Merge remote-tracking branch 'origin/master' into xuhd

# Conflicts:
#	frontend-web/.env.production
#	frontend-web/.env.sit
#	frontend-web/package.json
#	offline-backend-20260512/backend/config.yaml
This commit is contained in:
xuhd committed 2026-06-11 14:19:01 +08:00
commit 1668c1da87
177 files changed
+21030 -2738

No files matched your search

@@ -10,11 +10,13 @@ from pydantic import BaseModel, ConfigDict, Field
from deerflow.config.acp_config import ACPAgentConfig, load_acp_config_from_dict
from deerflow.config.agents_api_config import AgentsApiConfig, load_agents_api_config_from_dict
from deerflow.config.browser_context_config import BrowserContextConfig
from deerflow.config.checkpointer_config import CheckpointerConfig, load_checkpointer_config_from_dict
from deerflow.config.database_config import DatabaseConfig
from deerflow.config.extensions_config import ExtensionsConfig
from deerflow.config.gateway_config import GatewayConfig
from deerflow.config.guardrails_config import GuardrailsConfig, load_guardrails_config_from_dict
from deerflow.config.knowledge_config import KnowledgeConfig
from deerflow.config.log_system_config import LogSystemConfig
from deerflow.config.login_config import AuthLoginConfig
from deerflow.config.memory_config import MemoryConfig, load_memory_config_from_dict
@@ -133,6 +135,8 @@ class AppConfig(BaseModel):
run_events: RunEventsConfig = Field(default_factory=RunEventsConfig, description="Run event storage configuration")
checkpointer: CheckpointerConfig | None = Field(default=None, description="Checkpointer configuration")
stream_bridge: StreamBridgeConfig | None = Field(default=None, description="Stream bridge configuration")
browser_context: BrowserContextConfig = Field(default_factory=BrowserContextConfig, description="Optional browser page capture integration")
knowledge: KnowledgeConfig = Field(default_factory=KnowledgeConfig, description="Product knowledge base (obsidian-wiki compatible vault) configuration")
@classmethod
def resolve_config_path(cls, config_path: str | None = None) -> Path:
@@ -0,0 +1,74 @@
"""Configuration for browser page context capture."""
from pydantic import BaseModel, Field
class BrowserContextConfig(BaseModel):
"""Controls the optional Chrome-extension page capture integration."""
enabled: bool = Field(
default=False,
description="Enable /api/browser-context endpoints for Chrome extension page capture.",
)
max_content_chars: int = Field(
default=200_000,
ge=1_000,
description="Maximum captured page text stored per request. Longer content is truncated.",
)
max_title_chars: int = Field(
default=300,
ge=20,
description="Maximum title length accepted from the browser extension.",
)
max_url_chars: int = Field(
default=2_048,
ge=100,
description="Maximum source URL length accepted from the browser extension.",
)
filename_prefix: str = Field(
default="webpage",
description="Prefix used for Markdown files created from captured pages.",
)
route_base: str = Field(
default="/page/workspace",
description="Frontend route base used when returning chat paths to the extension.",
)
task_result_timeout_seconds: int = Field(
default=60,
ge=5,
description="Maximum time the browser_fetch_page tool waits for the extension result.",
)
task_poll_interval_seconds: float = Field(
default=1.0,
ge=0.25,
description="How often the backend tool checks for a returned browser task result.",
)
task_lease_seconds: int = Field(
default=120,
ge=10,
description="How long a claimed browser task is reserved before another extension may retry it.",
)
tool_result_max_chars: int = Field(
default=60_000,
ge=1_000,
description="Maximum page characters returned from browser_fetch_page into the model context.",
)
actions_enabled: bool = Field(
default=True,
description="Enable the interactive browser_act tool (click/type/scroll/wait/navigate on the user's page).",
)
action_result_timeout_seconds: int = Field(
default=45,
ge=5,
description="Maximum time the browser_act tool waits for the extension to perform one step and return an observation.",
)
max_observed_elements: int = Field(
default=150,
ge=10,
description="Maximum number of interactive elements returned in a browser_act observation.",
)
observation_text_max_chars: int = Field(
default=12_000,
ge=500,
description="Maximum page text characters returned alongside a browser_act observation.",
)
@@ -3,7 +3,7 @@
import json
import os
from pathlib import Path
from typing import Any, Literal
from typing import Any, Literal
from pydantic import BaseModel, ConfigDict, Field
@@ -53,115 +53,115 @@ class McpServerConfig(BaseModel):
model_config = ConfigDict(extra="allow", populate_by_name=True)
class SkillDisplayTableColumn(BaseModel):
"""A configured table column for structured skill result display."""
