feat(auth): authentication module with multi-tenant isolation (RFC-001)

Introduce an always-on auth layer with auto-created admin on first boot, multi-tenant isolation for threads/stores, and a full setup/login flow. Backend - JWT access tokens with `ver` field for stale-token rejection; bump on password/email change - Password hashing, HttpOnly+Secure cookies (Secure derived from request scheme at runtime) - CSRF middleware covering both REST and LangGraph routes - IP-based login rate limiting (5 attempts / 5-min lockout) with bounded dict growth and X-Forwarded-For bypass fix - Multi-worker-safe admin auto-creation (single DB write, WAL once) - needs_setup + token_version on User model; SQLite schema migration - Thread/store isolation by owner; orphan thread migration on first admin registration - thread_id validated as UUID to prevent log injection - CLI tool to reset admin password - Decorator-based authz module extracted from auth core Frontend - Login and setup pages with SSR guard for needs_setup flow - Account settings page (change password / email) - AuthProvider + route guards; skips redirect when no users registered - i18n (en-US / zh-CN) for auth surfaces - Typed auth API client; parseAuthError unwraps FastAPI detail envelope Infra & tooling - Unified `serve.sh` with gateway mode + auto dep install - Public PyPI uv.toml pin for CI compatibility - Regenerated uv.lock with public index Tests - HTTP vs HTTPS cookie security tests - Auth middleware, rate limiter, CSRF, setup flow coverage
2026-05-24 17:06:00 +00:00 · 2026-04-08 00:31:43 +08:00
parent 636053fb6d
commit 27b66d6753
214 changed files with 18830 additions and 1065 deletions
@@ -1,72 +1,6 @@
-import fnmatch
 from pathlib import Path

-IGNORE_PATTERNS = [
-    # Version Control
-    ".git",
-    ".svn",
-    ".hg",
-    ".bzr",
-    # Dependencies
-    "node_modules",
-    "__pycache__",
-    ".venv",
-    "venv",
-    ".env",
-    "env",
-    ".tox",
-    ".nox",
-    ".eggs",
-    "*.egg-info",
-    "site-packages",
-    # Build outputs
-    "dist",
-    "build",
-    ".next",
-    ".nuxt",
-    ".output",
-    ".turbo",
-    "target",
-    "out",
-    # IDE & Editor
-    ".idea",
-    ".vscode",
-    "*.swp",
-    "*.swo",
-    "*~",
-    ".project",
-    ".classpath",
-    ".settings",
-    # OS generated
-    ".DS_Store",
-    "Thumbs.db",
-    "desktop.ini",
-    "*.lnk",
-    # Logs & temp files
-    "*.log",
-    "*.tmp",
-    "*.temp",
-    "*.bak",
-    "*.cache",
-    ".cache",
-    "logs",
-    # Coverage & test artifacts
-    ".coverage",
-    "coverage",
-    ".nyc_output",
-    "htmlcov",
-    ".pytest_cache",
-    ".mypy_cache",
-    ".ruff_cache",
-]
-
-
-def _should_ignore(name: str) -> bool:
-    """Check if a file/directory name matches any ignore pattern."""
-    for pattern in IGNORE_PATTERNS:
-        if fnmatch.fnmatch(name, pattern):
-            return True
-    return False
+from deerflow.sandbox.search import should_ignore_name


 def list_dir(path: str, max_depth: int = 2) -> list[str]:
@@ -95,7 +29,7 @@ def list_dir(path: str, max_depth: int = 2) -> list[str]:

        try:
            for item in current_path.iterdir():
-                if _should_ignore(item.name):
+                if should_ignore_name(item.name):
                    continue

                post_fix = "/" if item.is_dir() else ""
@@ -1,11 +1,23 @@
+import errno
 import ntpath
 import os
 import shutil
 import subprocess
+from dataclasses import dataclass
 from pathlib import Path

 from deerflow.sandbox.local.list_dir import list_dir
 from deerflow.sandbox.sandbox import Sandbox
+from deerflow.sandbox.search import GrepMatch, find_glob_matches, find_grep_matches
+
+
+@dataclass(frozen=True)
+class PathMapping:
+    """A path mapping from a container path to a local path with optional read-only flag."""
+
+    container_path: str
+    local_path: str
+    read_only: bool = False


 class LocalSandbox(Sandbox):
@@ -39,17 +51,42 @@ class LocalSandbox(Sandbox):

        return None

-    def __init__(self, id: str, path_mappings: dict[str, str] | None = None):
+    def __init__(self, id: str, path_mappings: list[PathMapping] | None = None):
        """
        Initialize local sandbox with optional path mappings.

        Args:
            id: Sandbox identifier
-            path_mappings: Dictionary mapping container paths to local paths
-                          Example: {"/mnt/skills": "/absolute/path/to/skills"}
+            path_mappings: List of path mappings with optional read-only flag.
+                          Skills directory is read-only by default.
        """
        super().__init__(id)
-        self.path_mappings = path_mappings or {}
+        self.path_mappings = path_mappings or []
+
+    def _is_read_only_path(self, resolved_path: str) -> bool:
+        """Check if a resolved path is under a read-only mount.
+
+        When multiple mappings match (nested mounts), prefer the most specific
+        mapping (i.e. the one whose local_path is the longest prefix of the
+        resolved path), similar to how ``_resolve_path`` handles container paths.
+        """
+        resolved = str(Path(resolved_path).resolve())
+
+        best_mapping: PathMapping | None = None
+        best_prefix_len = -1
+
+        for mapping in self.path_mappings:
+            local_resolved = str(Path(mapping.local_path).resolve())
+            if resolved == local_resolved or resolved.startswith(local_resolved + os.sep):
+                prefix_len = len(local_resolved)
+                if prefix_len > best_prefix_len:
+                    best_prefix_len = prefix_len
+                    best_mapping = mapping
+
+        if best_mapping is None:
+            return False
+
+        return best_mapping.read_only

    def _resolve_path(self, path: str) -> str:
        """
@@ -64,7 +101,9 @@ class LocalSandbox(Sandbox):
        path_str = str(path)

