💄 style: enhance handling of blocked content on Gemini #13270
Conversation
…e handling of blocked content
|
@sxjeru is attempting to deploy a commit to the LobeHub OSS Team on Vercel. A member of the Team first needs to authorize it. |
|
@ONLY-yours @arvinxx - This PR enhances blocked content handling for Gemini streaming, touching the model-runtime stream parser, chat agent executor, and Conversation UI. Please take a look. |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: f16c141f8c
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| if (blockedReason) { | ||
| const convertedUsage = convertGoogleAIUsage(usageMetadata, payload?.pricing); | ||
| const humanFriendlyMessage = getBlockReasonMessage(blockedReason); | ||
|
|
||
| return [ |
There was a problem hiding this comment.
Preserve candidate text when handling blocked finishes
This branch returns usage + error immediately for blocked finishReason, which skips the text/tool parsing paths later in the same function. If Google sends a terminal chunk that includes both finishReason and new content.parts (or a non-streaming single chunk with partial text), the newly generated text is dropped instead of being emitted before the error, so users lose part of the model output.
Useful? React with 👍 / 👎.
There was a problem hiding this comment.
经多次测试，认为末尾块不会包含 content
Codecov Report❌ Patch coverage is Additional details and impacted files@@ Coverage Diff @@
## canary #13270 +/- ##
==========================================
+ Coverage 66.91% 66.94% +0.03%
==========================================
Files 1869 1870 +1
Lines 147974 148158 +184
Branches 14201 16988 +2787
==========================================
+ Hits 99018 99187 +169
- Misses 48845 48860 +15
Partials 111 111
Flags with carried forward coverage won't be shown. Click here to find out more.
🚀 New features to boost your workflow:
|
There was a problem hiding this comment.
Pull request overview
This PR improves the Gemini (Google) streaming UX when content is blocked/truncated by ensuring the interruption reason is surfaced to the user while preserving any partial output that was already streamed.
Changes:
- Emit a
ProviderBizErrorstream event when Google returns a terminal blockedfinishReason(e.g.PROHIBITED_CONTENT), and add/update corresponding tests. - Localize Google blocked-content errors in the agent executor before updating message error state.
- Force the assistant message UI to show errors for Google blocked-content cases even when partial content exists; update copy for Google block-reason messages.
Reviewed changes
Copilot reviewed 7 out of 7 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
| src/store/chat/agents/createAgentExecutors.ts | Localizes Google blocked-content errors before persisting them to message error state. |
| src/store/chat/agents/tests/createAgentExecutors/call-llm.test.ts | Adds coverage ensuring partial output is preserved while error state is updated. |
| src/locales/default/error.ts | Updates default locale strings for Google block reasons. |
| src/features/Conversation/Messages/Assistant/index.tsx | Forces error display for Google blocked-content scenarios even with partial message text. |
| packages/model-runtime/src/core/streams/google/index.ts | Adds handling for blocked terminal candidate finishReason and emits an error event. |
| packages/model-runtime/src/core/streams/google/google-ai.test.ts | Updates expectations and adds a new test for blocked terminal candidate finishReason. |
| packages/model-runtime/src/core/streams/google/const.ts | Updates the human-friendly messages mapped from Google block reasons. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| }, | ||
| onErrorHandle: async (error) => { | ||
| await context.get().optimisticUpdateMessageError(assistantMessageId, error, { | ||
| const localizedError = localizeGoogleBlockedError(error); |
There was a problem hiding this comment.
