test(eval): refresh eval harness CLI commands#211
Draft
ProfSynapse wants to merge 3 commits into
Draft
Conversation
Catalogues field-level drift between tests/eval/fixtures/tools.ts NEXUS_TOOLS and current production getParameterSchema() returns. 8 of 11 fixture entries drift; documents the v5.9.0 contentManager_replace hard-break and several production-side tools missing from the fixture. Filed under docs/research/ because docs/eval/ is gitignored. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
…rchitecture The eval harness exposed direct domain tool schemas (NEXUS_TOOLS) to the LLM even though production only ships getTools/useTools. The contradiction inflated failure rates for models that picked the meta tools (correct production behavior) while the harness asserted on direct domain calls. Convert all toolSet: nexus scenarios — adversarial, basic-tool-call, multi-turn, provider-parity, system-prompt — to toolSet: meta. Each direct domain call becomes a getTools selector turn + useTools CLI-command turn. Inner domain mock responses kept alongside getTools/useTools responses so both LiveToolExecutor (mirror-parse capture) and EvalToolExecutor (inner-unwrap capture) match. After: 0 scenarios use toolSet: nexus; all 12 scenario files use toolSet: meta exclusively. Harness now matches production two-tool MCP contract. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Validation