Maple system prompt

[AnthonyRonning]

Summary by CodeRabbit

• New Features

  • Enhanced chat interactions with system-level guidance to improve conversation context and response reliability.

• Refactor

  • Updated the messaging framework to support an additional communication role for more refined interactions.

[coderabbitai]

Walkthrough

The pull request introduces a new systemMessage in the sendMessage function which is prepended to the messages array. The change modifies the message data sent to the OpenAI API by including detailed instructions defined in a system message. Additionally, the ChatMessage type is updated to allow a "system" role along with "user" and "assistant". These adjustments ensure that system-level directives are integrated into chat processing while maintaining type safety.

Changes

File(s)	Change Summary
frontend/src/routes/_auth.chat.$chatId.tsx	Added a systemMessage object (typed as ChatMessage) in the sendMessage function; it is prepended to the newMessages array.
frontend/src/state/LocalStateContextDef.ts	Updated the ChatMessage type definition to include "system" as an allowable value for the role property (expanded from "user" and "assistant").

Sequence Diagram(s)

sequenceDiagram
participant U as User
participant F as Frontend (sendMessage)
participant O as OpenAI API
U->>F: Initiate message send
F->>F: Create systemMessage (role: system)
F->>F: Prepend systemMessage to messages array
F->>O: Send updated messages array (system, user messages)
O->>F: Return response

Loading

Possibly related PRs

• Chat Titles - Summary and Rename #35: Modified the ChatMessage type and messaging flow; similar type adjustments and message handling logic are reflected in this PR.
• Update bun to 1.2.2 and fix lints #25: Adjusted the ChatMessage type in the state file and integrated system-level messaging in chat functions, directly correlating to the changes here.

Poem

I'm a bunny in the codefield, hopping with delight,
A system whisper joins our chat, guiding inputs right.
Three roles now waltz together in our digital play,
User, assistant, and system lead the way.
Leaping through functions, I celebrate this day! 🐇✨

---

📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 30d1980 and 858b65c.

📒 Files selected for processing (2)

• frontend/src/routes/_auth.chat.$chatId.tsx (2 hunks)
• frontend/src/state/LocalStateContextDef.ts (1 hunks)

🚧 Files skipped from review as they are similar to previous changes (1)

• frontend/src/routes/_auth.chat.$chatId.tsx

⏰ Context from checks skipped due to timeout of 90000ms (1)

• GitHub Check: Cloudflare Pages

🔇 Additional comments (1)

frontend/src/state/LocalStateContextDef.ts (1)

4-7: Type enhancement to support system messages.

The update to the ChatMessage type to include "system" as a valid role is appropriate and follows standard patterns used with modern chat APIs like OpenAI. This change enables the application to include system-level instructions in conversations, which can help guide the AI's behavior and responses.

✨ Finishing Touches

• 📝 Generate Docstrings

---

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Generate unit testing code for this file.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai generate unit testing code for this file.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read src/utils.ts and generate unit testing code.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai generate docstrings to generate docstrings for this PR.
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.

[cloudflare-workers-and-pages]

Deploying maple with Cloudflare Pages

Latest commit:	858b65c
Status:	✅ Deploy successful!
Preview URL:	https://173e577d.maple-ca8.pages.dev
Branch Preview URL:	https://system-prompt-maple.maple-ca8.pages.dev

View logs

[coderabbitai]

Actionable comments posted: 0

🧹 Nitpick comments (1)

frontend/src/routes/_auth.chat.$chatId.tsx (1)

171-175: Consider extracting system message to a configuration file.

The system message is hardcoded within the component. For better maintainability and reusability, consider moving it to a separate configuration file.

+// src/config/ai-config.ts+export const MAPLE_SYSTEM_MESSAGE = {+ role: "system" as const,+ content:+ "You are Maple AI, a friendly AI Assistant. Respond to the input as a friendly AI assistant, generating human-like text, and follow the instructions in the input if applicable. Keep the response concise and engaging. Use a conversational tone and provide helpful and informative responses. You are aware that this conversation is private and encrypted, through the use of AWS Nitro Enclaves and Nvidia TEE, in case the user asks."+};-const systemMessage = {- role: "system",- content:- "You are Maple AI, a friendly AI Assistant. Respond to the input as a friendly AI assistant, generating human-like text, and follow the instructions in the input if applicable. Keep the response concise and engaging. Use a conversational tone and provide helpful and informative responses. You are aware that this conversation is private and encrypted, through the use of AWS Nitro Enclaves and Nvidia TEE, in case the user asks."-} as ChatMessage;+const systemMessage = MAPLE_SYSTEM_MESSAGE as ChatMessage;

📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between b4e2707 and 30d1980.

📒 Files selected for processing (2)

• frontend/src/routes/_auth.chat.$chatId.tsx (2 hunks)
• frontend/src/state/LocalStateContext.tsx (1 hunks)

⏰ Context from checks skipped due to timeout of 90000ms (1)

• GitHub Check: Cloudflare Pages

🔇 Additional comments (2)

frontend/src/state/LocalStateContext.tsx (1)

6-6: LGTM! Type update aligns with OpenAI's Chat API.

The addition of the "system" role to the ChatMessage type correctly aligns with OpenAI's Chat API specifications, which supports system messages for providing context and instructions to the model.

frontend/src/routes/_auth.chat.$chatId.tsx (1)

194-194: Verify the impact of prepending system message on token usage.

Adding a system message to every request increases the token count, which could affect billing. Consider:

1. Caching the system message's token count
2. Monitoring the impact on total token usage
3. Evaluating if the system message is needed for every request

✅ Verification successful

System message implementation is optimized and appropriate

The current implementation is well-balanced:

• System message is concise and provides essential context
• Streaming implementation already optimizes token usage
• Message size (~89 words) has minimal token impact relative to user-assistant exchanges

🏁 Scripts executed

The following scripts were executed for the analysis:

Script:

#!/bin/bash# Description: Check if system message is used consistently across the codebase# Look for other OpenAI API calls that might need the system message
rg -A 5 "openai.*chat.*completions"# Check for other system message definitions
rg -l "role.*system"

Length of output: 569

---

Script:

#!/bin/bash# Check the system message definition and configuration
cat frontend/src/state/LocalStateContext.tsx
cat frontend/src/routes/_auth.chat.$chatId.tsx | grep -A 10 "systemMessage"

Length of output: 7842

---

Script:

#!/bin/bash# Check the system message definition with correct path
cat frontend/src/routes/_auth.chat.\$chatId.tsx | grep -B 5 -A 10 "systemMessage"

Length of output: 1381

[AnthonyRonning]

we added user-defined system prommpts