        # Try each mapping (longest prefix first for more specific matches)
-        for container_path, local_path in sorted(self.path_mappings.items(), key=lambda x: len(x[0]), reverse=True):
+        for mapping in sorted(self.path_mappings, key=lambda m: len(m.container_path), reverse=True):
+            container_path = mapping.container_path
+            local_path = mapping.local_path
            if path_str == container_path or path_str.startswith(container_path + "/"):
                # Replace the container path prefix with local path
                relative = path_str[len(container_path) :].lstrip("/")
@@ -84,15 +123,16 @@ class LocalSandbox(Sandbox):
        Returns:
            Container path if mapping exists, otherwise original path
        """
-        path_str = str(Path(path).resolve())
+        normalized_path = path.replace("\\", "/")
+        path_str = str(Path(normalized_path).resolve())

        # Try each mapping (longest local path first for more specific matches)
-        for container_path, local_path in sorted(self.path_mappings.items(), key=lambda x: len(x[1]), reverse=True):
-            local_path_resolved = str(Path(local_path).resolve())
-            if path_str.startswith(local_path_resolved):
+        for mapping in sorted(self.path_mappings, key=lambda m: len(m.local_path), reverse=True):
+            local_path_resolved = str(Path(mapping.local_path).resolve())
+            if path_str == local_path_resolved or path_str.startswith(local_path_resolved + "/"):
                # Replace the local path prefix with container path
                relative = path_str[len(local_path_resolved) :].lstrip("/")
-                resolved = f"{container_path}/{relative}" if relative else container_path
+                resolved = f"{mapping.container_path}/{relative}" if relative else mapping.container_path
                return resolved

        # No mapping found, return original path
@@ -111,7 +151,7 @@ class LocalSandbox(Sandbox):
        import re

        # Sort mappings by local path length (longest first) for correct prefix matching
-        sorted_mappings = sorted(self.path_mappings.items(), key=lambda x: len(x[1]), reverse=True)
+        sorted_mappings = sorted(self.path_mappings, key=lambda m: len(m.local_path), reverse=True)

        if not sorted_mappings:
            return output
@@ -119,12 +159,11 @@ class LocalSandbox(Sandbox):
        # Create pattern that matches absolute paths
        # Match paths like /Users/... or other absolute paths
        result = output
-        for container_path, local_path in sorted_mappings:
-            local_path_resolved = str(Path(local_path).resolve())
+        for mapping in sorted_mappings:
            # Escape the local path for use in regex
-            escaped_local = re.escape(local_path_resolved)
-            # Match the local path followed by optional path components
-            pattern = re.compile(escaped_local + r"(?:/[^\s\"';&|<>()]*)?")
+            escaped_local = re.escape(str(Path(mapping.local_path).resolve()))
+            # Match the local path followed by optional path components with either separator
+            pattern = re.compile(escaped_local + r"(?:[/\\][^\s\"';&|<>()]*)?")

            def replace_match(match: re.Match) -> str:
                matched_path = match.group(0)
@@ -147,7 +186,7 @@ class LocalSandbox(Sandbox):
        import re

        # Sort mappings by length (longest first) for correct prefix matching
-        sorted_mappings = sorted(self.path_mappings.items(), key=lambda x: len(x[0]), reverse=True)
+        sorted_mappings = sorted(self.path_mappings, key=lambda m: len(m.container_path), reverse=True)

        # Build regex pattern to match all container paths
        # Match container path followed by optional path components
@@ -157,7 +196,7 @@ class LocalSandbox(Sandbox):
        # Create pattern that matches any of the container paths.
        # The lookahead (?=/|$|...) ensures we only match at a path-segment boundary,
        # preventing /mnt/skills from matching inside /mnt/skills-extra.
-        patterns = [re.escape(container_path) + r"(?=/|$|[\s\"';&|<>()])(?:/[^\s\"';&|<>()]*)?" for container_path, _ in sorted_mappings]
+        patterns = [re.escape(m.container_path) + r"(?=/|$|[\s\"';&|<>()])(?:/[^\s\"';&|<>()]*)?" for m in sorted_mappings]
        pattern = re.compile("|".join(f"({p})" for p in patterns))

        def replace_match(match: re.Match) -> str:
@@ -248,6 +287,8 @@ class LocalSandbox(Sandbox):

    def write_file(self, path: str, content: str, append: bool = False) -> None:
        resolved_path = self._resolve_path(path)
+        if self._is_read_only_path(resolved_path):
+            raise OSError(errno.EROFS, "Read-only file system", path)
        try:
            dir_path = os.path.dirname(resolved_path)
            if dir_path:
@@ -259,8 +300,43 @@ class LocalSandbox(Sandbox):
            # Re-raise with the original path for clearer error messages, hiding internal resolved paths
            raise type(e)(e.errno, e.strerror, path) from None

