69 Commits

Author SHA1 Message Date
LIghtJUNction 4b7d42c2a3 chore: ruff format 2026-03-17 16:53:45 +08:00
LIghtJUNction f6321be8c8 sync 2026-03-17 16:51:45 +08:00
Rhonin Wang d5b98b353c fix: parse multiline frontmatter description in SKILL.md (#6460)
* fix(skills): support multiline frontmatter descriptions

* fix(skills): 修复多行 frontmatter 描述解析

* style(skills): clean up frontmatter parser follow-ups

---------

Co-authored-by: RhoninSeiei <RhoninSeiei@users.noreply.github.com>
2026-03-17 13:53:16 +08:00
LIghtJUNction a05bfed15d Merge pull request #6434 from a61995987/fix-修正shell工具未正确应用工具调用超时的问题
Fix 修正shell工具未正确应用工具调用超时的问题
2026-03-16 20:51:03 +08:00
LIghtJUNction a027fb310c Update astrbot/core/computer/tools/shell.py
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-03-16 20:34:17 +08:00
Chen 4b0d9ae979 Merge branch 'fix-修正shell工具未正确应用工具调用超时的问题' of https://github.com/a61995987/AstrBot into fix-修正shell工具未正确应用工具调用超时的问题 2026-03-16 18:11:12 +08:00
Chen a1a3db2218 fix-修正shell工具未正确应用工具调用超时的问题 2026-03-16 18:10:23 +08:00
Chen 3e278dbd9e Merge branch 'AstrBotDevs:master' into fix-修正shell工具未正确应用工具调用超时的问题 2026-03-16 18:02:15 +08:00
LIghtJUNction 3f24f82486 Merge branch 'master' into dev 2026-03-16 17:02:15 +08:00
Soulter 420d82df11 chore: ruff format 2026-03-15 22:43:29 +08:00
Yufeng He d87cf897da Fix TypeError when API returns null choices (#6313)
* Fix CreateSkillPayloadTool array schema missing items field

The payload parameter's anyOf array variant lacked an items field,
causing Gemini API to reject the tool declaration with 400 Bad Request:
'parameters.properties[payload].any_of[1].items: missing field.'

Add items: {type: object} to the array variant to satisfy the Gemini
API requirement for array type schemas.

Fixes #6279

* Fix TypeError when OpenAI-compatible API returns null choices

Some providers (e.g. OpenRouter) may return a completion where
choices is None rather than an empty list — for instance on rate
limiting, content filtering, or transient errors. The existing code
used len(completion.choices) which throws TypeError on None.

Replace all len(...choices) == 0 checks with 'not ... .choices' which
handles both None and empty list. Affects _query_stream, _parse_openai_completion,
and _extract_reasoning_content.

