test: pin EvalCase session state injection into agent instructions - #6705
Open
sgoel2be24-cyber wants to merge 4 commits into
Open
test: pin EvalCase session state injection into agent instructions#6705sgoel2be24-cyber wants to merge 4 commits into
sgoel2be24-cyber wants to merge 4 commits into
Conversation
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
Eval tools already saw session_input.state while instruction templates historically did not (google#5037). Current main injects correctly; this locks that path so it cannot regress.
sgoel2be24-cyber
force-pushed
the
fix/eval-instruction-session-state
branch
from
August 13, 2026 04:17
6c8e083 to
d59c1fc
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Please ensure you have read the contribution guide before creating a pull request.
Link to Issue or Description of Change
1. Link to an existing issue (if applicable):
Problem:
Eval tools already saw
EvalCase.session_input.state, but instruction templates with{some_key}historically did not during eval.Solution:
Current
mainalready runsinject_session_statefor string instructions in the eval Runner. This PR adds a LocalEvalService regression so that path cannot silently break.Testing Plan
Unit Tests:
1 passed—tests/unittests/evaluation/test_local_eval_service.py::test_eval_injects_session_input_state_into_instructionManual End-to-End (E2E) Tests:
Not applicable: this is a unit regression for eval instruction injection. No runtime/CLI surface change.
Checklist
Additional context
Assistance: drafted with an AI coding agent and reviewed before opening.
Made with Cursor