+    def glob(self, path: str, pattern: str, *, include_dirs: bool = False, max_results: int = 200) -> tuple[list[str], bool]:
+        resolved_path = Path(self._resolve_path(path))
+        matches, truncated = find_glob_matches(resolved_path, pattern, include_dirs=include_dirs, max_results=max_results)
+        return [self._reverse_resolve_path(match) for match in matches], truncated
+
+    def grep(
+        self,
+        path: str,
+        pattern: str,
+        *,
+        glob: str | None = None,
+        literal: bool = False,
+        case_sensitive: bool = False,
+        max_results: int = 100,
+    ) -> tuple[list[GrepMatch], bool]:
+        resolved_path = Path(self._resolve_path(path))
+        matches, truncated = find_grep_matches(
+            resolved_path,
+            pattern,
+            glob_pattern=glob,
+            literal=literal,
+            case_sensitive=case_sensitive,
+            max_results=max_results,
+        )
+        return [
+            GrepMatch(
+                path=self._reverse_resolve_path(match.path),
+                line_number=match.line_number,
+                line=match.line,
+            )
+            for match in matches
+        ], truncated
+
    def update_file(self, path: str, content: bytes) -> None:
        resolved_path = self._resolve_path(path)
+        if self._is_read_only_path(resolved_path):
+            raise OSError(errno.EROFS, "Read-only file system", path)
        try:
            dir_path = os.path.dirname(resolved_path)
            if dir_path:
@@ -1,6 +1,7 @@
 import logging
+from pathlib import Path

-from deerflow.sandbox.local.local_sandbox import LocalSandbox
+from deerflow.sandbox.local.local_sandbox import LocalSandbox, PathMapping
 from deerflow.sandbox.sandbox import Sandbox
 from deerflow.sandbox.sandbox_provider import SandboxProvider

@@ -14,16 +15,17 @@ class LocalSandboxProvider(SandboxProvider):
        """Initialize the local sandbox provider with path mappings."""
        self._path_mappings = self._setup_path_mappings()

-    def _setup_path_mappings(self) -> dict[str, str]:
+    def _setup_path_mappings(self) -> list[PathMapping]:
        """
        Setup path mappings for local sandbox.

-        Maps container paths to actual local paths, including skills directory.
+        Maps container paths to actual local paths, including skills directory
+        and any custom mounts configured in config.yaml.

        Returns:
-            Dictionary of path mappings
+            List of path mappings
        """
-        mappings = {}
+        mappings: list[PathMapping] = []

        # Map skills container path to local skills directory
        try:
@@ -35,10 +37,63 @@ class LocalSandboxProvider(SandboxProvider):

            # Only add mapping if skills directory exists
            if skills_path.exists():
-                mappings[container_path] = str(skills_path)
+                mappings.append(
+                    PathMapping(
+                        container_path=container_path,
+                        local_path=str(skills_path),
+                        read_only=True,  # Skills directory is always read-only
+                    )
+                )
+
+            # Map custom mounts from sandbox config
+            _RESERVED_CONTAINER_PREFIXES = [container_path, "/mnt/acp-workspace", "/mnt/user-data"]
+            sandbox_config = config.sandbox
+            if sandbox_config and sandbox_config.mounts:
+                for mount in sandbox_config.mounts:
+                    host_path = Path(mount.host_path)
+                    container_path = mount.container_path.rstrip("/") or "/"
+
+                    if not host_path.is_absolute():
+                        logger.warning(
+                            "Mount host_path must be absolute, skipping: %s -> %s",
+                            mount.host_path,
+                            mount.container_path,
+                        )
+                        continue
+
+                    if not container_path.startswith("/"):
+                        logger.warning(
+                            "Mount container_path must be absolute, skipping: %s -> %s",
+                            mount.host_path,
+                            mount.container_path,
+                        )
+                        continue
+
+                    # Reject mounts that conflict with reserved container paths
+                    if any(container_path == p or container_path.startswith(p + "/") for p in _RESERVED_CONTAINER_PREFIXES):
+                        logger.warning(
+                            "Mount container_path conflicts with reserved prefix, skipping: %s",
+                            mount.container_path,
+                        )
+                        continue
+                    # Ensure the host path exists before adding mapping
+                    if host_path.exists():
+                        mappings.append(
+                            PathMapping(
+                                container_path=container_path,
+                                local_path=str(host_path.resolve()),
+                                read_only=mount.read_only,
+                            )
+                        )
+                    else:
+                        logger.warning(
+                            "Mount host_path does not exist, skipping: %s -> %s",
+                            mount.host_path,
+                            mount.container_path,
+                        )
        except Exception as e:
            # Log but don't fail if config loading fails
-            logger.warning("Could not setup skills path mapping: %s", e, exc_info=True)
+            logger.warning("Could not setup path mappings: %s", e, exc_info=True)

        return mappings

@@ -1,5 +1,7 @@
 from abc import ABC, abstractmethod

+from deerflow.sandbox.search import GrepMatch
+

 class Sandbox(ABC):
    """Abstract base class for sandbox environments"""
@@ -61,6 +63,25 @@ class Sandbox(ABC):
        """
        pass

