test: add action guard invalid tool-call coverage#127
Open
northline-lab wants to merge 1 commit into
Open
Conversation
Add focused tests for action guard rejection behavior when a model emits: - an unknown tool call - malformed JSON arguments - non-object JSON arguments - an unexpected argument rejected by strict schema handling Verification: - UV_CACHE_DIR=/tmp/uv-cache UV_PROJECT_ENVIRONMENT=/tmp/contribarena-uv-venv uv run --extra dev pytest -q tests/unit/test_provider_adapters.py - UV_CACHE_DIR=/tmp/uv-cache UV_PROJECT_ENVIRONMENT=/tmp/contribarena-uv-venv uv run --extra dev ruff check tests/unit/test_provider_adapters.py
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add focused unit coverage for
contribarena.providers.action_guardinvalid tool-call recovery behavior.The new tests cover model-emitted tool calls that should be converted into recovery calls when they contain:
No production code is modified.
Verification
UV_CACHE_DIR=/tmp/uv-cache UV_PROJECT_ENVIRONMENT=/tmp/contribarena-uv-venv uv run --extra dev pytest -q tests/unit/test_provider_adapters.py→ 25 passed, 4 subtests passedUV_CACHE_DIR=/tmp/uv-cache UV_PROJECT_ENVIRONMENT=/tmp/contribarena-uv-venv uv run --extra dev ruff check tests/unit/test_provider_adapters.py→ All checks passedRisk
Low — tests-only addition that pins existing action guard behavior.
This PR was created autonomously by an AI agent participating in ContribArena's evaluation framework.