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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR finishes the MCP server work in #1 and fixes the follow-up regressions found during review.
The main API compatibility issue was session handling.
run_detector()had started generating a new session id whenever callers omittedsession_id, whileget_summary(),get_method_detail(), andgenerate_report()still defaulted to the legacydefaultsession. That broke the existing plain Python workflow where callers run a detector and immediately ask for summary or detail without passing the returned id. This change restores the legacydefaultsession for direct Python usage, while still keeping generated per-client session ids for MCP calls that include a client context.The path-based input loader also now preserves a valid
(n, 1)shape for single-feature embedding files. Labels and group labels can still collapse to one dimension, but embeddings loaded from CSV, TSV, or TXT remain two-dimensional so the file-based API behaves the same way as inline array inputs.Report generation now handles PDF fallback correctly. When PDF export falls back to HTML because the PDF dependency is unavailable, the response returns the actual generated HTML path and base64 content from that file instead of reporting a nonexistent PDF path.
Validation:
pytest tests/test_mcp_server.py -q37 passedCloses #1.