gensokyo-devandgensokyo-dev 8084916859 perf(eval): measure MCP catalog usage through the real Codex harness (#9035) ...

* perf(eval): measure MCP catalog usage through real Codex sessions

* fix(eval): control the active Codex code mode host

* fix(eval): reject unavailable host controls without hiding client errors

* test(eval): cover the supported default and actionable client errors

* docs(eval): record pinned Codex catalog and real package measurements

* fix(eval): pin matrix identity and retain failed trial observations

---------

Co-authored-by: gensokyo-dev <gensokyo-dev@users.noreply.github.com>

2026-11-06 02:25:34 +08:00

..

analysis-efficiency

perf(eval): measure MCP catalog usage through the real Codex harness (#9035)

2026-11-06 02:25:34 +08:00

browser

refactor(browser): move bundle fixture composition out of runtime

2026-10-24 10:49:46 +08:00

cli

feat(guidance): search installed workflow sections (#6996)

2026-10-29 16:47:10 +08:00

http

feat(mcp): add opt-in streamable HTTP transport (#4955)

2026-10-19 23:58:51 +08:00

mcp

test: strengthen integration oracles and verification (#8295)

2026-11-01 00:15:28 +08:00

process

test: strengthen integration oracles and verification (#8295)

2026-11-01 00:15:28 +08:00

workspace

fix(javascript): preserve runtime path bytes and Electron ownership (#4941)

2026-10-20 17:25:19 +08:00

applicationSessionFixture.ts

refactor(cli): retain typed analysis outcomes through delivery

2026-10-27 09:16:02 +08:00

artifactClientScope.ts

test: strengthen regression oracles and cleanup ownership (#8152)

2026-10-31 00:22:16 +08:00

failFileReadAfterAbort.ts

fix(files): preserve physical read failures across late cancellation

2026-10-21 06:14:03 +08:00

holdFirstFileRead.ts

fix(io): retain cleanup ownership and honor cancellation

2026-10-12 14:12:44 +08:00

hostCleanup.ts

fix(process): re-read unreadable tokens before signaling and name the process (#8553)

2026-11-02 00:21:23 -08:00

javascriptApplicationFixture.ts

fix(javascript): preserve runtime path bytes and Electron ownership (#4941)

2026-10-20 17:25:19 +08:00

javascriptApplicationScope.ts

refactor(javascript): share the reconstruction input contract

2026-10-24 15:02:26 +08:00

javascriptArtifactPathResolution.ts

refactor(javascript): centralize package and JSON document facts

2026-10-23 14:40:52 +08:00

javascriptSemanticGraphFixture.ts

test(javascript): share semantic graph fixtures (#1631)

2026-10-11 04:05:35 +08:00

jsonClientRegistrationContract.ts

fix: streamline tests and preserve Darwin process ownership (#8275)

2026-10-31 16:43:04 +08:00

ownedRizinCommandEvidenceTests.ts

fix(reverse): reconcile cleanup ownership and mutation diagnostics (#2799)

2026-10-14 04:47:34 +08:00

publishedDirectoryCloseFailure.ts

test: strengthen integration oracles and verification (#8295)

2026-11-01 00:15:28 +08:00

referenceSourceResourceScope.ts

fix(reference)!: retain source and metadata cleanup owners

2026-10-11 06:10:10 +08:00

reverseDebuggerMcpTestHelpers.ts

test(mcp): consolidate fixture connection and cleanup ownership

2026-10-24 14:49:13 +08:00

reverseEngineeringCompositionEdgeCases.ts

fix(objdump)!: preserve unknown executable identity (#8824)

2026-11-04 02:01:44 +08:00

reverseEngineeringCompositionFixtures.ts

fix(reverse): reconcile cleanup ownership and mutation diagnostics (#2799)

2026-10-14 04:47:34 +08:00

reverseEngineeringMcpHarness.ts

fix(reverse): reconcile cleanup ownership and mutation diagnostics (#2799)

2026-10-14 04:47:34 +08:00

reverseEngineeringService.ts

fix(reverse): reconcile cleanup ownership and mutation diagnostics (#2799)

2026-10-14 04:47:34 +08:00

workflowGit.ts

fix(ci): scope verification and reuse native runners (#1344)

2026-10-09 18:22:03 +00:00