+    @abstractmethod
+    def glob(self, path: str, pattern: str, *, include_dirs: bool = False, max_results: int = 200) -> tuple[list[str], bool]:
+        """Find paths that match a glob pattern under a root directory."""
+        pass
+
+    @abstractmethod
+    def grep(
+        self,
+        path: str,
+        pattern: str,
+        *,
+        glob: str | None = None,
+        literal: bool = False,
+        case_sensitive: bool = False,
+        max_results: int = 100,
+    ) -> tuple[list[GrepMatch], bool]:
+        """Search for matches inside text files under a directory."""
+        pass
+
    @abstractmethod
    def update_file(self, path: str, content: bytes) -> None:
        """Update a file with binary content.
@@ -0,0 +1,210 @@
+import fnmatch
+import os
+import re
+from dataclasses import dataclass
+from pathlib import Path, PurePosixPath
+
+IGNORE_PATTERNS = [
+    ".git",
+    ".svn",
+    ".hg",
+    ".bzr",
+    "node_modules",
+    "__pycache__",
+    ".venv",
+    "venv",
+    ".env",
+    "env",
+    ".tox",
+    ".nox",
+    ".eggs",
+    "*.egg-info",
+    "site-packages",
+    "dist",
+    "build",
+    ".next",
+    ".nuxt",
+    ".output",
+    ".turbo",
+    "target",
+    "out",
+    ".idea",
+    ".vscode",
+    "*.swp",
+    "*.swo",
+    "*~",
+    ".project",
+    ".classpath",
+    ".settings",
+    ".DS_Store",
+    "Thumbs.db",
+    "desktop.ini",
+    "*.lnk",
+    "*.log",
+    "*.tmp",
+    "*.temp",
+    "*.bak",
+    "*.cache",
+    ".cache",
+    "logs",
+    ".coverage",
+    "coverage",
+    ".nyc_output",
+    "htmlcov",
+    ".pytest_cache",
+    ".mypy_cache",
+    ".ruff_cache",
+]
+
+DEFAULT_MAX_FILE_SIZE_BYTES = 1_000_000
+DEFAULT_LINE_SUMMARY_LENGTH = 200
+
+
+@dataclass(frozen=True)
+class GrepMatch:
+    path: str
+    line_number: int
+    line: str
+
+
+def should_ignore_name(name: str) -> bool:
+    for pattern in IGNORE_PATTERNS:
+        if fnmatch.fnmatch(name, pattern):
+            return True
+    return False
+
+
+def should_ignore_path(path: str) -> bool:
+    return any(should_ignore_name(segment) for segment in path.replace("\\", "/").split("/") if segment)
+
+
+def path_matches(pattern: str, rel_path: str) -> bool:
+    path = PurePosixPath(rel_path)
+    if path.match(pattern):
+        return True
+    if pattern.startswith("**/"):
+        return path.match(pattern[3:])
+    return False
+
+
+def truncate_line(line: str, max_chars: int = DEFAULT_LINE_SUMMARY_LENGTH) -> str:
+    line = line.rstrip("\n\r")
+    if len(line) <= max_chars:
+        return line
+    return line[: max_chars - 3] + "..."
+
+
+def is_binary_file(path: Path, sample_size: int = 8192) -> bool:
+    try:
+        with path.open("rb") as handle:
+            return b"\0" in handle.read(sample_size)
+    except OSError:
+        return True
+
+
+def find_glob_matches(root: Path, pattern: str, *, include_dirs: bool = False, max_results: int = 200) -> tuple[list[str], bool]:
+    matches: list[str] = []
+    truncated = False
+    root = root.resolve()
+
+    if not root.exists():
+        raise FileNotFoundError(root)
+    if not root.is_dir():
+        raise NotADirectoryError(root)
+
+    for current_root, dirs, files in os.walk(root):
+        dirs[:] = [name for name in dirs if not should_ignore_name(name)]
+        # root is already resolved; os.walk builds current_root by joining under root,
+        # so relative_to() works without an extra stat()/resolve() per directory.
+        rel_dir = Path(current_root).relative_to(root)
+
+        if include_dirs:
+            for name in dirs:
+                rel_path = (rel_dir / name).as_posix()
+                if path_matches(pattern, rel_path):
+                    matches.append(str(Path(current_root) / name))
+                    if len(matches) >= max_results:
+                        truncated = True
+                        return matches, truncated
+
+        for name in files:
+            if should_ignore_name(name):
+                continue
+            rel_path = (rel_dir / name).as_posix()
+            if path_matches(pattern, rel_path):
+                matches.append(str(Path(current_root) / name))
+                if len(matches) >= max_results:
+                    truncated = True
+                    return matches, truncated
+
+    return matches, truncated
+
+
+def find_grep_matches(
+    root: Path,
+    pattern: str,
+    *,
+    glob_pattern: str | None = None,
+    literal: bool = False,
+    case_sensitive: bool = False,
+    max_results: int = 100,
+    max_file_size: int = DEFAULT_MAX_FILE_SIZE_BYTES,
+    line_summary_length: int = DEFAULT_LINE_SUMMARY_LENGTH,
+) -> tuple[list[GrepMatch], bool]:
+    matches: list[GrepMatch] = []
+    truncated = False
+    root = root.resolve()
+
+    if not root.exists():
+        raise FileNotFoundError(root)
+    if not root.is_dir():
+        raise NotADirectoryError(root)
+
+    regex_source = re.escape(pattern) if literal else pattern
+    flags = 0 if case_sensitive else re.IGNORECASE
+    regex = re.compile(regex_source, flags)
+
+    # Skip lines longer than this to prevent ReDoS on minified / no-newline files.
+    _max_line_chars = line_summary_length * 10
+
+    for current_root, dirs, files in os.walk(root):
+        dirs[:] = [name for name in dirs if not should_ignore_name(name)]
+        rel_dir = Path(current_root).relative_to(root)
+
+        for name in files:
+            if should_ignore_name(name):
+                continue
+
+            candidate_path = Path(current_root) / name
+            rel_path = (rel_dir / name).as_posix()
+
+            if glob_pattern is not None and not path_matches(glob_pattern, rel_path):
+                continue
+
+            try:
+                if candidate_path.is_symlink():
+                    continue
+                file_path = candidate_path.resolve()
+                if not file_path.is_relative_to(root):
+                    continue
+                if file_path.stat().st_size > max_file_size or is_binary_file(file_path):
+                    continue
+                with file_path.open(encoding="utf-8", errors="replace") as handle:
+                    for line_number, line in enumerate(handle, start=1):
+                        if len(line) > _max_line_chars:
+                            continue
+                        if regex.search(line):
+                            matches.append(
+                                GrepMatch(
+                                    path=str(file_path),
+                                    line_number=line_number,
+                                    line=truncate_line(line, line_summary_length),
+                                )
+                            )
+                            if len(matches) >= max_results:
+                                truncated = True
+                                return matches, truncated
+            except OSError:
+                continue
+
+    return matches, truncated
@@ -7,6 +7,7 @@ from langchain.tools import ToolRuntime, tool
 from langgraph.typing import ContextT

