🐛 fix: adjust historyCount calculation to include accurate user messages#13051
Merged
Conversation
|
@sxjeru is attempting to deploy a commit to the LobeHub OSS Team on Vercel. A member of the Team first needs to authorize it. |
Contributor
Reviewer's GuideAdjusts how historyCount is interpreted so it represents only prior history messages, with the current user message added separately, and adds tests to verify correct message selection behavior under different historyCount configurations. Sequence diagram for historyCount-based message preparationsequenceDiagram
actor User
participant UI
participant ChatService
participant AgentRuntimeService
participant ContextEngineering
participant LLMProvider
User->>UI: Submit current user message
UI->>ChatService: createAssistantMessage(messages, model, provider, resolvedAgentConfig)
ChatService->>ContextEngineering: buildLlmMessages(enableHistoryCount, historyCount + 1, inputTemplate, messages)
ContextEngineering-->>ChatService: llmMessages (system date + selected history + current user)
ChatService->>LLMProvider: getChatCompletion(llmMessages)
LLMProvider-->>ChatService: assistant response
User->>AgentRuntimeService: Trigger agent runtime chat
AgentRuntimeService->>ContextEngineering: buildLlmMessages(enableHistoryCount, historyCount + 1, inputTemplate, messages)
ContextEngineering-->>AgentRuntimeService: llmMessages (system date + selected history + current user)
AgentRuntimeService->>LLMProvider: getChatCompletion(llmMessages)
LLMProvider-->>AgentRuntimeService: assistant response
Class diagram for ChatService and AgentRuntimeService historyCount usageclassDiagram
class ChatService {
+createAssistantMessage(messages, model, provider, resolvedAgentConfig)
+getChatCompletion(request)
}
class AgentRuntimeService {
+runWithContextEngineering(dataMessages, agentStoreState, chatConfig, modelRuntimeConfig)
}
class ContextEngineering {
+buildLlmMessages(enableHistoryCount, historyCount, inputTemplate, messages, modelRuntimeConfig)
}
ChatService --> ContextEngineering : uses historyCount_plus_1
AgentRuntimeService --> ContextEngineering : uses historyCount_plus_1
Flow diagram for message selection with historyCountflowchart TD
A[Start createAssistantMessage] --> B[Add system date message]
B --> C[Check enableHistoryCount]
C -->|false| D[Include all user and assistant messages]
D --> Z[Send messages to LLM]
C -->|true| E[Read historyCount]
E -->|0| F[Select only current user message]
F --> Z
E -->|>0| G[Select last historyCount user and assistant messages]
G --> H[Append current user message]
H --> Z[Send messages to LLM]
File-Level Changes
Possibly linked issues
Tips and commandsInteracting with Sourcery
Customizing Your ExperienceAccess your dashboard to:
Getting Help
|
Contributor
There was a problem hiding this comment.
Hey - I've left some high level feedback:
- The
historyCountoffset logic (+ 1for current user) is duplicated in bothAgentRuntimeServiceandChatService; consider extracting a shared helper or clearly centralizing this calculation so future changes don’t diverge between call sites. - In the new
historyCounttests, before accessinggetChatCompletionSpy.mock.calls[0], consider asserting that the spy was called exactly once to make the tests more robust against future internal changes.
Prompt for AI Agents
Please address the comments from this code review:
## Overall Comments
- The `historyCount` offset logic (`+ 1` for current user) is duplicated in both `AgentRuntimeService` and `ChatService`; consider extracting a shared helper or clearly centralizing this calculation so future changes don’t diverge between call sites.
- In the new `historyCount` tests, before accessing `getChatCompletionSpy.mock.calls[0]`, consider asserting that the spy was called exactly once to make the tests more robust against future internal changes.Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.
Contributor
There was a problem hiding this comment.
Pull request overview
This PR fixes how historyCount is calculated when preparing messages for contextEngineering, so that a configured historyCount represents only historical messages and the request still includes the current user message (without unintentionally pulling in the last assistant message when historyCount = 0).
Changes:
- Adjust
historyCountpassed intocontextEngineeringfrom+ 2to+ 1(to account for the current user message only). - Apply the same fix in both the main
ChatServiceflow and theAgentRuntimeServiceflow. - Add unit tests validating message slicing behavior for enabled/disabled
historyCount, including thehistoryCount = 0edge case.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| src/services/chat/index.ts | Fixes historyCount calculation for chat message preprocessing so 0 history doesn’t include prior assistant messages. |
| src/services/chat/chat.test.ts | Adds tests to assert correct message count/ordering for history enabled/disabled and historyCount = 0. |
| src/services/agentRuntime/index.ts | Keeps agent runtime behavior consistent with ChatService by applying the same historyCount + 1 logic. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Codecov Report❌ Patch coverage is Additional details and impacted files@@ Coverage Diff @@
## canary #13051 +/- ##
=========================================
Coverage ? 74.67%
=========================================
Files ? 1488
Lines ? 121964
Branches ? 14086
=========================================
Hits ? 91081
Misses ? 30771
Partials ? 112
Flags with carried forward coverage won't be shown. Click here to find out more.
🚀 New features to boost your workflow:
|
12 tasks
Member
|
❤️ 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. |
Merged
ONLY-yours
added a commit
that referenced
this pull request
Mar 27, 2026
# 🚀 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
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
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.
💻 Change Type
🔗 Related Issue
🔀 Description of Change
目前当附带历史消息数为 0 时，实际会携带 3 条 message ，包括 system + 最近一条 assistance + user
理论上不应该携带任何 assistance 消息才对。
包括设为 1 时会携带两条历史消息。
🧪 How to Test
📸 Screenshots / Videos
📝 Additional Information
Summary by Sourcery
Adjust chat history trimming logic so historyCount represents only prior messages and ensure the current user message is always included once.
Bug Fixes:
Tests: