add a timeout arguments on per-request basis (as per MCP specifications) #601
Conversation
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
|
fixes #600 |
|
@dsp-ant / @jerome3o-anthropic, I know the amount of notifications must be crazy but it's a very quick and simple change that makes the python sdk more compliant with the MCP specifications with regard to timeouts. Hope you get some time to review it at some point. |
dsp-ant
approved these changes
Apr 29, 2025
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Outdated suggestions cannot be applied.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.
Motivation and Context
The MCP Specifications says:
How Has This Been Tested?
No regression on the test / test running locally.
Breaking Changes
No it's a transparent change which enable to set timeout on per-request basis. If not set it default to the previous behavior of not having a timeout or using the session based timeout.
Types of changes
Checklist
Additional context
Notes:
I have added the capacity to set the read timeout only on the tool_call requests which is probably the most critical one but we might want to extend that to other calls from the client as well.