feat(mcp): implement sampling/createMessage capability - #207
Merged
Conversation
- Add sampling.ts with CreateMessage request handler that routes through queryLLM for multi-provider LLM support - Declare sampling capability in getMcpClientCapabilities() so MCP servers know the client supports sampling - Register/unregister sampling handler in client lifecycle - Convert between MCP SamplingMessage and internal Anthropic format - Resolve model from server's modelPreferences hints - Map stop_reason between internal and MCP spec formats - Export sampling control APIs (enable/disable/test helpers) - Update capability tests for sampling enabled/disabled states
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Implement MCP sampling capability, allowing MCP servers to request LLM completions through the client via the
sampling/createMessageprotocol method.Changes
sampling.tswith CreateMessage request handler routing throughqueryLLMfor multi-provider LLM supportsamplingcapability ingetMcpClientCapabilities()so MCP servers know the client supports samplingcreateMcpClient/closeMcpClient)modelPreferenceshints (speed→quick, intelligence→main)stop_reasonbetween internal (end_turn) and MCP spec (endTurn) formatsisMcpSamplingEnabled,setMcpSamplingEnabled) and test helpersDesign Decisions
quickmodel pointer by default for fast, low-cost sampling responsesmodelPreferences.hintsto match against configured modelssetMcpSamplingEnabled(false)