Add agenteval-judge and agenteval-metrics modules (Phase 2)#2
Closed
pratyush618 wants to merge 1 commit intomainfrom
Closed
Add agenteval-judge and agenteval-metrics modules (Phase 2)#2pratyush618 wants to merge 1 commit intomainfrom
pratyush618 wants to merge 1 commit intomainfrom
Conversation
Implement the judge module with OpenAI and Anthropic LLM providers,
and 7 P0 evaluation metrics for end-to-end agent evaluation.
Judge module:
- JudgeConfig builder, HttpJudgeClient with exponential backoff retry
- JudgeResponseParser (JSON-first, regex-fallback score extraction)
- OpenAiJudgeModel (/v1/chat/completions, json_object mode)
- AnthropicJudgeModel (/v1/messages, x-api-key auth)
- JudgeModels static factory with env var API key resolution
- Unchecked exception hierarchy (JudgeException, RateLimit, Timeout)
Metrics module:
- LLMJudgeMetric abstract base with template method lifecycle
- PromptTemplate classpath loader with {{variable}} substitution
- 5 response metrics: AnswerRelevancy, Faithfulness, Correctness
(G-Eval), Hallucination, Toxicity
- 2 agent metrics: ToolSelectionAccuracy (deterministic F1/LCS),
TaskCompletion (LLM-as-judge)
- 6 prompt templates as classpath .txt resources
180 tests pass (71 core + 39 judge + 70 metrics), no API keys needed.
pratyush618
force-pushed
the
feat/judge-and-metrics
branch
from
e8a814e to
47e6c18
Compare
Collaborator
Author
|
Recreating PR with clean history |
This was referenced Apr 23, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Implement the judge module with OpenAI and Anthropic LLM providers, and 7 P0 evaluation metrics for end-to-end agent evaluation.
Judge module:
Metrics module: