Skip to content

feat: add a toggle to disable thinking mode in Ollama#5941

Merged
Soulter merged 2 commits intoAstrBotDevs:masterfrom
catDforD:feat/5714-ollama-thinking-mode
Mar 20, 2026
Merged

feat: add a toggle to disable thinking mode in Ollama#5941
Soulter merged 2 commits intoAstrBotDevs:masterfrom
catDforD:feat/5714-ollama-thinking-mode

Conversation

@catDforD
Copy link
Copy Markdown
Contributor

@catDforD catDforD commented Mar 9, 2026

closes #5714
closes #5769

当前 AstrBot 中的 Ollama 提供商走的是 OpenAI 兼容接口,但在该接口下直接使用 think:false 不能稳定关闭 thinking。这个 PR 为 Ollama 提供商增加了一个专用开关,在启用时内部改为注入 reasoning_effort=none,从而更稳定地关闭思考模式,减少模型响应延迟。顺带一提,#5769 其实也是相似的问题,这里应该都能解决。

Modifications / 改动点

  • 为 Ollama 提供商源的高级配置新增 关闭思考模式 开关
  • 在启用该开关时,对 Ollama 的 OpenAI 兼容请求注入 reasoning_effort=none
  • 在开关开启时,移除冲突的 reasoning / think 额外请求参数
  • 为旧的 Ollama provider source 配置补默认值,确保新字段能正常显示
  • 补充该配置项的中英文文案
  • 增加对应测试,覆盖 Ollama 请求覆盖逻辑

文件变更说明

  • astrbot/core/config/default.py

    • 为 Ollama source 增加默认配置项和元数据定义
  • astrbot/core/provider/sources/openai_source.py

    • 增加 Ollama 专用的 thinking 关闭逻辑,映射到 reasoning_effort=none
  • dashboard/src/composables/useProviderSources.ts

    • 修复高级配置条件渲染所需的上下文保留问题,并兼容旧配置
  • dashboard/src/i18n/locales/en-US/features/config-metadata.json

    • 增加英文文案
  • dashboard/src/i18n/locales/zh-CN/features/config-metadata.json

    • 增加中文文案
  • tests/test_openai_source.py

    • 增加相关单元测试
  • This is NOT a breaking change. / 这不是一个破坏性变更。

Screenshots or Test Results / 运行截图或测试结果

配置界面截图如下:

image

测试视频如下:

freecompress-202603091727.mp4

视频中未显示 工具调用 是否会有影响,但是我实际测试过,开关思考模式不会对工具调用产生影响。

本地已完成以下验证:

ruff check .
uv run pytest tests/test_openai_source.py
cd dashboard && pnpm build

验证结果:

  • ruff check . 通过
  • uv run pytest tests/test_openai_source.py 通过,共 12 passed
  • pnpm build 通过
  • 在运行中的 Dashboard 中手动确认:
    • 已加载最新前端产物
    • Ollama 高级配置中已显示“关闭思考模式”开关
    • 开关可以正常勾选
  • 对本地 Ollama 服务验证确认:
    • reasoning_effort=none 能在 OpenAI 兼容接口下更稳定地关闭 thinking
    • think:false 在该接口下不稳定,不适合作为 AstrBot 的实现方案

Checklist / 检查清单

  • 😊 如果 PR 中有新加入的功能,已经通过 Issue / 邮件等方式和作者讨论过。/ If there are new features added in the PR, I have discussed it with the authors through issues/emails, etc.
  • 👀 我的更改经过了良好的测试,并已在上方提供了“验证步骤”和“运行截图”。/ My changes have been well-tested, and "Verification Steps" and "Screenshots" have been provided above.
  • 🤓 我确保没有引入新依赖库,或者引入了新依赖库的同时将其添加到了 requirements.txtpyproject.toml 文件相应位置。/ I have ensured that no new dependencies are introduced, OR if new dependencies are introduced, they have been added to the appropriate locations in requirements.txt and pyproject.toml.
  • 😮 我的更改没有引入恶意代码。/ My changes do not introduce malicious code.

Summary by Sourcery

通过添加一个 Ollama 专用开关,更可靠地在 OpenAI 兼容提供方中禁用模型的思考模式,并确保现有的 Ollama 来源拥有安全的默认值。

New Features:

  • 引入一个仅适用于 Ollama 的高级配置选项,用于禁用思考模式,其方式是通过 OpenAI 兼容端点将请求映射为 reasoning_effort=none

Enhancements:

  • 在 OpenAI 提供方中规范化并应用针对不同提供方的 extra_body 覆盖逻辑,使得在禁用思考模式时,Ollama 请求会移除冲突的 reasoning/think 参数。
  • 确保仪表盘中的 Ollama 提供方来源能够为新的禁用思考标志回填默认值,并调整高级配置处理逻辑,在隐藏被排除的键以避免渲染的同时,仍然保留字段访问能力。

Tests:

  • 添加单元测试,以验证在启用禁用思考选项时,Ollama 请求会注入 reasoning_effort=none,并移除冲突的 reasoning/think 字段。
Original summary in English

Summary by Sourcery

Add an Ollama-specific toggle to more reliably disable the model’s thinking mode via the OpenAI-compatible provider, and ensure existing Ollama sources get a safe default.

New Features:

  • Introduce an Ollama-only advanced configuration option to disable thinking mode by mapping requests to reasoning_effort=none via the OpenAI-compatible endpoint.

Enhancements:

  • Normalize and apply provider-specific overrides to extra_body in the OpenAI provider so Ollama requests remove conflicting reasoning/think parameters when thinking is disabled.
  • Ensure dashboard provider sources for Ollama backfill a default value for the new disable-thinking flag and adjust advanced-config handling to preserve field accessors while hiding excluded keys from rendering.

