docs: add run-level API endpoints to CLAUDE.md routers table

Replace bare list[dict] response with {data: [...], has_more: bool} envelope,
forwarding limit/before_seq/after_seq query params to the event store.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

.env.example

@@ -24,7 +24,6 @@ INFOQUEST_API_KEY=your-infoquest-api-key
 # SLACK_BOT_TOKEN=your-slack-bot-token
 # SLACK_APP_TOKEN=your-slack-app-token
 # TELEGRAM_BOT_TOKEN=your-telegram-bot-token
-# DISCORD_BOT_TOKEN=your-discord-bot-token
 
 # Enable LangSmith to monitor and debug your LLM calls, agent runs, and tool executions.
 # LANGSMITH_TRACING=true
@@ -40,8 +39,3 @@ INFOQUEST_API_KEY=your-infoquest-api-key
 #
 # WECOM_BOT_ID=your-wecom-bot-id
 # WECOM_BOT_SECRET=your-wecom-bot-secret
-# DINGTALK_CLIENT_ID=your-dingtalk-client-id
-# DINGTALK_CLIENT_SECRET=your-dingtalk-client-secret
-
-# Set to "false" to disable Swagger UI, ReDoc, and OpenAPI schema in production
-# GATEWAY_ENABLE_DOCS=false

.github/workflows/e2e-tests.yml

@@ -1,63 +0,0 @@
-name: E2E Tests
-
-on:
-  push:
-    branches: [ 'main' ]
-    paths:
-      - 'frontend/**'
-      - '.github/workflows/e2e-tests.yml'
-  pull_request:
-    types: [opened, synchronize, reopened, ready_for_review]
-    paths:
-      - 'frontend/**'
-      - '.github/workflows/e2e-tests.yml'
-
-concurrency:
-  group: e2e-tests-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-permissions:
-  contents: read
-
-jobs:
-  e2e-tests:
-    if: ${{ github.event_name != 'pull_request' || github.event.pull_request.draft == false }}
-    runs-on: ubuntu-latest
-    timeout-minutes: 15
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v6
-
-      - name: Setup Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version: '22'
-
-      - name: Enable Corepack
-        run: corepack enable
-
-      - name: Use pinned pnpm version
-        run: corepack prepare pnpm@10.26.2 --activate
-
-      - name: Install frontend dependencies
-        working-directory: frontend
-        run: pnpm install --frozen-lockfile
-
-      - name: Install Playwright Chromium
-        working-directory: frontend
-        run: npx playwright install chromium --with-deps
-
-      - name: Run E2E tests
-        working-directory: frontend
-        run: pnpm exec playwright test
-        env:
-          SKIP_ENV_VALIDATION: '1'
-
-      - name: Upload Playwright report
-        uses: actions/upload-artifact@v4
-        if: ${{ !cancelled() }}
-        with:
-          name: playwright-report
-          path: frontend/playwright-report/
-          retention-days: 7

.github/workflows/frontend-unit-tests.yml

@@ -1,43 +0,0 @@
-name: Frontend Unit Tests
-
-on:
-  push:
-    branches: [ 'main' ]
-  pull_request:
-    types: [opened, synchronize, reopened, ready_for_review]
-
-concurrency:
-  group: frontend-unit-tests-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-permissions:
-  contents: read
-
-jobs:
-  frontend-unit-tests:
-    if: github.event.pull_request.draft == false
-    runs-on: ubuntu-latest
-    timeout-minutes: 15
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v6
-
-      - name: Setup Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version: '22'
-
-      - name: Enable Corepack
-        run: corepack enable
-
-      - name: Use pinned pnpm version
-        run: corepack prepare pnpm@10.26.2 --activate
-
-      - name: Install frontend dependencies
-        working-directory: frontend
-        run: pnpm install --frozen-lockfile
-
-      - name: Run unit tests of frontend
-        working-directory: frontend
-        run: make test

.gitignore

@@ -40,7 +40,6 @@ coverage/
 skills/custom/*
 logs/
 log/
-debug.log
 
 # Local git hooks (keep only on this machine, do not push)
 .githooks/
@@ -56,7 +55,5 @@ web/
 backend/Dockerfile.langgraph
 config.yaml.bak
 .playwright-mcp
-/frontend/test-results/
-/frontend/playwright-report/
 .gstack/
 .worktrees

.pre-commit-config.yaml

@@ -1,33 +0,0 @@
-repos:
-  # Backend: ruff lint + format via uv (uses the same ruff version as backend deps)
-  - repo: local
-    hooks:
-      - id: ruff
-        name: ruff lint
-        entry: bash -c 'cd backend && uv run ruff check --fix "${@/#backend\//}"' --
-        language: system
-        types_or: [python]
-        files: ^backend/
-      - id: ruff-format
-        name: ruff format
-        entry: bash -c 'cd backend && uv run ruff format "${@/#backend\//}"' --
-        language: system
-        types_or: [python]
-        files: ^backend/
-
-  # Frontend: eslint + prettier (must run from frontend/ for node_modules resolution)
-  - repo: local
-    hooks:
-      - id: frontend-eslint
-        name: eslint (frontend)
-        entry: bash -c 'cd frontend && npx eslint --fix "${@/#frontend\//}"' --
-        language: system
-        types_or: [javascript, tsx, ts]
-        files: ^frontend/
-
-      - id: frontend-prettier
-        name: prettier (frontend)
-        entry: bash -c 'cd frontend && npx prettier --write "${@/#frontend\//}"' --
-        language: system
-        files: ^frontend/
-        types_or: [javascript, tsx, ts, json, css]

CONTRIBUTING.md

@@ -166,7 +166,7 @@ Required tools:
 
 1. **Configure the application** (same as Docker setup above)
 
-2. **Install dependencies** (this also sets up pre-commit hooks):
+2. **Install dependencies**:
    ```bash
    make install
    ```
@@ -298,24 +298,19 @@ Nginx (port 2026) ← Unified entry point
 ```bash
 # Backend tests
 cd backend
-make test
+uv run pytest
 
-# Frontend unit tests
+# Frontend checks
 cd frontend
-make test
-
-# Frontend E2E tests (requires Chromium; builds and auto-starts the Next.js production server)
-cd frontend
-make test-e2e
+pnpm check
 ```
 
 ### PR Regression Checks
 
-Every pull request triggers the following CI workflows:
+Every pull request runs the backend regression workflow at [.github/workflows/backend-unit-tests.yml](.github/workflows/backend-unit-tests.yml), including:
 
-- **Backend unit tests** — [.github/workflows/backend-unit-tests.yml](.github/workflows/backend-unit-tests.yml)
-- **Frontend unit tests** — [.github/workflows/frontend-unit-tests.yml](.github/workflows/frontend-unit-tests.yml)
-- **Frontend E2E tests** — [.github/workflows/e2e-tests.yml](.github/workflows/e2e-tests.yml) (triggered only when `frontend/` files change)
+- `tests/test_provisioner_kubeconfig.py`
+- `tests/test_docker_sandbox_mode_detection.py`
 
 ## Code Style
 

Makefile

@@ -1,6 +1,6 @@
 # DeerFlow - Unified Development Environment
 
-.PHONY: help config config-upgrade check install setup doctor dev dev-daemon start start-daemon stop up down clean docker-init docker-start docker-stop docker-logs docker-logs-frontend docker-logs-gateway
+.PHONY: help config config-upgrade check install setup doctor dev dev-pro dev-daemon dev-daemon-pro start start-pro start-daemon start-daemon-pro stop up up-pro down clean docker-init docker-start docker-start-pro docker-stop docker-logs docker-logs-frontend docker-logs-gateway
 
 BASH ?= bash
 BACKEND_UV_RUN = cd backend && uv run
@@ -23,22 +23,28 @@ help:
 	@echo "  make config          - Generate local config files (aborts if config already exists)"
 	@echo "  make config-upgrade  - Merge new fields from config.example.yaml into config.yaml"
 	@echo "  make check           - Check if all required tools are installed"
-	@echo "  make install         - Install all dependencies (frontend + backend + pre-commit hooks)"
+	@echo "  make install         - Install all dependencies (frontend + backend)"
 	@echo "  make setup-sandbox   - Pre-pull sandbox container image (recommended)"
 	@echo "  make dev             - Start all services in development mode (with hot-reloading)"
+	@echo "  make dev-pro         - Start in dev + Gateway mode (experimental, no LangGraph server)"
 	@echo "  make dev-daemon      - Start dev services in background (daemon mode)"
+	@echo "  make dev-daemon-pro  - Start dev daemon + Gateway mode (experimental)"
 	@echo "  make start           - Start all services in production mode (optimized, no hot-reloading)"
+	@echo "  make start-pro       - Start in prod + Gateway mode (experimental)"
 	@echo "  make start-daemon    - Start prod services in background (daemon mode)"
+	@echo "  make start-daemon-pro - Start prod daemon + Gateway mode (experimental)"
 	@echo "  make stop            - Stop all running services"
 	@echo "  make clean           - Clean up processes and temporary files"
 	@echo ""
 	@echo "Docker Production Commands:"
 	@echo "  make up              - Build and start production Docker services (localhost:2026)"
+	@echo "  make up-pro          - Build and start production Docker in Gateway mode (experimental)"
 	@echo "  make down            - Stop and remove production Docker containers"
 	@echo ""
 	@echo "Docker Development Commands:"
 	@echo "  make docker-init     - Pull the sandbox image"
 	@echo "  make docker-start    - Start Docker services (mode-aware from config.yaml, localhost:2026)"
+	@echo "  make docker-start-pro - Start Docker in Gateway mode (experimental, no LangGraph container)"
 	@echo "  make docker-stop     - Stop Docker development services"
 	@echo "  make docker-logs     - View Docker development logs"
 	@echo "  make docker-logs-frontend - View Docker frontend logs"
@@ -67,8 +73,6 @@ install:
 	@cd backend && uv sync
 	@echo "Installing frontend dependencies..."
 	@cd frontend && pnpm install
-	@echo "Installing pre-commit hooks..."
-	@$(BACKEND_UV_RUN) --with pre-commit pre-commit install
 	@echo "✓ All dependencies installed"
 	@echo ""
 	@echo "=========================================="
@@ -95,7 +99,7 @@ setup-sandbox:
 	echo ""; \
 	if command -v container >/dev/null 2>&1 && [ "$$(uname)" = "Darwin" ]; then \
 		echo "Detected Apple Container on macOS, pulling image..."; \
-		container image pull "$$IMAGE" || echo "⚠ Apple Container pull failed, will try Docker"; \
+		container pull "$$IMAGE" || echo "⚠ Apple Container pull failed, will try Docker"; \
 	fi; \
 	if command -v docker >/dev/null 2>&1; then \
 		echo "Pulling image using Docker..."; \
@@ -117,21 +121,41 @@ dev:
 	@$(PYTHON) ./scripts/check.py
 	@$(RUN_WITH_GIT_BASH) ./scripts/serve.sh --dev
 
+# Start all services in dev + Gateway mode (experimental: agent runtime embedded in Gateway)
+dev-pro:
+	@$(PYTHON) ./scripts/check.py
+	@$(RUN_WITH_GIT_BASH) ./scripts/serve.sh --dev --gateway
+
 # Start all services in production mode (with optimizations)
 start:
 	@$(PYTHON) ./scripts/check.py
 	@$(RUN_WITH_GIT_BASH) ./scripts/serve.sh --prod
 
+# Start all services in prod + Gateway mode (experimental)
+start-pro:
+	@$(PYTHON) ./scripts/check.py
+	@$(RUN_WITH_GIT_BASH) ./scripts/serve.sh --prod --gateway
+
 # Start all services in daemon mode (background)
 dev-daemon:
 	@$(PYTHON) ./scripts/check.py
 	@$(RUN_WITH_GIT_BASH) ./scripts/serve.sh --dev --daemon
 
+# Start daemon + Gateway mode (experimental)
+dev-daemon-pro:
+	@$(PYTHON) ./scripts/check.py
+	@$(RUN_WITH_GIT_BASH) ./scripts/serve.sh --dev --gateway --daemon
+
 # Start prod services in daemon mode (background)
 start-daemon:
 	@$(PYTHON) ./scripts/check.py
 	@$(RUN_WITH_GIT_BASH) ./scripts/serve.sh --prod --daemon
 
+# Start prod daemon + Gateway mode (experimental)
+start-daemon-pro:
+	@$(PYTHON) ./scripts/check.py
+	@$(RUN_WITH_GIT_BASH) ./scripts/serve.sh --prod --gateway --daemon
+
 # Stop all services
 stop:
 	@$(RUN_WITH_GIT_BASH) ./scripts/serve.sh --stop
@@ -156,6 +180,10 @@ docker-init:
 docker-start:
 	@$(RUN_WITH_GIT_BASH) ./scripts/docker.sh start
 
+# Start Docker in Gateway mode (experimental)
+docker-start-pro:
+	@$(RUN_WITH_GIT_BASH) ./scripts/docker.sh start --gateway
+
 # Stop Docker development environment
 docker-stop:
 	@$(RUN_WITH_GIT_BASH) ./scripts/docker.sh stop
@@ -178,6 +206,10 @@ docker-logs-gateway:
 up:
 	@$(RUN_WITH_GIT_BASH) ./scripts/deploy.sh
 
+# Build and start production services in Gateway mode
+up-pro:
+	@$(RUN_WITH_GIT_BASH) ./scripts/deploy.sh --gateway
+
 # Stop and remove production containers
 down:
 	@$(RUN_WITH_GIT_BASH) ./scripts/deploy.sh down

README.md

@@ -243,6 +243,9 @@ make up     # Build images and start all production services
 make down   # Stop and remove containers
 ```
 
+> [!NOTE]
+> The LangGraph agent server currently runs via `langgraph dev` (the open-source CLI server).
+
 Access: http://localhost:2026
 
 See [CONTRIBUTING.md](CONTRIBUTING.md) for detailed Docker development guide.
@@ -251,7 +254,7 @@ See [CONTRIBUTING.md](CONTRIBUTING.md) for detailed Docker development guide.
 
 If you prefer running services locally:
 
-Prerequisite: complete the "Configuration" steps above first (`make setup`). `make dev` requires a valid `config.yaml` in the project root. Set `DEER_FLOW_PROJECT_ROOT` to define that root explicitly, or `DEER_FLOW_CONFIG_PATH` to point at a specific config file. Runtime state defaults to `.deer-flow` under the project root and can be moved with `DEER_FLOW_HOME`; skills default to `skills/` under the project root and can be moved with `DEER_FLOW_SKILLS_PATH`. Run `make doctor` to verify your setup before starting.
+Prerequisite: complete the "Configuration" steps above first (`make setup`). `make dev` requires a valid `config.yaml` in the project root (can be overridden via `DEER_FLOW_CONFIG_PATH`). Run `make doctor` to verify your setup before starting.
 On Windows, run the local development flow from Git Bash. Native `cmd.exe` and PowerShell shells are not supported for the bash-based service scripts, and WSL is not guaranteed because some scripts rely on Git for Windows utilities such as `cygpath`.
 
 1. **Check prerequisites**:
@@ -261,7 +264,7 @@ On Windows, run the local development flow from Git Bash. Native `cmd.exe` and P
 
 2. **Install dependencies**:
    ```bash
-   make install  # Install backend + frontend dependencies + pre-commit hooks
+   make install  # Install backend + frontend dependencies
    ```
 
 3. **(Optional) Pre-pull sandbox image**:
@@ -286,31 +289,53 @@ On Windows, run the local development flow from Git Bash. Native `cmd.exe` and P
 
 #### Startup Modes
 
-DeerFlow runs the agent runtime inside the Gateway API. Development mode enables hot-reload; production mode uses a pre-built frontend.
+DeerFlow supports multiple startup modes across two dimensions:
+
+- **Dev / Prod** — dev enables hot-reload; prod uses pre-built frontend
+- **Standard / Gateway** — standard uses a separate LangGraph server (4 processes); Gateway mode (experimental) embeds the agent runtime in the Gateway API (3 processes)
 
 | | **Local Foreground** | **Local Daemon** | **Docker Dev** | **Docker Prod** |
 |---|---|---|---|---|
 | **Dev** | `./scripts/serve.sh --dev`<br/>`make dev` | `./scripts/serve.sh --dev --daemon`<br/>`make dev-daemon` | `./scripts/docker.sh start`<br/>`make docker-start` | — |
+| **Dev + Gateway** | `./scripts/serve.sh --dev --gateway`<br/>`make dev-pro` | `./scripts/serve.sh --dev --gateway --daemon`<br/>`make dev-daemon-pro` | `./scripts/docker.sh start --gateway`<br/>`make docker-start-pro` | — |
 | **Prod** | `./scripts/serve.sh --prod`<br/>`make start` | `./scripts/serve.sh --prod --daemon`<br/>`make start-daemon` | — | `./scripts/deploy.sh`<br/>`make up` |
+| **Prod + Gateway** | `./scripts/serve.sh --prod --gateway`<br/>`make start-pro` | `./scripts/serve.sh --prod --gateway --daemon`<br/>`make start-daemon-pro` | — | `./scripts/deploy.sh --gateway`<br/>`make up-pro` |
 
 | Action | Local | Docker Dev | Docker Prod |
 |---|---|---|---|
 | **Stop** | `./scripts/serve.sh --stop`<br/>`make stop` | `./scripts/docker.sh stop`<br/>`make docker-stop` | `./scripts/deploy.sh down`<br/>`make down` |
 | **Restart** | `./scripts/serve.sh --restart [flags]` | `./scripts/docker.sh restart` | — |
 
-Gateway owns `/api/langgraph/*` and translates those public LangGraph-compatible paths to its native `/api/*` routers behind nginx.
+> **Gateway mode** eliminates the LangGraph server process — the Gateway API handles agent execution directly via async tasks, managing its own concurrency.
+
+#### Why Gateway Mode?
+
+In standard mode, DeerFlow runs a dedicated [LangGraph Platform](https://langchain-ai.github.io/langgraph/) server alongside the Gateway API. This architecture works well but has trade-offs:
+
+| | Standard Mode | Gateway Mode |
+|---|---|---|
+| **Architecture** | Gateway (REST API) + LangGraph (agent runtime) | Gateway embeds agent runtime |
+| **Concurrency** | `--n-jobs-per-worker` per worker (requires license) | `--workers` × async tasks (no per-worker cap) |
+| **Containers / Processes** | 4 (frontend, gateway, langgraph, nginx) | 3 (frontend, gateway, nginx) |
+| **Resource usage** | Higher (two Python runtimes) | Lower (single Python runtime) |
+| **LangGraph Platform license** | Required for production images | Not required |
+| **Cold start** | Slower (two services to initialize) | Faster |
+
+Both modes are functionally equivalent — the same agents, tools, and skills work in either mode.
 
 #### Docker Production Deployment
 
-`deploy.sh` supports building and starting separately:
+`deploy.sh` supports building and starting separately. Images are mode-agnostic — runtime mode is selected at start time:
 
 ```bash
 # One-step (build + start)
-deploy.sh
+deploy.sh                    # standard mode (default)
+deploy.sh --gateway          # gateway mode
 
-# Two-step (build once, start later)
+# Two-step (build once, start with any mode)
 deploy.sh build              # build all images
-deploy.sh start              # start pre-built images
+deploy.sh start              # start in standard mode
+deploy.sh start --gateway    # start in gateway mode
 
 # Stop
 deploy.sh down
@@ -345,14 +370,13 @@ DeerFlow supports receiving tasks from messaging apps. Channels auto-start when
 | Feishu / Lark | WebSocket | Moderate |
 | WeChat | Tencent iLink (long-polling) | Moderate |
 | WeCom | WebSocket | Moderate |
-| DingTalk | Stream Push (WebSocket) | Moderate |
 
 **Configuration in `config.yaml`:**
 
 ```yaml
 channels:
-  # LangGraph-compatible Gateway API base URL (default: http://localhost:8001/api)
-  langgraph_url: http://localhost:8001/api
+  # LangGraph Server URL (default: http://localhost:2024)
+  langgraph_url: http://localhost:2024
   # Gateway API URL (default: http://localhost:8001)
   gateway_url: http://localhost:8001
 
@@ -415,19 +439,11 @@ channels:
           context:
             thinking_enabled: true
             subagent_enabled: true
-
-  dingtalk:
-    enabled: true
-    client_id: $DINGTALK_CLIENT_ID             # Client ID of your DingTalk application
-    client_secret: $DINGTALK_CLIENT_SECRET     # Client Secret of your DingTalk application
-    allowed_users: []                          # empty = allow all
-    card_template_id: ""                       # Optional: AI Card template ID for streaming typewriter effect
 ```
 
 Notes:
 - `assistant_id: lead_agent` calls the default LangGraph assistant directly.
 - If `assistant_id` is set to a custom agent name, DeerFlow still routes through `lead_agent` and injects that value as `agent_name`, so the custom agent's SOUL/config takes effect for IM channels.
-- IM channel workers call Gateway's LangGraph-compatible API internally and automatically attach process-local internal auth plus the CSRF cookie/header pair required for thread and run creation.
 
 Set the corresponding API keys in your `.env` file:
 
@@ -450,10 +466,6 @@ WECHAT_ILINK_BOT_ID=your_ilink_bot_id
 # WeCom
 WECOM_BOT_ID=your_bot_id
 WECOM_BOT_SECRET=your_bot_secret
-
-# DingTalk
-DINGTALK_CLIENT_ID=your_client_id
-DINGTALK_CLIENT_SECRET=your_client_secret
 ```
 
 **Telegram Setup**
@@ -492,15 +504,7 @@ DINGTALK_CLIENT_SECRET=your_client_secret
 4. Make sure backend dependencies include `wecom-aibot-python-sdk`. The channel uses a WebSocket long connection and does not require a public callback URL.
 5. The current integration supports inbound text, image, and file messages. Final images/files generated by the agent are also sent back to the WeCom conversation.
 
-**DingTalk Setup**
-
-1. Create a DingTalk application in the [DingTalk Developer Console](https://open.dingtalk.com/) and enable **Robot** capability.
-2. Set the message receiving mode to **Stream Mode** in the robot configuration page.
-3. Copy the `Client ID` and `Client Secret`, set `DINGTALK_CLIENT_ID` and `DINGTALK_CLIENT_SECRET` in `.env`, and enable the channel in `config.yaml`.
-4. *(Optional)* To enable streaming AI Card replies (typewriter effect), create an **AI Card** template on the [DingTalk Card Platform](https://open.dingtalk.com/document/dingstart/typewriter-effect-streaming-ai-card), then set `card_template_id` in `config.yaml` to the template ID. You also need to apply for the `Card.Streaming.Write` and `Card.Instance.Write` permissions.
-
-
-When DeerFlow runs in Docker Compose, IM channels execute inside the `gateway` container. In that case, do not point `channels.langgraph_url` or `channels.gateway_url` at `localhost`; use container service names such as `http://gateway:8001/api` and `http://gateway:8001`, or set `DEER_FLOW_CHANNELS_LANGGRAPH_URL` and `DEER_FLOW_CHANNELS_GATEWAY_URL`.
+When DeerFlow runs in Docker Compose, IM channels execute inside the `gateway` container. In that case, do not point `channels.langgraph_url` or `channels.gateway_url` at `localhost`; use container service names such as `http://langgraph:2024` and `http://gateway:8001`, or set `DEER_FLOW_CHANNELS_LANGGRAPH_URL` and `DEER_FLOW_CHANNELS_GATEWAY_URL`.
 
 **Commands**
 
@@ -654,8 +658,6 @@ This is the difference between a chatbot with tool access and an agent with an a
 
 **Summarization**: Within a session, DeerFlow manages context aggressively — summarizing completed sub-tasks, offloading intermediate results to the filesystem, compressing what's no longer immediately relevant. This lets it stay sharp across long, multi-step tasks without blowing the context window.
 
-**Strict Tool-Call Recovery**: When a provider or middleware interrupts a tool-call loop, DeerFlow now strips provider-level raw tool-call metadata on forced-stop assistant messages and injects placeholder tool results for dangling calls before the next model invocation. This keeps OpenAI-compatible reasoning models that strictly validate `tool_call_id` sequences from failing with malformed history errors.
-
 ### Long-Term Memory
 
 Most agents forget everything the moment a conversation ends. DeerFlow remembers.

README_fr.md

@@ -290,7 +290,6 @@ DeerFlow peut recevoir des tâches depuis des applications de messagerie. Les ca
 | Telegram | Bot API (long-polling) | Facile |
 | Slack | Socket Mode | Modérée |
 | Feishu / Lark | WebSocket | Modérée |
-| DingTalk | Stream Push (WebSocket) | Modérée |
 
 **Configuration dans `config.yaml` :**
 
@@ -342,13 +341,6 @@ channels:
           context:
             thinking_enabled: true
             subagent_enabled: true
-
-  dingtalk:
-    enabled: true
-    client_id: $DINGTALK_CLIENT_ID             # ClientId depuis DingTalk Open Platform
-    client_secret: $DINGTALK_CLIENT_SECRET     # ClientSecret depuis DingTalk Open Platform
-    allowed_users: []                          # vide = tout le monde autorisé
-    card_template_id: ""                       # Optionnel : ID de modèle AI Card pour l'effet machine à écrire en streaming
 ```
 
 Définissez les clés API correspondantes dans votre fichier `.env` :
@@ -364,10 +356,6 @@ SLACK_APP_TOKEN=xapp-...
 # Feishu / Lark
 FEISHU_APP_ID=cli_xxxx
 FEISHU_APP_SECRET=your_app_secret
-
-# DingTalk
-DINGTALK_CLIENT_ID=your_client_id
-DINGTALK_CLIENT_SECRET=your_client_secret
 ```
 
 **Configuration Telegram**
@@ -390,13 +378,6 @@ DINGTALK_CLIENT_SECRET=your_client_secret
 3. Dans **Events**, abonnez-vous à `im.message.receive_v1` et sélectionnez le mode **Long Connection**.
 4. Copiez l'App ID et l'App Secret. Définissez `FEISHU_APP_ID` et `FEISHU_APP_SECRET` dans `.env` et activez le canal dans `config.yaml`.
 
-**Configuration DingTalk**
-
-1. Créez une application sur [DingTalk Open Platform](https://open.dingtalk.com/) et activez la capacité **Robot**.
-2. Dans la page de configuration du robot, définissez le mode de réception des messages sur **Stream**.
-3. Copiez le `Client ID` et le `Client Secret`. Définissez `DINGTALK_CLIENT_ID` et `DINGTALK_CLIENT_SECRET` dans `.env` et activez le canal dans `config.yaml`.
-4. *(Optionnel)* Pour activer les réponses en streaming AI Card (effet machine à écrire), créez un modèle **AI Card** sur la [plateforme de cartes DingTalk](https://open.dingtalk.com/document/dingstart/typewriter-effect-streaming-ai-card), puis définissez `card_template_id` dans `config.yaml` avec l'ID du modèle. Vous devez également demander les permissions `Card.Streaming.Write` et `Card.Instance.Write`.
-
 **Commandes**
 
 Une fois un canal connecté, vous pouvez interagir avec DeerFlow directement depuis le chat :

README_ja.md

@@ -243,7 +243,6 @@ DeerFlowはメッセージングアプリからのタスク受信をサポート
 | Telegram | Bot API（ロングポーリング） | 簡単 |
 | Slack | Socket Mode | 中程度 |
 | Feishu / Lark | WebSocket | 中程度 |
-| DingTalk | Stream Push（WebSocket） | 中程度 |
 
 **`config.yaml`での設定：**
 
@@ -295,13 +294,6 @@ channels:
           context:
             thinking_enabled: true
             subagent_enabled: true
-
-  dingtalk:
-    enabled: true
-    client_id: $DINGTALK_CLIENT_ID             # DingTalk Open PlatformのClientId
-    client_secret: $DINGTALK_CLIENT_SECRET     # DingTalk Open PlatformのClientSecret
-    allowed_users: []                          # 空 = 全員許可
-    card_template_id: ""                       # オプション：ストリーミングタイプライター効果用のAIカードテンプレートID
 ```
 
 対応するAPIキーを`.env`ファイルに設定します：
@@ -317,10 +309,6 @@ SLACK_APP_TOKEN=xapp-...
 # Feishu / Lark
 FEISHU_APP_ID=cli_xxxx
 FEISHU_APP_SECRET=your_app_secret
-
-# DingTalk
-DINGTALK_CLIENT_ID=your_client_id
-DINGTALK_CLIENT_SECRET=your_client_secret
 ```
 
 **Telegramのセットアップ**
@@ -343,13 +331,6 @@ DINGTALK_CLIENT_SECRET=your_client_secret
 3. **イベント**で`im.message.receive_v1`を購読し、**ロングコネクション**モードを選択。
 4. App IDとApp Secretをコピー。`.env`に`FEISHU_APP_ID`と`FEISHU_APP_SECRET`を設定し、`config.yaml`でチャネルを有効にします。
 
-**DingTalkのセットアップ**
-
-1. [DingTalk Open Platform](https://open.dingtalk.com/)でアプリを作成し、**ロボット**機能を有効化します。
-2. ロボット設定ページでメッセージ受信モードを**Streamモード**に設定します。
-3. `Client ID`と`Client Secret`をコピー。`.env`に`DINGTALK_CLIENT_ID`と`DINGTALK_CLIENT_SECRET`を設定し、`config.yaml`でチャネルを有効にします。
-4. *（オプション）* ストリーミングAIカード返信（タイプライター効果）を有効にするには、[DingTalkカードプラットフォーム](https://open.dingtalk.com/document/dingstart/typewriter-effect-streaming-ai-card)で**AIカード**テンプレートを作成し、`config.yaml`の`card_template_id`にテンプレートIDを設定します。`Card.Streaming.Write` および `Card.Instance.Write` 権限の申請も必要です。
-
 **コマンド**
 
 チャネル接続後、チャットから直接DeerFlowと対話できます：

README_ru.md

@@ -256,7 +256,6 @@ DeerFlow принимает задачи прямо из мессенджеро
 | Telegram | Bot API (long-polling) | Просто |
 | Slack | Socket Mode | Средне |
 | Feishu / Lark | WebSocket | Средне |
-| DingTalk | Stream Push (WebSocket) | Средне |
 
 **Конфигурация в `config.yaml`:**
 
@@ -279,13 +278,6 @@ channels:
     enabled: true
     bot_token: $TELEGRAM_BOT_TOKEN
     allowed_users: []
-
-  dingtalk:
-    enabled: true
-    client_id: $DINGTALK_CLIENT_ID             # ClientId с DingTalk Open Platform
-    client_secret: $DINGTALK_CLIENT_SECRET     # ClientSecret с DingTalk Open Platform
-    allowed_users: []                          # пусто = разрешить всем
-    card_template_id: ""                       # Опционально: ID шаблона AI Card для потокового эффекта печатной машинки
 ```
 
 **Настройка Telegram**
@@ -293,13 +285,6 @@ channels:
 1. Напишите [@BotFather](https://t.me/BotFather), отправьте `/newbot` и скопируйте HTTP API-токен.
 2. Укажите `TELEGRAM_BOT_TOKEN` в `.env` и включите канал в `config.yaml`.
 
-**Настройка DingTalk**
-
-1. Создайте приложение на [DingTalk Open Platform](https://open.dingtalk.com/) и включите возможность **Робот**.
-2. На странице настроек робота установите режим приёма сообщений на **Stream**.
-3. Скопируйте `Client ID` и `Client Secret`. Укажите `DINGTALK_CLIENT_ID` и `DINGTALK_CLIENT_SECRET` в `.env` и включите канал в `config.yaml`.
-4. *(Опционально)* Для включения потоковых ответов AI Card (эффект печатной машинки) создайте шаблон **AI Card** на [платформе карточек DingTalk](https://open.dingtalk.com/document/dingstart/typewriter-effect-streaming-ai-card), затем укажите `card_template_id` в `config.yaml` с ID шаблона. Также необходимо запросить разрешения `Card.Streaming.Write` и `Card.Instance.Write`.
-
 **Доступные команды**
 
 | Команда | Описание |

README_zh.md

@@ -194,7 +194,7 @@ make down   # 停止并移除容器
 
 如果你更希望直接在本地启动各个服务：
 
-前提：先完成上面的“配置”步骤（`make config` 和模型 API key 配置）。`make dev` 需要有效配置文件，默认读取项目根目录下的 `config.yaml`。可以用 `DEER_FLOW_PROJECT_ROOT` 显式指定项目根目录，也可以用 `DEER_FLOW_CONFIG_PATH` 指向某个具体配置文件。运行期状态默认写到项目根目录下的 `.deer-flow`，可用 `DEER_FLOW_HOME` 覆盖；skills 默认读取项目根目录下的 `skills/`，可用 `DEER_FLOW_SKILLS_PATH` 覆盖。
+前提：先完成上面的“配置”步骤（`make config` 和模型 API key 配置）。`make dev` 需要有效配置文件，默认读取项目根目录下的 `config.yaml`，也可以通过 `DEER_FLOW_CONFIG_PATH` 覆盖。
 在 Windows 上，请使用 Git Bash 运行本地开发流程。基于 bash 的服务脚本不支持直接在原生 `cmd.exe` 或 PowerShell 中执行，且 WSL 也不保证可用，因为部分脚本依赖 Git for Windows 的 `cygpath` 等工具。
 
 1. **检查依赖环境**：
@@ -248,7 +248,6 @@ DeerFlow 支持从即时通讯应用接收任务。只要配置完成，对应
 | Slack | Socket Mode | 中等 |
 | Feishu / Lark | WebSocket | 中等 |
 | 企业微信智能机器人 | WebSocket | 中等 |
-| 钉钉 | Stream Push（WebSocket） | 中等 |
 
 **`config.yaml` 中的配置示例：**
 
@@ -305,13 +304,6 @@ channels:
           context:
             thinking_enabled: true
             subagent_enabled: true
-
-  dingtalk:
-    enabled: true
-    client_id: $DINGTALK_CLIENT_ID             # 钉钉开放平台 ClientId
-    client_secret: $DINGTALK_CLIENT_SECRET     # 钉钉开放平台 ClientSecret
-    allowed_users: []                          # 留空表示允许所有人
-    card_template_id: ""                       # 可选：AI 卡片模板 ID，用于流式打字机效果
 ```
 
 说明：
@@ -335,10 +327,6 @@ FEISHU_APP_SECRET=your_app_secret
 # 企业微信智能机器人
 WECOM_BOT_ID=your_bot_id
 WECOM_BOT_SECRET=your_bot_secret
-
-# 钉钉
-DINGTALK_CLIENT_ID=your_client_id
-DINGTALK_CLIENT_SECRET=your_client_secret
 ```
 
 **Telegram 配置**
@@ -369,13 +357,6 @@ DINGTALK_CLIENT_SECRET=your_client_secret
 4. 安装后端依赖时确保包含 `wecom-aibot-python-sdk`，渠道会通过 WebSocket 长连接接收消息，无需公网回调地址。
 5. 当前支持文本、图片和文件入站消息；agent 生成的最终图片/文件也会回传到企业微信会话中。
 
-**钉钉配置**
-
-1. 在 [钉钉开放平台](https://open.dingtalk.com/) 创建应用，并启用 **机器人** 能力。
-2. 在机器人配置页面设置消息接收模式为 **Stream模式**。
-3. 复制 `Client ID` 和 `Client Secret`，在 `.env` 中设置 `DINGTALK_CLIENT_ID` 和 `DINGTALK_CLIENT_SECRET`，并在 `config.yaml` 中启用该渠道。
-4. *（可选）* 如需开启流式 AI 卡片回复（打字机效果），请在[钉钉卡片平台](https://open.dingtalk.com/document/dingstart/typewriter-effect-streaming-ai-card)创建 **AI 卡片**模板，然后在 `config.yaml` 中将 `card_template_id` 设为该模板 ID。同时需要申请 `Card.Streaming.Write` 和 `Card.Instance.Write` 权限。
-
 **命令**
 
 渠道连接完成后，你可以直接在聊天窗口里和 DeerFlow 交互：

backend/CLAUDE.md

@@ -7,13 +7,15 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 DeerFlow is a LangGraph-based AI super agent system with a full-stack architecture. The backend provides a "super agent" with sandbox execution, persistent memory, subagent delegation, and extensible tool integration - all operating in per-thread isolated environments.
 
 **Architecture**:
-- **Gateway API** (port 8001): REST API plus embedded LangGraph-compatible agent runtime
+- **LangGraph Server** (port 2024): Agent runtime and workflow execution
+- **Gateway API** (port 8001): REST API for models, MCP, skills, memory, artifacts, uploads, and local thread cleanup
 - **Frontend** (port 3000): Next.js web interface
 - **Nginx** (port 2026): Unified reverse proxy entry point
 - **Provisioner** (port 8002, optional in Docker dev): Started only when sandbox is configured for provisioner/Kubernetes mode
 
-**Runtime**:
-- `make dev`, Docker dev, and production all run the agent runtime in Gateway via `RunManager` + `run_agent()` + `StreamBridge` (`packages/harness/deerflow/runtime/`). Nginx exposes that runtime at `/api/langgraph/*` and rewrites it to Gateway's native `/api/*` routers.
+**Runtime Modes**:
+- **Standard mode** (`make dev`): LangGraph Server handles agent execution as a separate process. 4 processes total.
+- **Gateway mode** (`make dev-pro`, experimental): Agent runtime embedded in Gateway via `RunManager` + `run_agent()` + `StreamBridge` (`packages/harness/deerflow/runtime/`). Service manages its own concurrency via async tasks. 3 processes total, no LangGraph Server.
 
 **Project Structure**:
 ```
@@ -23,7 +25,7 @@ deer-flow/
 ├── extensions_config.json      # MCP servers and skills configuration
 ├── backend/                    # Backend application (this directory)
 │   ├── Makefile               # Backend-only commands (dev, gateway, lint)
-│   ├── langgraph.json         # LangGraph Studio graph configuration
+│   ├── langgraph.json         # LangGraph server configuration
 │   ├── packages/
 │   │   └── harness/           # deerflow-harness package (import: deerflow.*)
 │   │       ├── pyproject.toml
@@ -81,15 +83,16 @@ When making code changes, you MUST update the relevant documentation:
 ```bash
 make check      # Check system requirements
 make install    # Install all dependencies (frontend + backend)
-make dev        # Start all services (Gateway + Frontend + Nginx), with config.yaml preflight
-make start      # Start production services locally
+make dev        # Start all services (LangGraph + Gateway + Frontend + Nginx), with config.yaml preflight
+make dev-pro    # Gateway mode (experimental): skip LangGraph, agent runtime embedded in Gateway
+make start-pro  # Production + Gateway mode (experimental)
 make stop       # Stop all services
 ```
 
 **Backend directory** (for backend development only):
 ```bash
 make install    # Install backend dependencies
-make dev        # Run Gateway API with reload (port 8001)
+make dev        # Run LangGraph server only (port 2024)
 make gateway    # Run Gateway API only (port 8001)
 make test       # Run all backend tests
 make lint       # Lint with ruff
@@ -112,7 +115,7 @@ CI runs these regression tests for every pull request via [.github/workflows/bac
 The backend is split into two layers with a strict dependency direction:
 
 - **Harness** (`packages/harness/deerflow/`): Publishable agent framework package (`deerflow-harness`). Import prefix: `deerflow.*`. Contains agent orchestration, tools, sandbox, models, MCP, skills, config — everything needed to build and run agents.
-- **App** (`app/`): Unpublished application code. Import prefix: `app.*`. Contains the FastAPI Gateway API and IM channel integrations (Feishu, Slack, Telegram, DingTalk).
+- **App** (`app/`): Unpublished application code. Import prefix: `app.*`. Contains the FastAPI Gateway API and IM channel integrations (Feishu, Slack, Telegram).
 
 **Dependency rule**: App imports deerflow, but deerflow never imports app. This boundary is enforced by `tests/test_harness_boundary.py` which runs in CI.
 
@@ -153,26 +156,20 @@ from deerflow.config import get_app_config
 
 ### Middleware Chain
 
-Lead-agent middlewares are assembled in strict append order across `packages/harness/deerflow/agents/middlewares/tool_error_handling_middleware.py` (`build_lead_runtime_middlewares`) and `packages/harness/deerflow/agents/lead_agent/agent.py` (`_build_middlewares`):
+Middlewares execute in strict order in `packages/harness/deerflow/agents/lead_agent/agent.py`:
 
 1. **ThreadDataMiddleware** - Creates per-thread directories under the user's isolation scope (`backend/.deer-flow/users/{user_id}/threads/{thread_id}/user-data/{workspace,uploads,outputs}`); resolves `user_id` via `get_effective_user_id()` (falls back to `"default"` in no-auth mode); Web UI thread deletion now follows LangGraph thread removal with Gateway cleanup of the local thread directory
 2. **UploadsMiddleware** - Tracks and injects newly uploaded files into conversation
 3. **SandboxMiddleware** - Acquires sandbox, stores `sandbox_id` in state
-4. **DanglingToolCallMiddleware** - Injects placeholder ToolMessages for AIMessage tool_calls that lack responses (e.g., due to user interruption), including raw provider tool-call payloads preserved only in `additional_kwargs["tool_calls"]`
-5. **LLMErrorHandlingMiddleware** - Normalizes provider/model invocation failures into recoverable assistant-facing errors before later middleware/tool stages run
-6. **GuardrailMiddleware** - Pre-tool-call authorization via pluggable `GuardrailProvider` protocol (optional, if `guardrails.enabled` in config). Evaluates each tool call and returns error ToolMessage on deny. Three provider options: built-in `AllowlistProvider` (zero deps), OAP policy providers (e.g. `aport-agent-guardrails`), or custom providers. See [docs/GUARDRAILS.md](docs/GUARDRAILS.md) for setup, usage, and how to implement a provider.
-7. **SandboxAuditMiddleware** - Audits sandboxed shell/file operations for security logging before tool execution continues
-8. **ToolErrorHandlingMiddleware** - Converts tool exceptions into error `ToolMessage`s so the run can continue instead of aborting
-9. **SummarizationMiddleware** - Context reduction when approaching token limits (optional, if enabled)
-10. **TodoListMiddleware** - Task tracking with `write_todos` tool (optional, if plan_mode)
-11. **TokenUsageMiddleware** - Records token usage metrics when token tracking is enabled (optional)
-12. **TitleMiddleware** - Auto-generates thread title after first complete exchange and normalizes structured message content before prompting the title model
-13. **MemoryMiddleware** - Queues conversations for async memory update (filters to user + final AI responses)
-14. **ViewImageMiddleware** - Injects base64 image data before LLM call (conditional on vision support)
-15. **DeferredToolFilterMiddleware** - Hides deferred tool schemas from the bound model until tool search is enabled (optional)
-16. **SubagentLimitMiddleware** - Truncates excess `task` tool calls from model response to enforce `MAX_CONCURRENT_SUBAGENTS` limit (optional, if `subagent_enabled`)
-17. **LoopDetectionMiddleware** - Detects repeated tool-call loops; hard-stop responses clear both structured `tool_calls` and raw provider tool-call metadata before forcing a final text answer
-18. **ClarificationMiddleware** - Intercepts `ask_clarification` tool calls, interrupts via `Command(goto=END)` (must be last)
+4. **DanglingToolCallMiddleware** - Injects placeholder ToolMessages for AIMessage tool_calls that lack responses (e.g., due to user interruption)
+5. **GuardrailMiddleware** - Pre-tool-call authorization via pluggable `GuardrailProvider` protocol (optional, if `guardrails.enabled` in config). Evaluates each tool call and returns error ToolMessage on deny. Three provider options: built-in `AllowlistProvider` (zero deps), OAP policy providers (e.g. `aport-agent-guardrails`), or custom providers. See [docs/GUARDRAILS.md](docs/GUARDRAILS.md) for setup, usage, and how to implement a provider.
+6. **SummarizationMiddleware** - Context reduction when approaching token limits (optional, if enabled)
+7. **TodoListMiddleware** - Task tracking with `write_todos` tool (optional, if plan_mode)
+8. **TitleMiddleware** - Auto-generates thread title after first complete exchange and normalizes structured message content before prompting the title model
+9. **MemoryMiddleware** - Queues conversations for async memory update (filters to user + final AI responses)
+10. **ViewImageMiddleware** - Injects base64 image data before LLM call (conditional on vision support)
+11. **SubagentLimitMiddleware** - Truncates excess `task` tool calls from model response to enforce `MAX_CONCURRENT_SUBAGENTS` limit (optional, if subagent_enabled)
+12. **ClarificationMiddleware** - Intercepts `ask_clarification` tool calls, interrupts via `Command(goto=END)` (must be last)
 
 ### Configuration System
 
@@ -205,7 +202,7 @@ Configuration priority:
 
 ### Gateway API (`app/gateway/`)
 
-FastAPI application on port 8001 with health check at `GET /health`. Set `GATEWAY_ENABLE_DOCS=false` to disable `/docs`, `/redoc`, and `/openapi.json` in production (default: enabled).
+FastAPI application on port 8001 with health check at `GET /health`.
 
 **Routers**:
 
@@ -312,10 +309,9 @@ Proxied through nginx: `/api/langgraph/*` → LangGraph, all other `/api/*` →
 
 ### IM Channels System (`app/channels/`)
 
-Bridges external messaging platforms (Feishu, Slack, Telegram, DingTalk) to the DeerFlow agent via the LangGraph Server.
+Bridges external messaging platforms (Feishu, Slack, Telegram) to the DeerFlow agent via the LangGraph Server.
 
-
-**Architecture**: Channels communicate with Gateway through the `langgraph-sdk` HTTP client (same as the frontend), ensuring threads are created and managed server-side. The internal SDK client injects process-local internal auth plus a matching CSRF cookie/header pair so Gateway accepts state-changing thread/run requests from channel workers without relying on browser session cookies.
+**Architecture**: Channels communicate with the LangGraph Server through `langgraph-sdk` HTTP client (same as the frontend), ensuring threads are created and managed server-side.
 
