meeting-room/meeting_room/tools.py

"""
Tools system for Meeting Room agents.
Provides file access and web capabilities via OpenAI function calling.

The ToolRegistry class encapsulates all tool logic with a configurable
workdir. Module-level wrappers maintain backward compatibility.
"""

import fnmatch
import httpx
import json
import os
import re
import subprocess


# ─── Tool schemas (OpenAI function calling format) ───

TOOL_SCHEMAS = [
    {
        "type": "function",
        "function": {
            "name": "read_file",
            "description": "Read file contents. Returns text with line numbers.",
            "parameters": {
                "type": "object",
                "properties": {
                    "path": {"type": "string", "description": "Path to the file"},
                    "offset": {"type": "integer", "description": "Start from this line (1-indexed)", "default": 1},
                    "limit": {"type": "integer", "description": "Maximum number of lines", "default": 100},
                },
                "required": ["path"],
            },
        },
    },
    {
        "type": "function",
        "function": {
            "name": "list_files",
            "description": "List files and directories.",
            "parameters": {
                "type": "object",
                "properties": {
                    "path": {"type": "string", "description": "Directory to list"},
                    "pattern": {"type": "string", "description": "Filter by name (glob)"},
                    "max_depth": {"type": "integer", "description": "Traversal depth", "default": 3},
                },
                "required": [],
            },
        },
    },
    {
        "type": "function",
        "function": {
            "name": "search_in_files",
            "description": "Search text in files (regex).",
            "parameters": {
                "type": "object",
                "properties": {
                    "query": {"type": "string", "description": "Search query (regex)"},
                    "path": {"type": "string", "description": "Directory to search in"},
                    "file_pattern": {"type": "string", "description": "Filter by extension (e.g. *.py)"},
                },
                "required": ["query"],
            },
        },
    },
    {
        "type": "function",
        "function": {
            "name": "web_search",
            "description": "Search the web. Returns titles, snippets and URLs.",
            "parameters": {
                "type": "object",
                "properties": {
                    "query": {"type": "string", "description": "Search query"},
                    "max_results": {"type": "integer", "description": "Maximum results", "default": 5},
                },
                "required": ["query"],
            },
        },
    },
    {
        "type": "function",
        "function": {
            "name": "web_fetch",
            "description": "Fetch web page content.",
            "parameters": {
                "type": "object",
                "properties": {
                    "url": {"type": "string", "description": "URL to fetch"},
                    "max_length": {"type": "integer", "description": "Maximum characters", "default": 5000},
                },
                "required": ["url"],
            },
        },
    },
    {
        "type": "function",
        "function": {
            "name": "write_file",
            "description": "Write content to a file.",
            "parameters": {
                "type": "object",
                "properties": {
                    "path": {"type": "string", "description": "Path to the file"},
                    "content": {"type": "string", "description": "Content to write"},
                },
                "required": ["path", "content"],
            },
        },
    },
    {
        "type": "function",
        "function": {
            "name": "run_command",
            "description": "Run a shell command.",
            "parameters": {
                "type": "object",
                "properties": {
                    "command": {"type": "string", "description": "Command to run"},
                    "timeout": {"type": "integer", "description": "Timeout in seconds", "default": 30},
                },
                "required": ["command"],
            },
        },
    },
]

# Directories to skip during file traversal
_SKIP_DIRS = {".git", ".venv", "venv", "node_modules", "__pycache__", ".mypy_cache", ".pytest_cache"}

# Tool set definitions
TOOL_SETS = {
    "all":      ["read_file", "list_files", "search_in_files", "web_search", "web_fetch", "write_file", "run_command"],
    "full":     ["read_file", "list_files", "search_in_files", "web_search", "web_fetch", "write_file", "run_command"],
    "files":    ["read_file", "list_files", "search_in_files", "write_file"],
    "readonly": ["read_file", "list_files", "search_in_files"],
    "web":      ["web_search", "web_fetch"],
    "none":     [],
}


def _truncate(text: str, max_len: int = 5000) -> str:
    if len(text) <= max_len:
        return text
    return text[:max_len] + f"\n... [truncated, {len(text)} chars total]"


class ToolRegistry:
    """Manages tool schemas and execution for a given working directory."""

    def __init__(self, workdir: str = ".") -> None:
        self._workdir = os.path.abspath(workdir)

    # ── Path resolution ──

    def _resolve_path(self, path: str) -> str:
        if os.path.isabs(path):
            return path
        return os.path.normpath(os.path.join(self._workdir, path))

    # ── Schema / dispatch ──

    def get_tool_schemas(self, tool_set: str | list = "all") -> list[dict]:
        if isinstance(tool_set, list):
            names = tool_set
        else:
            names = TOOL_SETS.get(tool_set, TOOL_SETS["all"])
        return [s for s in TOOL_SCHEMAS if s["function"]["name"] in names]

    def execute_tool(self, name: str, arguments: dict) -> str:
        method_map = {
            "read_file":      self.tool_read_file,
            "list_files":      self.tool_list_files,
            "search_in_files": self.tool_search_in_files,
            "web_search":      self.tool_web_search,
            "web_fetch":       self.tool_web_fetch,
            "write_file":      self.tool_write_file,
            "run_command":     self.tool_run_command,
        }
        func = method_map.get(name)
        if not func:
            return f"Unknown tool: {name}"
        try:
            return func(**arguments)
        except Exception as e:
            return f"Error executing {name}: {e}"

    # ── Tool implementations ──

    def tool_read_file(self, path: str, offset: int = 1, limit: int = 100) -> str:
        resolved = self._resolve_path(path)
        if not os.path.isfile(resolved):
            return f"Error: file not found — {resolved}"
        try:
            with open(resolved, encoding="utf-8", errors="replace") as f:
                lines = f.readlines()
            total = len(lines)
            selected = lines[offset - 1 : offset - 1 + limit]
            result = "".join(f"{i}|{line}" for i, line in enumerate(selected, start=offset))
            return _truncate(f"[{resolved} — {total} lines]\n{result}")
        except Exception as e:
            return f"Error reading file: {e}"

    def tool_list_files(self, path: str = "", pattern: str = "", max_depth: int = 3) -> str:
        base = self._resolve_path(path or ".")
        if not os.path.isdir(base):
            return f"Error: directory not found — {base}"
        try:
            results: list[str] = []
            base_depth = base.count(os.sep)
            for dirpath, dirnames, filenames in os.walk(base):
                # Prune skipped directories in-place so os.walk skips them
                dirnames[:] = [d for d in dirnames if d not in _SKIP_DIRS]
                # Check depth
                current_depth = dirpath.count(os.sep) - base_depth
                if current_depth >= max_depth:
                    # Don't descend further, but still list this dir's files
                    dirnames.clear()
                # Add directory itself
                rel_dir = os.path.relpath(dirpath, base)
                if rel_dir == ".":
                    results.append(dirpath)
                else:
                    results.append(dirpath)
                # Add files
                for fname in filenames:
                    if pattern and not fnmatch.fnmatch(fname, pattern):
                        continue
                    results.append(os.path.join(dirpath, fname))
            results.sort()
            return _truncate("\n".join(results))
        except Exception as e:
            return f"Error: {e}"

    def tool_search_in_files(self, query: str, path: str = "", file_pattern: str = "") -> str:
        base = self._resolve_path(path or ".")
        if not os.path.isdir(base):
            return f"Error: directory not found — {base}"
        try:
            regex = re.compile(query, re.IGNORECASE)
        except re.error as e:
            return f"Error: invalid regex — {e}"
        try:
            results: list[str] = []
            for dirpath, dirnames, filenames in os.walk(base):
                dirnames[:] = [d for d in dirnames if d not in _SKIP_DIRS]
                for fname in filenames:
                    if file_pattern and not fnmatch.fnmatch(fname, file_pattern):
                        continue
                    fpath = os.path.join(dirpath, fname)
                    try:
                        with open(fpath, encoding="utf-8", errors="replace") as f:
                            for line_num, line in enumerate(f, start=1):
                                if regex.search(line):
                                    results.append(f"{fpath}:{line_num}:{line.rstrip()}")
                                    if len(results) >= 200:
                                        return _truncate("\n".join(results))
                    except (OSError, UnicodeDecodeError):
                        continue
            if not results:
                return "No matches found."
            return _truncate("\n".join(results))
        except Exception as e:
            return f"Error: {e}"

