feat: add .zip document support and auto-mount cache dirs into remote backends (#4846)

- Add .zip to SUPPORTED_DOCUMENT_TYPES so gateway platforms (Telegram,
  Slack, Discord) cache uploaded zip files instead of rejecting them.
- Add get_cache_directory_mounts() and iter_cache_files() to
  credential_files.py for host-side cache directory passthrough
  (documents, images, audio, screenshots).
- Docker: bind-mount cache dirs read-only alongside credentials/skills.
  Changes are live (bind mount semantics).
- Modal: mount cache files at sandbox creation + resync before each
  command via _sync_files() with mtime+size change detection.
- Handles backward-compat with legacy dir names (document_cache,
  image_cache, audio_cache, browser_screenshots) via get_hermes_dir().
- Container paths always use the new cache/<subdir> layout regardless
  of host layout.

This replaces the need for a dedicated extract_archive tool (PR #4819)
— the agent can now use standard terminal commands (unzip, tar) on
uploaded files inside remote containers.

Closes: related to PR #4819 by kshitijk4poor

tools/credential_files.py

@@ -1,29 +1,21 @@
-"""Credential file passthrough registry for remote terminal backends.
+"""File passthrough registry for remote terminal backends.
 
-Skills that declare ``required_credential_files`` in their frontmatter need
-those files available inside sandboxed execution environments (Modal, Docker).
-By default remote backends create bare containers with no host files.
+Remote backends (Docker, Modal, SSH) create sandboxes with no host files.
+This module ensures that credential files, skill directories, and host-side
+cache directories (documents, images, audio, screenshots) are mounted or
+synced into those sandboxes so the agent can access them.
 
-This module provides a session-scoped registry so skill-declared credential
-files (and user-configured overrides) are mounted into remote sandboxes.
+**Credentials and skills** — session-scoped registry fed by skill declarations
+(``required_credential_files``) and user config (``terminal.credential_files``).
 
-Two sources feed the registry:
+**Cache directories** — gateway-cached uploads, browser screenshots, TTS
+audio, and processed images.  Mounted read-only so the remote terminal can
+reference files the host side created (e.g. ``unzip`` an uploaded archive).
 
-1. **Skill declarations** — when a skill is loaded via ``skill_view``, its
-   ``required_credential_files`` entries are registered here if the files
-   exist on the host.
-2. **User config** — ``terminal.credential_files`` in config.yaml lets users
-   explicitly list additional files to mount.
-
-Remote backends (``tools/environments/modal.py``, ``docker.py``) call
-:func:`get_credential_file_mounts` at sandbox creation time.
-
-Each registered entry is a dict::
-
-    {
-        "host_path": "/home/user/.hermes/google_token.json",
-        "container_path": "/root/.hermes/google_token.json",
-    }
+Remote backends call :func:`get_credential_file_mounts`,
+:func:`get_skills_directory_mount` / :func:`iter_skills_files`, and
+:func:`get_cache_directory_mounts` / :func:`iter_cache_files` at sandbox
+creation time and before each command (for resync on Modal).
 """
 
 from __future__ import annotations
@@ -300,6 +292,71 @@ def iter_skills_files(
     return result
 
 
+# ---------------------------------------------------------------------------
+# Cache directory mounts (documents, images, audio, screenshots)
+# ---------------------------------------------------------------------------
+
+# The four cache subdirectories that should be mirrored into remote backends.
+# Each tuple is (new_subpath, old_name) matching hermes_constants.get_hermes_dir().
+_CACHE_DIRS: list[tuple[str, str]] = [
+    ("cache/documents", "document_cache"),
+    ("cache/images", "image_cache"),
+    ("cache/audio", "audio_cache"),
+    ("cache/screenshots", "browser_screenshots"),
+]
+
+
+def get_cache_directory_mounts(
+    container_base: str = "/root/.hermes",
+) -> List[Dict[str, str]]:
+    """Return mount entries for each cache directory that exists on disk.
+
+    Used by Docker to create bind mounts.  Each entry has ``host_path`` and
+    ``container_path`` keys.  The host path is resolved via
+    ``get_hermes_dir()`` for backward compatibility with old directory layouts.
+    """
+    from hermes_constants import get_hermes_dir
+
+    mounts: List[Dict[str, str]] = []
+    for new_subpath, old_name in _CACHE_DIRS:
+        host_dir = get_hermes_dir(new_subpath, old_name)
+        if host_dir.is_dir():
+            # Always map to the *new* container layout regardless of host layout.
+            container_path = f"{container_base.rstrip('/')}/{new_subpath}"
+            mounts.append({
+                "host_path": str(host_dir),
+                "container_path": container_path,
+            })
+    return mounts
+
+
+def iter_cache_files(
+    container_base: str = "/root/.hermes",
+) -> List[Dict[str, str]]:
+    """Return individual (host_path, container_path) entries for cache files.
+
+    Used by Modal to upload files individually and resync before each command.
+    Skips symlinks.  The container paths use the new ``cache/<subdir>`` layout.
+    """
+    from hermes_constants import get_hermes_dir
+
+    result: List[Dict[str, str]] = []
+    for new_subpath, old_name in _CACHE_DIRS:
+        host_dir = get_hermes_dir(new_subpath, old_name)
+        if not host_dir.is_dir():
+            continue
+        container_root = f"{container_base.rstrip('/')}/{new_subpath}"
+        for item in host_dir.rglob("*"):
+            if item.is_symlink() or not item.is_file():
+                continue
+            rel = item.relative_to(host_dir)
+            result.append({
+                "host_path": str(item),
+                "container_path": f"{container_root}/{rel}",
+            })
+    return result
+
+
 def clear_credential_files() -> None:
     """Reset the skill-scoped registry (e.g. on session reset)."""
     _registered_files.clear()