 **Components**:
 - `message_bus.py` - Async pub/sub hub (`InboundMessage` → queue → dispatcher; `OutboundMessage` → callbacks → channels)
@@ -323,25 +319,23 @@ Bridges external messaging platforms (Feishu, Slack, Telegram, DingTalk) to the
 - `manager.py` - Core dispatcher: creates threads via `client.threads.create()`, routes commands, keeps Slack/Telegram on `client.runs.wait()`, and uses `client.runs.stream(["messages-tuple", "values"])` for Feishu incremental outbound updates
 - `base.py` - Abstract `Channel` base class (start/stop/send lifecycle)
 - `service.py` - Manages lifecycle of all configured channels from `config.yaml`
-- `slack.py` / `feishu.py` / `telegram.py` / `dingtalk.py` - Platform-specific implementations (`feishu.py` tracks the running card `message_id` in memory and patches the same card in place; `dingtalk.py` optionally uses AI Card streaming for in-place updates when `card_template_id` is configured)
+- `slack.py` / `feishu.py` / `telegram.py` - Platform-specific implementations (`feishu.py` tracks the running card `message_id` in memory and patches the same card in place)
 
 **Message Flow**:
 1. External platform -> Channel impl -> `MessageBus.publish_inbound()`
 2. `ChannelManager._dispatch_loop()` consumes from queue
-3. For chat: look up/create thread through Gateway's LangGraph-compatible API
+3. For chat: look up/create thread on LangGraph Server
 4. Feishu chat: `runs.stream()` → accumulate AI text → publish multiple outbound updates (`is_final=False`) → publish final outbound (`is_final=True`)
 5. Slack/Telegram chat: `runs.wait()` → extract final response → publish outbound
 6. Feishu channel sends one running reply card up front, then patches the same card for each outbound update (card JSON sets `config.update_multi=true` for Feishu's patch API requirement)
-7. DingTalk AI Card mode (when `card_template_id` configured): `runs.stream()` → create card with initial text → stream updates via `PUT /v1.0/card/streaming` → finalize on `is_final=True`. Falls back to `sampleMarkdown` if card creation or streaming fails
-8. For commands (`/new`, `/status`, `/models`, `/memory`, `/help`): handle locally or query Gateway API
-9. Outbound → channel callbacks → platform reply
+7. For commands (`/new`, `/status`, `/models`, `/memory`, `/help`): handle locally or query Gateway API
+8. Outbound → channel callbacks → platform reply
 
 **Configuration** (`config.yaml` -> `channels`):
-- `langgraph_url` - LangGraph-compatible Gateway API base URL (default: `http://localhost:8001/api`)
+- `langgraph_url` - LangGraph Server URL (default: `http://localhost:2024`)
 - `gateway_url` - Gateway API URL for auxiliary commands (default: `http://localhost:8001`)
-- In Docker Compose, IM channels run inside the `gateway` container, so `localhost` points back to that container. Use `http://gateway:8001/api` for `langgraph_url` and `http://gateway:8001` for `gateway_url`, or set `DEER_FLOW_CHANNELS_LANGGRAPH_URL` / `DEER_FLOW_CHANNELS_GATEWAY_URL`.
-- Per-channel configs: `feishu` (app_id, app_secret), `slack` (bot_token, app_token), `telegram` (bot_token), `dingtalk` (client_id, client_secret, optional `card_template_id` for AI Card streaming)
-
+- In Docker Compose, IM channels run inside the `gateway` container, so `localhost` points back to that container. Use `http://langgraph:2024` / `http://gateway:8001`, or set `DEER_FLOW_CHANNELS_LANGGRAPH_URL` / `DEER_FLOW_CHANNELS_GATEWAY_URL`.
+- Per-channel configs: `feishu` (app_id, app_secret), `slack` (bot_token, app_token), `telegram` (bot_token)
 
 ### Memory System (`packages/harness/deerflow/agents/memory/`)
 
@@ -410,9 +404,9 @@ Both can be modified at runtime via Gateway API endpoints or `DeerFlowClient` me
 
 `DeerFlowClient` provides direct in-process access to all DeerFlow capabilities without HTTP services. All return types align with the Gateway API response schemas, so consumer code works identically in HTTP and embedded modes.
 
-**Architecture**: Imports the same `deerflow` modules that Gateway API uses. Shares the same config files and data directories. No FastAPI dependency.
+**Architecture**: Imports the same `deerflow` modules that LangGraph Server and Gateway API use. Shares the same config files and data directories. No FastAPI dependency.
 
-**Agent Conversation**:
+**Agent Conversation** (replaces LangGraph Server):
 - `chat(message, thread_id)` — synchronous, accumulates streaming deltas per message-id and returns the final AI text
 - `stream(message, thread_id)` — subscribes to LangGraph `stream_mode=["values", "messages", "custom"]` and yields `StreamEvent`:
   - `"values"` — full state snapshot (title, messages, artifacts); AI text already delivered via `messages` mode is **not** re-synthesized here to avoid duplicate deliveries
@@ -475,15 +469,20 @@ This starts all services and makes the application available at `http://localhos
 | | **Local Foreground** | **Local Daemon** | **Docker Dev** | **Docker Prod** |
 |---|---|---|---|---|
 | **Dev** | `./scripts/serve.sh --dev`<br/>`make dev` | `./scripts/serve.sh --dev --daemon`<br/>`make dev-daemon` | `./scripts/docker.sh start`<br/>`make docker-start` | — |
+| **Dev + Gateway** | `./scripts/serve.sh --dev --gateway`<br/>`make dev-pro` | `./scripts/serve.sh --dev --gateway --daemon`<br/>`make dev-daemon-pro` | `./scripts/docker.sh start --gateway`<br/>`make docker-start-pro` | — |
 | **Prod** | `./scripts/serve.sh --prod`<br/>`make start` | `./scripts/serve.sh --prod --daemon`<br/>`make start-daemon` | — | `./scripts/deploy.sh`<br/>`make up` |
+| **Prod + Gateway** | `./scripts/serve.sh --prod --gateway`<br/>`make start-pro` | `./scripts/serve.sh --prod --gateway --daemon`<br/>`make start-daemon-pro` | — | `./scripts/deploy.sh --gateway`<br/>`make up-pro` |
 
 | Action | Local | Docker Dev | Docker Prod |
 |---|---|---|---|
 | **Stop** | `./scripts/serve.sh --stop`<br/>`make stop` | `./scripts/docker.sh stop`<br/>`make docker-stop` | `./scripts/deploy.sh down`<br/>`make down` |
 | **Restart** | `./scripts/serve.sh --restart [flags]` | `./scripts/docker.sh restart` | — |
 
+Gateway mode embeds the agent runtime in Gateway, no LangGraph server.
+
 **Nginx routing**:
-- `/api/langgraph/*` → Gateway embedded runtime (8001), rewritten to `/api/*`
+- Standard mode: `/api/langgraph/*` → LangGraph Server (2024)
+- Gateway mode: `/api/langgraph/*` → Gateway embedded runtime (8001) (via envsubst)
 - `/api/*` (other) → Gateway API (8001)
 - `/` (non-API) → Frontend (3000)
 
@@ -492,11 +491,15 @@ This starts all services and makes the application available at `http://localhos
 From the **backend** directory:
 
 ```bash
-# Gateway API
+# Terminal 1: LangGraph server
+make dev
+
+# Terminal 2: Gateway API
 make gateway
 ```
 
 Direct access (without nginx):
+- LangGraph: `http://localhost:2024`
 - Gateway: `http://localhost:8001`
 
 ### Frontend Configuration

backend/Makefile

@@ -2,7 +2,7 @@ install:
 	uv sync
 
 dev:
-	PYTHONPATH=. uv run uvicorn app.gateway.app:app --host 0.0.0.0 --port 8001 --reload
+	uv run langgraph dev --no-browser --no-reload --n-jobs-per-worker 10
 
 gateway:
 	PYTHONPATH=. uv run uvicorn app.gateway.app:app --host 0.0.0.0 --port 8001

backend/app/channels/__init__.py

@@ -2,7 +2,7 @@
 
 Provides a pluggable channel system that connects external messaging platforms
 (Feishu/Lark, Slack, Telegram) to the DeerFlow agent via the ChannelManager,
-which uses ``langgraph-sdk`` to communicate with Gateway's LangGraph-compatible API.
+which uses ``langgraph-sdk`` to communicate with the underlying LangGraph Server.
 """
 
 from app.channels.base import Channel

backend/app/channels/base.py

@@ -31,10 +31,6 @@ class Channel(ABC):
     def is_running(self) -> bool:
         return self._running
 
-    @property
-    def supports_streaming(self) -> bool:
-        return False
-
     # -- lifecycle ---------------------------------------------------------
 
     @abstractmethod

backend/app/channels/dingtalk.py

@@ -1,740 +0,0 @@
-"""DingTalk channel implementation."""
-
-from __future__ import annotations
-
-import asyncio
-import json
-import logging
-import re
-import threading
-import time
-from pathlib import Path
-from typing import Any
-
-import httpx
-
-from app.channels.base import Channel
-from app.channels.commands import KNOWN_CHANNEL_COMMANDS
-from app.channels.message_bus import InboundMessage, InboundMessageType, MessageBus, OutboundMessage, ResolvedAttachment
-
-logger = logging.getLogger(__name__)
-
-DINGTALK_API_BASE = "https://api.dingtalk.com"
-
-_TOKEN_REFRESH_MARGIN_SECONDS = 300
-
-_CONVERSATION_TYPE_P2P = "1"
-_CONVERSATION_TYPE_GROUP = "2"
-
-_MAX_UPLOAD_SIZE_BYTES = 20 * 1024 * 1024
-
-
-def _normalize_conversation_type(raw: Any) -> str:
-    """Normalize ``conversationType`` to ``"1"`` (P2P) or ``"2"`` (group).
-
-    Stream payloads may send int or string values.
-    """
-    if raw is None:
-        return _CONVERSATION_TYPE_P2P
-    s = str(raw).strip()
-    if s == _CONVERSATION_TYPE_GROUP:
-        return _CONVERSATION_TYPE_GROUP
-    return _CONVERSATION_TYPE_P2P
-
-
-def _normalize_allowed_users(allowed_users: Any) -> set[str]:
-    if allowed_users is None:
-        return set()
-    if isinstance(allowed_users, str):
-        values = [allowed_users]
-    elif isinstance(allowed_users, (list, tuple, set)):
-        values = allowed_users
-    else:
-        logger.warning(
-            "DingTalk allowed_users should be a list of user IDs; treating %s as one string value",
-            type(allowed_users).__name__,
-        )
-        values = [allowed_users]
-    return {str(uid) for uid in values if str(uid)}
-
-
-def _is_dingtalk_command(text: str) -> bool:
-    if not text.startswith("/"):
-        return False
-    return text.split(maxsplit=1)[0].lower() in KNOWN_CHANNEL_COMMANDS
-
-
-def _extract_text_from_rich_text(rich_text_list: list) -> str:
-    parts: list[str] = []
-    for item in rich_text_list:
-        if isinstance(item, dict) and "text" in item:
-            parts.append(item["text"])
-    return " ".join(parts)
-
-
-_FENCED_CODE_BLOCK_RE = re.compile(r"```(\w*)\n(.*?)```", re.DOTALL)
-_INLINE_CODE_RE = re.compile(r"`([^`\n]+)`")
-_HORIZONTAL_RULE_RE = re.compile(r"^-{3,}$", re.MULTILINE)
-_TABLE_SEPARATOR_RE = re.compile(r"^\|[-:| ]+\|$", re.MULTILINE)
-
-
-def _convert_markdown_table(text: str) -> str:
-    # DingTalk sampleMarkdown does not render pipe-delimited tables.
-    lines = text.split("\n")
-    result: list[str] = []
-    i = 0
-    while i < len(lines):
-        line = lines[i]
-        # Detect table: header row followed by separator row
-        if i + 1 < len(lines) and line.strip().startswith("|") and _TABLE_SEPARATOR_RE.match(lines[i + 1].strip()):
-            headers = [h.strip() for h in line.strip().strip("|").split("|")]
-            i += 2  # skip header + separator
-            while i < len(lines) and lines[i].strip().startswith("|"):
-                cells = [c.strip() for c in lines[i].strip().strip("|").split("|")]
-                for h, c in zip(headers, cells):
-                    result.append(f"> **{h}**: {c}")
-                result.append("")
-                i += 1
-        else:
-            result.append(line)
-            i += 1
-    return "\n".join(result)
-
-
-def _adapt_markdown_for_dingtalk(text: str) -> str:
-    """Adapt markdown for DingTalk's limited sampleMarkdown renderer."""
-
-    def _code_block_to_quote(match: re.Match) -> str:
-        lang = match.group(1)
-        code = match.group(2).rstrip("\n")
-        prefix = f"> **{lang}**\n" if lang else ""
-        quoted_lines = "\n".join(f"> {line}" for line in code.split("\n"))
-        return f"{prefix}{quoted_lines}\n"
-
-    text = _FENCED_CODE_BLOCK_RE.sub(_code_block_to_quote, text)
-    text = _INLINE_CODE_RE.sub(r"**\1**", text)
-    text = _convert_markdown_table(text)
-    text = _HORIZONTAL_RULE_RE.sub("───────────", text)
-    return text
-
-
-class DingTalkChannel(Channel):
-    """DingTalk IM channel using Stream Push (WebSocket, no public IP needed)."""
-
-    def __init__(self, bus: MessageBus, config: dict[str, Any]) -> None:
-        super().__init__(name="dingtalk", bus=bus, config=config)
-        self._thread: threading.Thread | None = None
-        self._main_loop: asyncio.AbstractEventLoop | None = None
-        self._client_id: str = ""
-        self._client_secret: str = ""
-        self._allowed_users: set[str] = _normalize_allowed_users(config.get("allowed_users"))
-        self._cached_token: str = ""
-        self._token_expires_at: float = 0.0
-        self._token_lock = asyncio.Lock()
-        self._card_template_id: str = config.get("card_template_id", "")
-        self._card_track_ids: dict[str, str] = {}
-        self._dingtalk_client: Any = None
-        self._stream_client: Any = None
-        self._incoming_messages: dict[str, Any] = {}
-        self._incoming_messages_lock = threading.Lock()
-        self._card_repliers: dict[str, Any] = {}
-
-    @property
-    def supports_streaming(self) -> bool:
-        return bool(self._card_template_id)
-
-    async def start(self) -> None:
-        if self._running:
-            return
-
-        try:
-            import dingtalk_stream  # noqa: F401
-        except ImportError:
-            logger.error("dingtalk-stream is not installed. Install it with: uv add dingtalk-stream")
-            return
-
-        client_id = self.config.get("client_id", "")
-        client_secret = self.config.get("client_secret", "")
-
-        if not client_id or not client_secret:
-            logger.error("DingTalk channel requires client_id and client_secret")
-            return
-
-        self._client_id = client_id
-        self._client_secret = client_secret
-        self._main_loop = asyncio.get_running_loop()
-
-        if self._card_template_id:
-            logger.info("[DingTalk] AI Card mode enabled (template=%s)", self._card_template_id)
-
-        self._running = True
-        self.bus.subscribe_outbound(self._on_outbound)
-
-        self._thread = threading.Thread(
-            target=self._run_stream,
-            args=(client_id, client_secret),
-            daemon=True,
-        )
-        self._thread.start()
-        logger.info("DingTalk channel started")
-
-    async def stop(self) -> None:
-        self._running = False
-        self.bus.unsubscribe_outbound(self._on_outbound)
-
-        stream_client = self._stream_client
-        if stream_client is not None:
-            try:
-                if hasattr(stream_client, "disconnect"):
-                    stream_client.disconnect()
-            except Exception:
-                logger.debug("[DingTalk] error disconnecting stream client", exc_info=True)
-
-        self._dingtalk_client = None
-        self._stream_client = None
-        with self._incoming_messages_lock:
-            self._incoming_messages.clear()
-        self._card_repliers.clear()
-        self._card_track_ids.clear()
-        if self._thread:
-            self._thread.join(timeout=5)
-            self._thread = None
-        logger.info("DingTalk channel stopped")
-
-    def _resolve_routing(self, msg: OutboundMessage) -> tuple[str, str, str]:
-        """Return (conversation_type, sender_staff_id, conversation_id).
-
-        Uses msg.chat_id as the primary routing key; metadata as fallback.
-        """
-        conversation_type = _normalize_conversation_type(msg.metadata.get("conversation_type"))
-        sender_staff_id = msg.metadata.get("sender_staff_id", "")
-        conversation_id = msg.metadata.get("conversation_id", "")
-        if conversation_type == _CONVERSATION_TYPE_GROUP:
-            conversation_id = msg.chat_id or conversation_id
-        else:
-            sender_staff_id = msg.chat_id or sender_staff_id
-        return conversation_type, sender_staff_id, conversation_id
-
-    async def send(self, msg: OutboundMessage, *, _max_retries: int = 3) -> None:
-        conversation_type, sender_staff_id, conversation_id = self._resolve_routing(msg)
-        robot_code = self._client_id
-
-        # Card mode: stream update to existing AI card
-        source_key = self._make_card_source_key_from_outbound(msg)
-        out_track_id = self._card_track_ids.get(source_key)
-
-        # ``card_template_id`` enables ``runs.stream`` (non-final + final outbounds).
-        # If card creation failed, skip non-final chunks to avoid duplicate messages.
-        if self._card_template_id and not out_track_id and not msg.is_final:
-            return
-
-        if out_track_id:
-            try:
-                await self._stream_update_card(
-                    out_track_id,
-                    msg.text,
-                    is_finalize=msg.is_final,
-                )
-            except Exception:
-                logger.warning("[DingTalk] card stream failed, falling back to sampleMarkdown")
-                if msg.is_final:
-                    self._card_track_ids.pop(source_key, None)
-                    self._card_repliers.pop(out_track_id, None)
-                    await self._send_markdown_fallback(robot_code, conversation_type, sender_staff_id, conversation_id, msg.text)
-                    return
-            if msg.is_final:
-                self._card_track_ids.pop(source_key, None)
-                self._card_repliers.pop(out_track_id, None)
-            return
-
-        # Non-card mode: send sampleMarkdown with retry
-        last_exc: Exception | None = None
-        for attempt in range(_max_retries):
-            try:
-                if conversation_type == _CONVERSATION_TYPE_GROUP:
-                    await self._send_group_message(robot_code, conversation_id, msg.text, at_user_ids=[sender_staff_id] if sender_staff_id else None)
-                else:
-                    await self._send_p2p_message(robot_code, sender_staff_id, msg.text)
-                return
-            except Exception as exc:
-                last_exc = exc
-                if attempt < _max_retries - 1:
-                    delay = 2**attempt
-                    logger.warning(
-                        "[DingTalk] send failed (attempt %d/%d), retrying in %ds: %s",
-                        attempt + 1,
-                        _max_retries,
-                        delay,
-                        exc,
-                    )
-                    await asyncio.sleep(delay)
-
-        logger.error("[DingTalk] send failed after %d attempts: %s", _max_retries, last_exc)
-        if last_exc is None:
-            raise RuntimeError("DingTalk send failed without an exception from any attempt")
-        raise last_exc
-
-    async def _send_markdown_fallback(
-        self,
-        robot_code: str,
-        conversation_type: str,
-        sender_staff_id: str,
-        conversation_id: str,
-        text: str,
-    ) -> None:
-        try:
-            if conversation_type == _CONVERSATION_TYPE_GROUP:
-                await self._send_group_message(robot_code, conversation_id, text)
-            else:
-                await self._send_p2p_message(robot_code, sender_staff_id, text)
-        except Exception:
-            logger.exception("[DingTalk] markdown fallback also failed")
-            raise
-
-    async def send_file(self, msg: OutboundMessage, attachment: ResolvedAttachment) -> bool:
-        if attachment.size > _MAX_UPLOAD_SIZE_BYTES:
-            logger.warning("[DingTalk] file too large (%d bytes), skipping: %s", attachment.size, attachment.filename)
-            return False
-
-        conversation_type, sender_staff_id, conversation_id = self._resolve_routing(msg)
-        robot_code = self._client_id
-
-        try:
-            media_id = await self._upload_media(attachment.actual_path, "image" if attachment.is_image else "file")
-            if not media_id:
-                return False
-
-            if attachment.is_image:
-                msg_key = "sampleImageMsg"
-                msg_param = json.dumps({"photoURL": media_id})
-            else:
-                msg_key = "sampleFile"
-                msg_param = json.dumps(
-                    {
-                        "fileUrl": media_id,
-                        "fileName": attachment.filename,
-                        "fileSize": str(attachment.size),
-                    }
-                )
-
-            token = await self._get_access_token()
-            async with httpx.AsyncClient(timeout=httpx.Timeout(30.0)) as client:
-                if conversation_type == _CONVERSATION_TYPE_GROUP:
-                    response = await client.post(
-                        f"{DINGTALK_API_BASE}/v1.0/robot/groupMessages/send",
-                        headers=self._api_headers(token),
-                        json={
-                            "msgKey": msg_key,
-                            "msgParam": msg_param,
-                            "robotCode": robot_code,
-                            "openConversationId": conversation_id,
-                        },
-                    )
-                else:
-                    response = await client.post(
-                        f"{DINGTALK_API_BASE}/v1.0/robot/oToMessages/batchSend",
-                        headers=self._api_headers(token),
-                        json={
-                            "msgKey": msg_key,
-                            "msgParam": msg_param,
-                            "robotCode": robot_code,
-                            "userIds": [sender_staff_id],
-                        },
-                    )
-                response.raise_for_status()
-
-            logger.info("[DingTalk] file sent: %s", attachment.filename)
-            return True
-        except (httpx.HTTPError, OSError, ValueError, TypeError, AttributeError):
-            logger.exception("[DingTalk] failed to send file: %s", attachment.filename)
-            return False
-
-    # -- stream client (runs in dedicated thread) --------------------------
-
-    def _run_stream(self, client_id: str, client_secret: str) -> None:
-        try:
-            import dingtalk_stream
-
-            credential = dingtalk_stream.Credential(client_id, client_secret)
-            client = dingtalk_stream.DingTalkStreamClient(credential)
-            self._stream_client = client
-            client.register_callback_handler(
-                dingtalk_stream.chatbot.ChatbotMessage.TOPIC,
-                _DingTalkMessageHandler(self),
-            )
-            client.start_forever()
-        except Exception:
-            if self._running:
-                logger.exception("DingTalk Stream Push error")
-        finally:
-            self._stream_client = None
-
-    def _on_chatbot_message(self, message: Any) -> None:
-        if not self._running:
-            return
-        try:
-            sender_staff_id = message.sender_staff_id or ""
-            conversation_type = _normalize_conversation_type(message.conversation_type)
-            conversation_id = message.conversation_id or ""
-            msg_id = message.message_id or ""
-            sender_nick = message.sender_nick or ""
-
-            if self._allowed_users and sender_staff_id not in self._allowed_users:
-                logger.debug("[DingTalk] ignoring message from non-allowed user: %s", sender_staff_id)
-                return
-
-            text = self._extract_text(message)
-            if not text:
-                logger.info("[DingTalk] empty text, ignoring message")
-                return
-
-            logger.info(
-                "[DingTalk] parsed message: conv_type=%s, msg_id=%s, sender=%s(%s), text=%r",
-                conversation_type,
-                msg_id,
-                sender_staff_id,
-                sender_nick,
-                text[:100],
-            )
-
-            if _is_dingtalk_command(text):
-                msg_type = InboundMessageType.COMMAND
-            else:
-                msg_type = InboundMessageType.CHAT
-
-            # P2P: topic_id=None (single thread per user, like Telegram private chat)
-            # Group: topic_id=msg_id (each new message starts a new topic, like Feishu)
-            topic_id: str | None = msg_id if conversation_type == _CONVERSATION_TYPE_GROUP else None
-
-            # chat_id uses conversation_id for groups, sender_staff_id for P2P
-            chat_id = conversation_id if conversation_type == _CONVERSATION_TYPE_GROUP else sender_staff_id
-
-            inbound = self._make_inbound(
-                chat_id=chat_id,
-                user_id=sender_staff_id,
-                text=text,
-                msg_type=msg_type,
-                thread_ts=msg_id,
-                metadata={
-                    "conversation_type": conversation_type,
-                    "conversation_id": conversation_id,
-                    "sender_staff_id": sender_staff_id,
-                    "sender_nick": sender_nick,
-                    "message_id": msg_id,
-                },
-            )
-            inbound.topic_id = topic_id
-
-            if self._card_template_id:
-                source_key = self._make_card_source_key(inbound)
-                with self._incoming_messages_lock:
-                    self._incoming_messages[source_key] = message
-
-            if self._main_loop and self._main_loop.is_running():
-                logger.info("[DingTalk] publishing inbound message to bus (type=%s, msg_id=%s)", msg_type.value, msg_id)
-                fut = asyncio.run_coroutine_threadsafe(
-                    self._prepare_inbound(chat_id, inbound),
-                    self._main_loop,
-                )
-                fut.add_done_callback(lambda f, mid=msg_id: self._log_future_error(f, "prepare_inbound", mid))
-            else:
-                logger.warning("[DingTalk] main loop not running, cannot publish inbound message")
-        except Exception:
-            logger.exception("[DingTalk] error processing chatbot message")
-
-    @staticmethod
-    def _extract_text(message: Any) -> str:
-        msg_type = message.message_type
-        if msg_type == "text" and message.text:
-            return message.text.content.strip()
-        if msg_type == "richText" and message.rich_text_content:
-            return _extract_text_from_rich_text(message.rich_text_content.rich_text_list).strip()
-        return ""
-
-    async def _prepare_inbound(self, chat_id: str, inbound: InboundMessage) -> None:
-        # Running reply must finish before publish_inbound so AI card tracks are
-        # registered before the manager emits streaming outbounds.
-        await self._send_running_reply(chat_id, inbound)
-        await self.bus.publish_inbound(inbound)
-
-    async def _send_running_reply(self, chat_id: str, inbound: InboundMessage) -> None:
-        conversation_type = inbound.metadata.get("conversation_type", _CONVERSATION_TYPE_P2P)
-        sender_staff_id = inbound.metadata.get("sender_staff_id", "")
-        conversation_id = inbound.metadata.get("conversation_id", "")
-        text = "\u23f3 Working on it..."
-
-        try:
-            if self._card_template_id:
-                source_key = self._make_card_source_key(inbound)
-                with self._incoming_messages_lock:
-                    chatbot_message = self._incoming_messages.pop(source_key, None)
-                out_track_id = await self._create_and_deliver_card(
-                    text,
-                    chatbot_message=chatbot_message,
-                )
-                if out_track_id:
-                    self._card_track_ids[source_key] = out_track_id
-                    logger.info("[DingTalk] AI card running reply sent for chat=%s", chat_id)
-                    return
-
-            robot_code = self._client_id
-            if conversation_type == _CONVERSATION_TYPE_GROUP:
-                await self._send_text_message_to_group(robot_code, conversation_id, text)
-            else:
-                await self._send_text_message_to_user(robot_code, sender_staff_id, text)
-            logger.info("[DingTalk] 'Working on it...' reply sent for chat=%s", chat_id)
-        except Exception:
-            logger.exception("[DingTalk] failed to send running reply for chat=%s", chat_id)
-
-    # -- DingTalk API helpers ----------------------------------------------
-
-    async def _get_access_token(self) -> str:
-        if self._cached_token and time.monotonic() < self._token_expires_at:
-            return self._cached_token
-        async with self._token_lock:
-            if self._cached_token and time.monotonic() < self._token_expires_at:
-                return self._cached_token
-            async with httpx.AsyncClient(timeout=httpx.Timeout(10.0)) as client:
-                response = await client.post(
-                    f"{DINGTALK_API_BASE}/v1.0/oauth2/accessToken",
-                    json={"appKey": self._client_id, "appSecret": self._client_secret},  # DingTalk API field names
-                )
-                response.raise_for_status()
-                data = response.json()
-
-                if not isinstance(data, dict):
-                    raise ValueError(f"DingTalk access token response must be a JSON object, got {type(data).__name__}")
-
-                access_token = data.get("accessToken")
-                if not isinstance(access_token, str) or not access_token.strip():
-                    raise ValueError("DingTalk access token response did not contain a usable accessToken")
-
-                raw_expires_in = data.get("expireIn", 7200)
-                try:
-                    expires_in = int(raw_expires_in)
-                except (TypeError, ValueError):
-                    logger.warning("[DingTalk] invalid expireIn value %r, using default 7200s", raw_expires_in)
-                    expires_in = 7200
-
-                self._cached_token = access_token.strip()
-                self._token_expires_at = time.monotonic() + expires_in - _TOKEN_REFRESH_MARGIN_SECONDS
-                return self._cached_token
-
-    @staticmethod
-    def _api_headers(token: str) -> dict[str, str]:
-        return {
-            "x-acs-dingtalk-access-token": token,
-            "Content-Type": "application/json",
-        }
-
-    async def _send_text_message_to_user(self, robot_code: str, user_id: str, text: str) -> None:
-        token = await self._get_access_token()
-        async with httpx.AsyncClient(timeout=httpx.Timeout(30.0)) as client:
-            response = await client.post(
-                f"{DINGTALK_API_BASE}/v1.0/robot/oToMessages/batchSend",
-                headers=self._api_headers(token),
-                json={
-                    "msgKey": "sampleText",
-                    "msgParam": json.dumps({"content": text}),
-                    "robotCode": robot_code,
-                    "userIds": [user_id],
-                },
-            )
-            response.raise_for_status()
-
-    async def _send_text_message_to_group(self, robot_code: str, conversation_id: str, text: str) -> None:
-        token = await self._get_access_token()
-        async with httpx.AsyncClient(timeout=httpx.Timeout(30.0)) as client:
-            response = await client.post(
-                f"{DINGTALK_API_BASE}/v1.0/robot/groupMessages/send",
-                headers=self._api_headers(token),
-                json={
-                    "msgKey": "sampleText",
-                    "msgParam": json.dumps({"content": text}),
-                    "robotCode": robot_code,
-                    "openConversationId": conversation_id,
-                },
-            )
-            response.raise_for_status()
-
-    async def _send_p2p_message(self, robot_code: str, user_id: str, text: str) -> None:
-        text = _adapt_markdown_for_dingtalk(text)
-        token = await self._get_access_token()
-        async with httpx.AsyncClient(timeout=httpx.Timeout(30.0)) as client:
-            response = await client.post(
-                f"{DINGTALK_API_BASE}/v1.0/robot/oToMessages/batchSend",
-                headers=self._api_headers(token),
-                json={
-                    "msgKey": "sampleMarkdown",
-                    "msgParam": json.dumps({"title": "DeerFlow", "text": text}),
-                    "robotCode": robot_code,
-                    "userIds": [user_id],
-                },
-            )
-            response.raise_for_status()
-            data = response.json()
-            if data.get("processQueryKey"):
-                logger.info("[DingTalk] P2P message sent to user=%s", user_id)
-            else:
-                logger.warning("[DingTalk] P2P send response: %s", data)
-
-    async def _send_group_message(
-        self,
-        robot_code: str,
-        conversation_id: str,
-        text: str,
-        *,
-        at_user_ids: list[str] | None = None,  # noqa: ARG002
-    ) -> None:
-        # at_user_ids accepted for call-site compatibility but not passed to the API
-        # (sampleMarkdown does not support @mentions).
-        text = _adapt_markdown_for_dingtalk(text)
-        token = await self._get_access_token()
-
-        async with httpx.AsyncClient(timeout=httpx.Timeout(30.0)) as client:
-            response = await client.post(
-                f"{DINGTALK_API_BASE}/v1.0/robot/groupMessages/send",
-                headers=self._api_headers(token),
-                json={
-                    "msgKey": "sampleMarkdown",
-                    "msgParam": json.dumps({"title": "DeerFlow", "text": text}),
-                    "robotCode": robot_code,
-                    "openConversationId": conversation_id,
-                },
-            )
-            response.raise_for_status()
-            data = response.json()
-            if data.get("processQueryKey"):
-                logger.info("[DingTalk] group message sent to conversation=%s", conversation_id)
-            else:
-                logger.warning("[DingTalk] group send response: %s", data)
-
-    # -- AI Card streaming helpers -------------------------------------------
-
-    def _make_card_source_key(self, inbound: InboundMessage) -> str:
-        m = inbound.metadata
-        return f"{m.get('conversation_type', '')}:{m.get('sender_staff_id', '')}:{m.get('conversation_id', '')}:{m.get('message_id', '')}"
-
-    def _make_card_source_key_from_outbound(self, msg: OutboundMessage) -> str:
-        m = msg.metadata
-        correlation_id = m.get("message_id") or msg.thread_ts or ""
-        return f"{m.get('conversation_type', '')}:{m.get('sender_staff_id', '')}:{m.get('conversation_id', '')}:{correlation_id}"
-
-    async def _create_and_deliver_card(
-        self,
-        initial_text: str,
-        *,
-        chatbot_message: Any = None,
-    ) -> str | None:
-        if self._dingtalk_client is None or chatbot_message is None:
-            logger.warning("[DingTalk] SDK client or chatbot_message unavailable, skipping AI card")
-            return None
-
-        try:
-            from dingtalk_stream.card_replier import AICardReplier
-        except ImportError:
-            logger.warning("[DingTalk] dingtalk-stream card_replier not available")
-            return None
-
-        try:
-            replier = AICardReplier(self._dingtalk_client, chatbot_message)
-            card_instance_id = await replier.async_create_and_deliver_card(
-                card_template_id=self._card_template_id,
-                card_data={"content": initial_text},
-            )
-            if not card_instance_id:
-                return None
-
-            self._card_repliers[card_instance_id] = replier
-            logger.info("[DingTalk] AI card created: outTrackId=%s", card_instance_id)
-            return card_instance_id
-        except Exception:
-            logger.exception("[DingTalk] failed to create AI card")
-            return None
-
-    async def _stream_update_card(
-        self,
-        out_track_id: str,
-        content: str,
-        *,
-        is_finalize: bool = False,
-        is_error: bool = False,
-    ) -> None:
-        replier = self._card_repliers.get(out_track_id)
-        if not replier:
-            raise RuntimeError(f"No AICardReplier found for track ID {out_track_id}")
-
-        await replier.async_streaming(
-            card_instance_id=out_track_id,
-            content_key="content",
-            content_value=content,
-            append=False,
-            finished=is_finalize,
-            failed=is_error,
-        )
-
-    # -- media upload --------------------------------------------------------
-
-    async def _upload_media(self, file_path: str | Path, media_type: str) -> str | None:
-        try:
-            file_bytes = await asyncio.to_thread(Path(file_path).read_bytes)
-            token = await self._get_access_token()
-            async with httpx.AsyncClient(timeout=httpx.Timeout(60.0)) as client:
-                response = await client.post(
-                    f"{DINGTALK_API_BASE}/v1.0/files/upload",
-                    headers={"x-acs-dingtalk-access-token": token},
-                    files={"file": ("upload", file_bytes)},
-                    data={"type": media_type},
-                )
-                response.raise_for_status()
-                try:
-                    payload = response.json()
-                except json.JSONDecodeError:
-                    logger.exception("[DingTalk] failed to decode upload response JSON: %s", file_path)
-                    return None
-                if not isinstance(payload, dict):
-                    logger.warning("[DingTalk] unexpected upload response type %s for %s", type(payload).__name__, file_path)
-                    return None
-                return payload.get("mediaId")
-        except (httpx.HTTPError, OSError):
-            logger.exception("[DingTalk] failed to upload media: %s", file_path)
-            return None
-
-    @staticmethod
-    def _log_future_error(fut: Any, name: str, msg_id: str) -> None:
-        try:
-            exc = fut.exception()
-            if exc:
-                logger.error("[DingTalk] %s failed for msg_id=%s: %s", name, msg_id, exc)
-        except (asyncio.CancelledError, asyncio.InvalidStateError):
-            pass
-
-
-class _DingTalkMessageHandler:
-    """Callback handler registered with dingtalk-stream."""
-
-    def __init__(self, channel: DingTalkChannel) -> None:
-        self._channel = channel
-
-    def pre_start(self) -> None:
-        if hasattr(self, "dingtalk_client") and self.dingtalk_client is not None:
-            self._channel._dingtalk_client = self.dingtalk_client
-
-    async def raw_process(self, callback_message: Any) -> Any:
-        import dingtalk_stream
-        from dingtalk_stream.frames import Headers
-
-        code, message = await self.process(callback_message)
-        ack_message = dingtalk_stream.AckMessage()
-        ack_message.code = code
-        ack_message.headers.message_id = callback_message.headers.message_id
-        ack_message.headers.content_type = Headers.CONTENT_TYPE_APPLICATION_JSON
-        ack_message.data = {"response": message}
-        return ack_message
-
-    async def process(self, callback: Any) -> tuple[int, str]:
-        import dingtalk_stream
-
-        incoming_message = dingtalk_stream.ChatbotMessage.from_dict(callback.data)
-        self._channel._on_chatbot_message(incoming_message)
-        return dingtalk_stream.AckMessage.STATUS_OK, "OK"

backend/app/channels/discord.py

@@ -1,273 +0,0 @@
-"""Discord channel integration using discord.py."""
-
-from __future__ import annotations
-
-import asyncio
-import logging
-import threading
-from typing import Any
-
-from app.channels.base import Channel
-from app.channels.message_bus import InboundMessageType, MessageBus, OutboundMessage, ResolvedAttachment
-
-logger = logging.getLogger(__name__)
-
-_DISCORD_MAX_MESSAGE_LEN = 2000
-
-
-class DiscordChannel(Channel):
-    """Discord bot channel.
-
-    Configuration keys (in ``config.yaml`` under ``channels.discord``):
-        - ``bot_token``: Discord Bot token.
-        - ``allowed_guilds``: (optional) List of allowed Discord guild IDs. Empty = allow all.
-    """
-
-    def __init__(self, bus: MessageBus, config: dict[str, Any]) -> None:
-        super().__init__(name="discord", bus=bus, config=config)
-        self._bot_token = str(config.get("bot_token", "")).strip()
-        self._allowed_guilds: set[int] = set()
-        for guild_id in config.get("allowed_guilds", []):
-            try:
-                self._allowed_guilds.add(int(guild_id))
-            except (TypeError, ValueError):
-                continue
-
-        self._client = None
-        self._thread: threading.Thread | None = None
-        self._discord_loop: asyncio.AbstractEventLoop | None = None
-        self._main_loop: asyncio.AbstractEventLoop | None = None
-        self._discord_module = None
-
-    async def start(self) -> None:
-        if self._running:
-            return
-
-        try:
-            import discord
-        except ImportError:
-            logger.error("discord.py is not installed. Install it with: uv add discord.py")
-            return
-
-        if not self._bot_token:
-            logger.error("Discord channel requires bot_token")
-            return
-
-        intents = discord.Intents.default()
-        intents.messages = True
-        intents.guilds = True
-        intents.message_content = True
-
-        client = discord.Client(
-            intents=intents,
-            allowed_mentions=discord.AllowedMentions.none(),
-        )
-        self._client = client
-        self._discord_module = discord
-        self._main_loop = asyncio.get_event_loop()
-
-        @client.event
-        async def on_message(message) -> None:
-            await self._on_message(message)
-
-        self._running = True
-        self.bus.subscribe_outbound(self._on_outbound)
-
-        self._thread = threading.Thread(target=self._run_client, daemon=True)
-        self._thread.start()
-        logger.info("Discord channel started")
-
-    async def stop(self) -> None:
-        self._running = False
-        self.bus.unsubscribe_outbound(self._on_outbound)
-
-        if self._client and self._discord_loop and self._discord_loop.is_running():
-            close_future = asyncio.run_coroutine_threadsafe(self._client.close(), self._discord_loop)
-            try:
-                await asyncio.wait_for(asyncio.wrap_future(close_future), timeout=10)
-            except TimeoutError:
-                logger.warning("[Discord] client close timed out after 10s")
-            except Exception:
-                logger.exception("[Discord] error while closing client")
-
-        if self._thread:
-            self._thread.join(timeout=10)
-            self._thread = None
-
-        self._client = None
-        self._discord_loop = None
-        self._discord_module = None
-        logger.info("Discord channel stopped")
-
-    async def send(self, msg: OutboundMessage) -> None:
-        target = await self._resolve_target(msg)
-        if target is None:
-            logger.error("[Discord] target not found for chat_id=%s thread_ts=%s", msg.chat_id, msg.thread_ts)
-            return
-
-        text = msg.text or ""
-        for chunk in self._split_text(text):
-            send_future = asyncio.run_coroutine_threadsafe(target.send(chunk), self._discord_loop)
-            await asyncio.wrap_future(send_future)
-
-    async def send_file(self, msg: OutboundMessage, attachment: ResolvedAttachment) -> bool:
-        target = await self._resolve_target(msg)
-        if target is None:
-            logger.error("[Discord] target not found for file upload chat_id=%s thread_ts=%s", msg.chat_id, msg.thread_ts)
-            return False
-
-        if self._discord_module is None:
-            return False
-
-        try:
-            fp = open(str(attachment.actual_path), "rb")  # noqa: SIM115
-            file = self._discord_module.File(fp, filename=attachment.filename)
-            send_future = asyncio.run_coroutine_threadsafe(target.send(file=file), self._discord_loop)
-            await asyncio.wrap_future(send_future)
-            logger.info("[Discord] file uploaded: %s", attachment.filename)
-            return True
-        except Exception:
-            logger.exception("[Discord] failed to upload file: %s", attachment.filename)
-            return False
-
-    async def _on_message(self, message) -> None:
-        if not self._running or not self._client:
-            return
-
-        if message.author.bot:
-            return
-
-        if self._client.user and message.author.id == self._client.user.id:
-            return
-
-        guild = message.guild
-        if self._allowed_guilds:
-            if guild is None or guild.id not in self._allowed_guilds:
-                return
-
-        text = (message.content or "").strip()
-        if not text:
-            return
-
-        if self._discord_module is None:
-            return
-
-        if isinstance(message.channel, self._discord_module.Thread):
-            chat_id = str(message.channel.parent_id or message.channel.id)
-            thread_id = str(message.channel.id)
-        else:
-            thread = await self._create_thread(message)
-            if thread is None:
-                return
-            chat_id = str(message.channel.id)
-            thread_id = str(thread.id)
-
-        msg_type = InboundMessageType.COMMAND if text.startswith("/") else InboundMessageType.CHAT
-        inbound = self._make_inbound(
-            chat_id=chat_id,
-            user_id=str(message.author.id),
-            text=text,
-            msg_type=msg_type,
-            thread_ts=thread_id,
-            metadata={
-                "guild_id": str(guild.id) if guild else None,
-                "channel_id": str(message.channel.id),
-                "message_id": str(message.id),
-            },
-        )
-        inbound.topic_id = thread_id
-
-        if self._main_loop and self._main_loop.is_running():
-            future = asyncio.run_coroutine_threadsafe(self.bus.publish_inbound(inbound), self._main_loop)
-            future.add_done_callback(lambda f: logger.exception("[Discord] publish_inbound failed", exc_info=f.exception()) if f.exception() else None)
-
-    def _run_client(self) -> None:
-        self._discord_loop = asyncio.new_event_loop()
-        asyncio.set_event_loop(self._discord_loop)
-        try:
-            self._discord_loop.run_until_complete(self._client.start(self._bot_token))
-        except Exception:
-            if self._running:
-                logger.exception("Discord client error")
-        finally:
-            try:
-                if self._client and not self._client.is_closed():
-                    self._discord_loop.run_until_complete(self._client.close())
-            except Exception:
-                logger.exception("Error during Discord shutdown")
-
-    async def _create_thread(self, message):
-        try:
-            thread_name = f"deerflow-{message.author.display_name}-{message.id}"[:100]
-            return await message.create_thread(name=thread_name)
-        except Exception:
-            logger.exception("[Discord] failed to create thread for message=%s (threads may be disabled or missing permissions)", message.id)
-            try:
-                await message.channel.send("Could not create a thread for your message. Please check that threads are enabled in this channel.")
-            except Exception:
-                pass
-            return None
-
-    async def _resolve_target(self, msg: OutboundMessage):
-        if not self._client or not self._discord_loop:
-            return None
-
-        target_ids: list[str] = []
-        if msg.thread_ts:
-            target_ids.append(msg.thread_ts)
-        if msg.chat_id and msg.chat_id not in target_ids:
-            target_ids.append(msg.chat_id)
-
-        for raw_id in target_ids:
-            target = await self._get_channel_or_thread(raw_id)
-            if target is not None:
-                return target
-        return None
-
-    async def _get_channel_or_thread(self, raw_id: str):
-        if not self._client or not self._discord_loop:
-            return None
-
-        try:
-            target_id = int(raw_id)
-        except (TypeError, ValueError):
-            return None
-
-        get_future = asyncio.run_coroutine_threadsafe(self._fetch_channel(target_id), self._discord_loop)
-        try:
-            return await asyncio.wrap_future(get_future)
-        except Exception:
-            logger.exception("[Discord] failed to resolve target id=%s", raw_id)
-            return None
-
-    async def _fetch_channel(self, target_id: int):
-        if not self._client:
-            return None
-
-        channel = self._client.get_channel(target_id)
-        if channel is not None:
-            return channel
-
-        try:
-            return await self._client.fetch_channel(target_id)
-        except Exception:
-            return None
-
-    @staticmethod
-    def _split_text(text: str) -> list[str]:
-        if not text:
-            return [""]
-
-        chunks: list[str] = []
-        remaining = text
-        while len(remaining) > _DISCORD_MAX_MESSAGE_LEN:
-            split_at = remaining.rfind("\n", 0, _DISCORD_MAX_MESSAGE_LEN)
-            if split_at <= 0:
-                split_at = _DISCORD_MAX_MESSAGE_LEN
-            chunks.append(remaining[:split_at])
-            remaining = remaining[split_at:].lstrip("\n")
-
-        if remaining:
-            chunks.append(remaining)
-
-        return chunks

backend/app/channels/feishu.py

@@ -63,10 +63,6 @@ class FeishuChannel(Channel):
         self._GetMessageResourceRequest = None
         self._thread_lock = threading.Lock()
 
-    @property
-    def supports_streaming(self) -> bool:
-        return True
-
     async def start(self) -> None:
         if self._running:
             return

backend/app/channels/manager.py

@@ -1,4 +1,4 @@
-"""ChannelManager — consumes inbound messages and dispatches them to the DeerFlow agent via Gateway."""
+"""ChannelManager — consumes inbound messages and dispatches them to the DeerFlow agent via LangGraph Server."""
 
 from __future__ import annotations
 
@@ -17,13 +17,11 @@ from langgraph_sdk.errors import ConflictError
 from app.channels.commands import KNOWN_CHANNEL_COMMANDS
 from app.channels.message_bus import InboundMessage, InboundMessageType, MessageBus, OutboundMessage, ResolvedAttachment
 from app.channels.store import ChannelStore
-from app.gateway.csrf_middleware import CSRF_COOKIE_NAME, CSRF_HEADER_NAME, generate_csrf_token
-from app.gateway.internal_auth import create_internal_auth_headers
 from deerflow.runtime.user_context import get_effective_user_id
 
 logger = logging.getLogger(__name__)
 
-DEFAULT_LANGGRAPH_URL = "http://localhost:8001/api"
+DEFAULT_LANGGRAPH_URL = "http://localhost:2024"
 DEFAULT_GATEWAY_URL = "http://localhost:8001"
 DEFAULT_ASSISTANT_ID = "lead_agent"
 CUSTOM_AGENT_NAME_PATTERN = re.compile(r"^[A-Za-z0-9-]+$")
@@ -38,8 +36,6 @@ STREAM_UPDATE_MIN_INTERVAL_SECONDS = 0.35
 THREAD_BUSY_MESSAGE = "This conversation is already processing another request. Please wait for it to finish and try again."
 
