fix(activation): add per-call timeout to embedding fetch#81
Merged
Conversation
The EmbeddingClient.embedBatch fetch had no AbortSignal, so a slow or rate-limited embedding proxy (e.g. the unified LLM proxy) caused the request to hang indefinitely. The held TCP connection silently broke the /activate HTTP route and the MCP 'activate' tool — the MCP 15s timeout surfaced the hang as a generic TimeoutError with no indication of the actual cause. Add a configurable per-call timeout (default 20s, override via EMBEDDING_TIMEOUT_MS) wired into the fetch via AbortSignal.timeout. Also expose timeoutMs as an EmbeddingClient constructor option for testability. Regression test uses a hanging local Bun.serve to verify the fetch aborts within the configured window.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The EmbeddingClient.embedBatch fetch had no AbortSignal, so a slow or rate-limited embedding proxy (e.g. the unified LLM proxy) caused the request to hang indefinitely. The held TCP connection silently broke the /activate HTTP route and the MCP 'activate' tool — the MCP 15s timeout surfaced the hang as a generic TimeoutError with no indication of the actual cause.
Add a configurable per-call timeout (default 20s, override via EMBEDDING_TIMEOUT_MS) wired into the fetch via AbortSignal.timeout. Also expose timeoutMs as an EmbeddingClient constructor option for testability. Regression test uses a hanging local Bun.serve to verify the fetch aborts within the configured window.