* fix: adapt MiMo STT to V2.5 models and reject non-WAV audio
The MiMo-V2 series went offline on 2026-06-30, so the default STT model
mimo-v2-omni fails for every default configuration. Switch the default
to mimo-v2.5-asr, the dedicated speech recognition model whose official
docs use exactly the bare input_audio payload this provider sends.
For non-ASR multimodal models such as mimo-v2.5, the audio understanding
docs require a text instruction alongside the audio, so restore the
system/user transcription prompts for that model family only.
Also validate that the resolved audio payload really is RIFF/WAVE before
calling the API: when a platform voice file (e.g. Tencent SILK from QQ)
slips through the WAV conversion chain unchanged, fail locally with an
actionable error instead of the opaque HTTP 400 from the API.
Fixes#9113
* fix: accept unpadded MiMo wav headers
---------
Co-authored-by: tangtaizong666 <212687958+tangtaizong666@users.noreply.github.com>
* fix: preserve assistant messages with reasoning_content in sanitize pass
When _sanitize_assistant_messages encounters an assistant message with empty content and no tool_calls but with reasoning_content, keep it with content set to empty string instead of dropping it. Reasoning models (DeepSeek V4, MiMo, etc.) require this history for subsequent turn validation.
* Update astrbot/core/provider/sources/openai_source.py
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
* fix: default to empty TokenUsage when completion.usage is None
When completion.usage is None (e.g. certain proxy/streaming edge cases), llm_response.usage stayed unset (None). Plugins accessing .input_tokens on it would crash with AttributeError.
Always assign llm_response.usage — extract from completion.usage if present, otherwise fall back to a zeroed TokenUsage().
Closes#8605
---------
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: renchonghan <renchonghan@users.noreply.github.com>
* sanitize orphaned tool_result blocks in Anthropic provider
Sanitize tool_result blocks and merge consecutive messages with the same role to comply with Anthropic API requirements.
* Fix content handling in message merging logic
* fix: sanitize anthropic assistant messages
* fix: validate anthropic tool result ordering
---------
Co-authored-by: Soulter <905617992@qq.com>
* fix: tool definition does not pass back to gemini properly, causing repeated tool calls.
fixes: #8789fixes: #8773fixes: #7111fixes: #6402fixes: #7684
* fix: remove unnecessary logging and improve log messages in Gemini source
* fix: improve type checking for tool calls in Google Gemini provider
* fix: unify media reference handling
* fix: accept bare base64 record media refs
* chore: update agents.md
* fix: unify file URI handling across media components and utilities
* fix: unify media reference type handling with MediaRefStr alias
* Potential fix for pull request finding 'CodeQL / Incomplete URL substring sanitization'
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Update astrbot/core/platform/sources/discord/discord_platform_adapter.py
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
* fix: unify media handling and improve base64 decoding across components
* fix: simplify client_kwargs type definition and enhance media message handling in platform adapter
* fix: unify media utility documentation and enhance function descriptions
* perf: drop "pilk" requirement, improve audio outbound for tencent-related IM apps which using silk
* fix: unify Tencent Silk audio handling and enhance media resolver functionality
---
- Centralize media reference materialization and base64 resolution for local paths, http(s), base64://, data URIs, and legacy bare base64 payloads.
- Normalize incoming Record audio to wav and Image media to temporary jpg during preprocess, with event-scoped cleanup.
- Reuse the shared media resolver across OpenAI, Gemini, Anthropic, MiMo, DeerFlow, STT, and platform media paths while sanitizing logs and cleaning temporary conversion outputs.
- Ensure generated TTS audio is tracked for cleanup after the event finishes.
fix#8676fix#8543fix#7588fix#7580fix#8030fix#8034fix#7461fix#7565fix#6509fix#7144fix#7795
---------
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
* fix(context): restore turn cap, serialize content parts and tool calls for llm compress, fix AftCompact debug log
Three context-compaction regression fixes after #8226:
1. Restore max_context_length -> enforce_max_turns propagation so
normal turn-based truncation works again.
2. Serialize ContentPart and ToolCall objects into plain dicts in
_message_to_dict so llm_compress no longer fails with JSON
serialization errors.
3. Print _provider_messages (compacted) instead of run_context.messages
(unchanged) in AftCompact debug log; truncate long role lists to
first4,...,last4 to avoid log spam.
Assertions in tests are also hardened to avoid coupling to exact prompt
wording.