 CHANNEL_CAPABILITIES = {
-    "dingtalk": {"supports_streaming": False},
-    "discord": {"supports_streaming": False},
     "feishu": {"supports_streaming": True},
     "slack": {"supports_streaming": False},
     "telegram": {"supports_streaming": False},
@@ -49,13 +45,6 @@ CHANNEL_CAPABILITIES = {
 
 InboundFileReader = Callable[[dict[str, Any], httpx.AsyncClient], Awaitable[bytes | None]]
 
-_METADATA_DROP_KEYS = frozenset({"raw_message", "ref_msg"})
-
-
-def _slim_metadata(meta: dict[str, Any]) -> dict[str, Any]:
-    """Return a shallow copy of *meta* with known-large keys removed."""
-    return {k: v for k, v in meta.items() if k not in _METADATA_DROP_KEYS}
-
 
 INBOUND_FILE_READERS: dict[str, InboundFileReader] = {}
 
@@ -519,7 +508,7 @@ class ChannelManager:
     """Core dispatcher that bridges IM channels to the DeerFlow agent.
 
     It reads from the MessageBus inbound queue, creates/reuses threads on
-    Gateway's LangGraph-compatible API, sends messages via ``runs.wait``, and publishes
+    the LangGraph Server, sends messages via ``runs.wait``, and publishes
     outbound responses back through the bus.
     """
 
@@ -544,20 +533,12 @@ class ChannelManager:
         self._default_session = _as_dict(default_session)
         self._channel_sessions = dict(channel_sessions or {})
         self._client = None  # lazy init — langgraph_sdk async client
-        self._csrf_token = generate_csrf_token()
         self._semaphore: asyncio.Semaphore | None = None
         self._running = False
         self._task: asyncio.Task | None = None
 
     @staticmethod
     def _channel_supports_streaming(channel_name: str) -> bool:
-        from .service import get_channel_service
-
-        service = get_channel_service()
-        if service:
-            channel = service.get_channel(channel_name)
-            if channel is not None:
-                return channel.supports_streaming
         return CHANNEL_CAPABILITIES.get(channel_name, {}).get("supports_streaming", False)
 
     def _resolve_session_layer(self, msg: InboundMessage) -> tuple[dict[str, Any], dict[str, Any]]:
@@ -604,14 +585,7 @@ class ChannelManager:
         if self._client is None:
             from langgraph_sdk import get_client
 
-            self._client = get_client(
-                url=self._langgraph_url,
-                headers={
-                    **create_internal_auth_headers(),
-                    CSRF_HEADER_NAME: self._csrf_token,
-                    "Cookie": f"{CSRF_COOKIE_NAME}={self._csrf_token}",
-                },
-            )
+            self._client = get_client(url=self._langgraph_url)
         return self._client
 
     # -- lifecycle ---------------------------------------------------------
@@ -694,7 +668,7 @@ class ChannelManager:
     # -- chat handling -----------------------------------------------------
 
     async def _create_thread(self, client, msg: InboundMessage) -> str:
-        """Create a new thread through Gateway and store the mapping."""
+        """Create a new thread on the LangGraph Server and store the mapping."""
         thread = await client.threads.create()
         thread_id = thread["thread_id"]
         self.store.set_thread_id(
@@ -704,7 +678,7 @@ class ChannelManager:
             topic_id=msg.topic_id,
             user_id=msg.user_id,
         )
-        logger.info("[Manager] new thread created through Gateway: thread_id=%s for chat_id=%s topic_id=%s", thread_id, msg.chat_id, msg.topic_id)
+        logger.info("[Manager] new thread created on LangGraph Server: thread_id=%s for chat_id=%s topic_id=%s", thread_id, msg.chat_id, msg.topic_id)
         return thread_id
 
     async def _handle_chat(self, msg: InboundMessage, extra_context: dict[str, Any] | None = None) -> None:
@@ -787,7 +761,6 @@ class ChannelManager:
             artifacts=artifacts,
             attachments=attachments,
             thread_ts=msg.thread_ts,
-            metadata=_slim_metadata(msg.metadata),
         )
         logger.info("[Manager] publishing outbound message to bus: channel=%s, chat_id=%s", msg.channel_name, msg.chat_id)
         await self.bus.publish_outbound(outbound)
@@ -849,7 +822,6 @@ class ChannelManager:
                         text=latest_text,
                         is_final=False,
                         thread_ts=msg.thread_ts,
-                        metadata=_slim_metadata(msg.metadata),
                     )
                 )
                 last_published_text = latest_text
@@ -894,7 +866,6 @@ class ChannelManager:
                     attachments=attachments,
                     is_final=True,
                     thread_ts=msg.thread_ts,
-                    metadata=_slim_metadata(msg.metadata),
                 )
             )
 
@@ -914,7 +885,7 @@ class ChannelManager:
             return
 
         if command == "new":
-            # Create a new thread through Gateway
+            # Create a new thread on the LangGraph Server
             client = self._get_client()
             thread = await client.threads.create()
             new_thread_id = thread["thread_id"]
@@ -953,7 +924,6 @@ class ChannelManager:
             thread_id=self.store.get_thread_id(msg.channel_name, msg.chat_id) or "",
             text=reply,
             thread_ts=msg.thread_ts,
-            metadata=_slim_metadata(msg.metadata),
         )
         await self.bus.publish_outbound(outbound)
 
@@ -987,6 +957,5 @@ class ChannelManager:
             thread_id=self.store.get_thread_id(msg.channel_name, msg.chat_id) or "",
             text=error_text,
             thread_ts=msg.thread_ts,
-            metadata=_slim_metadata(msg.metadata),
         )
         await self.bus.publish_outbound(outbound)

backend/app/channels/service.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 
 import logging
 import os
-from typing import TYPE_CHECKING, Any
+from typing import Any
 
 from app.channels.base import Channel
 from app.channels.manager import DEFAULT_GATEWAY_URL, DEFAULT_LANGGRAPH_URL, ChannelManager
@@ -13,13 +13,8 @@ from app.channels.store import ChannelStore
 
 logger = logging.getLogger(__name__)
 
-if TYPE_CHECKING:
-    from deerflow.config.app_config import AppConfig
-
 # Channel name → import path for lazy loading
 _CHANNEL_REGISTRY: dict[str, str] = {
-    "dingtalk": "app.channels.dingtalk:DingTalkChannel",
-    "discord": "app.channels.discord:DiscordChannel",
     "feishu": "app.channels.feishu:FeishuChannel",
     "slack": "app.channels.slack:SlackChannel",
     "telegram": "app.channels.telegram:TelegramChannel",
@@ -27,17 +22,6 @@ _CHANNEL_REGISTRY: dict[str, str] = {
     "wecom": "app.channels.wecom:WeComChannel",
 }
 
-# Keys that indicate a user has configured credentials for a channel.
-_CHANNEL_CREDENTIAL_KEYS: dict[str, list[str]] = {
-    "dingtalk": ["client_id", "client_secret"],
-    "discord": ["bot_token"],
-    "feishu": ["app_id", "app_secret"],
-    "slack": ["bot_token", "app_token"],
-    "telegram": ["bot_token"],
-    "wecom": ["bot_id", "bot_secret"],
-    "wechat": ["bot_token"],
-}
-
 _CHANNELS_LANGGRAPH_URL_ENV = "DEER_FLOW_CHANNELS_LANGGRAPH_URL"
 _CHANNELS_GATEWAY_URL_ENV = "DEER_FLOW_CHANNELS_GATEWAY_URL"
 
@@ -80,15 +64,14 @@ class ChannelService:
         self._running = False
 
     @classmethod
-    def from_app_config(cls, app_config: AppConfig | None = None) -> ChannelService:
+    def from_app_config(cls) -> ChannelService:
         """Create a ChannelService from the application config."""
-        if app_config is None:
-            from deerflow.config.app_config import get_app_config
+        from deerflow.config.app_config import get_app_config
 
-            app_config = get_app_config()
+        config = get_app_config()
         channels_config = {}
         # extra fields are allowed by AppConfig (extra="allow")
-        extra = app_config.model_extra or {}
+        extra = config.model_extra or {}
         if "channels" in extra:
             channels_config = extra["channels"]
         return cls(channels_config=channels_config)
@@ -104,16 +87,7 @@ class ChannelService:
             if not isinstance(channel_config, dict):
                 continue
             if not channel_config.get("enabled", False):
-                cred_keys = _CHANNEL_CREDENTIAL_KEYS.get(name, [])
-                has_creds = any(not isinstance(channel_config.get(k), bool) and channel_config.get(k) is not None and str(channel_config[k]).strip() for k in cred_keys)
-                if has_creds:
-                    logger.warning(
-                        "Channel '%s' has credentials configured but is disabled. Set enabled: true under channels.%s in config.yaml to activate it.",
-                        name,
-                        name,
-                    )
-                else:
-                    logger.info("Channel %s is disabled, skipping", name)
+                logger.info("Channel %s is disabled, skipping", name)
                 continue
 
             await self._start_channel(name, channel_config)
@@ -168,16 +142,11 @@ class ChannelService:
 
         try:
             channel = channel_cls(bus=self.bus, config=config)
-            self._channels[name] = channel
             await channel.start()
-            if not channel.is_running:
-                self._channels.pop(name, None)
-                logger.error("Channel %s did not enter a running state after start()", name)
-                return False
+            self._channels[name] = channel
             logger.info("Channel %s started", name)
             return True
         except Exception:
-            self._channels.pop(name, None)
             logger.exception("Failed to start channel %s", name)
             return False
 
@@ -212,12 +181,12 @@ def get_channel_service() -> ChannelService | None:
     return _channel_service
 
 
-async def start_channel_service(app_config: AppConfig | None = None) -> ChannelService:
+async def start_channel_service() -> ChannelService:
     """Create and start the global ChannelService from app config."""
     global _channel_service
     if _channel_service is not None:
         return _channel_service
-    _channel_service = ChannelService.from_app_config(app_config)
+    _channel_service = ChannelService.from_app_config()
     await _channel_service.start()
     return _channel_service
 

backend/app/channels/slack.py

@@ -16,31 +16,13 @@ logger = logging.getLogger(__name__)
 _slack_md_converter = SlackMarkdownConverter()
 
 
-def _normalize_allowed_users(allowed_users: Any) -> set[str]:
-    if allowed_users is None:
-        return set()
-    if isinstance(allowed_users, str):
-        values = [allowed_users]
-    elif isinstance(allowed_users, list | tuple | set):
-        values = allowed_users
-    else:
-        logger.warning(
-            "Slack allowed_users should be a list of Slack user IDs or a single Slack user ID string; treating %s as one string value",
-            type(allowed_users).__name__,
-        )
-        values = [allowed_users]
-    return {str(user_id) for user_id in values if str(user_id)}
-
-
 class SlackChannel(Channel):
     """Slack IM channel using Socket Mode (WebSocket, no public IP).
 
     Configuration keys (in ``config.yaml`` under ``channels.slack``):
         - ``bot_token``: Slack Bot User OAuth Token (xoxb-...).
         - ``app_token``: Slack App-Level Token (xapp-...) for Socket Mode.
-        - ``allowed_users``: (optional) List of allowed Slack user IDs, or a
-          single Slack user ID string as shorthand. Empty = allow all. Other
-          scalar values are treated as a single string with a warning.
+        - ``allowed_users``: (optional) List of allowed Slack user IDs. Empty = allow all.
     """
 
     def __init__(self, bus: MessageBus, config: dict[str, Any]) -> None:
@@ -48,7 +30,7 @@ class SlackChannel(Channel):
         self._socket_client = None
         self._web_client = None
         self._loop: asyncio.AbstractEventLoop | None = None
-        self._allowed_users = _normalize_allowed_users(config.get("allowed_users", []))
+        self._allowed_users: set[str] = {str(user_id) for user_id in config.get("allowed_users", [])}
 
     async def start(self) -> None:
         if self._running:

backend/app/channels/wecom.py

@@ -29,10 +29,6 @@ class WeComChannel(Channel):
         self._ws_stream_ids: dict[str, str] = {}
         self._working_message = "Working on it..."
 
-    @property
-    def supports_streaming(self) -> bool:
-        return True
-
     def _clear_ws_context(self, thread_ts: str | None) -> None:
         if not thread_ts:
             return

backend/app/gateway/app.py

@@ -1,4 +1,3 @@
-import asyncio
 import logging
 import os
 from collections.abc import AsyncGenerator
@@ -28,13 +27,9 @@ from app.gateway.routers import (
     threads,
     uploads,
 )
-from deerflow.config import app_config as deerflow_app_config
-from deerflow.config.app_config import apply_logging_level
+from deerflow.config.app_config import get_app_config
 
-AppConfig = deerflow_app_config.AppConfig
-get_app_config = deerflow_app_config.get_app_config
-
-# Default logging; lifespan overrides from config.yaml log_level.
+# Configure logging
 logging.basicConfig(
     level=logging.INFO,
     format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
@@ -43,23 +38,20 @@ logging.basicConfig(
 
 logger = logging.getLogger(__name__)
 
-# Upper bound (seconds) each lifespan shutdown hook is allowed to run.
-# Bounds worker exit time so uvicorn's reload supervisor does not keep
-# firing signals into a worker that is stuck waiting for shutdown cleanup.
-_SHUTDOWN_HOOK_TIMEOUT_SECONDS = 5.0
-
 
 async def _ensure_admin_user(app: FastAPI) -> None:
-    """Startup hook: handle first boot and migrate orphan threads otherwise.
+    """Startup hook: generate init token on first boot; migrate orphan threads otherwise.
 
     After admin creation, migrate orphan threads from the LangGraph
     store (metadata.user_id unset) to the admin account. This is the
     "no-auth → with-auth" upgrade path: users who ran DeerFlow without
     authentication have existing LangGraph thread data that needs an
     owner assigned.
-        First boot (no admin exists):
-            - Does NOT create any user accounts automatically.
-            - The operator must visit ``/setup`` to create the first admin.
+    First boot (no admin exists):
+      - Generates a one-time ``init_token`` stored in ``app.state.init_token``
+      - Logs the token to stdout so the operator can copy-paste it into the
+        ``/setup`` form to create the first admin account interactively.
+      - Does NOT create any user accounts automatically.
 
     Subsequent boots (admin already exists):
       - Runs the one-time "no-auth → with-auth" orphan thread migration for
@@ -70,35 +62,35 @@ async def _ensure_admin_user(app: FastAPI) -> None:
     alongside the auth module via create_all, so freshly created tables
     never contain NULL-owner rows.
     """
+    import secrets
+
     from sqlalchemy import select
 
     from app.gateway.deps import get_local_provider
     from deerflow.persistence.engine import get_session_factory
     from deerflow.persistence.user.model import UserRow
 
-    try:
-        provider = get_local_provider()
-    except RuntimeError:
-        # Auth persistence may not be initialized in some test/boot paths.
-        # Skip admin migration work rather than failing gateway startup.
-        logger.warning("Auth persistence not ready; skipping admin bootstrap check")
-        return
-
-    sf = get_session_factory()
-    if sf is None:
-        return
-
+    provider = get_local_provider()
     admin_count = await provider.count_admin_users()
 
     if admin_count == 0:
+        init_token = secrets.token_urlsafe(32)
+        app.state.init_token = init_token
         logger.info("=" * 60)
         logger.info("  First boot detected — no admin account exists.")
+        logger.info("  Use the one-time token below to create the admin account.")
+        logger.info("  Copy it into the /setup form when prompted.")
+        logger.info("  INIT TOKEN: %s", init_token)
         logger.info("  Visit /setup to complete admin account creation.")
         logger.info("=" * 60)
         return
 
     # Admin already exists — run orphan thread migration for any
     # LangGraph thread metadata that pre-dates the auth module.
+    sf = get_session_factory()
+    if sf is None:
+        return
+
     async with sf() as session:
         stmt = select(UserRow).where(UserRow.system_role == "admin").limit(1)
         row = (await session.execute(stmt)).scalar_one_or_none()
@@ -164,8 +156,7 @@ async def lifespan(app: FastAPI) -> AsyncGenerator[None, None]:
 
     # Load config and check necessary environment variables at startup
     try:
-        app.state.config = get_app_config()
-        apply_logging_level(app.state.config.log_level)
+        get_app_config()
         logger.info("Configuration loaded successfully")
     except Exception as e:
         error_msg = f"Failed to load configuration during gateway startup: {e}"
@@ -186,26 +177,18 @@ async def lifespan(app: FastAPI) -> AsyncGenerator[None, None]:
         try:
             from app.channels.service import start_channel_service
 
-            channel_service = await start_channel_service(app.state.config)
+            channel_service = await start_channel_service()
             logger.info("Channel service started: %s", channel_service.get_status())
         except Exception:
             logger.exception("No IM channels configured or channel service failed to start")
 
         yield
 
-        # Stop channel service on shutdown (bounded to prevent worker hang)
+        # Stop channel service on shutdown
         try:
             from app.channels.service import stop_channel_service
 
-            await asyncio.wait_for(
-                stop_channel_service(),
-                timeout=_SHUTDOWN_HOOK_TIMEOUT_SECONDS,
-            )
-        except TimeoutError:
-            logger.warning(
-                "Channel service shutdown exceeded %.1fs; proceeding with worker exit.",
-                _SHUTDOWN_HOOK_TIMEOUT_SECONDS,
-            )
+            await stop_channel_service()
         except Exception:
             logger.exception("Failed to stop channel service")
 
@@ -218,8 +201,6 @@ def create_app() -> FastAPI:
     Returns:
         Configured FastAPI application instance.
     """
-    config = get_gateway_config()
-    docs_kwargs = {"docs_url": "/docs", "redoc_url": "/redoc", "openapi_url": "/openapi.json"} if config.enable_docs else {"docs_url": None, "redoc_url": None, "openapi_url": None}
 
     app = FastAPI(
         title="DeerFlow API Gateway",
@@ -244,7 +225,9 @@ This gateway provides custom endpoints for models, MCP configuration, skills, an
         """,
         version="0.1.0",
         lifespan=lifespan,
-        **docs_kwargs,
+        docs_url="/docs",
+        redoc_url="/redoc",
+        openapi_url="/openapi.json",
         openapi_tags=[
             {
                 "name": "models",
@@ -382,6 +365,11 @@ This gateway provides custom endpoints for models, MCP configuration, skills, an
         """
         return {"status": "healthy", "service": "deer-flow-gateway"}
 
+    # Ensure init_token always exists on app.state (None until lifespan sets it
+    # if no admin is found).  This prevents AttributeError in tests that don't
+    # run the full lifespan.
+    app.state.init_token = None
+
     return app
 
 

backend/app/gateway/auth/config.py

@@ -4,8 +4,11 @@ import logging
 import os
 import secrets
 
+from dotenv import load_dotenv
 from pydantic import BaseModel, Field
 
+load_dotenv()
+
 logger = logging.getLogger(__name__)
 
 
@@ -34,9 +37,6 @@ def get_auth_config() -> AuthConfig:
     """Get the global AuthConfig instance. Parses from env on first call."""
     global _auth_config
     if _auth_config is None:
-        from dotenv import load_dotenv
-
-        load_dotenv()
         jwt_secret = os.environ.get("AUTH_JWT_SECRET")
         if not jwt_secret:
             jwt_secret = secrets.token_urlsafe(32)

backend/app/gateway/auth/errors.py

@@ -21,6 +21,7 @@ class AuthErrorCode(StrEnum):
     PROVIDER_NOT_FOUND = "provider_not_found"
     NOT_AUTHENTICATED = "not_authenticated"
     SYSTEM_ALREADY_INITIALIZED = "system_already_initialized"
+    INVALID_INIT_TOKEN = "invalid_init_token"
 
 
 class TokenError(StrEnum):

backend/app/gateway/auth/local_provider.py

@@ -1,14 +1,10 @@
 """Local email/password authentication provider."""
 
-import logging
-
 from app.gateway.auth.models import User
-from app.gateway.auth.password import hash_password_async, needs_rehash, verify_password_async
+from app.gateway.auth.password import hash_password_async, verify_password_async
 from app.gateway.auth.providers import AuthProvider
 from app.gateway.auth.repositories.base import UserRepository
 
-logger = logging.getLogger(__name__)
-
 
 class LocalAuthProvider(AuthProvider):
     """Email/password authentication provider using local database."""
@@ -47,15 +43,6 @@ class LocalAuthProvider(AuthProvider):
         if not await verify_password_async(password, user.password_hash):
             return None
 
-        if needs_rehash(user.password_hash):
-            try:
-                user.password_hash = await hash_password_async(password)
-                await self._repo.update_user(user)
-            except Exception:
-                # Rehash is an opportunistic upgrade; a transient DB error must not
-                # prevent an otherwise-valid login from succeeding.
-                logger.warning("Failed to rehash password for user %s; login will still succeed", user.email, exc_info=True)
-
         return user
 
     async def get_user(self, user_id: str) -> User | None:

backend/app/gateway/auth/password.py

@@ -1,66 +1,18 @@
-"""Password hashing utilities with versioned hash format.
-
-Hash format: ``$dfv<N>$<bcrypt_hash>`` where ``<N>`` is the version.
-
-- **v1** (legacy): ``bcrypt(password)`` — plain bcrypt, susceptible to
-  72-byte silent truncation.
-- **v2** (current): ``bcrypt(b64(sha256(password)))`` — SHA-256 pre-hash
-  avoids the 72-byte truncation limit so the full password contributes
-  to the hash.
-
-Verification auto-detects the version and falls back to v1 for hashes
-without a prefix, so existing deployments upgrade transparently on next
-login.
-"""
+"""Password hashing utilities using bcrypt directly."""
 
 import asyncio
-import base64
-import hashlib
 
 import bcrypt
 
-_CURRENT_VERSION = 2
-_PREFIX_V2 = "$dfv2$"
-_PREFIX_V1 = "$dfv1$"
-
-
-def _pre_hash_v2(password: str) -> bytes:
-    """SHA-256 pre-hash to bypass bcrypt's 72-byte limit."""
-    return base64.b64encode(hashlib.sha256(password.encode("utf-8")).digest())
-
 
 def hash_password(password: str) -> str:
-    """Hash a password (current version: v2 — SHA-256 + bcrypt)."""
-    raw = bcrypt.hashpw(_pre_hash_v2(password), bcrypt.gensalt()).decode("utf-8")
-    return f"{_PREFIX_V2}{raw}"
+    """Hash a password using bcrypt."""
+    return bcrypt.hashpw(password.encode("utf-8"), bcrypt.gensalt()).decode("utf-8")
 
 
 def verify_password(plain_password: str, hashed_password: str) -> bool:
-    """Verify a password, auto-detecting the hash version.
-
-    Accepts v2 (``$dfv2$…``), v1 (``$dfv1$…``), and bare bcrypt hashes
-    (treated as v1 for backward compatibility with pre-versioning data).
-    """
-    try:
-        if hashed_password.startswith(_PREFIX_V2):
-            bcrypt_hash = hashed_password[len(_PREFIX_V2) :]
-            return bcrypt.checkpw(_pre_hash_v2(plain_password), bcrypt_hash.encode("utf-8"))
-
-        if hashed_password.startswith(_PREFIX_V1):
-            bcrypt_hash = hashed_password[len(_PREFIX_V1) :]
-        else:
-            bcrypt_hash = hashed_password
-
-        return bcrypt.checkpw(plain_password.encode("utf-8"), bcrypt_hash.encode("utf-8"))
-    except ValueError:
-        # bcrypt raises ValueError for malformed or corrupt hashes (e.g., invalid salt).
-        # Fail closed rather than crashing the request.
-        return False
-
-
-def needs_rehash(hashed_password: str) -> bool:
-    """Return True if the hash uses an older version and should be rehashed."""
-    return not hashed_password.startswith(_PREFIX_V2)
+    """Verify a password against its hash."""
+    return bcrypt.checkpw(plain_password.encode("utf-8"), hashed_password.encode("utf-8"))
 
 
 async def hash_password_async(password: str) -> str:

backend/app/gateway/auth/providers.py

@@ -12,12 +12,12 @@ class AuthProvider(ABC):
 
         Returns User if authentication succeeds, None otherwise.
         """
-        raise NotImplementedError
+        ...
 
     @abstractmethod
     async def get_user(self, user_id: str) -> "User | None":
         """Retrieve user by ID."""
-        raise NotImplementedError
+        ...
 
 
 # Import User at runtime to avoid circular imports

backend/app/gateway/auth/repositories/base.py

@@ -35,7 +35,7 @@ class UserRepository(ABC):
         Raises:
             ValueError: If email already exists
         """
-        raise NotImplementedError
+        ...
 
     @abstractmethod
     async def get_user_by_id(self, user_id: str) -> User | None:
@@ -47,7 +47,7 @@ class UserRepository(ABC):
         Returns:
             User if found, None otherwise
         """
-        raise NotImplementedError
+        ...
 
     @abstractmethod
     async def get_user_by_email(self, email: str) -> User | None:
@@ -59,7 +59,7 @@ class UserRepository(ABC):
         Returns:
             User if found, None otherwise
         """
-        raise NotImplementedError
+        ...
 
     @abstractmethod
     async def update_user(self, user: User) -> User:
@@ -76,17 +76,17 @@ class UserRepository(ABC):
                 a hard failure (not a no-op) so callers cannot mistake a
                 concurrent-delete race for a successful update.
         """
-        raise NotImplementedError
+        ...
 
     @abstractmethod
     async def count_users(self) -> int:
         """Return total number of registered users."""
-        raise NotImplementedError
+        ...
 
     @abstractmethod
     async def count_admin_users(self) -> int:
         """Return number of users with system_role == 'admin'."""
-        raise NotImplementedError
+        ...
 
     @abstractmethod
     async def get_user_by_oauth(self, provider: str, oauth_id: str) -> User | None:
@@ -99,4 +99,4 @@ class UserRepository(ABC):
         Returns:
             User if found, None otherwise
         """
-        raise NotImplementedError
+        ...

backend/app/gateway/auth_middleware.py

@@ -18,7 +18,6 @@ from starlette.types import ASGIApp
 
 from app.gateway.auth.errors import AuthErrorCode, AuthErrorResponse
 from app.gateway.authz import _ALL_PERMISSIONS, AuthContext
-from app.gateway.internal_auth import INTERNAL_AUTH_HEADER_NAME, get_internal_user, is_valid_internal_auth_token
 from deerflow.runtime.user_context import reset_current_user, set_current_user
 
 # Paths that never require authentication.
@@ -76,12 +75,8 @@ class AuthMiddleware(BaseHTTPMiddleware):
         if _is_public(request.url.path):
             return await call_next(request)
 
-        internal_user = None
-        if is_valid_internal_auth_token(request.headers.get(INTERNAL_AUTH_HEADER_NAME)):
-            internal_user = get_internal_user()
-
         # Non-public path: require session cookie
-        if internal_user is None and not request.cookies.get("access_token"):
+        if not request.cookies.get("access_token"):
             return JSONResponse(
                 status_code=401,
                 content={
@@ -105,13 +100,10 @@ class AuthMiddleware(BaseHTTPMiddleware):
         # bubble up, so we catch and render it as JSONResponse here.
         from app.gateway.deps import get_current_user_from_request
 
-        if internal_user is not None:
-            user = internal_user
-        else:
-            try:
-                user = await get_current_user_from_request(request)
-            except HTTPException as exc:
-                return JSONResponse(status_code=exc.status_code, content={"detail": exc.detail})
+        try:
+            user = await get_current_user_from_request(request)
+        except HTTPException as exc:
+            return JSONResponse(status_code=exc.status_code, content={"detail": exc.detail})
 
         # Stamp both request.state.user (for the contextvar pattern)
         # and request.state.auth (so @require_permission's "auth is

backend/app/gateway/authz.py

@@ -30,9 +30,7 @@ Inspired by LangGraph Auth system: https://github.com/langchain-ai/langgraph/blo
 from __future__ import annotations
 
 import functools
-import inspect
 from collections.abc import Callable
-from types import SimpleNamespace
 from typing import TYPE_CHECKING, Any, ParamSpec, TypeVar
 
 from fastapi import HTTPException, Request
@@ -119,15 +117,6 @@ _ALL_PERMISSIONS: list[str] = [
 ]
 
 
-def _make_test_request_stub() -> Any:
-    """Create a minimal request-like object for direct unit calls.
-
-    Used when decorated route handlers are invoked without FastAPI's
-    request injection. Includes fields accessed by auth helpers.
-    """
-    return SimpleNamespace(state=SimpleNamespace(), cookies={}, _deerflow_test_bypass_auth=True)
-
-
 async def _authenticate(request: Request) -> AuthContext:
     """Authenticate request and return AuthContext.
 
@@ -145,11 +134,7 @@ async def _authenticate(request: Request) -> AuthContext:
 
 
 def require_auth[**P, T](func: Callable[P, T]) -> Callable[P, T]:
-    """Decorator that authenticates the request and enforces authentication.
-
-    Independently raises HTTP 401 for unauthenticated requests, regardless of
-    whether ``AuthMiddleware`` is present in the ASGI stack. Sets the resolved
-    ``AuthContext`` on ``request.state.auth`` for downstream handlers.
+    """Decorator that authenticates the request and sets AuthContext.
 
     Must be placed ABOVE other decorators (executes after them).
 
@@ -162,33 +147,19 @@ def require_auth[**P, T](func: Callable[P, T]) -> Callable[P, T]:
             ...
 
     Raises:
-        HTTPException: 401 if the request is unauthenticated.
-        ValueError: If 'request' parameter is missing.
+        ValueError: If 'request' parameter is missing
     """
 
     @functools.wraps(func)
     async def wrapper(*args: Any, **kwargs: Any) -> Any:
         request = kwargs.get("request")
         if request is None:
-            # Unit tests may call decorated handlers directly without a
-            # FastAPI Request object. Inject a minimal request stub when
-            # the wrapped function declares `request`.
-            if "request" in inspect.signature(func).parameters:
-                kwargs["request"] = _make_test_request_stub()
-            else:
-                raise ValueError("require_auth decorator requires 'request' parameter")
-            request = kwargs["request"]
-
-        if getattr(request, "_deerflow_test_bypass_auth", False):
-            return await func(*args, **kwargs)
+            raise ValueError("require_auth decorator requires 'request' parameter")
 
         # Authenticate and set context
         auth_context = await _authenticate(request)
         request.state.auth = auth_context
 
-        if not auth_context.is_authenticated:
-            raise HTTPException(status_code=401, detail="Authentication required")
-
         return await func(*args, **kwargs)
 
     return wrapper
@@ -239,17 +210,7 @@ def require_permission(
         async def wrapper(*args: Any, **kwargs: Any) -> Any:
             request = kwargs.get("request")
             if request is None:
-                # Unit tests may call decorated route handlers directly without
-                # constructing a FastAPI Request object. Inject a minimal stub
-                # when the wrapped function declares `request`.
-                if "request" in inspect.signature(func).parameters:
-                    kwargs["request"] = _make_test_request_stub()
-                else:
-                    return await func(*args, **kwargs)
-                request = kwargs["request"]
-
-            if getattr(request, "_deerflow_test_bypass_auth", False):
-                return await func(*args, **kwargs)
+                raise ValueError("require_permission decorator requires 'request' parameter")
 
             auth: AuthContext = getattr(request.state, "auth", None)
             if auth is None:

backend/app/gateway/config.py

@@ -9,7 +9,6 @@ class GatewayConfig(BaseModel):
     host: str = Field(default="0.0.0.0", description="Host to bind the gateway server")
     port: int = Field(default=8001, description="Port to bind the gateway server")
     cors_origins: list[str] = Field(default_factory=lambda: ["http://localhost:3000"], description="Allowed CORS origins")
-    enable_docs: bool = Field(default=True, description="Enable Swagger/ReDoc/OpenAPI endpoints")
 
 
 _gateway_config: GatewayConfig | None = None
@@ -24,6 +23,5 @@ def get_gateway_config() -> GatewayConfig:
             host=os.getenv("GATEWAY_HOST", "0.0.0.0"),
             port=int(os.getenv("GATEWAY_PORT", "8001")),
             cors_origins=cors_origins_str.split(","),
-            enable_docs=os.getenv("GATEWAY_ENABLE_DOCS", "true").lower() == "true",
         )
     return _gateway_config

backend/app/gateway/deps.py

@@ -8,18 +8,13 @@ Initialization is handled directly in ``app.py`` via :class:`AsyncExitStack`.
 
 from __future__ import annotations
 
-from collections.abc import AsyncGenerator, Callable
+from collections.abc import AsyncGenerator
 from contextlib import AsyncExitStack, asynccontextmanager
-from typing import TYPE_CHECKING, TypeVar, cast
+from typing import TYPE_CHECKING
 
 from fastapi import FastAPI, HTTPException, Request
-from langgraph.types import Checkpointer
 
-from deerflow.config.app_config import AppConfig
-from deerflow.persistence.feedback import FeedbackRepository
-from deerflow.runtime import RunContext, RunManager, StreamBridge
-from deerflow.runtime.events.store.base import RunEventStore
-from deerflow.runtime.runs.store.base import RunStore
+from deerflow.runtime import RunContext, RunManager
 
 if TYPE_CHECKING:
     from app.gateway.auth.local_provider import LocalAuthProvider
@@ -27,17 +22,6 @@ if TYPE_CHECKING:
     from deerflow.persistence.thread_meta.base import ThreadMetaStore
 
 
-T = TypeVar("T")
-
-
-def get_config(request: Request) -> AppConfig:
-    """Return the app-scoped ``AppConfig`` stored on ``app.state``."""
-    config = getattr(request.app.state, "config", None)
-    if config is None:
-        raise HTTPException(status_code=503, detail="Configuration not available")
-    return config
-
-
 @asynccontextmanager
 async def langgraph_runtime(app: FastAPI) -> AsyncGenerator[None, None]:
     """Bootstrap and tear down all LangGraph runtime singletons.
@@ -47,24 +31,22 @@ async def langgraph_runtime(app: FastAPI) -> AsyncGenerator[None, None]:
         async with langgraph_runtime(app):
             yield
     """
+    from deerflow.config import get_app_config
     from deerflow.persistence.engine import close_engine, get_session_factory, init_engine_from_config
     from deerflow.runtime import make_store, make_stream_bridge
     from deerflow.runtime.checkpointer.async_provider import make_checkpointer
     from deerflow.runtime.events.store import make_run_event_store
 
     async with AsyncExitStack() as stack:
-        config = getattr(app.state, "config", None)
-        if config is None:
-            raise RuntimeError("langgraph_runtime() requires app.state.config to be initialized")
-
-        app.state.stream_bridge = await stack.enter_async_context(make_stream_bridge(config))
+        app.state.stream_bridge = await stack.enter_async_context(make_stream_bridge())
 
         # Initialize persistence engine BEFORE checkpointer so that
         # auto-create-database logic runs first (postgres backend).
+        config = get_app_config()
         await init_engine_from_config(config.database)
 
-        app.state.checkpointer = await stack.enter_async_context(make_checkpointer(config))
-        app.state.store = await stack.enter_async_context(make_store(config))
+        app.state.checkpointer = await stack.enter_async_context(make_checkpointer())
+        app.state.store = await stack.enter_async_context(make_store())
 
         # Initialize repositories — one get_session_factory() call for all.
         sf = get_session_factory()
@@ -102,25 +84,25 @@ async def langgraph_runtime(app: FastAPI) -> AsyncGenerator[None, None]:
 # ---------------------------------------------------------------------------
 
 
-def _require(attr: str, label: str) -> Callable[[Request], T]:
+def _require(attr: str, label: str):
     """Create a FastAPI dependency that returns ``app.state.<attr>`` or 503."""
 
-    def dep(request: Request) -> T:
+    def dep(request: Request):
         val = getattr(request.app.state, attr, None)
         if val is None:
             raise HTTPException(status_code=503, detail=f"{label} not available")
-        return cast(T, val)
+        return val
 
     dep.__name__ = dep.__qualname__ = f"get_{attr}"
     return dep
 
 
-get_stream_bridge: Callable[[Request], StreamBridge] = _require("stream_bridge", "Stream bridge")
-get_run_manager: Callable[[Request], RunManager] = _require("run_manager", "Run manager")
-get_checkpointer: Callable[[Request], Checkpointer] = _require("checkpointer", "Checkpointer")
-get_run_event_store: Callable[[Request], RunEventStore] = _require("run_event_store", "Run event store")
-get_feedback_repo: Callable[[Request], FeedbackRepository] = _require("feedback_repo", "Feedback")
-get_run_store: Callable[[Request], RunStore] = _require("run_store", "Run store")
+get_stream_bridge = _require("stream_bridge", "Stream bridge")
+get_run_manager = _require("run_manager", "Run manager")
+get_checkpointer = _require("checkpointer", "Checkpointer")
+get_run_event_store = _require("run_event_store", "Run event store")
+get_feedback_repo = _require("feedback_repo", "Feedback")
+get_run_store = _require("run_store", "Run store")
 
 
 def get_store(request: Request):
@@ -139,19 +121,23 @@ def get_thread_store(request: Request) -> ThreadMetaStore:
 def get_run_context(request: Request) -> RunContext:
     """Build a :class:`RunContext` from ``app.state`` singletons.
 
-    Returns a *base* context with infrastructure dependencies.
+    Returns a *base* context with infrastructure dependencies.  Callers that
+    need per-run fields (e.g. ``follow_up_to_run_id``) should use
+    ``dataclasses.replace(ctx, follow_up_to_run_id=...)`` before passing it
+    to :func:`run_agent`.
     """
-    config = get_config(request)
+    from deerflow.config import get_app_config
+
     return RunContext(
         checkpointer=get_checkpointer(request),
         store=get_store(request),
         event_store=get_run_event_store(request),
-        run_events_config=getattr(config, "run_events", None),
+        run_events_config=getattr(get_app_config(), "run_events", None),
         thread_store=get_thread_store(request),
-        app_config=config,
     )
 
 
+
 # ---------------------------------------------------------------------------
 # Auth helpers (used by authz.py and auth middleware)
 # ---------------------------------------------------------------------------

backend/app/gateway/internal_auth.py

@@ -1,26 +0,0 @@
-"""Process-local authentication for Gateway internal callers."""
-
-from __future__ import annotations
-
-import secrets
-from types import SimpleNamespace
-
-from deerflow.runtime.user_context import DEFAULT_USER_ID
-
-INTERNAL_AUTH_HEADER_NAME = "X-DeerFlow-Internal-Token"
-_INTERNAL_AUTH_TOKEN = secrets.token_urlsafe(32)
-
-
-def create_internal_auth_headers() -> dict[str, str]:
-    """Return headers that authenticate same-process Gateway internal calls."""
-    return {INTERNAL_AUTH_HEADER_NAME: _INTERNAL_AUTH_TOKEN}
-
-
-def is_valid_internal_auth_token(token: str | None) -> bool:
-    """Return True when *token* matches the process-local internal token."""
-    return bool(token) and secrets.compare_digest(token, _INTERNAL_AUTH_TOKEN)
-
-
-def get_internal_user():
-    """Return the synthetic user used for trusted internal channel calls."""
-    return SimpleNamespace(id=DEFAULT_USER_ID, system_role="internal")

backend/app/gateway/langgraph_auth.py

@@ -73,7 +73,7 @@ async def authenticate(request):
     if isinstance(payload, TokenError):
         raise Auth.exceptions.HTTPException(
             status_code=401,
-            detail="Invalid token",
+            detail=f"Token error: {payload.value}",
         )
 
     user = await get_local_provider().get_user(payload.sub)

backend/app/gateway/routers/agents.py

@@ -8,7 +8,6 @@ import yaml
 from fastapi import APIRouter, HTTPException
 from pydantic import BaseModel, Field
 
-from deerflow.config.agents_api_config import get_agents_api_config
 from deerflow.config.agents_config import AgentConfig, list_custom_agents, load_agent_config, load_agent_soul
 from deerflow.config.paths import get_paths
 
@@ -25,7 +24,6 @@ class AgentResponse(BaseModel):
     description: str = Field(default="", description="Agent description")
     model: str | None = Field(default=None, description="Optional model override")
     tool_groups: list[str] | None = Field(default=None, description="Optional tool group whitelist")
-    skills: list[str] | None = Field(default=None, description="Optional skill whitelist (None=all, []=none)")
     soul: str | None = Field(default=None, description="SOUL.md content")
 
 
@@ -42,7 +40,6 @@ class AgentCreateRequest(BaseModel):
     description: str = Field(default="", description="Agent description")
     model: str | None = Field(default=None, description="Optional model override")
     tool_groups: list[str] | None = Field(default=None, description="Optional tool group whitelist")
-    skills: list[str] | None = Field(default=None, description="Optional skill whitelist (None=all enabled, []=none)")
     soul: str = Field(default="", description="SOUL.md content — agent personality and behavioral guardrails")
 
 
@@ -52,7 +49,6 @@ class AgentUpdateRequest(BaseModel):
     description: str | None = Field(default=None, description="Updated description")
     model: str | None = Field(default=None, description="Updated model override")
     tool_groups: list[str] | None = Field(default=None, description="Updated tool group whitelist")
-    skills: list[str] | None = Field(default=None, description="Updated skill whitelist (None=all, []=none)")
     soul: str | None = Field(default=None, description="Updated SOUL.md content")
 
 
@@ -77,15 +73,6 @@ def _normalize_agent_name(name: str) -> str:
     return name.lower()
 
 
-def _require_agents_api_enabled() -> None:
-    """Reject access unless the custom-agent management API is explicitly enabled."""
-    if not get_agents_api_config().enabled:
-        raise HTTPException(
-            status_code=403,
-            detail=("Custom-agent management API is disabled. Set agents_api.enabled=true to expose agent and user-profile routes over HTTP."),
-        )
-
-
 def _agent_config_to_response(agent_cfg: AgentConfig, include_soul: bool = False) -> AgentResponse:
     """Convert AgentConfig to AgentResponse."""
     soul: str | None = None
@@ -97,7 +84,6 @@ def _agent_config_to_response(agent_cfg: AgentConfig, include_soul: bool = False
         description=agent_cfg.description,
         model=agent_cfg.model,
         tool_groups=agent_cfg.tool_groups,
-        skills=agent_cfg.skills,
         soul=soul,
     )
 
@@ -114,8 +100,6 @@ async def list_agents() -> AgentsListResponse:
     Returns:
         List of all custom agents with their metadata and soul content.
     """
-    _require_agents_api_enabled()
-
     try:
         agents = list_custom_agents()
         return AgentsListResponse(agents=[_agent_config_to_response(a, include_soul=True) for a in agents])
@@ -141,7 +125,6 @@ async def check_agent_name(name: str) -> dict:
     Raises:
         HTTPException: 422 if the name is invalid.
     """
-    _require_agents_api_enabled()
     _validate_agent_name(name)
     normalized = _normalize_agent_name(name)
     available = not get_paths().agent_dir(normalized).exists()
@@ -166,7 +149,6 @@ async def get_agent(name: str) -> AgentResponse:
     Raises:
         HTTPException: 404 if agent not found.
     """
-    _require_agents_api_enabled()
     _validate_agent_name(name)
     name = _normalize_agent_name(name)
 
@@ -199,7 +181,6 @@ async def create_agent_endpoint(request: AgentCreateRequest) -> AgentResponse:
     Raises:
         HTTPException: 409 if agent already exists, 422 if name is invalid.
     """
-    _require_agents_api_enabled()
     _validate_agent_name(request.name)
     normalized_name = _normalize_agent_name(request.name)
 
@@ -219,8 +200,6 @@ async def create_agent_endpoint(request: AgentCreateRequest) -> AgentResponse:
             config_data["model"] = request.model
         if request.tool_groups is not None:
             config_data["tool_groups"] = request.tool_groups
-        if request.skills is not None:
-            config_data["skills"] = request.skills
 
         config_file = agent_dir / "config.yaml"
         with open(config_file, "w", encoding="utf-8") as f:
@@ -264,7 +243,6 @@ async def update_agent(name: str, request: AgentUpdateRequest) -> AgentResponse:
     Raises:
         HTTPException: 404 if agent not found.
     """
-    _require_agents_api_enabled()
     _validate_agent_name(name)
     name = _normalize_agent_name(name)
 
@@ -277,32 +255,21 @@ async def update_agent(name: str, request: AgentUpdateRequest) -> AgentResponse:
 
     try:
         # Update config if any config fields changed
-        # Use model_fields_set to distinguish "field omitted" from "explicitly set to null".
-        # This is critical for skills where None means "inherit all" (not "don't change").
-        fields_set = request.model_fields_set
-        config_changed = bool(fields_set & {"description", "model", "tool_groups", "skills"})
+        config_changed = any(v is not None for v in [request.description, request.model, request.tool_groups])
 
         if config_changed:
             updated: dict = {
                 "name": agent_cfg.name,
-                "description": request.description if "description" in fields_set else agent_cfg.description,
+                "description": request.description if request.description is not None else agent_cfg.description,
             }
-            new_model = request.model if "model" in fields_set else agent_cfg.model
+            new_model = request.model if request.model is not None else agent_cfg.model
             if new_model is not None:
                 updated["model"] = new_model
 
-            new_tool_groups = request.tool_groups if "tool_groups" in fields_set else agent_cfg.tool_groups
+            new_tool_groups = request.tool_groups if request.tool_groups is not None else agent_cfg.tool_groups
             if new_tool_groups is not None:
                 updated["tool_groups"] = new_tool_groups
 
-            # skills: None = inherit all, [] = no skills, ["a","b"] = whitelist
-            if "skills" in fields_set:
-                new_skills = request.skills
-            else:
-                new_skills = agent_cfg.skills
-            if new_skills is not None:
-                updated["skills"] = new_skills
-
             config_file = agent_dir / "config.yaml"
             with open(config_file, "w", encoding="utf-8") as f:
                 yaml.dump(updated, f, default_flow_style=False, allow_unicode=True)
@@ -348,8 +315,6 @@ async def get_user_profile() -> UserProfileResponse:
     Returns:
         UserProfileResponse with content=None if USER.md does not exist yet.
     """
-    _require_agents_api_enabled()
-
     try:
         user_md_path = get_paths().user_md_file
         if not user_md_path.exists():
@@ -376,8 +341,6 @@ async def update_user_profile(request: UserProfileUpdateRequest) -> UserProfileR
     Returns:
         UserProfileResponse with the saved content.
     """
-    _require_agents_api_enabled()
-
     try:
         paths = get_paths()
         paths.base_dir.mkdir(parents=True, exist_ok=True)
@@ -404,7 +367,6 @@ async def delete_agent(name: str) -> None:
     Raises:
         HTTPException: 404 if agent not found.
     """
-    _require_agents_api_enabled()
     _validate_agent_name(name)
     name = _normalize_agent_name(name)
 

backend/app/gateway/routers/auth.py

@@ -2,6 +2,7 @@
 
 import logging
 import os
+import secrets
 import time
 from ipaddress import ip_address, ip_network
 
@@ -146,13 +147,7 @@ def _set_session_cookie(response: Response, token: str, request: Request) -> Non
 
 
 # ── Rate Limiting ────────────────────────────────────────────────────────
-# In-process dict — not shared across workers.
-#
-# **Limitation**: with multi-worker deployments (e.g., gunicorn -w N), each
-# worker maintains its own lockout table, so an attacker effectively gets
-# N × _MAX_LOGIN_ATTEMPTS guesses before being locked out everywhere. For
-# production multi-worker setups, replace this with a shared store (Redis,
-# database-backed counter) to enforce a true per-IP limit.
+# In-process dict — not shared across workers. Sufficient for single-worker deployments.
 
