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
This commit is contained in:
Claude 2026-06-17 20:31:13 +00:00
parent c79c203970
commit 1340c36b16
No known key found for this signature in database
5 changed files with 62 additions and 7 deletions

View file

@ -7,6 +7,7 @@ on:
branches: ["main", "claude/**"]
paths:
- "stt/server/**"
- "!stt/server/**/*.md" # les changements doc-only ne rebuildent pas l'image
- ".github/workflows/build-stt-server.yml"
workflow_dispatch: