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

..

MainWindow

f

2026-06-18 16:49:59 +02:00

AppState.swift

feat: stream LLM tokens to the extension via /v1/ai/stream

2026-06-20 20:26:22 +02:00

AskView.swift

f

2026-06-18 16:49:59 +02:00

GrammarGemApp.swift

feat: backend-neutral AI seam, Ollama backend, extension bridge + trust/correctness fixes

2026-06-20 20:21:29 +02:00

MenuBarContent.swift

f

2026-06-18 16:49:59 +02:00

OnboardingView.swift

f

2026-06-18 16:49:59 +02:00

SettingsView.swift

f

2026-06-18 16:49:59 +02:00