refactor: extract shared skill installer and upload manager to harness (#1202)
* refactor: extract shared skill installer and upload manager to harness
Move duplicated business logic from Gateway routers and Client into
shared harness modules, eliminating code duplication.
New shared modules:
- deerflow.skills.installer: 6 functions (zip security, extraction, install)
- deerflow.uploads.manager: 7 functions (normalize, deduplicate, validate,
list, delete, get_uploads_dir, ensure_uploads_dir)
Key improvements:
- SkillAlreadyExistsError replaces stringly-typed 409 status routing
- normalize_filename rejects backslash-containing filenames
- Read paths (list/delete) no longer mkdir via get_uploads_dir
- Write paths use ensure_uploads_dir for explicit directory creation
- list_files_in_dir does stat inside scandir context (no re-stat)
- install_skill_from_archive uses single is_file() check (one syscall)
- Fix agent config key not reset on update_mcp_config/update_skill
Tests: 42 new (22 installer + 20 upload manager) + client hardening
* refactor: centralize upload URL construction and clean up installer
- Extract upload_virtual_path(), upload_artifact_url(), enrich_file_listing()
into shared manager.py, eliminating 6 duplicated URL constructions across
Gateway router and Client
- Derive all upload URLs from VIRTUAL_PATH_PREFIX constant instead of
hardcoded "mnt/user-data/uploads" strings
- Eliminate TOCTOU pre-checks and double file read in installer — single
ZipFile() open with exception handling replaces is_file() + is_zipfile()
+ ZipFile() sequence
- Add missing re-exports: ensure_uploads_dir in uploads/__init__.py,
SkillAlreadyExistsError in skills/__init__.py
- Remove redundant .lower() on already-lowercase CONVERTIBLE_EXTENSIONS
- Hoist sandbox_uploads_dir(thread_id) before loop in uploads router
* fix: add input validation for thread_id and filename length
- Reject thread_id containing unsafe filesystem characters (only allow
alphanumeric, hyphens, underscores, dots) — prevents 500 on inputs
like <script> or shell metacharacters
- Reject filenames longer than 255 bytes (OS limit) in normalize_filename
- Gateway upload router maps ValueError to 400 for invalid thread_id
* fix: address PR review — symlink safety, input validation coverage, error ordering
- list_files_in_dir: use follow_symlinks=False to prevent symlink metadata
leakage; check is_dir() instead of exists() for non-directory paths
- install_skill_from_archive: restore is_file() pre-check before extension
validation so error messages match the documented exception contract
- validate_thread_id: move from ensure_uploads_dir to get_uploads_dir so
all entry points (upload/list/delete) are protected
- delete_uploaded_file: catch ValueError from thread_id validation (was 500)
- requires_llm marker: also skip when OPENAI_API_KEY is unset
- e2e fixture: update TitleMiddleware exclusion comment (kept filtering —
middleware triggers extra LLM calls that add non-determinism to tests)
* chore: revert uv.lock to main — no dependency changes in this PR
* fix: use monkeypatch for global config in e2e fixture to prevent test pollution
The e2e_env fixture was calling set_title_config() and
set_summarization_config() directly, which mutated global singletons
without automatic cleanup. When pytest ran test_client_e2e.py before
test_title_middleware_core_logic.py, the leaked enabled=False caused
5 title tests to fail in CI.
Switched to monkeypatch.setattr on the module-level private variables
so pytest restores the originals after each test.
* fix: address code review — URL encoding, API consistency, test isolation
- upload_artifact_url: percent-encode filename to handle spaces/#/?
