mirror of
https://github.com/Memo-2023/mana-monorepo.git
synced 2026-05-15 09:21:09 +02:00
be81d11dc3
Enable real-time token streaming during the planner "calling-llm" phase
so the user sees live progress ("empfange Plan… 128 tokens") instead of
a static spinner. The parser still receives the full text once complete —
no partial-JSON risk.
Changes:
- Extract shared SSE parser from playground into @mana/shared-llm/sse-parser
- remote.ts: use stream:true when onToken callback is provided
- AiPlanInput: add optional onToken field (shared-ai)
- ai-plan task: pass onToken through to backend.generate()
- runner.ts: throttled (500ms) phaseDetail updates during streaming
- Playground: refactored to use shared SSE parser
Also includes: AI agent architecture comparison report (docs/reports/)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
||
|---|---|---|
| .. | ||
| backends | ||
| errors.ts | ||
| index.ts | ||
| orchestrator.ts | ||
| pricing.test.ts | ||
| pricing.ts | ||
| queue.ts | ||
| sse-parser.ts | ||
| store.svelte.ts | ||
| task.ts | ||
| tiers.ts | ||
| types.ts | ||