Tests:

  • Add unit tests to validate that Ollama requests inject reasoning_effort=none and strip conflicting reasoning/think fields when the disable-thinking option is enabled.

@auto-assign auto-assign bot requested review from Fridemn and advent259141 March 9, 2026 09:37
@dosubot dosubot bot added the size:L This PR changes 100-499 lines, ignoring generated files. label Mar 9, 2026
@gemini-code-assist
Copy link
Copy Markdown
Contributor

Summary of Changes

Hello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

此拉取请求旨在解决 Ollama 提供商在使用 OpenAI 兼容接口时,通过 think:false 无法稳定关闭思考模式的问题。通过引入一个新的专用开关,并在启用时注入 reasoning_effort=none,本变更提供了一种更可靠的方式来控制模型的思考行为,从而减少响应延迟并提高稳定性。

Highlights

  • Ollama 思考模式开关: 为 Ollama 提供商添加了“关闭思考模式”开关,以提供更稳定的控制方式。
  • 注入 reasoning_effort=none: 当该开关启用时,通过 OpenAI 兼容接口注入 reasoning_effort=none,以更稳定地关闭思考模式,解决 think:false 不稳定的问题。
  • 移除冲突参数: 在开关开启时,移除了冲突的 reasoningthink 请求参数。
  • 配置默认值与国际化: 为旧的 Ollama 提供商配置补充了 ollama_disable_thinking 字段的默认值,并增加了新配置项的中英文文案。
  • 单元测试: 补充了相关的单元测试,覆盖了 Ollama 请求覆盖逻辑。
Changelog
  • astrbot/core/config/default.py
    • 为 Ollama 提供商配置添加了 ollama_disable_thinking 字段的默认值。
    • 定义了 ollama_disable_thinking 配置项的元数据,包括描述、类型、提示和条件。
  • astrbot/core/provider/sources/openai_source.py
    • 新增了 _ollama_disable_thinking_enabled 方法,用于检查是否启用了 Ollama 的思考模式关闭功能。
    • 新增了 _apply_provider_specific_extra_body_overrides 方法,用于在 Ollama 提供商启用关闭思考模式时,从 extra_body 中移除 reasoningthink 参数,并注入 reasoning_effort=none
    • _query_query_stream 方法中调用了 _apply_provider_specific_extra_body_overrides
  • dashboard/src/composables/useProviderSources.ts
    • 修改了 advancedSourceConfig 计算属性,以更灵活地处理高级配置项的枚举性,并兼容旧配置。
    • 新增了 ensureProviderSourceDefaults 函数,用于为提供商源(特别是 Ollama)设置默认值,确保 ollama_disable_thinking 字段的正确显示。
    • 在加载现有提供商源和创建新提供商源时,应用了 ensureProviderSourceDefaults 函数。
  • dashboard/src/i18n/locales/en-US/features/config-metadata.json
    • 添加了 ollama_disable_thinking 配置项的英文描述和提示。
  • dashboard/src/i18n/locales/zh-CN/features/config-metadata.json
    • 添加了 ollama_disable_thinking 配置项的中文描述和提示。
  • tests/test_openai_source.py
    • 导入了 ChatCompletion 类型。
    • 新增了 test_apply_provider_specific_extra_body_overrides_disables_ollama_thinking 测试,验证当 ollama_disable_thinking 启用时,reasoningthink 参数被移除,reasoning_effort 被设置为 none
    • 新增了 test_query_injects_reasoning_effort_none_for_ollama 测试,验证在实际 _query 调用中,当 ollama_disable_thinking 启用时,reasoning_effort=none 被正确注入。
Activity
  • 作者提供了配置界面的截图和测试视频,展示了新功能的 UI 和行为。
  • 作者进行了本地验证,包括 ruff checkpytestpnpm build,并确认所有测试通过。
  • 作者手动验证了 Dashboard 中“关闭思考模式”开关的显示和功能,并确认 reasoning_effort=none 在本地 Ollama 服务下能更稳定地关闭思考模式。
  • 作者确认此变更为非破坏性变更。
  • 作者完成了 PR 检查清单中的所有项。
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

Copy link
Copy Markdown
Contributor

@sourcery-ai sourcery-ai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

嗨——我已经审阅了你的改动,看起来非常不错!


Sourcery 对开源项目是免费的——如果你觉得我们的审查有帮助,请考虑分享给更多人 ✨
帮我变得更有用!请在每条评论上点 👍 或 👎,我会根据你的反馈改进后续的审查。
Original comment in English

Hey - I've reviewed your changes and they look great!


Sourcery is free for open source - if you like our reviews please consider sharing them ✨
Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.

@dosubot dosubot bot added the area:provider The bug / feature is about AI Provider, Models, LLM Agent, LLM Agent Runner. label Mar 9, 2026
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

这个 PR 实现得很好,为 Ollama 提供商添加了一个关闭思考模式的专用开关。代码改动清晰,覆盖了后端逻辑、前端配置、国际化文案和单元测试,确保了功能的完整性和稳定性。特别是,后端对 extra_body 的处理很健壮,前端通过 ensureProviderSourceDefaults 确保了向后兼容性,并且测试用例覆盖了核心逻辑。我只发现了一个可以改进的小问题,即 _query_query_stream 方法中参数合并逻辑存在不一致,具体请看我的评论。

to_del.append(key)
for key in to_del:
del payloads[key]
self._apply_provider_specific_extra_body_overrides(extra_body)
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

您好,此处的改动是正确的,但在审查代码时,我注意到 _query_stream 方法中构造 extra_body 的逻辑与 _query 方法中不一致。

_query_stream 中(当前方法):