- deduplicate_filename: mutate seen set in place (caller no longer
needs manual .add() — less error-prone API)
- list_files_in_dir: document that size is int, enrich stringifies
- e2e fixture: monkeypatch _app_config instead of set_app_config()
to prevent global singleton pollution (same pattern as title/summarization fix)
- _make_e2e_config: read LLM connection details from env vars so
external contributors can override defaults
- Update tests to match new deduplicate_filename contract
* docs: rewrite RFC in English and add alternatives/breaking changes sections
* fix: address code review feedback on PR #1202
- Rename deduplicate_filename to claim_unique_filename to make
the in-place set mutation explicit in the function name
- Replace PermissionError with PathTraversalError(ValueError) for
path traversal detection — malformed input is 400, not 403
* fix: set _app_config_is_custom in e2e test fixture to prevent config.yaml lookup in CI
---------
Co-authored-by: greatmengqi <chenmengqi.0376@bytedance.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: DanielWalnut <45447813+hetaoBackend@users.noreply.github.com>
2026-03-25 16:28:33 +08:00
|
|
|
"""Tests for deerflow.skills.installer — shared skill installation logic."""
|
|
|
|
|
|
|
|
|
|
import stat
|
|
|
|
|
import zipfile
|
|
|
|
|
from pathlib import Path
|
|
|
|
|
|
|
|
|
|
import pytest
|
|
|
|
|
|
|
|
|
|
from deerflow.skills.installer import (
|
|
|
|
|
install_skill_from_archive,
|
|
|
|
|
is_symlink_member,
|
|
|
|
|
is_unsafe_zip_member,
|
|
|
|
|
resolve_skill_dir_from_archive,
|
|
|
|
|
safe_extract_skill_archive,
|
|
|
|
|
should_ignore_archive_entry,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# is_unsafe_zip_member
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestIsUnsafeZipMember:
|
|
|
|
|
def test_absolute_path(self):
|
|
|
|
|
info = zipfile.ZipInfo("/etc/passwd")
|
|
|
|
|
assert is_unsafe_zip_member(info) is True
|
|
|
|
|
|
|
|
|
|
def test_dotdot_traversal(self):
|
|
|
|
|
info = zipfile.ZipInfo("foo/../../../etc/passwd")
|
|
|
|
|
assert is_unsafe_zip_member(info) is True
|
|
|
|
|
|
|
|
|
|
def test_safe_member(self):
|
|
|
|
|
info = zipfile.ZipInfo("my-skill/SKILL.md")
|
|
|
|
|
assert is_unsafe_zip_member(info) is False
|
|
|
|
|
|
|
|
|
|
def test_empty_filename(self):
|
|
|
|
|
info = zipfile.ZipInfo("")
|
|
|
|
|
assert is_unsafe_zip_member(info) is False
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# is_symlink_member
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestIsSymlinkMember:
|
|
|
|
|
def test_detects_symlink(self):
|
|
|
|
|
info = zipfile.ZipInfo("link.txt")
|
|
|
|
|
info.external_attr = (stat.S_IFLNK | 0o777) << 16
|
|
|
|
|
assert is_symlink_member(info) is True
|
|
|
|
|
|
|
|
|
|
def test_regular_file(self):
|
|
|
|
|
info = zipfile.ZipInfo("file.txt")
|
|
|
|
|
info.external_attr = (stat.S_IFREG | 0o644) << 16
|
|
|
|
|
assert is_symlink_member(info) is False
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# should_ignore_archive_entry
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestShouldIgnoreArchiveEntry:
|
|
|
|
|
def test_macosx_ignored(self):
|
|
|
|
|
assert should_ignore_archive_entry(Path("__MACOSX")) is True
|
|
|
|
|
|
|
|
|
|
def test_dotfile_ignored(self):
|
|
|
|
|
assert should_ignore_archive_entry(Path(".DS_Store")) is True
|
|
|
|
|
|
|
|
|
|
def test_normal_dir_not_ignored(self):
|
|
|
|
|
assert should_ignore_archive_entry(Path("my-skill")) is False
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# resolve_skill_dir_from_archive
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestResolveSkillDir:
|
|
|
|
|
def test_single_dir(self, tmp_path):
|
|
|
|
|
(tmp_path / "my-skill").mkdir()
|
|
|
|
|
(tmp_path / "my-skill" / "SKILL.md").write_text("content")
|
|
|
|
|
assert resolve_skill_dir_from_archive(tmp_path) == tmp_path / "my-skill"
|
|
|
|
|
|
|
|
|
|
def test_with_macosx(self, tmp_path):
|
|
|
|
|
(tmp_path / "my-skill").mkdir()
|
|
|
|
|
(tmp_path / "my-skill" / "SKILL.md").write_text("content")
|
|
|
|
|
(tmp_path / "__MACOSX").mkdir()
|
|
|
|
|
assert resolve_skill_dir_from_archive(tmp_path) == tmp_path / "my-skill"
|
|
|
|
|
|
|
|
|
|
def test_empty_after_filter(self, tmp_path):
|
|
|
|
|
(tmp_path / "__MACOSX").mkdir()
|
|
|
|
|
(tmp_path / ".DS_Store").write_text("meta")
|
|
|
|
|
with pytest.raises(ValueError, match="empty"):
|
|
|
|
|
resolve_skill_dir_from_archive(tmp_path)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# safe_extract_skill_archive
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestSafeExtract:
|
|
|
|
|
def _make_zip(self, tmp_path, members: dict[str, str | bytes]) -> Path:
|
|
|
|
|
"""Create a zip with given filename->content entries."""
