feat: skill-eval companion artifacts (grading, timing, benchmark)#579
Merged
feat: skill-eval companion artifacts (grading, timing, benchmark)#579
Conversation
Add ArtifactWriter module that produces grading/<test>.json, timing.json, and benchmark.json from existing JSONL eval results. Includes --artifacts CLI flag for eval run command. - Grading artifacts map per-evaluator hits/misses to skill-creator's expectations/evidence format with AgentV extensions (evaluators, workspace_changes, conversation) - Timing artifact aggregates duration and token usage across all results - Benchmark artifact computes per-target statistics (mean/stddev) for pass_rate, time, tokens, tool_calls, and cost - JSONL parser handles snake_case keys from existing output files - 29 tests covering artifact generation, schema compatibility, and I/O - Schemas are supersets of Anthropic skill-creator conventions Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Deploying agentv with
|
| Latest commit: |
391e4fd
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://2f6d16ef.agentv.pages.dev |
| Branch Preview URL: | https://feat-565-companion-artifacts.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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #565
Changes
ArtifactWritermodule following existingJsonlWriterpatterngrading/<test-id>.json,timing.json,benchmark.jsonfrom JSONL--artifacts <dir>CLI flag onagentv eval runArtifact Schemas
grading/<test-id>.json— Per-test grading with expectations (text/passed/evidence), summary, execution_metrics, and AgentV extensions (evaluators, workspace_changes, conversation)timing.json— Aggregate duration_ms, total_tokens, and token_usage (input/output)benchmark.json— Cross-test statistics per target with mean/stddev for pass_rate, time_seconds, tokens, tool_calls, cost_usdInteroperability
Shared fields (
expectations[].text/passed/evidence,summary,run_summary) use identical names and types as Anthropic's skill-creator. AgentV-specific fields are additive (evaluators, workspace_changes, conversation, per_evaluator_summary).