fz-mirrors/AstrBot
1
0
Fork 0
mirror of https://github.com/AstrBotDevs/AstrBot synced 2026-07-17 17:51:20 +08:00
Code Issues Packages Projects Releases Wiki Activity
4,788 Commits 171 Branches 254 Tags
b9b3d509863a75daeb728547eeb6616a07bc052d
Commit Graph

4788 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
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
Stable Genius
589776ab3f fix: skip empty knowledge-base embedding batches (#6106) 
Co-authored-by: stablegenius49 <185121704+stablegenius49@users.noreply.github.com>
 2026-03-21 20:56:13 +08:00
Stable Genius
5b71d01efb fix: convert Feishu opus files for Whisper API STT (#6078) 
* fix: convert lark opus files for whisper api

* chore: ruff format

---------

Co-authored-by: Stable Genius <259448942+stablegenius49@users.noreply.github.com>
Co-authored-by: Soulter <905617992@qq.com>
 2026-03-21 20:44:36 +08:00
LIghtJUNction
43e107068a chore: cloudflare 2026-03-21 17:35:30 +08:00
LIghtJUNction
09157f8b88 Fix: combine conditions for bot mention check in Discord adapter 2026-03-21 17:12:29 +08:00
若月千鸮
173583781e fix(lark): Defer card creation and renew on tool call break (#6743) 
* fix(lark): defer streaming card creation and renew card on tool call break

- Defer CardKit streaming card creation until the first text token
  arrives, preventing an empty card from rendering before content.
- Handle `type="break"` signal in send_streaming: close the current
  card and lazily create a new one for post-tool-call text, so the
  new card appears below the tool status message in correct order.
- Only emit "break" signal when show_tool_use is enabled; when tool
  output is hidden, the AI response continues on the same card.

* style: format ruff

* fix: cr bug

* fix: cr
 2026-03-21 17:08:25 +08:00
LIghtJUNction
256c8cceeb Fix: handle None values for ctx.author and ctx.interaction in Discord adapter 2026-03-21 16:15:33 +08:00
LIghtJUNction
7391f8e5ee Fix: only enable CORS credentials when allow_origin is not wildcard 2026-03-21 16:00:17 +08:00
LIghtJUNction
b563518711 Fix: replace fullwidth comma with halfwidth comma in discord_platform_adapter.py 2026-03-21 15:21:35 +08:00
LIghtJUNction
255a4c0d5b Fix: support configuring allowed CORS origins via CORS_ALLOW_ORIGIN env 
var for cross-origin credential requests
 2026-03-21 15:20:43 +08:00
LIghtJUNction
859ca98f1e Fix: support configuring allowed CORS origins via CORS_ALLOW_ORIGIN env var for cross-origin credential requests 2026-03-21 15:14:08 +08:00
LIghtJUNction
a58319f594 Fix: Discord adapter not adding At component when bot is mentioned, causing group messages to not wake the bot 2026-03-21 14:26:22 +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
4412f789e1 Fix: downgrade SSL APPLICATION_DATA_AFTER_CLOSE_NOTIFY errors to debug level 2026-03-21 14:13:07 +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
97efa3ab38 Fix: _BUNDLED_DIST undefined, use self.bundled_dist instead 2026-03-21 13:54:39 +08:00
LIghtJUNction
61e525afd4 Merge branch 'master' into dev 2026-03-21 12:25:04 +08:00
Stable Genius
25c136ef95 fix: fall back on Windows skill file encodings (#6058) 
Co-authored-by: stablegenius49 <185121704+stablegenius49@users.noreply.github.com>
 2026-03-21 11:00:40 +08:00
Stable Genius
5e69b62e4c fix(webchat): render standalone HTML replies as code (#6074) 
Co-authored-by: Stable Genius <259448942+stablegenius49@users.noreply.github.com>
Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com>
 2026-03-21 10:52:46 +08:00
Stable Genius
968868f16b fix: ensure Gemini array schemas always include items (#6051) 
Co-authored-by: Stable Genius <259448942+stablegenius49@users.noreply.github.com>
 2026-03-21 10:44:48 +08:00
qingyun
e643bc94e5 fix(skills): use actual sandbox path from cache instead of hardcoded workspace root (#6331) 
* fix(skills): use actual sandbox path from cache instead of hardcoded workspace root

Fixes #6273

When using Shipyard booter, the sandbox workspace directory is
`/home/ship_{session_id}/workspace/` instead of the hardcoded `/workspace`.
This caused Agent to fail reading SKILL.md files with 'No such file or directory'.