|
|
|
|
|
zip_path = tmp_path / "test.zip"
|
|
|
|
|
with zipfile.ZipFile(zip_path, "w") as zf:
|
|
|
|
|
for name, content in members.items():
|
|
|
|
|
if isinstance(content, str):
|
|
|
|
|
content = content.encode()
|
|
|
|
|
zf.writestr(name, content)
|
|
|
|
|
return zip_path
|
|
|
|
|
|
|
|
|
|
def test_rejects_zip_bomb(self, tmp_path):
|
|
|
|
|
zip_path = self._make_zip(tmp_path, {"big.txt": "x" * 1000})
|
|
|
|
|
dest = tmp_path / "out"
|
|
|
|
|
dest.mkdir()
|
|
|
|
|
with zipfile.ZipFile(zip_path) as zf:
|
|
|
|
|
with pytest.raises(ValueError, match="too large"):
|
|
|
|
|
safe_extract_skill_archive(zf, dest, max_total_size=100)
|
|
|
|
|
|
|
|
|
|
def test_rejects_absolute_path(self, tmp_path):
|
|
|
|
|
zip_path = tmp_path / "abs.zip"
|
|
|
|
|
with zipfile.ZipFile(zip_path, "w") as zf:
|
|
|
|
|
zf.writestr("/etc/passwd", "root:x:0:0")
|
|
|
|
|
dest = tmp_path / "out"
|
|
|
|
|
dest.mkdir()
|
|
|
|
|
with zipfile.ZipFile(zip_path) as zf:
|
|
|
|
|
with pytest.raises(ValueError, match="unsafe"):
|
|
|
|
|
safe_extract_skill_archive(zf, dest)
|
|
|
|
|
|
|
|
|
|
def test_skips_symlinks(self, tmp_path):
|
|
|
|
|
zip_path = tmp_path / "sym.zip"
|
|
|
|
|
with zipfile.ZipFile(zip_path, "w") as zf:
|
|
|
|
|
info = zipfile.ZipInfo("link.txt")
|
|
|
|
|
info.external_attr = (stat.S_IFLNK | 0o777) << 16
|
|
|
|
|
zf.writestr(info, "/etc/passwd")
|
|
|
|
|
zf.writestr("normal.txt", "hello")
|
|
|
|
|
dest = tmp_path / "out"
|
|
|
|
|
dest.mkdir()
|
|
|
|
|
with zipfile.ZipFile(zip_path) as zf:
|
|
|
|
|
safe_extract_skill_archive(zf, dest)
|
|
|
|
|
assert (dest / "normal.txt").exists()
|
|
|
|
|
assert not (dest / "link.txt").exists()
|
|
|
|
|
|
|
|
|
|
def test_normal_archive(self, tmp_path):
|
feat(harness): integration ACP agent tool (#1344)
* refactor: extract shared utils to break harness→app cross-layer imports
Move _validate_skill_frontmatter to src/skills/validation.py and
CONVERTIBLE_EXTENSIONS + convert_file_to_markdown to src/utils/file_conversion.py.
This eliminates the two reverse dependencies from client.py (harness layer)
into gateway/routers/ (app layer), preparing for the harness/app package split.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: split backend/src into harness (deerflow.*) and app (app.*)
Physically split the monolithic backend/src/ package into two layers:
- **Harness** (`packages/harness/deerflow/`): publishable agent framework
package with import prefix `deerflow.*`. Contains agents, sandbox, tools,
models, MCP, skills, config, and all core infrastructure.
