ys/GenericAgent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
257 Commits 1 Branch 0 Tags
117028b5d93b4dfba0342786302769bc2d772cd8
Commit Graph

257 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Liang Jiaqing
117028b5d9 simphtml: refine pathType detection, simplify secondary marking, init response, reduce sleep 2026-03-30 20:37:27 +08:00
Liang Jiaqing
f320d141a0 feat: CDP bridge extension integration - ext_ws session type, DOM-channel CDP/batch/cookies/tabs, autofill bringToFront fix, await support in SOP 2026-03-30 20:01:27 +08:00
Liang Jiaqing
bc5d1eafaf feat: add --bg/--input flags to agentmain, rename & simplify subagent SOP 2026-03-30 15:03:28 +08:00
Liang Jiaqing
6cec6d8014 feat: autonomous SOP refactor + helper.py with auto date/numbering 
- Refactored autonomous_operation_sop.md with clearer path warnings and workflow
- Added helper.py: complete_task() auto-prepends R-number + date to history
- Updated scheduled_task_sop.md and web_setup_sop.md
 2026-03-30 14:30:30 +08:00
Liang Jiaqing
473659ba6e refactor: agent loop done_hooks, inline_eval, scheduler logging & health_check 
- agent_loop: for→while, _done_hooks callback mechanism, max_turns=40
- agentmain: pass self to handler, abort clears task queue
- stapp: heartbeat yield for Streamlit StopException detection
- ga: _inline_eval param for in-process eval, no_tool thresholds tuned
- scheduler: logging, max_delay_hours, weekday repeat, health_check()
 2026-03-30 13:51:21 +08:00
Liang Jiaqing
7b704b5dbc fix: _parse_openai_sse防御None值迭代(tool_calls/delta可能为null) 2026-03-30 11:19:56 +08:00
Liang Jiaqing
5459ebbb59 fix: output窗口滚动漂移 - 用行偏移代替fraction恢复位置，无变化时跳过刷新 2026-03-29 21:32:40 +08:00
Liang Jiaqing
f0dea09123 fix: fallback tool_use parser handles both with/without space in type key 2026-03-29 21:04:34 +08:00
Liang Jiaqing
58e2f45793 fix: dump tool_use as array format to match fallback parser 2026-03-29 20:54:25 +08:00
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
08ac18be6e fix: code_run encoding compat; wechat truncate long code blocks & limit msg count 2026-03-29 17:43:06 +08:00
Liang Jiaqing
52151853b3 fix: encode str input when text=True is intercepted by header wrapper 2026-03-29 15:15:35 +08:00
Liang Jiaqing
53c492b682 agentmain: auto-switch cn schema for glm/minimax/kimi; tools_schema: trim descriptions; hub: fix scroll position on refresh 2026-03-29 15:08:11 +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
1d94384ee5 feat: add Qt/Streamlit alternative frontends, fix hub output auto-scroll, update README 2026-03-28 20:56:14 +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
Liang Jiaqing
38e2a460e3 refactor: optimize code extraction priority in tool handlers & update autofill SOP 2026-03-27 19:43:46 +08:00
Liang Jiaqing
a1c289dbd1 feat(web_driver): support await in executeCode via AsyncFunction fallback 2026-03-27 18:57:47 +08:00
Liang Jiaqing
55a5eae4f6 perf: replace MutationObserver with setInterval to fix performance issue 2026-03-27 18:41:39 +08:00
Jiaqing Liang
04448dcee9 update userscript guard and scheduler flag 2026-03-27 15:41:42 +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
650c14dc1a update wechat group QR code (group 2, as group 1 is full) 2026-03-26 13:37:41 +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
274bbcb9e4 docs: update WeChat group QR code 2026-03-24 22:55:04 +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
651e0d2bc8 refactor: extract code_run header to external file, add subprocess gbk fallback patch 2026-03-24 09:52:55 +08:00
Liang Jiaqing
5643bfb5f0 code_run自动注入常用import+memory路径; ljqCtrl_sop补充文本输入方法 2026-03-24 00:00:20 +08:00
Liang Jiaqing
515b0cd985 feat: unified media download in wechatapp + proxy support for NativeOAISession 2026-03-23 20:57:39 +08:00
Liang Jiaqing
60f40e3c5e feat(wechat): add send_file via CDN upload; fix _strip_md robustness 
- Add WxBotClient.send_file() with AES-128-ECB encryption and CDN upload
- Extract [FILE:] tags before _clean() to preserve filenames
- Fix _strip_md: support 3+ backticks via backreference, stop stripping underscores
- Remove verbose key_info echo from update_working_checkpoint
 2026-03-23 17:55:20 +08:00
Jiaqing Liang
eb8834b9df feat: enhance text_only mode - add form element annotations, block-level line breaks, and whitespace cleanup 2026-03-23 15:26:05 +08:00
Jiaqing Liang
b4bdaf11da style: remove trailing periods in tool schema descriptions (-31 tokens/round) 2026-03-23 13:56:03 +08:00
Jiaqing Liang
47e9a55feb feat: add file ref expansion syntax for file_patch and file_write 2026-03-23 13:50:11 +08:00
Jiaqing Liang
66dff812fb docs: add personal WeChat bot frontend to Latest News 2026-03-23 12:05:23 +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
fd5150ffad feat: strip markdown formatting in wechat output 2026-03-22 20:45:40 +08:00
Liang Jiaqing
ba6ab901f8 feat: add WeChat bot frontend (wechatapp.py) 2026-03-22 20:20:33 +08:00