 from deerflow.agents.thread_state import ThreadDataState, ThreadState
+from deerflow.config import get_app_config
 from deerflow.config.paths import VIRTUAL_PATH_PREFIX
 from deerflow.sandbox.exceptions import (
    SandboxError,
@@ -16,6 +17,7 @@ from deerflow.sandbox.exceptions import (
 from deerflow.sandbox.file_operation_lock import get_file_operation_lock
 from deerflow.sandbox.sandbox import Sandbox
 from deerflow.sandbox.sandbox_provider import get_sandbox_provider
+from deerflow.sandbox.search import GrepMatch
 from deerflow.sandbox.security import LOCAL_HOST_BASH_DISABLED_MESSAGE, is_host_bash_allowed

 _ABSOLUTE_PATH_PATTERN = re.compile(r"(?<![:\w])(?<!:/)/(?:[^\s\"'`;&|<>()]+)")
@@ -31,6 +33,10 @@ _LOCAL_BASH_SYSTEM_PATH_PREFIXES = (

 _DEFAULT_SKILLS_CONTAINER_PATH = "/mnt/skills"
 _ACP_WORKSPACE_VIRTUAL_PATH = "/mnt/acp-workspace"
+_DEFAULT_GLOB_MAX_RESULTS = 200
+_MAX_GLOB_MAX_RESULTS = 1000
+_DEFAULT_GREP_MAX_RESULTS = 100
+_MAX_GREP_MAX_RESULTS = 500


 def _get_skills_container_path() -> str:
@@ -113,6 +119,54 @@ def _is_acp_workspace_path(path: str) -> bool:
    return path == _ACP_WORKSPACE_VIRTUAL_PATH or path.startswith(f"{_ACP_WORKSPACE_VIRTUAL_PATH}/")


+def _get_custom_mounts():
+    """Get custom volume mounts from sandbox config.
+
+    Result is cached after the first successful config load.  If config loading
+    fails an empty list is returned *without* caching so that a later call can
+    pick up the real value once the config is available.
+    """
+    cached = getattr(_get_custom_mounts, "_cached", None)
+    if cached is not None:
+        return cached
+    try:
+        from pathlib import Path
+
+        from deerflow.config import get_app_config
+
+        config = get_app_config()
+        mounts = []
+        if config.sandbox and config.sandbox.mounts:
+            # Only include mounts whose host_path exists, consistent with
+            # LocalSandboxProvider._setup_path_mappings() which also filters
+            # by host_path.exists().
+            mounts = [m for m in config.sandbox.mounts if Path(m.host_path).exists()]
+        _get_custom_mounts._cached = mounts  # type: ignore[attr-defined]
+        return mounts
+    except Exception:
+        # If config loading fails, return an empty list without caching so that
+        # a later call can retry once the config is available.
+        return []
+
+
+def _is_custom_mount_path(path: str) -> bool:
+    """Check if path is under a custom mount container_path."""
+    for mount in _get_custom_mounts():
+        if path == mount.container_path or path.startswith(f"{mount.container_path}/"):
+            return True
+    return False
+
+
+def _get_custom_mount_for_path(path: str):
+    """Get the mount config matching this path (longest prefix first)."""
+    best = None
+    for mount in _get_custom_mounts():
+        if path == mount.container_path or path.startswith(f"{mount.container_path}/"):
+            if best is None or len(mount.container_path) > len(best.container_path):
+                best = mount
+    return best
+
+
 def _extract_thread_id_from_thread_data(thread_data: "ThreadDataState | None") -> str | None:
    """Extract thread_id from thread_data by inspecting workspace_path.

