fix(mcp): reject empty anchor in MemoryFetch (#219) - #251
Merged
Conversation
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Signed-off-by: radimsem <me@radimsemerak.cz>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #219.
What
HandleFetchpassedinput.Anchorstraight toEngine.Fetchwith no guard. An empty anchor produced a genericfailed to fetch: ...node not founderror that obscured the real problem (a missing required argument), hurting LLM tool-use recovery loops.Change
pkg/mcp/tools/fetch.go— add an empty-anchor guard immediately afterdefer d.logCall(...)(so the rejected call still logs), returninganchor is required. Mirrors the existing precedent inrelated.go,fetch_batch.go, andhistory.go.pkg/mcp/tools/tools_test.go—TestHandleFetch_EmptyAnchor, mirroringTestHandleHistory_EmptyAnchor. Asserts theanchor is requiredmessage and the absence of the genericfailed to fetcherror, so the test proves the guard short-circuits beforeEngine.Fetchrather than passing on the engine's own empty-ID error (the [enhancement] HandleWrite swallows GetNode errors with blank identifier — non-ErrNoRows DB failures silently fall into the create path #218 false-positive trap).Notes
anchoris already documented as the required node ID, so noskills/remind/update is needed — consistent with the sibling guards.🤖 Generated with Claude Code