luna/oh-my-opencode
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

refactor(prometheus): align GPT prompt with 5.4 system prompt style

Browse Source 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
This commit is contained in:
YeonGyu-Kim
2026-03-06 13:44:20 +09:00
parent de8e5ea97f
commit 983b4d8ca7
1 changed files with 7 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/agents/prometheus/gpt.ts
+7 -19
View File
@@ -1,24 +1,11 @@
/** /**
* GPT-5.2 Optimized Prometheus System Prompt * GPT-5.4 Optimized Prometheus System Prompt
* *
* Restructured following OpenAI's GPT-5.2 Prompting Guide principles: * Tuned for GPT-5.4 system prompt design principles:
* - XML-tagged instruction blocks for clear structure * - XML-tagged instruction blocks for clear structure
* - Explicit verbosity constraints * - Prose-first output, explicit verbosity constraints
* - Scope discipline (no extra features) * - Scope discipline (no extra features)
* - Tool usage rules (prefer tools over internal knowledge) * - Principle-driven: Decision Complete, Explore Before Asking, Two Kinds of Unknowns
* - Uncertainty handling (explore before asking)
* - Compact, principle-driven instructions
*
* Key characteristics (from GPT-5.2 Prompting Guide):
* - "Stronger instruction adherence" — follows instructions more literally
* - "Conservative grounding bias" — prefers correctness over speed
* - "More deliberate scaffolding" — builds clearer plans by default
* - Explicit decision criteria needed (model won't infer)
*
* Inspired by Codex Plan Mode's principle-driven approach:
* - "Decision Complete" as north star quality metric
* - "Explore Before Asking" — ground in environment first
* - "Two Kinds of Unknowns" — discoverable facts vs preferences
*/ */
export const PROMETHEUS_GPT_SYSTEM_PROMPT = ` export const PROMETHEUS_GPT_SYSTEM_PROMPT = `
@@ -57,6 +44,7 @@ This is your north star quality metric.
- Status updates: 1-2 sentences with concrete outcomes only. - Status updates: 1-2 sentences with concrete outcomes only.
- Do NOT rephrase the user's request unless semantics change. - Do NOT rephrase the user's request unless semantics change.
- Do NOT narrate routine tool calls ("reading file...", "searching..."). - Do NOT narrate routine tool calls ("reading file...", "searching...").
- NEVER open with filler: "Great question!", "That's a great idea!", "You're right to call that out", "Done —", "Got it".
- NEVER end with "Let me know if you have questions" or "When you're ready, say X" — these are passive and unhelpful. - NEVER end with "Let me know if you have questions" or "When you're ready, say X" — these are passive and unhelpful.
- ALWAYS end interview turns with a clear question or explicit next action. - ALWAYS end interview turns with a clear question or explicit next action.
</output_verbosity_spec> </output_verbosity_spec>
@@ -463,8 +451,8 @@ Wave 2: [dependent tasks with categories]
</user_updates_spec> </user_updates_spec>
You are Prometheus, the strategic planning consultant. You bring foresight and structure to complex work through thoughtful consultation. You are Prometheus, the strategic planning consultant. You bring foresight and structure to complex work through thoughtful consultation.
` `;
export function getGptPrometheusPrompt(): string { export function getGptPrometheusPrompt(): string {
return PROMETHEUS_GPT_SYSTEM_PROMPT return PROMETHEUS_GPT_SYSTEM_PROMPT;
} }