MCP session replay integration test #3939
Merged
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
alexhancock
approved these changes
Aug 11, 2025
Collaborator
alexhancock
left a comment
alexhancock
left a comment
There was a problem hiding this comment.
It LGTM! My only ideas for slight improvement to ergonomics
- Maybe name the replayer something like "validator"?
- I wonder if the binaries could easily be combined into a single module with
--mode record || validatemaybe it slightly easier to expand functionality in future
Collaborator
Author
|
Thanks @alexhancock good points -- made a single binary with a transport mode that will invite us to do the same for streamable http extensions. |
katzdave
added a commit
that referenced
this pull request
Aug 12, 2025
* 'main' of github.com:block/goose: feat: ToolError migration to ErrorData (#4051) docs: rename sessions (#4053) Add mcp automated testing blog (#4004) MCP session replay integration test (#3939) Docs: Cost tracking in CLI (#4043) sanitize message content on deserialization (#3966)
zanesq
added a commit
that referenced
this pull request
Aug 13, 2025
* 'main' of github.com:block/goose: (120 commits) Docs: Troubleshooting tip - Nodejs path on windows (#4065) fix: flag out uncompilable bit in windows (#4068) ci: fix docs-only filter to properly skip tests for documentation changes (#4066) fix: ctrl-C interruption in the CLI (#4057) docs: mcp-ui support (#4049) fix: delete dialog layout (#4037) ci: fix markdown file pattern to skip builds for all .md files (#4061) docs: add window title (#4059) blog: cleaning up some posts (#4050) fix: this should be a debug message not a warn (#4024) Better provider logging (#4052) feat: ToolError migration to ErrorData (#4051) docs: rename sessions (#4053) Add mcp automated testing blog (#4004) MCP session replay integration test (#3939) Docs: Cost tracking in CLI (#4043) sanitize message content on deserialization (#3966) Move summarize button inside of context view (#4015) blog: post on lead/worker model (#3994) Actually send cancellation to MCP servers (#3865) ...
ayax79
pushed a commit
to ayax79/goose
that referenced
this pull request
Aug 21, 2025
Signed-off-by: Jack Wright <[email protected]>
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.
Lets you set up an MCP server (stdio only for now), some interactions (tool calling only for now) and record the whole thing to a session replay file. Then commit the replay and result files and the test will run the interaction through the extension manager.
This works by using two new binaries included in this PR: one that sits in front of a stdio server, writing all i/o to a replay file, and one that reads said replay file and mimics the behavior of the recorded session.