mirror of
https://gitee.com/wanwujie/deer-flow
synced 2026-04-19 04:14:46 +08:00
* 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 - **App** (`app/`): unpublished application code with import prefix `app.*`.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on startup When config.example.yaml schema changes, developers' local config.yaml files can silently become outdated.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> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
95 lines
3.5 KiB
Python
95 lines
3.5 KiB
Python
import base64
|
|
import mimetypes
|
|
from pathlib import Path
|
|
from typing import Annotated
|
|
|
|
from langchain.tools import InjectedToolCallId, ToolRuntime, tool
|
|
from langchain_core.messages import ToolMessage
|
|
from langgraph.types import Command
|
|
from langgraph.typing import ContextT
|
|
|
|
from deerflow.agents.thread_state import ThreadState
|
|
from deerflow.sandbox.tools import get_thread_data, replace_virtual_path
|
|
|
|
|
|
@tool("view_image", parse_docstring=True)
|
|
def view_image_tool(
|
|
runtime: ToolRuntime[ContextT, ThreadState],
|
|
image_path: str,
|
|
tool_call_id: Annotated[str, InjectedToolCallId],
|
|
) -> Command:
|
|
"""Read an image file.
|
|
|
|
Use this tool to read an image file and make it available for display.
|
|
|
|
When to use the view_image tool:
|
|
- When you need to view an image file.
|
|
|
|
When NOT to use the view_image tool:
|
|
- For non-image files (use present_files instead)
|
|
- For multiple files at once (use present_files instead)
|
|
|
|
Args:
|
|
image_path: Absolute path to the image file. Common formats supported: jpg, jpeg, png, webp.
|
|
"""
|
|
# Replace virtual path with actual path
|
|
# /mnt/user-data/* paths are mapped to thread-specific directories
|
|
thread_data = get_thread_data(runtime)
|
|
actual_path = replace_virtual_path(image_path, thread_data)
|
|
|
|
# Validate that the path is absolute
|
|
path = Path(actual_path)
|
|
if not path.is_absolute():
|
|
return Command(
|
|
update={"messages": [ToolMessage(f"Error: Path must be absolute, got: {image_path}", tool_call_id=tool_call_id)]},
|
|
)
|
|
|
|
# Validate that the file exists
|
|
if not path.exists():
|
|
return Command(
|
|
update={"messages": [ToolMessage(f"Error: Image file not found: {image_path}", tool_call_id=tool_call_id)]},
|
|
)
|
|
|
|
# Validate that it's a file (not a directory)
|
|
if not path.is_file():
|
|
return Command(
|
|
update={"messages": [ToolMessage(f"Error: Path is not a file: {image_path}", tool_call_id=tool_call_id)]},
|
|
)
|
|
|
|
# Validate image extension
|
|
valid_extensions = {".jpg", ".jpeg", ".png", ".webp"}
|
|
if path.suffix.lower() not in valid_extensions:
|
|
return Command(
|
|
update={"messages": [ToolMessage(f"Error: Unsupported image format: {path.suffix}. Supported formats: {', '.join(valid_extensions)}", tool_call_id=tool_call_id)]},
|
|
)
|
|
|
|
# Detect MIME type from file extension
|
|
mime_type, _ = mimetypes.guess_type(actual_path)
|
|
if mime_type is None:
|
|
# Fallback to default MIME types for common image formats
|
|
extension_to_mime = {
|
|
".jpg": "image/jpeg",
|
|
".jpeg": "image/jpeg",
|
|
".png": "image/png",
|
|
".webp": "image/webp",
|
|
}
|
|
mime_type = extension_to_mime.get(path.suffix.lower(), "application/octet-stream")
|
|
|
|
# Read image file and convert to base64
|
|
try:
|
|
with open(actual_path, "rb") as f:
|
|
image_data = f.read()
|
|
image_base64 = base64.b64encode(image_data).decode("utf-8")
|
|
except Exception as e:
|
|
return Command(
|
|
update={"messages": [ToolMessage(f"Error reading image file: {str(e)}", tool_call_id=tool_call_id)]},
|
|
)
|
|
|
|
# Update viewed_images in state
|
|
# The merge_viewed_images reducer will handle merging with existing images
|
|
new_viewed_images = {image_path: {"base64": image_base64, "mime_type": mime_type}}
|
|
|
|
return Command(
|
|
update={"viewed_images": new_viewed_images, "messages": [ToolMessage("Successfully read image", tool_call_id=tool_call_id)]},
|
|
)
|