label: str = Field(description="Column label shown in the frontend table")
field: str = Field(description="Field name or dot path read from each result item")
width: str | None = Field(default=None, description="Optional CSS width for this column")
model_config = ConfigDict(extra="allow", populate_by_name=True)
class SkillDisplayResultSetConfig(BaseModel):
"""Display adapter for one result array inside a skill response."""
key: str = Field(description="Stable key for this result set")
label: str | None = Field(default=None, description="Human-readable result set label")
enabled: bool = Field(default=True, description="Whether this result set is enabled")
mode: Literal["citation", "list", "table", "card", "custom", "none"] = Field(
default="citation",
description="How the frontend should render this result set",
)
result_path: str = Field(default="results", description="Dot path to the array of result items", alias="resultPath")
title_field: str | None = Field(default=None, description="Field used as item title", alias="titleField")
summary_field: str | None = Field(default=None, description="Field used as short summary/snippet", alias="summaryField")
content_field: str | None = Field(default=None, description="Field used as full item content", alias="contentField")
source_field: str | None = Field(default=None, description="Field used as source label", alias="sourceField")
author_field: str | None = Field(default=None, description="Field used as author/byline label", alias="authorField")
type_field: str | None = Field(default=None, description="Field used as source/type badge", alias="typeField")
time_field: str | None = Field(default=None, description="Field used as publication/update time", alias="timeField")
score_field: str | None = Field(default=None, description="Field used as relevance score", alias="scoreField")
url_field: str | None = Field(default=None, description="Field containing a direct URL", alias="urlField")
id_field: str | None = Field(default=None, description="Field containing an ID for template URLs", alias="idField")
link_strategy: Literal["auto", "url", "id"] = Field(
default="auto",
description="Whether links use a URL field, an ID template, or automatic fallback",
alias="linkStrategy",
)
link_template: str | None = Field(default=None, description="Template used when linkStrategy is id", alias="linkTemplate")
citation_token: Literal["doubleBracket", "singleBracket"] = Field(
default="singleBracket",
description="Citation token style expected in model output",
alias="citationToken",
)
max_items: int = Field(default=100, ge=1, le=100, description="Maximum displayed items", alias="maxItems")
custom_instruction: str = Field(
default="",
description="User-authored instruction for custom rendering schema generation",
alias="customInstruction",
)
table_columns: list[SkillDisplayTableColumn] = Field(
default_factory=list,
description="Columns used when mode is table",
alias="tableColumns",
)
model_config = ConfigDict(extra="allow", populate_by_name=True)
class SkillDisplayConfig(BaseModel):
"""Frontend display adapter for structured skill results."""
