Switch to RLM instead of ReAct

nanocode.py

@@ -1,6 +1,3 @@
-#!/usr/bin/env python3
-"""nanocode-dspy - minimal claude code alternative using DSPy ReAct"""
-
 import os
 import re
 import glob as globlib
@@ -9,6 +6,9 @@ from modaic import PrecompiledProgram, PrecompiledConfig
 import dspy
 from dspy.utils.callback import BaseCallback
 
+# --- Modaic ---
+
+MODAIC_REPO_PATH = "farouk1/nanocode"
 
 # --- ANSI colors ---
 
@@ -22,7 +22,6 @@ YELLOW = "\033[33m"
 RED = "\033[31m"
 MAGENTA = "\033[35m"
 
-
 # --- Display utilities ---
 
 
@@ -172,14 +171,14 @@ def run_bash(cmd: str) -> str:
 # --- Model selection ---
 
 AVAILABLE_MODELS = {
-    "1": ("Claude 3.5 Sonnet", "anthropic/claude-3.5-sonnet"),
-    "2": ("Claude 3.5 Haiku", "anthropic/claude-3.5-haiku"),
-    "3": ("GPT-4o", "openai/gpt-4o"),
-    "4": ("GPT-4o mini", "openai/gpt-4o-mini"),
-    "5": ("Gemini Pro 1.5", "google/gemini-pro-1.5"),
-    "6": ("Llama 3.1 405B", "meta-llama/llama-3.1-405b-instruct"),
-    "7": ("DeepSeek V3", "deepseek/deepseek-chat"),
-    "8": ("Qwen 2.5 72B", "qwen/qwen-2.5-72b-instruct"),
+    "1": ("GPT-5.2 Codex", "openai/gpt-5.2-codex"),
+    "2": ("GPT-5.2", "openai/gpt-5.2"),
+    "3": ("Claude Opus 4.5", "anthropic/claude-opus-4.5"),
+    "4": ("Claude Opus 4", "anthropic/claude-opus-4"),
+    "5": ("Qwen 3 Coder", "qwen/qwen3-coder"),
+    "6": ("Gemini 3 Flash Preview", "google/gemini-3-flash-preview"),
+    "7": ("Kimi K2 0905", "moonshotai/kimi-k2-0905"),
+    "8": ("Minimax M2.1", "minimax/minimax-m2.1"),
 }
 
 
@@ -223,9 +222,6 @@ def select_model():
             exit(1)
 
 
-# --- DSPy Signature ---
-
-
 class CodingAssistant(dspy.Signature):
     """You are a concise coding assistant. Help the user with their coding task by using the available tools to read, write, edit files, search the codebase, and run commands."""
 
@@ -238,9 +234,14 @@ class CodingAssistant(dspy.Signature):
     )
 
 
-# ReAct agent with tools
-
-tools = [read_file, write_file, edit_file, glob_files, grep_files, run_bash]
+tools = {
+    "readfile": read_file,
+    "writefile": write_file,
+    "editfile": edit_file,
+    "globfiles": glob_files,
+    "grepfiles": grep_files,
+    "runbash": run_bash,
+}
 
 
 class ToolLoggingCallback(BaseCallback):
@@ -272,31 +273,44 @@ class ToolLoggingCallback(BaseCallback):
                     print(f"  {MAGENTA}⏺ {call.name}({args_str}){RESET}", flush=True)
 
 
-class AgentConfig(PrecompiledConfig):
-    max_iters: int = 15
+class RLMCodingConfig(PrecompiledConfig):
+    max_iters: int = 20
     lm: str = "openrouter/anthropic/claude-3.5-sonnet"  # Default fallback
+    sub_lm: str = "openrouter/openai/gpt-4.1"  # Default fallback
     api_base: str = "https://openrouter.ai/api/v1"
     max_tokens: int = 16000
+    max_output_chars: int = 100000
+    verbose: bool = False
 
 
-class AgentProgram(PrecompiledProgram):
-    config: AgentConfig
+class RLMCodingProgram(PrecompiledProgram):
+    config: RLMCodingConfig
 
-    def __init__(self, config: AgentConfig, **kwargs):
+    def __init__(self, config: RLMCodingConfig, **kwargs):
         self.config = config
         super().__init__(config, **kwargs)
 
-        # Configure logging callback globally
+        # tool logging for introspections on multi-turn conversations
         dspy.settings.configure(callbacks=[ToolLoggingCallback()])
-
-        agent = dspy.ReAct(
-            CodingAssistant, tools=tools, max_iters=self.config.max_iters
-        )
         lm = dspy.LM(
             self.config.lm,
             api_base=self.config.api_base,
             max_tokens=self.config.max_tokens,
         )
+        sub_lm = dspy.LM(
+            self.config.sub_lm,
+            api_base=self.config.api_base,
+            max_tokens=self.config.max_tokens,
+        )
+        agent = dspy.RLM(
+            CodingAssistant,
+            sub_lm=sub_lm,
+            tools=tools,
+            max_output_chars=self.config.max_output_chars,
+            max_iterations=self.config.max_iters,
+            verbose=self.config.verbose,
+        )
+
         agent.set_lm(lm)
         self.agent = agent
 
@@ -304,12 +318,7 @@ class AgentProgram(PrecompiledProgram):
         assert task, "Task cannot be empty"
         return self.agent(task=task)
 
-
-# --- Main ---
-
-
 def main():
-    """Create AgentConfig with selected model."""
     model = os.getenv("MODEL")
     if model is None:
         model = select_model()
@@ -318,10 +327,10 @@ def main():
     if not model.startswith("openrouter/"):
         model = f"openrouter/{model}"
 
-    config = AgentConfig()
+    config = RLMCodingConfig()
     config.lm = model
 
-    agent = AgentProgram(config)
+    agent = RLMCodingProgram(config)
     print(
         f"{BOLD}nanocode-dspy{RESET} | {DIM}{agent.config.lm} | {os.getcwd()}{RESET}\n"
     )
@@ -376,6 +385,6 @@ def main():
 
 
 if __name__ == "__main__":
-    agent = AgentProgram(AgentConfig(lm="openai/gpt-5.2-codex"))
-    agent.push_to_hub("farouk1/nanocode")
+    agent = RLMCodingProgram(RLMCodingConfig(lm="openai/gpt-5.2-codex"))
+    agent.push_to_hub(MODAIC_REPO_PATH, commit_message="Switch to RLM instead of ReAct", tag="v0.0.1")
     #main()