Support large target repos with with bind-mount option. (#577)

* fix: resolve pre-commit check failures

- Change RuntimeError to TypeError for type validation in report/writer.py
- Update pyupgrade to v3.21.2 for Python 3.14 compatibility

* chore: add pytest test infrastructure

Mirror the layout introduced on feature/438-token_budget: pytest +
pytest-asyncio dev deps, asyncio_mode auto, a tests.* mypy override, and
pytest in the mypy pre-commit hook deps so the tests/ package type-checks.

* feat: add --mount and large-target pre-flight for local repos (#492)

Large local targets were copied into the sandbox file-by-file via the SDK
LocalDir entry, which stalls on big repos and could leave /workspace empty.

- --mount <path> bind-mounts a host directory read-only at /workspace/<subdir>
  instead of copying it, bypassing the per-file stream.
- A size pre-flight (STRIX_MAX_LOCAL_COPY_MB, default 1024) fails fast with a
  clear message suggesting --mount when a non-mounted local target is too big.

* fix: reject empty --mount paths

An empty or whitespace-only --mount value resolves to the current working
directory and would silently bind-mount it into the sandbox. Reject it.

* fix: dedupe local targets so a dir is never both copied and mounted

If the same directory is passed via --target and --mount (or as duplicate
values), it previously produced two targets — copied AND bind-mounted, and
the copied one could trip the size pre-flight. Dedupe by resolved path,
preferring the bind mount.

* fix: treat non-positive STRIX_MAX_LOCAL_COPY_MB as disabled

Previously a value of 0 (or negative) made every local target count as
oversized, aborting all local scans. Now <= 0 disables the pre-flight.

* fix: log unreadable subtrees during size pre-flight

os.walk silently swallowed directory-listing errors, so a permission-denied
subtree could make a large repo under-count and slip past the pre-flight.
Surface such omissions via an onerror warning.

* docs: document --mount and STRIX_MAX_LOCAL_COPY_MB

Add CLI reference + example for --mount, document the size pre-flight env var,
note the read-only-is-not-a-hard-boundary caveat and that remote repos are not
size-checked, and clarify the backends docstring on when bind mounts apply.

* Update strix/interface/main.py


* Update strix/runtime/docker_client.py


---------

strix/interface/main.py

@@ -33,9 +33,12 @@ from strix.interface.tui import run_tui
 from strix.interface.utils import (
     assign_workspace_subdirs,
     build_final_stats_text,
+    build_mount_targets_info,
     check_docker_connection,
     clone_repository,
     collect_local_sources,
+    dedupe_local_targets,
+    find_oversized_local_targets,
     generate_run_name,
     image_exists,
     infer_target_type,
@@ -328,6 +331,9 @@ Examples:
   # Local code analysis
   strix --target ./my-project
 
+  # Large local repository (bind-mounted read-only instead of copied)
+  strix --mount ./huge-monorepo
+
   # Domain penetration test
   strix --target example.com
 
@@ -363,6 +369,15 @@ Examples:
         "Can be specified multiple times for multi-target scans. "
         "Required for fresh runs; loaded from disk when ``--resume`` is set.",
     )
+    parser.add_argument(
+        "--mount",
+        type=str,
+        action="append",
+        metavar="PATH",
+        help="Bind-mount a local directory into the sandbox (read-only) instead of "
+        "copying it file-by-file. Use this for large repositories that are too big to "
+        "stream into the container. Can be specified multiple times.",
+    )
     parser.add_argument(
         "--instruction",
         type=str,
@@ -473,9 +488,9 @@ Examples:
     args.user_explicit_instruction = args.instruction if args.resume else None
 
     if args.resume:
-        if args.target:
+        if args.target or args.mount:
             parser.error(
-                "Cannot combine --resume with --target. --resume picks up where "
+                "Cannot combine --resume with --target/--mount. --resume picks up where "
                 "the prior run left off, including the original target list."
             )
         _load_resume_state(args, parser)
@@ -488,13 +503,13 @@ Examples:
                 f"or remove --resume to start over with the same targets."
             )
     else:
-        if not args.target:
+        if not args.target and not args.mount:
             parser.error(
-                "the following arguments are required: -t/--target "
+                "the following arguments are required: -t/--target or --mount "
                 "(or use --resume <run_name> to continue a prior scan)"
             )
         args.targets_info = []
-        for target in args.target:
+        for target in args.target or []:
             try:
                 target_type, target_dict = infer_target_type(target)
 
