fix systemprompt bug

[boston008]

fix systemprompt bug
System prompt not send to llm in the chat

Summary by Sourcery

Fix the system prompt not being sent to the LLM by enhancing the message-building logic to conditionally prepend the system prompt and updating sendMessage invocations accordingly.

Enhancements:

• Integrate system prompt into the LLM message sequence by updating sendMessage calls to use buildLLMMessages
• Refactor buildLLMMessages to guard against missing or duplicate system prompt and prepend a constructed system prompt message
• Simplify state updates by standardizing setMessages to use the previous state callback

[sourcery-ai]

Reviewer's guide (collapsed on small PRs)

Reviewer's Guide

Refactors message assembly and send flows to ensure system prompts are always included and to streamline state handling, preventing stale message arrays.

Sequence diagram for sending a chat message with system prompt

sequenceDiagram
actor User
participant LLMChatInterface
participant llmChatService
User->>LLMChatInterface: Submit chat message
LLMChatInterface->>LLMChatInterface: buildLLMMessages([...messages, userMessage])
LLMChatInterface->>llmChatService: sendMessage(selectedProvider, messagesWithSystemPrompt, ...)
llmChatService-->>LLMChatInterface: Response chunk(s)
LLMChatInterface->>LLMChatInterface: Update messages state

Loading

Class diagram for Message and buildLLMMessages changes

classDiagram
class Message {
  +id: string
  +session_id: string
  +content: string
  +sender: string
  +timestamp: string
}
class LLMChatInterface {
  +buildLLMMessages(userMessages: Message[]): Message[]
}
LLMChatInterface --> Message: uses

Loading

File-Level Changes

Change	Details	Files
Simplify message state handling and avoid stale state in send flows	Unified setMessages calls to use functional updates without explicit type annotation Computed messagesForLLM before calling sendMessage in handleSend to capture the correct message array	web/src/pages/chat/llm-chat-interface.tsx
Ensure system prompt is included in every LLM request	Replaced direct updatedMessages arguments with buildLLMMessages results in llmChatService.sendMessage calls Applied buildLLMMessages in both tool result continuation and user send flows	web/src/pages/chat/llm-chat-interface.tsx
Refactor buildLLMMessages to handle system prompt insertion robustly	Added return type annotation and early return when systemPrompt is absent Detected existing system prompt by id to prevent duplication Fixed systemPrompt message fields (session_id fallback, sender as 'user') and updated prepend logic	web/src/pages/chat/llm-chat-interface.tsx

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey @boston008 - I've reviewed your changes - here's some feedback:

• Instead of prepending the system prompt content onto the first user message, consider sending it as a distinct system message with a system sender to preserve clear message semantics and avoid confusing the LLM or downstream logic.
• Revert to using the functional state update form (setMessages(prev => [...prev, userMessage])) when appending messages to avoid potential stale state issues under rapid consecutive updates.
• Remove or conditionally gate the console.debug statements to prevent internal logs from cluttering production consoles.

Prompt for AI Agents

Please address the comments from this code review:
## Overall Comments
- Instead of prepending the system prompt content onto the first user message, consider sending it as a distinct system message with a `system` sender to preserve clear message semantics and avoid confusing the LLM or downstream logic.
- Revert to using the functional state update form (`setMessages(prev => [...prev, userMessage])`) when appending messages to avoid potential stale state issues under rapid consecutive updates.
- Remove or conditionally gate the `console.debug` statements to prevent internal logs from cluttering production consoles.

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[iFurySt]

@boston008 it'd be great if you could use the status to indicate the PR's status. That said, if it's still a WIP, you can switch to draft instead of keeping it open. that way I'll know you are ready to review. thanks!

[sourcery-ai]

Hey @boston008 - I've reviewed your changes and they look great!

Prompt for AI Agents

Please address the comments from this code review:
## Individual Comments

### Comment 1
<location> `web/src/pages/chat/llm-chat-interface.tsx:402` </location>
<code_context>
+      session_id: sessionId || '',
       content: systemPrompt,
-      sender: 'system' as const,
+      sender: 'user',
       timestamp: new Date().toISOString(),
     };
</code_context>

<issue_to_address>
System prompt message is assigned sender 'user' instead of 'system'.

Using 'user' as the sender for a system prompt may lead to misclassification in logic or UI. Consider using 'system' to clearly distinguish system messages.
</issue_to_address>

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}