Fixes #6252
2026-03-15 22:28:26 +08:00
advent259141 3a8bfa0873 style: ruff format on merge-touched files 2026-03-13 09:20:08 +08:00
advent259141 c07fba7add merge: resolve conflicts with origin/master
- .gitignore: keep both .serena and .worktrees/ entries
- astr_main_agent_resources.py: keep deletion (refactored to tools/)
- send_message.py: port video message type support from master
2026-03-13 09:17:31 +08:00
zenfun 855483c8c2 style: fix ruff I001/F401 violations in changed files 2026-03-13 01:18:39 +08:00
zenfun 048c511b18 fix: align browser property with base class and remove dead env writes
- shipyard_neo: browser property now returns None when not initialized
  instead of raising RuntimeError, matching ComputerBooter base contract
- computer_tool_provider: remove dead os.environ writes for shipyard
  (SHIPYARD_ENDPOINT / SHIPYARD_ACCESS_TOKEN are never read anywhere)
  and remove unused os import
2026-03-13 01:14:23 +08:00
zenfun dfc0c34d95 fix: address review issues in tool injection refactor
- Rewrite TestApplySandboxToolsRefactored to test ComputerToolProvider
  directly (_apply_sandbox_tools was removed; old tests permanently skipped)
- Add TestExecutorCapabilityGuard with 5 strict tests for browser
  capability rejection at executor level
- Fix typo: "on hehalf you" -> "on behalf of you" in subagent result
- Remove extra blank lines (ruff E303) after _apply_sandbox_tools comment
- Remove dead _build_sync_and_scan_command (no callers after refactor)
2026-03-13 01:11:50 +08:00
Chen b1a119edb4 ruff 2026-03-12 03:44:36 +08:00
Chen 3dc4bb8e34 将shell调用时的timeout转为int 获取系统配置时正确传递umo 2026-03-12 03:42:33 +08:00
Chen f5e7ca12f7 feat: 增加 shell 工具自定义超时配置 2026-03-12 03:26:18 +08:00
zenfun a5a1ba72fd refactor: add get_sandbox_capabilities API and structured logging to computer_client 2026-03-12 02:58:15 +08:00
zenfun e1d76117b4 refactor: standardize booter structured logging format 2026-03-12 02:57:04 +08:00
zenfun ad3911a21f refactor: add debug logging to sandbox tool resolution 2026-03-12 02:56:59 +08:00
zenfun e85eef05b8 fix: stabilize tool injection for LLM prefix cache hits
Two changes to make the tool schema sent to the LLM deterministic:
1. ToolSet.normalize() — sort tools by name before serialization.
   Called at the end of build_main_agent() after all injection passes.
   Eliminates ordering drift from plugin load order, MCP reconnection,
   and persona tool list differences.
2. Always inject full sandbox tool set — ComputerToolProvider now
   returns get_default_sandbox_tools() unconditionally, regardless of
   sandbox boot state. Browser tools are always in the schema even if
   the sandbox profile lacks browser capability. The executor rejects
   calls to unavailable browser tools with a descriptive error instead
   of silently omitting them from the schema.
   This eliminates the pre-boot/post-boot tool set jump that caused
   prefix cache misses on the second request of a conversation.
2026-03-12 02:43:19 +08:00
zenfun f16edd4fff refactor: delegate tool injection to booter self-description API
- Add get_default_tools/get_tools/get_system_prompt_parts to ComputerBooter base
- Each booter subclass (ShipyardNeo, Shipyard, Boxlite) declares its own tools
- ComputerToolProvider now delegates to booter API via computer_client helpers
- Add unified query API: get_sandbox_tools, get_default_sandbox_tools, etc.
- Extract Neo prompts to dedicated computer/prompts.py module
- Add booter type constants (booters/constants.py)
- Fix subagent tool path to pass sandbox_cfg and session_id
- Fix Sourcery issues: shell injection in send_message, typo in prompts,
  internal tools bypass inactivated_llm_tools check
2026-03-12 02:43:19 +08:00
Soulter 304094630c perf: optimize booter selection for edge cases and message sending tool (#6064)
* feat: add video message support and enhance message type descriptions in SendMessageToUserTool

* feat: add error handling for disabled sandbox runtime in get_booter function
2026-03-12 00:29:52 +08:00
エイカク 589cce18af fix: improve Windows local skill file reading (#6028)
* chore: ignore local worktrees

* fix: improve Windows local skill file reading

* fix: address Windows path and decoding review feedback

* fix: simplify shell decoding follow-up

* fix: harden sandbox skill prompt metadata

* fix: preserve safe sandbox skill summaries

* fix: relax sandbox summary sanitization

* fix: tighten path sanitization for skill prompts

* fix: harden sandbox skill display metadata

* fix: preserve Unicode skill paths in prompts

* fix: quote Windows skill prompt paths

* fix: simplify local shell output decoding

* fix: localize Windows prompt path handling

* fix: normalize Windows-style skill paths in prompts

* fix: align prompt and shell decoding behavior
2026-03-11 23:58:28 +09:00
Gao Jinzhe 42b8293f99 Merge branch 'AstrBotDevs:master' into agent-fix-clean 2026-03-11 09:48:36 +08:00
advent259141 ff4412a627 refactor: Centralize and decouple computer-use tool injection logic into a new ComputerToolProvider and associated tool modules. 2026-03-10 22:00:23 +08:00
advent259141 bf430e659a feat: Introduce cron job management and refactor tool provisioning with dedicated providers for computer-use runtimes. 2026-03-10 21:05:09 +08:00
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
Soulter df421e5554 fix: test 2026-03-03 16:04:08 +08:00
miaoxutao123 92ee534a2c feat: add OS information to tool descriptions and implement unit tests (#5677)
* feat: add OS information to tool descriptions and implement unit tests

* refactor: use module-level constant for OS name as suggested in PR review
2026-03-03 15:16:38 +08:00
RC-CHN f818ad0758 Merge remote-tracking branch 'origin/master' into feat/neo-skill-self-iteration 2026-03-02 09:37:06 +08:00
Soulter d561046ba3 feat: enhance shell command execution description for cross-platform compatibility
fixes: #5499
2026-03-01 15:35:40 +08:00
RC-CHN 73e665bef7 feat(neo): guide skill lifecycle tool workflow
Add explicit Neo lifecycle instructions to the main agent prompt so
skill creation and updates follow payload -> candidate -> promotion
instead of direct local folder writes.