  1. custom_extra_body 更新 extra_body
  2. payloads 中的参数再次更新 extra_body
    这意味着 payloads 中的参数会覆盖 custom_extra_body 中的同名参数。

_query 中:

  1. payloads 中的参数构造 extra_body
  2. custom_extra_body 更新 extra_body
    这意味着 custom_extra_body 会覆盖 payloads 中的同名参数。

通常 custom_extra_body(来自静态配置)的优先级应该更高。为了保持行为一致性并避免潜在的 bug,建议将 _query_stream 中的逻辑调整为与 _query 一致。

虽然这超出了本次变更的核心范围,但由于您接触了这部分代码,这是一个很好的改进机会。

@lynb233
Copy link
Copy Markdown

lynb233 commented Mar 11, 2026

感谢大佬

@Potatoii
Copy link
Copy Markdown

非常好功能, 期待合入

@catDforD catDforD changed the base branch from master to dev March 16, 2026 04:58
@Soulter Soulter changed the title feat: 添加 Ollama 关闭思考模式开关 #5714 feat: add a toggle to disable thinking mode in Ollama Mar 20, 2026
@Soulter Soulter changed the base branch from dev to master March 20, 2026 16:13
@dosubot dosubot bot added the lgtm This PR has been approved by a maintainer label Mar 20, 2026
@Soulter Soulter merged commit dde0281 into AstrBotDevs:master Mar 20, 2026
1 of 4 checks passed
KBVsent pushed a commit to KBVsent/AstrBot that referenced this pull request Mar 21, 2026
* 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>
xkeyC added a commit to xkeyC/AstrBot that referenced this pull request Mar 28, 2026
* perf: onebot, satori docs improvement

* ci: add pr check

* chore: Delete .github/workflows/pr-checklist-check.yml

* feat: localize session management group & interval method texts (AstrBotDevs#6471)

* fix(ui): localize session management group texts

Replace hardcoded Chinese strings in SessionManagementPage with i18n
lookups for group management labels, dialogs, and action feedback.

Add and align translation keys in en-US, ru-RU, and zh-CN for group
management and batch operation messages to ensure consistent multilingual
UI behavior.

* fix(ui): localize interval method hint text

* fix: SQLite 'database is locked' by adding busy timeout (AstrBotDevs#6474)

The async engine is created without a busy timeout, so concurrent
writes (agent responses, metrics, session updates) fail instantly
with 'database is locked' instead of waiting for the lock.

Add connect_args={'timeout': 30} for SQLite engines so the driver
waits up to 30 seconds for the write lock. Combined with the existing
WAL journal mode, this handles the typical concurrent write bursts
from agent + metrics + session operations.

Fixes AstrBotDevs#6443

* fix: parse multiline frontmatter description in SKILL.md (AstrBotDevs#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>

* chore(deps): bump the github-actions group with 2 updates (AstrBotDevs#6461)

Bumps the github-actions group with 2 updates: [ncipollo/release-action](https://github.com/ncipollo/release-action) and [actions/github-script](https://github.com/actions/github-script).


Updates `ncipollo/release-action` from 1.20.0 to 1.21.0
- [Release notes](https://github.com/ncipollo/release-action/releases)
- [Commits](ncipollo/release-action@v1.20.0...v1.21.0)

Updates `actions/github-script` from 7 to 8
- [Release notes](https://github.com/actions/github-script/releases)
- [Commits](actions/github-script@v7...v8)

---
updated-dependencies:
- dependency-name: ncipollo/release-action
  dependency-version: 1.21.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: github-actions
- dependency-name: actions/github-script
  dependency-version: '8'
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: github-actions
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* chore: remove deprecated version field from compose.yml (AstrBotDevs#5495)

The version field is no longer required in Docker Compose v2 and has been deprecated.

* fix: reading skills on Windows (AstrBotDevs#6490)

There is an issue with reading the skill directory on the Windows system, which results in a high probability of files under the skill directory being unrecognizable, now fix it.

* fix: subagent lookup failure when using default persona (AstrBotDevs#5672)

* fix: resolve subagent persona lookup for 'default' and unify resolution logic

- Add PersonaManager.get_persona_v3_by_id() to centralize v3 persona resolution
- Handle 'default' persona_id mapping to DEFAULT_PERSONALITY in subagent orchestrator
- Fix HandoffTool.default_description using agent_name parameter correctly
- Add tests for default persona in subagent config and tool deduplication

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

* refactor: simplify get_default_persona_v3 using get_persona_v3_by_id

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

---------

Co-authored-by: whatevertogo <whatevertogo@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com>

* fix: register_agent decorator NameError (AstrBotDevs#5765)

* fix: 修改 register_agent 以避免运行时导入 AstrAgentContext

* test: improve register_agent test robustness

- Add fixture for llm_tools cleanup to avoid test interference
- Use multiple import patterns to make guard more robust to refactors
- Add assertion to verify decorated coroutine is wired as handoff handler

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

* 删除测试文件: 移除 register_agent 装饰器的运行时行为测试

---------

Co-authored-by: whatevertogo <whatevertogo@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Soulter <905617992@qq.com>

* fix: only pass dimensions when explicitly configured in embedding config (AstrBotDevs#6432)

* fix: only pass dimensions param when explicitly configured

Models like bge-m3 don't support the dimensions parameter in the
embedding API, causing HTTP 400 errors. Previously dimensions was
always sent with a default value of 1024, even when the user never
configured it. Now dimensions is only included in the request when
embedding_dimensions is explicitly set in provider config.

