fz-mirrors/AstrBot
1
0
Fork 0
mirror of https://github.com/AstrBotDevs/AstrBot synced 2026-07-17 09:50:31 +08:00
Code Issues Packages Projects Releases Wiki Activity
4,788 Commits 171 Branches 254 Tags
b9b3d509863a75daeb728547eeb6616a07bc052d
Commit Graph

76 Commits

Author SHA1 Message Date
LIghtJUNction
eca534f6d4 feat(core): add ToolSessionManager for stateful tool execution 
Introduce session-level state management for tools that need to maintain
state across conversation turns within the same session (UMO).

- Add ToolSessionManager class for central per-(UMO, tool_name) state
- Add ToolSessionState with set_persistent(key) support
- Add is_stateful flag to FunctionTool base class
- Wire session_manager through run_context in all agent runners
- Update ExecuteShellTool to use framework session manager
- Update CLAUDE.md with stateful tool documentation

BREAKING: Tools that were manually managing session state via _sessions
dict should migrate to use the framework's ToolSessionManager for proper
lifecycle management and persistence support.
 2026-03-29 15:40:57 +08:00
LIghtJUNction
dd53727e81 style: apply ruff --unsafe-fixes for common issues 
Fixed 31 issues including:
- Remove print statements (T201)
- Fix star imports (F403)
- Other auto-fixable style issues
 2026-03-24 16:36:46 +08:00
LIghtJUNction
310d2d6998 feat: add integration tests infrastructure and MCP echo server fixture 
- Add tests/integration/ directory with fixtures/
- Create echo_mcp_server.py for MCP testing
- Create test_mcp_integration.py with basic tests
- Fix bug in MCP client: use stdio_transport instead of _streams_context
- Add examples/abp_demo.py demonstrating ABP protocol
- Update openspec with integration tests change
 2026-03-23 23:01:55 +08:00
LIghtJUNction
f60ffdb62a refactor(dashboard): remove unused sha256 utility 
The sha256.ts module is no longer used by any frontend code.
 2026-03-23 20:38:43 +08:00
LIghtJUNction
99c66c2410 feat(cli): add real-time log streaming in non-interactive mode 
- Non-interactive mode now streams logs to stdout with color-coded levels
- Add proper async cleanup when shutting down
- Fix type annotations in coze and deerflow agent runners
 2026-03-23 17:21:05 +08:00
LIghtJUNction
8e0314a559 refactor: reorganize agent runner imports for openai-agents integration 
- Move AgentResponse to its own module in core/agent/response
- Update import paths in all runner files
- Add provider_config parameter to ToolLoopAgentRunner
 2026-03-23 13:29:53 +08:00
LIghtJUNction
19e0952a6f fix: standardize dashboard env vars to ASTRBOT_* prefix only 
- Remove all DASHBOARD_* and ASTRBOT_DASHBOARD_* fallback chains
- server.py now only checks ASTRBOT_HOST, ASTRBOT_PORT, ASTRBOT_SSL_*
- cmd_run.py no longer sets legacy DASHBOARD_* environment variables
- Clean up import paths for agent runners
 2026-03-23 13:18:23 +08:00
LIghtJUNction
ce6e9f9d0b refactor: move openai_agents to _internal/agents 
Move the openai-agents SDK integration from core/agent/runners/openai_agents
to _internal/agents/openai_agents to follow the internal implementation pattern.
 2026-03-23 12:56:09 +08:00
LIghtJUNction
80c46c0639 feat: add openai-agents SDK integration 
Add integration layer for using the openai-agents library with
AstrBot's existing agent infrastructure:

- OpenAIAgentsRunner: A BaseAgentRunner implementation that wraps
  the openai-agents Agent class
- Tool adapter to convert AstrBot FunctionTool to openai-agents format
- Support for tool handlers and FunctionToolManager integration
 2026-03-23 12:53:00 +08:00
LIghtJUNction
f55016bcb2 refactor: type annotations and i18n improvements 
- Add i18n support to cmd_conf.py (config validators)
- Fix BaseFunctionToolExecutor to be an ABC
- Add explicit type annotations for dict payloads
- Various type annotation improvements
 2026-03-23 12:49:13 +08:00
LIghtJUNction
a05f9eba7d feat: add TUI platform adapter and chat route 
- Add TUI platform adapter (tui_adapter, tui_event, tui_queue_mgr)
- Add TUI chat route for dashboard
- Add cmd_run_tui command
- Fix shared_preferences TypeVar syntax
- Various platform adapter and provider updates
 2026-03-23 05:57:55 +08:00
LIghtJUNction
5ba7ecec9e Merge branch 'master' of https://github.com/AstrBotDevs/AstrBot into dev 2026-03-22 20:16:52 +08:00
Frank
1879e5961d fix: keep all CallToolResult content items (#6149) 
Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com>
 2026-03-22 17:21:22 +08:00
LIghtJUNction
f9243a73d5 feat: reduce default max_agent_step to 3 and refactor shell execution 
- Lower default max_agent_step from 30 to 3 across all agent runners
  (coze, dashscope, deerflow, dify) for faster responses
- Refactor ExecuteShellTool to use plumbum with session-based isolation,
  maintaining shell state per session (cwd, env vars, etc.)
- Remove unused API-specific environment variables from cmd_run
- Fix data access bug in shipyard_neo._maybe_model_dump
- Add plumbum>=1.10.0 dependency
 2026-03-21 23:47:43 +08:00
LIghtJUNction
26c5e67efe Refactor: change relative imports to absolute imports in tool_loop_agent_runner.py 2026-03-21 14:13:43 +08:00
LIghtJUNction
cefeaf8d9f Fix: add task tracking to BaseAgentRunner and ToolLoopAgentRunner, replace asdict with custom serialization in Response 2026-03-21 13:55:05 +08:00
LIghtJUNction
61e525afd4 Merge branch 'master' into dev 2026-03-21 12:25:04 +08:00
LIghtJUNction
b2a04ffed1 Fix syntax error in tool_loop_agent_runner.py 2026-03-21 04:21:21 +08:00
LIghtJUNction
3405c72b5e Modify context configuration parameters 
Updated max_context_tokens default value and adjusted enforce_max_turns logic.
 2026-03-21 04:17:59 +08:00
LIghtJUNction
4ee93c7f83 Limit max_step to a maximum of 3 
基本都是设置为30，30太夸张了，这是日志里面截出来的：
system,user,assistant,user,assistant,user,assistant,tool,assistant,user,assistant,user,assistant,user,assistant,tool,assistant,user,assistant,user,assistant,user,assistant,user,assistant,user,assistant,user,assistant,user,assistant,tool,assistant,user,assistant,user,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,user,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,user,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,user,assistant,tool,assistant,user,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,user,assistant,user,assistant,user,assistant,user,assistant,user,assistant,tool,assistant,user,assistant,tool,assistant,tool,assistant,user,assistant,tool,assistant,tool,assistant,tool,assistant,user,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,user,assistant,user,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,user,assistant,tool,assistant,tool,assistant,user,assistant,tool,assistant,user,assistant,tool,assistant,tool,assistant,tool,assistant,user,assistant,tool,assistant,user,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,user,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,user,assistant,tool,assistant,user,assistant,tool,assistant,user,assistant,user,assistant,user,assistant,user,assistant,tool,assistant,user,assistant,tool,assistant,user,assistant,tool,assistant,user,assistant,user,assistant,user,assistant,user,assistant,user,assistant,tool,assistant,user,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,tool,assistant,user,assistant,tool,tool,assistant,tool,assistant,user,assistant,tool,assistant,user,assistant,user,assistant,user,assistant,user,assistant,user,assistant,user
 2026-03-21 04:12:49 +08:00
Yufeng He
7beab796bb fix: skills-like re-query missing extra_user_content_parts causes image_caption not to be injected (#6710) 
当使用 skills-like tool mode 时，_resolve_tool_exec 的 re-query 调用没有
传递 extra_user_content_parts，导致图片描述等附加内容丢失。

fixes #6702

Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com>
 2026-03-21 01:11:34 +08:00
qingyun
b2797b6f16 fix(agent): reject follow-up messages after stop request (#6704) 
* fix: reject follow-up messages after stop requested (#6626)

Once a user sends /stop, follow-up messages should no longer be
accepted for that runner. Previously, there was a race window where
messages sent after stop could still be queued as follow-ups.

