scawful/yaze
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Enhance system prompt JSON schema and clarify tool result formatting in conversational agent

Browse Source
This commit is contained in:
scawful
2025-10-04 03:19:28 -04:00
parent 551f926aba
commit 9acd6ba17f
3 changed files with 28 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
assets/agent/system_prompt.txt
View File

@@ -3,19 +3,26 @@ You are an expert ROM hacking assistant for The Legend of Zelda: A Link to the P
Your task is to generate a sequence of z3ed CLI commands to achieve the user's request, or to answer questions about the ROM using available tools. Your task is to generate a sequence of z3ed CLI commands to achieve the user's request, or to answer questions about the ROM using available tools.
# Output Format # Output Format
You MUST respond with ONLY a JSON object with the following structure: You MUST respond with ONLY a JSON object. NO other text before or after the JSON.
**REQUIRED JSON SCHEMA:**
```json
{ {
"text_response": "Your natural language reply to the user.", "text_response": "string (your natural language reply)",
"tool_calls": [{ "tool_name": "tool_name", "args": { "arg1": "value1" } }], "tool_calls": [{"tool_name": "string", "args": {"key": "value"}}],
"commands": ["command1", "command2"], "commands": ["string array of z3ed commands"],
"reasoning": "Your thought process." "reasoning": "string (your thought process)"
} }
```
**CRITICAL:** The field name is `"text_response"` NOT `"response"` NOT `"answer"` NOT anything else.
# CRITICAL RULES: # CRITICAL RULES:
1. If you previously called tools and received [TOOL RESULT], you MUST include text_response with your answer 1. If you previously called tools and received [TOOL RESULT], you MUST include "text_response" with your answer
2. NEVER send an empty text_response after receiving tool results 2. NEVER send an empty "text_response" after receiving tool results
3. NEVER call the same tool twice with the same arguments 3. NEVER call the same tool twice with the same arguments
4. If you have all the information needed to answer, provide text_response WITHOUT calling more tools 4. If you have all the information needed to answer, provide "text_response" WITHOUT calling more tools
5. The field name is `"text_response"` - this exact spelling is REQUIRED
# Tool Calling Workflow (CRITICAL) # Tool Calling Workflow (CRITICAL)

7
src/cli/service/agent/conversational_agent_service.cc
View File

@@ -270,7 +270,12 @@ absl::StatusOr<ChatMessage> ConversationalAgentService::SendMessage(
} }
// Add tool result with a clear marker for the LLM // Add tool result with a clear marker for the LLM
std::string marked_output = "[TOOL RESULT] " + tool_output; // Format as plain text to avoid confusing the LLM with nested JSON
std::string marked_output = absl::StrCat(
"[TOOL RESULT for ", tool_call.tool_name, "]\n",
"The tool returned the following data:\n",
tool_output, "\n\n",
"Please provide a text_response field in your JSON to summarize this information for the user.");
history_.push_back( history_.push_back(
CreateMessage(ChatMessage::Sender::kUser, marked_output)); CreateMessage(ChatMessage::Sender::kUser, marked_output));
} }

7
src/cli/service/ai/ollama_ai_service.cc
View File

@@ -222,6 +222,13 @@ absl::StatusOr<AgentResponse> OllamaAIService::GenerateResponse(
std::string llm_output = ollama_wrapper["response"].get<std::string>(); std::string llm_output = ollama_wrapper["response"].get<std::string>();
// Debug: Print raw LLM output when verbose mode is enabled
const char* verbose_env = std::getenv("Z3ED_VERBOSE");
if (verbose_env && std::string(verbose_env) == "1") {
std::cout << "\n" << "\033[35m" << "🔍 Raw LLM Response:" << "\033[0m" << "\n"
<< "\033[2m" << llm_output << "\033[0m" << "\n\n";
}
// Parse the LLM's JSON response (the agent structure) // Parse the LLM's JSON response (the agent structure)
nlohmann::json response_json; nlohmann::json response_json;
try { try {