Unpack tool output and hoist artifacts #2
Closed
Conversation
This file contains 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
|
Thanks. I made some changes to your branch here https://github.com/rectalogic/langchain-mcp/compare/tools We can just partition TextContent from the other pydantic MCP types, then jsonify the TextContent list and return the list of artifact MCP objects as-is. However, the standard tests fail on your branch and mine. It looks like the standard langchain tests don't properly handle |
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Outdated suggestions cannot be applied.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.
Previously, langchain-mcp was making the
ToolMessagecontent the entire output from MCP. MCP servers deliver tool output as a list of content objects, but not all of this object is for the LLM to see.This change extracts the text from the tool output so that it is the only thing that the LLM sees. It also extracts artifacts from the tool output and places them in the
ToolMessage's artifact attribute.There doesn't seem to be any recommended way to perform this extraction from the maintainers of MCP itself, so this change (naively) concatenates text blocks. I'm not sure how we are meant to deal with image and resource content blocks.