jxxghp
af35101774
fix: default to text replies for voice input
2026-04-29 18:54:58 +08:00
jxxghp
9ed5018cc2
refactor: clarify attachment data url handling
2026-04-29 18:51:39 +08:00
jxxghp
7299733960
调整语音文件大小限制，超出 10MB 时禁止识别
2026-04-29 18:41:54 +08:00
jxxghp
bd5c3d848c
修复 _resolve_provider_name 方法递归调用问题，改为静态方法并标准化 provider 名称解析逻辑
2026-04-29 18:41:24 +08:00
jxxghp
38c48fa4ce
优化 OpenAIVoiceProvider 逻辑，简化凭证与 provider 解析方法并调整最大转录文件大小限制
2026-04-29 18:32:12 +08:00
jxxghp
b7749c44fd
重构语音能力配置与逻辑，统一音频输入输出开关并优化语音回复判断
2026-04-29 18:15:34 +08:00
jxxghp
e4a7333b79
调整 LLM_TEMPERATURE 配置参数默认值为 0.3
2026-04-29 16:54:14 +08:00
jxxghp
4b27b7bc42
重构 UgreenCrypto 模块路径至 app.modules.ugreen 并更新相关引用
2026-04-29 16:29:17 +08:00
jxxghp
c91e87115a
调整 System Core Prompt.txt，将核心能力说明移至更显著位置并优化结构
2026-04-29 16:25:16 +08:00
jxxghp
4a3cc5ee18
新增多个人设说明文档并完善测试用例
2026-04-29 16:20:44 +08:00
jxxghp
54d6c2ad4a
更新 __init__.py
2026-04-29 15:27:37 +08:00
jxxghp
090dcacd30
更新 README.md
2026-04-29 14:38:35 +08:00
jxxghp
344280cd61
Refactor agent persona runtime layering
2026-04-29 14:12:47 +08:00
jxxghp
2c7fb5786c
更新 _plugin_tool_utils.py
2026-04-29 09:16:02 +08:00
jxxghp
6b9790026c
refine plugin agent tool responsibilities
2026-04-29 08:50:48 +08:00
jxxghp
6c70531967
Refactor _query_plugin_data to static async method
2026-04-29 08:31:38 +08:00
jxxghp
bcc321eb70
add plugin agent management tools
2026-04-29 08:29:04 +08:00
MseeP.ai
2ff1cd1045
Add MseeP.ai badge to README.md
2026-04-29 08:02:47 +08:00
jxxghp
7fc496cf5b
更新 __init__.py
2026-04-29 07:31:52 +08:00
jxxghp
8789f35228
Improve non-verbose agent tool summaries
2026-04-29 07:07:33 +08:00
jxxghp
d4dec90e2f
更新 version.py
2026-04-28 20:49:05 +08:00
jxxghp
5c1487a9a6
Optimize agent tool async blocking paths
2026-04-28 20:36:49 +08:00
jxxghp
c5b716c231
feat: introduce unified agent runtime config and system task prompt framework
...
- Add structured runtime config files (AGENT_PROFILE.md, AGENT_WORKFLOW.md, AGENT_HOOKS.md, USER_PREFERENCES.md, SYSTEM_TASKS.md, CURRENT_PERSONA.md) for persona, workflow, hooks, and system tasks
- Implement agent_runtime_manager to load, validate, and render runtime config and system task prompts
- Refactor agent initialization to use runtime-managed directories for skills, jobs, memory, and activity logs
- Add AgentHooksMiddleware for structured pre/in/post hooks injection
- Replace hardcoded system task prompts with template-driven rendering from SYSTEM_TASKS.md
- Update tests to cover runtime config loading, migration, and system task prompt rendering
- Update .gitignore to exclude config/agent/
2026-04-28 13:04:28 +08:00
jxxghp
483fe55372
fix: correct Plex notification image lookup
...
Closes #5700
2026-04-28 09:19:18 +08:00
jxxghp
5d588ee127
fix: correct traditional Chinese subtitle rename detection
...
Fixes #5703
2026-04-28 09:00:14 +08:00
jxxghp
afcd895f52
fix: backfill transfer download history matching
...
Fixes #5702
2026-04-28 08:55:40 +08:00
jxxghp
1ded58adbb
fix: adapt audiences user data parser
2026-04-27 12:56:45 +08:00
jxxghp
019a077407
Apply suggestions from code review
...
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
2026-04-27 11:35:44 +08:00
PKC278
0f190057d3
fix #5528
2026-04-27 11:35:44 +08:00
jxxghp
840c8f7298
更新 APP_VERSION 至 v2.10.6
2026-04-27 11:32:39 +08:00
jxxghp
6a6bcf59a0
增强 execute_command 工具：支持输出截断、并发限制与进程组清理，新增单元测试
2026-04-27 10:05:25 +08:00
jxxghp
323844b26d
revert execute_command streaming changes
...
Restore the previous subprocess handling for execute_command and drop the new command streaming test so agent startup is unblocked.
2026-04-27 08:12:37 +08:00
jxxghp
140d224a9a
fix agent stream blocking during command execution
...
Offload synchronous message edits from the event loop and stream subprocess output so long-running commands stay responsive.
2026-04-27 07:57:32 +08:00
jxxghp
7bc032d17c
Revert Telegram duplicate edit fix
2026-04-27 07:36:13 +08:00
jxxghp
2df476dbff
Fix Telegram duplicate message edits
2026-04-27 07:17:58 +08:00
jxxghp
bae086d8b8
更新 __init__.py
2026-04-27 06:57:18 +08:00
jxxghp
221eb21694
refine internal middleware llm usage for streaming agents
...
Use a non-streaming model for middleware-only calls so internal outputs do not leak into user streams and model-based middleware stays consistent.
2026-04-27 06:55:41 +08:00
jxxghp
4208c79d72
refine tool提示语为更简洁风格，补充last_buffer_char属性及非VERBOSE模式流式输出换行逻辑，新增工具流式分隔符单元测试
2026-04-26 11:15:11 +08:00
jxxghp
90245a13e1
refine non-verbose prompt wording
2026-04-26 08:54:07 +08:00
jxxghp
b5979b9b09
refine agent subscription defaults and silent tool prompts
2026-04-26 08:51:56 +08:00
jxxghp
0277288a41
feat: add agent session usage status reporting
...
Track per-session model and token usage so users can inspect context pressure and cumulative usage with /session_status.
2026-04-26 08:19:05 +08:00
jxxghp
79bfeaf2af
移除工具调用前的流重置，保留模型思考文本可见
2026-04-25 23:12:34 +08:00
jxxghp
4fe41ba5e9
更新 base.py
2026-04-25 22:16:15 +08:00
jxxghp
14d6e2febc
Refine agent prompts for concise professional replies
2026-04-25 22:04:35 +08:00
jxxghp
97c7e71207
更新 Agent Prompt.txt
2026-04-25 21:51:47 +08:00
jxxghp
8f29a218ea
chore: bump version to v2.10.5
2026-04-25 12:55:33 +08:00
jxxghp
4fd5aa3eb6
fix: improve DeepSeek reasoning_content payload handling and update langchain dependencies
2026-04-25 12:46:21 +08:00
jxxghp
bfc27d151c
更新 ask_user_choice.py
2026-04-25 11:36:36 +08:00
jxxghp
f2b56b8f40
更新 ask_user_choice.py
2026-04-25 11:35:32 +08:00
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