Closes AstrBotDevs#6421

Signed-off-by: JiangNan <1394485448@qq.com>

* fix: handle invalid dimensions config and align get_dim return

- Add try-except around int() conversion in _embedding_kwargs to
  gracefully handle invalid embedding_dimensions config values
- Update get_dim() to return 0 when embedding_dimensions is not
  explicitly configured, so callers know dimensions weren't specified
  and can handle it accordingly
- Both methods now share consistent logic for reading the config

Signed-off-by: JiangNan <1394485448@qq.com>

* fix: improve logging for invalid embedding_dimensions configuration

---------

Signed-off-by: JiangNan <1394485448@qq.com>
Co-authored-by: Soulter <905617992@qq.com>

* perf: Implement Pydantic data models for the KOOK adapter to enhance data retrieval and message schema validation (AstrBotDevs#5719)

* refactor: 给kook适配器添加kook事件数据类

* format: 使用StrEnum替换kook适配器中的(str,enum)

* docs: add aiocqhttp and satori protocol documentation; remove outdated lagrange and napcat guides

* refactor: downgrade StrEnum to (str, Enum) in kook_type for backward compatibility  (AstrBotDevs#6512)

我那时候搓 AstrBotDevs#5719 的时候 AstrBotDevs#5729 已经合并了, 既然ruff的py限制版本里是`3.12`,那我那时候干脆用的StrEnum,现在发现那个pr revert了,那我也降级回旧Enum写法好了

* feat: install plugin using metadata name and validate importable identifiers (AstrBotDevs#6530)

* feat: install plugin using metadata name and validate importable identifiers

* fix: cleanup temporary upload extraction directory on plugin install failure

* Update astrbot/core/star/star_manager.py

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

* fix: avoid unnecessary install when repository directory already exists

---------

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

* fix: restrict workflows to upstream repo (AstrBotDevs#6531)

* Clarify FileUpload/DownloadTool descriptions to fix LLM tool selection (AstrBotDevs#6527)

Multiple models (Gemini 3, GPT-5.2, Claude Sonnet, Kimi K2.5) consistently
pick FileDownloadTool when they should pick FileUploadTool. The old
descriptions used "upload/download" which is ambiguous from the LLM's
perspective — it doesn't know which side is "local" vs "remote".

Rewrite descriptions to use explicit directional language:
- Upload: "Transfer FROM host INTO sandbox" + "when user sends a file"
- Download: "Transfer FROM sandbox OUT to host" + "ONLY when user asks
  to retrieve/export"

Also improve parameter descriptions with the same directional clarity.

Fixes AstrBotDevs#6497

Co-authored-by: Yufeng He <40085740+universeplayer@users.noreply.github.com>

* perf(dashboard): subset MDI icon font and self-host Google Fonts (AstrBotDevs#6532)

* perf(dashboard): subset MDI icon font and self-host Google Fonts

* perf(dashboard): subset MDI icon font and self-host Google Fonts

* perf(dashboard): subset MDI icon font and self-host Google Fonts

* perf(dashboard): subset MDI icon font cr fix

* chore: update lockfile

* enhance:更改未完成更新的文档用词问题(多处“消息平台”已更名为“机器人”) (AstrBotDevs#6568)

* Update kubernetes.md

* Update discord.md

* Update kubernetes.md

* Update AstrBot setup instructions in Kubernetes doc

* fix: set packaged Windows runtime build env for pip native builds (AstrBotDevs#6575)

* Fix Windows packaged runtime pip build env

* test(pip): cover packaged runtime env injection edges

* refactor(pip): tighten packaged runtime env handling

* test(pip): cover missing runtime build dirs

* fix(pip): build runtime env inside locked section

* test(pip): expand windows path normalization coverage

* refactor(pip): build runtime env from snapshots

* fix(pip): preserve windows env key semantics

* refactor(pip): simplify windows runtime env handling

Keep the in-process pip environment mutation and case-insensitive INCLUDE/LIB handling localized so packaged Windows builds are easier to follow. Add a UNC no-op regression case to guard path normalization.

* refactor(pip): streamline runtime env mutation helpers

Keep packaged Windows pip environment handling easier to follow by reusing a temporary environment context manager, isolating case-insensitive INCLUDE/LIB lookup, and documenting native path normalization behavior.

* feat (doc) : Add doc for shipyard-neo sandbox driver (AstrBotDevs#6590)

* fix(ui): localize session management group texts

Replace hardcoded Chinese strings in SessionManagementPage with i18n
lookups for group management labels, dialogs, and action feedback.

Add and align translation keys in en-US, ru-RU, and zh-CN for group
management and batch operation messages to ensure consistent multilingual
UI behavior.

* fix(ui): localize interval method hint text

* docs(sandbox): document shipyard neo setup

Expand the Chinese sandbox guide to cover Shipyard Neo as the
recommended driver and distinguish it from legacy Shipyard.

Add deployment and configuration guidance for standalone and
compose-based setups, include a full annotated config example,
and clarify profile selection, TTL behavior, workspace paths,
and persistence semantics.

* docs(sandbox): recommend standalone shipyard neo

Clarify that Shipyard Neo is best deployed on a separate,
better-provisioned host for long-term use.

Update the setup steps and AstrBot connection guidance, and
remove the earlier combined Docker Compose deployment flow.

* docs(sandbox): expand shipyard neo guide

Document Shipyard Neo as the recommended sandbox driver and
clarify how it differs from the legacy Shipyard setup.

Add guidance for deployment, performance requirements, Bay
configuration, profile selection, TTL behavior, workspace
persistence, and browser capability support.

Also reorganize the sandbox configuration section and keep the
legacy Shipyard instructions for compatibility.