tools/environments/docker.py

@@ -315,7 +315,11 @@ class DockerEnvironment(BaseEnvironment):
         # Mount credential files (OAuth tokens, etc.) declared by skills.
         # Read-only so the container can authenticate but not modify host creds.
         try:
-            from tools.credential_files import get_credential_file_mounts, get_skills_directory_mount
+            from tools.credential_files import (
+                get_credential_file_mounts,
+                get_skills_directory_mount,
+                get_cache_directory_mounts,
+            )
 
             for mount_entry in get_credential_file_mounts():
                 volume_args.extend([
@@ -341,6 +345,21 @@ class DockerEnvironment(BaseEnvironment):
                     skills_mount["host_path"],
                     skills_mount["container_path"],
                 )
+
+            # Mount host-side cache directories (documents, images, audio,
+            # screenshots) so the agent can access uploaded files and other
+            # cached media from inside the container.  Read-only — the
+            # container reads these but the host gateway manages writes.
+            for cache_mount in get_cache_directory_mounts():
+                volume_args.extend([
+                    "-v",
+                    f"{cache_mount['host_path']}:{cache_mount['container_path']}:ro",
+                ])
+                logger.info(
+                    "Docker: mounting cache dir %s -> %s",
+                    cache_mount["host_path"],
+                    cache_mount["container_path"],
+                )
         except Exception as e:
             logger.debug("Docker: could not load credential file mounts: %s", e)
 

tools/environments/modal.py

@@ -186,7 +186,11 @@ class ModalEnvironment(BaseModalExecutionEnvironment):
 
         cred_mounts = []
         try:
-            from tools.credential_files import get_credential_file_mounts, iter_skills_files
+            from tools.credential_files import (
+                get_credential_file_mounts,
+                iter_skills_files,
+                iter_cache_files,
+            )
 
             for mount_entry in get_credential_file_mounts():
                 cred_mounts.append(
@@ -212,6 +216,20 @@ class ModalEnvironment(BaseModalExecutionEnvironment):
                 )
             if skills_files:
                 logger.info("Modal: mounting %d skill files", len(skills_files))
+
+            # Mount host-side cache files (documents, images, audio,
+            # screenshots).  New files arriving mid-session are picked up
+            # by _sync_files() before each command execution.
+            cache_files = iter_cache_files()
+            for entry in cache_files:
+                cred_mounts.append(
+                    _modal.Mount.from_local_file(
+                        entry["host_path"],
+                        remote_path=entry["container_path"],
+                    )
+                )
+            if cache_files:
+                logger.info("Modal: mounting %d cache files", len(cache_files))
         except Exception as e:
             logger.debug("Modal: could not load credential file mounts: %s", e)
 
@@ -308,13 +326,19 @@ class ModalEnvironment(BaseModalExecutionEnvironment):
         return True
 
     def _sync_files(self) -> None:
-        """Push credential files and skill files into the running sandbox.
+        """Push credential, skill, and cache files into the running sandbox.
 
         Runs before each command. Uses mtime+size caching so only changed
-        files are pushed (~13μs overhead in the no-op case).
+        files are pushed (~13μs overhead in the no-op case).  Cache files
+        are especially important here — new uploads/screenshots may appear
+        mid-session after sandbox creation.
         """
         try:
-            from tools.credential_files import get_credential_file_mounts, iter_skills_files
+            from tools.credential_files import (
+                get_credential_file_mounts,
+                iter_skills_files,
+                iter_cache_files,
+            )
 
             for entry in get_credential_file_mounts():
                 if self._push_file_to_sandbox(entry["host_path"], entry["container_path"]):
@@ -323,6 +347,10 @@ class ModalEnvironment(BaseModalExecutionEnvironment):
             for entry in iter_skills_files():
                 if self._push_file_to_sandbox(entry["host_path"], entry["container_path"]):
                     logger.debug("Modal: synced skill file %s", entry["container_path"])
+
+            for entry in iter_cache_files():
+                if self._push_file_to_sandbox(entry["host_path"], entry["container_path"]):
+                    logger.debug("Modal: synced cache file %s", entry["container_path"])
         except Exception as e:
             logger.debug("Modal: file sync failed: %s", e)