AlphaPulse

0 Fork 0

T

eezd b549f3f441 Replace temperature with reasoning effort and retry in-stream errors

- Providers get a default reasoning effort (low..max, empty = not sent);
  chat can override it per message. OpenAI sends reasoning_effort,
  Claude sends output_config.effort with adaptive thinking, and thinking
  blocks are replayed during the tool loop.
- Show a thinking indicator while waiting for model output.
- Surface in-stream upstream errors (e.g. overloaded) instead of
  breaking the SSE stream, and retry them up to 3 times when nothing
  has been emitted yet.

2026-10-14 15:12:27 +08:00

backend

Replace temperature with reasoning effort and retry in-stream errors

2026-10-14 15:12:27 +08:00

deploy

Add AI chat with skills management and model provider settings

2026-10-14 13:11:45 +08:00

web

Replace temperature with reasoning effort and retry in-stream errors

2026-10-14 15:12:27 +08:00

.gitignore

Stop tracking docs directory

2026-10-14 11:24:41 +08:00

AGENTS.md

Initial AlphaPulse implementation: news crawler and Binance klines

2026-10-13 13:32:55 +08:00