fix: sanitize server names for passing into model tool calls #563
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
Desktop App for this PRThe following build is available for testing: The app is signed and notarized for macOS. After downloading, unzip the file and drag the Goose.app to your Applications folder. This link is provided by nightly.link and will work even if you're not logged into GitHub. |
michaelneale
added a commit
that referenced
this pull request
Jan 9, 2025
* v1.0: feat: Implement a simplified reference agent and dev toolkit (#564) fix: sanitize server names for passing into model tool calls (#563) added a new mcp system + refactor to support it (#552) feat: port over nondeveloper system into mcp server (#561) fix: check server capability when client sends requests (#558) fix: update instructions (#557)
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Outdated suggestions cannot be applied.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.
sanitize the server name response from the MCP servers, this is propagated throughout the agent's usage and eventually into the tool call to the LLMs
a couple of the example servers use
example-server/$NAMEand that currently breaks goose the error is aError: Request failed: 400 Bad Requestand digging into it you eventually get a crypticBoth anthropic and openai have the same format:
note: this does not handle the tool names nor the char limit, will need to have a broader design