Shen Hao
222a144858
config: update mykey_template.py with new configuration examples
2026-04-15 03:54:42 +08:00
Liang Jiaqing
acb0f93d5f
refactor: reorder mykey_template, add name field to native configs
2026-04-13 22:48:51 +08:00
Liang Jiaqing
8d537e954b
fix: simphtml visibility/dialog/SVG improvements & minor agent fixes
...
- simphtml: rewrite visibility inheritance (area-based maxC), add isVisible to childrenInfo,
fix className SVG compat (getAttribute), expand isDialog detection, hoist deep fixed dialogs,
clear SVG attrs, fix warning message concat
- ga: return error messages instead of None for code_run/web_execute_js failures
- stapp: disable unsafe_allow_html
- code_run_header: add excepthook hint for ImportError/AttributeError
- mykey_template: remove stale prompt_cache comment
2026-04-03 09:40:09 +08:00
Liang Jiaqing
88f32b208b
feat: support NativeToolClient and optimize tool use format for native API
2026-04-01 23:09:48 +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
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
122b6c431c
improve mykey_template: add apibase rules, all session types with full cfg comments
2026-03-21 12:23:58 +08:00
YangChen-pro
70ed09ad2b
Support configurable OpenAI reasoning effort
2026-03-18 22:54:58 +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
61d07a16a6
update: minor fixes to agentmain, mykey_template, sidercall
2026-03-07 22:34:23 +08:00
remy
df3b347653
Add retry/backoff and richer error logs for relay calls
2026-03-02 00:38:27 +10:00
remy
998382aebe
Add responses api_mode support for OpenAI relay
2026-03-02 00:17:25 +10:00
Liang Jiaqing
08d6cedc7d
feat: 优化LLM显示、修复API路径、重构自主操作SOP、添加sche_tasks到gitignore
...
- agentmain.py: LLM列表显示增加backend类型
- sidercall.py: 统一API endpoint路径为/v1/chat/completions
- autonomous_operation_sop.md: 重构任务选择逻辑和报告目录规则
- .gitignore: 添加sche_tasks/目录排除
- 移除git追踪的sche_tasks任务报告文件
2026-02-20 11:10:04 +08:00
Liang Jiaqing
8d3582e3b7
feat: add ACK mechanism for WS execute_js + timeout diagnostics
...
- TMWebDriver: add self.acks dict, HTTP implicit ACK on longpoll dequeue, WS explicit ACK handler, enhanced timeout diagnostics (4 cases)
- Fix: data.get('type') in 'result' -> == 'result'
- JS userscript: send ACK on script receive
- tgapp: fix proxy URL prefix
- mykey_template: add tg/proxy fields
2026-02-13 15:30:49 +08:00
Liang Jiaqing
87e522ff8e
feat: add ClaudeSession for native Claude Messages API support
2026-02-12 18:07:45 +08:00
Liang Jiaqing
69153f7a42
multi oai config support, timeout fix, execute_js_rich optimization
2026-02-12 16:56:11 +08:00
Liang Jiaqing
d6c9bf8d20
Update global memory: remove obsolete git status and mail tool references
2026-02-01 09:53:04 +08:00
Liang Jiaqing
ead42063f4
Auto-commit: sync local changes
2026-02-01 09:45:14 +08:00