 _MAX_LOGIN_ATTEMPTS = 5
 _LOCKOUT_SECONDS = 300  # 5 minutes
@@ -382,37 +377,9 @@ async def get_me(request: Request):
     return UserResponse(id=str(user.id), email=user.email, system_role=user.system_role, needs_setup=user.needs_setup)
 
 
-_SETUP_STATUS_COOLDOWN: dict[str, float] = {}
-_SETUP_STATUS_COOLDOWN_SECONDS = 60
-_MAX_TRACKED_SETUP_STATUS_IPS = 10000
-
-
 @router.get("/setup-status")
-async def setup_status(request: Request):
+async def setup_status():
     """Check if an admin account exists. Returns needs_setup=True when no admin exists."""
-    client_ip = _get_client_ip(request)
-    now = time.time()
-    last_check = _SETUP_STATUS_COOLDOWN.get(client_ip, 0)
-    elapsed = now - last_check
-    if elapsed < _SETUP_STATUS_COOLDOWN_SECONDS:
-        retry_after = max(1, int(_SETUP_STATUS_COOLDOWN_SECONDS - elapsed))
-        raise HTTPException(
-            status_code=status.HTTP_429_TOO_MANY_REQUESTS,
-            detail="Setup status check is rate limited",
-            headers={"Retry-After": str(retry_after)},
-        )
-    # Evict stale entries when dict grows too large to bound memory usage.
-    if len(_SETUP_STATUS_COOLDOWN) >= _MAX_TRACKED_SETUP_STATUS_IPS:
-        cutoff = now - _SETUP_STATUS_COOLDOWN_SECONDS
-        stale = [k for k, t in _SETUP_STATUS_COOLDOWN.items() if t < cutoff]
-        for k in stale:
-            del _SETUP_STATUS_COOLDOWN[k]
-        # If still too large after evicting expired entries, remove oldest half.
-        if len(_SETUP_STATUS_COOLDOWN) >= _MAX_TRACKED_SETUP_STATUS_IPS:
-            by_time = sorted(_SETUP_STATUS_COOLDOWN.items(), key=lambda kv: kv[1])
-            for k, _ in by_time[: len(by_time) // 2]:
-                del _SETUP_STATUS_COOLDOWN[k]
-    _SETUP_STATUS_COOLDOWN[client_ip] = now
     admin_count = await get_local_provider().count_admin_users()
     return {"needs_setup": admin_count == 0}
 
@@ -422,6 +389,7 @@ class InitializeAdminRequest(BaseModel):
 
     email: EmailStr
     password: str = Field(..., min_length=8)
+    init_token: str | None = Field(default=None, description="One-time initialization token printed to server logs on first boot")
 
     _strong_password = field_validator("password")(classmethod(lambda cls, v: _validate_strong_password(v)))
 
@@ -431,13 +399,31 @@ async def initialize_admin(request: Request, response: Response, body: Initializ
     """Create the first admin account on initial system setup.
 
     Only callable when no admin exists. Returns 409 Conflict if an admin
-    already exists.
+    already exists. Requires the one-time ``init_token`` that is logged to
+    stdout at startup whenever the system has no admin account.
 
-    On success, the admin account is created with ``needs_setup=False`` and
-    the session cookie is set.
+    On success the token is consumed (one-time use), the admin account is
+    created with ``needs_setup=False``, and the session cookie is set.
     """
+    # Validate the one-time initialization token.  The token is generated
+    # at startup and stored in app.state.init_token; it is consumed here on
+    # the first successful call so it cannot be replayed.
+    # Using str | None allows a missing/null token to return 403 (not 422),
+    # giving a consistent error response regardless of whether the token is
+    # absent or incorrect.
+    stored_token: str | None = getattr(request.app.state, "init_token", None)
+    provided_token: str = body.init_token or ""
+    if stored_token is None or not secrets.compare_digest(stored_token, provided_token):
+        raise HTTPException(
+            status_code=status.HTTP_403_FORBIDDEN,
+            detail=AuthErrorResponse(code=AuthErrorCode.INVALID_INIT_TOKEN, message="Invalid or expired initialization token").model_dump(),
+        )
+
     admin_count = await get_local_provider().count_admin_users()
     if admin_count > 0:
+        # Do NOT consume the token on this error path — consuming it here
+        # would allow an attacker to exhaust the token by calling with the
+        # correct token when admin already exists (denial-of-service).
         raise HTTPException(
             status_code=status.HTTP_409_CONFLICT,
             detail=AuthErrorResponse(code=AuthErrorCode.SYSTEM_ALREADY_INITIALIZED, message="System already initialized").model_dump(),
@@ -447,11 +433,16 @@ async def initialize_admin(request: Request, response: Response, body: Initializ
         user = await get_local_provider().create_user(email=body.email, password=body.password, system_role="admin", needs_setup=False)
     except ValueError:
         # DB unique-constraint race: another concurrent request beat us.
+        # Do NOT consume the token here for the same reason as above.
         raise HTTPException(
             status_code=status.HTTP_409_CONFLICT,
             detail=AuthErrorResponse(code=AuthErrorCode.SYSTEM_ALREADY_INITIALIZED, message="System already initialized").model_dump(),
         )
 
+    # Consume the token only after successful initialization — this is the
+    # single place where one-time use is enforced.
+    request.app.state.init_token = None
+
     token = create_access_token(str(user.id), token_version=user.token_version)
     _set_session_cookie(response, token, request)
 

backend/app/gateway/routers/models.py

@@ -1,8 +1,7 @@
-from fastapi import APIRouter, Depends, HTTPException
+from fastapi import APIRouter, HTTPException
 from pydantic import BaseModel, Field
 
-from app.gateway.deps import get_config
-from deerflow.config.app_config import AppConfig
+from deerflow.config import get_app_config
 
 router = APIRouter(prefix="/api", tags=["models"])
 
@@ -18,17 +17,10 @@ class ModelResponse(BaseModel):
     supports_reasoning_effort: bool = Field(default=False, description="Whether model supports reasoning effort")
 
 
-class TokenUsageResponse(BaseModel):
-    """Token usage display configuration."""
-
-    enabled: bool = Field(default=False, description="Whether token usage display is enabled")
-
-
 class ModelsListResponse(BaseModel):
     """Response model for listing all models."""
 
     models: list[ModelResponse]
-    token_usage: TokenUsageResponse
 
 
 @router.get(
@@ -37,14 +29,14 @@ class ModelsListResponse(BaseModel):
     summary="List All Models",
     description="Retrieve a list of all available AI models configured in the system.",
 )
-async def list_models(config: AppConfig = Depends(get_config)) -> ModelsListResponse:
+async def list_models() -> ModelsListResponse:
     """List all available models from configuration.
 
     Returns model information suitable for frontend display,
     excluding sensitive fields like API keys and internal configuration.
 
     Returns:
-        A list of all configured models with their metadata and token usage display settings.
+        A list of all configured models with their metadata.
 
     Example Response:
         ```json
@@ -52,27 +44,21 @@ async def list_models(config: AppConfig = Depends(get_config)) -> ModelsListResp
             "models": [
                 {
                     "name": "gpt-4",
-                    "model": "gpt-4",
                     "display_name": "GPT-4",
                     "description": "OpenAI GPT-4 model",
-                    "supports_thinking": false,
-                    "supports_reasoning_effort": false
+                    "supports_thinking": false
                 },
                 {
                     "name": "claude-3-opus",
-                    "model": "claude-3-opus",
                     "display_name": "Claude 3 Opus",
                     "description": "Anthropic Claude 3 Opus model",
-                    "supports_thinking": true,
-                    "supports_reasoning_effort": false
+                    "supports_thinking": true
                 }
-            ],
-            "token_usage": {
-                "enabled": true
-            }
+            ]
         }
         ```
     """
+    config = get_app_config()
     models = [
         ModelResponse(
             name=model.name,
@@ -84,10 +70,7 @@ async def list_models(config: AppConfig = Depends(get_config)) -> ModelsListResp
         )
         for model in config.models
     ]
-    return ModelsListResponse(
-        models=models,
-        token_usage=TokenUsageResponse(enabled=config.token_usage.enabled),
-    )
+    return ModelsListResponse(models=models)
 
 
 @router.get(
@@ -96,7 +79,7 @@ async def list_models(config: AppConfig = Depends(get_config)) -> ModelsListResp
     summary="Get Model Details",
     description="Retrieve detailed information about a specific AI model by its name.",
 )
-async def get_model(model_name: str, config: AppConfig = Depends(get_config)) -> ModelResponse:
+async def get_model(model_name: str) -> ModelResponse:
     """Get a specific model by name.
 
     Args:
@@ -118,6 +101,7 @@ async def get_model(model_name: str, config: AppConfig = Depends(get_config)) ->
         }
         ```
     """
+    config = get_app_config()
     model = config.get_model_config(model_name)
     if model is None:
         raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found")

backend/app/gateway/routers/runs.py

@@ -123,8 +123,7 @@ async def run_messages(
     run = await _resolve_run(run_id, request)
     event_store = get_run_event_store(request)
     rows = await event_store.list_messages_by_run(
-        run["thread_id"],
-        run_id,
+        run["thread_id"], run_id,
         limit=limit + 1,
         before_seq=before_seq,
         after_seq=after_seq,

backend/app/gateway/routers/skills.py

@@ -1,20 +1,29 @@
 import json
 import logging
+import shutil
 from pathlib import Path
 
-from fastapi import APIRouter, Depends, HTTPException
+from fastapi import APIRouter, HTTPException
 from pydantic import BaseModel, Field
 
-from app.gateway.deps import get_config
 from app.gateway.path_utils import resolve_thread_virtual_path
 from deerflow.agents.lead_agent.prompt import refresh_skills_system_prompt_cache_async
-from deerflow.config.app_config import AppConfig
 from deerflow.config.extensions_config import ExtensionsConfig, SkillStateConfig, get_extensions_config, reload_extensions_config
-from deerflow.skills import Skill
-from deerflow.skills.installer import SkillAlreadyExistsError
+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
-from deerflow.skills.storage import get_or_new_skill_storage
-from deerflow.skills.types import SKILL_MD_FILE, SkillCategory
 
 logger = logging.getLogger(__name__)
 
@@ -27,7 +36,7 @@ class SkillResponse(BaseModel):
     name: str = Field(..., description="Name of the skill")
     description: str = Field(..., description="Description of what the skill does")
     license: str | None = Field(None, description="License information")
-    category: SkillCategory = Field(..., description="Category of the skill (public or custom)")
+    category: str = Field(..., description="Category of the skill (public or custom)")
     enabled: bool = Field(default=True, description="Whether this skill is enabled")
 
 
@@ -91,9 +100,9 @@ def _skill_to_response(skill: Skill) -> SkillResponse:
     summary="List All Skills",
     description="Retrieve a list of all available skills from both public and custom directories.",
 )
-async def list_skills(config: AppConfig = Depends(get_config)) -> SkillsListResponse:
+async def list_skills() -> SkillsListResponse:
     try:
-        skills = get_or_new_skill_storage(app_config=config).load_skills(enabled_only=False)
+        skills = load_skills(enabled_only=False)
         return SkillsListResponse(skills=[_skill_to_response(skill) for skill in skills])
     except Exception as e:
         logger.error(f"Failed to load skills: {e}", exc_info=True)
@@ -106,10 +115,10 @@ async def list_skills(config: AppConfig = Depends(get_config)) -> SkillsListResp
     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, config: AppConfig = Depends(get_config)) -> SkillInstallResponse:
+async def install_skill(request: SkillInstallRequest) -> SkillInstallResponse:
     try:
         skill_file_path = resolve_thread_virtual_path(request.thread_id, request.path)
-        result = await get_or_new_skill_storage(app_config=config).ainstall_skill_from_archive(skill_file_path)
+        result = install_skill_from_archive(skill_file_path)
         await refresh_skills_system_prompt_cache_async()
         return SkillInstallResponse(**result)
     except FileNotFoundError as e:
@@ -126,9 +135,9 @@ async def install_skill(request: SkillInstallRequest, config: AppConfig = Depend
 
 
 @router.get("/skills/custom", response_model=SkillsListResponse, summary="List Custom Skills")
-async def list_custom_skills(config: AppConfig = Depends(get_config)) -> SkillsListResponse:
+async def list_custom_skills() -> SkillsListResponse:
     try:
-        skills = [skill for skill in get_or_new_skill_storage(app_config=config).load_skills(enabled_only=False) if skill.category == SkillCategory.CUSTOM]
+        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)
@@ -136,14 +145,13 @@ async def list_custom_skills(config: AppConfig = Depends(get_config)) -> SkillsL
 
 
 @router.get("/skills/custom/{skill_name}", response_model=CustomSkillContentResponse, summary="Get Custom Skill Content")
-async def get_custom_skill(skill_name: str, config: AppConfig = Depends(get_config)) -> CustomSkillContentResponse:
+async def get_custom_skill(skill_name: str) -> CustomSkillContentResponse:
     try:
-        skill_name = skill_name.replace("\r\n", "").replace("\n", "")
-        skills = get_or_new_skill_storage(app_config=config).load_skills(enabled_only=False)
-        skill = next((s for s in skills if s.name == skill_name and s.category == SkillCategory.CUSTOM), None)
+        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=get_or_new_skill_storage(app_config=config).read_custom_skill(skill_name))
+        return CustomSkillContentResponse(**_skill_to_response(skill).model_dump(), content=read_custom_skill_content(skill_name))
     except HTTPException:
         raise
     except Exception as e:
@@ -152,31 +160,30 @@ async def get_custom_skill(skill_name: str, config: AppConfig = Depends(get_conf
 
 
 @router.put("/skills/custom/{skill_name}", response_model=CustomSkillContentResponse, summary="Edit Custom Skill")
-async def update_custom_skill(skill_name: str, request: CustomSkillUpdateRequest, config: AppConfig = Depends(get_config)) -> CustomSkillContentResponse:
+async def update_custom_skill(skill_name: str, request: CustomSkillUpdateRequest) -> CustomSkillContentResponse:
     try:
-        skill_name = skill_name.replace("\r\n", "").replace("\n", "")
-        storage = get_or_new_skill_storage(app_config=config)
-        storage.ensure_custom_skill_is_editable(skill_name)
-        storage.validate_skill_markdown_content(skill_name, request.content)
-        scan = await scan_skill_content(request.content, executable=False, location=f"{skill_name}/{SKILL_MD_FILE}", app_config=config)
+        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}")
-        prev_content = storage.read_custom_skill(skill_name)
-        storage.write_custom_skill(skill_name, SKILL_MD_FILE, request.content)
-        storage.append_history(
+        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_FILE,
+                "file_path": "SKILL.md",
                 "prev_content": prev_content,
                 "new_content": request.content,
                 "scanner": {"decision": scan.decision, "reason": scan.reason},
             },
         )
         await refresh_skills_system_prompt_cache_async()
-        return await get_custom_skill(skill_name, config)
+        return await get_custom_skill(skill_name)
     except HTTPException:
         raise
     except FileNotFoundError as e:
@@ -189,22 +196,24 @@ async def update_custom_skill(skill_name: str, request: CustomSkillUpdateRequest
 
 
 @router.delete("/skills/custom/{skill_name}", summary="Delete Custom Skill")
-async def delete_custom_skill(skill_name: str, config: AppConfig = Depends(get_config)) -> dict[str, bool]:
+async def delete_custom_skill(skill_name: str) -> dict[str, bool]:
     try:
-        skill_name = skill_name.replace("\r\n", "").replace("\n", "")
-        storage = get_or_new_skill_storage(app_config=config)
-        storage.delete_custom_skill(
+        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,
-            history_meta={
+            {
                 "action": "human_delete",
                 "author": "human",
                 "thread_id": None,
-                "file_path": SKILL_MD_FILE,
-                "prev_content": None,
+                "file_path": "SKILL.md",
+                "prev_content": prev_content,
                 "new_content": None,
                 "scanner": {"decision": "allow", "reason": "Deletion requested."},
             },
         )
+        shutil.rmtree(skill_dir)
         await refresh_skills_system_prompt_cache_async()
         return {"success": True}
     except FileNotFoundError as e:
@@ -217,13 +226,11 @@ async def delete_custom_skill(skill_name: str, config: AppConfig = Depends(get_c
 
 
 @router.get("/skills/custom/{skill_name}/history", response_model=CustomSkillHistoryResponse, summary="Get Custom Skill History")
-async def get_custom_skill_history(skill_name: str, config: AppConfig = Depends(get_config)) -> CustomSkillHistoryResponse:
+async def get_custom_skill_history(skill_name: str) -> CustomSkillHistoryResponse:
     try:
-        skill_name = skill_name.replace("\r\n", "").replace("\n", "")
-        storage = get_or_new_skill_storage(app_config=config)
-        if not storage.custom_skill_exists(skill_name) and not storage.get_skill_history_file(skill_name).exists():
+        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=storage.read_history(skill_name))
+        return CustomSkillHistoryResponse(history=read_history(skill_name))
     except HTTPException:
         raise
     except Exception as e:
@@ -232,39 +239,38 @@ async def get_custom_skill_history(skill_name: str, config: AppConfig = Depends(
 
 
 @router.post("/skills/custom/{skill_name}/rollback", response_model=CustomSkillContentResponse, summary="Rollback Custom Skill")
-async def rollback_custom_skill(skill_name: str, request: SkillRollbackRequest, config: AppConfig = Depends(get_config)) -> CustomSkillContentResponse:
+async def rollback_custom_skill(skill_name: str, request: SkillRollbackRequest) -> CustomSkillContentResponse:
     try:
-        storage = get_or_new_skill_storage(app_config=config)
-        if not storage.custom_skill_exists(skill_name) and not storage.get_skill_history_file(skill_name).exists():
+        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 = storage.read_history(skill_name)
+        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")
-        storage.validate_skill_markdown_content(skill_name, target_content)
-        scan = await scan_skill_content(target_content, executable=False, location=f"{skill_name}/{SKILL_MD_FILE}", app_config=config)
-        skill_file = storage.get_custom_skill_file(skill_name)
+        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_FILE,
+            "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":
-            storage.append_history(skill_name, history_entry)
+            append_history(skill_name, history_entry)
             raise HTTPException(status_code=400, detail=f"Rollback blocked by security scanner: {scan.reason}")
-        storage.write_custom_skill(skill_name, SKILL_MD_FILE, target_content)
-        storage.append_history(skill_name, history_entry)
+        atomic_write(skill_file, target_content)
+        append_history(skill_name, history_entry)
         await refresh_skills_system_prompt_cache_async()
-        return await get_custom_skill(skill_name, config)
+        return await get_custom_skill(skill_name)
     except HTTPException:
         raise
     except IndexError:
@@ -284,10 +290,9 @@ async def rollback_custom_skill(skill_name: str, request: SkillRollbackRequest,
     summary="Get Skill Details",
     description="Retrieve detailed information about a specific skill by its name.",
 )
-async def get_skill(skill_name: str, config: AppConfig = Depends(get_config)) -> SkillResponse:
+async def get_skill(skill_name: str) -> SkillResponse:
     try:
-        skill_name = skill_name.replace("\r\n", "").replace("\n", "")
-        skills = get_or_new_skill_storage(app_config=config).load_skills(enabled_only=False)
+        skills = load_skills(enabled_only=False)
         skill = next((s for s in skills if s.name == skill_name), None)
 
         if skill is None:
@@ -307,10 +312,9 @@ async def get_skill(skill_name: str, config: AppConfig = Depends(get_config)) ->
     summary="Update Skill",
     description="Update a skill's enabled status by modifying the extensions_config.json file.",
 )
-async def update_skill(skill_name: str, request: SkillUpdateRequest, config: AppConfig = Depends(get_config)) -> SkillResponse:
+async def update_skill(skill_name: str, request: SkillUpdateRequest) -> SkillResponse:
     try:
-        skill_name = skill_name.replace("\r\n", "").replace("\n", "")
-        skills = get_or_new_skill_storage(app_config=config).load_skills(enabled_only=False)
+        skills = load_skills(enabled_only=False)
         skill = next((s for s in skills if s.name == skill_name), None)
 
         if skill is None:
@@ -336,7 +340,7 @@ async def update_skill(skill_name: str, request: SkillUpdateRequest, config: App
         reload_extensions_config()
         await refresh_skills_system_prompt_cache_async()
 
-        skills = get_or_new_skill_storage(app_config=config).load_skills(enabled_only=False)
+        skills = load_skills(enabled_only=False)
         updated_skill = next((s for s in skills if s.name == skill_name), None)
 
         if updated_skill is None:

backend/app/gateway/routers/suggestions.py

@@ -1,13 +1,11 @@
 import json
 import logging
 
-from fastapi import APIRouter, Depends, Request
+from fastapi import APIRouter, Request
 from langchain_core.messages import HumanMessage, SystemMessage
 from pydantic import BaseModel, Field
 
 from app.gateway.authz import require_permission
-from app.gateway.deps import get_config
-from deerflow.config.app_config import AppConfig
 from deerflow.models import create_chat_model
 
 logger = logging.getLogger(__name__)
@@ -102,12 +100,7 @@ def _format_conversation(messages: list[SuggestionMessage]) -> str:
     description="Generate short follow-up questions a user might ask next, based on recent conversation context.",
 )
 @require_permission("threads", "read", owner_check=True)
-async def generate_suggestions(
-    thread_id: str,
-    body: SuggestionsRequest,
-    request: Request,
-    config: AppConfig = Depends(get_config),
-) -> SuggestionsResponse:
+async def generate_suggestions(thread_id: str, body: SuggestionsRequest, request: Request) -> SuggestionsResponse:
     if not body.messages:
         return SuggestionsResponse(suggestions=[])
 
@@ -129,8 +122,8 @@ async def generate_suggestions(
     user_content = f"Conversation Context:\n{conversation}\n\nGenerate {n} follow-up questions"
 
     try:
-        model = create_chat_model(name=body.model_name, thinking_enabled=False, app_config=config)
-        response = await model.ainvoke([SystemMessage(content=system_instruction), HumanMessage(content=user_content)], config={"run_name": "suggest_agent"})
+        model = create_chat_model(name=body.model_name, thinking_enabled=False)
+        response = await model.ainvoke([SystemMessage(content=system_instruction), HumanMessage(content=user_content)])
         raw = _extract_response_text(response.content)
         suggestions = _parse_json_string_list(raw) or []
         cleaned = [s.replace("\n", " ").strip() for s in suggestions if s.strip()]

backend/app/gateway/routers/thread_runs.py

@@ -54,6 +54,7 @@ class RunCreateRequest(BaseModel):
     after_seconds: float | None = Field(default=None, description="Delayed execution")
     if_not_exists: Literal["reject", "create"] = Field(default="create", description="Thread creation policy")
     feedback_keys: list[str] | None = Field(default=None, description="LangSmith feedback keys")
+    follow_up_to_run_id: str | None = Field(default=None, description="Run ID this message follows up on. Auto-detected from latest successful run if not provided.")
 
 
 class RunResponse(BaseModel):
@@ -311,15 +312,11 @@ async def list_thread_messages(
         if i in last_ai_indices:
             run_id = msg["run_id"]
             fb = feedback_map.get(run_id)
-            msg["feedback"] = (
-                {
-                    "feedback_id": fb["feedback_id"],
-                    "rating": fb["rating"],
-                    "comment": fb.get("comment"),
-                }
-                if fb
-                else None
-            )
+            msg["feedback"] = {
+                "feedback_id": fb["feedback_id"],
+                "rating": fb["rating"],
+                "comment": fb.get("comment"),
+            } if fb else None
         else:
             msg["feedback"] = None
 
@@ -342,8 +339,7 @@ async def list_run_messages(
     """
     event_store = get_run_event_store(request)
     rows = await event_store.list_messages_by_run(
-        thread_id,
-        run_id,
+        thread_id, run_id,
         limit=limit + 1,
         before_seq=before_seq,
         after_seq=after_seq,

backend/app/gateway/routers/threads.py

@@ -13,6 +13,7 @@ matching the LangGraph Platform wire format expected by the
 from __future__ import annotations
 
 import logging
+import re
 import time
 import uuid
 from typing import Any
@@ -21,7 +22,7 @@ from fastapi import APIRouter, HTTPException, Request
 from pydantic import BaseModel, Field, field_validator
 
 from app.gateway.authz import require_permission
-from app.gateway.deps import get_checkpointer
+from app.gateway.deps import get_checkpointer, get_current_user, get_feedback_repo, get_run_event_store
 from app.gateway.utils import sanitize_log_param
 from deerflow.config.paths import Paths, get_paths
 from deerflow.runtime import serialize_channel_values
@@ -404,6 +405,164 @@ async def get_thread(thread_id: str, request: Request) -> ThreadResponse:
 
 
 # ---------------------------------------------------------------------------
+# Event-store-backed message loader
+# ---------------------------------------------------------------------------
+
+_LEGACY_CMD_INNER_CONTENT_RE = re.compile(
+    r"ToolMessage\(content=(?P<q>['\"])(?P<inner>.*?)(?P=q)",
+    re.DOTALL,
+)
+
+
+def _sanitize_legacy_command_repr(content_field: Any) -> Any:
+    """Recover the inner ToolMessage text from a legacy ``str(Command(...))`` repr.
+
+    Runs captured before the ``on_tool_end`` fix in ``journal.py`` stored
+    ``str(Command(update={'messages':[ToolMessage(content='X', ...)]}))`` as the
+    tool_result content. New runs store ``'X'`` directly. For legacy rows, try
+    to extract ``'X'`` defensively; return the original string if extraction
+    fails (still no worse than the checkpoint fallback for summarized threads).
+    """
+    if not isinstance(content_field, str) or not content_field.startswith("Command(update="):
+        return content_field
+    match = _LEGACY_CMD_INNER_CONTENT_RE.search(content_field)
+    return match.group("inner") if match else content_field
+
+
+async def _get_event_store_messages(request: Request, thread_id: str) -> list[dict] | None:
+    """Load the full message stream for ``thread_id`` from the event store.
+
+    The event store is append-only and unaffected by summarization — the
+    checkpoint's ``channel_values["messages"]`` is rewritten in-place when the
+    SummarizationMiddleware runs, which drops all pre-summarize messages. The
+    event store retains the full transcript, so callers in Gateway mode should
+    prefer it for rendering the conversation history.
+
+    In addition to the core message content, this helper attaches two extra
+    fields to every returned dict:
+
+    - ``run_id``: the ``run_id`` of the event that produced this message.
+      Always present.
+    - ``feedback``: thumbs-up/down data. Present only on the **final
+      ``ai_message`` of each run** (matching the per-run feedback semantics
+      of ``POST /api/threads/{id}/runs/{run_id}/feedback``). The frontend uses
+      the presence of this field to decide whether to render the feedback
+      button, which sidesteps the positional-index mapping bug that an
+      out-of-band ``/messages`` fetch exhibited.
+
+    Behaviour contract:
+
+    - **Full pagination.** ``RunEventStore.list_messages`` returns the newest
+      ``limit`` records when no cursor is given, so a fixed limit silently
+      drops older messages on long threads. We size the read from
+      ``count_messages()`` and then page forward with ``after_seq`` cursors.
+    - **Copy-on-read.** Each content dict is copied before ``id`` is patched
+      so the live store object is never mutated; ``MemoryRunEventStore``
+      returns live references.
+    - **Stable ids.** Messages with ``id=None`` (human + tool_result) receive
+      a deterministic ``uuid5(NAMESPACE_URL, f"{thread_id}:{seq}")`` so React
+      keys are stable across requests without altering stored data. AI messages
+      retain their LLM-assigned ``lc_run--*`` ids.
+    - **Legacy Command repr.** Rows captured before the ``journal.py``
+      ``on_tool_end`` fix stored ``str(Command(update={...}))`` as the tool
+      result content. ``_sanitize_legacy_command_repr`` extracts the inner
+      ToolMessage text.
+    - **User context.** ``DbRunEventStore`` is user-scoped by default via
+      ``resolve_user_id(AUTO)`` in ``runtime/user_context.py``. This helper
+      must run inside a request where ``@require_permission`` has populated
+      the user contextvar. Both callers below are decorated appropriately.
+      Do not call this helper from CLI or migration scripts without passing
+      ``user_id=None`` explicitly to the underlying store methods.
+
+    Returns ``None`` when the event store is not configured or has no message
+    events for this thread, so callers fall back to checkpoint messages.
+    """
+    try:
+        event_store = get_run_event_store(request)
+    except Exception:
+        return None
+
+    try:
+        total = await event_store.count_messages(thread_id)
+    except Exception:
+        logger.exception("count_messages failed for thread %s", sanitize_log_param(thread_id))
+        return None
+    if not total:
+        return None
+
+    # Batch by page_size to keep memory bounded for very long threads.
+    page_size = 500
+    collected: list[dict] = []
+    after_seq: int | None = None
+    while True:
+        try:
+            page = await event_store.list_messages(thread_id, limit=page_size, after_seq=after_seq)
+        except Exception:
+            logger.exception("list_messages failed for thread %s", sanitize_log_param(thread_id))
+            return None
+        if not page:
+            break
+        collected.extend(page)
+        if len(page) < page_size:
+            break
+        next_cursor = page[-1].get("seq")
+        if next_cursor is None or (after_seq is not None and next_cursor <= after_seq):
+            break
+        after_seq = next_cursor
+
+    # Build the message list; track the final ``ai_message`` index per run so
+    # feedback can be attached at the right position (matches thread_runs.py).
+    messages: list[dict] = []
+    last_ai_per_run: dict[str, int] = {}
+    for evt in collected:
+        raw = evt.get("content")
+        if not isinstance(raw, dict) or "type" not in raw:
+            continue
+        content = dict(raw)
+        if content.get("id") is None:
+            content["id"] = str(uuid.uuid5(uuid.NAMESPACE_URL, f"{thread_id}:{evt['seq']}"))
+        if content.get("type") == "tool":
+            content["content"] = _sanitize_legacy_command_repr(content.get("content"))
+        run_id = evt.get("run_id")
+        if run_id:
+            content["run_id"] = run_id
+        if evt.get("event_type") == "ai_message" and run_id:
+            last_ai_per_run[run_id] = len(messages)
+        messages.append(content)
+
+    if not messages:
+        return None
+
+    # Attach feedback to the final ai_message of each run. If the feedback
+    # subsystem is unavailable, leave the ``feedback`` field absent entirely
+    # so the frontend hides the button rather than showing it over a broken
+    # write path.
+    feedback_available = False
+    feedback_map: dict[str, dict] = {}
+    try:
+        feedback_repo = get_feedback_repo(request)
+        user_id = await get_current_user(request)
+        feedback_map = await feedback_repo.list_by_thread_grouped(thread_id, user_id=user_id)
+        feedback_available = True
+    except Exception:
+        logger.exception("feedback lookup failed for thread %s", sanitize_log_param(thread_id))
+
+    if feedback_available:
+        for run_id, idx in last_ai_per_run.items():
+            fb = feedback_map.get(run_id)
+            messages[idx]["feedback"] = (
+                {
+                    "feedback_id": fb["feedback_id"],
+                    "rating": fb["rating"],
+                    "comment": fb.get("comment"),
+                }
+                if fb
+                else None
+            )
+
+    return messages
+
+
 @router.get("/{thread_id}/state", response_model=ThreadStateResponse)
 @require_permission("threads", "read", owner_check=True)
 async def get_thread_state(thread_id: str, request: Request) -> ThreadStateResponse:
@@ -444,6 +603,11 @@ async def get_thread_state(thread_id: str, request: Request) -> ThreadStateRespo
 
     values = serialize_channel_values(channel_values)
 
+    # Prefer event-store messages: append-only, immune to summarization.
+    es_messages = await _get_event_store_messages(request, thread_id)
+    if es_messages is not None:
+        values["messages"] = es_messages
+
     return ThreadStateResponse(
         values=values,
         next=next_tasks,
@@ -563,6 +727,11 @@ async def get_thread_history(thread_id: str, body: ThreadHistoryRequest, request
     if body.before:
         config["configurable"]["checkpoint_id"] = body.before
 
+    # Load the full event-store message stream once; attach to the latest
+    # checkpoint entry only (matching the prior semantics). The event store
+    # is append-only and immune to summarization.
+    es_messages = await _get_event_store_messages(request, thread_id)
+
     entries: list[HistoryEntry] = []
     is_latest_checkpoint = True
     try:
@@ -586,11 +755,17 @@ async def get_thread_history(thread_id: str, body: ThreadHistoryRequest, request
             if thread_data := channel_values.get("thread_data"):
                 values["thread_data"] = thread_data
 
-            # Attach messages only to the latest checkpoint entry.
+            # Attach messages only to the latest checkpoint. Prefer the
+            # event-store stream (complete and unaffected by summarization);
+            # fall back to checkpoint channel_values when the event store is
+            # unavailable or empty.
             if is_latest_checkpoint:
-                messages = channel_values.get("messages")
-                if messages:
-                    values["messages"] = serialize_channel_values({"messages": messages}).get("messages", [])
+                if es_messages is not None:
+                    values["messages"] = es_messages
+                else:
+                    messages = channel_values.get("messages")
+                    if messages:
+                        values["messages"] = serialize_channel_values({"messages": messages}).get("messages", [])
             is_latest_checkpoint = False
 
             # Derive next tasks

backend/app/gateway/routers/uploads.py

@@ -4,15 +4,13 @@ import logging
 import os
 import stat
 
-from fastapi import APIRouter, Depends, File, HTTPException, Request, UploadFile
+from fastapi import APIRouter, File, HTTPException, Request, UploadFile
 from pydantic import BaseModel
 
 from app.gateway.authz import require_permission
-from app.gateway.deps import get_config
-from deerflow.config.app_config import AppConfig
 from deerflow.config.paths import get_paths
 from deerflow.runtime.user_context import get_effective_user_id
-from deerflow.sandbox.sandbox_provider import SandboxProvider, get_sandbox_provider
+from deerflow.sandbox.sandbox_provider import get_sandbox_provider
 from deerflow.uploads.manager import (
     PathTraversalError,
     delete_file_safe,
@@ -30,11 +28,6 @@ logger = logging.getLogger(__name__)
 
 router = APIRouter(prefix="/api/threads/{thread_id}/uploads", tags=["uploads"])
 
-UPLOAD_CHUNK_SIZE = 8192
-DEFAULT_MAX_FILES = 10
-DEFAULT_MAX_FILE_SIZE = 50 * 1024 * 1024
-DEFAULT_MAX_TOTAL_SIZE = 100 * 1024 * 1024
-
 
 class UploadResponse(BaseModel):
     """Response model for file upload."""
@@ -44,14 +37,6 @@ class UploadResponse(BaseModel):
     message: str
 
 
-class UploadLimits(BaseModel):
-    """Application-level upload limits exposed to clients."""
-
-    max_files: int
-    max_file_size: int
-    max_total_size: int
-
-
 def _make_file_sandbox_writable(file_path: os.PathLike[str] | str) -> None:
     """Ensure uploaded files remain writable when mounted into non-local sandboxes.
 
@@ -70,124 +55,27 @@ def _make_file_sandbox_writable(file_path: os.PathLike[str] | str) -> None:
     os.chmod(file_path, writable_mode, **chmod_kwargs)
 
 
-def _uses_thread_data_mounts(sandbox_provider: SandboxProvider) -> bool:
-    return bool(getattr(sandbox_provider, "uses_thread_data_mounts", False))
-
-
-def _get_uploads_config_value(app_config: AppConfig, key: str, default: object) -> object:
-    """Read a value from the uploads config, supporting dict and attribute access."""
-    uploads_cfg = getattr(app_config, "uploads", None)
-    if isinstance(uploads_cfg, dict):
-        return uploads_cfg.get(key, default)
-    return getattr(uploads_cfg, key, default)
-
-
-def _get_upload_limit(app_config: AppConfig, key: str, default: int, *, legacy_key: str | None = None) -> int:
-    try:
-        value = _get_uploads_config_value(app_config, key, None)
-        if value is None and legacy_key is not None:
-            value = _get_uploads_config_value(app_config, legacy_key, None)
-        if value is None:
-            value = default
-        limit = int(value)
-        if limit <= 0:
-            raise ValueError
-        return limit
-    except Exception:
-        logger.warning("Invalid uploads.%s value; falling back to %d", key, default)
-        return default
-
-
-def _get_upload_limits(app_config: AppConfig) -> UploadLimits:
-    return UploadLimits(
-        max_files=_get_upload_limit(app_config, "max_files", DEFAULT_MAX_FILES, legacy_key="max_file_count"),
-        max_file_size=_get_upload_limit(app_config, "max_file_size", DEFAULT_MAX_FILE_SIZE, legacy_key="max_single_file_size"),
-        max_total_size=_get_upload_limit(app_config, "max_total_size", DEFAULT_MAX_TOTAL_SIZE),
-    )
-
-
-def _cleanup_uploaded_paths(paths: list[os.PathLike[str] | str]) -> None:
-    for path in reversed(paths):
-        try:
-            os.unlink(path)
-        except FileNotFoundError:
-            pass
-        except Exception:
-            logger.warning("Failed to clean up upload path after rejected request: %s", path, exc_info=True)
-
-
-async def _write_upload_file_streaming(
-    file: UploadFile,
-    file_path: os.PathLike[str] | str,
-    *,
-    display_filename: str,
-    max_single_file_size: int,
-    max_total_size: int,
-    total_size: int,
-) -> tuple[int, int]:
-    file_size = 0
-    with open(file_path, "wb") as output:
-        while chunk := await file.read(UPLOAD_CHUNK_SIZE):
-            file_size += len(chunk)
-            total_size += len(chunk)
-            if file_size > max_single_file_size:
-                raise HTTPException(status_code=413, detail=f"File too large: {display_filename}")
-            if total_size > max_total_size:
-                raise HTTPException(status_code=413, detail="Total upload size too large")
-            output.write(chunk)
-    return file_size, total_size
-
-
-def _auto_convert_documents_enabled(app_config: AppConfig) -> bool:
-    """Return whether automatic host-side document conversion is enabled.
-
-    The secure default is disabled unless an operator explicitly opts in via
-    uploads.auto_convert_documents in config.yaml.
-    """
-    try:
-        raw = _get_uploads_config_value(app_config, "auto_convert_documents", False)
-        if isinstance(raw, str):
-            return raw.strip().lower() in {"1", "true", "yes", "on"}
-        return bool(raw)
-    except Exception:
-        return False
-
-
 @router.post("", response_model=UploadResponse)
-@require_permission("threads", "write", owner_check=True, require_existing=False)
+@require_permission("threads", "write", owner_check=True, require_existing=True)
 async def upload_files(
     thread_id: str,
     request: Request,
     files: list[UploadFile] = File(...),
-    config: AppConfig = Depends(get_config),
 ) -> UploadResponse:
     """Upload multiple files to a thread's uploads directory."""
     if not files:
         raise HTTPException(status_code=400, detail="No files provided")
 
-    limits = _get_upload_limits(config)
-    if len(files) > limits.max_files:
-        raise HTTPException(status_code=413, detail=f"Too many files: maximum is {limits.max_files}")
-
     try:
         uploads_dir = ensure_uploads_dir(thread_id)
     except ValueError as e:
         raise HTTPException(status_code=400, detail=str(e))
     sandbox_uploads = get_paths().sandbox_uploads_dir(thread_id, user_id=get_effective_user_id())
     uploaded_files = []
-    written_paths = []
-    sandbox_sync_targets = []
-    total_size = 0
 
     sandbox_provider = get_sandbox_provider()
-    sync_to_sandbox = not _uses_thread_data_mounts(sandbox_provider)
-    sandbox = None
-    if sync_to_sandbox:
-        sandbox_id = sandbox_provider.acquire(thread_id)
-        sandbox = sandbox_provider.get(sandbox_id)
-        if sandbox is None:
-            raise HTTPException(status_code=500, detail="Failed to acquire sandbox")
-    auto_convert_documents = _auto_convert_documents_enabled(config)
+    sandbox_id = sandbox_provider.acquire(thread_id)
+    sandbox = sandbox_provider.get(sandbox_id)
 
     for file in files:
         if not file.filename:
@@ -200,41 +88,35 @@ async def upload_files(
             continue
 
         try:
+            content = await file.read()
             file_path = uploads_dir / safe_filename
-            written_paths.append(file_path)
-            file_size, total_size = await _write_upload_file_streaming(
-                file,
-                file_path,
-                display_filename=safe_filename,
-                max_single_file_size=limits.max_file_size,
-                max_total_size=limits.max_total_size,
-                total_size=total_size,
-            )
+            file_path.write_bytes(content)
 
             virtual_path = upload_virtual_path(safe_filename)
 
-            if sync_to_sandbox:
-                sandbox_sync_targets.append((file_path, virtual_path))
+            if sandbox_id != "local":
+                _make_file_sandbox_writable(file_path)
+                sandbox.update_file(virtual_path, content)
 
             file_info = {
                 "filename": safe_filename,
-                "size": str(file_size),
+                "size": str(len(content)),
                 "path": str(sandbox_uploads / safe_filename),
                 "virtual_path": virtual_path,
                 "artifact_url": upload_artifact_url(thread_id, safe_filename),
             }
 
-            logger.info(f"Saved file: {safe_filename} ({file_size} bytes) to {file_info['path']}")
+            logger.info(f"Saved file: {safe_filename} ({len(content)} bytes) to {file_info['path']}")
 
             file_ext = file_path.suffix.lower()
-            if auto_convert_documents and file_ext in CONVERTIBLE_EXTENSIONS:
+            if file_ext in CONVERTIBLE_EXTENSIONS:
                 md_path = await convert_file_to_markdown(file_path)
                 if md_path:
-                    written_paths.append(md_path)
                     md_virtual_path = upload_virtual_path(md_path.name)
 
-                    if sync_to_sandbox:
-                        sandbox_sync_targets.append((md_path, md_virtual_path))
+                    if sandbox_id != "local":
+                        _make_file_sandbox_writable(md_path)
+                        sandbox.update_file(md_virtual_path, md_path.read_bytes())
 
                     file_info["markdown_file"] = md_path.name
                     file_info["markdown_path"] = str(sandbox_uploads / md_path.name)
@@ -243,19 +125,10 @@ async def upload_files(
 
             uploaded_files.append(file_info)
 
-        except HTTPException as e:
-            _cleanup_uploaded_paths(written_paths)
-            raise e
         except Exception as e:
             logger.error(f"Failed to upload {file.filename}: {e}")
-            _cleanup_uploaded_paths(written_paths)
             raise HTTPException(status_code=500, detail=f"Failed to upload {file.filename}: {str(e)}")
 
-    if sync_to_sandbox:
-        for file_path, virtual_path in sandbox_sync_targets:
-            _make_file_sandbox_writable(file_path)
-            sandbox.update_file(virtual_path, file_path.read_bytes())
-
     return UploadResponse(
         success=True,
         files=uploaded_files,
@@ -263,17 +136,6 @@ async def upload_files(
     )
 
 
-@router.get("/limits", response_model=UploadLimits)
-@require_permission("threads", "read", owner_check=True)
-async def get_upload_limits(
-    thread_id: str,
-    request: Request,
-    config: AppConfig = Depends(get_config),
-) -> UploadLimits:
-    """Return upload limits used by the gateway for this thread."""
-    return _get_upload_limits(config)
-
-
 @router.get("/list", response_model=dict)
 @require_permission("threads", "read", owner_check=True)
 async def list_uploaded_files(thread_id: str, request: Request) -> dict:

backend/app/gateway/services.py

@@ -8,16 +8,16 @@ frames, and consuming stream bridge events.  Router modules
 from __future__ import annotations
 
 import asyncio
+import dataclasses
 import json
 import logging
 import re
-from collections.abc import Mapping
 from typing import Any
 
 from fastapi import HTTPException, Request
 from langchain_core.messages import HumanMessage
 
-from app.gateway.deps import get_run_context, get_run_manager, get_stream_bridge
+from app.gateway.deps import get_run_context, get_run_manager, get_run_store, get_stream_bridge
 from app.gateway.utils import sanitize_log_param
 from deerflow.runtime import (
     END_SENTINEL,
@@ -98,52 +98,13 @@ def normalize_input(raw_input: dict[str, Any] | None) -> dict[str, Any]:
 _DEFAULT_ASSISTANT_ID = "lead_agent"
 
 
-# Whitelist of run-context keys that the langgraph-compat layer forwards from
-# ``body.context`` into the run config. ``config["context"]`` exists in
-# LangGraph >=0.6, but these values must be written to both ``configurable``
-# (for legacy ``_get_runtime_config`` consumers) and ``context`` because
-# LangGraph >=1.1.9 no longer makes ``ToolRuntime.context`` fall back to
-# ``configurable`` for consumers like ``setup_agent``.
-_CONTEXT_CONFIGURABLE_KEYS: frozenset[str] = frozenset(
-    {
-        "model_name",
-        "mode",
-        "thinking_enabled",
-        "reasoning_effort",
-        "is_plan_mode",
-        "subagent_enabled",
-        "max_concurrent_subagents",
-        "agent_name",
-        "is_bootstrap",
-    }
-)
-
-
-def merge_run_context_overrides(config: dict[str, Any], context: Mapping[str, Any] | None) -> None:
-    """Merge whitelisted keys from ``body.context`` into both ``config['configurable']``
-    and ``config['context']`` so they are visible to legacy configurable readers and
-    to LangGraph ``ToolRuntime.context`` consumers (e.g. the ``setup_agent`` tool —
-    see issue #2677)."""
-    if not context:
-        return
-    configurable = config.setdefault("configurable", {})
-    runtime_context = config.setdefault("context", {})
-    for key in _CONTEXT_CONFIGURABLE_KEYS:
-        if key in context:
-            if isinstance(configurable, dict):
-                configurable.setdefault(key, context[key])
-            if isinstance(runtime_context, dict):
-                runtime_context.setdefault(key, context[key])
-
-
 def resolve_agent_factory(assistant_id: str | None):
     """Resolve the agent factory callable from config.
 