This fix gates the follow_up() method to check both done() and
_stop_requested before accepting a new follow-up message.

Acceptance criteria met:
- After /stop, later follow-up messages return None (rejected)
- Post-stop follow-ups are not added to _pending_follow_ups
- No post-stop text is injected into tool results
- Graceful-stop behavior otherwise unchanged
- Follow-ups submitted before stop retain current behavior

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* test: add regression tests for issue #6626 follow-up rejection

Add focused tests that verify the complete tool-result injection path
for follow-up messages after stop is requested:

- test_follow_up_rejected_and_runner_stops_without_execution: Verifies
  that when stop is requested before any execution, follow-ups are
  rejected and the runner stops gracefully without executing tools.

- test_follow_up_merged_into_tool_result_before_stop: Verifies that
  follow-ups queued before stop are properly merged into tool results
  via _merge_follow_up_notice().

- test_follow_up_after_stop_not_merged_into_tool_result: Regression
  test that simulates the race condition from issue #6626. Verifies
  that only pre-stop follow-ups are merged into tool results, and
  post-stop follow-ups are rejected at the admission point.

These tests validate the fix in ToolLoopAgentRunner.follow_up() that
checks both self.done() and self._stop_requested before accepting
new follow-up messages.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix(agent): update stop request check in ToolLoopAgentRunner

---------

Co-authored-by: ccsang <ccsang@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Soulter <905617992@qq.com>
 2026-03-21 01:06:37 +08:00
SJ
b816f26fe6 fix(core): interrupt subagent tool waits on stop (#5850) 
* fix(core): interrupt subagent tool waits on stop

* test: relax subagent handoff timeout

* test: cover stop-aware tool interruption

* refactor: unify runner stop state

* refactor: simplify tool executor interruption

* fix: preserve tool interruption propagation

* refactor: tighten interruption helpers

---------

Co-authored-by: idiotsj <idiotsj@users.noreply.github.com>
 2026-03-21 00:59:52 +08:00
LIghtJUNction
92bae1fdae docs: replace prints with logger in upload_doc_images_to_r2.py 2026-03-19 23:30:25 +08:00
LIghtJUNction
a3371ad6c8 core: refactor modules & fix typing/runtime issues 2026-03-19 23:06:27 +08:00
LIghtJUNction
14ec513b0d fix: clean lint suppressions and async route errors 2026-03-18 18:06:42 +08:00
LIghtJUNction
4bf2f0cb28 fix(dashboard): handle missing static assets gracefully and fix async/ruff issues 
- Dashboard: Catch missing index.html error, log warning, and disable WebUI instead of crashing.
- Dashboard: Use anyio.Path for async file existence checks in SSL config.
- CLI/Backup: Replace blocking file operations with anyio async operations.
- Core: Replace blocking file operations with anyio in Coze/Dify clients and TTS simulation.
- Provider: Rename 'timeout' param to 'init_timeout'/'request_timeout' to fix ASYNC109 warnings.
- Ruff: Fix various ASYNC230/ASYNC240 errors across multiple files.
 2026-03-18 16:46:22 +08:00
LIghtJUNction
f3d6f762c3 refactor: rename skills_like to lazy_load and add skill schema support 2026-03-17 20:46:07 +08:00
ccsang
8e6c835b85 refactor(agent): extract image-handling logic into helper function 
Address Sourcery AI review feedback: the image-handling logic was
duplicated for ImageContent and EmbeddedResource cases.

Changes:
- Extract _handle_image_content() helper function
- Consolidate image caching, result appending, and yielding logic
- Reduce code duplication and improve maintainability
 2026-03-16 00:17:33 +00:00
ccsang
fb2a2a63f2 fix(agent): process all content items in CallToolResult, not just the first 
Fixes #6140

When a tool returns CallToolResult with multiple content items (e.g.,
both TextContent and ImageContent), the agent was only processing
content[0], ignoring the rest.

