Add typed MCP transcript outputs - #422
Closed
Lauritz-Timm wants to merge 4 commits into
Closed
Conversation
This was referenced Jul 30, 2026
Lauritz-Timm
force-pushed
the
feat/mcp-transcript-output
branch
from
August 4, 2026 19:01
0f3f47b to
498f1ad
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Add direct typed MCP output for the transcript tool family.
Motivation
All five transcript tools encode machine data inside MCP text. Modern clients must decode JSON-RPC and then parse another string, while generic structured wrappers duplicate large transcript payloads.
Changes
output/transcript.rsdomain moduleCompatibility and safety
MCP
2024-11-05receives the existing text and no structured fields. Only negotiated modern clients receive typed values. Schemas are closed at every described object boundary.Validation
Focused tests chain session creation, message recording, search, replay, and statistics. They validate the real emitted values against the generated schemas and verify stable IDs, nested values, named counts, closed schemas, timestamp compatibility, and exact legacy output preservation.
The evaluation measured a 31.3% reduction in estimated wire tokens for modern transcript statistics.