Clarify lifecycle tool descriptions and parameter semantics, including
skill_key/source_execution_ids usage and stable release sync_to_local
behavior, to reduce ambiguity and improve consistent skill publishing.
2026-02-26 16:14:16 +08:00
RC-CHN e95bd8d3a6 style: format code 2026-02-26 15:27:37 +08:00
RC-CHN d5a3107f8f style: format code 2026-02-26 15:24:10 +08:00
RC-CHN 847ef0f3f4 Merge remote-tracking branch 'origin/master' into feat/neo-skill-self-iteration 2026-02-26 10:04:48 +08:00
Axi404 00b011809a fix: enforce admin guard for sandbox file transfer tools (#5402)
* fix: enforce admin guard for sandbox file transfer tools

* refactor: deduplicate computer tools admin permission checks

* fix: add missing space in permission error message
2026-02-24 20:59:44 +08:00
zenfun c1917ebf4f fix(computer): resolve absolute skill paths at runtime in scan command
- Resolve skills root via Path.resolve() so LLM prompts always
  reference absolute paths regardless of sandbox cwd
- Use resolved path in skill metadata for reliable cat/head commands
- Add DRY cross-reference comment for frontmatter parser
- Remove dead skills_root_abs field from JSON output (no consumer)
- Remove unnecessary os import and fake resolve/abspath branch
2026-02-21 01:03:45 +08:00
zenfun 1962ff2def feat(computer): expose sandbox capabilities and smart profile selection
Add capabilities property to ComputerBooter base class (returns None)
and ShipyardNeoBooter (returns immutable tuple from sandbox).

- Extract DEFAULT_PROFILE class constant to replace scattered magic string
- Use tuple[str, ...] for immutability (no defensive copy needed)
- Add _resolve_profile() for smart profile selection:
  - honour user-specified profile
  - query Bay API, prefer browser-capable profiles
  - re-raise auth errors (401/403), fallback on transient failures
- Conditionally create NeoBrowserComponent only when profile has browser
- Log resolved profile and capabilities at boot
2026-02-21 01:03:05 +08:00
zenfun 92a8e40cde feat(computer): auto-start Bay container for zero-config Neo integration
Add BayContainerManager to manage Bay container lifecycle via Docker
Engine API, similar to how BoxliteBooter manages Ship containers.

When ShipyardNeoBooter endpoint is empty or set to '__auto__', Bay is
automatically pulled, started, health-checked, and credentials are
read from the container.

- New bay_manager.py: ensure_running, wait_healthy, read_credentials
- Integrate auto-start into ShipyardNeoBooter boot/shutdown
- Reuse Bay container across sessions (unless-stopped policy)
- Friendly error messages for Docker and credential failures
2026-02-20 23:11:19 +08:00
Soulter 3b2ce9f500 feat: add admin permission checks for Python and Shell execution (#5214) 2026-02-19 01:48:48 +08:00
RC-CHN bc3e09f47b refactor(computer): split sandbox skill sync phases
separate sandbox skill syncing into distinct apply and scan steps
while keeping the legacy combined command for compatibility

improve observability by adding phase-based logs and richer shell
error details that include exit code, stderr, and stdout tail

reuse a shared python-exec command builder to reduce duplication
and keep command generation consistent
2026-02-18 13:35:17 +08:00
Soulter 9b0e24ec49 chore: bump version to 4.17.4 2026-02-17 21:19:53 +08:00
Soulter f22221f781 fix: improve permission denied message for local execution in Python and shell tools 2026-02-17 18:02:41 +08:00
RC-CHN 591803d407 refactor(skills): centralize neo promote and sync flow
extract shared promote/sync orchestration into `NeoSkillSyncManager` so
computer tools and dashboard routes use the same rollback and error logic

add a reusable neo tool base runner to remove duplicated admin checks and
try/catch handling across skill-related tools, keeping responses consistent

factor sync result serialization into a single helper and reuse it where
stable release sync output is returned
2026-02-17 17:20:42 +08:00
RC-CHN cf9a7235f7 fix(computer): return none for unsupported browser capability
set the base booter browser property to return None instead of
raising NotImplementedError so callers can handle missing browser
support through capability checks
2026-02-17 16:59:05 +08:00
RC-CHN d62a6f107b fix(computer): mask bay api key in logs
Also add shipyard-neo-sdk dependency for neo support
2026-02-17 16:40:55 +08:00
Ruochen Pan 1a539830f8 Merge branch 'master' into feat/neo-skill-self-iteration 2026-02-17 16:23:14 +08:00