     Custom agents are implemented as ``lead_agent`` + an ``agent_name``
-    injected into ``configurable`` or ``context`` — see
-    :func:`build_run_config`.  All ``assistant_id`` values therefore map to the
-    same factory; the routing happens inside ``make_lead_agent`` when it reads
-    ``cfg["agent_name"]``.
+    injected into ``configurable`` — see :func:`build_run_config`.  All
+    ``assistant_id`` values therefore map to the same factory; the routing
+    happens inside ``make_lead_agent`` when it reads ``cfg["agent_name"]``.
     """
     from deerflow.agents.lead_agent.agent import make_lead_agent
 
@@ -160,12 +121,10 @@ def build_run_config(
     """Build a RunnableConfig dict for the agent.
 
     When *assistant_id* refers to a custom agent (anything other than
-    ``"lead_agent"`` / ``None``), the name is forwarded as ``agent_name`` in
-    whichever runtime options container is active: ``context`` for
-    LangGraph >= 0.6.0 requests, otherwise ``configurable``.
-    ``make_lead_agent`` reads this key to load the matching
-    ``agents/<name>/SOUL.md`` and per-agent config — without it the agent
-    silently runs as the default lead agent.
+    ``"lead_agent"`` / ``None``), the name is forwarded as
+    ``configurable["agent_name"]``.  ``make_lead_agent`` reads this key to
+    load the matching ``agents/<name>/SOUL.md`` and per-agent config —
+    without it the agent silently runs as the default lead agent.
 
     This mirrors the channel manager's ``_resolve_run_params`` logic so that
     the LangGraph Platform-compatible HTTP API and the IM channel path behave
@@ -184,14 +143,7 @@ def build_run_config(
                     thread_id,
                     list(request_config.get("configurable", {}).keys()),
                 )
-            context_value = request_config["context"]
-            if context_value is None:
-                context = {}
-            elif isinstance(context_value, Mapping):
-                context = dict(context_value)
-            else:
-                raise ValueError("request config 'context' must be a mapping or null.")
-            config["context"] = context
+            config["context"] = request_config["context"]
         else:
             configurable = {"thread_id": thread_id}
             configurable.update(request_config.get("configurable", {}))
@@ -203,19 +155,13 @@ def build_run_config(
         config["configurable"] = {"thread_id": thread_id}
 
     # Inject custom agent name when the caller specified a non-default assistant.
-    # Honour an explicit agent_name in the active runtime options container.
-    if assistant_id and assistant_id != _DEFAULT_ASSISTANT_ID:
-        normalized = assistant_id.strip().lower().replace("_", "-")
-        if not normalized or not re.fullmatch(r"[a-z0-9-]+", normalized):
-            raise ValueError(f"Invalid assistant_id {assistant_id!r}: must contain only letters, digits, and hyphens after normalization.")
-        if "configurable" in config:
-            target = config["configurable"]
-        elif "context" in config:
-            target = config["context"]
-        else:
-            target = config.setdefault("configurable", {})
-        if target is not None and "agent_name" not in target:
-            target["agent_name"] = normalized
+    # Honour an explicit configurable["agent_name"] in the request if already set.
+    if assistant_id and assistant_id != _DEFAULT_ASSISTANT_ID and "configurable" in config:
+        if "agent_name" not in config["configurable"]:
+            normalized = assistant_id.strip().lower().replace("_", "-")
+            if not normalized or not re.fullmatch(r"[a-z0-9-]+", normalized):
+                raise ValueError(f"Invalid assistant_id {assistant_id!r}: must contain only letters, digits, and hyphens after normalization.")
+            config["configurable"]["agent_name"] = normalized
     if metadata:
         config.setdefault("metadata", {}).update(metadata)
     return config
@@ -249,6 +195,21 @@ async def start_run(
 
     disconnect = DisconnectMode.cancel if body.on_disconnect == "cancel" else DisconnectMode.continue_
 
+    # Resolve follow_up_to_run_id: explicit from request, or auto-detect from latest successful run
+    follow_up_to_run_id = getattr(body, "follow_up_to_run_id", None)
+    if follow_up_to_run_id is None:
+        run_store = get_run_store(request)
+        try:
+            recent_runs = await run_store.list_by_thread(thread_id, limit=1)
+            if recent_runs and recent_runs[0].get("status") == "success":
+                follow_up_to_run_id = recent_runs[0]["run_id"]
+        except Exception:
+            pass  # Don't block run creation
+
+    # Enrich base context with per-run field
+    if follow_up_to_run_id:
+        run_ctx = dataclasses.replace(run_ctx, follow_up_to_run_id=follow_up_to_run_id)
+
     try:
         record = await run_mgr.create_or_reject(
             thread_id,
@@ -257,6 +218,7 @@ async def start_run(
             metadata=body.metadata or {},
             kwargs={"input": body.input, "config": body.config},
             multitask_strategy=body.multitask_strategy,
+            follow_up_to_run_id=follow_up_to_run_id,
         )
     except ConflictError as exc:
         raise HTTPException(status_code=409, detail=str(exc)) from exc
@@ -283,11 +245,25 @@ async def start_run(
     graph_input = normalize_input(body.input)
     config = build_run_config(thread_id, body.config, body.metadata, assistant_id=body.assistant_id)
 
-    # Merge DeerFlow-specific context overrides into both ``configurable`` and ``context``.
+    # Merge DeerFlow-specific context overrides into configurable.
     # The ``context`` field is a custom extension for the langgraph-compat layer
     # that carries agent configuration (model_name, thinking_enabled, etc.).
     # Only agent-relevant keys are forwarded; unknown keys (e.g. thread_id) are ignored.
-    merge_run_context_overrides(config, getattr(body, "context", None))
+    context = getattr(body, "context", None)
+    if context:
+        _CONTEXT_CONFIGURABLE_KEYS = {
+            "model_name",
+            "mode",
+            "thinking_enabled",
+            "reasoning_effort",
+            "is_plan_mode",
+            "subagent_enabled",
+            "max_concurrent_subagents",
+        }
+        configurable = config.setdefault("configurable", {})
+        for key in _CONTEXT_CONFIGURABLE_KEYS:
+            if key in context:
+                configurable.setdefault(key, context[key])
 
     stream_modes = normalize_stream_modes(body.stream_mode)
 

backend/debug.py

@@ -19,70 +19,24 @@ import asyncio
 import logging
 
 from dotenv import load_dotenv
+from langchain_core.messages import HumanMessage
 
-try:
-    from prompt_toolkit import PromptSession
-    from prompt_toolkit.history import InMemoryHistory
-
-    _HAS_PROMPT_TOOLKIT = True
-except ImportError:
-    _HAS_PROMPT_TOOLKIT = False
+from deerflow.agents import make_lead_agent
 
 load_dotenv()
 
-_LOG_FMT = "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
-_LOG_DATEFMT = "%Y-%m-%d %H:%M:%S"
-
-
-def _setup_logging(log_level: int = logging.INFO) -> None:
-    """Route logs to ``debug.log`` using *log_level* for the initial root/file setup.
-
-    This configures the root logger and the ``debug.log`` file handler so logs do
-    not print on the interactive console. It is idempotent: any pre-existing
-    handlers on the root logger (e.g. installed by ``logging.basicConfig`` in
-    transitively imported modules) are removed so the debug session output only
-    lands in ``debug.log``.
-
-    Note: later config-driven logging adjustments may change named logger
-    verbosity without raising the root logger or file-handler thresholds set
-    here, so the eventual contents of ``debug.log`` may not be filtered solely by
-    this function's ``log_level`` argument.
-    """
-    root = logging.root
-    for h in list(root.handlers):
-        root.removeHandler(h)
-        h.close()
-    root.setLevel(log_level)
-
-    file_handler = logging.FileHandler("debug.log", mode="a", encoding="utf-8")
-    file_handler.setLevel(log_level)
-    file_handler.setFormatter(logging.Formatter(_LOG_FMT, datefmt=_LOG_DATEFMT))
-    root.addHandler(file_handler)
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
+    datefmt="%Y-%m-%d %H:%M:%S",
+)
 
 
 async def main():
-    # Install file logging first so warnings emitted while loading config do not
-    # leak onto the interactive terminal via Python's lastResort handler.
-    _setup_logging()
-
-    from deerflow.config import get_app_config
-    from deerflow.config.app_config import apply_logging_level
-
-    app_config = get_app_config()
-    apply_logging_level(app_config.log_level)
-
-    # Delay the rest of the deerflow imports until *after* logging is installed
-    # so that any import-time side effects (e.g. deerflow.agents starts a
-    # background skill-loader thread on import) emit logs to debug.log instead
-    # of leaking onto the interactive terminal via Python's lastResort handler.
-    from langchain_core.messages import HumanMessage
-    from langgraph.runtime import Runtime
-
-    from deerflow.agents import make_lead_agent
-    from deerflow.mcp import initialize_mcp_tools
-
     # Initialize MCP tools at startup
     try:
+        from deerflow.mcp import initialize_mcp_tools
+
         await initialize_mcp_tools()
     except Exception as e:
         print(f"Warning: Failed to initialize MCP tools: {e}")
@@ -98,27 +52,16 @@ async def main():
         }
     }
 
-    runtime = Runtime(context={"thread_id": config["configurable"]["thread_id"]})
-    config["configurable"]["__pregel_runtime"] = runtime
-
     agent = make_lead_agent(config)
 
-    session = PromptSession(history=InMemoryHistory()) if _HAS_PROMPT_TOOLKIT else None
-
     print("=" * 50)
     print("Lead Agent Debug Mode")
     print("Type 'quit' or 'exit' to stop")
-    print(f"Logs: debug.log (log_level={app_config.log_level})")
-    if not _HAS_PROMPT_TOOLKIT:
-        print("Tip: `uv sync --group dev` to enable arrow-key & history support")
     print("=" * 50)
 
     while True:
         try:
-            if session:
-                user_input = (await session.prompt_async("\nYou: ")).strip()
-            else:
-                user_input = input("\nYou: ").strip()
+            user_input = input("\nYou: ").strip()
             if not user_input:
                 continue
             if user_input.lower() in ("quit", "exit"):
@@ -127,15 +70,15 @@ async def main():
 
             # Invoke the agent
             state = {"messages": [HumanMessage(content=user_input)]}
-            result = await agent.ainvoke(state, config=config)
+            result = await agent.ainvoke(state, config=config, context={"thread_id": "debug-thread-001"})
 
             # Print the response
             if result.get("messages"):
                 last_message = result["messages"][-1]
                 print(f"\nAgent: {last_message.content}")
 
-        except (KeyboardInterrupt, EOFError):
-            print("\nGoodbye!")
+        except KeyboardInterrupt:
+            print("\nInterrupted. Goodbye!")
             break
         except Exception as e:
             print(f"\nError: {e}")

backend/docs/ARCHITECTURE.md

@@ -199,7 +199,7 @@ class ThreadState(AgentState):
 │   Built-in Tools    │  │  Configured Tools   │  │     MCP Tools       │
 │  (packages/harness/deerflow/tools/)       │  │  (config.yaml)      │  │  (extensions.json)  │
 ├─────────────────────┤  ├─────────────────────┤  ├─────────────────────┤
-│ - present_files     │  │ - web_search        │  │ - github            │
+│ - present_file      │  │ - web_search        │  │ - github            │
 │ - ask_clarification │  │ - web_fetch         │  │ - filesystem        │
 │ - view_image        │  │ - bash              │  │ - postgres          │
 │                     │  │ - read_file         │  │ - brave-search      │

backend/docs/CONFIGURATION.md

@@ -259,8 +259,6 @@ sandbox:
 
 When you configure `sandbox.mounts`, DeerFlow exposes those `container_path` values in the agent prompt so the agent can discover and operate on mounted directories directly instead of assuming everything must live under `/mnt/user-data`.
 
-For bare-metal Docker sandbox runs that use localhost, DeerFlow binds the sandbox HTTP port to `127.0.0.1` by default so it is not exposed on every host interface. Docker-outside-of-Docker deployments that connect through `host.docker.internal` keep the broad legacy bind for compatibility. Set `DEER_FLOW_SANDBOX_BIND_HOST` explicitly if your deployment needs a different bind address.
-
 ### Skills
 
 Configure the skills directory for specialized workflows:
@@ -321,16 +319,11 @@ models:
 - `DEEPSEEK_API_KEY` - DeepSeek API key
 - `NOVITA_API_KEY` - Novita API key (OpenAI-compatible endpoint)
 - `TAVILY_API_KEY` - Tavily search API key
-- `DEER_FLOW_PROJECT_ROOT` - Project root for relative runtime paths
 - `DEER_FLOW_CONFIG_PATH` - Custom config file path
-- `DEER_FLOW_EXTENSIONS_CONFIG_PATH` - Custom extensions config file path
-- `DEER_FLOW_HOME` - Runtime state directory (defaults to `.deer-flow` under the project root)
-- `DEER_FLOW_SKILLS_PATH` - Skills directory when `skills.path` is omitted
-- `GATEWAY_ENABLE_DOCS` - Set to `false` to disable Swagger UI (`/docs`), ReDoc (`/redoc`), and OpenAPI schema (`/openapi.json`) endpoints (default: `true`)
 
 ## Configuration Location
 
-The configuration file should be placed in the **project root directory** (`deer-flow/config.yaml`). Set `DEER_FLOW_PROJECT_ROOT` when the process may start from another working directory, or set `DEER_FLOW_CONFIG_PATH` to point at a specific file.
+The configuration file should be placed in the **project root directory** (`deer-flow/config.yaml`), not in the backend directory.
 
 ## Configuration Priority
 
@@ -338,12 +331,12 @@ DeerFlow searches for configuration in this order:
 
 1. Path specified in code via `config_path` argument
 2. Path from `DEER_FLOW_CONFIG_PATH` environment variable
-3. `config.yaml` under `DEER_FLOW_PROJECT_ROOT`, or under the current working directory when `DEER_FLOW_PROJECT_ROOT` is unset
-4. Legacy backend/repository-root locations for monorepo compatibility
+3. `config.yaml` in current working directory (typically `backend/` when running)
+4. `config.yaml` in parent directory (project root: `deer-flow/`)
 
 ## Best Practices
 
-1. **Place `config.yaml` in project root** - Set `DEER_FLOW_PROJECT_ROOT` if the runtime starts elsewhere
+1. **Place `config.yaml` in project root** - Not in `backend/` directory
 2. **Never commit `config.yaml`** - It's already in `.gitignore`
 3. **Use environment variables for secrets** - Don't hardcode API keys
 4. **Keep `config.example.yaml` updated** - Document all new options
@@ -354,7 +347,7 @@ DeerFlow searches for configuration in this order:
 
 ### "Config file not found"
 - Ensure `config.yaml` exists in the **project root** directory (`deer-flow/config.yaml`)
-- If the runtime starts outside the project root, set `DEER_FLOW_PROJECT_ROOT`
+- The backend searches parent directory by default, so root location is preferred
 - Alternatively, set `DEER_FLOW_CONFIG_PATH` environment variable to custom location
 
 ### "Invalid API key"
@@ -364,7 +357,7 @@ DeerFlow searches for configuration in this order:
 ### "Skills not loading"
 - Check that `deer-flow/skills/` directory exists
 - Verify skills have valid `SKILL.md` files
-- Check `skills.path` or `DEER_FLOW_SKILLS_PATH` if using a custom path
+- Check `skills.path` configuration if using custom path
 
 ### "Docker sandbox fails to start"
 - Ensure Docker is running

backend/docs/FILE_UPLOAD.md

@@ -2,12 +2,12 @@
 
 ## 概述
 
-DeerFlow 后端提供了完整的文件上传功能，支持多文件上传，并可选地将 Office 文档和 PDF 转换为 Markdown 格式。
+DeerFlow 后端提供了完整的文件上传功能，支持多文件上传，并自动将 Office 文档和 PDF 转换为 Markdown 格式。
 
 ## 功能特性
 
 - ✅ 支持多文件同时上传
-- ✅ 可选地转换文档为 Markdown（PDF、PPT、Excel、Word）
+- ✅ 自动转换文档为 Markdown（PDF、PPT、Excel、Word）
 - ✅ 文件存储在线程隔离的目录中
 - ✅ Agent 自动感知已上传的文件
 - ✅ 支持文件列表查询和删除
@@ -22,8 +22,6 @@ POST /api/threads/{thread_id}/uploads
 **请求体：** `multipart/form-data`
 - `files`: 一个或多个文件
 
-网关会在应用层限制上传规模，默认最多 10 个文件、单文件 50 MiB、单次请求总计 100 MiB。可通过 `config.yaml` 的 `uploads.max_files`、`uploads.max_file_size`、`uploads.max_total_size` 调整；前端会读取同一组限制并在选择文件时提示，超过限制时后端返回 `413 Payload Too Large`。
-
 **响应：**
 ```json
 {
@@ -50,23 +48,7 @@ POST /api/threads/{thread_id}/uploads
 - `virtual_path`: Agent 在沙箱中使用的虚拟路径
 - `artifact_url`: 前端通过 HTTP 访问文件的 URL
 
-### 2. 查询上传限制
-```
-GET /api/threads/{thread_id}/uploads/limits
-```
-
-返回网关当前生效的上传限制，供前端在用户选择文件前提示和拦截。
-
-**响应：**
-```json
-{
-  "max_files": 10,
-  "max_file_size": 52428800,
-  "max_total_size": 104857600
-}
-```
-
-### 3. 列出已上传文件
+### 2. 列出已上传文件
 ```
 GET /api/threads/{thread_id}/uploads/list
 ```
@@ -89,7 +71,7 @@ GET /api/threads/{thread_id}/uploads/list
 }
 ```
 
-### 4. 删除文件
+### 3. 删除文件
 ```
 DELETE /api/threads/{thread_id}/uploads/{filename}
 ```
@@ -104,7 +86,7 @@ DELETE /api/threads/{thread_id}/uploads/{filename}
 
 ## 支持的文档格式
 
-以下格式在显式启用 `uploads.auto_convert_documents: true` 时会自动转换为 Markdown：
+以下格式会自动转换为 Markdown：
 - PDF (`.pdf`)
 - PowerPoint (`.ppt`, `.pptx`)
 - Excel (`.xls`, `.xlsx`)
@@ -112,8 +94,6 @@ DELETE /api/threads/{thread_id}/uploads/{filename}
 
 转换后的 Markdown 文件会保存在同一目录下，文件名为原文件名 + `.md` 扩展名。
 
-默认情况下，自动转换是关闭的，以避免在网关主机上对不受信任的 Office/PDF 上传执行解析。只有在受信任部署中明确接受此风险时，才应将 `uploads.auto_convert_documents` 设置为 `true`。
-
 ## Agent 集成
 
 ### 自动文件列举
@@ -227,7 +207,6 @@ backend/.deer-flow/threads/
 - 最大文件大小：100MB（可在 nginx.conf 中配置 `client_max_body_size`）
 - 文件名安全性：系统会自动验证文件路径，防止目录遍历攻击
 - 线程隔离：每个线程的上传文件相互隔离，无法跨线程访问
-- 自动文档转换默认关闭；如需启用，需在 `config.yaml` 中显式设置 `uploads.auto_convert_documents: true`
 
 ## 技术实现
 

backend/docs/GUARDRAILS.md

@@ -296,7 +296,7 @@ These are the tool names your provider will see in `request.tool_name`:
 | `web_search` | Web search query |
 | `web_fetch` | Fetch URL content |
 | `image_search` | Image search |
-| `present_files` | Present file to user |
+| `present_file` | Present file to user |
 | `view_image` | Display image |
 | `ask_clarification` | Ask user a question |
 | `task` | Delegate to subagent |

backend/docs/HARNESS_APP_SPLIT.md

@@ -0,0 +1,343 @@
+# DeerFlow 后端拆分设计文档：Harness + App
+
+> 状态：Draft
+> 作者：DeerFlow Team
+> 日期：2026-03-13
+
+## 1. 背景与动机
+
+DeerFlow 后端当前是一个单一 Python 包（`src.*`），包含了从底层 agent 编排到上层用户产品的所有代码。随着项目发展，这种结构带来了几个问题：
+
+- **复用困难**：其他产品（CLI 工具、Slack bot、第三方集成）想用 agent 能力，必须依赖整个后端，包括 FastAPI、IM SDK 等不需要的依赖
+- **职责模糊**：agent 编排逻辑和用户产品逻辑混在同一个 `src/` 下，边界不清晰
+- **依赖膨胀**：LangGraph Server 运行时不需要 FastAPI/uvicorn/Slack SDK，但当前必须安装全部依赖
+
+本文档提出将后端拆分为两部分：**deerflow-harness**（可发布的 agent 框架包）和 **app**（不打包的用户产品代码）。
+
+## 2. 核心概念
+
+### 2.1 Harness（线束/框架层）
+
+Harness 是 agent 的构建与编排框架，回答 **"如何构建和运行 agent"** 的问题：
+
+- Agent 工厂与生命周期管理
+- Middleware pipeline
+- 工具系统（内置工具 + MCP + 社区工具）
+- 沙箱执行环境
+- 子 agent 委派
+- 记忆系统
+- 技能加载与注入
+- 模型工厂
+- 配置系统
+
+**Harness 是一个可发布的 Python 包**（`deerflow-harness`），可以独立安装和使用。
+
+**Harness 的设计原则**：对上层应用完全无感知。它不知道也不关心谁在调用它——可以是 Web App、CLI、Slack Bot、或者一个单元测试。
+
+### 2.2 App（应用层）
+
+App 是面向用户的产品代码，回答 **"如何将 agent 呈现给用户"** 的问题：
+
+- Gateway API（FastAPI REST 接口）
+- IM Channels（飞书、Slack、Telegram 集成）
+- Custom Agent 的 CRUD 管理
+- 文件上传/下载的 HTTP 接口
+
+**App 不打包、不发布**，它是 DeerFlow 项目内部的应用代码，直接运行。
+
+**App 依赖 Harness，但 Harness 不依赖 App。**
+
+### 2.3 边界划分
+
+| 模块 | 归属 | 说明 |
+|------|------|------|
+| `config/` | Harness | 配置系统是基础设施 |
+| `reflection/` | Harness | 动态模块加载工具 |
+| `utils/` | Harness | 通用工具函数 |
+| `agents/` | Harness | Agent 工厂、middleware、state、memory |
+| `subagents/` | Harness | 子 agent 委派系统 |
+| `sandbox/` | Harness | 沙箱执行环境 |
+| `tools/` | Harness | 工具注册与发现 |
+| `mcp/` | Harness | MCP 协议集成 |
+| `skills/` | Harness | 技能加载、解析、定义 schema |
+| `models/` | Harness | LLM 模型工厂 |
+| `community/` | Harness | 社区工具（tavily、jina 等） |
+| `client.py` | Harness | 嵌入式 Python 客户端 |
+| `gateway/` | App | FastAPI REST API |
+| `channels/` | App | IM 平台集成 |
+
+**关于 Custom Agents**：agent 定义格式（`config.yaml` + `SOUL.md` schema）由 Harness 层的 `config/agents_config.py` 定义，但文件的存储、CRUD、发现机制由 App 层的 `gateway/routers/agents.py` 负责。
+
+## 3. 目标架构
+
+### 3.1 目录结构
+
+```
+backend/
+├── packages/
+│   └── harness/
+│       ├── pyproject.toml          # deerflow-harness 包定义
+│       └── deerflow/               # Python 包根（import 前缀: deerflow.*）
+│           ├── __init__.py
+│           ├── config/
+│           ├── reflection/
+│           ├── utils/
+│           ├── agents/
+│           │   ├── lead_agent/
+│           │   ├── middlewares/
+│           │   ├── memory/
+│           │   ├── checkpointer/
+│           │   └── thread_state.py
+│           ├── subagents/
+│           ├── sandbox/
+│           ├── tools/
+│           ├── mcp/
+│           ├── skills/
+│           ├── models/
+│           ├── community/
+│           └── client.py
+├── app/                            # 不打包（import 前缀: app.*）
+│   ├── __init__.py
+│   ├── gateway/
+│   │   ├── __init__.py
+│   │   ├── app.py
+│   │   ├── config.py
+│   │   ├── path_utils.py
+│   │   └── routers/
+│   └── channels/
+│       ├── __init__.py
+│       ├── base.py
+│       ├── manager.py
+│       ├── service.py
+│       ├── store.py
+│       ├── message_bus.py
+│       ├── feishu.py
+│       ├── slack.py
+│       └── telegram.py
+├── pyproject.toml                  # uv workspace root
+├── langgraph.json
+├── tests/
+├── docs/
+└── Makefile
+```
+
+### 3.2 Import 规则
+
+两个层使用不同的 import 前缀，职责边界一目了然：
+
+```python
+# ---------------------------------------------------------------
+# Harness 内部互相引用（deerflow.* 前缀）
+# ---------------------------------------------------------------
+from deerflow.agents import make_lead_agent
+from deerflow.models import create_chat_model
+from deerflow.config import get_app_config
+from deerflow.tools import get_available_tools
+
+# ---------------------------------------------------------------
+# App 内部互相引用（app.* 前缀）
+# ---------------------------------------------------------------
+from app.gateway.app import app
+from app.gateway.routers.uploads import upload_files
+from app.channels.service import start_channel_service
+
+# ---------------------------------------------------------------
+# App 调用 Harness（单向依赖，Harness 永远不 import app）
+# ---------------------------------------------------------------
+from deerflow.agents import make_lead_agent
+from deerflow.models import create_chat_model
+from deerflow.skills import load_skills
+from deerflow.config.extensions_config import get_extensions_config
+```
+
+**App 调用 Harness 示例 — Gateway 中启动 agent**：
+
+```python
+# app/gateway/routers/chat.py
+from deerflow.agents.lead_agent.agent import make_lead_agent
+from deerflow.models import create_chat_model
+from deerflow.config import get_app_config
+
+async def create_chat_session(thread_id: str, model_name: str):
+    config = get_app_config()
+    model = create_chat_model(name=model_name)
+    agent = make_lead_agent(config=...)
+    # ... 使用 agent 处理用户消息
+```
+
+**App 调用 Harness 示例 — Channel 中查询 skills**：
+
+```python
+# app/channels/manager.py
+from deerflow.skills import load_skills
+from deerflow.agents.memory.updater import get_memory_data
+
+def handle_status_command():
+    skills = load_skills(enabled_only=True)
+    memory = get_memory_data()
+    return f"Skills: {len(skills)}, Memory facts: {len(memory.get('facts', []))}"
+```
+
+**禁止方向**：Harness 代码中绝不能出现 `from app.` 或 `import app.`。
+
+### 3.3 为什么 App 不打包
+
+| 方面 | 打包（放 packages/ 下） | 不打包（放 backend/app/） |
+|------|------------------------|--------------------------|
+| 命名空间 | 需要 pkgutil `extend_path` 合并，或独立前缀 | 天然独立，`app.*` vs `deerflow.*` |
+| 发布需求 | 没有——App 是项目内部代码 | 不需要 pyproject.toml |
+| 复杂度 | 需要管理两个包的构建、版本、依赖声明 | 直接运行，零额外配置 |
+| 运行方式 | `pip install deerflow-app` | `PYTHONPATH=. uvicorn app.gateway.app:app` |
+
+App 的唯一消费者是 DeerFlow 项目自身，没有独立发布的需求。放在 `backend/app/` 下作为普通 Python 包，通过 `PYTHONPATH` 或 editable install 让 Python 找到即可。
+
+### 3.4 依赖关系
+
+```
+┌─────────────────────────────────────┐
+│  app/  (不打包，直接运行)             │
+│  ├── fastapi, uvicorn               │
+│  ├── slack-sdk, lark-oapi, ...      │
+│  └── import deerflow.*              │
+└──────────────┬──────────────────────┘
+               │
+               ▼
+┌─────────────────────────────────────┐
+│  deerflow-harness  (可发布的包)       │
+│  ├── langgraph, langchain           │
+│  ├── markitdown, pydantic, ...      │
+│  └── 零 app 依赖                     │
+└─────────────────────────────────────┘
+```
+
+**依赖分类**：
+
+| 分类 | 依赖包 |
+|------|--------|
+| Harness only | agent-sandbox, langchain*, langgraph*, markdownify, markitdown, pydantic, pyyaml, readabilipy, tavily-python, firecrawl-py, tiktoken, ddgs, duckdb, httpx, kubernetes, dotenv |
+| App only | fastapi, uvicorn, sse-starlette, python-multipart, lark-oapi, slack-sdk, python-telegram-bot, markdown-to-mrkdwn |
+| Shared | langgraph-sdk（channels 用 HTTP client）, pydantic, httpx |
+
+### 3.5 Workspace 配置
+
+`backend/pyproject.toml`（workspace root）：
+
+```toml
+[project]
+name = "deer-flow"
+version = "0.1.0"
+requires-python = ">=3.12"
+dependencies = ["deerflow-harness"]
+
+[dependency-groups]
+dev = ["pytest>=8.0.0", "ruff>=0.14.11"]
+# App 的额外依赖（fastapi 等）也声明在 workspace root，因为 app 不打包
+app = ["fastapi", "uvicorn", "sse-starlette", "python-multipart"]
+channels = ["lark-oapi", "slack-sdk", "python-telegram-bot"]
+
+[tool.uv.workspace]
+members = ["packages/harness"]
+
+[tool.uv.sources]
+deerflow-harness = { workspace = true }
+```
+
+## 4. 当前的跨层依赖问题
+
+在拆分之前，需要先解决 `client.py` 中两处从 harness 到 app 的反向依赖：
+
+### 4.1 `_validate_skill_frontmatter`
+
+```python
+# client.py — harness 导入了 app 层代码
+from src.gateway.routers.skills import _validate_skill_frontmatter
+```
+
+**解决方案**：将该函数提取到 `deerflow/skills/validation.py`。这是一个纯逻辑函数（解析 YAML frontmatter、校验字段），与 FastAPI 无关。
+
+### 4.2 `CONVERTIBLE_EXTENSIONS` + `convert_file_to_markdown`
+
+```python
+# client.py — harness 导入了 app 层代码
+from src.gateway.routers.uploads import CONVERTIBLE_EXTENSIONS, convert_file_to_markdown
+```
+
+**解决方案**：将它们提取到 `deerflow/utils/file_conversion.py`。仅依赖 `markitdown` + `pathlib`，是通用工具函数。
+
+## 5. 基础设施变更
+
+### 5.1 LangGraph Server
+
+LangGraph Server 只需要 harness 包。`langgraph.json` 更新：
+
+```json
+{
+  "dependencies": ["./packages/harness"],
+  "graphs": {
+    "lead_agent": "deerflow.agents:make_lead_agent"
+  },
+  "checkpointer": {
+    "path": "./packages/harness/deerflow/agents/checkpointer/async_provider.py:make_checkpointer"
+  }
+}
+```
+
+### 5.2 Gateway API
+
+```bash
+# serve.sh / Makefile
+# PYTHONPATH 包含 backend/ 根目录，使 app.* 和 deerflow.* 都能被找到
+PYTHONPATH=. uvicorn app.gateway.app:app --host 0.0.0.0 --port 8001
+```
+
+### 5.3 Nginx
+
+无需变更（只做 URL 路由，不涉及 Python 模块路径）。
+
+### 5.4 Docker
+
+Dockerfile 中的 module 引用从 `src.` 改为 `deerflow.` / `app.`，`COPY` 命令需覆盖 `packages/` 和 `app/` 目录。
+
+## 6. 实施计划
+
+分 3 个 PR 递进执行：
+
+### PR 1：提取共享工具函数（Low Risk）
+
+1. 创建 `src/skills/validation.py`，从 `gateway/routers/skills.py` 提取 `_validate_skill_frontmatter`
+2. 创建 `src/utils/file_conversion.py`，从 `gateway/routers/uploads.py` 提取文件转换逻辑
+3. 更新 `client.py`、`gateway/routers/skills.py`、`gateway/routers/uploads.py` 的 import
+4. 运行全部测试确认无回归
+
+### PR 2：Rename + 物理拆分（High Risk，原子操作）
+
+1. 创建 `packages/harness/` 目录，创建 `pyproject.toml`
+2. `git mv` 将 harness 相关模块从 `src/` 移入 `packages/harness/deerflow/`
+3. `git mv` 将 app 相关模块从 `src/` 移入 `app/`
+4. 全局替换 import：
+   - harness 模块：`src.*` → `deerflow.*`（所有 `.py` 文件、`langgraph.json`、测试、文档）
+   - app 模块：`src.gateway.*` → `app.gateway.*`、`src.channels.*` → `app.channels.*`
+5. 更新 workspace root `pyproject.toml`
+6. 更新 `langgraph.json`、`Makefile`、`Dockerfile`
+7. `uv sync` + 全部测试 + 手动验证服务启动
+
+### PR 3：边界检查 + 文档（Low Risk）
+
+1. 添加 lint 规则：检查 harness 不 import app 模块
+2. 更新 `CLAUDE.md`、`README.md`
+
+## 7. 风险与缓解
+
+| 风险 | 影响 | 缓解措施 |
+|------|------|----------|
+| 全局 rename 误伤 | 字符串中的 `src` 被错误替换 | 正则精确匹配 `\bsrc\.`，review diff |
+| LangGraph Server 找不到模块 | 服务启动失败 | `langgraph.json` 的 `dependencies` 指向正确的 harness 包路径 |
+| App 的 `PYTHONPATH` 缺失 | Gateway/Channel 启动 import 报错 | Makefile/Docker 统一设置 `PYTHONPATH=.` |
+| `config.yaml` 中的 `use` 字段引用旧路径 | 运行时模块解析失败 | `config.yaml` 中的 `use` 字段同步更新为 `deerflow.*` |
+| 测试中 `sys.path` 混乱 | 测试失败 | 用 editable install（`uv sync`）确保 deerflow 可导入，`conftest.py` 中添加 `app/` 到 `sys.path` |
+
+## 8. 未来演进
+
+- **独立发布**：harness 可以发布到内部 PyPI，让其他项目直接 `pip install deerflow-harness`
+- **插件化 App**：不同的 app（web、CLI、bot）可以各自独立，都依赖同一个 harness
+- **更细粒度拆分**：如果 harness 内部模块继续增长，可以进一步拆分（如 `deerflow-sandbox`、`deerflow-mcp`）

backend/docs/MCP_SERVER.md

@@ -45,41 +45,6 @@ Example:
 }
 ```
 
-## Custom Tool Interceptors
-
-You can register custom interceptors that run before every MCP tool call. This is useful for injecting per-request headers (e.g., user auth tokens from the LangGraph execution context), logging, or metrics.
-
-Declare interceptors in `extensions_config.json` using the `mcpInterceptors` field:
-
-```json
-{
-  "mcpInterceptors": [
-    "my_package.mcp.auth:build_auth_interceptor"
-  ],
-  "mcpServers": { ... }
-}
-```
-
-Each entry is a Python import path in `module:variable` format (resolved via `resolve_variable`). The variable must be a **no-arg builder function** that returns an async interceptor compatible with `MultiServerMCPClient`’s `tool_interceptors` interface, or `None` to skip.
-
-Example interceptor that injects auth headers from LangGraph metadata:
-
-```python
-def build_auth_interceptor():
-    async def interceptor(request, handler):
-        from langgraph.config import get_config
-        metadata = get_config().get("metadata", {})
-        headers = dict(request.headers or {})
-        if token := metadata.get("auth_token"):
-            headers["X-Auth-Token"] = token
-        return await handler(request.override(headers=headers))
-    return interceptor
-```
-
-- A single string value is accepted and normalized to a one-element list.
-- Invalid paths or builder failures are logged as warnings without blocking other interceptors.
-- The builder return value must be `callable`; non-callable values are skipped with a warning.
-
 ## How It Works
 
 MCP servers expose tools that are automatically discovered and integrated into DeerFlow’s agent system at runtime. Once enabled, these tools become available to agents without additional code changes.

backend/docs/SETUP.md

@@ -23,9 +23,6 @@ DeerFlow uses a YAML configuration file that should be placed in the **project r
    # Option A: Set environment variables (recommended)
    export OPENAI_API_KEY="your-key-here"
 
-   # Optional: pin the project root when running from another directory
-   export DEER_FLOW_PROJECT_ROOT="/path/to/deer-flow"
-
    # Option B: Edit config.yaml directly
    vim config.yaml  # or your preferred editor
    ```
@@ -38,20 +35,17 @@ DeerFlow uses a YAML configuration file that should be placed in the **project r
 
 ## Important Notes
 
-- **Location**: `config.yaml` should be in `deer-flow/` (project root)
+- **Location**: `config.yaml` should be in `deer-flow/` (project root), not `deer-flow/backend/`
 - **Git**: `config.yaml` is automatically ignored by git (contains secrets)
-- **Runtime root**: Set `DEER_FLOW_PROJECT_ROOT` if DeerFlow may start from outside the project root
-- **Runtime data**: State defaults to `.deer-flow` under the project root; set `DEER_FLOW_HOME` to move it
-- **Skills**: Skills default to `skills/` under the project root; set `DEER_FLOW_SKILLS_PATH` or `skills.path` to move them
+- **Priority**: If both `backend/config.yaml` and `../config.yaml` exist, backend version takes precedence
 
 ## Configuration File Locations
 
 The backend searches for `config.yaml` in this order:
 
-1. Explicit `config_path` argument from code
-2. `DEER_FLOW_CONFIG_PATH` environment variable (if set)
-3. `config.yaml` under `DEER_FLOW_PROJECT_ROOT`, or the current working directory when `DEER_FLOW_PROJECT_ROOT` is unset
-4. Legacy backend/repository-root locations for monorepo compatibility
+1. `DEER_FLOW_CONFIG_PATH` environment variable (if set)
+2. `backend/config.yaml` (current directory when running from backend/)
+3. `deer-flow/config.yaml` (parent directory - **recommended location**)
 
 **Recommended**: Place `config.yaml` in project root (`deer-flow/config.yaml`).
 
@@ -83,8 +77,8 @@ python -c "from deerflow.config.app_config import AppConfig; print(AppConfig.res
 
 If it can't find the config:
 1. Ensure you've copied `config.example.yaml` to `config.yaml`
-2. Verify you're in the project root, or set `DEER_FLOW_PROJECT_ROOT`
-3. Check the file exists: `ls -la config.yaml`
+2. Verify you're in the correct directory
+3. Check the file exists: `ls -la ../config.yaml`
 
 ### Permission denied
 
@@ -95,4 +89,4 @@ chmod 600 ../config.yaml  # Protect sensitive configuration
 ## See Also
 
 - [Configuration Guide](CONFIGURATION.md) - Detailed configuration options
-- [Architecture Overview](../CLAUDE.md) - System architecture
+- [Architecture Overview](../CLAUDE.md) - System architecture

backend/docs/TODO.md

@@ -11,7 +11,6 @@
 - [x] Add Plan Mode with TodoList middleware
 - [x] Add vision model support with ViewImageMiddleware
 - [x] Skills system with SKILL.md format
-- [x] Replace `time.sleep(5)` with `asyncio.sleep()` in `packages/harness/deerflow/tools/builtins/task_tool.py` (subagent polling)
 
 ## Planned Features
 
@@ -22,9 +21,10 @@
 - [ ] Support for more document formats in upload
 - [ ] Skill marketplace / remote skill installation
 - [ ] Optimize async concurrency in agent hot path (IM channels multi-task scenario)
-- [ ] Replace `subprocess.run()` with `asyncio.create_subprocess_shell()` in `packages/harness/deerflow/sandbox/local/local_sandbox.py`
+  - Replace `time.sleep(5)` with `asyncio.sleep()` in `packages/harness/deerflow/tools/builtins/task_tool.py` (subagent polling)
+  - Replace `subprocess.run()` with `asyncio.create_subprocess_shell()` in `packages/harness/deerflow/sandbox/local/local_sandbox.py`
   - Replace sync `requests` with `httpx.AsyncClient` in community tools (tavily, jina_ai, firecrawl, infoquest, image_search)
-  - [x] Replace sync `model.invoke()` with async `model.ainvoke()` in title_middleware and memory updater
+  - Replace sync `model.invoke()` with async `model.ainvoke()` in title_middleware and memory updater
   - Consider `asyncio.to_thread()` wrapper for remaining blocking file I/O
   - For production: use `langgraph up` (multi-worker) instead of `langgraph dev` (single-worker)
 

backend/docs/summarization.md

@@ -41,13 +41,6 @@ summarization:
 
   # Custom summary prompt (optional)
   summary_prompt: null
-
-  # Tool names treated as skill file reads for skill rescue
-  skill_file_read_tool_names:
-    - read_file
-    - read
-    - view
-    - cat
 ```
 
 ### Configuration Options
@@ -132,26 +125,6 @@ keep:
 - **Default**: `null` (uses LangChain's default prompt)
 - **Description**: Custom prompt template for generating summaries. The prompt should guide the model to extract the most important context.
 
-#### `preserve_recent_skill_count`
-- **Type**: Integer (≥ 0)
-- **Default**: `5`
-- **Description**: Number of most-recently-loaded skill files (tool results whose tool name is in `skill_file_read_tool_names` and whose target path is under `skills.container_path`, e.g. `/mnt/skills/...`) that are rescued from summarization. Prevents the agent from losing skill instructions after compression. Set to `0` to disable skill rescue entirely.
-
-#### `preserve_recent_skill_tokens`
-- **Type**: Integer (≥ 0)
-- **Default**: `25000`
-- **Description**: Total token budget reserved for rescued skill reads. Once this budget is exhausted, older skill bundles are allowed to be summarized.
-
-#### `preserve_recent_skill_tokens_per_skill`
-- **Type**: Integer (≥ 0)
-- **Default**: `5000`
-- **Description**: Per-skill token cap. Any individual skill read whose tool result exceeds this size is not rescued (it falls through to the summarizer like ordinary content).
-
-#### `skill_file_read_tool_names`
-- **Type**: List of strings
-- **Default**: `["read_file", "read", "view", "cat"]`
-- **Description**: Tool names treated as skill file reads during summarization rescue. A tool call is only eligible for skill rescue when its name appears in this list and its target path is under `skills.container_path`.
-
 **Default Prompt Behavior:**
 The default LangChain prompt instructs the model to:
 - Extract highest quality/most relevant context
@@ -174,7 +147,6 @@ The default LangChain prompt instructs the model to:
    - A single summary message is added
    - Recent messages are preserved
 6. **AI/Tool Pair Protection**: The system ensures AI messages and their corresponding tool messages stay together
-7. **Skill Rescue**: Before the summary is generated, the most recently loaded skill files (tool results whose tool name is in `skill_file_read_tool_names` and whose target path is under `skills.container_path`) are lifted out of the summarization set and prepended to the preserved tail. Selection walks newest-first under three budgets: `preserve_recent_skill_count`, `preserve_recent_skill_tokens`, and `preserve_recent_skill_tokens_per_skill`. The triggering AIMessage and all of its paired ToolMessages move together so tool_call ↔ tool_result pairing stays intact.
 