enabled: bool = Field(default=False, description="Whether result display adaptation is enabled")
mode: Literal["citation", "list", "table", "card", "custom", "none"] = Field(
default="none",
description="How the frontend should render this skill's structured results",
)
result_path: str = Field(default="results", description="Dot path to the array of result items", alias="resultPath")
title_field: str | None = Field(default=None, description="Field used as item title", alias="titleField")
summary_field: str | None = Field(default=None, description="Field used as short summary/snippet", alias="summaryField")
content_field: str | None = Field(default=None, description="Field used as full item content", alias="contentField")
source_field: str | None = Field(default=None, description="Field used as source label", alias="sourceField")
author_field: str | None = Field(default=None, description="Field used as author/byline label", alias="authorField")
type_field: str | None = Field(default=None, description="Field used as source/type badge", alias="typeField")
time_field: str | None = Field(default=None, description="Field used as publication/update time", alias="timeField")
score_field: str | None = Field(default=None, description="Field used as relevance score", alias="scoreField")
url_field: str | None = Field(default=None, description="Field containing a direct URL", alias="urlField")
id_field: str | None = Field(default=None, description="Field containing an ID for template URLs", alias="idField")
link_strategy: Literal["auto", "url", "id"] = Field(
default="auto",
description="Whether links use a URL field, an ID template, or automatic fallback",
alias="linkStrategy",
)
link_template: str | None = Field(default=None, description="Template used when linkStrategy is id", alias="linkTemplate")
citation_token: Literal["doubleBracket", "singleBracket"] = Field(
default="doubleBracket",
description="Citation token style expected in model output",
alias="citationToken",
)
max_items: int = Field(default=8, ge=1, le=100, description="Maximum displayed items", alias="maxItems")
custom_instruction: str = Field(
default="",
description="User-authored instruction for custom rendering schema generation",
alias="customInstruction",
)
table_columns: list[SkillDisplayTableColumn] = Field(
default_factory=list,
description="Columns used when mode is table",
alias="tableColumns",
)
result_sets: list[SkillDisplayResultSetConfig] = Field(
default_factory=list,
description="Optional per-result-array display adapters",
alias="resultSets",
)
model_config = ConfigDict(extra="allow", populate_by_name=True)
class SkillStateConfig(BaseModel):
"""Configuration for a single skill's state."""
enabled: bool = Field(default=True, description="Whether this skill is enabled")
display: SkillDisplayConfig | None = Field(default=None, description="Optional frontend display adapter")
class SkillDisplayTableColumn(BaseModel):
"""A configured table column for structured skill result display."""
label: str = Field(description="Column label shown in the frontend table")
field: str = Field(description="Field name or dot path read from each result item")
width: str | None = Field(default=None, description="Optional CSS width for this column")
model_config = ConfigDict(extra="allow", populate_by_name=True)
class SkillDisplayResultSetConfig(BaseModel):
"""Display adapter for one result array inside a skill response."""
key: str = Field(description="Stable key for this result set")
label: str | None = Field(default=None, description="Human-readable result set label")
enabled: bool = Field(default=True, description="Whether this result set is enabled")
mode: Literal["citation", "list", "table", "card", "custom", "none"] = Field(
default="citation",
description="How the frontend should render this result set",
)
result_path: str = Field(default="results", description="Dot path to the array of result items", alias="resultPath")
title_field: str | None = Field(default=None, description="Field used as item title", alias="titleField")
summary_field: str | None = Field(default=None, description="Field used as short summary/snippet", alias="summaryField")
content_field: str | None = Field(default=None, description="Field used as full item content", alias="contentField")
source_field: str | None = Field(default=None, description="Field used as source label", alias="sourceField")
author_field: str | None = Field(default=None, description="Field used as author/byline label", alias="authorField")
type_field: str | None = Field(default=None, description="Field used as source/type badge", alias="typeField")
time_field: str | None = Field(default=None, description="Field used as publication/update time", alias="timeField")
score_field: str | None = Field(default=None, description="Field used as relevance score", alias="scoreField")
url_field: str | None = Field(default=None, description="Field containing a direct URL", alias="urlField")
id_field: str | None = Field(default=None, description="Field containing an ID for template URLs", alias="idField")
link_strategy: Literal["auto", "url", "id"] = Field(
default="auto",
description="Whether links use a URL field, an ID template, or automatic fallback",
alias="linkStrategy",
)
link_template: str | None = Field(default=None, description="Template used when linkStrategy is id", alias="linkTemplate")
citation_token: Literal["doubleBracket", "singleBracket"] = Field(
default="singleBracket",
description="Citation token style expected in model output",
alias="citationToken",
)
max_items: int = Field(default=100, ge=1, le=100, description="Maximum displayed items", alias="maxItems")
custom_instruction: str = Field(
default="",
description="User-authored instruction for custom rendering schema generation",
alias="customInstruction",
)
table_columns: list[SkillDisplayTableColumn] = Field(
default_factory=list,
description="Columns used when mode is table",
alias="tableColumns",
)
model_config = ConfigDict(extra="allow", populate_by_name=True)
class SkillDisplayConfig(BaseModel):
"""Frontend display adapter for structured skill results."""