* fix(tool_loop_agent_runner): simplify context handling by removing redundant provider messages
* fix(tool_loop_agent_runner): rename context manager variables for clarity
* fix: update context compression to use recent token ratio instead of fixed count
* fix: enhance LLMSummaryCompressor to sanitize contexts and improve message handling
* ruff format
---------
Co-authored-by: Soulter <905617992@qq.com>
* fix(provider): wrap batch embedding texts in Content to avoid collapse on gemini-embedding-2
* fix(gemini_embedding): format list comprehension for better readability
---------
Co-authored-by: Rat0323 <Rat0323@users.noreply.github.com>
Co-authored-by: Soulter <905617992@qq.com>
Set MiniMax-M3 as the default fallback model for the Token Plan provider.
The model list itself is already fetched dynamically from the MiniMax API,
so all available models including M3 are auto-discovered. This change just
updates the hardcoded fallback used when no model is configured to the
current flagship.
MiniMax-M2.7 remains fully usable; users can still configure it explicitly.
* fix: handle delta=None chunks in streaming to prevent SDK to_dict() error
When certain OpenAI-compatible providers (Gemini, DeepSeek, some proxies)
return chunks with choice.delta=None (e.g. ContentBlockDeltaEvent),
ChatCompletionStreamState._convert_initial_chunk_into_snapshot internally
calls choice.delta.to_dict() at line 747, causing:
'NoneType' object has no attribute 'to_dict'
Fix:
1. Skip handle_chunk when delta is None (delta=None chunks have no
content contribution anyway)
2. Wrap get_final_completion in try/except to gracefully fall back to
empty ChatCompletion if SDK state is corrupted
Refs: openai-python#5069, openai-python#5047
* fix: resolve bugs found by Sourcery and gemini-code-assist review
- Remove orphan logger.error that caused NameError on every chunk
- Replace broken empty ChatCompletion fallback with clean return;
streamed content already yielded, no data loss
Co-authored-by: sourcery-ai[bot] <sourcery-ai[bot]@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <gemini-code-assist[bot]@users.noreply.github.com>
* fix: properly replace get_final_completion fallback in _query_stream
Previous fix_pr_v3 wrongly injected code into terminate() instead.
Now correctly:
1. Replace empty ChatCompletion fallback with clean return in _query_stream
2. Revert terminate() to original (await self.client.close() only)
* fix: revert corrupted terminate() to original
Previous fix_pr_v3 injected wrong-indentation code into terminate().
---------
Co-authored-by: sourcery-ai[bot] <sourcery-ai[bot]@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <gemini-code-assist[bot]@users.noreply.github.com>
* fix: handle None tool arguments returned by Claude API for no-parameter tools
* fix: handle None tool arguments from Claude API for no-parameter tools
* fix: generalize None tool args comment
* fix: generalize None tool args comment
* 去除空格，以保证格式正确
When both aiohttp and httpx are installed, google-genai prefers aiohttp
as the async HTTP backend. In error response paths, the aiohttp backend
returns raw aiohttp.ClientResponse objects that google-genai cannot handle,
masking real API errors with:
Unsupported response type: <class 'aiohttp.client_reqrep.ClientResponse'>
This fix explicitly creates an httpx.AsyncClient and passes it via
HttpOptions.httpx_async_client, ensuring the chat provider always uses
the httpx backend. The managed client is closed in terminate().
- Preserve HTTP_PROXY/HTTPS_PROXY support via trust_env=True.
- Preserve provider-level proxy via httpx.AsyncClient(proxy=...).
- Avoid logging full proxy URLs for security.
Fixes#7564
* fix(provider): fix Anthropic custom headers and system prompt compatibility
- Pass custom_headers via AsyncAnthropic's `default_headers` parameter
instead of creating a separate httpx.AsyncClient. This avoids
`isinstance` check failures when multiple httpx installations exist
on sys.path (e.g. bundled Python + system Python).
- Use list format for the `system` parameter (`[{"type": "text", ...}]`)
instead of a plain string. The list format is supported by the official
Anthropic API and is also compatible with third-party API proxies that
reject the string format.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(provider): fix Anthropic custom headers and system prompt compatibility
- Pass custom_headers via AsyncAnthropic's `default_headers` parameter
instead of creating a separate httpx.AsyncClient. This avoids
`isinstance` check failures when multiple httpx installations exist
on sys.path (e.g. bundled Python + system Python).
