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

fix(docs): preserve verification reports after experiment archival (#7462)

2026-10-27 15:10:48 +08:00

android-jni-bindings-2026-10-27.md

feat(android): link native declarations to static JNI candidates (#7472)

2026-10-27 18:53:22 +08:00

android-manifest-components-2026-10-24.md

feat(android): project a structured manifest component inventory (#5025)

2026-10-24 17:14:23 +08:00

android-r8-mapping-2026-10-27.md

feat(android): apply caller-selected R8 mapping evidence (#7456)

2026-10-27 15:47:08 +08:00

apk-signature-2026-10-22.json

feat(apk): inspect signing declarations with retained fact queries

2026-10-22 11:48:09 +00:00

apk-signature-2026-10-22.md

feat(apk): inspect signing declarations with retained fact queries

2026-10-22 11:48:09 +00:00

apple-ips-2026-10-24.md

feat(apple): inspect IPS crash reports (#6511)

2026-10-24 16:02:59 +08:00

binary-hardening-2026-10-31.md

feat(native): report binary hardening for ELF, PE and Mach-O (#8524)

2026-11-06 01:07:00 +08:00

browser-saved-values-2026-10-26.md

feat(browser): reuse saved response values across scenario steps (#7267)

2026-10-27 08:15:52 +08:00

browser-scenario-validation-2026-10-27.md

feat(cli): validate browser scenarios offline (#7343)

2026-10-27 08:47:36 +08:00

capability-composition-2026-11-01.md

refactor(composition): unify capability bindings and cleanup ownership (#8441)

2026-11-01 13:30:21 +08:00

cli-json-lines-2026-10-23.md

feat(cli)!: export row-oriented results as JSON Lines (#5629)

2026-10-24 02:13:28 +08:00

cli-version-report-2026-10-23.md

feat(cli): report version and runtime with an explicit output format (#6530)

2026-10-24 00:06:03 +08:00

electron-cancellation-2026-10-16.json

fix(electron): preserve cancellation across waits, state reads and cleanup

2026-10-16 21:12:26 +08:00

electron-cancellation-2026-10-16.md

docs(limits): describe how to design admission recovery (#6368)

2026-10-23 05:10:36 +08:00

electron-ipc-listeners-2026-10-16.json

fix(electron): preserve native IPC listener behavior (#4389)

2026-10-17 04:17:11 +08:00

electron-ipc-listeners-2026-10-16.md

fix(electron): preserve native IPC listener behavior (#4389)

2026-10-17 04:17:11 +08:00

electron-native-once-2026-10-16.json

fix(electron): delegate once dispatch to the active runtime (#4605)

2026-10-17 06:38:13 +08:00

electron-native-once-2026-10-16.md

fix(electron): delegate once dispatch to the active runtime (#4605)

2026-10-17 06:38:13 +08:00

electron-native-once-2026-10-16.review.rows.jsonl

fix(electron): delegate once dispatch to the active runtime (#4605)

2026-10-17 06:38:13 +08:00

electron-native-once-2026-10-16.rows.jsonl

fix(electron): delegate once dispatch to the active runtime (#4605)

2026-10-17 06:38:13 +08:00

electron-shell-sync-2026-10-16.json

fix(electron): block synchronous shell effects during capture

2026-10-16 21:03:12 +00:00

electron-shell-sync-2026-10-16.md

fix(electron): block synchronous shell effects during capture

2026-10-16 21:03:12 +00:00

evidence-input-composition-2026-10-31.json

refactor(evidence): unify retained inputs across domains (#8299)

2026-10-31 14:45:21 +00:00

evidence-input-composition-2026-10-31.md

refactor(evidence): unify retained inputs across domains (#8299)

2026-10-31 14:45:21 +00:00

ghidra-dol-2026-10-24.md

feat(ghidra): analyze GameCube/Wii DOL executables through Ghidra (#6240)

2026-10-24 17:56:31 +08:00

ghidra-procedure-timeout-2026-10-23.md

feat(ghidra): bound one procedure's decompile without closing the session (#5662)

2026-10-24 07:42:50 +08:00

gpu-code-objects-2026-10-21.json

feat(gpu): inspect static CUDA and HIP code objects (#5813)