Changes:
- Replace direct content[0] access with enumerate(res.content) loop
- Process all content items: TextContent, ImageContent, EmbeddedResource
- Use content_index for image caching to distinguish multiple images

This fixes the issue where tools like Bilibili plugin return both
text descriptions and screenshots, but LLM only received one of them.
 2026-03-16 00:17:33 +00:00
whatevertogo
3fd6c4c8a6 fix: 修复 asyncio 事件循环相关问题 (#5774) 
* fix: 修复 asyncio 事件循环相关的问题

1. components.py: 修复异常处理结构错误
   - 将 except Exception 移到正确的内部 try 块
   - 确保 _download_file() 异常能被正确捕获和记录

2. session_lock.py: 修复跨事件循环 Lock 绑定问题
   - 添加 _access_lock_loop_id 追踪事件循环
   - 当事件循环变化时重新创建 Lock

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: 根据代码审查反馈修复问题

1. components.py: 移除 asyncio.set_event_loop() 调用
   - 创建临时 event loop 时不再设置为全局
   - 避免干扰其他 asyncio 使用

2. session_lock.py: 简化延迟初始化逻辑
   - 移除 loop-ID 追踪和 _get_lock 方法
   - 使用 setdefault 简化 session lock 创建
   - 保留延迟初始化行为

3. wecomai_queue_mgr.py: 使用 time.monotonic() 替代 loop.time()
   - 同步方法不再依赖活动的 event loop
   - 避免在非异步上下文中抛出 RuntimeError

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: 优化 asyncio 事件循环管理，使用安全的方式创建和关闭事件循环

* fix: 根据代码审查反馈改进异常处理和事件循环使用

- main.py: 显式处理 check_dashboard_files() 返回 None 的情况
- components.py: 使用 logger.exception 保留异常堆栈信息
- star_manager.py: 添加 Future 异常回调处理 __del__ 执行异常
- bay_manager.py: 缓存事件循环引用避免重复调用

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: 简化 SessionLockManager 使用 defaultdict 和 setdefault

- 使用 defaultdict(asyncio.Lock) 简化锁的懒创建
- 使用 setdefault 简化 _get_loop_state 逻辑
- 减少 get + if 分支，提升可读性

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: 降低 webui_dir 检查失败时的日志级别为 warning

改为警告而非退出，允许程序在无 WebUI 的情况下继续运行

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: 重构事件循环锁管理，简化锁状态管理逻辑

* 新增对 SessionLockManager 的多事件循环隔离测试

* fix: 修复测试中的变量声明和断言，确保事件循环管理器的正确性

* fix: 修复插件删除时异常处理逻辑，确保正确记录错误信息

* fix: 新增针对多个事件循环的 OneBot 实例的测试，确保锁对象在不同事件循环间不共享

---------

Co-authored-by: whatevertogo <whatevertogo@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-09 01:00:13 +09:00
エイカク
451ad685ae feat: 集成 DeerFlow Agent Runner 并优化流式处理 (#5581) 
* feat: integrate DeerFlow agent runner and improve stream handling