Changes:
- In build_skills_prompt: prefer skill.path (from sandbox cache) over
  hardcoded SANDBOX_WORKSPACE_ROOT for sandbox_only skills
- In list_skills: always prefer sandbox_cached_paths over hardcoded path
  for sandbox_only skills

The actual path is resolved at sandbox scan time via Path.resolve() in
_build_scan_command, which returns the correct absolute path based on
the sandbox's actual working directory.

* docs: add comment explaining show_sandbox_path behavior for sandbox_only skills

Address Sourcery AI review comment:
- Clarify that show_sandbox_path is implicitly True for sandbox_only skills
- Explain why the flag is effectively ignored (no local path exists)

* refactor: simplify path_str fallback using or operator

Address review feedback: use single-line fallback instead of if-not pattern.

* style: format skill_manager.py with ruff

Fix ruff format-check failure

* fix(skills): sanitize cached sandbox skill paths

Normalize sandbox cache paths before reading or writing them so invalid,
empty, or mismatched entries fall back to a safe default SKILL.md path.

This avoids using malformed cached paths, keeps path rendering
consistent, and ensures sandbox skill listings always point to the
expected workspace location.

---------

Co-authored-by: ccsang <ccsang@users.noreply.github.com>
Co-authored-by: RC-CHN <1051989940@qq.com>
 2026-03-21 10:39:52 +08:00
Soulter
df4eb33582 docs: update README.md to add separator in links section 2026-03-21 10:34:27 +08:00
LIghtJUNction
286f6668f4 Fix formatting of bundled_dist property method 2026-03-21 05:10:52 +08:00
LIghtJUNction
4a5ac407d1 Refactor bundled_dist path handling in AstrbotPaths 
Removed the _BUNDLED_DIST variable and added a bundled_dist property to calculate the path dynamically.
 2026-03-21 05:01:41 +08:00
LIghtJUNction
93cab0e198 Reorganize .env loading sequence in astrbot_path.py 
Refactor environment variable loading order in astrbot_path.py.
 2026-03-21 04:51:53 +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
LIghtJUNction
a710c06be2 Validate config_path before checking existence 
Add check for empty config_path in check_exist method
 2026-03-21 03:49:12 +08:00
LIghtJUNction
864a6851df Fix context manager usage for timeout enforcement 2026-03-21 03:36:32 +08:00
LIghtJUNction
37594dd74b Return Path object for project root property 2026-03-21 03:04:00 +08:00
LIghtJUNction
68c01cfba4 Fix handling of cached_tokens in _extract_usage 
Ensure cached_tokens is an integer and handle None safely.
 2026-03-21 02:37:04 +08:00
LIU Yaohua
8d9838a293 fix(agent): pass tool_call_timeout to subagent handsoff, cron and background task execution, and increase default timeout from 60 to 120 (#6713) 
* fix(agent): pass tool_call_timeout to SubAgent handoff execution

- Add tool_call_timeout parameter to _execute_handoff method
- Pass run_context.tool_call_timeout to ctx.tool_loop_agent
- Add unit test to verify tool_call_timeout is correctly passed
- Fixes #6711: SubAgent MCP tool call timeout now respects configured timeout

The SubAgent handoff execution was using the default 60-second timeout
instead of the configured tool_call_timeout from provider settings.
This change ensures that SubAgent MCP tool calls respect the user's
configured timeout settings.

