to see past mistakes (with exact error messages and fix commands) so it can avoid repeating them. This is more effective than explicit instructions because the LLM sees actual failures it made, not generic rules. Related: eclipse-score/score#2850
Moved internal documentation outside the public repository.
License Check Results🚀 The license check job ran with the Bazel command: bazel run --lockfile_mode=error //src:license-checkStatus: Click to expand output |
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| def load_task_specs(tasks_dir: Path) -> list[dict]: | ||
| """Load all task spec JSON files from the tasks directory.""" | ||
| specs = [] | ||
| for path in sorted(tasks_dir.glob("*.json")): |
Comment on lines
+81
to
+82
| [sys.executable, str(gate_script), "--metrics-json", str(metrics_json)] | ||
| + gate_args, |
Comment on lines
+106
to
+107
| [sys.executable, str(gate_script), "--metrics-json", str(metrics_json)] | ||
| + gate_args, |
| # Check 1-6: Harness interface and basic functionality | ||
| try: | ||
| harness = load_harness(candidate_path) | ||
| task_spec = json.loads(task_spec_path.read_text()) |
|
The created documentation from the pull request is available at: docu-html |
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.
📌 Description
🚨 Impact Analysis
✅ Checklist