Conversation
github-actions
bot
added
enhancement
…tion (#2113) When experiments.eval_model is set, create a dedicated judge provider so the evaluator is independent from the agent under test. Falls back to the primary provider when eval_model is unset (existing behavior preserved). - Add eval_provider field to ExperimentState (feature-gated) - Add AppBuilder::build_eval_provider() using create_summary_provider - Add Agent::with_eval_provider() builder method - Wire eval provider in both agent (/experiment start) and --experiment-run paths - Remove the TODO(#eval-model) comment from experiment_cmd.rs
bug-ops
force-pushed
the
feat-issue-2113-wire-eval-model-to-evaluator
branch
from
ede64f7 to
f0004d0
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 #2113
Summary
experiments.eval_modelis set (e.g.openai/gpt-4o,claude/claude-opus-4-6), a dedicated judge provider is created for the evaluator so the judge is independent from the agent under testeval_modelis not configured (existing behavior preserved, no breaking changes)/experiment start) and standalone CLI (--experiment-run)TODO(#eval-model)comment fromexperiment_cmd.rsChanges
ExperimentState: neweval_provider: Option<AnyProvider>field (feature-gated)AppBuilder::build_eval_provider(): creates provider fromeval_modelspec using existingcreate_summary_provider(supportsollama/<model>,claude,openai,compatible/<name>)Agent::with_eval_provider(): builder method to inject the eval providerrunner.rs: wired in agent build path andrun_experiment_sessionTest plan
cargo nextest run --workspace --features full --lib --bins)cargo clippy --workspace --features full -- -D warningscleancargo +nightly fmt --checkcleanenabled = falseby default — no production impact