Repository navigation
Reuse Session executors through a shared Harness contract - #193
Merged
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
A Session now retains its native executor between Turns. Core schedules durable work through one Runtime lifecycle; Codex, Claude and MiniMax implement the same Executor/Turn contract. Healthy follow-up Turns preserve their native process and exact history.
Validation:
make check, with the unchanged Web gate executed on mx and other gates on zju. Includes the dedicated PostgreSQL suite, generated-contract checks, 55 browser tests, Claude bridge tests and Rust checks.2064a177..fecf58dafound no substantiated in-scope issue.Native versions: Codex 0.153.4, Claude SDK 0.3.269 / native 2.1.269, MiniMax 0.4.12. Versioned evidence is retained under
/home/fanjingluo/.oac/acceptance/session-executor-reuse-20260928on zju, including failed runs and final cleanup records. The earlier MiniMax managed sample contained a native duplicate tool call; the one permitted fresh-Session strict retry passed.Timing samples prove retained ownership and avoided native preparation, not a universal response-time improvement. Queue and environment-ready durations cannot be separately derived from the standalone samples; this limit is preserved in the evidence.