@@ -245,16 +299,84 @@ def _get_mcp_allowed_paths() -> list[str]:
    return allowed_paths


+def _get_tool_config_int(name: str, key: str, default: int) -> int:
+    try:
+        tool_config = get_app_config().get_tool_config(name)
+        if tool_config is not None and key in tool_config.model_extra:
+            value = tool_config.model_extra.get(key)
+            if isinstance(value, int):
+                return value
+    except Exception:
+        pass
+    return default
+
+
+def _clamp_max_results(value: int, *, default: int, upper_bound: int) -> int:
+    if value <= 0:
+        return default
+    return min(value, upper_bound)
+
+
+def _resolve_max_results(name: str, requested: int, *, default: int, upper_bound: int) -> int:
+    requested_max_results = _clamp_max_results(requested, default=default, upper_bound=upper_bound)
+    configured_max_results = _clamp_max_results(
+        _get_tool_config_int(name, "max_results", default),
+        default=default,
+        upper_bound=upper_bound,
+    )
+    return min(requested_max_results, configured_max_results)
+
+
+def _resolve_local_read_path(path: str, thread_data: ThreadDataState) -> str:
+    validate_local_tool_path(path, thread_data, read_only=True)
+    if _is_skills_path(path):
+        return _resolve_skills_path(path)
+    if _is_acp_workspace_path(path):
+        return _resolve_acp_workspace_path(path, _extract_thread_id_from_thread_data(thread_data))
+    return _resolve_and_validate_user_data_path(path, thread_data)
+
+
+def _format_glob_results(root_path: str, matches: list[str], truncated: bool) -> str:
+    if not matches:
+        return f"No files matched under {root_path}"
+
+    lines = [f"Found {len(matches)} paths under {root_path}"]
+    if truncated:
+        lines[0] += f" (showing first {len(matches)})"
+    lines.extend(f"{index}. {path}" for index, path in enumerate(matches, start=1))
+    if truncated:
+        lines.append("Results truncated. Narrow the path or pattern to see fewer matches.")
+    return "\n".join(lines)
+
+
+def _format_grep_results(root_path: str, matches: list[GrepMatch], truncated: bool) -> str:
+    if not matches:
+        return f"No matches found under {root_path}"
+
+    lines = [f"Found {len(matches)} matches under {root_path}"]
+    if truncated:
+        lines[0] += f" (showing first {len(matches)})"
+    lines.extend(f"{match.path}:{match.line_number}: {match.line}" for match in matches)
+    if truncated:
+        lines.append("Results truncated. Narrow the path or add a glob filter.")
+    return "\n".join(lines)
+
+
 def _path_variants(path: str) -> set[str]:
    return {path, path.replace("\\", "/"), path.replace("/", "\\")}


+def _path_separator_for_style(path: str) -> str:
+    return "\\" if "\\" in path and "/" not in path else "/"
+
+
 def _join_path_preserving_style(base: str, relative: str) -> str:
    if not relative:
        return base
-    if "/" in base and "\\" not in base:
-        return f"{base.rstrip('/')}/{relative}"
-    return str(Path(base) / relative)
+    separator = _path_separator_for_style(base)
+    normalized_relative = relative.replace("\\" if separator == "/" else "/", separator).lstrip("/\\")
+    stripped_base = base.rstrip("/\\")
+    return f"{stripped_base}{separator}{normalized_relative}"


 def _sanitize_error(error: Exception, runtime: "ToolRuntime[ContextT, ThreadState] | None" = None) -> str:
@@ -299,7 +421,10 @@ def replace_virtual_path(path: str, thread_data: ThreadDataState | None) -> str:
            return actual_base
        if path.startswith(f"{virtual_base}/"):
            rest = path[len(virtual_base) :].lstrip("/")
-            return _join_path_preserving_style(actual_base, rest)
+            result = _join_path_preserving_style(actual_base, rest)
+            if path.endswith("/") and not result.endswith(("/", "\\")):
+                result += _path_separator_for_style(actual_base)
+            return result

    return path

@@ -379,6 +504,8 @@ def mask_local_paths_in_output(output: str, thread_data: ThreadDataState | None)

            result = pattern.sub(replace_acp, result)

+    # Custom mount host paths are masked by LocalSandbox._reverse_resolve_paths_in_output()
+
    # Mask user-data host paths
    if thread_data is None:
        return result
@@ -427,6 +554,7 @@ def validate_local_tool_path(path: str, thread_data: ThreadDataState | None, *,
      - ``/mnt/user-data/*``  — always allowed (read + write)
      - ``/mnt/skills/*``     — allowed only when *read_only* is True
      - ``/mnt/acp-workspace/*`` — allowed only when *read_only* is True
+      - Custom mount paths (from config.yaml) — respects per-mount ``read_only`` flag

    Args:
        path: The virtual path to validate.
@@ -458,7 +586,14 @@ def validate_local_tool_path(path: str, thread_data: ThreadDataState | None, *,
    if path.startswith(f"{VIRTUAL_PATH_PREFIX}/"):
        return

-    raise PermissionError(f"Only paths under {VIRTUAL_PATH_PREFIX}/, {_get_skills_container_path()}/, or {_ACP_WORKSPACE_VIRTUAL_PATH}/ are allowed")
+    # Custom mount paths — respect read_only config
+    if _is_custom_mount_path(path):
+        mount = _get_custom_mount_for_path(path)
+        if mount and mount.read_only and not read_only:
+            raise PermissionError(f"Write access to read-only mount is not allowed: {path}")
+        return
+
+    raise PermissionError(f"Only paths under {VIRTUAL_PATH_PREFIX}/, {_get_skills_container_path()}/, {_ACP_WORKSPACE_VIRTUAL_PATH}/, or configured mount paths are allowed")


 def _validate_resolved_user_data_path(resolved: Path, thread_data: ThreadDataState) -> None:
@@ -508,9 +643,10 @@ def validate_local_bash_command_paths(command: str, thread_data: ThreadDataState
    boundary and must not be treated as isolation from the host filesystem.

