Vendored deer-flow upstream (bytedance/deer-flow) plus prompt-injection hardening: - New deerflow.security package: content_delimiter, html_cleaner, sanitizer (8 layers — invisible chars, control chars, symbols, NFC, PUA, tag chars, horizontal whitespace collapse with newline/tab preservation, length cap) - New deerflow.community.searx package: web_search, web_fetch, image_search backed by a private SearX instance, every external string sanitized and wrapped in <<<EXTERNAL_UNTRUSTED_CONTENT>>> delimiters - All native community web providers (ddg_search, tavily, exa, firecrawl, jina_ai, infoquest, image_search) replaced with hard-fail stubs that raise NativeWebToolDisabledError at import time, so a misconfigured tool.use path fails loud rather than silently falling back to unsanitized output - Native client back-doors (jina_client.py, infoquest_client.py) stubbed too - Native-tool tests quarantined under tests/_disabled_native/ (collect_ignore_glob via local conftest.py) - Sanitizer Layer 7 fix: only collapse horizontal whitespace, preserve newlines and tabs so list/table structure survives - Hardened runtime config.yaml references only the searx-backed tools - Factory overlay (backend/) kept in sync with deer-flow tree as a reference / source See HARDENING.md for the full audit trail and verification steps.
42 lines
2.0 KiB
Python
42 lines
2.0 KiB
Python
from pydantic import BaseModel, ConfigDict, Field
|
|
|
|
|
|
class ModelConfig(BaseModel):
|
|
"""Config section for a model"""
|
|
|
|
name: str = Field(..., description="Unique name for the model")
|
|
display_name: str | None = Field(..., default_factory=lambda: None, description="Display name for the model")
|
|
description: str | None = Field(..., default_factory=lambda: None, description="Description for the model")
|
|
use: str = Field(
|
|
...,
|
|
description="Class path of the model provider(e.g. langchain_openai.ChatOpenAI)",
|
|
)
|
|
model: str = Field(..., description="Model name")
|
|
model_config = ConfigDict(extra="allow")
|
|
use_responses_api: bool | None = Field(
|
|
default=None,
|
|
description="Whether to route OpenAI ChatOpenAI calls through the /v1/responses API",
|
|
)
|
|
output_version: str | None = Field(
|
|
default=None,
|
|
description="Structured output version for OpenAI responses content, e.g. responses/v1",
|
|
)
|
|
supports_thinking: bool = Field(default_factory=lambda: False, description="Whether the model supports thinking")
|
|
supports_reasoning_effort: bool = Field(default_factory=lambda: False, description="Whether the model supports reasoning effort")
|
|
when_thinking_enabled: dict | None = Field(
|
|
default_factory=lambda: None,
|
|
description="Extra settings to be passed to the model when thinking is enabled",
|
|
)
|
|
when_thinking_disabled: dict | None = Field(
|
|
default_factory=lambda: None,
|
|
description="Extra settings to be passed to the model when thinking is disabled",
|
|
)
|
|
supports_vision: bool = Field(default_factory=lambda: False, description="Whether the model supports vision/image inputs")
|
|
thinking: dict | None = Field(
|
|
default_factory=lambda: None,
|
|
description=(
|
|
"Thinking settings for the model. If provided, these settings will be passed to the model when thinking is enabled. "
|
|
"This is a shortcut for `when_thinking_enabled` and will be merged with `when_thinking_enabled` if both are provided."
|
|
),
|
|
)
|