    def tool_web_search(self, query: str, max_results: int = 5) -> str:
        try:
            client = httpx.Client(timeout=15, follow_redirects=True)
            resp = client.get(
                "https://html.duckduckgo.com/html/",
                params={"q": query},
                headers={"User-Agent": "Mozilla/5.0"},
            )
            resp.raise_for_status()
            results = []
            for match in re.finditer(
                r'<a rel="nofollow" class="result__a" href="([^"]+)">\s*(.*?)\s*</a>.*?'
                r'<a class="result__snippet".*?>(.*?)</a>',
                resp.text, re.DOTALL,
            ):
                url = match.group(1)
                title = re.sub(r'<[^>]+>', '', match.group(2)).strip()
                snippet = re.sub(r'<[^>]+>', '', match.group(3)).strip()
                results.append(f"{title}\n  {url}\n  {snippet}")
                if len(results) >= max_results:
                    break
            if not results:
                return "No results found."
            return _truncate("\n\n".join(f"[{i+1}] {r}" for i, r in enumerate(results)))
        except Exception as e:
            return f"Search error: {e}"

    def tool_web_fetch(self, url: str, max_length: int = 5000) -> str:
        try:
            client = httpx.Client(timeout=20, follow_redirects=True)
            resp = client.get(url, headers={"User-Agent": "Mozilla/5.0"})
            resp.raise_for_status()
            content_type = resp.headers.get("content-type", "")
            if "html" in content_type:
                text = re.sub(r'<script[^>]*>.*?</script>', '', resp.text, flags=re.DOTALL)
                text = re.sub(r'<style[^>]*>.*?</style>', '', text, flags=re.DOTALL)
                text = re.sub(r'<[^>]+>', ' ', text)
                text = re.sub(r'\s+', ' ', text).strip()
            else:
                text = resp.text
            return _truncate(f"[{url} — {len(resp.text)} chars]\n{text}", max_length)
        except Exception as e:
            return f"Fetch error: {e}"

    def tool_write_file(self, path: str, content: str) -> str:
        resolved = self._resolve_path(path)
        try:
            os.makedirs(os.path.dirname(resolved) or ".", exist_ok=True)
            with open(resolved, "w", encoding="utf-8") as f:
                f.write(content)
            return f"Wrote {len(content)} chars to {resolved}"
        except Exception as e:
            return f"Write error: {e}"

    def tool_run_command(self, command: str, timeout: int = 30) -> str:
        try:
            result = subprocess.run(
                command, shell=True, capture_output=True, text=True,
                timeout=timeout, cwd=self._workdir,
            )
            output = result.stdout
            if result.stderr:
                output += f"\nSTDERR:\n{result.stderr}"
            if result.returncode != 0:
                output += f"\n[exit code: {result.returncode}]"
            return _truncate(output)
        except subprocess.TimeoutExpired:
            return f"Timeout ({timeout}s)"
        except Exception as e:
            return f"Error: {e}"


# ─── Module-level backward-compatible wrappers ───

_default_registry: ToolRegistry | None = None


def set_workdir(path: str) -> None:
    """Set the working directory for module-level tool functions."""
    global _default_registry
    _default_registry = ToolRegistry(workdir=path)


def _get_registry() -> ToolRegistry:
    global _default_registry
    if _default_registry is None:
        _default_registry = ToolRegistry()
    return _default_registry


def get_tool_schemas(tool_set: str | list = "all") -> list[dict]:
    """Return tool schemas for the given set name or explicit list."""
    return _get_registry().get_tool_schemas(tool_set)


def execute_tool(name: str, arguments: dict) -> str:
    """Execute a tool by name with the given arguments."""
    return _get_registry().execute_tool(name, arguments)


# Legacy dict-based dispatch (kept for any code that imports TOOL_FUNCTIONS)
TOOL_FUNCTIONS = {
    "read_file":       lambda **kw: _get_registry().tool_read_file(**kw),
    "list_files":      lambda **kw: _get_registry().tool_list_files(**kw),
    "search_in_files": lambda **kw: _get_registry().tool_search_in_files(**kw),
    "web_search":      lambda **kw: _get_registry().tool_web_search(**kw),
    "web_fetch":       lambda **kw: _get_registry().tool_web_fetch(**kw),
    "write_file":      lambda **kw: _get_registry().tool_write_file(**kw),
    "run_command":     lambda **kw: _get_registry().tool_run_command(**kw),
}