- **App** (`app/`): unpublished application code with import prefix `app.*`.
Contains gateway (FastAPI REST API) and channels (IM integrations).
Key changes:
- Move 13 harness modules to packages/harness/deerflow/ via git mv
- Move gateway + channels to app/ via git mv
- Rename all imports: src.* → deerflow.* (harness) / app.* (app layer)
- Set up uv workspace with deerflow-harness as workspace member
- Update langgraph.json, config.example.yaml, all scripts, Docker files
- Add build-system (hatchling) to harness pyproject.toml
- Add PYTHONPATH=. to gateway startup commands for app.* resolution
- Update ruff.toml with known-first-party for import sorting
- Update all documentation to reflect new directory structure
Boundary rule enforced: harness code never imports from app.
All 429 tests pass. Lint clean.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore: add harness→app boundary check test and update docs
Add test_harness_boundary.py that scans all Python files in
packages/harness/deerflow/ and fails if any `from app.*` or
`import app.*` statement is found. This enforces the architectural
rule that the harness layer never depends on the app layer.
Update CLAUDE.md to document the harness/app split architecture,
import conventions, and the boundary enforcement test.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add config versioning with auto-upgrade on startup
When config.example.yaml schema changes, developers' local config.yaml
files can silently become outdated. This adds a config_version field and
auto-upgrade mechanism so breaking changes (like src.* → deerflow.*
renames) are applied automatically before services start.
- Add config_version: 1 to config.example.yaml
- Add startup version check warning in AppConfig.from_file()
- Add scripts/config-upgrade.sh with migration registry for value replacements
- Add `make config-upgrade` target
- Auto-run config-upgrade in serve.sh and start-daemon.sh before starting services
- Add config error hints in service failure messages
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix comments
* fix: update src.* import in test_sandbox_tools_security to deerflow.*
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: handle empty config and search parent dirs for config.example.yaml
Address Copilot review comments on PR #1131:
- Guard against yaml.safe_load() returning None for empty config files
- Search parent directories for config.example.yaml instead of only
looking next to config.yaml, fixing detection in common setups
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: correct skills root path depth and config_version type coercion
- loader.py: fix get_skills_root_path() to use 5 parent levels (was 3)
after harness split, file lives at packages/harness/deerflow/skills/
so parent×3 resolved to backend/packages/harness/ instead of backend/
- app_config.py: coerce config_version to int() before comparison in
_check_config_version() to prevent TypeError when YAML stores value
as string (e.g. config_version: "1")
- tests: add regression tests for both fixes
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: update test imports from src.* to deerflow.*/app.* after harness refactor
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(harness): add tool-first ACP agent invocation (#37)
* feat(harness): add tool-first ACP agent invocation
* build(harness): make ACP dependency required
* fix(harness): address ACP review feedback
* feat(harness): decouple ACP agent workspace from thread data
ACP agents (codex, claude-code) previously used per-thread workspace
directories, causing path resolution complexity and coupling task
execution to DeerFlow's internal thread data layout. This change:
- Replace _resolve_cwd() with a fixed _get_work_dir() that always uses
{base_dir}/acp-workspace/, eliminating virtual path translation and
thread_id lookups
- Introduce /mnt/acp-workspace virtual path for lead agent read-only
access to ACP agent output files (same pattern as /mnt/skills)
- Add security guards: read-only validation, path traversal prevention,
command path allowlisting, and output masking for acp-workspace
- Update system prompt and tool description to guide LLM: send
