0e75245205e89e60576608b14f765917b2c35da3
Session 1 step 2 no longer needs a person. POST /api/ptt takes raw PCM16 16kHz mono, so the committed STT fixtures stand in for a microphone. Three fixtures pass end to end: 200, real speech back, right intent. Step 9 gets a cause. A spoken turn is 32-34s, of which one phrasing call is 30.0s. Both interactive calls decoded exactly 512 tokens, the chat cap, and were truncated. The resident model is a Thinking variant and llamaArgs never passes the enable_thinking:false that deploy/mavgpud.json passes for the workstation. Filed as V-531. Steps 7 and 8 cannot run. The morning routine is the only nudge source and the dispatcher drops it on presence=away every time, which is V-15. 287's own ten QA steps were rewritten in Vikunja: all ten were mavwaked, which does not run on homesrv by decision (V-463). Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011x5DgnExQ5XZy8TZPs5bot
Merge pull request 'Kuma: a fact per monitor, so she can name the service that is down' (#147) from task/444-kuma-a-fact-per-monitor-so-she-can-name into master
Description
No description provided
Languages
Go
97.1%
HTML
0.9%
Shell
0.6%
CSS
0.5%
Makefile
0.3%
Other
0.6%