* docs(sandbox): fix shipyard neo doc links

Update the sandbox guides in English and Chinese to link
directly to the upstream `config.yaml` example.

Replace duplicated TTL and persistence notes with references
to the dedicated sections to keep the guide concise and easier
to maintain.

* docs(sandbox): clarify section references in guides (AstrBotDevs#6591)

* fix: prevent wecom ai bot long connection replies from disappearing (AstrBotDevs#6606)

* fix: prevent empty fallback replies from clearing wecom ai bot output

* fix: 优化消息发送逻辑,避免发送空消息

---------

Co-authored-by: shijianhuai <shijianhuai@simuwang.com>
Co-authored-by: Soulter <905617992@qq.com>

* fix(wecom-aibot): significantly improve streaming readability and speed via add throttling (AstrBotDevs#6610)

* fix(wecom-ai): add 0.5s interval for streaming responses

* fix(wecom-ai): correct event type checking and add spacing in WecomAIBotMessageEvent

* feat: context token counting support for multimodal content (images, audio, and chain-of-thought) (AstrBotDevs#6596)

EstimateTokenCounter 之前只计算 TextPart,完全忽略 ImageURLPart、
AudioURLPart 和 ThinkPart。多模态对话中图片占 500-2000 token,
不被计入会导致 context 压缩触发过晚,API 先报 context_length_exceeded。

改动:
- ImageURLPart 按 765 token 估算(OpenAI vision 低/高分辨率中位数)
- AudioURLPart 按 500 token 估算
- ThinkPart 的文本内容正常计算
- 10 个新测试覆盖各类型单独和混合场景

Co-authored-by: Yufeng He <40085740+universeplayer@users.noreply.github.com>

* fix(openai): Token usage not working when using MoonshotAI official API (AstrBotDevs#6618)

fixes: AstrBotDevs#6614

* fix: update hint for ID whitelist configuration to clarify behavior when empty (AstrBotDevs#6611)

* fix: update hint for ID whitelist configuration to clarify behavior when empty

* fix: update whitelist hint

---------

Co-authored-by: machina <1531829828@qq.com>
Co-authored-by: Soulter <905617992@qq.com>

* fix: 截断器丢失唯一 user 消息导致智谱等 provider 返回 400 (AstrBotDevs#6581)

* fix: 截断器丢失唯一 user 消息导致 API 400

修复 AstrBotDevs#6196

当对话只有一条 user 消息(长 tool chain 场景:system → user → assistant
→ tool → assistant → tool → ...),三个截断方法都会把这条 user 消息丢掉,
导致智谱、Gemini 等要求 user 消息的 provider 返回 400。

改动:
- 提取 `_split_system_rest()` 去掉三个方法里重复的 system/non-system 拆分
- 新增 `_ensure_user_message()`:截断后如果没有 user 了,从原始消息里补回
  第一条 user,避免违反 API 格式要求
- 删掉 `truncate_by_dropping_oldest_turns` 里把没有 user 就清空全部消息的逻辑
- 5 个新测试覆盖单 user + 长 tool chain 场景,3 个旧测试更新断言

* style: format code

---------

Co-authored-by: Yufeng He <40085740+universeplayer@users.noreply.github.com>
Co-authored-by: RC-CHN <1051989940@qq.com>

* fix: prevent truncation logic from removing the only user message in long tool-calling conversations (AstrBotDevs#6198)

* fix: 压缩算法删除 user 消息 Bug 修复

* perf: improve truncate algo

---------

Co-authored-by: Soulter <905617992@qq.com>

* feat: add Kimi Coding Plan provider with Anthropic API compatibility (AstrBotDevs#6559)

* Add Kimi Code provider

* Add icon mapping for Kimi Code provider

* Clarify Kimi CodingPlan provider labeling

* Refine Kimi Code header handling

* modified docker compose

* fix: correct Kimi Coding Plan label and update API base URL

---------

Co-authored-by: Soulter <905617992@qq.com>

* fix(openai): improve logging for proxy and API base configuration (AstrBotDevs#6669)

fix: AstrBotDevs#6558

* fix(dashboard): simplify persona selector layout for mobile screens (AstrBotDevs#5907)

* fix: Follow-up logic persists after /stop trigger (AstrBotDevs#6656)

/stop 设置 agent_stop_requested 标记,但 runner 直到当前工具调用
超时才从 _ACTIVE_AGENT_RUNNERS 注销。在此窗口期内,用户发的新消息
被 try_capture_follow_up() 当作 follow-up 吞掉。

在 follow-up 捕获前检查 stop 标记:一旦用户请求停止,就不再把后续
消息注入到正在终止的 agent 上下文中。

Fixes AstrBotDevs#6626

* fix: auto-restart telegram polling loop on failure (AstrBotDevs#6648)

* fix: auto-restart telegram polling loop on failure (AstrBotDevs#373)

* fix: auto-restart telegram polling loop on failure

* fix: harden telegram polling restart lifecycle

* fix(telegram): 根据建议优化轮询鲁棒性并处理 Token 失效错误

* fix: 补全配置元数据及 i18n

* feat: add xiaomi MiMo TTS & STT providers (AstrBotDevs#6643)

* feat: add mimo tts provider support

* fix: handle empty mimo tts choices

* feat: add mimo stt provider support

* chore: rename "OpenAI" provider to "OpenAI Compatible" (AstrBotDevs#6707)

* fix: prevent accidental removal of MCP external tools due to name collisions with disabled built-in tools (AstrBotDevs#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 AstrBotDevs#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 AstrBotDevs#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>

* feat: add a toggle to disable thinking mode in Ollama (AstrBotDevs#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>