    In local mode, commands must use virtual paths under /mnt/user-data for
-    user data access. Skills paths under /mnt/skills and ACP workspace paths
-    under /mnt/acp-workspace are allowed (path-traversal checks only; write
-    prevention for bash commands is not enforced here).
+    user data access. Skills paths under /mnt/skills, ACP workspace paths
+    under /mnt/acp-workspace, and custom mount container paths (configured in
+    config.yaml) are allowed (path-traversal checks only; write prevention
+    for bash commands is not enforced here).
    A small allowlist of common system path prefixes is kept for executable
    and device references (e.g. /bin/sh, /dev/null).
    """
@@ -545,6 +681,11 @@ def validate_local_bash_command_paths(command: str, thread_data: ThreadDataState
            _reject_path_traversal(absolute_path)
            continue

+        # Allow custom mount container paths
+        if _is_custom_mount_path(absolute_path):
+            _reject_path_traversal(absolute_path)
+            continue
+
        if any(absolute_path == prefix.rstrip("/") or absolute_path.startswith(prefix) for prefix in _LOCAL_BASH_SYSTEM_PATH_PREFIXES):
            continue

@@ -589,6 +730,8 @@ def replace_virtual_paths_in_command(command: str, thread_data: ThreadDataState

        result = acp_pattern.sub(replace_acp_match, result)

+    # Custom mount paths are resolved by LocalSandbox._resolve_paths_in_command()
+
    # Replace user-data paths
    if VIRTUAL_PATH_PREFIX in result and thread_data is not None:
        pattern = re.compile(rf"{re.escape(VIRTUAL_PATH_PREFIX)}(/[^\s\"';&|<>()]*)?")
@@ -666,7 +809,8 @@ def sandbox_from_runtime(runtime: ToolRuntime[ContextT, ThreadState] | None = No
    if sandbox is None:
        raise SandboxNotFoundError(f"Sandbox with ID '{sandbox_id}' not found", sandbox_id=sandbox_id)

-    runtime.context["sandbox_id"] = sandbox_id  # Ensure sandbox_id is in context for downstream use
+    if runtime.context is not None:
+        runtime.context["sandbox_id"] = sandbox_id  # Ensure sandbox_id is in context for downstream use
    return sandbox


@@ -701,7 +845,8 @@ def ensure_sandbox_initialized(runtime: ToolRuntime[ContextT, ThreadState] | Non
        if sandbox_id is not None:
            sandbox = get_sandbox_provider().get(sandbox_id)
            if sandbox is not None:
-                runtime.context["sandbox_id"] = sandbox_id  # Ensure sandbox_id is in context for releasing in after_agent
+                if runtime.context is not None:
+                    runtime.context["sandbox_id"] = sandbox_id  # Ensure sandbox_id is in context for releasing in after_agent
                return sandbox
            # Sandbox was released, fall through to acquire new one

@@ -723,7 +868,8 @@ def ensure_sandbox_initialized(runtime: ToolRuntime[ContextT, ThreadState] | Non
    if sandbox is None:
        raise SandboxNotFoundError("Sandbox not found after acquisition", sandbox_id=sandbox_id)

-    runtime.context["sandbox_id"] = sandbox_id  # Ensure sandbox_id is in context for releasing in after_agent
+    if runtime.context is not None:
+        runtime.context["sandbox_id"] = sandbox_id  # Ensure sandbox_id is in context for releasing in after_agent
    return sandbox


@@ -885,8 +1031,9 @@ def ls_tool(runtime: ToolRuntime[ContextT, ThreadState], description: str, path:
                path = _resolve_skills_path(path)
            elif _is_acp_workspace_path(path):
                path = _resolve_acp_workspace_path(path, _extract_thread_id_from_thread_data(thread_data))
-            else:
+            elif not _is_custom_mount_path(path):
                path = _resolve_and_validate_user_data_path(path, thread_data)
+            # Custom mount paths are resolved by LocalSandbox._resolve_path()
        children = sandbox.list_dir(path)
        if not children:
            return "(empty)"
@@ -901,6 +1048,126 @@ def ls_tool(runtime: ToolRuntime[ContextT, ThreadState], description: str, path:
        return f"Error: Unexpected error listing directory: {_sanitize_error(e, runtime)}"


