Commit Graph

6 Commits

Author SHA1 Message Date
jxxghp
a05ffc07d4 refactor: remove legacy LLM_DISABLE_THINKING and LLM_REASONING_EFFORT config, unify thinking_level handling
- Eliminate support for LLM_DISABLE_THINKING and LLM_REASONING_EFFORT in config, code, and tests
- Simplify LLM thinking level logic to rely solely on LLM_THINKING_LEVEL
- Refactor LLMHelper and related endpoints to remove legacy parameter handling
- Update system API and test utilities to match new configuration structure
- Minor code cleanup and formatting improvements
2026-04-25 10:42:03 +08:00
jxxghp
4a81417fb7 fix: preserve deepseek reasoning content in tool loops 2026-04-25 09:37:01 +08:00
jxxghp
c7fa3dc863 feat: unify llm thinking level controls 2026-04-24 19:50:23 +08:00
jxxghp
38933d5882 feat(agent): support disabling model thinking 2026-04-22 10:36:36 +08:00
笨笨
409abb66be test: remove absolute path from llm helper test 2026-04-21 20:39:32 +08:00
笨笨
8aa8b1897b feat: add llm test endpoint 2026-04-21 20:39:32 +08:00