Repository navigation
Conversation
test_same_name_different_definitions_resolve_per_turn checks extras["tools"], but that list came from the per-turn turn_tools query before 0775cfa too, and the test makes no tool calls. So it still passes with the old global name-to-id map. This test has each turn call "lookup" and checks the call's tool_id against the turn's own definition. It fails with the global map and passes on main. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0175Q8iD3ANaDC2DqYJfmj7x
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
0775cfa ("Resolve tool ids through each turn's turn_tools rows") fixed
tool_calls[].tool_id/tool_results[].tool_idinlog_row_extras, so a turn reports the tool definition it was actually given when two definitions share a name.The test added with it,
test_same_name_different_definitions_resolve_per_turn, makes no tool calls. It checksextras["tools"], which came from the per-turnturn_toolsquery before that commit too. So it still passes if the old global name-to-id map is put back.This adds
test_tool_calls_name_the_definition_their_turn_was_givento the same class. It has two turns, each callinglookupwith a different definition, and asserts that each call'stool_idmatches its own turn's tool.select id, name from tools) swapped back in: the new test fails (turn 1's call points at turn 2's definition), and the existing test still passes.tests/test_logs_store.pypass.black --check .andruff check .are clean.Test only, no code changes.
Found and reviewed with AI tools; I ran the test against the old and current code before opening this.