 ### Token Counting
 

backend/langgraph.json

@@ -12,6 +12,6 @@
     "path": "./app/gateway/langgraph_auth.py:auth"
   },
   "checkpointer": {
-    "path": "./packages/harness/deerflow/runtime/checkpointer/async_provider.py:make_checkpointer"
+    "path": "./packages/harness/deerflow/agents/checkpointer/async_provider.py:make_checkpointer"
   }
 }

backend/packages/harness/deerflow/agents/factory.py

@@ -254,11 +254,9 @@ def _assemble_from_features(
             from deerflow.agents.middlewares.view_image_middleware import ViewImageMiddleware
 
             chain.append(ViewImageMiddleware())
+        from deerflow.tools.builtins import view_image_tool
 
-        if feat.sandbox is not False:
-            from deerflow.tools.builtins import view_image_tool
-
-            extra_tools.append(view_image_tool)
+        extra_tools.append(view_image_tool)
 
     # --- [11] Subagent ---
     if feat.subagent is not False:

backend/packages/harness/deerflow/agents/lead_agent/agent.py

@@ -1,41 +1,31 @@
 import logging
 
 from langchain.agents import create_agent
-from langchain.agents.middleware import AgentMiddleware
+from langchain.agents.middleware import AgentMiddleware, SummarizationMiddleware
 from langchain_core.runnables import RunnableConfig
 
 from deerflow.agents.lead_agent.prompt import apply_prompt_template
-from deerflow.agents.memory.summarization_hook import memory_flush_hook
 from deerflow.agents.middlewares.clarification_middleware import ClarificationMiddleware
 from deerflow.agents.middlewares.loop_detection_middleware import LoopDetectionMiddleware
 from deerflow.agents.middlewares.memory_middleware import MemoryMiddleware
 from deerflow.agents.middlewares.subagent_limit_middleware import SubagentLimitMiddleware
-from deerflow.agents.middlewares.summarization_middleware import BeforeSummarizationHook, DeerFlowSummarizationMiddleware
 from deerflow.agents.middlewares.title_middleware import TitleMiddleware
 from deerflow.agents.middlewares.todo_middleware import TodoMiddleware
 from deerflow.agents.middlewares.token_usage_middleware import TokenUsageMiddleware
 from deerflow.agents.middlewares.tool_error_handling_middleware import build_lead_runtime_middlewares
 from deerflow.agents.middlewares.view_image_middleware import ViewImageMiddleware
 from deerflow.agents.thread_state import ThreadState
-from deerflow.config.agents_config import load_agent_config, validate_agent_name
-from deerflow.config.app_config import AppConfig, get_app_config
+from deerflow.config.agents_config import load_agent_config
+from deerflow.config.app_config import get_app_config
+from deerflow.config.summarization_config import get_summarization_config
 from deerflow.models import create_chat_model
 
 logger = logging.getLogger(__name__)
 
 
-def _get_runtime_config(config: RunnableConfig) -> dict:
-    """Merge legacy configurable options with LangGraph runtime context."""
-    cfg = dict(config.get("configurable", {}) or {})
-    context = config.get("context", {}) or {}
-    if isinstance(context, dict):
-        cfg.update(context)
-    return cfg
-
-
-def _resolve_model_name(requested_model_name: str | None = None, *, app_config: AppConfig | None = None) -> str:
+def _resolve_model_name(requested_model_name: str | None = None) -> str:
     """Resolve a runtime model name safely, falling back to default if invalid. Returns None if no models are configured."""
-    app_config = app_config or get_app_config()
+    app_config = get_app_config()
     default_model_name = app_config.models[0].name if app_config.models else None
     if default_model_name is None:
         raise ValueError("No chat models are configured. Please configure at least one model in config.yaml.")
@@ -48,10 +38,9 @@ def _resolve_model_name(requested_model_name: str | None = None, *, app_config:
     return default_model_name
 
 
-def _create_summarization_middleware(*, app_config: AppConfig | None = None) -> DeerFlowSummarizationMiddleware | None:
+def _create_summarization_middleware() -> SummarizationMiddleware | None:
     """Create and configure the summarization middleware from config."""
-    resolved_app_config = app_config or get_app_config()
-    config = resolved_app_config.summarization
+    config = get_summarization_config()
 
     if not config.enabled:
         return None
@@ -72,9 +61,9 @@ def _create_summarization_middleware(*, app_config: AppConfig | None = None) ->
     # as middleware rather than lead_agent (SummarizationMiddleware is a
     # LangChain built-in, so we tag the model at creation time).
     if config.model_name:
-        model = create_chat_model(name=config.model_name, thinking_enabled=False, app_config=resolved_app_config)
+        model = create_chat_model(name=config.model_name, thinking_enabled=False)
     else:
-        model = create_chat_model(thinking_enabled=False, app_config=resolved_app_config)
+        model = create_chat_model(thinking_enabled=False)
     model = model.with_config(tags=["middleware:summarize"])
 
     # Prepare kwargs
@@ -90,24 +79,7 @@ def _create_summarization_middleware(*, app_config: AppConfig | None = None) ->
     if config.summary_prompt is not None:
         kwargs["summary_prompt"] = config.summary_prompt
 
-    hooks: list[BeforeSummarizationHook] = []
-    if resolved_app_config.memory.enabled:
-        hooks.append(memory_flush_hook)
-
-    # The logic below relies on two assumptions holding true: this factory is
-    # the sole entry point for DeerFlowSummarizationMiddleware, and the runtime
-    # config is not expected to change after startup.
-    skills_container_path = resolved_app_config.skills.container_path or "/mnt/skills"
-
-    return DeerFlowSummarizationMiddleware(
-        **kwargs,
-        skills_container_path=skills_container_path,
-        skill_file_read_tool_names=config.skill_file_read_tool_names,
-        before_summarization=hooks,
-        preserve_recent_skill_count=config.preserve_recent_skill_count,
-        preserve_recent_skill_tokens=config.preserve_recent_skill_tokens,
-        preserve_recent_skill_tokens_per_skill=config.preserve_recent_skill_tokens_per_skill,
-    )
+    return SummarizationMiddleware(**kwargs)
 
 
 def _create_todo_list_middleware(is_plan_mode: bool) -> TodoMiddleware | None:
@@ -235,14 +207,7 @@ Being proactive with task management demonstrates thoroughness and ensures all r
 # ViewImageMiddleware should be before ClarificationMiddleware to inject image details before LLM
 # ToolErrorHandlingMiddleware should be before ClarificationMiddleware to convert tool exceptions to ToolMessages
 # ClarificationMiddleware should be last to intercept clarification requests after model calls
-def _build_middlewares(
-    config: RunnableConfig,
-    model_name: str | None,
-    agent_name: str | None = None,
-    custom_middlewares: list[AgentMiddleware] | None = None,
-    *,
-    app_config: AppConfig | None = None,
-):
+def _build_middlewares(config: RunnableConfig, model_name: str | None, agent_name: str | None = None, custom_middlewares: list[AgentMiddleware] | None = None):
     """Build middleware chain based on runtime configuration.
 
     Args:
@@ -253,47 +218,46 @@ def _build_middlewares(
     Returns:
         List of middleware instances.
     """
-    resolved_app_config = app_config or get_app_config()
-    middlewares = build_lead_runtime_middlewares(app_config=resolved_app_config, lazy_init=True)
+    middlewares = build_lead_runtime_middlewares(lazy_init=True)
 
     # Add summarization middleware if enabled
-    summarization_middleware = _create_summarization_middleware(app_config=resolved_app_config)
+    summarization_middleware = _create_summarization_middleware()
     if summarization_middleware is not None:
         middlewares.append(summarization_middleware)
 
     # Add TodoList middleware if plan mode is enabled
-    cfg = _get_runtime_config(config)
-    is_plan_mode = cfg.get("is_plan_mode", False)
+    is_plan_mode = config.get("configurable", {}).get("is_plan_mode", False)
     todo_list_middleware = _create_todo_list_middleware(is_plan_mode)
     if todo_list_middleware is not None:
         middlewares.append(todo_list_middleware)
 
     # Add TokenUsageMiddleware when token_usage tracking is enabled
-    if resolved_app_config.token_usage.enabled:
+    if get_app_config().token_usage.enabled:
         middlewares.append(TokenUsageMiddleware())
 
     # Add TitleMiddleware
-    middlewares.append(TitleMiddleware(app_config=resolved_app_config))
+    middlewares.append(TitleMiddleware())
 
     # Add MemoryMiddleware (after TitleMiddleware)
-    middlewares.append(MemoryMiddleware(agent_name=agent_name, memory_config=resolved_app_config.memory))
+    middlewares.append(MemoryMiddleware(agent_name=agent_name))
 
     # Add ViewImageMiddleware only if the current model supports vision.
     # Use the resolved runtime model_name from make_lead_agent to avoid stale config values.
-    model_config = resolved_app_config.get_model_config(model_name) if model_name else None
+    app_config = get_app_config()
+    model_config = app_config.get_model_config(model_name) if model_name else None
     if model_config is not None and model_config.supports_vision:
         middlewares.append(ViewImageMiddleware())
 
     # Add DeferredToolFilterMiddleware to hide deferred tool schemas from model binding
-    if resolved_app_config.tool_search.enabled:
+    if app_config.tool_search.enabled:
         from deerflow.agents.middlewares.deferred_tool_filter_middleware import DeferredToolFilterMiddleware
 
         middlewares.append(DeferredToolFilterMiddleware())
 
     # Add SubagentLimitMiddleware to truncate excess parallel task calls
-    subagent_enabled = cfg.get("subagent_enabled", False)
+    subagent_enabled = config.get("configurable", {}).get("subagent_enabled", False)
     if subagent_enabled:
-        max_concurrent_subagents = cfg.get("max_concurrent_subagents", 3)
+        max_concurrent_subagents = config.get("configurable", {}).get("max_concurrent_subagents", 3)
         middlewares.append(SubagentLimitMiddleware(max_concurrent=max_concurrent_subagents))
 
     # LoopDetectionMiddleware — detect and break repetitive tool call loops
@@ -309,19 +273,11 @@ def _build_middlewares(
 
 
 def make_lead_agent(config: RunnableConfig):
-    """LangGraph graph factory; keep the signature compatible with LangGraph Server."""
-    runtime_config = _get_runtime_config(config)
-    runtime_app_config = runtime_config.get("app_config")
-    return _make_lead_agent(config, app_config=runtime_app_config or get_app_config())
-
-
-def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
     # Lazy import to avoid circular dependency
     from deerflow.tools import get_available_tools
     from deerflow.tools.builtins import setup_agent
 
-    cfg = _get_runtime_config(config)
-    resolved_app_config = app_config
+    cfg = config.get("configurable", {})
 
     thinking_enabled = cfg.get("thinking_enabled", True)
     reasoning_effort = cfg.get("reasoning_effort", None)
@@ -330,16 +286,17 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
     subagent_enabled = cfg.get("subagent_enabled", False)
     max_concurrent_subagents = cfg.get("max_concurrent_subagents", 3)
     is_bootstrap = cfg.get("is_bootstrap", False)
-    agent_name = validate_agent_name(cfg.get("agent_name"))
+    agent_name = cfg.get("agent_name")
 
     agent_config = load_agent_config(agent_name) if not is_bootstrap else None
     # Custom agent model from agent config (if any), or None to let _resolve_model_name pick the default
     agent_model_name = agent_config.model if agent_config and agent_config.model else None
 
     # Final model name resolution: request → agent config → global default, with fallback for unknown names
-    model_name = _resolve_model_name(requested_model_name or agent_model_name, app_config=resolved_app_config)
+    model_name = _resolve_model_name(requested_model_name or agent_model_name)
 
-    model_config = resolved_app_config.get_model_config(model_name)
+    app_config = get_app_config()
+    model_config = app_config.get_model_config(model_name)
 
     if model_config is None:
         raise ValueError("No chat model could be resolved. Please configure at least one model in config.yaml or provide a valid 'model_name'/'model' in the request.")
@@ -370,42 +327,26 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
             "reasoning_effort": reasoning_effort,
             "is_plan_mode": is_plan_mode,
             "subagent_enabled": subagent_enabled,
-            "tool_groups": agent_config.tool_groups if agent_config else None,
-            "available_skills": ["bootstrap"] if is_bootstrap else (agent_config.skills if agent_config and agent_config.skills is not None else None),
         }
     )
 
     if is_bootstrap:
         # Special bootstrap agent with minimal prompt for initial custom agent creation flow
         return create_agent(
-            model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, app_config=resolved_app_config),
-            tools=get_available_tools(model_name=model_name, subagent_enabled=subagent_enabled, app_config=resolved_app_config) + [setup_agent],
-            middleware=_build_middlewares(config, model_name=model_name, app_config=resolved_app_config),
-            system_prompt=apply_prompt_template(
-                subagent_enabled=subagent_enabled,
-                max_concurrent_subagents=max_concurrent_subagents,
-                available_skills=set(["bootstrap"]),
-                app_config=resolved_app_config,
-            ),
+            model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled),
+            tools=get_available_tools(model_name=model_name, subagent_enabled=subagent_enabled) + [setup_agent],
+            middleware=_build_middlewares(config, model_name=model_name),
+            system_prompt=apply_prompt_template(subagent_enabled=subagent_enabled, max_concurrent_subagents=max_concurrent_subagents, available_skills=set(["bootstrap"])),
             state_schema=ThreadState,
         )
 
     # Default lead agent (unchanged behavior)
     return create_agent(
-        model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, reasoning_effort=reasoning_effort, app_config=resolved_app_config),
-        tools=get_available_tools(
-            model_name=model_name,
-            groups=agent_config.tool_groups if agent_config else None,
-            subagent_enabled=subagent_enabled,
-            app_config=resolved_app_config,
-        ),
-        middleware=_build_middlewares(config, model_name=model_name, agent_name=agent_name, app_config=resolved_app_config),
+        model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, reasoning_effort=reasoning_effort),
+        tools=get_available_tools(model_name=model_name, groups=agent_config.tool_groups if agent_config else None, subagent_enabled=subagent_enabled),
+        middleware=_build_middlewares(config, model_name=model_name, agent_name=agent_name),
         system_prompt=apply_prompt_template(
-            subagent_enabled=subagent_enabled,
-            max_concurrent_subagents=max_concurrent_subagents,
-            agent_name=agent_name,
-            available_skills=set(agent_config.skills) if agent_config and agent_config.skills is not None else None,
-            app_config=resolved_app_config,
+            subagent_enabled=subagent_enabled, max_concurrent_subagents=max_concurrent_subagents, agent_name=agent_name, available_skills=set(agent_config.skills) if agent_config and agent_config.skills is not None else None
         ),
         state_schema=ThreadState,
     )

backend/packages/harness/deerflow/agents/lead_agent/prompt.py

@@ -1,20 +1,14 @@
-from __future__ import annotations
-
 import asyncio
 import logging
 import threading
 from datetime import datetime
 from functools import lru_cache
-from typing import TYPE_CHECKING
 
 from deerflow.config.agents_config import load_agent_soul
-from deerflow.skills.storage import get_or_new_skill_storage
-from deerflow.skills.types import Skill, SkillCategory
+from deerflow.skills import load_skills
+from deerflow.skills.types import Skill
 from deerflow.subagents import get_available_subagent_names
 
-if TYPE_CHECKING:
-    from deerflow.config.app_config import AppConfig
-
 logger = logging.getLogger(__name__)
 
 _ENABLED_SKILLS_REFRESH_WAIT_TIMEOUT_SECONDS = 5.0
@@ -26,7 +20,7 @@ _enabled_skills_refresh_event = threading.Event()
 
 
 def _load_enabled_skills_sync() -> list[Skill]:
-    return list(get_or_new_skill_storage().load_skills(enabled_only=True))
+    return list(load_skills(enabled_only=True))
 
 
 def _start_enabled_skills_refresh_thread() -> None:
@@ -117,21 +111,8 @@ def _get_enabled_skills():
     return []
 
 
-def _get_enabled_skills_for_config(app_config: AppConfig | None = None) -> list[Skill]:
-    """Return enabled skills using the caller's config source.
-
-    When a concrete ``app_config`` is supplied, bypass the global enabled-skills
-    cache so the skill list and skill paths are resolved from the same config
-    object. This keeps request-scoped config injection consistent even while the
-    release branch still supports global fallback paths.
-    """
-    if app_config is None:
-        return _get_enabled_skills()
-    return list(get_or_new_skill_storage(app_config=app_config).load_skills(enabled_only=True))
-
-
-def _skill_mutability_label(category: SkillCategory | str) -> str:
-    return "[custom, editable]" if category == SkillCategory.CUSTOM else "[built-in]"
+def _skill_mutability_label(category: str) -> str:
+    return "[custom, editable]" if category == "custom" else "[built-in]"
 
 
 def clear_skills_system_prompt_cache() -> None:
@@ -142,6 +123,31 @@ async def refresh_skills_system_prompt_cache_async() -> None:
     await asyncio.to_thread(_invalidate_enabled_skills_cache().wait)
 
 
+def _reset_skills_system_prompt_cache_state() -> None:
+    global _enabled_skills_cache, _enabled_skills_refresh_active, _enabled_skills_refresh_version
+
+    _get_cached_skills_prompt_section.cache_clear()
+    with _enabled_skills_lock:
+        _enabled_skills_cache = None
+        _enabled_skills_refresh_active = False
+        _enabled_skills_refresh_version = 0
+        _enabled_skills_refresh_event.clear()
+
+
+def _refresh_enabled_skills_cache() -> None:
+    """Backward-compatible test helper for direct synchronous reload."""
+    try:
+        skills = _load_enabled_skills_sync()
+    except Exception:
+        logger.exception("Failed to load enabled skills for prompt injection")
+        skills = []
+
+    with _enabled_skills_lock:
+        _enabled_skills_cache = skills
+        _enabled_skills_refresh_active = False
+        _enabled_skills_refresh_event.set()
+
+
 def _build_skill_evolution_section(skill_evolution_enabled: bool) -> str:
     if not skill_evolution_enabled:
         return ""
@@ -158,37 +164,7 @@ Skip simple one-off tasks.
 """
 
 
-def _build_available_subagents_description(available_names: list[str], bash_available: bool, *, app_config: AppConfig | None = None) -> str:
-    """Dynamically build subagent type descriptions from registry.
-
-    Mirrors Codex's pattern where agent_type_description is dynamically generated
-    from all registered roles, so the LLM knows about every available type.
-    """
-    # Built-in descriptions (kept for backward compatibility with existing prompt quality)
-    builtin_descriptions = {
-        "general-purpose": "For ANY non-trivial task - web research, code exploration, file operations, analysis, etc.",
-        "bash": (
-            "For command execution (git, build, test, deploy operations)" if bash_available else "Not available in the current sandbox configuration. Use direct file/web tools or switch to AioSandboxProvider for isolated shell access."
-        ),
-    }
-
-    # Lazy import moved outside loop to avoid repeated import overhead
-    from deerflow.subagents.registry import get_subagent_config
-
-    lines = []
-    for name in available_names:
-        if name in builtin_descriptions:
-            lines.append(f"- **{name}**: {builtin_descriptions[name]}")
-        else:
-            config = get_subagent_config(name, app_config=app_config)
-            if config is not None:
-                desc = config.description.split("\n")[0].strip()  # First line only for brevity
-                lines.append(f"- **{name}**: {desc}")
-
-    return "\n".join(lines)
-
-
-def _build_subagent_section(max_concurrent: int, *, app_config: AppConfig | None = None) -> str:
+def _build_subagent_section(max_concurrent: int) -> str:
     """Build the subagent system prompt section with dynamic concurrency limit.
 
     Args:
@@ -198,12 +174,13 @@ def _build_subagent_section(max_concurrent: int, *, app_config: AppConfig | None
         Formatted subagent section string.
     """
     n = max_concurrent
-    available_names = get_available_subagent_names(app_config=app_config) if app_config is not None else get_available_subagent_names()
-    bash_available = "bash" in available_names
-
-    # Dynamically build subagent type descriptions from registry (aligned with Codex's
-    # agent_type_description pattern where all registered roles are listed in the tool spec).
-    available_subagents = _build_available_subagents_description(available_names, bash_available, app_config=app_config)
+    bash_available = "bash" in get_available_subagent_names()
+    available_subagents = (
+        "- **general-purpose**: For ANY non-trivial task - web research, code exploration, file operations, analysis, etc.\n- **bash**: For command execution (git, build, test, deploy operations)"
+        if bash_available
+        else "- **general-purpose**: For ANY non-trivial task - web research, code exploration, file operations, analysis, etc.\n"
+        "- **bash**: Not available in the current sandbox configuration. Use direct file/web tools or switch to AioSandboxProvider for isolated shell access."
+    )
     direct_tool_examples = "bash, ls, read_file, web_search, etc." if bash_available else "ls, read_file, web_search, etc."
     direct_execution_example = (
         '# User asks: "Run the tests"\n# Thinking: Cannot decompose into parallel sub-tasks\n# → Execute directly\n\nbash("npm test")  # Direct execution, not task()'
@@ -443,7 +420,7 @@ You: "Deploying to staging..." [proceed]
 - Treat `/mnt/user-data/workspace` as your default current working directory for coding and file-editing tasks
 - When writing scripts or commands that create/read files from the workspace, prefer relative paths such as `hello.txt`, `../uploads/data.csv`, and `../outputs/report.md`
 - Avoid hardcoding `/mnt/user-data/...` inside generated scripts when a relative path from the workspace is enough
-- Final deliverables must be copied to `/mnt/user-data/outputs` and presented using `present_files` tool
+- Final deliverables must be copied to `/mnt/user-data/outputs` and presented using `present_file` tool
 {acp_section}
 </working_directory>
 
@@ -530,28 +507,21 @@ combined with a FastAPI gateway for REST API access [citation:FastAPI](https://f
 """
 
 
-def _get_memory_context(agent_name: str | None = None, *, app_config: AppConfig | None = None) -> str:
+def _get_memory_context(agent_name: str | None = None) -> str:
     """Get memory context for injection into system prompt.
 
     Args:
         agent_name: If provided, loads per-agent memory. If None, loads global memory.
-        app_config: Explicit application config. When provided, memory options
-            are read from this value instead of the global config singleton.
 
     Returns:
         Formatted memory context string wrapped in XML tags, or empty string if disabled.
     """
     try:
         from deerflow.agents.memory import format_memory_for_injection, get_memory_data
+        from deerflow.config.memory_config import get_memory_config
         from deerflow.runtime.user_context import get_effective_user_id
 
-        if app_config is None:
-            from deerflow.config.memory_config import get_memory_config
-
-            config = get_memory_config()
-        else:
-            config = app_config.memory
-
+        config = get_memory_config()
         if not config.enabled or not config.injection_enabled:
             return ""
 
@@ -565,8 +535,8 @@ def _get_memory_context(agent_name: str | None = None, *, app_config: AppConfig
 {memory_content}
 </memory>
 """
-    except Exception:
-        logger.exception("Failed to load memory context")
+    except Exception as e:
+        logger.error("Failed to load memory context: %s", e)
         return ""
 
 
@@ -602,24 +572,19 @@ You have access to skills that provide optimized workflows for specific tasks. E
 </skill_system>"""
 
 
-def get_skills_prompt_section(available_skills: set[str] | None = None, *, app_config: AppConfig | None = None) -> str:
+def get_skills_prompt_section(available_skills: set[str] | None = None) -> str:
     """Generate the skills prompt section with available skills list."""
-    skills = _get_enabled_skills_for_config(app_config)
+    skills = _get_enabled_skills()
 
-    if app_config is None:
-        try:
-            from deerflow.config import get_app_config
+    try:
+        from deerflow.config import get_app_config
 
-            config = get_app_config()
-            container_base_path = config.skills.container_path
-            skill_evolution_enabled = config.skill_evolution.enabled
-        except Exception:
-            container_base_path = "/mnt/skills"
-            skill_evolution_enabled = False
-    else:
-        config = app_config
+        config = get_app_config()
         container_base_path = config.skills.container_path
         skill_evolution_enabled = config.skill_evolution.enabled
+    except Exception:
+        container_base_path = "/mnt/skills"
+        skill_evolution_enabled = False
 
     if not skills and not skill_evolution_enabled:
         return ""
@@ -643,7 +608,7 @@ def get_agent_soul(agent_name: str | None) -> str:
     return ""
 
 
-def get_deferred_tools_prompt_section(*, app_config: AppConfig | None = None) -> str:
+def get_deferred_tools_prompt_section() -> str:
     """Generate <available-deferred-tools> block for the system prompt.
 
     Lists only deferred tool names so the agent knows what exists
@@ -652,17 +617,12 @@ def get_deferred_tools_prompt_section(*, app_config: AppConfig | None = None) ->
     """
     from deerflow.tools.builtins.tool_search import get_deferred_registry
 
-    if app_config is None:
-        try:
-            from deerflow.config import get_app_config
+    try:
+        from deerflow.config import get_app_config
 
-            config = get_app_config()
-        except Exception:
+        if not get_app_config().tool_search.enabled:
             return ""
-    else:
-        config = app_config
-
-    if not config.tool_search.enabled:
+    except Exception:
         return ""
 
     registry = get_deferred_registry()
@@ -673,19 +633,15 @@ def get_deferred_tools_prompt_section(*, app_config: AppConfig | None = None) ->
     return f"<available-deferred-tools>\n{names}\n</available-deferred-tools>"
 
 
-def _build_acp_section(*, app_config: AppConfig | None = None) -> str:
+def _build_acp_section() -> str:
     """Build the ACP agent prompt section, only if ACP agents are configured."""
-    if app_config is None:
-        try:
-            from deerflow.config.acp_config import get_acp_agents
+    try:
+        from deerflow.config.acp_config import get_acp_agents
 
-            agents = get_acp_agents()
-        except Exception:
+        agents = get_acp_agents()
+        if not agents:
             return ""
-    else:
-        agents = getattr(app_config, "acp_agents", {}) or {}
-
-    if not agents:
+    except Exception:
         return ""
 
     return (
@@ -693,24 +649,19 @@ def _build_acp_section(*, app_config: AppConfig | None = None) -> str:
         "- ACP agents (e.g. codex, claude_code) run in their own independent workspace — NOT in `/mnt/user-data/`\n"
         "- When writing prompts for ACP agents, describe the task only — do NOT reference `/mnt/user-data` paths\n"
         "- ACP agent results are accessible at `/mnt/acp-workspace/` (read-only) — use `ls`, `read_file`, or `bash cp` to retrieve output files\n"
-        "- To deliver ACP output to the user: copy from `/mnt/acp-workspace/<file>` to `/mnt/user-data/outputs/<file>`, then use `present_files`"
+        "- To deliver ACP output to the user: copy from `/mnt/acp-workspace/<file>` to `/mnt/user-data/outputs/<file>`, then use `present_file`"
     )
 
 
-def _build_custom_mounts_section(*, app_config: AppConfig | None = None) -> str:
+def _build_custom_mounts_section() -> str:
     """Build a prompt section for explicitly configured sandbox mounts."""
-    if app_config is None:
-        try:
-            from deerflow.config import get_app_config
+    try:
+        from deerflow.config import get_app_config
 
-            config = get_app_config()
-        except Exception:
-            logger.exception("Failed to load configured sandbox mounts for the lead-agent prompt")
-            return ""
-    else:
-        config = app_config
-
-    mounts = config.sandbox.mounts or []
+        mounts = get_app_config().sandbox.mounts or []
+    except Exception:
+        logger.exception("Failed to load configured sandbox mounts for the lead-agent prompt")
+        return ""
 
     if not mounts:
         return ""
@@ -724,20 +675,13 @@ def _build_custom_mounts_section(*, app_config: AppConfig | None = None) -> str:
     return f"\n**Custom Mounted Directories:**\n{mounts_list}\n- If the user needs files outside `/mnt/user-data`, use these absolute container paths directly when they match the requested directory"
 
 
-def apply_prompt_template(
-    subagent_enabled: bool = False,
-    max_concurrent_subagents: int = 3,
-    *,
-    agent_name: str | None = None,
-    available_skills: set[str] | None = None,
-    app_config: AppConfig | None = None,
-) -> str:
+def apply_prompt_template(subagent_enabled: bool = False, max_concurrent_subagents: int = 3, *, agent_name: str | None = None, available_skills: set[str] | None = None) -> str:
     # Get memory context
-    memory_context = _get_memory_context(agent_name, app_config=app_config)
+    memory_context = _get_memory_context(agent_name)
 
     # Include subagent section only if enabled (from runtime parameter)
     n = max_concurrent_subagents
-    subagent_section = _build_subagent_section(n, app_config=app_config) if subagent_enabled else ""
+    subagent_section = _build_subagent_section(n) if subagent_enabled else ""
 
     # Add subagent reminder to critical_reminders if enabled
     subagent_reminder = (
@@ -758,14 +702,14 @@ def apply_prompt_template(
     )
 
     # Get skills section
-    skills_section = get_skills_prompt_section(available_skills, app_config=app_config)
+    skills_section = get_skills_prompt_section(available_skills)
 
     # Get deferred tools section (tool_search)
-    deferred_tools_section = get_deferred_tools_prompt_section(app_config=app_config)
+    deferred_tools_section = get_deferred_tools_prompt_section()
 
     # Build ACP agent section only if ACP agents are configured
-    acp_section = _build_acp_section(app_config=app_config)
-    custom_mounts_section = _build_custom_mounts_section(app_config=app_config)
+    acp_section = _build_acp_section()
+    custom_mounts_section = _build_custom_mounts_section()
     acp_and_mounts_section = "\n".join(section for section in (acp_section, custom_mounts_section) if section)
 
     # Format the prompt with dynamic skills and memory

backend/packages/harness/deerflow/agents/memory/message_processing.py

@@ -1,109 +0,0 @@
-"""Shared helpers for turning conversations into memory update inputs."""
-
-from __future__ import annotations
-
-import re
-from copy import copy
-from typing import Any
-
-_UPLOAD_BLOCK_RE = re.compile(r"<uploaded_files>[\s\S]*?</uploaded_files>\n*", re.IGNORECASE)
-_CORRECTION_PATTERNS = (
-    re.compile(r"\bthat(?:'s| is) (?:wrong|incorrect)\b", re.IGNORECASE),
-    re.compile(r"\byou misunderstood\b", re.IGNORECASE),
-    re.compile(r"\btry again\b", re.IGNORECASE),
-    re.compile(r"\bredo\b", re.IGNORECASE),
-    re.compile(r"不对"),
-    re.compile(r"你理解错了"),
-    re.compile(r"你理解有误"),
-    re.compile(r"重试"),
-    re.compile(r"重新来"),
-    re.compile(r"换一种"),
-    re.compile(r"改用"),
-)
-_REINFORCEMENT_PATTERNS = (
-    re.compile(r"\byes[,.]?\s+(?:exactly|perfect|that(?:'s| is) (?:right|correct|it))\b", re.IGNORECASE),
-    re.compile(r"\bperfect(?:[.!?]|$)", re.IGNORECASE),
-    re.compile(r"\bexactly\s+(?:right|correct)\b", re.IGNORECASE),
-    re.compile(r"\bthat(?:'s| is)\s+(?:exactly\s+)?(?:right|correct|what i (?:wanted|needed|meant))\b", re.IGNORECASE),
-    re.compile(r"\bkeep\s+(?:doing\s+)?that\b", re.IGNORECASE),
-    re.compile(r"\bjust\s+(?:like\s+)?(?:that|this)\b", re.IGNORECASE),
-    re.compile(r"\bthis is (?:great|helpful)\b(?:[.!?]|$)", re.IGNORECASE),
-    re.compile(r"\bthis is what i wanted\b(?:[.!?]|$)", re.IGNORECASE),
-    re.compile(r"对[，,]?\s*就是这样(?:[。！？!?.]|$)"),
-    re.compile(r"完全正确(?:[。！？!?.]|$)"),
-    re.compile(r"(?:对[，,]?\s*)?就是这个意思(?:[。！？!?.]|$)"),
-    re.compile(r"正是我想要的(?:[。！？!?.]|$)"),
-    re.compile(r"继续保持(?:[。！？!?.]|$)"),
-)
-
-
-def extract_message_text(message: Any) -> str:
-    """Extract plain text from message content for filtering and signal detection."""
-    content = getattr(message, "content", "")
-    if isinstance(content, list):
-        text_parts: list[str] = []
-        for part in content:
-            if isinstance(part, str):
-                text_parts.append(part)
-            elif isinstance(part, dict):
-                text_val = part.get("text")
-                if isinstance(text_val, str):
-                    text_parts.append(text_val)
-        return " ".join(text_parts)
-    return str(content)
-
-
-def filter_messages_for_memory(messages: list[Any]) -> list[Any]:
-    """Keep only user inputs and final assistant responses for memory updates."""
-    filtered = []
-    skip_next_ai = False
-    for msg in messages:
-        msg_type = getattr(msg, "type", None)
-
-        if msg_type == "human":
-            content_str = extract_message_text(msg)
-            if "<uploaded_files>" in content_str:
-                stripped = _UPLOAD_BLOCK_RE.sub("", content_str).strip()
-                if not stripped:
-                    skip_next_ai = True
-                    continue
-                clean_msg = copy(msg)
-                clean_msg.content = stripped
-                filtered.append(clean_msg)
-                skip_next_ai = False
-            else:
-                filtered.append(msg)
-                skip_next_ai = False
-        elif msg_type == "ai":
-            tool_calls = getattr(msg, "tool_calls", None)
-            if not tool_calls:
-                if skip_next_ai:
-                    skip_next_ai = False
-                    continue
-                filtered.append(msg)
-
-    return filtered
-
-
-def detect_correction(messages: list[Any]) -> bool:
-    """Detect explicit user corrections in recent conversation turns."""
-    recent_user_msgs = [msg for msg in messages[-6:] if getattr(msg, "type", None) == "human"]
-
-    for msg in recent_user_msgs:
-        content = extract_message_text(msg).strip()
-        if content and any(pattern.search(content) for pattern in _CORRECTION_PATTERNS):
-            return True
-
-    return False
-
-
-def detect_reinforcement(messages: list[Any]) -> bool:
-    """Detect explicit positive reinforcement signals in recent conversation turns."""
-    recent_user_msgs = [msg for msg in messages[-6:] if getattr(msg, "type", None) == "human"]
-
-    for msg in recent_user_msgs:
-        content = extract_message_text(msg).strip()
-        if content and any(pattern.search(content) for pattern in _REINFORCEMENT_PATTERNS):
-            return True
-
-    return False

backend/packages/harness/deerflow/agents/memory/queue.py

@@ -66,93 +66,49 @@ class MemoryUpdateQueue:
             return
 
         with self._lock:
-            self._enqueue_locked(
+            existing_context = next(
+                (context for context in self._queue if context.thread_id == thread_id),
+                None,
+            )
+            merged_correction_detected = correction_detected or (existing_context.correction_detected if existing_context is not None else False)
+            merged_reinforcement_detected = reinforcement_detected or (existing_context.reinforcement_detected if existing_context is not None else False)
+            context = ConversationContext(
                 thread_id=thread_id,
                 messages=messages,
                 agent_name=agent_name,
                 user_id=user_id,
-                correction_detected=correction_detected,
-                reinforcement_detected=reinforcement_detected,
+                correction_detected=merged_correction_detected,
+                reinforcement_detected=merged_reinforcement_detected,
             )
+
+            # Check if this thread already has a pending update
+            # If so, replace it with the newer one
+            self._queue = [c for c in self._queue if c.thread_id != thread_id]
+            self._queue.append(context)
+
+            # Reset or start the debounce timer
             self._reset_timer()
 
         logger.info("Memory update queued for thread %s, queue size: %d", thread_id, len(self._queue))
 
-    def add_nowait(
-        self,
-        thread_id: str,
-        messages: list[Any],
-        agent_name: str | None = None,
-        user_id: str | None = None,
-        correction_detected: bool = False,
-        reinforcement_detected: bool = False,
-    ) -> None:
-        """Add a conversation and start processing immediately in the background."""
-        config = get_memory_config()
-        if not config.enabled:
-            return
-
-        with self._lock:
-            self._enqueue_locked(
-                thread_id=thread_id,
-                messages=messages,
-                agent_name=agent_name,
-                user_id=user_id,
-                correction_detected=correction_detected,
-                reinforcement_detected=reinforcement_detected,
-            )
-            self._schedule_timer(0)
-
-        logger.info("Memory update queued for immediate processing on thread %s, queue size: %d", thread_id, len(self._queue))
-
-    def _enqueue_locked(
-        self,
-        *,
-        thread_id: str,
-        messages: list[Any],
-        agent_name: str | None,
-        user_id: str | None,
-        correction_detected: bool,
-        reinforcement_detected: bool,
-    ) -> None:
-        existing_context = next(
-            (context for context in self._queue if context.thread_id == thread_id),
-            None,
-        )
-        merged_correction_detected = correction_detected or (existing_context.correction_detected if existing_context is not None else False)
-        merged_reinforcement_detected = reinforcement_detected or (existing_context.reinforcement_detected if existing_context is not None else False)
-        context = ConversationContext(
-            thread_id=thread_id,
-            messages=messages,
-            agent_name=agent_name,
-            user_id=user_id,
-            correction_detected=merged_correction_detected,
-            reinforcement_detected=merged_reinforcement_detected,
-        )
-
-        self._queue = [c for c in self._queue if c.thread_id != thread_id]
-        self._queue.append(context)
-
     def _reset_timer(self) -> None:
         """Reset the debounce timer."""
         config = get_memory_config()
-        self._schedule_timer(config.debounce_seconds)
 
-        logger.debug("Memory update timer set for %ss", config.debounce_seconds)
-
-    def _schedule_timer(self, delay_seconds: float) -> None:
-        """Schedule queue processing after the provided delay."""
         # Cancel existing timer if any
         if self._timer is not None:
             self._timer.cancel()
 
+        # Start new timer
         self._timer = threading.Timer(
-            delay_seconds,
+            config.debounce_seconds,
             self._process_queue,
         )
         self._timer.daemon = True
         self._timer.start()
 
+        logger.debug("Memory update timer set for %ss", config.debounce_seconds)
+
     def _process_queue(self) -> None:
         """Process all queued conversation contexts."""
         # Import here to avoid circular dependency
@@ -160,8 +116,8 @@ class MemoryUpdateQueue:
 
         with self._lock:
             if self._processing:
-                # Preserve immediate flush semantics even if another worker is active.
-                self._schedule_timer(0)
+                # Already processing, reschedule
+                self._reset_timer()
                 return
 
             if not self._queue:
@@ -215,13 +171,6 @@ class MemoryUpdateQueue:
 
         self._process_queue()
 
-    def flush_nowait(self) -> None:
-        """Start queue processing immediately in a background thread."""
-        with self._lock:
-            # Daemon thread: queued messages may be lost if the process exits
-            # before _process_queue completes. Acceptable for best-effort memory updates.
-            self._schedule_timer(0)
-
     def clear(self) -> None:
         """Clear the queue without processing.
 

backend/packages/harness/deerflow/agents/memory/storage.py

@@ -4,7 +4,6 @@ import abc
 import json
 import logging
 import threading
-import uuid
 from datetime import UTC, datetime
 from pathlib import Path
 from typing import Any
@@ -67,8 +66,6 @@ class FileMemoryStorage(MemoryStorage):
         # Per-user/agent memory cache: keyed by (user_id, agent_name) tuple (None = global)
         # Value: (memory_data, file_mtime)
         self._memory_cache: dict[tuple[str | None, str | None], tuple[dict[str, Any], float | None]] = {}
-        # Guards all reads and writes to _memory_cache across concurrent callers.
-        self._cache_lock = threading.Lock()
 
     def _validate_agent_name(self, agent_name: str) -> None:
         """Validate that the agent name is safe to use in filesystem paths.
@@ -116,60 +113,48 @@ class FileMemoryStorage(MemoryStorage):
             logger.warning("Failed to load memory file: %s", e)
             return create_empty_memory()
 
-    @staticmethod
-    def _cache_key(agent_name: str | None = None, *, user_id: str | None = None) -> tuple[str | None, str | None]:
-        return (user_id, agent_name)
-
     def load(self, agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
         """Load memory data (cached with file modification time check)."""
         file_path = self._get_memory_file_path(agent_name, user_id=user_id)
-        cache_key = self._cache_key(agent_name, user_id=user_id)
 
         try:
             current_mtime = file_path.stat().st_mtime if file_path.exists() else None
         except OSError:
             current_mtime = None
 
-        with self._cache_lock:
-            cached = self._memory_cache.get(cache_key)
-            if cached is not None and cached[1] == current_mtime:
-                return cached[0]
+        cache_key = (user_id, agent_name)
+        cached = self._memory_cache.get(cache_key)
 
-        memory_data = self._load_memory_from_file(agent_name, user_id=user_id)
-
-        with self._cache_lock:
+        if cached is None or cached[1] != current_mtime:
+            memory_data = self._load_memory_from_file(agent_name, user_id=user_id)
             self._memory_cache[cache_key] = (memory_data, current_mtime)
+            return memory_data
 
-        return memory_data
+        return cached[0]
 
     def reload(self, agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
         """Reload memory data from file, forcing cache invalidation."""
         file_path = self._get_memory_file_path(agent_name, user_id=user_id)
         memory_data = self._load_memory_from_file(agent_name, user_id=user_id)
-        cache_key = self._cache_key(agent_name, user_id=user_id)
 
         try:
             mtime = file_path.stat().st_mtime if file_path.exists() else None
         except OSError:
             mtime = None
 
-        with self._cache_lock:
-            self._memory_cache[cache_key] = (memory_data, mtime)
+        cache_key = (user_id, agent_name)
+        self._memory_cache[cache_key] = (memory_data, mtime)
         return memory_data
 
     def save(self, memory_data: dict[str, Any], agent_name: str | None = None, *, user_id: str | None = None) -> bool:
         """Save memory data to file and update cache."""
         file_path = self._get_memory_file_path(agent_name, user_id=user_id)
-        cache_key = self._cache_key(agent_name, user_id=user_id)
 
         try:
             file_path.parent.mkdir(parents=True, exist_ok=True)
-            # Shallow-copy before adding lastUpdated so the caller's dict is not
-            # mutated as a side-effect, and the cache reference is not silently
-            # updated before the file write succeeds.
-            memory_data = {**memory_data, "lastUpdated": utc_now_iso_z()}
+            memory_data["lastUpdated"] = utc_now_iso_z()
 
-            temp_path = file_path.with_suffix(f".{uuid.uuid4().hex}.tmp")
+            temp_path = file_path.with_suffix(".tmp")
             with open(temp_path, "w", encoding="utf-8") as f:
                 json.dump(memory_data, f, indent=2, ensure_ascii=False)
 
@@ -180,8 +165,8 @@ class FileMemoryStorage(MemoryStorage):
             except OSError:
                 mtime = None
 
-            with self._cache_lock:
-                self._memory_cache[cache_key] = (memory_data, mtime)
+            cache_key = (user_id, agent_name)
+            self._memory_cache[cache_key] = (memory_data, mtime)
             logger.info("Memory saved to %s", file_path)
             return True
         except OSError as e:

backend/packages/harness/deerflow/agents/memory/summarization_hook.py

@@ -1,31 +0,0 @@
-"""Hooks fired before summarization removes messages from state."""
-
-from __future__ import annotations
-
-from deerflow.agents.memory.message_processing import detect_correction, detect_reinforcement, filter_messages_for_memory
-from deerflow.agents.memory.queue import get_memory_queue
-from deerflow.agents.middlewares.summarization_middleware import SummarizationEvent
-from deerflow.config.memory_config import get_memory_config
-
-
-def memory_flush_hook(event: SummarizationEvent) -> None:
-    """Flush messages about to be summarized into the memory queue."""
-    if not get_memory_config().enabled or not event.thread_id:
-        return
-
-    filtered_messages = filter_messages_for_memory(list(event.messages_to_summarize))
-    user_messages = [message for message in filtered_messages if getattr(message, "type", None) == "human"]
-    assistant_messages = [message for message in filtered_messages if getattr(message, "type", None) == "ai"]
-    if not user_messages or not assistant_messages:
-        return
-
-    correction_detected = detect_correction(filtered_messages)
-    reinforcement_detected = not correction_detected and detect_reinforcement(filtered_messages)
-    queue = get_memory_queue()
-    queue.add_nowait(
-        thread_id=event.thread_id,
-        messages=filtered_messages,
-        agent_name=event.agent_name,
-        correction_detected=correction_detected,
-        reinforcement_detected=reinforcement_detected,
-    )

backend/packages/harness/deerflow/agents/memory/updater.py

@@ -1,9 +1,5 @@
 """Memory updater for reading, writing, and updating memory data."""
 
-import asyncio
-import atexit
-import concurrent.futures
-import copy
 import json
 import logging
 import math
@@ -26,18 +22,6 @@ from deerflow.models import create_chat_model
 logger = logging.getLogger(__name__)
 
 
-# Thread pool for offloading sync memory updates when called from an async
-# context.  Unlike the previous asyncio.run() approach, this runs *sync*
-# model.invoke() calls — no event loop is created, so the langchain async
-# httpx client pool (globally cached via @lru_cache) is never touched and
-# cross-loop connection reuse is impossible.
-_SYNC_MEMORY_UPDATER_EXECUTOR = concurrent.futures.ThreadPoolExecutor(
-    max_workers=4,
-    thread_name_prefix="memory-updater-sync",
-)
-atexit.register(lambda: _SYNC_MEMORY_UPDATER_EXECUTOR.shutdown(wait=False))
-
-
 def _create_empty_memory() -> dict[str, Any]:
     """Backward-compatible wrapper around the storage-layer empty-memory factory."""
     return create_empty_memory()
@@ -290,154 +274,6 @@ class MemoryUpdater:
         model_name = self._model_name or config.model_name
         return create_chat_model(name=model_name, thinking_enabled=False)
 
-    def _build_correction_hint(
-        self,
-        correction_detected: bool,
-        reinforcement_detected: bool,
-    ) -> str:
-        """Build optional prompt hints for correction and reinforcement signals."""
-        correction_hint = ""
-        if correction_detected:
-            correction_hint = (
-                "IMPORTANT: Explicit correction signals were detected in this conversation. "
-                "Pay special attention to what the agent got wrong, what the user corrected, "
-                "and record the correct approach as a fact with category "
-                '"correction" and confidence >= 0.95 when appropriate.'
-            )
-        if reinforcement_detected:
-            reinforcement_hint = (
-                "IMPORTANT: Positive reinforcement signals were detected in this conversation. "
-                "The user explicitly confirmed the agent's approach was correct or helpful. "
-                "Record the confirmed approach, style, or preference as a fact with category "
-                '"preference" or "behavior" and confidence >= 0.9 when appropriate.'
-            )
-            correction_hint = (correction_hint + "\n" + reinforcement_hint).strip() if correction_hint else reinforcement_hint
-
-        return correction_hint
-
-    def _prepare_update_prompt(
-        self,
-        messages: list[Any],
-        agent_name: str | None,
-        correction_detected: bool,
-        reinforcement_detected: bool,
-        user_id: str | None = None,
-    ) -> tuple[dict[str, Any], str] | None:
-        """Load memory and build the update prompt for a conversation."""
-        config = get_memory_config()
-        if not config.enabled or not messages:
-            return None
-
-        current_memory = get_memory_data(agent_name, user_id=user_id)
-        conversation_text = format_conversation_for_update(messages)
-        if not conversation_text.strip():
-            return None
-
-        correction_hint = self._build_correction_hint(
-            correction_detected=correction_detected,
-            reinforcement_detected=reinforcement_detected,
-        )
-        prompt = MEMORY_UPDATE_PROMPT.format(
-            current_memory=json.dumps(current_memory, indent=2),
-            conversation=conversation_text,
-            correction_hint=correction_hint,
-        )
-        return current_memory, prompt
-
-    def _finalize_update(
-        self,
-        current_memory: dict[str, Any],
-        response_content: Any,
-        thread_id: str | None,
-        agent_name: str | None,
-        user_id: str | None = None,
-    ) -> bool:
-        """Parse the model response, apply updates, and persist memory."""
-        response_text = _extract_text(response_content).strip()
-
-        if response_text.startswith("```"):
-            lines = response_text.split("\n")
-            response_text = "\n".join(lines[1:-1] if lines[-1] == "```" else lines[1:])
-
-        update_data = json.loads(response_text)
-        # Deep-copy before in-place mutation so a subsequent save() failure
-        # cannot corrupt the still-cached original object reference.
-        updated_memory = self._apply_updates(copy.deepcopy(current_memory), update_data, thread_id)
-        updated_memory = _strip_upload_mentions_from_memory(updated_memory)
-        return get_memory_storage().save(updated_memory, agent_name, user_id=user_id)
-
-    async def aupdate_memory(
-        self,
-        messages: list[Any],
-        thread_id: str | None = None,
-        agent_name: str | None = None,
-        correction_detected: bool = False,
-        reinforcement_detected: bool = False,
-        user_id: str | None = None,
-    ) -> bool:
-        """Update memory asynchronously by delegating to the sync path.
-
-        Uses ``asyncio.to_thread`` to run the *sync* ``model.invoke()`` path
-        in a worker thread so no second event loop is created and the
-        langchain async httpx client pool (shared with the lead agent) is
-        never touched.  This eliminates the cross-loop connection-reuse bug
-        described in issue #2615.
-        """
-        return await asyncio.to_thread(
-            self._do_update_memory_sync,
-            messages=messages,
-            thread_id=thread_id,
-            agent_name=agent_name,
-            correction_detected=correction_detected,
-            reinforcement_detected=reinforcement_detected,
-            user_id=user_id,
-        )
-
-    def _do_update_memory_sync(
-        self,
-        messages: list[Any],
-        thread_id: str | None = None,
-        agent_name: str | None = None,
-        correction_detected: bool = False,
-        reinforcement_detected: bool = False,
-        user_id: str | None = None,
-    ) -> bool:
-        """Pure-sync memory update using ``model.invoke()``.
-
-        Uses the *sync* LLM call path so no event loop is created.  This
-        guarantees that the langchain provider's globally cached async
-        httpx ``AsyncClient`` / connection pool (the one shared with the
-        lead agent) is never touched — no cross-loop connection reuse is
-        possible.
-        """
-        try:
-            prepared = self._prepare_update_prompt(
-                messages=messages,
-                agent_name=agent_name,
-                correction_detected=correction_detected,
-                reinforcement_detected=reinforcement_detected,
-                user_id=user_id,
-            )
-            if prepared is None:
-                return False
-
-            current_memory, prompt = prepared
-            model = self._get_model()
-            response = model.invoke(prompt, config={"run_name": "memory_agent"})
-            return self._finalize_update(
-                current_memory=current_memory,
-                response_content=response.content,
-                thread_id=thread_id,
-                agent_name=agent_name,
-                user_id=user_id,
-            )
-        except json.JSONDecodeError as e:
-            logger.warning("Failed to parse LLM response for memory update: %s", e)
-            return False
-        except Exception as e:
-            logger.exception("Memory update failed: %s", e)
-            return False
-
     def update_memory(
         self,
         messages: list[Any],
@@ -447,16 +283,7 @@ class MemoryUpdater:
         reinforcement_detected: bool = False,
         user_id: str | None = None,
     ) -> bool:
-        """Synchronously update memory using the sync LLM path.
-
-        Uses ``model.invoke()`` (sync HTTP) which operates on a completely
-        separate connection pool from the async ``AsyncClient`` shared by
-        the lead agent.  This eliminates the cross-loop connection-reuse
-        bug described in issue #2615.
-
-        When called from within a running event loop (e.g. from a LangGraph
-        node), the blocking sync call is offloaded to a thread pool so the
-        caller's loop is not blocked.
+        """Update memory based on conversation messages.
 
