Merge branch 'main' into rayhpeng/persistence-scaffold

# Conflicts:
#	config.example.yaml
This commit is contained in:
rayhpeng
2026-04-06 22:16:42 +08:00
27 changed files with 1495 additions and 64 deletions
+18
View File
@@ -106,3 +106,21 @@ class Channel(ABC):
logger.warning("[%s] file upload skipped for %s", self.name, attachment.filename)
except Exception:
logger.exception("[%s] failed to upload file %s", self.name, attachment.filename)
async def receive_file(self, msg: InboundMessage, thread_id: str) -> InboundMessage:
"""
Optionally process and materialize inbound file attachments for this channel.
By default, this method does nothing and simply returns the original message.
Subclasses (e.g. FeishuChannel) may override this to download files (images, documents, etc)
referenced in msg.files, save them to the sandbox, and update msg.text to include
the sandbox file paths for downstream model consumption.
Args:
msg: The inbound message, possibly containing file metadata in msg.files.
thread_id: The resolved DeerFlow thread ID for sandbox path context.
Returns:
The (possibly modified) InboundMessage, with text and/or files updated as needed.
"""
return msg
+146 -3
View File
@@ -5,12 +5,15 @@ from __future__ import annotations
import asyncio
import json
import logging
import re
import threading
from typing import Any
from typing import Any, Literal
from app.channels.base import Channel
from app.channels.commands import KNOWN_CHANNEL_COMMANDS
from app.channels.message_bus import InboundMessageType, MessageBus, OutboundMessage, ResolvedAttachment
from app.channels.message_bus import InboundMessage, InboundMessageType, MessageBus, OutboundMessage, ResolvedAttachment
from deerflow.config.paths import VIRTUAL_PATH_PREFIX, get_paths
from deerflow.sandbox.sandbox_provider import get_sandbox_provider
logger = logging.getLogger(__name__)
@@ -56,6 +59,8 @@ class FeishuChannel(Channel):
self._CreateFileRequestBody = None
self._CreateImageRequest = None
self._CreateImageRequestBody = None
self._GetMessageResourceRequest = None
self._thread_lock = threading.Lock()
async def start(self) -> None:
if self._running:
@@ -73,6 +78,7 @@ class FeishuChannel(Channel):
CreateMessageRequest,
CreateMessageRequestBody,
Emoji,
GetMessageResourceRequest,
PatchMessageRequest,
PatchMessageRequestBody,
ReplyMessageRequest,
@@ -96,6 +102,7 @@ class FeishuChannel(Channel):
self._CreateFileRequestBody = CreateFileRequestBody
self._CreateImageRequest = CreateImageRequest
self._CreateImageRequestBody = CreateImageRequestBody
self._GetMessageResourceRequest = GetMessageResourceRequest
app_id = self.config.get("app_id", "")
app_secret = self.config.get("app_secret", "")
@@ -275,6 +282,112 @@ class FeishuChannel(Channel):
raise RuntimeError(f"Feishu file upload failed: code={response.code}, msg={response.msg}")
return response.data.file_key
async def receive_file(self, msg: InboundMessage, thread_id: str) -> InboundMessage:
"""Download a Feishu file into the thread uploads directory.
Returns the sandbox virtual path when the image is persisted successfully.
