fix: Drive Starlette lifespan ourselves for SSE transport too#94
Merged
Conversation
FastMCP's per-session lifespan re-initialized the Qdrant store and embedding provider on every SSE client connect/disconnect, racing the global store singletons. Apply the same fix already used for streamable-http: build the app via mcp.sse_app() and wrap its lifespan manually. Also documents SSE as the deprecated legacy transport in the README. Fixes #93 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
streamable-http: build the app viamcp.sse_app()and wrap its lifespan ourselves so init/teardown happens once per process, not per sessionstreamable-httpfor new setupsFixes #93
Test plan
uv run pytest— 265 passedmcpSDKsse_client/ClientSession: connected twice (connect → list_tools → disconnect, reconnect → list_tools → disconnect) against the fixed server —Starting semcode MCP server...logged exactly once across both connections🤖 Generated with Claude Code