Funk-lab/admin/ia
Claude 1340c36b16
docs(stt): documenter le fix /no_think Qwen3 + instance embeddings :1238
- admin/ia/stt.md : caveat « thinking » Qwen3 (content vide / timeout 502) +
  fix /no_think + fallback reasoning_content ; roadmap 5e ; bannière.
- stt/server/README.md : env STT_DISABLE_THINKING + section caveat Qwen3.
- admin/ia/llama_server.md : 4e instance llama-embed :1238 (nomic, dim 768),
  double source d'embeddings (1234 Qwen3 / 1238 nomic), caveat thinking,
  correction dim Qwen3 (3584 → 4096).
- admin/ia/litellm.md : cross-ref caveat thinking (concerne tous les
  consommateurs de hermes-default/qwen3).
- ci : exclure **/*.md du trigger build-stt-server (doc-only ne rebuild plus).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013FmcxGsyXZXogiAHQLjnZT
2026-06-17 20:31:34 +00:00
..
alertmanager-webhook.md fix(webhook): réponse HTTP 200 immédiate + ask-agent asynchrone 2026-05-14 21:58:39 +02:00
hermes-auto-improve.md docs: synchroniser la doc avec l'état réel du cluster (revue Ansible + incident Qdrant) 2026-06-10 15:11:53 +02:00
hermes-souls.md feat(souls): révision complète des 4 SOUL.md Hermes + doc 2026-05-14 22:22:56 +02:00
hermes-voice.md feat(voice): améliorer hermes-voice + fix hermes-agent 2026-06-02 16:24:21 +02:00
hermes.md docs: mise à jour documentation — NVMe, Qwen3, gaps IaC 2026-05-30 22:58:24 +02:00
litellm.md docs(stt): documenter le fix /no_think Qwen3 + instance embeddings :1238 2026-06-17 20:31:34 +00:00
llama_server.md docs(stt): documenter le fix /no_think Qwen3 + instance embeddings :1238 2026-06-17 20:31:34 +00:00
rag.md feat(stt): embeddings dédiés nomic-embed-text sur gpu-01 (:1238) + migration auto 2026-06-17 18:56:14 +00:00
rocm.md docs: réorganisation complète de admin/ en 4 domaines thématiques 2026-05-14 00:47:58 +02:00
stt.md docs(stt): documenter le fix /no_think Qwen3 + instance embeddings :1238 2026-06-17 20:31:34 +00:00