"""
if not msg.thread_ts:
logger.warning("[Feishu] received file message without thread_ts, cannot associate with conversation: %s", msg)
return msg
files = msg.files
if not files:
logger.warning("[Feishu] received message with no files: %s", msg)
return msg
text = msg.text
for file in files:
if file.get("image_key"):
virtual_path = await self._receive_single_file(msg.thread_ts, file["image_key"], "image", thread_id)
text = text.replace("[image]", virtual_path, 1)
elif file.get("file_key"):
virtual_path = await self._receive_single_file(msg.thread_ts, file["file_key"], "file", thread_id)
text = text.replace("[file]", virtual_path, 1)
msg.text = text
return msg
async def _receive_single_file(self, message_id: str, file_key: str, type: Literal["image", "file"], thread_id: str) -> str:
request = self._GetMessageResourceRequest.builder().message_id(message_id).file_key(file_key).type(type).build()
def inner():
return self._api_client.im.v1.message_resource.get(request)
try:
response = await asyncio.to_thread(inner)
except Exception:
logger.exception("[Feishu] resource get request failed for resource_key=%s type=%s", file_key, type)
return f"Failed to obtain the [{type}]"
if not response.success():
logger.warning(
"[Feishu] resource get failed: resource_key=%s, type=%s, code=%s, msg=%s, log_id=%s ",
file_key,
type,
response.code,
response.msg,
response.get_log_id(),
)
return f"Failed to obtain the [{type}]"
image_stream = getattr(response, "file", None)
if image_stream is None:
logger.warning("[Feishu] resource get returned no file stream: resource_key=%s, type=%s", file_key, type)
return f"Failed to obtain the [{type}]"
try:
content: bytes = await asyncio.to_thread(image_stream.read)
except Exception:
logger.exception("[Feishu] failed to read resource stream: resource_key=%s, type=%s", file_key, type)
return f"Failed to obtain the [{type}]"
if not content:
logger.warning("[Feishu] empty resource content: resource_key=%s, type=%s", file_key, type)
return f"Failed to obtain the [{type}]"
paths = get_paths()
paths.ensure_thread_dirs(thread_id)
uploads_dir = paths.sandbox_uploads_dir(thread_id).resolve()
ext = "png" if type == "image" else "bin"
raw_filename = getattr(response, "file_name", "") or f"feishu_{file_key[-12:]}.{ext}"
# Sanitize filename: preserve extension, replace path chars in name part
if "." in raw_filename:
name_part, ext = raw_filename.rsplit(".", 1)
name_part = re.sub(r"[./\\]", "_", name_part)
filename = f"{name_part}.{ext}"
else:
filename = re.sub(r"[./\\]", "_", raw_filename)
resolved_target = uploads_dir / filename
def down_load():
# use thread_lock to avoid filename conflicts when writing
with self._thread_lock:
resolved_target.write_bytes(content)
try:
await asyncio.to_thread(down_load)
except Exception:
logger.exception("[Feishu] failed to persist downloaded resource: %s, type=%s", resolved_target, type)
return f"Failed to obtain the [{type}]"
virtual_path = f"{VIRTUAL_PATH_PREFIX}/uploads/{resolved_target.name}"
try:
sandbox_provider = get_sandbox_provider()
sandbox_id = sandbox_provider.acquire(thread_id)
if sandbox_id != "local":
sandbox = sandbox_provider.get(sandbox_id)
if sandbox is None:
logger.warning("[Feishu] sandbox not found for thread_id=%s", thread_id)
return f"Failed to obtain the [{type}]"
sandbox.update_file(virtual_path, content)
except Exception:
logger.exception("[Feishu] failed to sync resource into non-local sandbox: %s", virtual_path)
return f"Failed to obtain the [{type}]"
logger.info("[Feishu] downloaded resource mapped: file_key=%s -> %s", file_key, virtual_path)
return virtual_path
# -- message formatting ------------------------------------------------
@staticmethod
@@ -479,9 +592,28 @@ class FeishuChannel(Channel):
# Parse message content
content = json.loads(message.content)
# files_list store the any-file-key in feishu messages, which can be used to download the file content later
# In Feishu channel, image_keys are independent of file_keys.
# The file_key includes files, videos, and audio, but does not include stickers.
files_list = []
if "text" in content:
# Handle plain text messages
text = content["text"]
elif "file_key" in content:
file_key = content.get("file_key")
if isinstance(file_key, str) and file_key:
files_list.append({"file_key": file_key})
text = "[file]"
else:
text = ""
elif "image_key" in content:
image_key = content.get("image_key")
if isinstance(image_key, str) and image_key:
files_list.append({"image_key": image_key})
text = "[image]"
else:
text = ""
elif "content" in content and isinstance(content["content"], list):
# Handle rich-text messages with a top-level "content" list (e.g., topic groups/posts)
text_paragraphs: list[str] = []
@@ -495,6 +627,16 @@ class FeishuChannel(Channel):
text_value = element.get("text", "")
if text_value:
paragraph_text_parts.append(text_value)
elif element.get("tag") == "img":
image_key = element.get("image_key")
if isinstance(image_key, str) and image_key:
files_list.append({"image_key": image_key})
paragraph_text_parts.append("[image]")
elif element.get("tag") in ("file", "media"):
file_key = element.get("file_key")
if isinstance(file_key, str) and file_key:
files_list.append({"file_key": file_key})
paragraph_text_parts.append("[file]")
if paragraph_text_parts:
# Join text segments within a paragraph with spaces to avoid "helloworld"
text_paragraphs.append(" ".join(paragraph_text_parts))
@@ -514,7 +656,7 @@ class FeishuChannel(Channel):
text[:100] if text else "",
)
if not text:
if not (text or files_list):
logger.info("[Feishu] empty text, ignoring message")
return
@@ -534,6 +676,7 @@ class FeishuChannel(Channel):
text=text,
msg_type=msg_type,
thread_ts=msg_id,
files=files_list,
metadata={"message_id": msg_id, "root_id": root_id},
)
inbound.topic_id = topic_id
+12
View File
@@ -675,6 +675,18 @@ class ChannelManager:
thread_id = await self._create_thread(client, msg)
assistant_id, run_config, run_context = self._resolve_run_params(msg, thread_id)