@@ -509,9 +524,30 @@ Examples:
             except ValueError:
                 parser.error(f"Invalid target '{target}'")
 
+        try:
+            args.targets_info.extend(build_mount_targets_info(args.mount or []))
+        except ValueError as e:
+            parser.error(str(e))
+
+        args.targets_info = dedupe_local_targets(args.targets_info)
+
         assign_workspace_subdirs(args.targets_info)
         rewrite_localhost_targets(args.targets_info, HOST_GATEWAY_HOSTNAME)
 
+        max_local_copy_mb = load_settings().runtime.max_local_copy_mb
+        max_copy_bytes = max_local_copy_mb * 1024 * 1024
+        oversized = find_oversized_local_targets(args.targets_info, max_copy_bytes)
+        if oversized:
+            details = "; ".join(
+                f"{path} ({size / (1024 * 1024):.0f} MB)" for path, size in oversized
+            )
+            parser.error(
+                f"Local target too large to stream into the sandbox: {details}. "
+                f"The limit is {max_local_copy_mb} MB "
+                "(set STRIX_MAX_LOCAL_COPY_MB to change it). Re-run with "
+                "--mount <path> to bind-mount the directory instead of copying it."
+            )
+
     return args
 
 

strix/interface/utils.py

@@ -1,5 +1,6 @@
 import ipaddress
 import json
+import logging
 import os
 import re
 import secrets
@@ -23,6 +24,9 @@ from rich.text import Text
 from strix.config import load_settings
 
 
+logger = logging.getLogger(__name__)
+
+
 def get_severity_color(severity: str) -> str:
     severity_colors = {
         "critical": "#dc2626",
@@ -1185,8 +1189,8 @@ def is_whitebox_scan(targets_info: list[dict[str, Any]]) -> bool:
     return any(t.get("type") == "local_code" for t in targets_info or [])
 
 
-def collect_local_sources(targets_info: list[dict[str, Any]]) -> list[dict[str, str]]:
-    local_sources: list[dict[str, str]] = []
+def collect_local_sources(targets_info: list[dict[str, Any]]) -> list[dict[str, Any]]:
+    local_sources: list[dict[str, Any]] = []
 
     for target_info in targets_info:
         details = target_info["details"]
@@ -1197,6 +1201,7 @@ def collect_local_sources(targets_info: list[dict[str, Any]]) -> list[dict[str,
                 {
                     "source_path": details["target_path"],
                     "workspace_subdir": workspace_subdir,
+                    "mount": bool(details.get("mount", False)),
                 }
             )
 
@@ -1205,12 +1210,126 @@ def collect_local_sources(targets_info: list[dict[str, Any]]) -> list[dict[str,
                 {
                     "source_path": details["cloned_repo_path"],
                     "workspace_subdir": workspace_subdir,
+                    "mount": False,
                 }
             )
 
