Fam Zheng f646391f14 extract Output trait: decouple AI core from Telegram ...

- Add src/output.rs with Output trait and 3 implementations:
  TelegramOutput (streaming via draft/edit), GiteaOutput (comments),
  BufferOutput (for worker/tests)
- Refactor run_openai_with_tools and execute_tool to use &mut dyn Output
- Remove run_claude_streaming, invoke_claude_streaming, run_openai_streaming
  (dead code — only OpenAI-compatible backend is used now)
- Remove BackendConfig::Claude code path from handler
- stream.rs: 790 → 150 lines

2026-04-10 21:10:36 +01:00

72 KiB

Raw Blame History

View Raw