* test: add unit test for tool_call_timeout in SubAgent handoff

* fix: restore deleted test and fix test assertion

- Restore test_collect_handoff_image_urls_filters_extensionless_missing_event_file
- Fix test_collect_handoff_image_urls_keeps_extensionless_existing_event_file assertion
- Keep new test_execute_handoff_passes_tool_call_timeout_to_tool_loop_agent

* refactor: simplify tool_call_timeout passing in _execute_handoff

- Pass run_context.tool_call_timeout directly to ctx.tool_loop_agent
- Remove unnecessary local variable assignment
- Addresses review feedback from Sourcery AI

* fix(config): increase default tool call timeout from 60 to 120 seconds

---------

Co-authored-by: LehaoLin <linlehao@cuhk.edu.cn>
Co-authored-by: Soulter <905617992@qq.com>
 2026-03-21 01:30:53 +08:00
BillionToken
b273ba2a19 fix(config): respect disabled system functions in web search tools (#6584) 
Co-authored-by: BillionClaw <billionclaw@cl OSS.dev>
 2026-03-21 01:18:47 +08:00
Soulter
5214a8c0ba perf(webchat): enhance message handling with proactive saving and streaming completion (#6698) 2026-03-21 01:14:02 +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
LIghtJUNction
6e3273dbec 修复：argon2库已过时，无法在3.12运行 2026-03-21 01:03:39 +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
af77f82c51 更名：conf password可以修改账户名称，因此改名为admin 
astrbot conf admin -p xxx
 2026-03-21 00:47:14 +08:00
LIghtJUNction
1b92c517e7 Merge branch 'master' into dev 2026-03-21 00:31:18 +08:00
LIghtJUNction
c238880cd2 修复：server.py 2026-03-21 00:28:56 +08:00
晴空
d2e0bc778a fix: preserve PATHEXT for stdio mcp servers on windows (#5822) 
* fix: preserve PATHEXT for stdio mcp servers on windows

* chore: delete test_mcp_client.py

---------

Co-authored-by: Soulter <905617992@qq.com>
 2026-03-21 00:27:54 +08:00
LIghtJUNction
92b3e2d260 fix: avoid false dashboard port conflicts 2026-03-21 00:24:35 +08:00
Gargantua
dde02815c2 feat: add a toggle to disable thinking mode in Ollama (#5941) 
* feat: add ollama thinking toggle

* fix: simplify hint for ollama_disable_thinking configuration

---------

Co-authored-by: Gargantua <22532097@zju.edu.cn>
Co-authored-by: Soulter <905617992@qq.com>
 2026-03-21 00:19:08 +08:00
LIghtJUNction
00c9388da3 重构：彻底放弃md5保存密码 
main.py调整说明
修复一系列导入问题
修复一部分ruff check问题
 2026-03-21 00:09:58 +08:00
whatevertogo
2c279abad1 fix: prevent accidental removal of MCP external tools due to name collisions with disabled built-in tools (#5925) 
* fix: 解决 MCP 工具与内置工具重名时的连坐问题

- 修改 get_func 方法：优先返回已激活的工具
- 修改 get_full_tool_set 方法：使用 add_tool 防止同名冲突
- 修改 add_tool 方法：优先保留已激活的工具

Fixes #5821

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

* refactor: address PR review feedback for tool conflict resolution

- Fix inconsistency: get_func now uses reversed() to match ToolSet.add_tool's
  "last-active-wins" logic, preventing potential "tool hijacking" issues
- Improve readability: replace double negative condition with clearer logic
- Add compatibility: use getattr with default for tools without 'active' attribute
- Remove unnecessary deepcopy: MCPTool runtime objects should not be deep copied
- Update docstring: accurately describe the actual tool resolution behavior

Addresses review comments from sourcery-ai, gemini-code-assist, and Copilot.

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

* test: add tests for tool conflict resolution (issue #5821)

Add comprehensive tests for ToolSet.add_tool, get_func, and get_full_tool_set
to verify the conflict resolution behavior when MCP tools share names with
built-in tools.

Test cases:
- ToolSet.add_tool: active/inactive priority, last-one-wins for same state
- get_func: returns last active tool, fallback to last matching tool
- get_full_tool_set: deduplication logic, no deepcopy, MCP overrides disabled builtin

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

* fix: 修复工具冲突处理逻辑，确保未激活工具不被错误移除

---------

Co-authored-by: whatevertogo <whatevertogo@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-20 23:44:07 +08:00
_Kerman
abb5de2ed5 chore: rename "OpenAI" provider to "OpenAI Compatible" (#6707) 2026-03-20 23:19:26 +08:00
LIghtJUNction
7445126057 Merge branch 'master' into dev 2026-03-20 22:40:32 +08:00
LIghtJUNction
9f2240a2a6 fix async ssl path handling 2026-03-20 21:50:46 +08:00