common/hermes
2
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

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

Browse Source 
- 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
This commit is contained in:
Teknium
2026-04-03 13:16:26 -07:00
committed by GitHub
parent 8a384628a5
commit b1756084a3
9 changed files with 274 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
tests/gateway/test_discord_document_handling.py
View File

@@ -227,16 +227,19 @@ class TestIncomingDocumentHandling:
adapter.handle_message.assert_called_once()
@pytest.mark.asyncio
async def test_unsupported_type_skipped(self, adapter):
"""An unsupported file type (.zip) should be skipped silently."""
async def test_zip_document_cached(self, adapter):
"""A .zip file should be cached as a supported document."""
msg = make_message([
make_attachment(filename="archive.zip", content_type="application/zip")
])
await adapter._handle_message(msg)
with _mock_aiohttp_download(b"PK\x03\x04test"):
await adapter._handle_message(msg)
event = adapter.handle_message.call_args[0][0]
assert event.media_urls == []
assert event.message_type == MessageType.TEXT
assert len(event.media_urls) == 1
assert event.media_types == ["application/zip"]
assert event.message_type == MessageType.DOCUMENT
@pytest.mark.asyncio
async def test_download_error_handled(self, adapter):

2
tests/gateway/test_document_cache.py
View File

@@ -151,7 +151,7 @@ class TestSupportedDocumentTypes:
@pytest.mark.parametrize(
"ext",
[".pdf", ".md", ".txt", ".docx", ".xlsx", ".pptx"],
[".pdf", ".md", ".txt", ".zip", ".docx", ".xlsx", ".pptx"],
)
def test_expected_extensions_present(self, ext):
assert ext in SUPPORTED_DOCUMENT_TYPES

25
tests/gateway/test_slack.py
View File

@@ -408,19 +408,22 @@ class TestIncomingDocumentHandling:
assert "[Content of" not in (msg_event.text or "")
@pytest.mark.asyncio
async def test_unsupported_file_type_skipped(self, adapter):
"""A .zip file should be silently skipped."""
event = self._make_event(files=[{
"mimetype": "application/zip",
"name": "archive.zip",
"url_private_download": "https://files.slack.com/archive.zip",
"size": 1024,
}])
await adapter._handle_slack_message(event)
async def test_zip_file_cached(self, adapter):
"""A .zip file should be cached as a supported document."""
with patch.object(adapter, "_download_slack_file_bytes", new_callable=AsyncMock) as dl:
dl.return_value = b"PK\x03\x04zip"
event = self._make_event(files=[{
"mimetype": "application/zip",
"name": "archive.zip",
"url_private_download": "https://files.slack.com/archive.zip",
"size": 1024,
}])
await adapter._handle_slack_message(event)
msg_event = adapter.handle_message.call_args[0][0]
assert msg_event.message_type == MessageType.TEXT
assert len(msg_event.media_urls) == 0
assert msg_event.message_type == MessageType.DOCUMENT
assert len(msg_event.media_urls) == 1
assert msg_event.media_types == ["application/zip"]
@pytest.mark.asyncio
async def test_oversized_document_skipped(self, adapter):

7
tests/gateway/test_telegram_documents.py
View File

@@ -236,15 +236,16 @@ class TestDocumentDownloadBlock:
assert "Please summarize" in event.text
@pytest.mark.asyncio
async def test_unsupported_type_rejected(self, adapter):
async def test_zip_document_cached(self, adapter):
"""A .zip upload should be cached as a supported document."""
doc = _make_document(file_name="archive.zip", mime_type="application/zip", file_size=100)
msg = _make_message(document=doc)
update = _make_update(msg)
await adapter._handle_media_message(update, MagicMock())
event = adapter.handle_message.call_args[0][0]
assert "Unsupported document type" in event.text
assert ".zip" in event.text
assert event.media_urls and event.media_urls[0].endswith("archive.zip")
assert event.media_types == ["application/zip"]
@pytest.mark.asyncio
async def test_oversized_file_rejected(self, adapter):