* fix: preserve PATHEXT for stdio mcp servers on windows (AstrBotDevs#5822)

* fix: preserve PATHEXT for stdio mcp servers on windows

* chore: delete test_mcp_client.py

---------

Co-authored-by: Soulter <905617992@qq.com>

* fix(core): interrupt subagent tool waits on stop (AstrBotDevs#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>

* fix(agent): reject follow-up messages after stop request (AstrBotDevs#6704)

* fix: reject follow-up messages after stop requested (AstrBotDevs#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 AstrBotDevs#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 AstrBotDevs#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>

* fix: skills-like re-query missing extra_user_content_parts causes image_caption not to be injected (AstrBotDevs#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 AstrBotDevs#6702

Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com>

* perf(webchat): enhance message handling with proactive saving and streaming completion (AstrBotDevs#6698)

* fix(config): respect disabled system functions in web search tools (AstrBotDevs#6584)

Co-authored-by: BillionClaw <billionclaw@cl OSS.dev>

* fix(agent): pass tool_call_timeout to subagent handsoff, cron and background task execution, and increase default timeout from 60 to 120 (AstrBotDevs#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 AstrBotDevs#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>

* docs: update README.md to add separator in links section

* fix(skills): use actual sandbox path from cache instead of hardcoded workspace root (AstrBotDevs#6331)

* fix(skills): use actual sandbox path from cache instead of hardcoded workspace root

Fixes AstrBotDevs#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>

* fix: ensure Gemini array schemas always include items (AstrBotDevs#6051)

Co-authored-by: Stable Genius <259448942+stablegenius49@users.noreply.github.com>

* fix(webchat): render standalone HTML replies as code (AstrBotDevs#6074)

Co-authored-by: Stable Genius <259448942+stablegenius49@users.noreply.github.com>
Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com>

* fix: fall back on Windows skill file encodings (AstrBotDevs#6058)

Co-authored-by: stablegenius49 <185121704+stablegenius49@users.noreply.github.com>

* fix(lark): Defer card creation and renew on tool call break (AstrBotDevs#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

* fix: convert Feishu opus files for Whisper API STT (AstrBotDevs#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>

* fix: skip empty knowledge-base embedding batches (AstrBotDevs#6106)

Co-authored-by: stablegenius49 <185121704+stablegenius49@users.noreply.github.com>

* feat(skill_manager): normalize and rename legacy skill markdown files to `SKILL.md` (AstrBotDevs#6757)

* feat(skill_manager): normalize and rename legacy skill markdown files to `SKILL.md`

* fix(vec_db): format debug log message for empty batch insert

* feat(extension): add category filtering for market plugins and enhance UI components (AstrBotDevs#6762)

* chore: bump version to 4.21.0

* feat: supports weixin personal account (AstrBotDevs#6777)

* feat: supports weixin personal account

* feat(weixin): update documentation for personal WeChat integration and add QR code image

* feat(weixin): refactor send method to streamline message handling

* fix(weixin): correct AES key encoding in media payload construction

* feat(weixin): update weixin_oc_base_url description for clarity in config metadata

* feat(weixin): enhance WeChat integration with QR code support and configuration updates

* feat(weixin): implement WeixinOCClient for improved media handling and API requests

* feat(platform): update platform status refresh interval to 5 seconds

* fix(platform.tg_adapter): import Forbidden instead of deprecated Unauthorized (AstrBotDevs#6765) (AstrBotDevs#6769)

* feat: skip search when the entire knowledge base is empty (AstrBotDevs#6750)

* feat:增加知识库全为空时的跳过检索

* apply bot suggestions

* style:reformat code

* feat: fix preserve escaped newlines in frontmatter & update tests & ci workflows (AstrBotDevs#6783)

* Feat(webui): support pinning and dragging for installed plugins (AstrBotDevs#6649) (AstrBotDevs#6776)

* refactor(persona): replace local folder components with shared folder components

* feat(webui): implement draggable reordering with animation for pinned plugins

* refactor(webui): extract PinnedPluginItem into a standalone component

* fix: handle potential None values for token usage metrics in OpenAI provider (AstrBotDevs#6788)

Such as: unsupported operand type(s) for -: 'int' and 'NoneType'

fixes: AstrBotDevs#6772

* feat: supports image compressing (AstrBotDevs#6794)

* feat: supports image compressing (AstrBotDevs#6463)

Co-authored-by: Soulter <905617992@qq.com>

* feat: 增加图像压缩最大尺寸至1280

* Update astrbot/core/astr_main_agent.py

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

* feat: 增强临时文件管理,添加图像压缩路径跟踪与清理功能

* feat: 更新图片压缩功能提示,移除对 chat_completion 提供商的限制说明

---------

Co-authored-by: Chen <42998804+a61995987@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

* fix: keep all CallToolResult content items (AstrBotDevs#6149)

Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com>

* chore: bump version to 4.22.0

* docs: update wechat app version requirements for WeChat adapter and add instructions for profile photo/remark modifications

* chore: gitignore .env warker.js

* fix: remove privacy data from test case (AstrBotDevs#6803)

Co-authored-by: whatevertogo <whatevertogo@users.noreply.github.com>

* fix: align mimo tts style payload with official docs (AstrBotDevs#6814)

* feat(dashboard): add log and cache cleanup in settings (AstrBotDevs#6822)

* feat(dashboard): add log and cache cleanup in settings

* refactor: simplify storage cleaner log config handling

* fix: Repair abnormal indentation

* fix(storage): harden cleanup config handling

Use typed config value access to avoid treating invalid values as
enabled flags or log paths during storage cleanup.

Also stop exposing raw backend exceptions in the dashboard storage
status API and direct users to server logs for details.