2026-10-21 19:06:44 +08:00

gpu-code-objects-2026-10-21.md

feat(gpu): inspect static CUDA and HIP code objects (#5813)

2026-10-21 19:06:44 +08:00

il2cpp-generic-instances-2026-10-24.md

feat(il2cpp): link generic method instances behind --generic-instances (#5785)

2026-10-24 16:19:05 +08:00

investigation-lifecycle.md

feat(investigation)!: retain records across engine cleanup (#8361)

2026-10-31 21:34:45 +00:00

javascript-analysis-effects-2026-10-15.json

fix(javascript): declare owned analysis worker effects

2026-10-15 21:36:12 +08:00

javascript-analysis-effects-2026-10-15.md

fix(verifiers): centralize failure and cleanup ownership

2026-10-24 15:38:35 +08:00

javascript-assignment-influence-2026-10-24.md

feat(javascript): link assignment right-hand sides to their writes (#6206)

2026-10-24 10:04:38 +08:00

javascript-interruption-applicability-2026-10-15.json

fix(javascript): preserve analysis applicability after interruption (#4207)

2026-10-16 03:46:00 +08:00

javascript-interruption-applicability-2026-10-15.md

fix(javascript): preserve analysis applicability after interruption (#4207)

2026-10-16 03:46:00 +08:00

javascript-literal-byte-budget-2026-10-15.json

fix(javascript): enforce semantic byte bounds for literals

2026-10-15 23:43:05 +08:00

javascript-literal-byte-budget-2026-10-15.md

fix(javascript): enforce semantic byte bounds for literals

2026-10-15 23:43:05 +08:00

javascript-module-references-2026-10-15.json

feat(javascript): add filtered retained module reference views

2026-10-15 21:05:00 +08:00

javascript-module-references-2026-10-15.md

feat(javascript): add filtered retained module reference views

2026-10-15 21:05:00 +08:00

javascript-native-handoff-identity-2026-10-15.json

fix(javascript): bind native handoffs to canonical byte identity

2026-10-15 17:08:49 +00:00

javascript-native-handoff-identity-2026-10-15.md

fix(javascript): bind native handoffs to canonical byte identity

2026-10-15 17:08:49 +00:00

javascript-retained-facts-2026-10-15.json

feat(javascript): query retained application facts by exact path (#4265)

2026-10-16 12:46:53 +08:00

javascript-retained-facts-2026-10-15.md

refactor(javascript)!: consolidate renderer and route ownership

2026-10-27 09:05:24 +08:00

javascript-route-inventory-2026-10-21.md

docs: archive historical verification and release inventories (#7519)

2026-10-28 00:54:54 +08:00

javascript-source-paths-json-2026-10-24.md

feat(cli): accept JavaScript source selections from a JSON array or file (#5029)

2026-10-24 12:32:41 +08:00

javascript-window-options-2026-10-16.json

feat(electron): resolve stable local constant window options

2026-10-16 14:52:33 +08:00

javascript-window-options-2026-10-16.md

docs(limits): describe how to design admission recovery (#6368)

2026-10-23 05:10:36 +08:00

mcp-catalog-codex-2026-11-05.json

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

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

mcp-catalog-codex-2026-11-05.md

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

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

native-decompile-directory-2026-10-23.md

fix(analysis): retain source evidence through directory exports (#7250)

2026-10-26 23:56:03 +08:00

native-function-summary-2026-10-23.md

feat(analysis)!: default function MCP output to retained summaries (#5660)

2026-10-24 08:18:53 +08:00

pe-imports-2026-10-24.md

feat(pe): inspect import and delay-load tables (#6509)

2026-10-24 11:44:12 +08:00

pe-load-config-2026-10-24.md

feat(pe): inspect TLS callbacks and load configuration (#7008)

2026-10-24 22:06:41 +08:00

runtime-analysis-settings.md

feat(mcp): support runtime analysis limit recovery (#7049)

2026-10-25 09:45:26 +08:00

web-bundle-paging-2026-10-26.md

feat(web): page retained bundle endpoint observations and inferences (#7259)

2026-10-27 01:37:39 +08:00