Liang Jiaqing
844573387d
fix: convert tool_use blocks to text in NativeOAISession history to avoid API content type error
2026-03-29 19:08:20 +08:00
Liang Jiaqing
18ef86b69d
llmcore: move logs to temp/model_responses/ subdir; enhance error prefix detection
2026-03-29 15:06:19 +08:00
LJQ
d76842c549
Merge pull request #52 from octo-patch/feature/add-minimax-provider
...
feat: add MiniMax as first-class LLM provider
2026-03-29 14:51:02 +08:00
Liang Jiaqing
fe7e4c0952
refine: tool schema descriptions, docstring format, context_win 18000→20000
2026-03-29 13:06:06 +08:00
Liang Jiaqing
45679509ea
MixinSession: spring-back to primary + translate tools_schema to English
2026-03-29 12:48:36 +08:00
Liang Jiaqing
226fa69cc3
refactor MixinSession._raw_ask: simplify retry logic, skip yielding first-only error chunk
2026-03-29 10:53:26 +08:00
PR Bot
b6f697d40f
feat: add MiniMax as first-class LLM provider
...
- Temperature auto-clamping for MiniMax models: (0, 1] range enforcement
- <think> tag handling for MiniMax M2.7 reasoning output (alongside existing <thinking> support)
- MiniMax configuration example in mykey_template.py
- Updated README.md and GETTING_STARTED.md with MiniMax provider docs
- 19 unit tests + 6 integration tests (3 live tests with MINIMAX_API_KEY)
MiniMax models (M2.7, M2.7-highspeed, M2.5, M2.5-highspeed) are accessed via
the standard OpenAI-compatible interface at https://api.minimax.io/v1 , using
the existing LLMSession with an 'oai'-prefixed config key.
2026-03-29 07:09:46 +08:00
Liang Jiaqing
a5dbce396a
refactor: remove XAI/Gemini sessions, add MixinSession fallback, improve error handling
...
- Remove GeminiSession and XaiSession from llmcore.py
- Add MixinSession: multi-endpoint fallback with exponential backoff
- ga.py: handle empty/incomplete/max_tokens responses
- Update mykey_template.py and GETTING_STARTED.md accordingly
2026-03-28 08:14:35 +08:00
Jiaqing Liang
f6c5011eb0
refactor: rewrite GETTING_STARTED, cleanup README, add hub.pyw, remove QUICK_START.pdf
2026-03-27 12:58:13 +08:00
Liang Jiaqing
ff258dd0a9
refine: context window, timeout, abort guard, code_run multi-call check, clean logs
2026-03-26 21:31:48 +08:00
Liang Jiaqing
47ad98239f
enhance SSE parsing, add stream error/truncation detection, fix tool_call fallback extraction
2026-03-26 18:42:09 +08:00
Liang Jiaqing
551666a53b
refactor: unify OpenAI streaming into _openai_stream(), add Responses API support
...
- Extract shared _openai_stream() from LLMSession and NativeOAISession
- Add Responses API compatibility: system->developer role, flat tools format, no temperature
- Improve error handling: read body before raise_for_status in stream mode
- Add retry mechanism to NativeOAISession (was missing)
- Add api_mode, connect_timeout, read_timeout config to NativeOAISession
2026-03-25 23:50:28 +08:00
Liang Jiaqing
507e886322
refactor llmcore: extract _parse_claude_sse, simplify ToolClient, enhance logging and context trimming
2026-03-25 21:41:33 +08:00
Liang Jiaqing
1b60d2c773
minor: tweak prompt wording, improve OAI history compression
2026-03-25 10:00:16 +08:00
Liang Jiaqing
85250c2694
fix: unify assistant content format for prompt caching to work
2026-03-25 09:45:43 +08:00
Liang Jiaqing
b92d2bc97d
fix: always compress history tags, adjust context trim thresholds
2026-03-25 08:37:46 +08:00
Liang Jiaqing
ddce7ef549
feat: reflect hot-reload + enhance prompt caching & history compression
2026-03-24 22:58:20 +08:00
Liang Jiaqing
28f22c3973
feat: add prompt caching for NativeClaudeSession
2026-03-24 20:00:44 +08:00
Liang Jiaqing
f9a0aa71fa
fix: add tool_result placeholder for NativeClaudeSession to prevent 502
2026-03-24 19:54:27 +08:00
Liang Jiaqing
515b0cd985
feat: unified media download in wechatapp + proxy support for NativeOAISession
2026-03-23 20:57:39 +08:00
Jiaqing Liang
4b4dc51336
fix: tool_use regex negative lookahead to prevent cross-tag matching; tgapp relative path resolve
2026-03-23 11:46:10 +08:00
Liang Jiaqing
6f6d9f6570
feat: add NativeOAISession + minor fixes (code_run script fallback, thinking prompt tags)
2026-03-22 22:19:46 +08:00
Liang Jiaqing
a9f0e9628f
fix: llm session tweaks & agent init refactor
2026-03-22 09:55:24 +08:00
Liang Jiaqing
fdc24e4dd0
add NativeClaudeSession+NativeToolClient, support parallel tool calls, fix tool_calls[-1:], add llm log
2026-03-21 12:13:46 +08:00
Liang Jiaqing
85f17db487
feat: prompt_cache skip compress + style
2026-03-20 23:47:15 +08:00
YangChen-pro
70ed09ad2b
Support configurable OpenAI reasoning effort
2026-03-18 22:54:58 +08:00
Liang Jiaqing
00038cd1ae
refactor: unify LLM session constructors to accept cfg dict
2026-03-17 16:52:12 +08:00
Jiaqing Liang
065a5ee4bf
refactor: working memory dict, merge chat paths, simplify SKILL docs
2026-03-16 13:18:41 +08:00
wjl2023
2809a54b29
fix: Add moonshot API temperature=1.0 constraint
...
- Moonshot API (like Kimi) only accepts temperature=1.0
- Added 'moonshot' detection alongside 'kimi' in both raw_ask methods
- Prevents 400 errors when using moonshot models
2026-03-14 20:44:29 +08:00
Liang Jiaqing
68a936eb2c
debug print result; kimi temp=1.0 compat
2026-03-14 20:34:57 +08:00
Vivi 8n24
6fe93e9cb4
Add chat app adapters for QQ, Feishu, WeCom, and DingTalk
2026-03-13 16:04:18 +08:00
Liang Jiaqing
fd7bf241d0
rename sidercall.py to llmcore.py; add cache-aware cd to compress_history_tags
2026-03-13 13:21:32 +08:00