---------

Co-authored-by: RC-CHN <1051989940@qq.com>

* fix(t2i): sync active template across all configs (AstrBotDevs#6824)

* fix(t2i): sync active template across all configs

apply template activation and reset to every config profile instead of only
the default one, and reload each pipeline scheduler so changes take effect
consistently in multi-config setups

add a dashboard test that creates extra configs and verifies active template
updates and scheduler reload coverage across all config ids

* fix(t2i): reload all schedulers on template changes

extract a shared helper to reload pipeline schedulers for every config.
when syncing or resetting the active template, persist each config and
then reload all schedulers to keep mappings consistent.

also reload all schedulers when updating the currently active template,
and add dashboard tests to verify cross-config sync and scheduler
replacement behavior.

* fix: cannot use tools in siliconflow provider (AstrBotDevs#6829)

* fix: cannot use tools in siliconflow provider

* fix: handle empty choices in ChatCompletionStreamState

* fix: correct voice message support status in WeChat adapter documentation

* feat(lark): add collapsible reasoning panel support and enhance message handling (AstrBotDevs#6831)

* feat(lark): add collapsible reasoning panel support and enhance message handling

* feat(lark): refactor collapsible panel creation for improved readability and maintainability

* chore: ruff format

* perf: validate config_path before checking existence (AstrBotDevs#6722)

Add a check for empty config_path in check_exist method

* chore(deps): bump pnpm/action-setup in the github-actions group (AstrBotDevs#6862)

Bumps the github-actions group with 1 update: [pnpm/action-setup](https://github.com/pnpm/action-setup).


Updates `pnpm/action-setup` from 4.4.0 to 5.0.0
- [Release notes](https://github.com/pnpm/action-setup/releases)
- [Commits](pnpm/action-setup@v4.4.0...v5.0.0)

---
updated-dependencies:
- dependency-name: pnpm/action-setup
  dependency-version: 5.0.0
  dependency-type: direct:production
  update-type: version-update:semver-major
  dependency-group: github-actions
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* fix: wrong index in ObjectEditor updateKey causing false 'key exists' error

* fix: wrong index in ObjectEditor updateKey causing false 'key exists' error

* fix: same index mismatch issue in updateJSON

* fix(ui): stabilize ObjectEditor pair keys

Use generated ids for key-value pairs instead of array indexes to
prevent mismatch issues during editing and rendering.

Also replace duplicate-key alerts with toast warnings for a more
consistent UI experience.

---------

Co-authored-by: RC-CHN <1051989940@qq.com>

* feat(api): add GET file endpoint and update file route to support multiple methods (AstrBotDevs#6874)

* fix(openapi): rename route view function

* fix(ui): include vuetify radiobox icons (AstrBotDevs#6892)

Add the radiobox icons used indirectly by Vuetify internals
to the required MDI subset so they are kept during font
generation.

Regenerate the subset CSS and font files to prevent missing
radio button icons at runtime.

* fix(tests): update scanUsedIcons tests to include required radio icons (AstrBotDevs#6894)

* doc: Update docs/zh/platform/lark.md (AstrBotDevs#6897)

* 补充飞书配置群聊机器人的部分

- 移除了 im:message:send 权限,因为似乎飞书已经移除了该权限
- 新增关于飞书群聊如何配置权限的部分

* Update docs/zh/platform/lark.md

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

---------

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

* Feat(webui): show plugin author on cards & pinned item (AstrBotDevs#5802) (AstrBotDevs#6875)

* feat: 为卡片视图增加作者信息

* feat:置顶列表面板新增作者名称与插件名称

* docs(compshare): correct typos (AstrBotDevs#6878)

* Fix(WebUi): allow batch resetting provider config to "follow" (iss#6749) (AstrBotDevs#6825)

* feat(webui): use explicit 'follow' status for provider settings and improve batch operation logic

* fix: allow batch resetting provider config to "follow config"

* fix(AstrBotDevs#6749): use a unique constant for 'follow' status to avoid collisions with provider IDs

* fix: remove config.use_reloader = True

* refactor(ui): extract follow config sentinel constant

---------

Co-authored-by: RC-CHN <1051989940@qq.com>

* fix: keep weixin_oc polling after inbound timeouts (AstrBotDevs#6915)

* fix: keep weixin_oc polling after inbound timeouts

* Delete tests/test_weixin_oc_adapter.py

---------

Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com>

* fix(i18n): update OpenAI embedding hint for better compatibility guidance

fixes: AstrBotDevs#6855

* feat: auto-append /v1 to embedding_api_base in OpenAI embedding provider (AstrBotDevs#6863)

* fix: auto-append /v1 to embedding_api_base in OpenAI embedding provider (AstrBotDevs#6855)

When users configure `embedding_api_base` without the `/v1` suffix,
the OpenAI SDK does not auto-complete it, causing request path errors.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: ensure API base URL for OpenAI embedding ends with /v1 or /v4

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Soulter <905617992@qq.com>

* Fix payload handling for msg_id in QQ API (AstrBotDevs#6604)

Remove msg_id from payload to prevent errors with proactive tool-call path and avoid permission issues.

