BigMarc 2f3dd02148 feat: stream LLM tokens to the extension via /v1/ai/stream
- LocalEngineServer: add a streaming AI endpoint (newline-delimited JSON frames)
  over a no-Content-Length chunked response, plus an AIStreamHandler.
- AppState.handleServerAIStream: gate + iterate AIEngine.runStreaming, emitting
  each token — gives the runStreaming infrastructure its first real consumer.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-20 20:26:22 +02:00
..
f
2026-06-18 16:49:59 +02:00