self-contained tasks to ACP agents, copy results via /mnt/acp-workspace
- Add 11 new security tests for ACP workspace path handling
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor(prompt): inject ACP section only when ACP agents are configured
The ACP agent guidance in the system prompt is now conditionally built
by _build_acp_section(), which checks get_acp_agents() and returns an
empty string when no ACP agents are configured. This avoids polluting
the prompt with irrelevant instructions for users who don't use ACP.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix lint
* fix(harness): address Copilot review comments on sandbox path handling and ACP tool
- local_sandbox: fix path-segment boundary bug in _resolve_path (== or startswith +"/")
and add lookahead in _resolve_paths_in_command regex to prevent /mnt/skills matching
inside /mnt/skills-extra
- local_sandbox_provider: replace print() with logger.warning(..., exc_info=True)
- invoke_acp_agent_tool: guard getattr(option, "optionId") with None default + continue;
move full prompt from INFO to DEBUG level (truncated to 200 chars)
- sandbox/tools: fix _get_acp_workspace_host_path docstring to match implementation;
remove misleading "read-only" language from validate_local_bash_command_paths
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(acp): thread-isolated workspaces, permission guardrail, and ContextVar registry
P1.1 – ACP workspace thread isolation
- Add `Paths.acp_workspace_dir(thread_id)` for per-thread paths
- `_get_work_dir(thread_id)` in invoke_acp_agent_tool now uses
`{base_dir}/threads/{thread_id}/acp-workspace/`; falls back to
global workspace when thread_id is absent or invalid
- `_invoke` extracts thread_id from `RunnableConfig` via
`Annotated[RunnableConfig, InjectedToolArg]`
- `sandbox/tools.py`: `_get_acp_workspace_host_path(thread_id)`,
`_resolve_acp_workspace_path(path, thread_id)`, and all callers
(`replace_virtual_paths_in_command`, `mask_local_paths_in_output`,
`ls_tool`, `read_file_tool`) now resolve ACP paths per-thread
P1.2 – ACP permission guardrail
- New `auto_approve_permissions: bool = False` field in `ACPAgentConfig`
- `_build_permission_response(options, *, auto_approve: bool)` now
defaults to deny; only approves when `auto_approve=True`
- Document field in `config.example.yaml`
P2 – Deferred tool registry race condition
- Replace module-level `_registry` global with `contextvars.ContextVar`
- Each asyncio request context gets its own registry; worker threads
inherit the context automatically via `loop.run_in_executor`
- Expose `get_deferred_registry` / `set_deferred_registry` /
`reset_deferred_registry` helpers
Tests: 831 pass (57 for affected modules, 3 new tests)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(sandbox): mount /mnt/acp-workspace in docker sandbox container
The AioSandboxProvider was not mounting the ACP workspace into the
sandbox container, so /mnt/acp-workspace was inaccessible when the lead
agent tried to read ACP results in docker mode.
Changes:
- `ensure_thread_dirs`: also create `acp-workspace/` (chmod 0o777) so
the directory exists before the sandbox container starts — required
for Docker volume mounts
- `_get_thread_mounts`: add read-only `/mnt/acp-workspace` mount using
the per-thread host path (`host_paths.acp_workspace_dir(thread_id)`)
- Update stale CLAUDE.md description (was "fixed global workspace")
Tests: `test_aio_sandbox_provider.py` (4 new tests)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(lint): remove unused imports in test_aio_sandbox_provider
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix config
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-26 14:20:18 +08:00
|
|
|
zip_path = self._make_zip(
|
|
|
|
|
tmp_path,
|
|
|
|
|
{
|
|
|
|
|
"my-skill/SKILL.md": "---\nname: test\ndescription: x\n---\n# Test",
|
|
|
|
|
"my-skill/README.md": "readme",
|
|
|
|
|
},
|
|
|
|
|
)
|
refactor: extract shared skill installer and upload manager to harness (#1202)
* refactor: extract shared skill installer and upload manager to harness
Move duplicated business logic from Gateway routers and Client into
shared harness modules, eliminating code duplication.