Co-authored-by: Naer <88199249+V-YOP@users.noreply.github.com>

* fix(provider): add missing index field to streaming tool_call deltas (AstrBotDevs#6661) (AstrBotDevs#6692)

* fix(provider): add missing index field to streaming tool_call deltas

- Fix AstrBotDevs#6661: Streaming tool_call arguments lost when OpenAI-compatible proxy omits index field
- Gemini and some proxies (e.g. Continue) don't include index field in tool_call deltas
- Add default index=0 when missing to prevent ChatCompletionStreamState.handle_chunk() from rejecting chunks

Fixes AstrBotDevs#6661

* fix(provider): use enumerate for multi-tool-call index assignment

- Use enumerate() to assign correct index based on list position
- Iterate over all choices (not just the first) for completeness
- Addresses review feedback from sourcery-ai and gemini-code-assist

---------

Co-authored-by: Yaohua-Leo <3067173925@qq.com>
Co-authored-by: Soulter <905617992@qq.com>

* feat(skills): enhance skill installation to support multiple top-level folders and add duplicate handling, and Chinese skill name support (AstrBotDevs#6952)

* feat(skills): enhance skill installation to support multiple top-level folders and add duplicate handling

closes: AstrBotDevs#6949

* refactor(skill_manager): streamline skill name normalization and validation logic

* fix(skill_manager): update skill name regex to allow underscores in skill names

* fix(skill_manager): improve skill name normalization and validation logic

* chore: bump version to 4.22.1

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: JiangNan <1394485448@qq.com>
Co-authored-by: Soulter <905617992@qq.com>
Co-authored-by: LIghtJUNction <lightjunction.me@gmail.com>
Co-authored-by: Ruochen Pan <1051989940@qq.com>
Co-authored-by: Yufeng He <40085740+he-yufeng@users.noreply.github.com>
Co-authored-by: Rhonin Wang <33801807+RhoninSeiei@users.noreply.github.com>
Co-authored-by: RhoninSeiei <RhoninSeiei@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: YYMa <118096301+YuanyuanMa03@users.noreply.github.com>
Co-authored-by: linzhengtian <907305684@qq.com>
Co-authored-by: whatevertogo <149563971+whatevertogo@users.noreply.github.com>
Co-authored-by: whatevertogo <whatevertogo@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com>
Co-authored-by: jnMetaCode <1394485448@qq.com>
Co-authored-by: shuiping233 <49360196+shuiping233@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: 鸦羽 <Raven95676@gmail.com>
Co-authored-by: Yufeng He <40085740+universeplayer@users.noreply.github.com>
Co-authored-by: camera-2018 <40380042+camera-2018@users.noreply.github.com>
Co-authored-by: 糯米茨 <143102889+nuomicici@users.noreply.github.com>
Co-authored-by: エイカク <1259085392z@gmail.com>
Co-authored-by: Ruochen Pan <sorainygreen@gmail.com>
Co-authored-by: Scofield <59475095+shijianhuai@users.noreply.github.com>
Co-authored-by: shijianhuai <shijianhuai@simuwang.com>
Co-authored-by: machina <53079908+machinad@users.noreply.github.com>
Co-authored-by: machina <1531829828@qq.com>
Co-authored-by: leonforcode <leonbeyourside01@gmail.com>
Co-authored-by: daniel5u <danielsuuuuuu@gmail.com>
Co-authored-by: letr <123731298+letr007@users.noreply.github.com>
Co-authored-by: Helian Nuits <sxp20061207@163.com>
Co-authored-by: RichardLiu <97330937+RichardLiuda@users.noreply.github.com>
Co-authored-by: _Kerman <kermanx@qq.com>
Co-authored-by: Gargantua <124801228+catDforD@users.noreply.github.com>
Co-authored-by: Gargantua <22532097@zju.edu.cn>
Co-authored-by: 晴空 <3103908461@qq.com>
Co-authored-by: SJ <idiotgyz@gmail.com>
Co-authored-by: idiotsj <idiotsj@users.noreply.github.com>
Co-authored-by: qingyun <codingtsunami@gmail.com>
Co-authored-by: ccsang <ccsang@users.noreply.github.com>
Co-authored-by: BillionToken <hydr0codone@proton.me>
Co-authored-by: BillionClaw <billionclaw@cl OSS.dev>
Co-authored-by: LIU Yaohua <12531035@mail.sustech.edu.cn>
Co-authored-by: LehaoLin <linlehao@cuhk.edu.cn>
Co-authored-by: Stable Genius <stablegenius043@gmail.com>
Co-authored-by: Stable Genius <259448942+stablegenius49@users.noreply.github.com>
Co-authored-by: stablegenius49 <185121704+stablegenius49@users.noreply.github.com>
Co-authored-by: Lockinwize Lolite <mzwing@mzwing.eu.org>
Co-authored-by: Waterwzy <2916963017@qq.com>
Co-authored-by: M1LKT <144798909+M1LKT@users.noreply.github.com>
Co-authored-by: Chen <42998804+a61995987@users.noreply.github.com>
Co-authored-by: Frank <97429702+tsubasakong@users.noreply.github.com>
Co-authored-by: bread <104435263+bread-ovO@users.noreply.github.com>
Co-authored-by: Stardust <1441308506a@gmail.com>
Co-authored-by: Vorest <147138388+Vorest3679@users.noreply.github.com>
Co-authored-by: GH <BoneAsh@iCloud.com>
Co-authored-by: Zeng Qingwen <143274079+fishwww-ww@users.noreply.github.com>
Co-authored-by: Rainor_da! <51012640+1zzxy1@users.noreply.github.com>
Co-authored-by: Izayoi9 <105905446+Izayoi9@users.noreply.github.com>
Co-authored-by: naer-lily <88199249+naer-lily@users.noreply.github.com>
Co-authored-by: Naer <88199249+V-YOP@users.noreply.github.com>
Co-authored-by: Yaohua-Leo <3067173925@qq.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

area:provider The bug / feature is about AI Provider, Models, LLM Agent, LLM Agent Runner. lgtm This PR has been approved by a maintainer size:L This PR changes 100-499 lines, ignoring generated files.

Projects

None yet

4 participants