LLM: streaming + rich context + 32×32 frames + proxy log

- Streaming: requestSongTweak now uses streamObject when a progress
  callback is provided (via handleLlmTweak), emitting partial {rationale,
  edits} and updating toast/console as text arrives; falls back to
  generateObject if gateway doesn't support streaming. Models always
  called via provider.chat(modelId) / /v1/chat/completions, the correct
  path for meta/muse-spark-1.3-contributor via gateway.

- Rich context: spec.js gains FULL control wording (any amount/arrangement/
  bpm allowed), and detailed payload — trackSummary with bandBalance,
  tempo, normalization (per-feature lo/hi), sectionsDetailed (energy/
  flux/centroid/flatness/width/slope/endEnergy/duration), stats
  (kinds, avg/max energy, bars). LLM told You have FULL control.

- Low-res vision: new src/llm/thumbs.js — captureThumbnails(show, {8,32})
  samples section midpoints, warms up state, renders via Show, box-averages
  down to 32×32 JPEG data URLs, restores timeline. main.js now captures 8
  frames with two animation frames of pause, then passes them as {type:
  image, image: dataUrl} parts in the user message (llmTweak.js
  attachFramesToMessages).

- Proxy logging (no bearer): vite.config.js llmGatewayProxy now logs
  sanitized requests/responses to logs/llm-proxy.log (JSON lines, 1MB
  rotation, redacts apiKey/authorization from path/body/headers) so the
  coding agent can inspect prompts without re-calling. .gitignore adds
  logs/.

Co-Authored-By: Claude <noreply@anthropic.com>

flow-state/.gitignore

@@ -3,6 +3,7 @@ dist
 .vite
 out
 .env.local
+logs/
 
 # Scratch probes: one-off harnesses for debugging decode/encode/mux issues.
 # They are throwaway by nature and were committed once by accident.