* refactor: split DeerFlow stream flow and close stale client on reset

* fix: enforce max_step and correct timeout type check

* fix: harden DeerFlow config parsing and session lifecycle

* fix: preserve third-party runner error semantics and harden image parsing

* perf: bound DeerFlow values history and seen-id cache

* refactor: improve deerflow stream semantics and client lifecycle

* fix: harden third-party runner error semantics and fallback aggregation

* refactor: reduce deerflow image log noise and lazy-init api session

* perf: avoid unnecessary iterable copies in deerflow stream utils

* refactor: centralize runner error key and clarify deerflow client lifecycle

* refactor: simplify third-party runner output flow

* fix: defer streaming runner cleanup and unify error mapping

* fix: handle id-less values messages and redact stream payload logs

* fix: improve deerflow error signaling and third-party runner flow

* fix: support deerflow proxy and refine runner lifecycle

* fix: tighten deerflow image validation and runner lifecycle

* feat: support deerflow image output components

* fix: harden runner stream cleanup and refactor deerflow config

* fix: preserve deerflow done hook and simplify runner lifecycle

* refactor: simplify third-party runner aggregation and lifecycle closing

* fix: preserve first deerflow values payload and simplify runner flow

* refactor: unify runner final resolution and harden deerflow close state

* refactor: share int coercion and make deerflow close best effort

* refactor: extract deerflow mappers and streamline third-party lifecycle

* refactor: simplify third-party flow and harden sse flush parsing

* fix: make deerflow runner close path best effort

* refactor: simplify third-party orchestration and centralize deerflow keys

* refactor: simplify third-party chunk flow and deerflow finalization

* fix: harden deerflow stream parsing and simplify runner lifecycle

* refactor: remove redundant deerflow values text assignment

* fix: improve deerflow timeout diagnostics and image input feedback

* refactor: flatten third-party runner lifecycle and aggregation

* chore: use deerflow official remote svg icon

* chore: remove unused deerflow local logo asset
 2026-03-01 12:31:38 +09:00
エイカク
7bf44bd8d2 feat: support persona custom error reply message with fallback (#5547) 
* feat: support persona custom error reply message with fallback

* refactor: centralize persona custom error message helpers
 2026-02-28 13:34:12 +09:00
Soulter
5219ba5c4e feat: implement follow-up message handling in ToolLoopAgentRunner (#5484) 
* feat: implement follow-up message handling in ToolLoopAgentRunner

* fix: correct import path for follow-up module in InternalAgentSubStage
 2026-02-26 21:38:47 +08:00
Soulter
e357d9de74 feat: add stop functionality for active agent sessions and improve handling of stop requests (#5380) 
* feat: add stop functionality for active agent sessions and improve handling of stop requests

* feat: update stop button icon and tooltip in ChatInput component

* fix: correct indentation in tool call handling within ChatRoute class
 2026-02-23 20:21:30 +08:00
時壹
3ca8dd204f fix: prevent duplicate error message when all LLM providers fail (#5183) 2026-02-18 16:29:35 +08:00
Soulter
754144ad99 feat: add fallback chat model chain in tool loop runner (#5109) 
* feat: implement fallback provider support for chat models and update configuration

* feat: enhance provider selection display with count and chips for selected providers

* feat: update fallback chat providers to use provider settings and add warning for non-list fallback models
 2026-02-15 11:51:34 +08:00
Soulter
d2de0ea5ad feat: QQ 官方机器人平台支持主动推送消息、私聊场景下支持接收文件 (#5066) 
* feat: QQ 官方机器人平台支持主动推送消息、私聊场景下支持接收文件

* feat: enhance QQOfficialWebhook to remember session scenes for group, channel, and friend messages
 2026-02-12 19:07:53 +08:00
Soulter
9d93bda3fe feat: temporary file handling and introduce TempDirCleaner (#5026) 
* feat: temporary file handling and introduce TempDirCleaner

- Updated various modules to use `get_astrbot_temp_path()` instead of `get_astrbot_data_path()` for temporary file storage.
- Renamed temporary files for better identification and organization.
- Introduced `TempDirCleaner` to manage the size of the temporary directory, ensuring it does not exceed a specified limit by deleting the oldest files.
- Added configuration option for maximum temporary directory size in the dashboard.
- Implemented tests for `TempDirCleaner` to verify cleanup functionality and size management.

* ruff
 2026-02-12 01:04:48 +08:00
Dt8333
7dd95d8a59 chore: auto ann fix by ruff (#4903) 
* chore: auto fix by ruff

* refactor: 统一修正返回类型注解为 None/bool 以匹配实现

* refactor: 将 _get_next_page 改为异步并移除多余的请求错误抛出

* refactor: 将 get_client 的返回类型改为 object

* style: 为 LarkMessageEvent 的相关方法添加返回类型注解 None

---------

Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com>
 2026-02-09 00:22:24 +08:00
鸦羽
eca3ede7b0 fix: dedupe preset messages (#4961) 2026-02-08 22:18:13 +08:00
Gao Jinzhe
952023db30 feat: 允许 LLM 预览工具返回的图片并自主决定是否发送 (#4895) 
* feat: 允许 LLM 预览工具返回的图片并自主决定是否发送