New shared modules:
- deerflow.skills.installer: 6 functions (zip security, extraction, install)
- deerflow.uploads.manager: 7 functions (normalize, deduplicate, validate,
list, delete, get_uploads_dir, ensure_uploads_dir)
Key improvements:
- SkillAlreadyExistsError replaces stringly-typed 409 status routing
- normalize_filename rejects backslash-containing filenames
- Read paths (list/delete) no longer mkdir via get_uploads_dir
- Write paths use ensure_uploads_dir for explicit directory creation
- list_files_in_dir does stat inside scandir context (no re-stat)
- install_skill_from_archive uses single is_file() check (one syscall)
- Fix agent config key not reset on update_mcp_config/update_skill
Tests: 42 new (22 installer + 20 upload manager) + client hardening
* refactor: centralize upload URL construction and clean up installer
- Extract upload_virtual_path(), upload_artifact_url(), enrich_file_listing()
into shared manager.py, eliminating 6 duplicated URL constructions across
Gateway router and Client
- Derive all upload URLs from VIRTUAL_PATH_PREFIX constant instead of
hardcoded "mnt/user-data/uploads" strings
- Eliminate TOCTOU pre-checks and double file read in installer — single
ZipFile() open with exception handling replaces is_file() + is_zipfile()
+ ZipFile() sequence
- Add missing re-exports: ensure_uploads_dir in uploads/__init__.py,
SkillAlreadyExistsError in skills/__init__.py
- Remove redundant .lower() on already-lowercase CONVERTIBLE_EXTENSIONS
- Hoist sandbox_uploads_dir(thread_id) before loop in uploads router
* fix: add input validation for thread_id and filename length
- Reject thread_id containing unsafe filesystem characters (only allow
alphanumeric, hyphens, underscores, dots) — prevents 500 on inputs
like <script> or shell metacharacters
- Reject filenames longer than 255 bytes (OS limit) in normalize_filename
- Gateway upload router maps ValueError to 400 for invalid thread_id
* fix: address PR review — symlink safety, input validation coverage, error ordering
- list_files_in_dir: use follow_symlinks=False to prevent symlink metadata
leakage; check is_dir() instead of exists() for non-directory paths
- install_skill_from_archive: restore is_file() pre-check before extension
validation so error messages match the documented exception contract
- validate_thread_id: move from ensure_uploads_dir to get_uploads_dir so
all entry points (upload/list/delete) are protected
- delete_uploaded_file: catch ValueError from thread_id validation (was 500)
- requires_llm marker: also skip when OPENAI_API_KEY is unset
- e2e fixture: update TitleMiddleware exclusion comment (kept filtering —
middleware triggers extra LLM calls that add non-determinism to tests)
* chore: revert uv.lock to main — no dependency changes in this PR
* fix: use monkeypatch for global config in e2e fixture to prevent test pollution
The e2e_env fixture was calling set_title_config() and
set_summarization_config() directly, which mutated global singletons
without automatic cleanup. When pytest ran test_client_e2e.py before
test_title_middleware_core_logic.py, the leaked enabled=False caused
5 title tests to fail in CI.
Switched to monkeypatch.setattr on the module-level private variables
so pytest restores the originals after each test.
* fix: address code review — URL encoding, API consistency, test isolation
- upload_artifact_url: percent-encode filename to handle spaces/#/?
- deduplicate_filename: mutate seen set in place (caller no longer
needs manual .add() — less error-prone API)
- list_files_in_dir: document that size is int, enrich stringifies
- e2e fixture: monkeypatch _app_config instead of set_app_config()
to prevent global singleton pollution (same pattern as title/summarization fix)
- _make_e2e_config: read LLM connection details from env vars so
external contributors can override defaults
- Update tests to match new deduplicate_filename contract
* docs: rewrite RFC in English and add alternatives/breaking changes sections
* fix: address code review feedback on PR #1202
- Rename deduplicate_filename to claim_unique_filename to make
the in-place set mutation explicit in the function name
- Replace PermissionError with PathTraversalError(ValueError) for
path traversal detection — malformed input is 400, not 403
* fix: set _app_config_is_custom in e2e test fixture to prevent config.yaml lookup in CI
---------
Co-authored-by: greatmengqi <chenmengqi.0376@bytedance.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: DanielWalnut <45447813+hetaoBackend@users.noreply.github.com>
2026-03-25 16:28:33 +08:00
|
|
|
dest = tmp_path / "out"
|
|
|
|
|
dest.mkdir()
|
|
|
|
|
with zipfile.ZipFile(zip_path) as zf:
|
|
|
|
|
safe_extract_skill_archive(zf, dest)
|
|
|
|
|
assert (dest / "my-skill" / "SKILL.md").exists()
|
|
|
|
|
assert (dest / "my-skill" / "README.md").exists()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# install_skill_from_archive (full integration)
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestInstallSkillFromArchive:
|
|
|
|
|
def _make_skill_zip(self, tmp_path: Path, skill_name: str = "test-skill") -> Path:
|
|
|
|
|
"""Create a valid .skill archive."""
