Repository navigation
feat: no-tool correctness probes for abstention behavior (#107) - #134
Draft
askmy-stack wants to merge 1 commit into
Draft
askmy-stack wants to merge 1 commit into
askmy-stack wants to merge 1 commit into
Conversation
Add ProbeKind.no_tool so agents are scored on when not to call tools. Model outcomes distinguish unnecessary_tool vs wrong_tool; write/destructive unnecessary calls are high severity. Metrics and report section cover no-tool failures; offline remains structural-only. Co-authored-by: Abhinaysai Kamineni <askmy-stack@users.noreply.github.com>
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Implements #107: probes for when agents must not call tools.
ProbeKind.no_tool(e.g. email tools available, intent is “What is 2 + 2?”)unnecessary_toolvswrong_tool(distinct)high_severity_unnecessary+ HIGH SEVERITY messageno_tool_correctness_rate,unnecessary_tool_call_rate,unnecessary_high_severity_rateexamples/probes/no_tool_math.jsonType of change
Test plan
ruff/mypy/pytestCloses #107