* 复用 send_message_to_user 替代独立的图片发送工具

* feat: implement _HandleFunctionToolsResult class for improved tool response handling

* docs: add path handling guidelines to AGENTS.md

---------

Co-authored-by: Soulter <905617992@qq.com>
 2026-02-08 13:16:16 +08:00
Soulter
4658998b85 fix: messages[x] assistant content must contain at least one part (#4928) 
* fix: messages[x] assistant content must contain at least one part

fixes: #4876

* ruff format
 2026-02-07 00:33:07 +08:00
Soulter
6736fb85c2 fix: conversation token usage calculate wrongly and fix tool call infinitely (#4869) 2026-02-04 23:18:32 +08:00
Soulter
4c8c87d3fd feat: enhance cron job management and update UI terminology 2026-02-01 15:49:14 +08:00
Soulter
b2c6471ab0 fix: skill like tool (#4775) 2026-01-31 22:11:42 +08:00
vmoranv
f92f0a3e5d feat(core): supports anthropic-skills-like tool call mode (#4681) 
* feat(core): change llmtool to claude skills like func call

* feat: refactor tool execution logic in ToolLoopAgentRunner for improved clarity and efficiency

* feat(core): 添加工具调用模式配置选项

新增 tool_schema_mode 配置项，支持两种工具调用模式：
- skills_like：先发送工具名称和描述，再查询参数（两阶段）
- full：一次性发送完整工具模式

更新了默认配置、配置元数据定义以及代理子阶段处理逻辑，
添加了完整的工具调用提示语句，并在仪表板中提供了国际化支持。

* feat: 优化工具集获取逻辑，添加轻量和参数工具集返回方法

* refactor(runner): 重构工具模式处理逻辑到ToolLoopAgentRunner

- 将工具集激活逻辑提取到新的_build_active_tool_set方法中
- 实现工具模式配置功能，支持full和light模式的动态切换
- 移除InternalAgentSubStage中的工具模式应用逻辑，统一在runner中处理
- 添加_tool_schema_full_set和_tool_schema_param_set实例变量来管理工具集状态
- 修改工具查询逻辑以使用新的工具集管理方式

* fix: update default tool_schema_mode to 'full' in InternalAgentSubStage

* refactor: rename TOOL_CALL_PROMPT_FULL to TOOL_CALL_PROMPT_SKILLS_LIKE_MODE and update prompt logic

---------

Co-authored-by: Soulter <905617992@qq.com>
 2026-01-28 22:49:34 +08:00
Soulter
f797f132cf perf: refine tool call related prompts 2026-01-15 17:22:50 +08:00
letr
86e9b41dde fix(core): correct duplicate word in agent logger warning (#4390) 
- Fix duplicate '没有' in logger warning message
- Improve punctuation and readability of tool response comments
 2026-01-11 15:00:35 +08:00
Soulter
241f1c26d3 feat: context compress (#4322) 
* feat: context compressor

Co-authored-by: kawayiYokami <289104862@qq.com>

* Add comprehensive tests for ContextManager and ContextTruncator

- Implemented a full test suite for ContextManager covering initialization, message processing, token-based compression, and error handling.
- Added tests for ContextTruncator focusing on message fixing, truncation by turns, dropping oldest turns, and halving.
- Ensured that both test suites validate edge cases and maintain expected behavior with various message types, including system and tool messages.

* feat: add MockProvider for LLM compression tests

* chore: remove lock

* ruff fix

* fix

* perf

* feat: enhance context compression with token tracking and logging

* feat: update logging for context compression trigger

* feat: implement context compression logic with dynamic threshold and token tracking

* fix: reorder import statements for consistency

* feat: add token_usage tracking to conversations and update related processing logic

---------

Co-authored-by: kawayiYokami <289104862@qq.com>
 2026-01-05 17:26:10 +08:00