root/fusion
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(FN-4186): complete Step 1 — tighten chat prompt brevity guidance

Browse Source 
Fusion-Task-Id: FN-4186
Fusion-Task-Lineage: 30721f11-a830-4549-aa91-d8c3186c0dcf
This commit is contained in:
Fusion
2026-05-13 19:52:22 -07:00
committed by gsxdsm
parent 72ccff09ef
commit 85fbb642c0
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
packages/dashboard/src/chat.ts
View File

@@ -125,9 +125,9 @@ async function ensureEngineReady(): Promise<void> {
// ── Constants ───────────────────────────────────────────────────────────────
/** Chat system prompt for the AI agent */
const CHAT_SYSTEM_PROMPT = `You are a helpful AI assistant integrated into the fn task board system. You help users with questions about their project, code, architecture, and tasks. You have access to project files and can read them to provide informed responses. Be concise, accurate, and helpful. When referencing files or code, provide specific paths and line numbers when possible.`;
const CHAT_SYSTEM_PROMPT = `You are a helpful AI assistant integrated into the fn task board system. You help users with questions about their project, code, architecture, and tasks. You have access to project files and can read them to provide informed responses, including referencing specific file paths and line numbers when possible. Response length policy: default to a short, crisp reply (a few sentences or a short bulleted list) that directly answers the user; avoid preamble, restating the question, and filler. If a thorough answer genuinely needs long-form content (for example multi-step plans, design proposals, deep analyses, or long file excerpts), keep the chat reply brief with a one- or two-sentence summary and then send the full write-up via \`fn_send_message\` using \`type: "agent-to-user"\` and \`to_id: "dashboard"\`. That mailbox follow-up must add new substantive detail and must not duplicate the chat reply.`;
const CHAT_AGENT_MESSAGE_ROUTING_GUIDANCE = `## Messaging Semantics\n\nYour chat reply is the primary response to the user. Do not also call \`fn_send_message\` with the same content just to mirror your chat response into mailbox.\n\nOnly use \`fn_send_message\` when the user explicitly asks for mailbox/inbox/notification delivery (for example: "send me this in mail", "ntfy me when…", or "leave me a note in my inbox"). In that explicit-request case, send with \`type: "agent-to-user"\` and target the dashboard user alias (\`to_id: "dashboard"\` is preferred). Never route that as a user/CLI → agent message.`;
const CHAT_AGENT_MESSAGE_ROUTING_GUIDANCE = `## Messaging Semantics\n\nYour chat reply is the primary response to the user. Do not also call \`fn_send_message\` with the same content just to mirror your chat response into mailbox.\n\nUse \`fn_send_message\` only when either (a) the user explicitly asks for mailbox/inbox/notification delivery (for example: "send me this in mail", "ntfy me when…", or "leave me a note in my inbox"), or (b) you are sending a genuinely longer follow-up that did not fit in a short chat reply. In either case, send with \`type: "agent-to-user"\` and target the dashboard user alias (\`to_id: "dashboard"\` is preferred), and ensure the mailbox message is additive rather than a duplicate of the chat reply. Never route that as a user/CLI → agent message.`;
/** Rate limiting window in milliseconds (1 minute) */
const RATE_LIMIT_WINDOW_MS = 60 * 1000;