Compare CLI and MCP parameter defaults in the parity test - #20
Merged
Merged
Conversation
The parity test checked that every CLI research flag has a tool parameter but only pinned defaults for boolean flags, so the MCP tools could quietly default differently from `pwc` (as search_papers did with keyword versus hybrid). Compare every CLI default against the tool schema default, treating argparse's unset placeholders as null and listing the documented hosted row-cap divergences on `limit` as the only exceptions, so a future default change on either side fails the test. Co-Authored-By: Claude Fable 5.1 <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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Follow-up to #19, prompted by review feedback: instead of asserting that
search_papers.modedefaults to the literalhybrid, the parity test now compares every CLI research-flag default against the MCP tool schema default. A future change topwc search --mode(or any other flag default) on either side failstests/test_parity.py.None,SUPPRESS,(),[]) are treated as the schema'snull.DEFAULT_EXCEPTIONSlists the only deliberate divergences, all onlimitand already documented in README as the hosted 25-row cap:list_methods(50 → 25),list_benchmarksandlist_tasks(50 → server-chosen).Verification
Negative check: temporarily setting
DEFAULT_SEARCH_MODE = "keyword"inserver.pymakes the parity test fail withAssertionError: ('search_papers', 'mode').Test-only change; no component release needed.
🤖 Generated with Claude Code