2026-01-29 08:23:50 +08:00
"""
Image Search Tool - Search images using DuckDuckGo for reference in image generation .
"""
import json
import logging
from langchain . tools import tool
refactor: split backend into harness (deerflow.*) and app (app.*) (#1131)
* 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- **App** (`app/`): unpublished application code with import prefix `app.*`.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>
2026-03-14 22:55:52 +08:00
from deerflow . config import get_app_config
2026-01-29 08:23:50 +08:00
logger = logging . getLogger ( __name__ )
def _search_images (
query : str ,
max_results : int = 5 ,
region : str = " wt-wt " ,
safesearch : str = " moderate " ,
size : str | None = None ,
color : str | None = None ,
type_image : str | None = None ,
layout : str | None = None ,
license_image : str | None = None ,
) - > list [ dict ] :
"""
Execute image search using DuckDuckGo .
Args :
query : Search keywords
max_results : Maximum number of results
region : Search region
safesearch : Safe search level
size : Image size ( Small / Medium / Large / Wallpaper )
color : Color filter
type_image : Image type ( photo / clipart / gif / transparent / line )
layout : Layout ( Square / Tall / Wide )
license_image : License filter
Returns :
List of search results
"""
try :
from ddgs import DDGS
except ImportError :
logger . error ( " ddgs library not installed. Run: pip install ddgs " )
return [ ]
2026-01-29 14:57:26 +08:00
ddgs = DDGS ( timeout = 30 )
2026-01-29 08:23:50 +08:00
try :
kwargs = {
" region " : region ,
" safesearch " : safesearch ,
" max_results " : max_results ,
}
if size :
kwargs [ " size " ] = size
if color :
kwargs [ " color " ] = color
if type_image :
kwargs [ " type_image " ] = type_image
if layout :
kwargs [ " layout " ] = layout
if license_image :
kwargs [ " license_image " ] = license_image
results = ddgs . images ( query , * * kwargs )
return list ( results ) if results else [ ]
except Exception as e :
logger . error ( f " Failed to search images: { e } " )
return [ ]
@tool ( " image_search " , parse_docstring = True )
def image_search_tool (
query : str ,
max_results : int = 5 ,
size : str | None = None ,
type_image : str | None = None ,
layout : str | None = None ,
) - > str :
""" Search for images online. Use this tool BEFORE image generation to find reference images for characters, portraits, objects, scenes, or any content requiring visual accuracy.
* * When to use : * *
- Before generating character / portrait images : search for similar poses , expressions , styles
- Before generating specific objects / products : search for accurate visual references
- Before generating scenes / locations : search for architectural or environmental references
- Before generating fashion / clothing : search for style and detail references
The returned image URLs can be used as reference images in image generation to significantly improve quality .
Args :
query : Search keywords describing the images you want to find . Be specific for better results ( e . g . , " Japanese woman street photography 1990s " instead of just " woman " ) .
max_results : Maximum number of images to return . Default is 5.
size : Image size filter . Options : " Small " , " Medium " , " Large " , " Wallpaper " . Use " Large " for reference images .
type_image : Image type filter . Options : " photo " , " clipart " , " gif " , " transparent " , " line " . Use " photo " for realistic references .
layout : Layout filter . Options : " Square " , " Tall " , " Wide " . Choose based on your generation needs .
"""
config = get_app_config ( ) . get_tool_config ( " image_search " )
# Override max_results from config if set
if config is not None and " max_results " in config . model_extra :
max_results = config . model_extra . get ( " max_results " , max_results )
results = _search_images (
query = query ,
max_results = max_results ,
size = size ,
type_image = type_image ,
layout = layout ,
)
if not results :
return json . dumps ( { " error " : " No images found " , " query " : query } , ensure_ascii = False )
normalized_results = [
{
" title " : r . get ( " title " , " " ) ,
2026-01-29 14:57:26 +08:00
" image_url " : r . get ( " thumbnail " , " " ) ,
2026-01-29 08:23:50 +08:00
" thumbnail_url " : r . get ( " thumbnail " , " " ) ,
}
for r in results
]
output = {
" query " : query ,
" total_results " : len ( normalized_results ) ,
" results " : normalized_results ,
" usage_hint " : " Use the ' image_url ' values as reference images in image generation. Download them first if needed. " ,
}
return json . dumps ( output , indent = 2 , ensure_ascii = False )