- Use list format for the `system` parameter (`[{"type": "text", ...}]`)
instead of a plain string. The list format is supported by the official
Anthropic API and is also compatible with third-party API proxies that
reject the string format.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Add test unit
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: 压缩算法删除 user 消息 Bug 修复
* perf: improve truncate algo
* fix: improve context length error detection for PPIO platform compatibility
- Extend error detection to handle PPIO's error message format:
'The input is longer than the model's context length'
- Add case-insensitive matching using .lower() for robustness
- Maintain backward compatibility with existing 'maximum context length' check
This fixes the issue where PPIO platform models (e.g., ppio/zai-org/glm-5-turbo)
would fail with AgentState.ERROR due to unrecognized context length errors.
---------
Co-authored-by: Soulter <905617992@qq.com>
* fix: update reasoning_content handling to support empty string values
* fix: add reasoning_content field for DeepSeek v4 models in assistant messages
PR #7202 added empty-assistant filtering in `_query` so strict
providers (Moonshot, etc.) wouldn't 400 on history with blank
assistant entries. The streaming sibling `_query_stream` was
never updated, so DeepSeek Reasoner — which returns reasoning only
during tool calls, leaving serialized content as `""` — blew up with
`Invalid assistant message: content or tool_calls must be set` on
the next turn.
Hoisted the filter into a `_sanitize_assistant_messages` helper and
called it from both paths. Also widened the empty check to cover
`content == []`, which the original filter missed and which shows up
with providers that emit content as a list of parts.
* perf: improve tool calls in reasoning and multiple tool calls display
- Updated LiveChatRoute and OpenApiRoute to replace manual message accumulation with BotMessageAccumulator.
- Simplified message saving logic by using build_bot_history_content and collect_plain_text_from_message_parts.
- Enhanced message processing to handle various message types (plain, image, record, file, video) more efficiently.
- Improved reasoning handling by extracting thinking parts and displaying them correctly in the UI components.
- Refactored message normalization and reasoning extraction logic in useMessages composable for better clarity and maintainability.
- Updated ChatMessageList, MessageList, StandaloneChat, and ReasoningBlock components to accommodate new message structure and rendering logic.
* feat(chat): reasoning activity panel
- Introduced a new ReasoningSidebar component for displaying reasoning details.
- Refactored MessageList and StandaloneChat components to utilize renderBlocks for improved message part handling.
- Added ReasoningTimeline component to visualize reasoning steps.
- Updated message handling logic to differentiate between thinking and content blocks.
- Enhanced localization for reasoning-related terms in English, Russian, and Chinese.
- Improved styling for various components to ensure consistency and readability.
* Update astrbot/dashboard/routes/chat.py
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>
Improve robustness of tool call handling in OpenAI completions and agent tool loop by avoiding premature filtering and surfacing clearer errors when tools are missing.
* Refactor tool call argument handling in openai_source.py
* Improve error logging for missing tools
Log available tools when a specified tool is not found.
* feat: add MiniMax Token Plan provider with hardcoded model list (fix#7585)
- Add new provider 'minimax_token_plan' for MiniMax Token Plan users
- Inherit ProviderAnthropic to reuse all chat/completion logic
- Hardcode api_base to https://api.minimaxi.com/anthropic
- get_models() returns hardcoded list: MiniMax-M2.7, M2.5, M2.1, M2
- Highspeed models excluded (require premium tier)
- Reason for hardcoding: Token Plan API does not expose /models endpoint
- Fixes: https://github.com/AstrBotDevs/AstrBot/issues/7585
* fix: remove api_base from config template and add model validation
- Remove api_base from default_config_tmpl (always overridden, misleading)
- Add model validation against MINIMAX_TOKEN_PLAN_MODELS
- Raise clear ValueError if user configures an unsupported model
Addressed Sourcery AI review comments.
* fix: use custom_headers for Bearer token auth instead of auth_header
MiniMax Token Plan requires Authorization: Bearer <token> header.
Use custom_headers to inject the correct auth header instead of
the non-functional auth_header key.
Addressed Gemini Code Assist review comment.
* fix: update MiniMax Token Plan provider adapter and documentation to English
* feat: add MiniMax Token Plan configuration and icon support
* feat: remove default configuration template from MiniMax Token Plan provider adapter
---------
Co-authored-by: Soulter <905617992@qq.com>
