feat(pipeline): agent-mode artifacts align with CLI-mode schema#796
Merged
feat(pipeline): agent-mode artifacts align with CLI-mode schema#796
Conversation
- pipeline run/input: --out now optional, defaults to .agentv/results/runs/eval_<timestamp> - pipeline bench: index.jsonl now includes scores[], execution_status, response_path to match CLI-mode dashboard schema - results validate: new command to check run dir naming, index.jsonl fields, artifact presence, and score bounds - skill: update agent-mode workflow docs to use default --out, add validate step, clarify llm_scores.json -> index.jsonl flow; user-stated mode overrides .env
1. execution_status: run.ts now writes status into timing.json ('ok' or
'execution_error'), bench.ts reads it back instead of hardcoding 'ok'
2. response_path: use null instead of undefined so the field is always
present in index.jsonl
3. --workers concurrency: implement actual concurrency limiter using
Promise.race instead of unbounded Promise.all
4. validate.ts: validate scores[] entry structure (name, type, score,
verdict) and warn on unknown execution_status values
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Deploying agentv with
|
| Latest commit: |
b94ff8a
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://e2bbf6b9.agentv.pages.dev |
| Branch Preview URL: | https://feat-pipeline-agent-mode-art.agentv.pages.dev |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Agent-mode pipeline runs now produce artifacts in the same location and schema as CLI-mode runs. Changes: (1) pipeline run/input --out is optional, defaults to .agentv/results/runs/eval_timestamp; (2) pipeline bench enriches index.jsonl with scores[], execution_status, response_path; (3) new agentv results validate command; (4) agentv-bench SKILL.md updated with default paths, validate step, and user instruction overrides .env mode.