Remove list_files tool

nanocode.py

@@ -1,8 +1,6 @@
 import os
-import glob as globlib
 from modaic import PrecompiledProgram, PrecompiledConfig
 import dspy
-import re
 import subprocess
 from dspy.utils.callback import BaseCallback
 
@@ -36,13 +34,14 @@ def read_file(path: str, offset: int = 0, limit: int = None) -> str:
     Returns:
         File contents with line numbers
     """
-    print(f"{MAGENTA}⏺ Reading file: {path}{RESET}")
-
     lines = open(path).readlines()
     if limit is None:
         limit = len(lines)
     selected = lines[offset : offset + limit]
-    return "".join(f"{offset + idx + 1:4}| {line}" for idx, line in enumerate(selected))
+    content = "".join(f"{offset + idx + 1:4}| {line}" for idx, line in enumerate(selected))
+    tokens = len(content) // 4  # ~4 chars per token estimate
+    print(f"{MAGENTA}⏺ Reading file: {path} (~{tokens:,} tokens){RESET}")
+    return content
 
 
 def write_file(path: str, content: str) -> str:
@@ -53,13 +52,23 @@ def write_file(path: str, content: str) -> str:
         content: Content to write to the file
 
     Returns:
-        'ok' on success
+        Status message with file stats
     """
-    print(f"{MAGENTA}⏺ Creating file: {path}{RESET}")
+    is_new = not os.path.exists(path)
+    action = "Creating" if is_new else "Overwriting"
+
+    # Auto-create parent directories
+    parent = os.path.dirname(path)
+    if parent:
+        os.makedirs(parent, exist_ok=True)
 
     with open(path, "w") as f:
         f.write(content)
-    return "ok"
+
+    lines = content.count("\n") + (1 if content and not content.endswith("\n") else 0)
+    tokens = len(content) // 4
+    print(f"{MAGENTA}⏺ {action} file: {path} ({lines} lines, ~{tokens:,} tokens){RESET}")
+    return f"ok: wrote {lines} lines ({tokens:,} tokens) to {path}"
 
 
 def edit_file(path: str, old: str, new: str, replace_all: bool = False) -> str:
@@ -89,7 +98,9 @@ def edit_file(path: str, old: str, new: str, replace_all: bool = False) -> str:
 
 
 def glob_files(pattern: str, path: str = ".") -> str:
-    """Find files matching a glob pattern, sorted by modification time.
+    """Find files by filename matching a glob pattern, sorted by modification time.
+
+    Respects .gitignore files automatically via ripgrep.
 
     Args:
         pattern: Glob pattern to match (e.g., '**/*.py')
@@ -100,38 +111,49 @@ def glob_files(pattern: str, path: str = ".") -> str:
     """
     print(f"{MAGENTA}⏺ Glob: {pattern}{RESET}")
 
-    full_pattern = (path + "/" + pattern).replace("//", "/")
+    cmd = ["rg", "--files", "-g", pattern, path]
-    files = globlib.glob(full_pattern, recursive=True)
+    try:
-    files = sorted(
+        result = subprocess.run(cmd, capture_output=True, text=True, timeout=30)
-        files,
+        files = result.stdout.strip().split("\n") if result.stdout.strip() else []
-        key=lambda f: os.path.getmtime(f) if os.path.isfile(f) else 0,
+        files = sorted(
-        reverse=True,
+            files,
-    )
+            key=lambda f: os.path.getmtime(f) if os.path.isfile(f) else 0,
-    return "\n".join(files) or "no files found"
+            reverse=True,
+        )
+        return "\n".join(files) or "no files found"
+    except FileNotFoundError:
+        return "error: ripgrep (rg) not installed - install with 'brew install ripgrep'"
+    except subprocess.TimeoutExpired:
+        return "error: search timed out after 30s"
 
 
-def grep_files(pattern: str, path: str = ".") -> str:
+def grep_files(pattern: str, path: str = ".", glob: str = None, max_results: int = 50) -> str:
-    """Search files for a regex pattern.
+    """Search files for a regex pattern using ripgrep.
 
     Args:
         pattern: Regular expression pattern to search for
         path: Base directory to search in
+        glob: Optional glob pattern to filter files (e.g., '*.py')
+        max_results: Maximum number of results to return
 
     Returns:
         Matching lines in format 'filepath:line_num:content'
     """
     print(f"{MAGENTA}⏺ Grep: {pattern}{RESET}")
 
-    regex = re.compile(pattern)
+    cmd = ["rg", "-n", "--no-heading", "--color=never", f"-m{max_results}"]
-    hits = []
+    if glob:
-    for filepath in globlib.glob(path + "/**", recursive=True):
+        cmd.extend(["-g", glob])
-        try:
+    cmd.extend([pattern, path])
-            for line_num, line in enumerate(open(filepath), 1):
+
-                if regex.search(line):
+    try:
-                    hits.append(f"{filepath}:{line_num}:{line.rstrip()}")
+        result = subprocess.run(cmd, capture_output=True, text=True, timeout=30)
-        except Exception:
+        output = result.stdout.strip()
-            pass
+        return output if output else "no matches found"
-    return "\n".join(hits[:50]) or "no matches found"
+    except FileNotFoundError:
+        return "error: ripgrep (rg) not installed - install with 'brew install ripgrep'"
+    except subprocess.TimeoutExpired:
+        return "error: search timed out after 30s"
 