# If the inbound message contains file attachments, let the channel
# materialize (download) them and update msg.text to include sandbox file paths.
# This enables downstream models to access user-uploaded files by path.
# Channels that do not support file download will simply return the original message.
if msg.files:
from .service import get_channel_service
service = get_channel_service()
channel = service.get_channel(msg.channel_name) if service else None
logger.info("[Manager] preparing receive file context for %d attachments", len(msg.files))
msg = await channel.receive_file(msg, thread_id) if channel else msg
if extra_context:
run_context.update(extra_context)
+5
View File
@@ -6,6 +6,7 @@ import logging
import os
from typing import Any
from app.channels.base import Channel
from app.channels.manager import DEFAULT_GATEWAY_URL, DEFAULT_LANGGRAPH_URL, ChannelManager
from app.channels.message_bus import MessageBus
from app.channels.store import ChannelStore
@@ -164,6 +165,10 @@ class ChannelService:
"channels": channels_status,
}
def get_channel(self, name: str) -> Channel | None:
"""Return a running channel instance by name when available."""
return self._channels.get(name)
# -- singleton access -------------------------------------------------------
+205 -24
View File
@@ -1,14 +1,29 @@
import json
import logging
import shutil
from pathlib import Path
from fastapi import APIRouter, HTTPException
from pydantic import BaseModel, Field
from app.gateway.path_utils import resolve_thread_virtual_path
from deerflow.agents.lead_agent.prompt import clear_skills_system_prompt_cache
from deerflow.config.extensions_config import ExtensionsConfig, SkillStateConfig, get_extensions_config, reload_extensions_config
from deerflow.skills import Skill, load_skills
from deerflow.skills.installer import SkillAlreadyExistsError, install_skill_from_archive
from deerflow.skills.manager import (
append_history,
atomic_write,
custom_skill_exists,
ensure_custom_skill_is_editable,
get_custom_skill_dir,
get_custom_skill_file,
get_skill_history_file,
read_custom_skill_content,
read_history,
validate_skill_markdown_content,
)
from deerflow.skills.security_scanner import scan_skill_content
logger = logging.getLogger(__name__)
@@ -52,6 +67,22 @@ class SkillInstallResponse(BaseModel):
message: str = Field(..., description="Installation result message")
class CustomSkillContentResponse(SkillResponse):
content: str = Field(..., description="Raw SKILL.md content")
class CustomSkillUpdateRequest(BaseModel):
content: str = Field(..., description="Replacement SKILL.md content")
class CustomSkillHistoryResponse(BaseModel):
history: list[dict]
class SkillRollbackRequest(BaseModel):
history_index: int = Field(default=-1, description="History entry index to restore from, defaulting to the latest change.")
def _skill_to_response(skill: Skill) -> SkillResponse:
"""Convert a Skill object to a SkillResponse."""