+@tool("glob", parse_docstring=True)
+def glob_tool(
+    runtime: ToolRuntime[ContextT, ThreadState],
+    description: str,
+    pattern: str,
+    path: str,
+    include_dirs: bool = False,
+    max_results: int = _DEFAULT_GLOB_MAX_RESULTS,
+) -> str:
+    """Find files or directories that match a glob pattern under a root directory.
+
+    Args:
+        description: Explain why you are searching for these paths in short words. ALWAYS PROVIDE THIS PARAMETER FIRST.
+        pattern: The glob pattern to match relative to the root path, for example `**/*.py`.
+        path: The **absolute** root directory to search under.
+        include_dirs: Whether matching directories should also be returned. Default is False.
+        max_results: Maximum number of paths to return. Default is 200.
+    """
+    try:
+        sandbox = ensure_sandbox_initialized(runtime)
+        ensure_thread_directories_exist(runtime)
+        requested_path = path
+        effective_max_results = _resolve_max_results(
+            "glob",
+            max_results,
+            default=_DEFAULT_GLOB_MAX_RESULTS,
+            upper_bound=_MAX_GLOB_MAX_RESULTS,
+        )
+        thread_data = None
+        if is_local_sandbox(runtime):
+            thread_data = get_thread_data(runtime)
+            if thread_data is None:
+                raise SandboxRuntimeError("Thread data not available for local sandbox")
+            path = _resolve_local_read_path(path, thread_data)
+        matches, truncated = sandbox.glob(path, pattern, include_dirs=include_dirs, max_results=effective_max_results)
+        if thread_data is not None:
+            matches = [mask_local_paths_in_output(match, thread_data) for match in matches]
+        return _format_glob_results(requested_path, matches, truncated)
+    except SandboxError as e:
+        return f"Error: {e}"
+    except FileNotFoundError:
+        return f"Error: Directory not found: {requested_path}"
+    except NotADirectoryError:
+        return f"Error: Path is not a directory: {requested_path}"
+    except PermissionError:
+        return f"Error: Permission denied: {requested_path}"
+    except Exception as e:
+        return f"Error: Unexpected error searching paths: {_sanitize_error(e, runtime)}"
+
+
+@tool("grep", parse_docstring=True)
+def grep_tool(
+    runtime: ToolRuntime[ContextT, ThreadState],
+    description: str,
+    pattern: str,
+    path: str,
+    glob: str | None = None,
+    literal: bool = False,
+    case_sensitive: bool = False,
+    max_results: int = _DEFAULT_GREP_MAX_RESULTS,
+) -> str:
+    """Search for matching lines inside text files under a root directory.
+
+    Args:
+        description: Explain why you are searching file contents in short words. ALWAYS PROVIDE THIS PARAMETER FIRST.
+        pattern: The string or regex pattern to search for.
+        path: The **absolute** root directory to search under.
+        glob: Optional glob filter for candidate files, for example `**/*.py`.
+        literal: Whether to treat `pattern` as a plain string. Default is False.
+        case_sensitive: Whether matching is case-sensitive. Default is False.
+        max_results: Maximum number of matching lines to return. Default is 100.
+    """
+    try:
+        sandbox = ensure_sandbox_initialized(runtime)
+        ensure_thread_directories_exist(runtime)
+        requested_path = path
+        effective_max_results = _resolve_max_results(
+            "grep",
+            max_results,
+            default=_DEFAULT_GREP_MAX_RESULTS,
+            upper_bound=_MAX_GREP_MAX_RESULTS,
+        )
+        thread_data = None
+        if is_local_sandbox(runtime):
+            thread_data = get_thread_data(runtime)
+            if thread_data is None:
+                raise SandboxRuntimeError("Thread data not available for local sandbox")
+            path = _resolve_local_read_path(path, thread_data)
+        matches, truncated = sandbox.grep(
+            path,
+            pattern,
+            glob=glob,
+            literal=literal,
+            case_sensitive=case_sensitive,
+            max_results=effective_max_results,
+        )
+        if thread_data is not None:
+            matches = [
+                GrepMatch(
+                    path=mask_local_paths_in_output(match.path, thread_data),
+                    line_number=match.line_number,
+                    line=match.line,
+                )
+                for match in matches
+            ]
+        return _format_grep_results(requested_path, matches, truncated)
+    except SandboxError as e:
+        return f"Error: {e}"
+    except FileNotFoundError:
+        return f"Error: Directory not found: {requested_path}"
+    except NotADirectoryError:
+        return f"Error: Path is not a directory: {requested_path}"
+    except re.error as e:
+        return f"Error: Invalid regex pattern: {e}"
+    except PermissionError:
+        return f"Error: Permission denied: {requested_path}"
+    except Exception as e:
+        return f"Error: Unexpected error searching file contents: {_sanitize_error(e, runtime)}"
+
+
@tool("read_file", parse_docstring=True)
 def read_file_tool(
    runtime: ToolRuntime[ContextT, ThreadState],
@@ -928,8 +1195,9 @@ def read_file_tool(
                path = _resolve_skills_path(path)
            elif _is_acp_workspace_path(path):
                path = _resolve_acp_workspace_path(path, _extract_thread_id_from_thread_data(thread_data))
-            else:
+            elif not _is_custom_mount_path(path):
                path = _resolve_and_validate_user_data_path(path, thread_data)
+            # Custom mount paths are resolved by LocalSandbox._resolve_path()
        content = sandbox.read_file(path)
        if not content:
            return "(empty)"
@@ -977,7 +1245,9 @@ def write_file_tool(
        if is_local_sandbox(runtime):
            thread_data = get_thread_data(runtime)
            validate_local_tool_path(path, thread_data)
-            path = _resolve_and_validate_user_data_path(path, thread_data)
+            if not _is_custom_mount_path(path):
+                path = _resolve_and_validate_user_data_path(path, thread_data)
+            # Custom mount paths are resolved by LocalSandbox._resolve_path()
        with get_file_operation_lock(sandbox, path):
            sandbox.write_file(path, content, append)
        return "OK"
@@ -1019,7 +1289,9 @@ def str_replace_tool(
        if is_local_sandbox(runtime):
            thread_data = get_thread_data(runtime)
            validate_local_tool_path(path, thread_data)
-            path = _resolve_and_validate_user_data_path(path, thread_data)
+            if not _is_custom_mount_path(path):
+                path = _resolve_and_validate_user_data_path(path, thread_data)
+            # Custom mount paths are resolved by LocalSandbox._resolve_path()
        with get_file_operation_lock(sandbox, path):
            content = sandbox.read_file(path)
            if not content: