agent harness initialize repo

agent-with-tools/tools/__init__.py

@@ -0,0 +1,3 @@
+from tools.registry import get_tool_registry, get_tool_schemas
+
+__all__ = ["get_tool_registry", "get_tool_schemas"]

agent-with-tools/tools/filesystem.py

@@ -0,0 +1,57 @@
+import glob as glob_module
+import re
+from pathlib import Path
+
+
+def read_file(path: str, offset: int = 1, limit: int = 200) -> str:
+    """Read lines from a file, with optional offset and limit."""
+    p = Path(path)
+    if not p.exists():
+        return f"Error: file not found: {path}"
+    lines = p.read_text(errors="replace").splitlines()
+    selected = lines[offset - 1: offset - 1 + limit]
+    return "\n".join(f"{offset + i}: {line}" for i, line in enumerate(selected))
+
+
+def glob_files(pattern: str, path: str = ".") -> str:
+    """Find files matching a glob pattern inside a directory."""
+    matches = glob_module.glob(f"{path}/**/{pattern}", recursive=True)
+    matches += glob_module.glob(f"{path}/{pattern}")
+    unique = sorted(set(matches))
+    return "\n".join(unique) if unique else "(no matches)"
+
+
+def grep(pattern: str, path: str = ".", include: str = "*") -> str:
+    """Search file contents for a regex pattern, optionally filtering by filename glob."""
+    results = []
+    for filepath in glob_module.glob(f"{path}/**/{include}", recursive=True):
+        fp = Path(filepath)
+        if not fp.is_file():
+            continue
+        try:
+            for i, line in enumerate(fp.read_text(errors="replace").splitlines(), 1):
+                if re.search(pattern, line):
+                    results.append(f"{filepath}:{i}: {line}")
+        except OSError:
+            pass
+    return "\n".join(results) if results else "(no matches)"
+
+
+def write_file(path: str, content: str) -> str:
+    """Write content to a file, creating it if it does not exist."""
+    p = Path(path)
+    p.parent.mkdir(parents=True, exist_ok=True)
+    p.write_text(content)
+    return f"Wrote {len(content)} bytes to {path}"
+
+
+def edit_file(path: str, old_string: str, new_string: str) -> str:
+    """Replace the first occurrence of old_string with new_string in a file."""
+    p = Path(path)
+    if not p.exists():
+        return f"Error: file not found: {path}"
+    original = p.read_text()
+    if old_string not in original:
+        return f"Error: string not found in {path}"
+    p.write_text(original.replace(old_string, new_string, 1))
+    return f"Edited {path}"

agent-with-tools/tools/registry.py

@@ -0,0 +1,131 @@
+from tools.filesystem import read_file, glob_files, grep, write_file, edit_file
+from tools.shell import run_bash
+from tools.web import webfetch
+
+
+def get_tool_registry():
+    return {
+        "run_bash":   run_bash,
+        "read_file":  read_file,
+        "glob_files": glob_files,
+        "grep":       grep,
+        "write_file": write_file,
+        "edit_file":  edit_file,
+        "webfetch":   webfetch,
+    }
+
+
+def get_tool_schemas():
+    return [
+        {
+            "type": "function",
+            "function": {
+                "name": "run_bash",
+                "description": "Run a bash command on the user's machine and return the output.",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "command": {
+                            "type": "string",
+                            "description": "The bash command to execute.",
+                        }
+                    },
+                    "required": ["command"],
+                },
+            },
+        },
+        {
+            "type": "function",
+            "function": {
+                "name": "read_file",
+                "description": "Read lines from a file. Returns lines prefixed with line numbers.",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "path": {"type": "string", "description": "Absolute or relative path to the file."},
+                        "offset": {"type": "integer", "description": "First line to read (1-indexed). Defaults to 1."},
+                        "limit": {"type": "integer", "description": "Maximum number of lines to return. Defaults to 200."},
+                    },
+                    "required": ["path"],
+                },
+            },
+        },
+        {
+            "type": "function",
+            "function": {
+                "name": "glob_files",
+                "description": "Find files matching a glob pattern (e.g. '**/*.py') inside a directory.",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "pattern": {"type": "string", "description": "Glob pattern to match against file names."},
+                        "path": {"type": "string", "description": "Root directory to search in. Defaults to '.'."},
+                    },
+                    "required": ["pattern"],
+                },
+            },
+        },
+        {
+            "type": "function",
+            "function": {
+                "name": "grep",
+                "description": "Search file contents for a regex pattern and return matching lines with file paths and line numbers.",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "pattern": {"type": "string", "description": "Regular expression to search for."},
+                        "path": {"type": "string", "description": "Directory to search in. Defaults to '.'."},
+                        "include": {"type": "string", "description": "Filename glob to restrict which files are searched (e.g. '*.py'). Defaults to '*'."},
+                    },
+                    "required": ["pattern"],
+                },
+            },
+        },
+        {
+            "type": "function",
+            "function": {
+                "name": "write_file",
+                "description": "Write content to a file, creating it (and any missing parent directories) if it does not exist.",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "path": {"type": "string", "description": "Path of the file to write."},
+                        "content": {"type": "string", "description": "Full content to write to the file."},
+                    },
+                    "required": ["path", "content"],
+                },
+            },
+        },
+        {
+            "type": "function",
+            "function": {
+                "name": "edit_file",
+                "description": "Replace the first occurrence of a string in a file with a new string.",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "path": {"type": "string", "description": "Path of the file to edit."},
+                        "old_string": {"type": "string", "description": "Exact string to find and replace."},
+                        "new_string": {"type": "string", "description": "String to replace it with."},
+                    },
+                    "required": ["path", "old_string", "new_string"],
+                },
+            },
+        },
+        {
+            "type": "function",
+            "function": {
+                "name": "webfetch",
+                "description": (
+                    "Fetch a public URL (http/https only) and return its full plain-text content (up to 2 MB)."
+                ),
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "url": {"type": "string", "description": "The URL to fetch (http/https)."},
+                    },
+                    "required": ["url"],
+                },
+            },
+        },
+    ]

agent-with-tools/tools/shell.py

@@ -0,0 +1,12 @@
+import subprocess
+
+
+def run_bash(command: str) -> str:
+    """Run a bash command and return its output."""
+    result = subprocess.run(
+        command, shell=True, text=True, capture_output=True
+    )
+    output = result.stdout
+    if result.stderr:
+        output += f"\nSTDERR:\n{result.stderr}"
+    return output or "(no output)"

agent-with-tools/tools/web.py

@@ -0,0 +1,41 @@
+import re
+import urllib.request
+from urllib.parse import urlparse
+
+from bs4 import BeautifulSoup
+
+
+def webfetch(url: str) -> str:
+    """Fetch a URL and return its full plain-text content (up to 2 MB)."""
+    try:
+        parsed = urlparse(url)
+        if parsed.scheme not in ("http", "https"):
+            return f"Error fetching {url}: unsupported scheme '{parsed.scheme}'. Only http and https are allowed."
+        max_bytes = 2 * 1024 * 1024
+        req = urllib.request.Request(url, headers={"User-Agent": "agent/1.0"})
+        with urllib.request.urlopen(req, timeout=15) as resp:
+            content_type = resp.headers.get_content_type()
+            if content_type and content_type not in (
+                "text/html",
+                "text/plain",
+                "application/xhtml+xml",
+            ):
+                return f"Error fetching {url}: unsupported content type '{content_type}'."
+            charset = resp.headers.get_content_charset() or "utf-8"
+            raw_chunks = []
+            total = 0
+            while True:
+                chunk = resp.read(65536)
+                if not chunk:
+                    break
+                total += len(chunk)
+                if total > max_bytes:
+                    raw_chunks.append(chunk[: max_bytes - (total - len(chunk))])
+                    break
+                raw_chunks.append(chunk)
+        raw = b"".join(raw_chunks).decode(charset, errors="replace")
+        soup = BeautifulSoup(raw, "html.parser")
+        text = soup.get_text(separator="\n", strip=True)
+        return re.sub(r"\n{3,}", "\n\n", text).strip()
+    except Exception as e:
+        return f"Error fetching {url}: {e}"