115
tests/tools/test_credential_files.py
View File

@@ -10,7 +10,9 @@ import pytest
from tools.credential_files import (
clear_credential_files,
get_credential_file_mounts,
get_cache_directory_mounts,
get_skills_directory_mount,
iter_cache_files,
iter_skills_files,
register_credential_file,
register_credential_files,
@@ -358,3 +360,116 @@ class TestConfigPathTraversal:
mounts = get_credential_file_mounts()
assert len(mounts) == 1
assert "oauth.json" in mounts[0]["container_path"]
# ---------------------------------------------------------------------------
# Cache directory mounts
# ---------------------------------------------------------------------------
class TestCacheDirectoryMounts:
"""Tests for get_cache_directory_mounts() and iter_cache_files()."""
def test_returns_existing_cache_dirs(self, tmp_path, monkeypatch):
"""Existing cache dirs are returned with correct container paths."""
hermes_home = tmp_path / ".hermes"
hermes_home.mkdir()
(hermes_home / "cache" / "documents").mkdir(parents=True)
(hermes_home / "cache" / "audio").mkdir(parents=True)
monkeypatch.setenv("HERMES_HOME", str(hermes_home))
mounts = get_cache_directory_mounts()
paths = {m["container_path"] for m in mounts}
assert "/root/.hermes/cache/documents" in paths
assert "/root/.hermes/cache/audio" in paths
def test_skips_nonexistent_dirs(self, tmp_path, monkeypatch):
"""Dirs that don't exist on disk are not returned."""
hermes_home = tmp_path / ".hermes"
hermes_home.mkdir()
# Create only one cache dir
(hermes_home / "cache" / "documents").mkdir(parents=True)
monkeypatch.setenv("HERMES_HOME", str(hermes_home))
mounts = get_cache_directory_mounts()
assert len(mounts) == 1
assert mounts[0]["container_path"] == "/root/.hermes/cache/documents"
def test_legacy_dir_names_resolved(self, tmp_path, monkeypatch):
"""Old-style dir names (e.g. document_cache) are resolved correctly."""
hermes_home = tmp_path / ".hermes"
hermes_home.mkdir()
# Use legacy dir name — get_hermes_dir prefers old if it exists
(hermes_home / "document_cache").mkdir()
(hermes_home / "image_cache").mkdir()
monkeypatch.setenv("HERMES_HOME", str(hermes_home))
mounts = get_cache_directory_mounts()
host_paths = {m["host_path"] for m in mounts}
assert str(hermes_home / "document_cache") in host_paths
assert str(hermes_home / "image_cache") in host_paths
# Container paths always use the new layout
container_paths = {m["container_path"] for m in mounts}
assert "/root/.hermes/cache/documents" in container_paths
assert "/root/.hermes/cache/images" in container_paths
def test_empty_hermes_home(self, tmp_path, monkeypatch):
"""No cache dirs → empty list."""
hermes_home = tmp_path / ".hermes"
hermes_home.mkdir()
monkeypatch.setenv("HERMES_HOME", str(hermes_home))
assert get_cache_directory_mounts() == []
class TestIterCacheFiles:
"""Tests for iter_cache_files()."""
def test_enumerates_files(self, tmp_path, monkeypatch):
"""Regular files in cache dirs are returned."""
hermes_home = tmp_path / ".hermes"
doc_dir = hermes_home / "cache" / "documents"
doc_dir.mkdir(parents=True)
(doc_dir / "upload.zip").write_bytes(b"PK\x03\x04")
(doc_dir / "report.pdf").write_bytes(b"%PDF-1.4")
monkeypatch.setenv("HERMES_HOME", str(hermes_home))
entries = iter_cache_files()
names = {Path(e["container_path"]).name for e in entries}
assert "upload.zip" in names
assert "report.pdf" in names
def test_skips_symlinks(self, tmp_path, monkeypatch):
"""Symlinks inside cache dirs are skipped."""
hermes_home = tmp_path / ".hermes"
doc_dir = hermes_home / "cache" / "documents"
doc_dir.mkdir(parents=True)
real_file = doc_dir / "real.txt"
real_file.write_text("content")
(doc_dir / "link.txt").symlink_to(real_file)
monkeypatch.setenv("HERMES_HOME", str(hermes_home))
entries = iter_cache_files()
names = [Path(e["container_path"]).name for e in entries]
assert "real.txt" in names
assert "link.txt" not in names
def test_nested_files(self, tmp_path, monkeypatch):
"""Files in subdirectories are included with correct relative paths."""
hermes_home = tmp_path / ".hermes"
ss_dir = hermes_home / "cache" / "screenshots"
sub = ss_dir / "session_abc"
sub.mkdir(parents=True)
(sub / "screen1.png").write_bytes(b"PNG")
monkeypatch.setenv("HERMES_HOME", str(hermes_home))
entries = iter_cache_files()
assert len(entries) == 1
assert entries[0]["container_path"] == "/root/.hermes/cache/screenshots/session_abc/screen1.png"
def test_empty_cache(self, tmp_path, monkeypatch):
"""No cache dirs → empty list."""
hermes_home = tmp_path / ".hermes"
hermes_home.mkdir()
monkeypatch.setenv("HERMES_HOME", str(hermes_home))
assert iter_cache_files() == []