enabled: bool = Field(default=False, description="Whether result display adaptation is enabled")
mode: Literal["citation", "list", "table", "card", "custom", "none"] = Field(
default="none",
description="How the frontend should render this skill's structured results",
)
result_path: str = Field(default="results", description="Dot path to the array of result items", alias="resultPath")
title_field: str | None = Field(default=None, description="Field used as item title", alias="titleField")
summary_field: str | None = Field(default=None, description="Field used as short summary/snippet", alias="summaryField")
content_field: str | None = Field(default=None, description="Field used as full item content", alias="contentField")
source_field: str | None = Field(default=None, description="Field used as source label", alias="sourceField")
author_field: str | None = Field(default=None, description="Field used as author/byline label", alias="authorField")
type_field: str | None = Field(default=None, description="Field used as source/type badge", alias="typeField")
time_field: str | None = Field(default=None, description="Field used as publication/update time", alias="timeField")
score_field: str | None = Field(default=None, description="Field used as relevance score", alias="scoreField")
url_field: str | None = Field(default=None, description="Field containing a direct URL", alias="urlField")
id_field: str | None = Field(default=None, description="Field containing an ID for template URLs", alias="idField")
link_strategy: Literal["auto", "url", "id"] = Field(
default="auto",
description="Whether links use a URL field, an ID template, or automatic fallback",
alias="linkStrategy",
)
link_template: str | None = Field(default=None, description="Template used when linkStrategy is id", alias="linkTemplate")
citation_token: Literal["doubleBracket", "singleBracket"] = Field(
default="doubleBracket",
description="Citation token style expected in model output",
alias="citationToken",
)
max_items: int = Field(default=8, ge=1, le=100, description="Maximum displayed items", alias="maxItems")
custom_instruction: str = Field(
default="",
description="User-authored instruction for custom rendering schema generation",
alias="customInstruction",
)
table_columns: list[SkillDisplayTableColumn] = Field(
default_factory=list,
description="Columns used when mode is table",
alias="tableColumns",
)
result_sets: list[SkillDisplayResultSetConfig] = Field(
default_factory=list,
description="Optional per-result-array display adapters",
alias="resultSets",
)
model_config = ConfigDict(extra="allow", populate_by_name=True)
class SkillStateConfig(BaseModel):
"""Configuration for a single skill's state."""
enabled: bool = Field(default=True, description="Whether this skill is enabled")
display: SkillDisplayConfig | None = Field(default=None, description="Optional frontend display adapter")
class ExtensionsConfig(BaseModel):
@@ -0,0 +1,75 @@
"""Configuration for the product knowledge base (obsidian-wiki compatible)."""
from pydantic import BaseModel, Field
class KnowledgeExportConfig(BaseModel):
"""Knowledge graph export switches (``wiki-export`` compatible output)."""
enabled: bool = Field(default=True, description="Master switch for graph export.")
graph_html_enabled: bool = Field(default=True, description="Generate wiki-export/graph.html.")
graph_json_enabled: bool = Field(default=True, description="Generate wiki-export/graph.json.")
class KnowledgeQueryConfig(BaseModel):
"""Layered query strategy flags (``wiki-query`` style)."""
use_hot_md: bool = Field(default=True, description="Consult hot.md when searching.")
use_index_md: bool = Field(default=True, description="Consult index.md when searching.")
use_frontmatter_scan: bool = Field(default=True, description="Scan frontmatter when searching.")
class KnowledgeEmbeddingConfig(BaseModel):
"""Vector embedding config (phase 2).
