feat(phoenix): add AgentV eval adapter#1279
Merged
Merged
Conversation
Deploying agentv with
|
| Latest commit: |
9be0b5f
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://e2d3bd23.agentv.pages.dev |
| Branch Preview URL: | https://feat-phoenix-adapter.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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
@agentv/phoenix-adapteras a repo-local package for converting AgentV-authored eval suites into Phoenix dataset/experiment payloads.@agentv/core's eval loader so AgentV YAML remains the source of truth for case expansion, external datasets, Agent Skillsevals.json, assertion parsing, interpolation, and metadata handling.contains,regex,equals, andis-json; reports LLM/code/trace/composite/metric/custom evaluator families as unsupported instead of silently adapting them.bun run phoenix:assert-smoke.Verification
bun --filter @agentv/phoenix-adapter test— 18 tests passed.bun --filter @agentv/phoenix-adapter typecheck— passed.bun run phoenix:assert-smoke— dry-run smoke passed: 1 suite, 4 tests, baseline count 4, 0 failed suites.bun run test— passed (core/eval/phoenix-adapter/cli tests).git pushpassed: build, typecheck, lint, test, validate eval YAML files.Smoke / before-after evidence
Before this branch, AgentV had no in-repo Phoenix adapter package or
phoenix:assert-smokescript. On this branch:Full dry-run is intentionally not used as a CI gate yet. Current informational full dry-run result is 97 suites / 405 tests / 93 passed suites / 4 failed suites. The failures are documented in
packages/phoenix-adapter/docs/e2e-verification.mdand are source/baseline or source-reference parity issues, not Phoenix conversion crashes.Follow-up work
llm-graderandcode-gradersemantics.icontains-*,contains-any,starts-with, etc.).