return SkillResponse(
@@ -78,6 +109,180 @@ async def list_skills() -> SkillsListResponse:
raise HTTPException(status_code=500, detail=f"Failed to load skills: {str(e)}")
@router.post(
"/skills/install",
response_model=SkillInstallResponse,
summary="Install Skill",
description="Install a skill from a .skill file (ZIP archive) located in the thread's user-data directory.",
)
async def install_skill(request: SkillInstallRequest) -> SkillInstallResponse:
try:
skill_file_path = resolve_thread_virtual_path(request.thread_id, request.path)
result = install_skill_from_archive(skill_file_path)
return SkillInstallResponse(**result)
except FileNotFoundError as e:
raise HTTPException(status_code=404, detail=str(e))
except SkillAlreadyExistsError as e:
raise HTTPException(status_code=409, detail=str(e))
except ValueError as e:
raise HTTPException(status_code=400, detail=str(e))
except HTTPException:
raise
except Exception as e:
logger.error(f"Failed to install skill: {e}", exc_info=True)
raise HTTPException(status_code=500, detail=f"Failed to install skill: {str(e)}")
@router.get("/skills/custom", response_model=SkillsListResponse, summary="List Custom Skills")
async def list_custom_skills() -> SkillsListResponse:
try:
skills = [skill for skill in load_skills(enabled_only=False) if skill.category == "custom"]
return SkillsListResponse(skills=[_skill_to_response(skill) for skill in skills])
except Exception as e:
logger.error("Failed to list custom skills: %s", e, exc_info=True)
raise HTTPException(status_code=500, detail=f"Failed to list custom skills: {str(e)}")
@router.get("/skills/custom/{skill_name}", response_model=CustomSkillContentResponse, summary="Get Custom Skill Content")
async def get_custom_skill(skill_name: str) -> CustomSkillContentResponse:
try:
skills = load_skills(enabled_only=False)
skill = next((s for s in skills if s.name == skill_name and s.category == "custom"), None)
if skill is None:
raise HTTPException(status_code=404, detail=f"Custom skill '{skill_name}' not found")
return CustomSkillContentResponse(**_skill_to_response(skill).model_dump(), content=read_custom_skill_content(skill_name))
except HTTPException:
raise
except Exception as e:
logger.error("Failed to get custom skill %s: %s", skill_name, e, exc_info=True)
raise HTTPException(status_code=500, detail=f"Failed to get custom skill: {str(e)}")
@router.put("/skills/custom/{skill_name}", response_model=CustomSkillContentResponse, summary="Edit Custom Skill")
async def update_custom_skill(skill_name: str, request: CustomSkillUpdateRequest) -> CustomSkillContentResponse:
try:
ensure_custom_skill_is_editable(skill_name)
validate_skill_markdown_content(skill_name, request.content)
scan = await scan_skill_content(request.content, executable=False, location=f"{skill_name}/SKILL.md")
if scan.decision == "block":
raise HTTPException(status_code=400, detail=f"Security scan blocked the edit: {scan.reason}")
skill_file = get_custom_skill_dir(skill_name) / "SKILL.md"
prev_content = skill_file.read_text(encoding="utf-8")
atomic_write(skill_file, request.content)
append_history(
skill_name,
{
"action": "human_edit",
"author": "human",
"thread_id": None,
"file_path": "SKILL.md",
"prev_content": prev_content,
"new_content": request.content,
"scanner": {"decision": scan.decision, "reason": scan.reason},
},
)
clear_skills_system_prompt_cache()
return await get_custom_skill(skill_name)
except HTTPException:
raise
except FileNotFoundError as e:
raise HTTPException(status_code=404, detail=str(e))
except ValueError as e:
raise HTTPException(status_code=400, detail=str(e))
except Exception as e:
logger.error("Failed to update custom skill %s: %s", skill_name, e, exc_info=True)
raise HTTPException(status_code=500, detail=f"Failed to update custom skill: {str(e)}")
@router.delete("/skills/custom/{skill_name}", summary="Delete Custom Skill")
async def delete_custom_skill(skill_name: str) -> dict[str, bool]:
try:
ensure_custom_skill_is_editable(skill_name)
skill_dir = get_custom_skill_dir(skill_name)
prev_content = read_custom_skill_content(skill_name)
append_history(
skill_name,
{
"action": "human_delete",
"author": "human",
"thread_id": None,
"file_path": "SKILL.md",
"prev_content": prev_content,
"new_content": None,
"scanner": {"decision": "allow", "reason": "Deletion requested."},
},
)
shutil.rmtree(skill_dir)
clear_skills_system_prompt_cache()
return {"success": True}
except FileNotFoundError as e:
raise HTTPException(status_code=404, detail=str(e))
except ValueError as e:
raise HTTPException(status_code=400, detail=str(e))
except Exception as e:
logger.error("Failed to delete custom skill %s: %s", skill_name, e, exc_info=True)
raise HTTPException(status_code=500, detail=f"Failed to delete custom skill: {str(e)}")
@router.get("/skills/custom/{skill_name}/history", response_model=CustomSkillHistoryResponse, summary="Get Custom Skill History")
async def get_custom_skill_history(skill_name: str) -> CustomSkillHistoryResponse:
try:
if not custom_skill_exists(skill_name) and not get_skill_history_file(skill_name).exists():
raise HTTPException(status_code=404, detail=f"Custom skill '{skill_name}' not found")
return CustomSkillHistoryResponse(history=read_history(skill_name))
except HTTPException:
raise
except Exception as e:
logger.error("Failed to read history for %s: %s", skill_name, e, exc_info=True)
raise HTTPException(status_code=500, detail=f"Failed to read history: {str(e)}")
@router.post("/skills/custom/{skill_name}/rollback", response_model=CustomSkillContentResponse, summary="Rollback Custom Skill")
async def rollback_custom_skill(skill_name: str, request: SkillRollbackRequest) -> CustomSkillContentResponse:
try:
if not custom_skill_exists(skill_name) and not get_skill_history_file(skill_name).exists():
raise HTTPException(status_code=404, detail=f"Custom skill '{skill_name}' not found")
history = read_history(skill_name)
if not history:
raise HTTPException(status_code=400, detail=f"Custom skill '{skill_name}' has no history")
record = history[request.history_index]
target_content = record.get("prev_content")
if target_content is None:
raise HTTPException(status_code=400, detail="Selected history entry has no previous content to roll back to")
validate_skill_markdown_content(skill_name, target_content)
scan = await scan_skill_content(target_content, executable=False, location=f"{skill_name}/SKILL.md")
skill_file = get_custom_skill_file(skill_name)
current_content = skill_file.read_text(encoding="utf-8") if skill_file.exists() else None
history_entry = {
"action": "rollback",
"author": "human",
"thread_id": None,
"file_path": "SKILL.md",
"prev_content": current_content,
"new_content": target_content,
"rollback_from_ts": record.get("ts"),
"scanner": {"decision": scan.decision, "reason": scan.reason},
}
if scan.decision == "block":
append_history(skill_name, history_entry)
raise HTTPException(status_code=400, detail=f"Rollback blocked by security scanner: {scan.reason}")
atomic_write(skill_file, target_content)
append_history(skill_name, history_entry)
clear_skills_system_prompt_cache()
return await get_custom_skill(skill_name)
except HTTPException:
raise
except IndexError:
raise HTTPException(status_code=400, detail="history_index is out of range")
except FileNotFoundError as e:
raise HTTPException(status_code=404, detail=str(e))
except ValueError as e:
raise HTTPException(status_code=400, detail=str(e))
except Exception as e:
logger.error("Failed to roll back custom skill %s: %s", skill_name, e, exc_info=True)
raise HTTPException(status_code=500, detail=f"Failed to roll back custom skill: {str(e)}")
@router.get(
"/skills/{skill_name}",
response_model=SkillResponse,
@@ -147,27 +352,3 @@ async def update_skill(skill_name: str, request: SkillUpdateRequest) -> SkillRes
except Exception as e:
logger.error(f"Failed to update skill {skill_name}: {e}", exc_info=True)
raise HTTPException(status_code=500, detail=f"Failed to update skill: {str(e)}")
@router.post(
"/skills/install",
response_model=SkillInstallResponse,
summary="Install Skill",
description="Install a skill from a .skill file (ZIP archive) located in the thread's user-data directory.",
)
async def install_skill(request: SkillInstallRequest) -> SkillInstallResponse:
try:
skill_file_path = resolve_thread_virtual_path(request.thread_id, request.path)
result = install_skill_from_archive(skill_file_path)
return SkillInstallResponse(**result)
except FileNotFoundError as e:
raise HTTPException(status_code=404, detail=str(e))
except SkillAlreadyExistsError as e:
raise HTTPException(status_code=409, detail=str(e))
except ValueError as e:
raise HTTPException(status_code=400, detail=str(e))
except HTTPException:
raise
except Exception as e:
logger.error(f"Failed to install skill: {e}", exc_info=True)
raise HTTPException(status_code=500, detail=f"Failed to install skill: {str(e)}")