Val-sss c0ec272925 fix: LLMBackend auto-detect OpenAI-compatible API vs Ollama ...

Problem: user configures base_url as https://api.deepseek.com during
onboarding, but LLMBackend hardcodes /api/chat (Ollama endpoint),
resulting in 404 errors on cloud APIs.

Solution: auto-detect based on URL pattern:
  - localhost:11434 → Ollama (/api/chat)
  - Cloud domains (deepseek/siliconflow/openai/groq/etc) → OpenAI compat (/v1/chat/completions)
  - Remote non-localhost → OpenAI compat
  - URL containing /v1 → OpenAI compat

Also:
  - Pass api_key from config to LLMBackend
  - New _chat_openai_compat() method handles OpenAI format (Authorization header, standard payload)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-29 19:44:08 +08:00

..

__init__.py

Kaiwu v3 MVP: deterministic expert pipeline for local-model coding agent

2026-04-26 12:47:34 +08:00

main.py

fix: LLMBackend auto-detect OpenAI-compatible API vs Ollama

2026-04-29 19:44:08 +08:00

onboarding.py

v0.7.0: P1+P2+搜索重构+UI全面优化

2026-04-28 17:52:59 +08:00

status_bar.py

v0.7.0: P1+P2+搜索重构+UI全面优化

2026-04-28 17:52:59 +08:00