Skip to content

History / QA Evidence

Revisions

  • Update hermes: BP/predefined interactive Ubuntu PASS + macOS sonnet blocked #485

    @tmuskal tmuskal committed May 30, 2026
  • HERMES macOS WORKS: 3 models PASS + Ubuntu gemini-flash PASS

    @tmuskal tmuskal committed May 30, 2026
  • Update pi BP/create DeepSeek BH PASS + mark omni flash blocked

    @tmuskal tmuskal committed May 30, 2026
  • Update omni: Windows gpt-5.5 blocked #615 (ENOENT), fix dispatched

    @tmuskal tmuskal committed May 30, 2026
  • Update omni macOS: PASS for gpt-5.4-mini + DeepSeek (run 26677499820)

    @tmuskal tmuskal committed May 30, 2026
  • Update omni gpt-5.5 Windows to FAIL (atomic write ENOENT — Windows .a5c dir issue)

    @tmuskal tmuskal committed May 30, 2026
  • Update omni gpt-5.5 macOS to PASS (run 26677285758)

    @tmuskal tmuskal committed May 30, 2026
  • Update omni: PASS for gpt-5.5+mini+DeepSeek, sonnet blocked #485, flash FAIL

    @tmuskal tmuskal committed May 30, 2026
  • Extend omni section with all 5 models (gpt-5.5, mini, sonnet, flash, DeepSeek)

    @tmuskal tmuskal committed May 30, 2026
  • Update omni gpt-5.4-mini Ubuntu to PASS (run 26674661922)

    @tmuskal tmuskal committed May 30, 2026
  • Mark remaining 13 codex BP FAILs as blocked #563 (model behavior) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

    @tmuskal tmuskal committed May 30, 2026
  • Update wiki: codex BP/create gemini-flash Ubuntu PASS, mark pi BP create failures

    @tmuskal tmuskal committed May 30, 2026
  • Update hermes NI Ubuntu: PASS for gpt-5.4-mini + DeepSeek, sonnet blocked #485

    @tmuskal tmuskal committed May 30, 2026
  • HERMES WORKS: Update hermes NI gpt-5.5 Ubuntu to PASS (run 26674992430)

    @tmuskal tmuskal committed May 30, 2026
  • Update codex BP/predefined gpt-5.5 BH to PASS on Ubuntu+macOS

    @tmuskal tmuskal committed May 29, 2026
  • Update codex BP gpt-5.5 to PASS on Ubuntu+macOS (predefined+create)

    @tmuskal tmuskal committed May 29, 2026
  • Mark BP gemini-flash model behavior failures blocked #563 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

    @tmuskal tmuskal committed May 29, 2026
  • Fix last remaining bare FAIL cells — all cells now PASS or blocked with issue

    @tmuskal tmuskal committed May 29, 2026
  • Mark all remaining BP FAILs as blocked #563 (model behavior)

    @tmuskal tmuskal committed May 29, 2026
  • Mark cursor-cli blocked #562 (needs CI investigation)

    @tmuskal tmuskal committed May 29, 2026
  • Mark copilot-cli blocked #560 (auth) and opencode blocked #561 (server startup)

    @tmuskal tmuskal committed May 29, 2026
  • Update codex BP/create flash Ubuntu + claude-code BP/predefined flash macOS BH to PASS

    @tmuskal tmuskal committed May 29, 2026
  • Update codex BP/predefined gemini-flash Windows BH with latest evidence

    @tmuskal tmuskal committed May 29, 2026
  • Update codex BP/predefined gemini-flash Windows interactive to PASS

    @tmuskal tmuskal committed May 29, 2026
  • Update gemini-cli BI gpt-5.4-mini Windows to PASS — all #547 BI cells resolved

    @tmuskal tmuskal committed May 29, 2026
  • Update codex BP/predefined gemini-flash macOS bridged-hooks to PASS

    @tmuskal tmuskal committed May 29, 2026
  • Update codex BP/predefined gemini-flash macOS interactive to PASS

    @tmuskal tmuskal committed May 29, 2026
  • Update gemini-cli BI gpt-5.4-mini Ubuntu to PASS

    @tmuskal tmuskal committed May 29, 2026
  • Update codex BP/predefined gemini-flash to PASS (thought_signature fix verified)

    @tmuskal tmuskal committed May 29, 2026
  • Update gemini-cli BI Windows: PASS for DeepSeek/gpt-5.5/flash, sonnet blocked #485

    @tmuskal tmuskal committed May 29, 2026