docs: add tool evaluation proposals and plugin showcase #91
Conversation
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
Add two OpenSpec proposals for built-in tool evaluation features: 1. add-trajectory-argument-matching: Extend tool_trajectory evaluator to validate tool arguments (exact, pattern, or skip modes) 2. add-execution-metrics: Add extended execution metrics to traces (tokenUsage, costUsd, durationMs, explorationRatio) Add plugin showcase demonstrating patterns that should remain as code judges rather than built-ins: - tool_selection_judge.py: Semantic tool selection evaluation - efficiency_scorer.py: Custom efficiency thresholds - pairwise_tool_compare.py: Position-bias-mitigated comparison Based on research across 7 evaluation frameworks (Google ADK, Azure SDK, Mastra, Sniffbench, LangWatch, Letta, Agent-Skills).
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Outdated suggestions cannot be applied.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.
Summary
OpenSpec Proposals
1.
add-trajectory-argument-matchingExtend
tool_trajectoryevaluator to validate tool arguments, not just names:args: { query: "weather" }args: { query: /weather/i }args: any2.
add-execution-metricsAdd extended execution metrics to traces:
tokenUsage: { input, output, cached? }costUsd,durationMs,toolDurationsexplorationRatio,tokensPerToolPlugin Showcase
Demonstrates code judge plugins for domain-specific tool evaluation:
tool_selection_judge.pyefficiency_scorer.pypairwise_tool_compare.pyTest plan
openspec validate add-trajectory-argument-matching --strictpassesopenspec validate add-execution-metrics --strictpasses🤖 Generated with Claude Code