 
 # --- Shell operations ---
@@ -363,11 +385,11 @@ class RLMCodingProgram(PrecompiledProgram):
 if __name__ == "__main__":
     agent = RLMCodingProgram(RLMCodingConfig())
     #agent(task="explicity call llm_query(who is the ceo of apple?) to get the answer to 'who is the ceo of apple?'")
-    branches = ["main", "dev", "prod"]
+    branches = ["dev", "main", "prod"]
     for branch in branches:
         agent.push_to_hub(
             MODAIC_REPO_PATH,
-            commit_message="Fix config override bug by recreating LMs after load_state",
+            commit_message="Remove list_files tool",
             branch=branch,
         )
 

program.json

@@ -4,7 +4,7 @@
     "train": [],
     "demos": [],
     "signature": {
-      "instructions": "You are a concise coding assistant with access to sub agents.\n\nYou are tasked with producing the following outputs given the inputs `task`:\n- {answer}\n\nYou have access to a Python REPL environment. Write Python code and it will be executed. You will see the output, then write more code based on what you learned. This is an iterative process.\n\nAvailable:\n- Variables: `task` (your input data)\n- `llm_query(prompt)` - query a sub-LLM (~500K char capacity) for semantic analysis\n- `llm_query_batched(prompts)` - query multiple prompts concurrently (much faster for multiple queries)\n- `print()` - ALWAYS print to see results\n- `SUBMIT(answer)` - submit final output when done\n- Standard libraries: re, json, collections, math, etc.\n\nIMPORTANT: This is ITERATIVE. Each code block you write will execute, you'll see the output, then you decide what to do next. Do NOT try to solve everything in one step.\n\n1. EXPLORE FIRST - Look at your data before processing it. Print samples, check types/lengths, understand the structure.\n2. ITERATE - Write small code snippets, observe outputs, then decide next steps. State persists between iterations.\n3. VERIFY BEFORE SUBMITTING - If results seem wrong (zeros, empty, unexpected), reconsider your approach.\n4. USE llm_query FOR SEMANTICS - String matching finds WHERE things are; llm_query understands WHAT things mean.\n5. MINIMIZE RETYPING (INPUTS & OUTPUTS) - When values are long, precise, or error-prone (IDs, numbers, code, quotes), re-access them via variables and parse/compute in code instead of retyping. Use small, targeted prints to sanity-check, but avoid manual copying when variables can carry the exact value.\n6. SUBMIT ONLY AFTER SEEING OUTPUTS - SUBMIT ends the current run immediately. If you need to inspect printed output, run it in one step, review the result, then call SUBMIT in a later step.\n\nYou have max 50 sub-LLM calls. When done, call SUBMIT() with your output.\nAdditional tools available (use these instead of standard library equivalents):\n- `read_file(path: str, offset: int, limit: int) -> str` - Read file contents with line numbers.\n- `write_file(path: str, content: str) -> str` - Write content to a file.\n- `edit_file(path: str, old: str, new: str, replace_all: bool) -> str` - Replace text in a file.\n- `glob_files(pattern: str, path: str) -> str` - Find files matching a glob pattern, sorted by modification time.\n- `grep_files(pattern: str, path: str) -> str` - Search files for a regex pattern.\n- `run_bash(cmd: str) -> str` - Run a shell command and return output.",
+      "instructions": "You are a concise coding assistant with access to sub agents.\n\nYou are tasked with producing the following outputs given the inputs `task`:\n- {answer}\n\nYou have access to a Python REPL environment. Write Python code and it will be executed. You will see the output, then write more code based on what you learned. This is an iterative process.\n\nAvailable:\n- Variables: `task` (your input data)\n- `llm_query(prompt)` - query a sub-LLM (~500K char capacity) for semantic analysis\n- `llm_query_batched(prompts)` - query multiple prompts concurrently (much faster for multiple queries)\n- `print()` - ALWAYS print to see results\n- `SUBMIT(answer)` - submit final output when done\n- Standard libraries: re, json, collections, math, etc.\n\nIMPORTANT: This is ITERATIVE. Each code block you write will execute, you'll see the output, then you decide what to do next. Do NOT try to solve everything in one step.\n\n1. EXPLORE FIRST - Look at your data before processing it. Print samples, check types/lengths, understand the structure.\n2. ITERATE - Write small code snippets, observe outputs, then decide next steps. State persists between iterations.\n3. VERIFY BEFORE SUBMITTING - If results seem wrong (zeros, empty, unexpected), reconsider your approach.\n4. USE llm_query FOR SEMANTICS - String matching finds WHERE things are; llm_query understands WHAT things mean.\n5. MINIMIZE RETYPING (INPUTS & OUTPUTS) - When values are long, precise, or error-prone (IDs, numbers, code, quotes), re-access them via variables and parse/compute in code instead of retyping. Use small, targeted prints to sanity-check, but avoid manual copying when variables can carry the exact value.\n6. SUBMIT ONLY AFTER SEEING OUTPUTS - SUBMIT ends the current run immediately. If you need to inspect printed output, run it in one step, review the result, then call SUBMIT in a later step.\n\nYou have max 50 sub-LLM calls. When done, call SUBMIT() with your output.\nAdditional tools available (use these instead of standard library equivalents):\n- `read_file(path: str, offset: int, limit: int) -> str` - Read file contents with line numbers.\n- `write_file(path: str, content: str) -> str` - Write content to a file.\n- `edit_file(path: str, old: str, new: str, replace_all: bool) -> str` - Replace text in a file.\n- `glob_files(pattern: str, path: str) -> str` - Find files by filename matching a glob pattern, sorted by modification time.\n- `grep_files(pattern: str, path: str, glob: str, max_results: int) -> str` - Search files for a regex pattern using ripgrep.\n- `run_bash(cmd: str) -> str` - Run a shell command and return output.",
       "fields": [
         {
           "prefix": "Variables Info:",