localizeGoogleBlockedError 太具体了，应该是一个 localizeError
|
❤️ Great PR @sxjeru ❤️ The growth of project is inseparable from user feedback and contribution, thanks for your contribution! If you are interesting with the lobehub developer community, please join our discord and then dm @arvinxx or @canisminor1990. They will invite you to our private developer channel. We are talking about the lobe-chat development or sharing ai newsletter around the world. |
# 🚀 release: 20260326 This release includes **91 commits**. Key updates are below. - **Agent can now execute background tasks** — Agents can perform long-running operations without blocking your conversation. [#13289](#13289) - **Better error messages** — Redesigned error UI across chat and image generation with clearer explanations and recovery options. [#13302](#13302) - **Smoother topic switching** — No more full page reloads when switching topics while an agent is responding. [#13309](#13309) - **Faster image uploads** — Large images are now automatically compressed to 1920px before upload, reducing wait times. [#13224](#13224) - **Improved knowledge base** — Documents are now properly parsed before chunking, improving retrieval accuracy. [#13221](#13221) ### Bot Platform - **WeChat Bot support** — You can now connect LobeChat to WeChat, in addition to Discord. [#13191](#13191) - **Richer bot responses** — Bots now support custom markdown rendering and context injection. [#13294](#13294) - **New bot commands** — Added `/new` to start fresh conversations and `/stop` to halt generation. [#13194](#13194) - **Discord stability fixes** — Fixed thread creation issues and Redis connection drops. [#13228](#13228) [#13205](#13205) ### Models & Providers - **GLM-5** is now available in the LobeHub model list. [#13189](#13189) - **Coding Plan providers** — Added support for code planning assistant providers. [#13203](#13203) - **Tencent Hunyuan 3.0 ImageGen** — New image generation model from Tencent. [#13166](#13166) - **Gemini content handling** — Better handling when Gemini blocks content due to safety filters. [#13270](#13270) - **Claude token limits fixed** — Corrected max window tokens for Anthropic Claude models. [#13206](#13206) ### Skills & Tools - **Auto credential injection** — Skills can now automatically request and use required credentials. [#13124](#13124) - **Smarter tool permissions** — Built-in tools skip confirmation for safe paths like `/tmp`. [#13232](#13232) - **Model switcher improvements** — Quick access to provider settings and visual highlight for default model. [#13220](#13220) ### Memory - **Bulk delete memories** — You can now delete all memory entries at once. [#13161](#13161) - **Per-agent memory control** — Memory injection now respects individual agent settings. [#13265](#13265) ### Desktop App - **Gateway connection** — Desktop app can now connect to LobeHub Gateway for enhanced features. [#13234](#13234) - **Connection status indicator** — See gateway connection status in the titlebar. [#13260](#13260) - **Settings persistence** — Gateway toggle state now persists across app restarts. [#13300](#13300) ### CLI - **API key authentication** — CLI now supports API key auth for programmatic access. [#13190](#13190) - **Shell completion** — Tab completion for bash/zsh/fish shells. [#13164](#13164) - **Man pages** — Built-in manual pages for CLI commands. [#13200](#13200) ### Security - **XSS protection** — Sanitized search result image titles to prevent script injection. [#13303](#13303) - **Workflow hardening** — Fixed potential shell injection in release automation. [#13319](#13319) - **Dependency update** — Updated nodemailer to address security advisory. [#13326](#13326) ### Bug Fixes - Fixed skill page not redirecting correctly after import. [#13255](#13255) [#13261](#13261) - Fixed token counting in group chats. [#13247](#13247) - Fixed editor not resetting when switching to empty pages. [#13229](#13229) - Fixed manual tool toggle not working. [#13218](#13218) - Fixed Search1API response parsing. [#13207](#13207) [#13208](#13208) - Fixed mobile topic menus rendering issues. [#12477](#12477) - Fixed history count calculation for accurate context. [#13051](#13051) - Added missing Turkish translations. [#13196](#13196) ### Credits Huge thanks to these contributors: @bakiburakogun @hardy-one @Zhouguanyang @sxjeru @hezhijie0327 @arvinxx @cy948 @CanisMinor @Innei @lijian @lobehubbot @neko @rdmclin2 @rivertwilight @tjx666
💻 Change Type
🔗 Related Issue
🔀 Description of Change
在 Gemini 输出被截断后正确显示中断原因，此前未显示该报错提示。
🧪 How to Test
📸 Screenshots / Videos
📝 Additional Information