Repository navigation
ci: fix Asta MCP config so CLARA stage 3 gets snippet_search - #3772
Merged
Merged
Conversation
Claude Code rejects `"tools": ["*"]` (tools.0: expected object, received string) and silently skips the Asta_semanticscholar server, so CLARA stage 3 never had snippet_search. Same fix as Cellular-Semantics/clara_workflow#10. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This was referenced Oct 1, 2026
ubyndr
added a commit
to obophenotype/uberon
that referenced
this pull request
Oct 1, 2026
Ports three fixes made and tested against a real PR in cell-ontology (obophenotype/cell-ontology#3772, #3773), so uberon doesn't hit the same issues on its first real run: - Bump CLARA_WORKFLOW_REF to 234ac67, which includes Cellular-Semantics/clara_workflow#10: Asta_semanticscholar's `"tools": ["*"]` was invalid (Claude Code expects an array of objects, not strings) and silently dropped the entire server from the session -- not "connected with no tools," never attempted at all. That's why stage 3 snippet_search was never available in any run so far. - Point --mcp-config at clara_workflow_ref/.mcp.json (the external package's own, now-fixed config) instead of this repo's dedicated .github/clara-mcp.json, so MCP tool wiring travels with agent_instructions.md as one versioned unit via CLARA_WORKFLOW_REF, rather than needing to be kept in sync by hand in every consuming repo. Removes the now-unused .github/clara-mcp.json. - Revert track_progress back to its original conditional. The earlier "always false" change here was a misdiagnosis: it forced agent mode to work around what looked like a tag-mode problem, but a real historical cell-ontology run (#3745, 35205839595) proves tag mode completes this task fine, Write included. The actual instant failures seen while debugging were model_not_found (fixed via --model, already in place), not a mode problem -- forcing agent mode just traded tag mode's sufficient default permissions for agent mode's insufficient ones. Signed-off-by: @ai4c-agent Co-Authored-By: Claude Sonnet 5 <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.
Problem
CLARA stage 2/3 runs never had Asta
snippet_search. Claude Code rejects the Asta entry in.mcp.jsonand skips the server:In run 36842857078 (#3765),
mcp_serverslists onlyartl-mcp. The agent skipped Stage B and used Europe PMC full text only (comment).Fix
Remove
"tools": ["*"]from the Asta entry. The workflow'ssettingsalready allowsmcp__Asta_semanticscholar__*, so no other change is needed.The fix has to land on master: claude-code-action restores
.mcp.jsonfrom the base branch for PR runs, so a fix in a PR branch has no effect.Same fix upstream: Cellular-Semantics/clara_workflow#10. With the fixed config,
claude mcp listshowsAsta_semanticscholar ✔ Connected, and aclaude -ptest call tosnippet_searchreturned results.After merging
Re-run
/claraon #3765 after merging master into it. That branch is also behind master'sCLARA_WORKFLOW_REF(232e9b4→5c61100), which is why that run wroteruns/CL:…paths with colons instead ofruns/CL_….🤖 Generated with Claude Code