|
|
|
|
|
zip_path = tmp_path / f"{skill_name}.skill"
|
|
|
|
|
with zipfile.ZipFile(zip_path, "w") as zf:
|
|
|
|
|
zf.writestr(
|
|
|
|
|
f"{skill_name}/SKILL.md",
|
|
|
|
|
f"---\nname: {skill_name}\ndescription: A test skill\n---\n\n# {skill_name}\n",
|
|
|
|
|
)
|
|
|
|
|
return zip_path
|
|
|
|
|
|
|
|
|
|
def test_success(self, tmp_path):
|
|
|
|
|
zip_path = self._make_skill_zip(tmp_path)
|
|
|
|
|
skills_root = tmp_path / "skills"
|
|
|
|
|
skills_root.mkdir()
|
|
|
|
|
result = install_skill_from_archive(zip_path, skills_root=skills_root)
|
|
|
|
|
assert result["success"] is True
|
|
|
|
|
assert result["skill_name"] == "test-skill"
|
|
|
|
|
assert (skills_root / "custom" / "test-skill" / "SKILL.md").exists()
|
|
|
|
|
|
|
|
|
|
def test_duplicate_raises(self, tmp_path):
|
|
|
|
|
zip_path = self._make_skill_zip(tmp_path)
|
|
|
|
|
skills_root = tmp_path / "skills"
|
|
|
|
|
(skills_root / "custom" / "test-skill").mkdir(parents=True)
|
|
|
|
|
with pytest.raises(ValueError, match="already exists"):
|
|
|
|
|
install_skill_from_archive(zip_path, skills_root=skills_root)
|
|
|
|
|
|
|
|
|
|
def test_invalid_extension(self, tmp_path):
|
|
|
|
|
bad_path = tmp_path / "bad.zip"
|
|
|
|
|
bad_path.write_text("not a skill")
|
|
|
|
|
with pytest.raises(ValueError, match=".skill"):
|
|
|
|
|
install_skill_from_archive(bad_path)
|
|
|
|
|
|
|
|
|
|
def test_bad_frontmatter(self, tmp_path):
|
|
|
|
|
zip_path = tmp_path / "bad.skill"
|
|
|
|
|
with zipfile.ZipFile(zip_path, "w") as zf:
|
|
|
|
|
zf.writestr("bad/SKILL.md", "no frontmatter here")
|
|
|
|
|
skills_root = tmp_path / "skills"
|
|
|
|
|
skills_root.mkdir()
|
|
|
|
|
with pytest.raises(ValueError, match="Invalid skill"):
|
|
|
|
|
install_skill_from_archive(zip_path, skills_root=skills_root)
|
|
|
|
|
|
|
|
|
|
def test_nonexistent_file(self):
|
|
|
|
|
with pytest.raises(FileNotFoundError):
|
|
|
|
|
install_skill_from_archive(Path("/nonexistent/path.skill"))
|
|
|
|
|
|
|
|
|
|
def test_macosx_filtered_during_resolve(self, tmp_path):
|
|
|
|
|
"""Archive with __MACOSX dir still installs correctly."""
|
|
|
|
|
zip_path = tmp_path / "mac.skill"
|
|
|
|
|
with zipfile.ZipFile(zip_path, "w") as zf:
|
|
|
|
|
zf.writestr("my-skill/SKILL.md", "---\nname: my-skill\ndescription: desc\n---\n# My Skill\n")
|
|
|
|
|
zf.writestr("__MACOSX/._my-skill", "meta")
|
|
|
|
|
skills_root = tmp_path / "skills"
|
|
|
|
|
skills_root.mkdir()
|
|
|
|
|
result = install_skill_from_archive(zip_path, skills_root=skills_root)
|
|
|
|
|
assert result["success"] is True
|
|
|
|
|
assert result["skill_name"] == "my-skill"
|