Vector RAG is opt-in: set ``enabled: true`` and point ``base_url`` at an
OpenAI-compatible ``/embeddings`` endpoint. When disabled or unreachable,
search transparently falls back to keyword scoring, so the feature degrades
gracefully on offline deployments without an embedding model.
"""
enabled: bool = Field(default=False, description="Enable vector embeddings.")
provider: str = Field(default="openai", description="Embedding provider (openai-compatible).")
model: str = Field(default="", description="Embedding model name, e.g. text-embedding-3-small / bge-m3.")
base_url: str = Field(default="", description="OpenAI-compatible base URL (…/v1). Empty disables vector mode.")
api_key: str = Field(default="", description="API key for the embedding endpoint ($ENV resolved like other config).")
dimensions: int | None = Field(default=None, description="Optional embedding dimensions hint sent to the endpoint.")
batch_size: int = Field(default=32, description="Texts per embedding request.")
timeout_seconds: int = Field(default=30, description="HTTP timeout per embedding request.")
class KnowledgeConfig(BaseModel):
"""Product knowledge base configuration.
The first release ships a global, shared, obsidian-wiki compatible vault.
Knowledge metadata is mirrored into the database for fast listing/search,
while ``content_md`` is written to a Markdown vault that stays compatible
with ``ar9av/obsidian-wiki`` (index.md / log.md / hot.md / .manifest.json,
frontmatter, wikilinks, wiki-export graph artifacts).
"""
enabled: bool = Field(default=True, description="Enable the knowledge base feature.")
provider: str = Field(default="obsidian_wiki", description="Knowledge organization provider.")
vault_dir: str = Field(
default="data/knowledge/obsidian-vault",
description="Vault directory (relative to DEER_FLOW_HOME, or absolute).",
)
project_name: str = Field(default="zncm", description="Project namespace for projects/<name>/ pages.")
auto_ingest_enabled: bool = Field(default=False, description="Auto-sediment conversations in the background (phase 3).")
auto_ingest_min_chars: int = Field(default=300, description="Minimum characters before auto-ingest considers a turn.")
llm_extract_enabled: bool = Field(default=True, description="Distill notes with an LLM (wiki-capture style) instead of the rule-based fallback.")
extract_model_name: str | None = Field(default=None, description="Model (from models[]) used to distill knowledge. Falls back to models[0] when unset.")
extract_max_input_chars: int = Field(default=12000, description="Max characters of conversation transcript fed to the extraction LLM.")
max_thread_messages: int = Field(default=80, description="Maximum thread messages to scan when capturing.")
max_source_items: int = Field(default=20, description="Maximum source items recorded per note.")
related_notes_enabled: bool = Field(default=True, description="On capture, find existing notes on the same topic and link them under ## Related (real cross-references instead of placeholders).")
related_notes_limit: int = Field(default=3, description="Maximum real related notes linked into each captured note.")
multi_note_enabled: bool = Field(default=True, description="Allow the LLM extractor to split one conversation into multiple cross-linked knowledge notes.")
rag_enabled: bool = Field(default=False, description="Enable RAG injection before agent runs (phase 2).")
rag_limit: int = Field(default=5, description="Maximum knowledge snippets injected per query.")
sensitive_redaction_enabled: bool = Field(default=True, description="Redact secrets/PII (tokens, keys, phone, id-card, email) before persisting notes (phase 3).")
dedup_similarity_threshold: float = Field(default=0.82, description="Title/summary similarity above which two notes are flagged as duplicates (phase 3).")
entity_extraction_enabled: bool = Field(default=True, description="Extract entities/relations during LLM distillation and feed them into the graph (phase 4).")
export: KnowledgeExportConfig = Field(default_factory=KnowledgeExportConfig, description="Graph export configuration.")
query: KnowledgeQueryConfig = Field(default_factory=KnowledgeQueryConfig, description="Layered query configuration.")
embedding: KnowledgeEmbeddingConfig = Field(default_factory=KnowledgeEmbeddingConfig, description="Embedding configuration.")