     return local_sources
 
 
+def directory_size_bytes(path: Path) -> int:
+    """Total size in bytes of regular files under ``path`` (symlinks not followed).
+
+    Best-effort: files that disappear or can't be stat'd mid-walk are skipped.
+    Used as a cheap (stat-only) pre-flight to estimate the cost of streaming a
+    local target into the sandbox before we actually try to copy it.
+
+    Directories that can't be listed (e.g. permission denied) are logged and
+    skipped rather than silently dropped — so an under-count is at least
+    visible — but the returned total then excludes their contents.
+    """
+
+    def _on_walk_error(error: OSError) -> None:
+        logger.warning("Could not read %s while measuring size: %s", error.filename, error)
+
+    total = 0
+    for root, _dirs, files in os.walk(path, followlinks=False, onerror=_on_walk_error):
+        for name in files:
+            file_path = os.path.join(root, name)  # noqa: PTH118
+            try:
+                if os.path.islink(file_path):  # noqa: PTH114
+                    continue
+                total += os.path.getsize(file_path)  # noqa: PTH202
+            except OSError:
+                continue
+    return total
+
+
+def find_oversized_local_targets(
+    targets_info: list[dict[str, Any]], max_bytes: int
+) -> list[tuple[str, int]]:
+    """Return ``(path, size_bytes)`` for non-mounted local targets over ``max_bytes``.
+
+    Mounted targets are bind-mounted rather than copied, so their size is
+    irrelevant and they are excluded. A ``max_bytes`` of zero or less disables
+    the check entirely (returns no targets).
+    """
+    if max_bytes <= 0:
+        return []
+    oversized: list[tuple[str, int]] = []
+    for target in targets_info:
+        if target.get("type") != "local_code":
+            continue
+        details = target.get("details") or {}
+        if details.get("mount"):
+            continue
+        target_path = details.get("target_path")
+        if not target_path:
+            continue
+        size = directory_size_bytes(Path(target_path))
+        if size > max_bytes:
+            oversized.append((target_path, size))
+    return oversized
+
+
+def build_mount_targets_info(mount_paths: list[str]) -> list[dict[str, Any]]:
+    """Build ``targets_info`` entries for ``--mount`` directories.
+
+    Each path must be an existing local directory; it is bind-mounted into the
+    sandbox (read-only) instead of being copied file-by-file. Raises
+    ``ValueError`` for an empty path, or one that does not exist or is not a
+    directory.
+    """
+    targets_info: list[dict[str, Any]] = []
+    for raw in mount_paths:
+        if not raw or not raw.strip():
+            raise ValueError("--mount path must not be empty.")
+        path = Path(raw).expanduser()
+        try:
+            resolved = path.resolve()
+            is_dir = resolved.is_dir()
+        except (OSError, RuntimeError) as e:
+            raise ValueError(f"Invalid mount path '{raw}': {e!s}") from e
+        if not is_dir:
+            raise ValueError(
+                f"Mount path '{raw}' is not an existing directory. "
+                "--mount requires a path to a local directory."
+            )
+        targets_info.append(
+            {
+                "type": "local_code",
+                "details": {"target_path": str(resolved), "mount": True},
+                "original": str(resolved),
+            }
+        )
+    return targets_info
+
+
+def dedupe_local_targets(targets_info: list[dict[str, Any]]) -> list[dict[str, Any]]:
+    """Collapse local_code targets that resolve to the same path.
+
+    When a directory is supplied both as a copied ``--target`` and via
+    ``--mount`` (or as duplicate values of either), keep one entry and prefer
+    the bind-mounted one — so the same tree is never both streamed in and
+    mounted. Order is preserved; non-local targets pass through untouched.
+    """
+    result: list[dict[str, Any]] = []
+    index_by_path: dict[str, int] = {}
+    for target in targets_info:
+        details = target.get("details") or {}
+        path = details.get("target_path")
+        if target.get("type") != "local_code" or not path:
+            result.append(target)
+            continue
+        existing = index_by_path.get(path)
+        if existing is None:
+            index_by_path[path] = len(result)
+            result.append(target)
+        elif details.get("mount") and not (result[existing].get("details") or {}).get("mount"):
+            result[existing] = target  # bind mount supersedes the copied entry
+    return result
+
+
 def _is_localhost_host(host: str) -> bool:
     host_lower = host.lower().strip("[]")