         Args:
             messages: List of conversation messages.
@@ -469,35 +296,78 @@ class MemoryUpdater:
         Returns:
             True if update was successful, False otherwise.
         """
-        try:
-            loop = asyncio.get_running_loop()
-        except RuntimeError:
-            loop = None
+        config = get_memory_config()
+        if not config.enabled:
+            return False
 
-        if loop is not None and loop.is_running():
-            try:
-                future = _SYNC_MEMORY_UPDATER_EXECUTOR.submit(
-                    self._do_update_memory_sync,
-                    messages=messages,
-                    thread_id=thread_id,
-                    agent_name=agent_name,
-                    correction_detected=correction_detected,
-                    reinforcement_detected=reinforcement_detected,
-                    user_id=user_id,
-                )
-                return future.result()
-            except Exception:
-                logger.exception("Failed to offload memory update to executor")
+        if not messages:
+            return False
+
+        try:
+            # Get current memory
+            current_memory = get_memory_data(agent_name, user_id=user_id)
+
+            # Format conversation for prompt
+            conversation_text = format_conversation_for_update(messages)
+
+            if not conversation_text.strip():
                 return False
 
-        return self._do_update_memory_sync(
-            messages=messages,
-            thread_id=thread_id,
-            agent_name=agent_name,
-            correction_detected=correction_detected,
-            reinforcement_detected=reinforcement_detected,
-            user_id=user_id,
-        )
+            # Build prompt
+            correction_hint = ""
+            if correction_detected:
+                correction_hint = (
+                    "IMPORTANT: Explicit correction signals were detected in this conversation. "
+                    "Pay special attention to what the agent got wrong, what the user corrected, "
+                    "and record the correct approach as a fact with category "
+                    '"correction" and confidence >= 0.95 when appropriate.'
+                )
+            if reinforcement_detected:
+                reinforcement_hint = (
+                    "IMPORTANT: Positive reinforcement signals were detected in this conversation. "
+                    "The user explicitly confirmed the agent's approach was correct or helpful. "
+                    "Record the confirmed approach, style, or preference as a fact with category "
+                    '"preference" or "behavior" and confidence >= 0.9 when appropriate.'
+                )
+                correction_hint = (correction_hint + "\n" + reinforcement_hint).strip() if correction_hint else reinforcement_hint
+
+            prompt = MEMORY_UPDATE_PROMPT.format(
+                current_memory=json.dumps(current_memory, indent=2),
+                conversation=conversation_text,
+                correction_hint=correction_hint,
+            )
+
+            # Call LLM
+            model = self._get_model()
+            response = model.invoke(prompt)
+            response_text = _extract_text(response.content).strip()
+
+            # Parse response
+            # Remove markdown code blocks if present
+            if response_text.startswith("```"):
+                lines = response_text.split("\n")
+                response_text = "\n".join(lines[1:-1] if lines[-1] == "```" else lines[1:])
+
+            update_data = json.loads(response_text)
+
+            # Apply updates
+            updated_memory = self._apply_updates(current_memory, update_data, thread_id)
+
+            # Strip file-upload mentions from all summaries before saving.
+            # Uploaded files are session-scoped and won't exist in future sessions,
+            # so recording upload events in long-term memory causes the agent to
+            # try (and fail) to locate those files in subsequent conversations.
+            updated_memory = _strip_upload_mentions_from_memory(updated_memory)
+
+            # Save
+            return get_memory_storage().save(updated_memory, agent_name, user_id=user_id)
+
+        except json.JSONDecodeError as e:
+            logger.warning("Failed to parse LLM response for memory update: %s", e)
+            return False
+        except Exception as e:
+            logger.exception("Memory update failed: %s", e)
+            return False
 
     def _apply_updates(
         self,

backend/packages/harness/deerflow/agents/middlewares/clarification_middleware.py

@@ -3,7 +3,6 @@
 import json
 import logging
 from collections.abc import Callable
-from hashlib import sha256
 from typing import override
 
 from langchain.agents import AgentState
@@ -37,13 +36,6 @@ class ClarificationMiddleware(AgentMiddleware[ClarificationMiddlewareState]):
 
     state_schema = ClarificationMiddlewareState
 
-    def _stable_message_id(self, tool_call_id: str, formatted_message: str) -> str:
-        """Build a deterministic message ID so retried clarification calls replace, not append."""
-        if tool_call_id:
-            return f"clarification:{tool_call_id}"
-        digest = sha256(formatted_message.encode("utf-8")).hexdigest()[:16]
-        return f"clarification:{digest}"
-
     def _is_chinese(self, text: str) -> bool:
         """Check if text contains Chinese characters.
 
@@ -139,7 +131,6 @@ class ClarificationMiddleware(AgentMiddleware[ClarificationMiddlewareState]):
         # Create a ToolMessage with the formatted question
         # This will be added to the message history
         tool_message = ToolMessage(
-            id=self._stable_message_id(tool_call_id, formatted_message),
             content=formatted_message,
             tool_call_id=tool_call_id,
             name="ask_clarification",

backend/packages/harness/deerflow/agents/middlewares/dangling_tool_call_middleware.py

@@ -13,7 +13,6 @@ at the correct positions (immediately after each dangling AIMessage), not append
 to the end of the message list as before_model + add_messages reducer would do.
 """
 
-import json
 import logging
 from collections.abc import Awaitable, Callable
 from typing import override
@@ -34,44 +33,6 @@ class DanglingToolCallMiddleware(AgentMiddleware[AgentState]):
     offending AIMessage so the LLM receives a well-formed conversation.
     """
 
-    @staticmethod
-    def _message_tool_calls(msg) -> list[dict]:
-        """Return normalized tool calls from structured fields or raw provider payloads."""
-        tool_calls = getattr(msg, "tool_calls", None) or []
-        if tool_calls:
-            return list(tool_calls)
-
-        raw_tool_calls = (getattr(msg, "additional_kwargs", None) or {}).get("tool_calls") or []
-        normalized: list[dict] = []
-        for raw_tc in raw_tool_calls:
-            if not isinstance(raw_tc, dict):
-                continue
-
-            function = raw_tc.get("function")
-            name = raw_tc.get("name")
-            if not name and isinstance(function, dict):
-                name = function.get("name")
-
-            args = raw_tc.get("args", {})
-            if not args and isinstance(function, dict):
-                raw_args = function.get("arguments")
-                if isinstance(raw_args, str):
-                    try:
-                        parsed_args = json.loads(raw_args)
-                    except (TypeError, ValueError, json.JSONDecodeError):
-                        parsed_args = {}
-                    args = parsed_args if isinstance(parsed_args, dict) else {}
-
-            normalized.append(
-                {
-                    "id": raw_tc.get("id"),
-                    "name": name or "unknown",
-                    "args": args if isinstance(args, dict) else {},
-                }
-            )
-
-        return normalized
-
     def _build_patched_messages(self, messages: list) -> list | None:
         """Return a new message list with patches inserted at the correct positions.
 
@@ -90,7 +51,7 @@ class DanglingToolCallMiddleware(AgentMiddleware[AgentState]):
         for msg in messages:
             if getattr(msg, "type", None) != "ai":
                 continue
-            for tc in self._message_tool_calls(msg):
+            for tc in getattr(msg, "tool_calls", None) or []:
                 tc_id = tc.get("id")
                 if tc_id and tc_id not in existing_tool_msg_ids:
                     needs_patch = True
@@ -109,7 +70,7 @@ class DanglingToolCallMiddleware(AgentMiddleware[AgentState]):
             patched.append(msg)
             if getattr(msg, "type", None) != "ai":
                 continue
-            for tc in self._message_tool_calls(msg):
+            for tc in getattr(msg, "tool_calls", None) or []:
                 tc_id = tc.get("id")
                 if tc_id and tc_id not in existing_tool_msg_ids and tc_id not in patched_ids:
                     patched.append(

backend/packages/harness/deerflow/agents/middlewares/deferred_tool_filter_middleware.py

@@ -16,9 +16,6 @@ from typing import override
 from langchain.agents import AgentState
 from langchain.agents.middleware import AgentMiddleware
 from langchain.agents.middleware.types import ModelCallResult, ModelRequest, ModelResponse
-from langchain_core.messages import ToolMessage
-from langgraph.prebuilt.tool_node import ToolCallRequest
-from langgraph.types import Command
 
 logger = logging.getLogger(__name__)
 
@@ -38,7 +35,7 @@ class DeferredToolFilterMiddleware(AgentMiddleware[AgentState]):
         if not registry:
             return request
 
-        deferred_names = registry.deferred_names
+        deferred_names = {e.name for e in registry.entries}
         active_tools = [t for t in request.tools if getattr(t, "name", None) not in deferred_names]
 
         if len(active_tools) < len(request.tools):
@@ -46,28 +43,6 @@ class DeferredToolFilterMiddleware(AgentMiddleware[AgentState]):
 
         return request.override(tools=active_tools)
 
-    def _blocked_tool_message(self, request: ToolCallRequest) -> ToolMessage | None:
-        from deerflow.tools.builtins.tool_search import get_deferred_registry
-
-        registry = get_deferred_registry()
-        if not registry:
-            return None
-
-        tool_name = str(request.tool_call.get("name") or "")
-        if not tool_name:
-            return None
-
-        if not registry.contains(tool_name):
-            return None
-
-        tool_call_id = str(request.tool_call.get("id") or "missing_tool_call_id")
-        return ToolMessage(
-            content=(f"Error: Tool '{tool_name}' is deferred and has not been promoted yet. Call tool_search first to expose and promote this tool's schema, then retry."),
-            tool_call_id=tool_call_id,
-            name=tool_name,
-            status="error",
-        )
-
     @override
     def wrap_model_call(
         self,
@@ -76,17 +51,6 @@ class DeferredToolFilterMiddleware(AgentMiddleware[AgentState]):
     ) -> ModelCallResult:
         return handler(self._filter_tools(request))
 
-    @override
-    def wrap_tool_call(
-        self,
-        request: ToolCallRequest,
-        handler: Callable[[ToolCallRequest], ToolMessage | Command],
-    ) -> ToolMessage | Command:
-        blocked = self._blocked_tool_message(request)
-        if blocked is not None:
-            return blocked
-        return handler(request)
-
     @override
     async def awrap_model_call(
         self,
@@ -94,14 +58,3 @@ class DeferredToolFilterMiddleware(AgentMiddleware[AgentState]):
         handler: Callable[[ModelRequest], Awaitable[ModelResponse]],
     ) -> ModelCallResult:
         return await handler(self._filter_tools(request))
-
-    @override
-    async def awrap_tool_call(
-        self,
-        request: ToolCallRequest,
-        handler: Callable[[ToolCallRequest], Awaitable[ToolMessage | Command]],
-    ) -> ToolMessage | Command:
-        blocked = self._blocked_tool_message(request)
-        if blocked is not None:
-            return blocked
-        return await handler(request)

backend/packages/harness/deerflow/agents/middlewares/llm_error_handling_middleware.py

@@ -4,7 +4,6 @@ from __future__ import annotations
 
 import asyncio
 import logging
-import threading
 import time
 from collections.abc import Awaitable, Callable
 from email.utils import parsedate_to_datetime
@@ -20,8 +19,6 @@ from langchain.agents.middleware.types import (
 from langchain_core.messages import AIMessage
 from langgraph.errors import GraphBubbleUp
 
-from deerflow.config.app_config import AppConfig
-
 logger = logging.getLogger(__name__)
 
 _RETRIABLE_STATUS_CODES = {408, 409, 425, 429, 500, 502, 503, 504}
@@ -70,71 +67,6 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
     retry_base_delay_ms: int = 1000
     retry_cap_delay_ms: int = 8000
 
-    def __init__(self, *, app_config: AppConfig, **kwargs: Any) -> None:
-        super().__init__(**kwargs)
-
-        self.circuit_failure_threshold = app_config.circuit_breaker.failure_threshold
-        self.circuit_recovery_timeout_sec = app_config.circuit_breaker.recovery_timeout_sec
-
-        # Circuit Breaker state
-        self._circuit_lock = threading.Lock()
-        self._circuit_failure_count = 0
-        self._circuit_open_until = 0.0
-        self._circuit_state = "closed"
-        self._circuit_probe_in_flight = False
-
-    def _check_circuit(self) -> bool:
-        """Returns True if circuit is OPEN (fast fail), False otherwise."""
-        with self._circuit_lock:
-            now = time.time()
-
-            if self._circuit_state == "open":
-                if now < self._circuit_open_until:
-                    return True
-                self._circuit_state = "half_open"
-                self._circuit_probe_in_flight = False
-
-            if self._circuit_state == "half_open":
-                if self._circuit_probe_in_flight:
-                    return True
-                self._circuit_probe_in_flight = True
-                return False
-
-            return False
-
-    def _record_success(self) -> None:
-        with self._circuit_lock:
-            if self._circuit_state != "closed" or self._circuit_failure_count > 0:
-                logger.info("Circuit breaker reset (Closed). LLM service recovered.")
-            self._circuit_failure_count = 0
-            self._circuit_open_until = 0.0
-            self._circuit_state = "closed"
-            self._circuit_probe_in_flight = False
-
-    def _record_failure(self) -> None:
-        with self._circuit_lock:
-            if self._circuit_state == "half_open":
-                self._circuit_open_until = time.time() + self.circuit_recovery_timeout_sec
-                self._circuit_state = "open"
-                self._circuit_probe_in_flight = False
-                logger.error(
-                    "Circuit breaker probe failed (Open). Will probe again after %ds.",
-                    self.circuit_recovery_timeout_sec,
-                )
-                return
-
-            self._circuit_failure_count += 1
-            if self._circuit_failure_count >= self.circuit_failure_threshold:
-                self._circuit_open_until = time.time() + self.circuit_recovery_timeout_sec
-                if self._circuit_state != "open":
-                    self._circuit_state = "open"
-                    self._circuit_probe_in_flight = False
-                    logger.error(
-                        "Circuit breaker tripped (Open). Threshold reached (%d). Will probe after %ds.",
-                        self.circuit_failure_threshold,
-                        self.circuit_recovery_timeout_sec,
-                    )
-
     def _classify_error(self, exc: BaseException) -> tuple[bool, str]:
         detail = _extract_error_detail(exc)
         lowered = detail.lower()
@@ -151,8 +83,6 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
             "APITimeoutError",
             "APIConnectionError",
             "InternalServerError",
-            "ReadError",  # httpx.ReadError: connection dropped mid-stream
-            "RemoteProtocolError",  # httpx: server closed connection unexpectedly
         }:
             return True, "transient"
         if status_code in _RETRIABLE_STATUS_CODES:
@@ -174,9 +104,6 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
         reason_text = "provider is busy" if reason == "busy" else "provider request failed temporarily"
         return f"LLM request retry {attempt}/{self.retry_max_attempts}: {reason_text}. Retrying in {seconds}s."
 
-    def _build_circuit_breaker_message(self) -> str:
-        return "The configured LLM provider is currently unavailable due to continuous failures. Circuit breaker is engaged to protect the system. Please wait a moment before trying again."
-
     def _build_user_message(self, exc: BaseException, reason: str) -> str:
         detail = _extract_error_detail(exc)
         if reason == "quota":
@@ -211,20 +138,12 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
         request: ModelRequest,
         handler: Callable[[ModelRequest], ModelResponse],
     ) -> ModelCallResult:
-        if self._check_circuit():
-            return AIMessage(content=self._build_circuit_breaker_message())
-
         attempt = 1
         while True:
             try:
-                response = handler(request)
-                self._record_success()
-                return response
+                return handler(request)
             except GraphBubbleUp:
                 # Preserve LangGraph control-flow signals (interrupt/pause/resume).
-                with self._circuit_lock:
-                    if self._circuit_state == "half_open":
-                        self._circuit_probe_in_flight = False
                 raise
             except Exception as exc:
                 retriable, reason = self._classify_error(exc)
@@ -247,8 +166,6 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
                     _extract_error_detail(exc),
                     exc_info=exc,
                 )
-                if retriable:
-                    self._record_failure()
                 return AIMessage(content=self._build_user_message(exc, reason))
 
     @override
@@ -257,20 +174,12 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
         request: ModelRequest,
         handler: Callable[[ModelRequest], Awaitable[ModelResponse]],
     ) -> ModelCallResult:
-        if self._check_circuit():
-            return AIMessage(content=self._build_circuit_breaker_message())
-
         attempt = 1
         while True:
             try:
-                response = await handler(request)
-                self._record_success()
-                return response
+                return await handler(request)
             except GraphBubbleUp:
                 # Preserve LangGraph control-flow signals (interrupt/pause/resume).
-                with self._circuit_lock:
-                    if self._circuit_state == "half_open":
-                        self._circuit_probe_in_flight = False
                 raise
             except Exception as exc:
                 retriable, reason = self._classify_error(exc)
@@ -293,8 +202,6 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
                     _extract_error_detail(exc),
                     exc_info=exc,
                 )
-                if retriable:
-                    self._record_failure()
                 return AIMessage(content=self._build_user_message(exc, reason))
 
 

backend/packages/harness/deerflow/agents/middlewares/loop_detection_middleware.py

@@ -17,7 +17,6 @@ import json
 import logging
 import threading
 from collections import OrderedDict, defaultdict
-from copy import deepcopy
 from typing import override
 
 from langchain.agents import AgentState
@@ -32,8 +31,6 @@ _DEFAULT_WARN_THRESHOLD = 3  # inject warning after 3 identical calls
 _DEFAULT_HARD_LIMIT = 5  # force-stop after 5 identical calls
 _DEFAULT_WINDOW_SIZE = 20  # track last N tool calls
 _DEFAULT_MAX_TRACKED_THREADS = 100  # LRU eviction limit
-_DEFAULT_TOOL_FREQ_WARN = 30  # warn after 30 calls to the same tool type
-_DEFAULT_TOOL_FREQ_HARD_LIMIT = 50  # force-stop after 50 calls to the same tool type
 
 
 def _normalize_tool_call_args(raw_args: object) -> tuple[dict, str | None]:
@@ -128,14 +125,8 @@ def _hash_tool_calls(tool_calls: list[dict]) -> str:
 
 _WARNING_MSG = "[LOOP DETECTED] You are repeating the same tool calls. Stop calling tools and produce your final answer now. If you cannot complete the task, summarize what you accomplished so far."
 
-_TOOL_FREQ_WARNING_MSG = (
-    "[LOOP DETECTED] You have called {tool_name} {count} times without producing a final answer. Stop calling tools and produce your final answer now. If you cannot complete the task, summarize what you accomplished so far."
-)
-
 _HARD_STOP_MSG = "[FORCED STOP] Repeated tool calls exceeded the safety limit. Producing final answer with results collected so far."
 
-_TOOL_FREQ_HARD_STOP_MSG = "[FORCED STOP] Tool {tool_name} called {count} times — exceeded the per-tool safety limit. Producing final answer with results collected so far."
-
 
 class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
     """Detects and breaks repetitive tool call loops.
@@ -149,12 +140,6 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
             Default: 20.
         max_tracked_threads: Maximum number of threads to track before
             evicting the least recently used. Default: 100.
-        tool_freq_warn: Number of calls to the same tool *type* (regardless
-            of arguments) before injecting a frequency warning. Catches
-            cross-file read loops that hash-based detection misses.
-            Default: 30.
-        tool_freq_hard_limit: Number of calls to the same tool type before
-            forcing a stop. Default: 50.
     """
 
     def __init__(
@@ -163,23 +148,16 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
         hard_limit: int = _DEFAULT_HARD_LIMIT,
         window_size: int = _DEFAULT_WINDOW_SIZE,
         max_tracked_threads: int = _DEFAULT_MAX_TRACKED_THREADS,
-        tool_freq_warn: int = _DEFAULT_TOOL_FREQ_WARN,
-        tool_freq_hard_limit: int = _DEFAULT_TOOL_FREQ_HARD_LIMIT,
     ):
         super().__init__()
         self.warn_threshold = warn_threshold
         self.hard_limit = hard_limit
         self.window_size = window_size
         self.max_tracked_threads = max_tracked_threads
-        self.tool_freq_warn = tool_freq_warn
-        self.tool_freq_hard_limit = tool_freq_hard_limit
         self._lock = threading.Lock()
         # Per-thread tracking using OrderedDict for LRU eviction
         self._history: OrderedDict[str, list[str]] = OrderedDict()
         self._warned: dict[str, set[str]] = defaultdict(set)
-        # Per-thread, per-tool-type cumulative call counts
-        self._tool_freq: dict[str, dict[str, int]] = defaultdict(lambda: defaultdict(int))
-        self._tool_freq_warned: dict[str, set[str]] = defaultdict(set)
 
     def _get_thread_id(self, runtime: Runtime) -> str:
         """Extract thread_id from runtime context for per-thread tracking."""
@@ -196,19 +174,11 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
         while len(self._history) > self.max_tracked_threads:
             evicted_id, _ = self._history.popitem(last=False)
             self._warned.pop(evicted_id, None)
-            self._tool_freq.pop(evicted_id, None)
-            self._tool_freq_warned.pop(evicted_id, None)
             logger.debug("Evicted loop tracking for thread %s (LRU)", evicted_id)
 
     def _track_and_check(self, state: AgentState, runtime: Runtime) -> tuple[str | None, bool]:
         """Track tool calls and check for loops.
 
-        Two detection layers:
-          1. **Hash-based** (existing): catches identical tool call sets.
-          2. **Frequency-based** (new): catches the same *tool type* being
-             called many times with varying arguments (e.g. ``read_file``
-             on 40 different files).
-
         Returns:
             (warning_message_or_none, should_hard_stop)
         """
@@ -243,7 +213,6 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
             count = history.count(call_hash)
             tool_names = [tc.get("name", "?") for tc in tool_calls]
 
-            # --- Layer 1: hash-based (identical call sets) ---
             if count >= self.hard_limit:
                 logger.error(
                     "Loop hard limit reached — forcing stop",
@@ -270,40 +239,8 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
                         },
                     )
                     return _WARNING_MSG, False
-
-            # --- Layer 2: per-tool-type frequency ---
-            freq = self._tool_freq[thread_id]
-            for tc in tool_calls:
-                name = tc.get("name", "")
-                if not name:
-                    continue
-                freq[name] += 1
-                tc_count = freq[name]
-
-                if tc_count >= self.tool_freq_hard_limit:
-                    logger.error(
-                        "Tool frequency hard limit reached — forcing stop",
-                        extra={
-                            "thread_id": thread_id,
-                            "tool_name": name,
-                            "count": tc_count,
-                        },
-                    )
-                    return _TOOL_FREQ_HARD_STOP_MSG.format(tool_name=name, count=tc_count), True
-
-                if tc_count >= self.tool_freq_warn:
-                    warned = self._tool_freq_warned[thread_id]
-                    if name not in warned:
-                        warned.add(name)
-                        logger.warning(
-                            "Tool frequency warning — too many calls to same tool type",
-                            extra={
-                                "thread_id": thread_id,
-                                "tool_name": name,
-                                "count": tc_count,
-                            },
-                        )
-                        return _TOOL_FREQ_WARNING_MSG.format(tool_name=name, count=tc_count), False
+                # Warning already injected for this hash — suppress
+                return None, False
 
         return None, False
 
@@ -324,26 +261,6 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
         # Fallback: coerce unexpected types to str to avoid TypeError
         return str(content) + f"\n\n{text}"
 
-    @staticmethod
-    def _build_hard_stop_update(last_msg, content: str | list) -> dict:
-        """Clear tool-call metadata so forced-stop messages serialize as plain assistant text."""
-        update = {
-            "tool_calls": [],
-            "content": content,
-        }
-
-        additional_kwargs = dict(getattr(last_msg, "additional_kwargs", {}) or {})
-        for key in ("tool_calls", "function_call"):
-            additional_kwargs.pop(key, None)
-        update["additional_kwargs"] = additional_kwargs
-
-        response_metadata = deepcopy(getattr(last_msg, "response_metadata", {}) or {})
-        if response_metadata.get("finish_reason") == "tool_calls":
-            response_metadata["finish_reason"] = "stop"
-        update["response_metadata"] = response_metadata
-
-        return update
-
     def _apply(self, state: AgentState, runtime: Runtime) -> dict | None:
         warning, hard_stop = self._track_and_check(state, runtime)
 
@@ -351,8 +268,12 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
             # Strip tool_calls from the last AIMessage to force text output
             messages = state.get("messages", [])
             last_msg = messages[-1]
-            content = self._append_text(last_msg.content, warning or _HARD_STOP_MSG)
-            stripped_msg = last_msg.model_copy(update=self._build_hard_stop_update(last_msg, content))
+            stripped_msg = last_msg.model_copy(
+                update={
+                    "tool_calls": [],
+                    "content": self._append_text(last_msg.content, _HARD_STOP_MSG),
+                }
+            )
             return {"messages": [stripped_msg]}
 
         if warning:
@@ -362,7 +283,7 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
             # the conversation; injecting one mid-conversation crashes
             # langchain_anthropic's _format_messages(). HumanMessage works
             # with all providers. See #1299.
-            return {"messages": [HumanMessage(content=warning, name="loop_warning")]}
+            return {"messages": [HumanMessage(content=warning)]}
 
         return None
 
@@ -380,10 +301,6 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
             if thread_id:
                 self._history.pop(thread_id, None)
                 self._warned.pop(thread_id, None)
-                self._tool_freq.pop(thread_id, None)
-                self._tool_freq_warned.pop(thread_id, None)
             else:
                 self._history.clear()
                 self._warned.clear()
-                self._tool_freq.clear()
-                self._tool_freq_warned.clear()

backend/packages/harness/deerflow/agents/middlewares/memory_middleware.py

@@ -1,23 +1,51 @@
 """Middleware for memory mechanism."""
 
 import logging
-from typing import TYPE_CHECKING, override
+import re
+from typing import Any, override
 
 from langchain.agents import AgentState
 from langchain.agents.middleware import AgentMiddleware
 from langgraph.config import get_config
 from langgraph.runtime import Runtime
 
-from deerflow.agents.memory.message_processing import detect_correction, detect_reinforcement, filter_messages_for_memory
 from deerflow.agents.memory.queue import get_memory_queue
 from deerflow.config.memory_config import get_memory_config
 from deerflow.runtime.user_context import get_effective_user_id
 
-if TYPE_CHECKING:
-    from deerflow.config.memory_config import MemoryConfig
-
 logger = logging.getLogger(__name__)
 
+_UPLOAD_BLOCK_RE = re.compile(r"<uploaded_files>[\s\S]*?</uploaded_files>\n*", re.IGNORECASE)
+_CORRECTION_PATTERNS = (
+    re.compile(r"\bthat(?:'s| is) (?:wrong|incorrect)\b", re.IGNORECASE),
+    re.compile(r"\byou misunderstood\b", re.IGNORECASE),
+    re.compile(r"\btry again\b", re.IGNORECASE),
+    re.compile(r"\bredo\b", re.IGNORECASE),
+    re.compile(r"不对"),
+    re.compile(r"你理解错了"),
+    re.compile(r"你理解有误"),
+    re.compile(r"重试"),
+    re.compile(r"重新来"),
+    re.compile(r"换一种"),
+    re.compile(r"改用"),
+)
+
+_REINFORCEMENT_PATTERNS = (
+    re.compile(r"\byes[,.]?\s+(?:exactly|perfect|that(?:'s| is) (?:right|correct|it))\b", re.IGNORECASE),
+    re.compile(r"\bperfect(?:[.!?]|$)", re.IGNORECASE),
+    re.compile(r"\bexactly\s+(?:right|correct)\b", re.IGNORECASE),
+    re.compile(r"\bthat(?:'s| is)\s+(?:exactly\s+)?(?:right|correct|what i (?:wanted|needed|meant))\b", re.IGNORECASE),
+    re.compile(r"\bkeep\s+(?:doing\s+)?that\b", re.IGNORECASE),
+    re.compile(r"\bjust\s+(?:like\s+)?(?:that|this)\b", re.IGNORECASE),
+    re.compile(r"\bthis is (?:great|helpful)\b(?:[.!?]|$)", re.IGNORECASE),
+    re.compile(r"\bthis is what i wanted\b(?:[.!?]|$)", re.IGNORECASE),
+    re.compile(r"对[，,]?\s*就是这样(?:[。！？!?.]|$)"),
+    re.compile(r"完全正确(?:[。！？!?.]|$)"),
+    re.compile(r"(?:对[，,]?\s*)?就是这个意思(?:[。！？!?.]|$)"),
+    re.compile(r"正是我想要的(?:[。！？!?.]|$)"),
+    re.compile(r"继续保持(?:[。！？!?.]|$)"),
+)
+
 
 class MemoryMiddlewareState(AgentState):
     """Compatible with the `ThreadState` schema."""
@@ -25,6 +53,125 @@ class MemoryMiddlewareState(AgentState):
     pass
 
 
+def _extract_message_text(message: Any) -> str:
+    """Extract plain text from message content for filtering and signal detection."""
+    content = getattr(message, "content", "")
+    if isinstance(content, list):
+        text_parts: list[str] = []
+        for part in content:
+            if isinstance(part, str):
+                text_parts.append(part)
+            elif isinstance(part, dict):
+                text_val = part.get("text")
+                if isinstance(text_val, str):
+                    text_parts.append(text_val)
+        return " ".join(text_parts)
+    return str(content)
+
+
+def _filter_messages_for_memory(messages: list[Any]) -> list[Any]:
+    """Filter messages to keep only user inputs and final assistant responses.
+
+    This filters out:
+    - Tool messages (intermediate tool call results)
+    - AI messages with tool_calls (intermediate steps, not final responses)
+    - The <uploaded_files> block injected by UploadsMiddleware into human messages
+      (file paths are session-scoped and must not persist in long-term memory).
+      The user's actual question is preserved; only turns whose content is entirely
+      the upload block (nothing remains after stripping) are dropped along with
+      their paired assistant response.
+
+    Only keeps:
+    - Human messages (with the ephemeral upload block removed)
+    - AI messages without tool_calls (final assistant responses), unless the
+      paired human turn was upload-only and had no real user text.
+
+    Args:
+        messages: List of all conversation messages.
+
+    Returns:
+        Filtered list containing only user inputs and final assistant responses.
+    """
+    filtered = []
+    skip_next_ai = False
+    for msg in messages:
+        msg_type = getattr(msg, "type", None)
+
+        if msg_type == "human":
+            content_str = _extract_message_text(msg)
+            if "<uploaded_files>" in content_str:
+                # Strip the ephemeral upload block; keep the user's real question.
+                stripped = _UPLOAD_BLOCK_RE.sub("", content_str).strip()
+                if not stripped:
+                    # Nothing left — the entire turn was upload bookkeeping;
+                    # skip it and the paired assistant response.
+                    skip_next_ai = True
+                    continue
+                # Rebuild the message with cleaned content so the user's question
+                # is still available for memory summarisation.
+                from copy import copy
+
+                clean_msg = copy(msg)
+                clean_msg.content = stripped
+                filtered.append(clean_msg)
+                skip_next_ai = False
+            else:
+                filtered.append(msg)
+                skip_next_ai = False
+        elif msg_type == "ai":
+            tool_calls = getattr(msg, "tool_calls", None)
+            if not tool_calls:
+                if skip_next_ai:
+                    skip_next_ai = False
+                    continue
+                filtered.append(msg)
+        # Skip tool messages and AI messages with tool_calls
+
+    return filtered
+
+
+def detect_correction(messages: list[Any]) -> bool:
+    """Detect explicit user corrections in recent conversation turns.
+
+    The queue keeps only one pending context per thread, so callers pass the
+    latest filtered message list. Checking only recent user turns keeps signal
+    detection conservative while avoiding stale corrections from long histories.
+    """
+    recent_user_msgs = [msg for msg in messages[-6:] if getattr(msg, "type", None) == "human"]
+
+    for msg in recent_user_msgs:
+        content = _extract_message_text(msg).strip()
+        if not content:
+            continue
+        if any(pattern.search(content) for pattern in _CORRECTION_PATTERNS):
+            return True
+
+    return False
+
+
+def detect_reinforcement(messages: list[Any]) -> bool:
+    """Detect explicit positive reinforcement signals in recent conversation turns.
+
+    Complements detect_correction() by identifying when the user confirms the
+    agent's approach was correct. This allows the memory system to record what
+    worked well, not just what went wrong.
+
+    The queue keeps only one pending context per thread, so callers pass the
+    latest filtered message list. Checking only recent user turns keeps signal
+    detection conservative while avoiding stale signals from long histories.
+    """
+    recent_user_msgs = [msg for msg in messages[-6:] if getattr(msg, "type", None) == "human"]
+
+    for msg in recent_user_msgs:
+        content = _extract_message_text(msg).strip()
+        if not content:
+            continue
+        if any(pattern.search(content) for pattern in _REINFORCEMENT_PATTERNS):
+            return True
+
+    return False
+
+
 class MemoryMiddleware(AgentMiddleware[MemoryMiddlewareState]):
     """Middleware that queues conversation for memory update after agent execution.
 
@@ -37,17 +184,14 @@ class MemoryMiddleware(AgentMiddleware[MemoryMiddlewareState]):
 
     state_schema = MemoryMiddlewareState
 
-    def __init__(self, agent_name: str | None = None, *, memory_config: "MemoryConfig | None" = None):
+    def __init__(self, agent_name: str | None = None):
         """Initialize the MemoryMiddleware.
 
         Args:
             agent_name: If provided, memory is stored per-agent. If None, uses global memory.
-            memory_config: Explicit memory config. When omitted, legacy global
-                config fallback is used.
         """
         super().__init__()
         self._agent_name = agent_name
-        self._memory_config = memory_config
 
     @override
     def after_agent(self, state: MemoryMiddlewareState, runtime: Runtime) -> dict | None:
@@ -60,7 +204,7 @@ class MemoryMiddleware(AgentMiddleware[MemoryMiddlewareState]):
         Returns:
             None (no state changes needed from this middleware).
         """
-        config = self._memory_config or get_memory_config()
+        config = get_memory_config()
         if not config.enabled:
             return None
 
@@ -80,7 +224,7 @@ class MemoryMiddleware(AgentMiddleware[MemoryMiddlewareState]):
             return None
 
         # Filter to only keep user inputs and final assistant responses
-        filtered_messages = filter_messages_for_memory(messages)
+        filtered_messages = _filter_messages_for_memory(messages)
 
         # Only queue if there's meaningful conversation
         # At minimum need one user message and one assistant response

backend/packages/harness/deerflow/agents/middlewares/summarization_middleware.py

@@ -1,354 +0,0 @@
-"""Summarization middleware extensions for DeerFlow."""
-
-from __future__ import annotations
-
-import logging
-from collections.abc import Collection
-from dataclasses import dataclass
-from typing import Any, Protocol, override, runtime_checkable
-
-from langchain.agents import AgentState
-from langchain.agents.middleware import SummarizationMiddleware
-from langchain_core.messages import AIMessage, AnyMessage, HumanMessage, RemoveMessage, ToolMessage
-from langgraph.config import get_config
-from langgraph.graph.message import REMOVE_ALL_MESSAGES
-from langgraph.runtime import Runtime
-
-logger = logging.getLogger(__name__)
-
-
-@dataclass(frozen=True)
-class SummarizationEvent:
-    """Context emitted before conversation history is summarized away."""
-
-    messages_to_summarize: tuple[AnyMessage, ...]
-    preserved_messages: tuple[AnyMessage, ...]
-    thread_id: str | None
-    agent_name: str | None
-    runtime: Runtime
-
-
-@runtime_checkable
-class BeforeSummarizationHook(Protocol):
-    """Hook invoked before summarization removes messages from state."""
-
-    def __call__(self, event: SummarizationEvent) -> None: ...
-
-
-def _resolve_thread_id(runtime: Runtime) -> str | None:
-    """Resolve the current thread ID from runtime context or LangGraph config."""
-    thread_id = runtime.context.get("thread_id") if runtime.context else None
-    if thread_id is None:
-        try:
-            config_data = get_config()
-        except RuntimeError:
-            return None
-        thread_id = config_data.get("configurable", {}).get("thread_id")
-    return thread_id
-
-
-def _resolve_agent_name(runtime: Runtime) -> str | None:
-    """Resolve the current agent name from runtime context or LangGraph config."""
-    agent_name = runtime.context.get("agent_name") if runtime.context else None
-    if agent_name is None:
-        try:
-            config_data = get_config()
-        except RuntimeError:
-            return None
-        agent_name = config_data.get("configurable", {}).get("agent_name")
-    return agent_name
-
-
-def _tool_call_path(tool_call: dict[str, Any]) -> str | None:
-    """Best-effort extraction of a file path argument from a read_file-like tool call."""
-    args = tool_call.get("args") or {}
-    if not isinstance(args, dict):
-        return None
-    for key in ("path", "file_path", "filepath"):
-        value = args.get(key)
-        if isinstance(value, str) and value:
-            return value
-    return None
-
-
-def _clone_ai_message(
-    message: AIMessage,
-    tool_calls: list[dict[str, Any]],
-    *,
-    content: Any | None = None,
-) -> AIMessage:
-    """Clone an AIMessage while replacing its tool_calls list and optional content."""
-    update: dict[str, Any] = {"tool_calls": tool_calls}
-    if content is not None:
-        update["content"] = content
-    return message.model_copy(update=update)
-
-
-@dataclass
-class _SkillBundle:
-    """Skill-related tool calls and tool results associated with one AIMessage."""
-
-    ai_index: int
-    skill_tool_indices: tuple[int, ...]
-    skill_tool_call_ids: frozenset[str]
-    skill_tool_tokens: int
-    skill_key: str
-
-
-class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
-    """Summarization middleware with pre-compression hook dispatch and skill rescue."""
-
-    def __init__(
-        self,
-        *args,
-        skills_container_path: str | None = None,
-        skill_file_read_tool_names: Collection[str] | None = None,
-        before_summarization: list[BeforeSummarizationHook] | None = None,
-        preserve_recent_skill_count: int = 5,
-        preserve_recent_skill_tokens: int = 25_000,
-        preserve_recent_skill_tokens_per_skill: int = 5_000,
-        **kwargs,
-    ) -> None:
-        super().__init__(*args, **kwargs)
-        self._skills_container_path = skills_container_path or "/mnt/skills"
-        self._skill_file_read_tool_names = frozenset(skill_file_read_tool_names or {"read_file", "read", "view", "cat"})
-        self._before_summarization_hooks = before_summarization or []
-        self._preserve_recent_skill_count = max(0, preserve_recent_skill_count)
-        self._preserve_recent_skill_tokens = max(0, preserve_recent_skill_tokens)
-        self._preserve_recent_skill_tokens_per_skill = max(0, preserve_recent_skill_tokens_per_skill)
-
-    def before_model(self, state: AgentState, runtime: Runtime) -> dict | None:
-        return self._maybe_summarize(state, runtime)
-
-    async def abefore_model(self, state: AgentState, runtime: Runtime) -> dict | None:
-        return await self._amaybe_summarize(state, runtime)
-
-    def _maybe_summarize(self, state: AgentState, runtime: Runtime) -> dict | None:
-        messages = state["messages"]
-        self._ensure_message_ids(messages)
-
-        total_tokens = self.token_counter(messages)
-        if not self._should_summarize(messages, total_tokens):
-            return None
-
-        cutoff_index = self._determine_cutoff_index(messages)
-        if cutoff_index <= 0:
-            return None
-
-        messages_to_summarize, preserved_messages = self._partition_with_skill_rescue(messages, cutoff_index)
-        self._fire_hooks(messages_to_summarize, preserved_messages, runtime)
-        summary = self._create_summary(messages_to_summarize)
-        new_messages = self._build_new_messages(summary)
-
-        return {
-            "messages": [
-                RemoveMessage(id=REMOVE_ALL_MESSAGES),
-                *new_messages,
-                *preserved_messages,
-            ]
-        }
-
-    async def _amaybe_summarize(self, state: AgentState, runtime: Runtime) -> dict | None:
-        messages = state["messages"]
-        self._ensure_message_ids(messages)
-
-        total_tokens = self.token_counter(messages)
-        if not self._should_summarize(messages, total_tokens):
-            return None
-
-        cutoff_index = self._determine_cutoff_index(messages)
-        if cutoff_index <= 0:
-            return None
-
-        messages_to_summarize, preserved_messages = self._partition_with_skill_rescue(messages, cutoff_index)
-        self._fire_hooks(messages_to_summarize, preserved_messages, runtime)
-        summary = await self._acreate_summary(messages_to_summarize)
-        new_messages = self._build_new_messages(summary)
-
-        return {
-            "messages": [
-                RemoveMessage(id=REMOVE_ALL_MESSAGES),
-                *new_messages,
-                *preserved_messages,
-            ]
-        }
-
-    @override
-    def _build_new_messages(self, summary: str) -> list[HumanMessage]:
-        """Override the base implementation to let the human message with the special name 'summary'.
-        And this message will be ignored to display in the frontend, but still can be used as context for the model.
-        """
-        return [HumanMessage(content=f"Here is a summary of the conversation to date:\n\n{summary}", name="summary")]
-
-    def _partition_with_skill_rescue(
-        self,
-        messages: list[AnyMessage],
-        cutoff_index: int,
-    ) -> tuple[list[AnyMessage], list[AnyMessage]]:
-        """Partition like the parent, then rescue recently-loaded skill bundles."""
-        to_summarize, preserved = self._partition_messages(messages, cutoff_index)
-
-        if self._preserve_recent_skill_count == 0 or self._preserve_recent_skill_tokens == 0 or not to_summarize:
-            return to_summarize, preserved
-
-        try:
-            bundles = self._find_skill_bundles(to_summarize, self._skills_container_path)
-        except Exception:
-            logger.exception("Skill-preserving summarization rescue failed; falling back to default partition")
-            return to_summarize, preserved
-
-        if not bundles:
-            return to_summarize, preserved
-
-        rescue_bundles = self._select_bundles_to_rescue(bundles)
-        if not rescue_bundles:
-            return to_summarize, preserved
-
-        bundles_by_ai_index = {bundle.ai_index: bundle for bundle in rescue_bundles}
-        rescue_tool_indices = {idx for bundle in rescue_bundles for idx in bundle.skill_tool_indices}
-        rescued: list[AnyMessage] = []
-        remaining: list[AnyMessage] = []
-        for i, msg in enumerate(to_summarize):
-            bundle = bundles_by_ai_index.get(i)
-            if bundle is not None and isinstance(msg, AIMessage):
-                rescued_tool_calls = [tc for tc in msg.tool_calls if tc.get("id") in bundle.skill_tool_call_ids]
-                remaining_tool_calls = [tc for tc in msg.tool_calls if tc.get("id") not in bundle.skill_tool_call_ids]
-
-                if rescued_tool_calls:
-                    rescued.append(_clone_ai_message(msg, rescued_tool_calls, content=""))
-                if remaining_tool_calls or msg.content:
-                    remaining.append(_clone_ai_message(msg, remaining_tool_calls))
-                continue
-
-            if i in rescue_tool_indices:
-                rescued.append(msg)
-                continue
-
-            remaining.append(msg)
-
-        return remaining, rescued + preserved
-
-    def _find_skill_bundles(
-        self,
-        messages: list[AnyMessage],
-        skills_root: str,
-    ) -> list[_SkillBundle]:
-        """Locate AIMessage + paired ToolMessage groups that load skill files."""
-        bundles: list[_SkillBundle] = []
-        n = len(messages)
-        i = 0
-        while i < n:
-            msg = messages[i]
-            if not (isinstance(msg, AIMessage) and msg.tool_calls):
-                i += 1
-                continue
-
-            tool_calls = list(msg.tool_calls)
-            skill_paths_by_id: dict[str, str] = {}
-            for tc in tool_calls:
-                if self._is_skill_tool_call(tc, skills_root):
-                    tc_id = tc.get("id")
-                    path = _tool_call_path(tc)
-                    if tc_id and path:
-                        skill_paths_by_id[tc_id] = path
-
-            if not skill_paths_by_id:
-                i += 1
-                continue
-
-            skill_tool_tokens = 0
-            skill_key_parts: list[str] = []
-            skill_tool_indices: list[int] = []
-            matched_skill_call_ids: set[str] = set()
-
-            j = i + 1
-            while j < n and isinstance(messages[j], ToolMessage):
-                j += 1
-
-            for k in range(i + 1, j):
-                tool_msg = messages[k]
-                if isinstance(tool_msg, ToolMessage) and tool_msg.tool_call_id in skill_paths_by_id:
-                    skill_tool_tokens += self.token_counter([tool_msg])
-                    skill_key_parts.append(skill_paths_by_id[tool_msg.tool_call_id])
-                    skill_tool_indices.append(k)
-                    matched_skill_call_ids.add(tool_msg.tool_call_id)
-
-            if not skill_tool_indices:
-                i = j
-                continue
-
-            bundles.append(
-                _SkillBundle(
-                    ai_index=i,
-                    skill_tool_indices=tuple(skill_tool_indices),
-                    skill_tool_call_ids=frozenset(matched_skill_call_ids),
-                    skill_tool_tokens=skill_tool_tokens,
-                    skill_key="|".join(sorted(skill_key_parts)),
-                )
-            )
-            i = j
-
-        return bundles
-
-    def _select_bundles_to_rescue(self, bundles: list[_SkillBundle]) -> list[_SkillBundle]:
-        """Pick bundles to keep, walking newest-first under count/token budgets."""
-        selected: list[_SkillBundle] = []
-        if not bundles:
-            return selected
-
-        seen_skill_keys: set[str] = set()
-        total_tokens = 0
-        kept = 0
-
-        for bundle in reversed(bundles):
-            if kept >= self._preserve_recent_skill_count:
-                break
-            if bundle.skill_key in seen_skill_keys:
-                continue
-            if bundle.skill_tool_tokens > self._preserve_recent_skill_tokens_per_skill:
-                continue
-            if total_tokens + bundle.skill_tool_tokens > self._preserve_recent_skill_tokens:
-                continue
-
-            selected.append(bundle)
-            total_tokens += bundle.skill_tool_tokens
-            kept += 1
-            seen_skill_keys.add(bundle.skill_key)
-
-        selected.reverse()
-        return selected
-
-    def _is_skill_tool_call(self, tool_call: dict[str, Any], skills_root: str) -> bool:
-        """Return True when ``tool_call`` reads a file under the configured skills root."""
-        name = tool_call.get("name") or ""
-        if name not in self._skill_file_read_tool_names:
-            return False
-        path = _tool_call_path(tool_call)
-        if not path:
-            return False
-        normalized_root = skills_root.rstrip("/")
-        return path == normalized_root or path.startswith(normalized_root + "/")
-
-    def _fire_hooks(
-        self,
-        messages_to_summarize: list[AnyMessage],
-        preserved_messages: list[AnyMessage],
-        runtime: Runtime,
-    ) -> None:
-        if not self._before_summarization_hooks:
-            return
-
-        event = SummarizationEvent(
-            messages_to_summarize=tuple(messages_to_summarize),
-            preserved_messages=tuple(preserved_messages),
-            thread_id=_resolve_thread_id(runtime),
-            agent_name=_resolve_agent_name(runtime),
-            runtime=runtime,
-        )
-
-        for hook in self._before_summarization_hooks:
-            try:
-                hook(event)
-            except Exception:
-                hook_name = getattr(hook, "__name__", None) or type(hook).__name__
-                logger.exception("before_summarization hook %s failed", hook_name)

backend/packages/harness/deerflow/agents/middlewares/thread_data_middleware.py

@@ -1,10 +1,8 @@
 import logging
-from datetime import UTC, datetime
 from typing import NotRequired, override
 
 from langchain.agents import AgentState
 from langchain.agents.middleware import AgentMiddleware
-from langchain_core.messages import HumanMessage
 from langgraph.config import get_config
 from langgraph.runtime import Runtime
 
@@ -99,20 +97,8 @@ class ThreadDataMiddleware(AgentMiddleware[ThreadDataMiddlewareState]):
             paths = self._create_thread_directories(thread_id, user_id=user_id)
             logger.debug("Created thread data directories for thread %s", thread_id)
 
-        messages = list(state.get("messages", []))
-        last_message = messages[-1] if messages else None
-
-        if last_message and isinstance(last_message, HumanMessage):
-            messages[-1] = HumanMessage(
-                content=last_message.content,
-                id=last_message.id,
-                name=last_message.name or "user-input",
-                additional_kwargs={**last_message.additional_kwargs, "run_id": runtime.context.get("run_id"), "timestamp": datetime.now(UTC).isoformat()},
-            )
-
         return {
             "thread_data": {
                 **paths,
-            },
-            "messages": messages,
+            }
         }

backend/packages/harness/deerflow/agents/middlewares/title_middleware.py

@@ -1,8 +1,7 @@
 """Middleware for automatic thread title generation."""
 
 import logging
-import re
-from typing import TYPE_CHECKING, Any, NotRequired, override
+from typing import Any, NotRequired, override
 
 from langchain.agents import AgentState
 from langchain.agents.middleware import AgentMiddleware
@@ -12,10 +11,6 @@ from langgraph.runtime import Runtime
 from deerflow.config.title_config import get_title_config
 from deerflow.models import create_chat_model
 
-if TYPE_CHECKING:
-    from deerflow.config.app_config import AppConfig
-    from deerflow.config.title_config import TitleConfig
-
 logger = logging.getLogger(__name__)
 
 
@@ -30,18 +25,6 @@ class TitleMiddleware(AgentMiddleware[TitleMiddlewareState]):
 
     state_schema = TitleMiddlewareState
 
-    def __init__(self, *, app_config: "AppConfig | None" = None, title_config: "TitleConfig | None" = None):
-        super().__init__()
-        self._app_config = app_config
-        self._title_config = title_config
-
-    def _get_title_config(self):
-        if self._title_config is not None:
-            return self._title_config
-        if self._app_config is not None:
-            return self._app_config.title
-        return get_title_config()
-
     def _normalize_content(self, content: object) -> str:
         if isinstance(content, str):
             return content
@@ -63,7 +46,7 @@ class TitleMiddleware(AgentMiddleware[TitleMiddlewareState]):
 
     def _should_generate_title(self, state: TitleMiddlewareState) -> bool:
         """Check if we should generate a title for this thread."""
-        config = self._get_title_config()
+        config = get_title_config()
         if not config.enabled:
             return False
 
@@ -88,14 +71,14 @@ class TitleMiddleware(AgentMiddleware[TitleMiddlewareState]):
 
         Returns (prompt_string, user_msg) so callers can use user_msg as fallback.
         """
-        config = self._get_title_config()
+        config = get_title_config()
         messages = state.get("messages", [])
 
         user_msg_content = next((m.content for m in messages if m.type == "human"), "")
         assistant_msg_content = next((m.content for m in messages if m.type == "ai"), "")
 
         user_msg = self._normalize_content(user_msg_content)
-        assistant_msg = self._strip_think_tags(self._normalize_content(assistant_msg_content))
+        assistant_msg = self._normalize_content(assistant_msg_content)
 
         prompt = config.prompt_template.format(
             max_words=config.max_words,
@@ -104,20 +87,15 @@ class TitleMiddleware(AgentMiddleware[TitleMiddlewareState]):
         )
         return prompt, user_msg
 
-    def _strip_think_tags(self, text: str) -> str:
-        """Remove <think>...</think> blocks emitted by reasoning models (e.g. minimax, DeepSeek-R1)."""
-        return re.sub(r"<think>[\s\S]*?</think>", "", text, flags=re.IGNORECASE).strip()
-
     def _parse_title(self, content: object) -> str:
         """Normalize model output into a clean title string."""
-        config = self._get_title_config()
+        config = get_title_config()
         title_content = self._normalize_content(content)
-        title_content = self._strip_think_tags(title_content)
         title = title_content.strip().strip('"').strip("'")
         return title[: config.max_chars] if len(title) > config.max_chars else title
 
     def _fallback_title(self, user_msg: str) -> str:
-        config = self._get_title_config()
+        config = get_title_config()
         fallback_chars = min(config.max_chars, 50)
         if len(user_msg) > fallback_chars:
             return user_msg[:fallback_chars].rstrip() + "..."
@@ -134,7 +112,6 @@ class TitleMiddleware(AgentMiddleware[TitleMiddlewareState]):
         except Exception:
             parent = {}
         config = {**parent}
-        config["run_name"] = "title_agent"
         config["tags"] = [*(config.get("tags") or []), "middleware:title"]
         return config
 
@@ -151,17 +128,14 @@ class TitleMiddleware(AgentMiddleware[TitleMiddlewareState]):
         if not self._should_generate_title(state):
             return None
 
-        config = self._get_title_config()
+        config = get_title_config()
         prompt, user_msg = self._build_title_prompt(state)
 
         try:
-            model_kwargs = {"thinking_enabled": False}
-            if self._app_config is not None:
-                model_kwargs["app_config"] = self._app_config
             if config.model_name:
-                model = create_chat_model(name=config.model_name, **model_kwargs)
+                model = create_chat_model(name=config.model_name, thinking_enabled=False)
             else:
-                model = create_chat_model(**model_kwargs)
+                model = create_chat_model(thinking_enabled=False)
             response = await model.ainvoke(prompt, config=self._get_runnable_config())
             title = self._parse_title(response.content)
             if title:

backend/packages/harness/deerflow/agents/middlewares/todo_middleware.py

@@ -1,14 +1,9 @@
-"""Middleware that extends TodoListMiddleware with context-loss detection and premature-exit prevention.
+"""Middleware that extends TodoListMiddleware with context-loss detection.
 
 When the message history is truncated (e.g., by SummarizationMiddleware), the
 original `write_todos` tool call and its ToolMessage can be scrolled out of the
 active context window. This middleware detects that situation and injects a
 reminder message so the model still knows about the outstanding todo list.
-
-Additionally, this middleware prevents the agent from exiting the loop while
-there are still incomplete todo items. When the model produces a final response
-(no tool calls) but todos are not yet complete, the middleware injects a reminder
-and jumps back to the model node to force continued engagement.
 """
 
 from __future__ import annotations
@@ -17,7 +12,6 @@ from typing import Any, override
 
 from langchain.agents.middleware import TodoListMiddleware
 from langchain.agents.middleware.todo import PlanningState, Todo
-from langchain.agents.middleware.types import hook_config
 from langchain_core.messages import AIMessage, HumanMessage
 from langgraph.runtime import Runtime
 
@@ -40,11 +34,6 @@ def _reminder_in_messages(messages: list[Any]) -> bool:
     return False
 
 
-def _completion_reminder_count(messages: list[Any]) -> int:
-    """Return the number of todo_completion_reminder HumanMessages in *messages*."""
-    return sum(1 for msg in messages if isinstance(msg, HumanMessage) and getattr(msg, "name", None) == "todo_completion_reminder")
-
-
 def _format_todos(todos: list[Todo]) -> str:
     """Format a list of Todo items into a human-readable string."""
     lines: list[str] = []
@@ -68,7 +57,7 @@ class TodoMiddleware(TodoListMiddleware):
     def before_model(
         self,
         state: PlanningState,
-        runtime: Runtime,
+        runtime: Runtime,  # noqa: ARG002
     ) -> dict[str, Any] | None:
         """Inject a todo-list reminder when write_todos has left the context window."""
         todos: list[Todo] = state.get("todos") or []  # type: ignore[assignment]
@@ -109,71 +98,3 @@ class TodoMiddleware(TodoListMiddleware):
     ) -> dict[str, Any] | None:
         """Async version of before_model."""
         return self.before_model(state, runtime)
-
-    # Maximum number of completion reminders before allowing the agent to exit.
-    # This prevents infinite loops when the agent cannot make further progress.
-    _MAX_COMPLETION_REMINDERS = 2
-
-    @hook_config(can_jump_to=["model"])
-    @override
-    def after_model(
-        self,
-        state: PlanningState,
-        runtime: Runtime,
-    ) -> dict[str, Any] | None:
-        """Prevent premature agent exit when todo items are still incomplete.
-
-        In addition to the base class check for parallel ``write_todos`` calls,
-        this override intercepts model responses that have no tool calls while
-        there are still incomplete todo items. It injects a reminder
-        ``HumanMessage`` and jumps back to the model node so the agent
-        continues working through the todo list.
-
-        A retry cap of ``_MAX_COMPLETION_REMINDERS`` (default 2) prevents
-        infinite loops when the agent cannot make further progress.
-        """
-        # 1. Preserve base class logic (parallel write_todos detection).
-        base_result = super().after_model(state, runtime)
-        if base_result is not None:
-            return base_result
-
-        # 2. Only intervene when the agent wants to exit (no tool calls).
-        messages = state.get("messages") or []
-        last_ai = next((m for m in reversed(messages) if isinstance(m, AIMessage)), None)
-        if not last_ai or last_ai.tool_calls:
-            return None
-
-        # 3. Allow exit when all todos are completed or there are no todos.
-        todos: list[Todo] = state.get("todos") or []  # type: ignore[assignment]
-        if not todos or all(t.get("status") == "completed" for t in todos):
-            return None
-
-        # 4. Enforce a reminder cap to prevent infinite re-engagement loops.
-        if _completion_reminder_count(messages) >= self._MAX_COMPLETION_REMINDERS:
-            return None
-
-        # 5. Inject a reminder and force the agent back to the model.
-        incomplete = [t for t in todos if t.get("status") != "completed"]
-        incomplete_text = "\n".join(f"- [{t.get('status', 'pending')}] {t.get('content', '')}" for t in incomplete)
-        reminder = HumanMessage(
-            name="todo_completion_reminder",
-            content=(
-                "<system_reminder>\n"
-                "You have incomplete todo items that must be finished before giving your final response:\n\n"
-                f"{incomplete_text}\n\n"
-                "Please continue working on these tasks. Call `write_todos` to mark items as completed "
-                "as you finish them, and only respond when all items are done.\n"
-                "</system_reminder>"
-            ),
-        )
-        return {"jump_to": "model", "messages": [reminder]}
-
-    @override
-    @hook_config(can_jump_to=["model"])
-    async def aafter_model(
-        self,
-        state: PlanningState,
-        runtime: Runtime,
-    ) -> dict[str, Any] | None:
-        """Async version of after_model."""
-        return self.after_model(state, runtime)

backend/packages/harness/deerflow/agents/middlewares/tool_error_handling_middleware.py

@@ -11,8 +11,6 @@ from langgraph.errors import GraphBubbleUp
 from langgraph.prebuilt.tool_node import ToolCallRequest
 from langgraph.types import Command
 
-from deerflow.config.app_config import AppConfig
-
 logger = logging.getLogger(__name__)
 
 _MISSING_TOOL_CALL_ID = "missing_tool_call_id"
@@ -69,7 +67,6 @@ class ToolErrorHandlingMiddleware(AgentMiddleware[AgentState]):
 
 def _build_runtime_middlewares(
     *,
-    app_config: AppConfig,
     include_uploads: bool,
     include_dangling_tool_call_patch: bool,
     lazy_init: bool = True,
@@ -94,10 +91,12 @@ def _build_runtime_middlewares(
 
         middlewares.append(DanglingToolCallMiddleware())
 
-    middlewares.append(LLMErrorHandlingMiddleware(app_config=app_config))
+    middlewares.append(LLMErrorHandlingMiddleware())
 
     # Guardrail middleware (if configured)
-    guardrails_config = app_config.guardrails
+    from deerflow.config.guardrails_config import get_guardrails_config
+
+    guardrails_config = get_guardrails_config()
     if guardrails_config.enabled and guardrails_config.provider:
         import inspect
 
@@ -126,42 +125,19 @@ def _build_runtime_middlewares(
     return middlewares
 
 
-def build_lead_runtime_middlewares(*, app_config: AppConfig, lazy_init: bool = True) -> list[AgentMiddleware]:
+def build_lead_runtime_middlewares(*, lazy_init: bool = True) -> list[AgentMiddleware]:
     """Middlewares shared by lead agent runtime before lead-only middlewares."""
     return _build_runtime_middlewares(
-        app_config=app_config,
         include_uploads=True,
         include_dangling_tool_call_patch=True,
         lazy_init=lazy_init,
     )
 
 
-def build_subagent_runtime_middlewares(
-    *,
-    app_config: AppConfig | None = None,
-    model_name: str | None = None,
-    lazy_init: bool = True,
-) -> list[AgentMiddleware]:
+def build_subagent_runtime_middlewares(*, lazy_init: bool = True) -> list[AgentMiddleware]:
     """Middlewares shared by subagent runtime before subagent-only middlewares."""
-    if app_config is None:
-        from deerflow.config import get_app_config
-
-        app_config = get_app_config()
-
-    middlewares = _build_runtime_middlewares(
-        app_config=app_config,
+    return _build_runtime_middlewares(
         include_uploads=False,
         include_dangling_tool_call_patch=True,
         lazy_init=lazy_init,
     )
-
-    if model_name is None and app_config.models:
-        model_name = app_config.models[0].name
-
-    model_config = app_config.get_model_config(model_name) if model_name else None
-    if model_config is not None and model_config.supports_vision:
-        from deerflow.agents.middlewares.view_image_middleware import ViewImageMiddleware
-
-        middlewares.append(ViewImageMiddleware())
-
-    return middlewares

backend/packages/harness/deerflow/agents/middlewares/uploads_middleware.py

@@ -263,27 +263,22 @@ class UploadsMiddleware(AgentMiddleware[UploadsMiddlewareState]):
         files_message = self._create_files_message(new_files, historical_files)
 
         # Extract original content - handle both string and list formats
-        original_content = last_message.content
-        if isinstance(original_content, str):
-            # Simple case: string content, just prepend files message
-            updated_content = f"{files_message}\n\n{original_content}"
-        elif isinstance(original_content, list):
-            # Complex case: list content (multimodal), preserve all blocks
-            # Prepend files message as the first text block
-            files_block = {"type": "text", "text": f"{files_message}\n\n"}
-            # Keep all original blocks (including images)
-            updated_content = [files_block, *original_content]
-        else:
-            # Other types, preserve as-is
-            updated_content = original_content
+        original_content = ""
+        if isinstance(last_message.content, str):
+            original_content = last_message.content
+        elif isinstance(last_message.content, list):
+            text_parts = []
+            for block in last_message.content:
+                if isinstance(block, dict) and block.get("type") == "text":
+                    text_parts.append(block.get("text", ""))
+            original_content = "\n".join(text_parts)
 
         # Create new message with combined content.
         # Preserve additional_kwargs (including files metadata) so the frontend
         # can read structured file info from the streamed message.
         updated_message = HumanMessage(
-            content=updated_content,
+            content=f"{files_message}\n\n{original_content}",
             id=last_message.id,
-            name=last_message.name,
             additional_kwargs=last_message.additional_kwargs,
         )
 

backend/packages/harness/deerflow/client.py

@@ -41,7 +41,7 @@ from deerflow.config.extensions_config import ExtensionsConfig, SkillStateConfig
 from deerflow.config.paths import get_paths
 from deerflow.models import create_chat_model
 from deerflow.runtime.user_context import get_effective_user_id
-from deerflow.skills.storage import get_or_new_skill_storage
+from deerflow.skills.installer import install_skill_from_archive
 from deerflow.uploads.manager import (
     claim_unique_filename,
     delete_file_safe,
@@ -228,21 +228,14 @@ class DeerFlowClient:
         max_concurrent_subagents = cfg.get("max_concurrent_subagents", 3)
 
         kwargs: dict[str, Any] = {
-            "model": create_chat_model(name=model_name, thinking_enabled=thinking_enabled, app_config=self._app_config),
+            "model": create_chat_model(name=model_name, thinking_enabled=thinking_enabled),
             "tools": self._get_tools(model_name=model_name, subagent_enabled=subagent_enabled),
-            "middleware": _build_middlewares(
-                config,
-                model_name=model_name,
-                agent_name=self._agent_name,
-                custom_middlewares=self._middlewares,
-                app_config=self._app_config,
-            ),
+            "middleware": _build_middlewares(config, model_name=model_name, agent_name=self._agent_name, custom_middlewares=self._middlewares),
             "system_prompt": apply_prompt_template(
                 subagent_enabled=subagent_enabled,
                 max_concurrent_subagents=max_concurrent_subagents,
                 agent_name=self._agent_name,
                 available_skills=self._available_skills,
-                app_config=self._app_config,
             ),
             "state_schema": ThreadState,
         }
@@ -250,7 +243,7 @@ class DeerFlowClient:
         if checkpointer is None:
             from deerflow.runtime.checkpointer import get_checkpointer
 
-            checkpointer = get_checkpointer(app_config=self._app_config)
+            checkpointer = get_checkpointer()
         if checkpointer is not None:
             kwargs["checkpointer"] = checkpointer
 
@@ -258,15 +251,12 @@ class DeerFlowClient:
         self._agent_config_key = key
         logger.info("Agent created: agent_name=%s, model=%s, thinking=%s", self._agent_name, model_name, thinking_enabled)
 
-    def _get_tools(self, *, model_name: str | None, subagent_enabled: bool):
+    @staticmethod
+    def _get_tools(*, model_name: str | None, subagent_enabled: bool):
         """Lazy import to avoid circular dependency at module level."""
         from deerflow.tools import get_available_tools
 
-        return get_available_tools(
-            model_name=model_name,
-            subagent_enabled=subagent_enabled,
-            app_config=self._app_config,
-        )
+        return get_available_tools(model_name=model_name, subagent_enabled=subagent_enabled)
 
     @staticmethod
     def _serialize_tool_calls(tool_calls) -> list[dict]:
@@ -387,7 +377,7 @@ class DeerFlowClient:
         if checkpointer is None:
             from deerflow.runtime.checkpointer.provider import get_checkpointer
 
-            checkpointer = get_checkpointer(app_config=self._app_config)
+            checkpointer = get_checkpointer()
 
         thread_info_map = {}
 
@@ -442,7 +432,7 @@ class DeerFlowClient:
         if checkpointer is None:
             from deerflow.runtime.checkpointer.provider import get_checkpointer
 
-            checkpointer = get_checkpointer(app_config=self._app_config)
+            checkpointer = get_checkpointer()
 
         config = {"configurable": {"thread_id": thread_id}}
         checkpoints = []
@@ -733,10 +723,6 @@ class DeerFlowClient:
             Dict with "models" key containing list of model info dicts,
             matching the Gateway API ``ModelsListResponse`` schema.
         """
-        token_usage_enabled = getattr(getattr(self._app_config, "token_usage", None), "enabled", False)
-        if not isinstance(token_usage_enabled, bool):
-            token_usage_enabled = False
-
         return {
             "models": [
                 {
@@ -748,8 +734,7 @@ class DeerFlowClient:
                     "supports_reasoning_effort": getattr(model, "supports_reasoning_effort", False),
                 }
                 for model in self._app_config.models
-            ],
-            "token_usage": {"enabled": token_usage_enabled},
+            ]
         }
 
     def list_skills(self, enabled_only: bool = False) -> dict:
@@ -762,6 +747,8 @@ class DeerFlowClient:
             Dict with "skills" key containing list of skill info dicts,
             matching the Gateway API ``SkillsListResponse`` schema.
         """
+        from deerflow.skills.loader import load_skills
+
         return {
             "skills": [
                 {
@@ -771,7 +758,7 @@ class DeerFlowClient:
                     "category": s.category,
                     "enabled": s.enabled,
                 }
-                for s in get_or_new_skill_storage().load_skills(enabled_only=enabled_only)
+                for s in load_skills(enabled_only=enabled_only)
             ]
         }
 
@@ -880,9 +867,9 @@ class DeerFlowClient:
         Returns:
             Skill info dict, or None if not found.
         """
-        from deerflow.skills.storage import get_or_new_skill_storage
+        from deerflow.skills.loader import load_skills
 
-        skill = next((s for s in get_or_new_skill_storage().load_skills(enabled_only=False) if s.name == name), None)
+        skill = next((s for s in load_skills(enabled_only=False) if s.name == name), None)
         if skill is None:
             return None
         return {
@@ -907,9 +894,9 @@ class DeerFlowClient:
             ValueError: If the skill is not found.
             OSError: If the config file cannot be written.
         """
-        from deerflow.skills.storage import get_or_new_skill_storage
+        from deerflow.skills.loader import load_skills
 
-        skills = get_or_new_skill_storage().load_skills(enabled_only=False)
+        skills = load_skills(enabled_only=False)
         skill = next((s for s in skills if s.name == name), None)
         if skill is None:
             raise ValueError(f"Skill '{name}' not found")
@@ -932,7 +919,7 @@ class DeerFlowClient:
         self._agent_config_key = None
         reload_extensions_config()
 
-        updated = next((s for s in get_or_new_skill_storage().load_skills(enabled_only=False) if s.name == name), None)
+        updated = next((s for s in load_skills(enabled_only=False) if s.name == name), None)
         if updated is None:
             raise RuntimeError(f"Skill '{name}' disappeared after update")
         return {
@@ -956,7 +943,7 @@ class DeerFlowClient:
             FileNotFoundError: If the file does not exist.
             ValueError: If the file is invalid.
         """
-        return get_or_new_skill_storage().install_skill_from_archive(skill_path)
+        return install_skill_from_archive(skill_path)
 
     # ------------------------------------------------------------------
     # Public API — memory management

backend/packages/harness/deerflow/community/aio_sandbox/aio_sandbox.py

@@ -48,12 +48,6 @@ class AioSandbox(Sandbox):
             self._home_dir = context.home_dir
         return self._home_dir
 
-    # Default no_change_timeout for exec_command (seconds).  Matches the
-    # client-level timeout so that long-running commands which produce no
-    # output are not prematurely terminated by the sandbox's built-in 120 s
-    # default.
-    _DEFAULT_NO_CHANGE_TIMEOUT = 600
-
     def execute_command(self, command: str) -> str:
         """Execute a shell command in the sandbox.
 
@@ -72,13 +66,13 @@ class AioSandbox(Sandbox):
         """
         with self._lock:
             try:
-                result = self._client.shell.exec_command(command=command, no_change_timeout=self._DEFAULT_NO_CHANGE_TIMEOUT)
+                result = self._client.shell.exec_command(command=command)
                 output = result.data.output if result.data else ""
 
                 if output and _ERROR_OBSERVATION_SIGNATURE in output:
                     logger.warning("ErrorObservation detected in sandbox output, retrying with a fresh session")
                     fresh_id = str(uuid.uuid4())
-                    result = self._client.shell.exec_command(command=command, id=fresh_id, no_change_timeout=self._DEFAULT_NO_CHANGE_TIMEOUT)
+                    result = self._client.shell.exec_command(command=command, id=fresh_id)
                     output = result.data.output if result.data else ""
 
                 return output if output else "(no output)"
@@ -114,7 +108,7 @@ class AioSandbox(Sandbox):
         """
         with self._lock:
             try:
-                result = self._client.shell.exec_command(command=f"find {shlex.quote(path)} -maxdepth {max_depth} -type f -o -type d 2>/dev/null | head -500", no_change_timeout=self._DEFAULT_NO_CHANGE_TIMEOUT)
+                result = self._client.shell.exec_command(command=f"find {shlex.quote(path)} -maxdepth {max_depth} -type f -o -type d 2>/dev/null | head -500")
                 output = result.data.output if result.data else ""
                 if output:
                     return [line.strip() for line in output.strip().split("\n") if line.strip()]

backend/packages/harness/deerflow/community/aio_sandbox/aio_sandbox_provider.py

@@ -120,16 +120,6 @@ class AioSandboxProvider(SandboxProvider):
         if self._config.get("idle_timeout", DEFAULT_IDLE_TIMEOUT) > 0:
             self._start_idle_checker()
 
-    @property
-    def uses_thread_data_mounts(self) -> bool:
-        """Whether thread workspace/uploads/outputs are visible via mounts.
-
-        Local container backends bind-mount the thread data directories, so files
-        written by the gateway are already visible when the sandbox starts.
-        Remote backends may require explicit file sync.
-        """
-        return isinstance(self._backend, LocalContainerBackend)
-
     # ── Factory methods ──────────────────────────────────────────────────
 
     def _create_backend(self) -> SandboxBackend:

backend/packages/harness/deerflow/community/aio_sandbox/local_backend.py

@@ -9,7 +9,6 @@ from __future__ import annotations
 import json
 import logging
 import os
-import shlex
 import subprocess
 from datetime import datetime
 
@@ -87,88 +86,6 @@ def _format_container_mount(runtime: str, host_path: str, container_path: str, r
     return ["-v", mount_spec]
 
 
-def _redact_container_command_for_log(cmd: list[str]) -> list[str]:
-    """Return a Docker/Container command with environment values redacted."""
-    redacted: list[str] = []
-    redact_next_env = False
-
-    for arg in cmd:
-        if redact_next_env:
-            if "=" in arg:
-                key = arg.split("=", 1)[0]
-                redacted.append(f"{key}=<redacted>" if key else "<redacted>")
-            else:
-                redacted.append(arg)
-            redact_next_env = False
-            continue
-
-        if arg in {"-e", "--env"}:
-            redacted.append(arg)
-            redact_next_env = True
-            continue
-
-        if arg.startswith("--env="):
-            value = arg.removeprefix("--env=")
-            if "=" in value:
-                key = value.split("=", 1)[0]
-                redacted.append(f"--env={key}=<redacted>" if key else "--env=<redacted>")
-            else:
-                redacted.append(arg)
-            continue
-
-        redacted.append(arg)
-
-    return redacted
-
-
-def _format_container_command_for_log(cmd: list[str]) -> str:
-    if os.name == "nt":
-        return subprocess.list2cmdline(cmd)
-    return shlex.join(cmd)
-
-
-def _normalize_sandbox_host(host: str) -> str:
-    return host.strip().lower()
-
-
-def _is_ipv6_loopback_sandbox_host(host: str) -> bool:
-    return _normalize_sandbox_host(host) in {"::1", "[::1]"}
-
-
-def _is_loopback_sandbox_host(host: str) -> bool:
-    return _normalize_sandbox_host(host) in {"", "localhost", "127.0.0.1", "::1", "[::1]"}
-
-
-def _resolve_docker_bind_host(sandbox_host: str | None = None, bind_host: str | None = None) -> str:
-    """Choose the host interface for legacy Docker ``-p`` sandbox publishing.
-
-    Bare-metal/local runs talk to sandboxes through localhost and should not
-    expose the sandbox HTTP API on every host interface.  Docker-outside-of-
-    Docker deployments commonly use ``host.docker.internal`` from another
-    container; keep their legacy broad bind unless operators opt into a
-    narrower bind with ``DEER_FLOW_SANDBOX_BIND_HOST``.  When operators choose
-    an IPv6 loopback sandbox host, bind Docker to IPv6 loopback as well so the
-    advertised sandbox URL and published socket use the same address family.
-    """
-    explicit_bind = bind_host if bind_host is not None else os.environ.get("DEER_FLOW_SANDBOX_BIND_HOST")
-    if explicit_bind is not None:
-        explicit_bind = explicit_bind.strip()
-        if explicit_bind:
-            logger.debug("Docker sandbox bind: %s (explicit bind host override)", explicit_bind)
-            return explicit_bind
-
-    host = sandbox_host if sandbox_host is not None else os.environ.get("DEER_FLOW_SANDBOX_HOST", "localhost")
-    if _is_ipv6_loopback_sandbox_host(host):
-        logger.debug("Docker sandbox bind: [::1] (IPv6 loopback sandbox host)")
-        return "[::1]"
-    if _is_loopback_sandbox_host(host):
-        logger.debug("Docker sandbox bind: 127.0.0.1 (loopback default)")
-        return "127.0.0.1"
-
-    logger.debug("Docker sandbox bind: 0.0.0.0 (non-loopback sandbox host compatibility)")
-    return "0.0.0.0"
-
-
 class LocalContainerBackend(SandboxBackend):
     """Backend that manages sandbox containers locally using Docker or Apple Container.
 
@@ -507,17 +424,12 @@ class LocalContainerBackend(SandboxBackend):
         if self._runtime == "docker":
             cmd.extend(["--security-opt", "seccomp=unconfined"])
 
-        if self._runtime == "docker":
-            port_mapping = f"{_resolve_docker_bind_host()}:{port}:8080"
-        else:
-            port_mapping = f"{port}:8080"
-
         cmd.extend(
             [
                 "--rm",
                 "-d",
                 "-p",
-                port_mapping,
+                f"{port}:8080",
                 "--name",
                 container_name,
             ]
@@ -552,8 +464,7 @@ class LocalContainerBackend(SandboxBackend):
 
         cmd.append(self._image)
 
-        log_cmd = _format_container_command_for_log(_redact_container_command_for_log(cmd))
-        logger.info(f"Starting container using {self._runtime}: {log_cmd}")
+        logger.info(f"Starting container using {self._runtime}: {' '.join(cmd)}")
 
         try:
             result = subprocess.run(cmd, capture_output=True, text=True, check=True)

backend/packages/harness/deerflow/community/jina_ai/jina_client.py

@@ -38,6 +38,6 @@ class JinaClient:
 
             return response.text
         except Exception as e:
-            error_message = f"Request to Jina API failed: {type(e).__name__}: {e}"
-            logger.warning(error_message)
+            error_message = f"Request to Jina API failed: {str(e)}"
+            logger.exception(error_message)
             return f"Error: {error_message}"

backend/packages/harness/deerflow/community/jina_ai/tools.py

@@ -1,5 +1,3 @@
-import asyncio
-
 from langchain.tools import tool
 
 from deerflow.community.jina_ai.jina_client import JinaClient
@@ -28,5 +26,5 @@ async def web_fetch_tool(url: str) -> str:
     html_content = await jina_client.crawl(url, return_format="html", timeout=timeout)
     if isinstance(html_content, str) and html_content.startswith("Error:"):
         return html_content
-    article = await asyncio.to_thread(readability_extractor.extract_article, html_content)
+    article = readability_extractor.extract_article(html_content)
     return article.to_markdown()[:4096]

backend/packages/harness/deerflow/config/agents_api_config.py

@@ -1,32 +0,0 @@
-"""Configuration for the custom agents management API."""
-
-from pydantic import BaseModel, Field
-
-
-class AgentsApiConfig(BaseModel):
-    """Configuration for custom-agent and user-profile management routes."""
-
-    enabled: bool = Field(
-        default=False,
-        description=("Whether to expose the custom-agent management API over HTTP. When disabled, the gateway rejects read/write access to custom agent SOUL.md, config, and USER.md prompt-management routes."),
-    )
-
-
-_agents_api_config: AgentsApiConfig = AgentsApiConfig()
-
-
-def get_agents_api_config() -> AgentsApiConfig:
-    """Get the current agents API configuration."""
-    return _agents_api_config
-
-
-def set_agents_api_config(config: AgentsApiConfig) -> None:
-    """Set the agents API configuration."""
-    global _agents_api_config
-    _agents_api_config = config
-
-
-def load_agents_api_config_from_dict(config_dict: dict) -> None:
-    """Load agents API configuration from a dictionary."""
-    global _agents_api_config
-    _agents_api_config = AgentsApiConfig(**config_dict)

backend/packages/harness/deerflow/config/agents_config.py

@@ -15,17 +15,6 @@ SOUL_FILENAME = "SOUL.md"
 AGENT_NAME_PATTERN = re.compile(r"^[A-Za-z0-9-]+$")
 
 
-def validate_agent_name(name: str | None) -> str | None:
-    """Validate a custom agent name before using it in filesystem paths."""
-    if name is None:
-        return None
-    if not isinstance(name, str):
-        raise ValueError("Invalid agent name. Expected a string or None.")
-    if not AGENT_NAME_PATTERN.fullmatch(name):
-        raise ValueError(f"Invalid agent name '{name}'. Must match pattern: {AGENT_NAME_PATTERN.pattern}")
-    return name
-
-
 class AgentConfig(BaseModel):
     """Configuration for a custom agent."""
 
@@ -57,7 +46,8 @@ def load_agent_config(name: str | None) -> AgentConfig | None:
     if name is None:
         return None
 
-    name = validate_agent_name(name)
+    if not AGENT_NAME_PATTERN.match(name):
+        raise ValueError(f"Invalid agent name '{name}'. Must match pattern: {AGENT_NAME_PATTERN.pattern}")
     agent_dir = get_paths().agent_dir(name)
     config_file = agent_dir / "config.yaml"
 

backend/packages/harness/deerflow/config/app_config.py

@@ -8,8 +8,7 @@ import yaml
 from dotenv import load_dotenv
 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.acp_config import load_acp_config_from_dict
 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
@@ -17,7 +16,6 @@ from deerflow.config.guardrails_config import GuardrailsConfig, load_guardrails_
 from deerflow.config.memory_config import MemoryConfig, load_memory_config_from_dict
 from deerflow.config.model_config import ModelConfig
 from deerflow.config.run_events_config import RunEventsConfig
-from deerflow.config.runtime_paths import existing_project_file
 from deerflow.config.sandbox_config import SandboxConfig
 from deerflow.config.skill_evolution_config import SkillEvolutionConfig
 from deerflow.config.skills_config import SkillsConfig
@@ -34,54 +32,17 @@ load_dotenv()
 logger = logging.getLogger(__name__)
 
 
-CONFIG_FILE_DATABASE_DEFAULTS = {
-    "backend": "sqlite",
-    "sqlite_dir": ".deer-flow/data",
-}
-
-
-class CircuitBreakerConfig(BaseModel):
-    """Configuration for the LLM Circuit Breaker."""
-
-    failure_threshold: int = Field(default=5, description="Number of consecutive failures before tripping the circuit")
-    recovery_timeout_sec: int = Field(default=60, description="Time in seconds before attempting to recover the circuit")
-
-
-def _legacy_config_candidates() -> tuple[Path, ...]:
-    """Return source-tree config.yaml locations for monorepo compatibility."""
+def _default_config_candidates() -> tuple[Path, ...]:
+    """Return deterministic config.yaml locations without relying on cwd."""
     backend_dir = Path(__file__).resolve().parents[4]
     repo_root = backend_dir.parent
     return (backend_dir / "config.yaml", repo_root / "config.yaml")
 
 
-def logging_level_from_config(name: str | None) -> int:
-    """Map ``config.yaml`` ``log_level`` string to a :mod:`logging` level constant."""
-    mapping = logging.getLevelNamesMapping()
-    return mapping.get((name or "info").strip().upper(), logging.INFO)
-
-
-def apply_logging_level(name: str | None) -> None:
-    """Resolve *name* to a logging level and apply it to the ``deerflow``/``app`` logger hierarchies.
-
-    Only the ``deerflow`` and ``app`` logger levels are changed so that
-    third-party library verbosity (e.g. uvicorn, sqlalchemy) is not
-    affected. Root handler levels are lowered (never raised) so that
-    messages from the configured loggers can propagate through without
-    being filtered, while preserving handler thresholds that may be
-    intentionally restrictive for third-party log output.
-    """
-    level = logging_level_from_config(name)
-    for logger_name in ("deerflow", "app"):
-        logging.getLogger(logger_name).setLevel(level)
-    for handler in logging.root.handlers:
-        if level < handler.level:
-            handler.setLevel(level)
-
-
 class AppConfig(BaseModel):
     """Config for the DeerFlow application"""
 
-    log_level: str = Field(default="info", description="Logging level for deerflow and app modules (debug/info/warning/error); third-party libraries are not affected")
+    log_level: str = Field(default="info", description="Logging level for deerflow modules (debug/info/warning/error)")
     token_usage: TokenUsageConfig = Field(default_factory=TokenUsageConfig, description="Token usage tracking configuration")
     models: list[ModelConfig] = Field(default_factory=list, description="Available models")
     sandbox: SandboxConfig = Field(description="Sandbox configuration")
@@ -94,12 +55,9 @@ class AppConfig(BaseModel):
     title: TitleConfig = Field(default_factory=TitleConfig, description="Automatic title generation configuration")
     summarization: SummarizationConfig = Field(default_factory=SummarizationConfig, description="Conversation summarization configuration")
     memory: MemoryConfig = Field(default_factory=MemoryConfig, description="Memory subsystem configuration")
-    agents_api: AgentsApiConfig = Field(default_factory=AgentsApiConfig, description="Custom-agent management API configuration")
-    acp_agents: dict[str, ACPAgentConfig] = Field(default_factory=dict, description="ACP-compatible agent configuration")
     subagents: SubagentsAppConfig = Field(default_factory=SubagentsAppConfig, description="Subagent runtime configuration")
     guardrails: GuardrailsConfig = Field(default_factory=GuardrailsConfig, description="Guardrail middleware configuration")
-    circuit_breaker: CircuitBreakerConfig = Field(default_factory=CircuitBreakerConfig, description="LLM circuit breaker configuration")
-    model_config = ConfigDict(extra="allow")
+    model_config = ConfigDict(extra="allow", frozen=False)
     database: DatabaseConfig = Field(default_factory=DatabaseConfig, description="Unified database backend configuration")
     run_events: RunEventsConfig = Field(default_factory=RunEventsConfig, description="Run event storage configuration")
     checkpointer: CheckpointerConfig | None = Field(default=None, description="Checkpointer configuration")
@@ -112,8 +70,7 @@ class AppConfig(BaseModel):
         Priority:
         1. If provided `config_path` argument, use it.
         2. If provided `DEER_FLOW_CONFIG_PATH` environment variable, use it.
-        3. Otherwise, search the caller project root.
-        4. Finally, search legacy backend/repository-root defaults for monorepo compatibility.
+        3. Otherwise, search deterministic backend/repository-root defaults from `_default_config_candidates()`.
         """
         if config_path:
             path = Path(config_path)
@@ -126,14 +83,10 @@ class AppConfig(BaseModel):
                 raise FileNotFoundError(f"Config file specified by environment variable `DEER_FLOW_CONFIG_PATH` not found at {path}")
             return path
         else:
-            project_config = existing_project_file(("config.yaml",))
-            if project_config is not None:
-                return project_config
-
-            for path in _legacy_config_candidates():
+            for path in _default_config_candidates():
                 if path.exists():
                     return path
-            raise FileNotFoundError("`config.yaml` file not found in the project root or legacy backend/repository root locations")
+            raise FileNotFoundError("`config.yaml` file not found at the default backend or repository root locations")
 
     @classmethod
     def from_file(cls, config_path: str | None = None) -> Self:
@@ -155,7 +108,6 @@ class AppConfig(BaseModel):
         cls._check_config_version(config_data, resolved_path)
 
         config_data = cls.resolve_env_variables(config_data)
-        cls._apply_database_defaults(config_data)
 
         # Load title config if present
         if "title" in config_data:
@@ -169,10 +121,6 @@ class AppConfig(BaseModel):
         if "memory" in config_data:
             load_memory_config_from_dict(config_data["memory"])
 
-        # Always refresh agents API config so removed config sections reset
-        # singleton-backed state to its default/disabled values on reload.
-        load_agents_api_config_from_dict(config_data.get("agents_api") or {})
-
         # Load subagents config if present
         if "subagents" in config_data:
             load_subagents_config_from_dict(config_data["subagents"])
@@ -185,10 +133,6 @@ class AppConfig(BaseModel):
         if "guardrails" in config_data:
             load_guardrails_config_from_dict(config_data["guardrails"])
 
-        # Load circuit_breaker config if present
-        if "circuit_breaker" in config_data:
-            config_data["circuit_breaker"] = config_data["circuit_breaker"]
-
         # Load checkpointer config if present
         if "checkpointer" in config_data:
             load_checkpointer_config_from_dict(config_data["checkpointer"])
@@ -207,18 +151,6 @@ class AppConfig(BaseModel):
         result = cls.model_validate(config_data)
         return result
 
-    @classmethod
-    def _apply_database_defaults(cls, config_data: dict[str, Any]) -> None:
-        """Apply config.yaml defaults for persistence when the section is absent."""
-        database_config = config_data.get("database")
-        if database_config is None:
-            database_config = {}
-            config_data["database"] = database_config
-        if not isinstance(database_config, dict):
-            return
-        for key, value in CONFIG_FILE_DATABASE_DEFAULTS.items():
-            database_config.setdefault(key, value)
-
     @classmethod
     def _check_config_version(cls, config_data: dict, config_path: Path) -> None:
         """Check if the user's config.yaml is outdated compared to config.example.yaml.
@@ -323,9 +255,6 @@ class AppConfig(BaseModel):
         return next((group for group in self.tool_groups if group.name == name), None)
 
 
-# Compatibility singleton layer for code paths that have not yet been
-# migrated to explicit ``AppConfig`` threading. New composition roots should
-# prefer constructing ``AppConfig`` once and passing it down directly.
 _app_config: AppConfig | None = None
 _app_config_path: Path | None = None
 _app_config_mtime: float | None = None

backend/packages/harness/deerflow/config/extensions_config.py

@@ -7,8 +7,6 @@ from typing import Any, Literal
 
 from pydantic import BaseModel, ConfigDict, Field
 
-from deerflow.config.runtime_paths import existing_project_file
-
 
 class McpOAuthConfig(BaseModel):
     """OAuth configuration for an MCP server (HTTP/SSE transports)."""
@@ -75,8 +73,8 @@ class ExtensionsConfig(BaseModel):
         Priority:
         1. If provided `config_path` argument, use it.
         2. If provided `DEER_FLOW_EXTENSIONS_CONFIG_PATH` environment variable, use it.
-        3. Otherwise, search the caller project root for `extensions_config.json`, then `mcp_config.json`.
-        4. For backward compatibility, also search legacy backend/repository-root defaults.
+        3. Otherwise, check for `extensions_config.json` in the current directory, then in the parent directory.
+        4. For backward compatibility, also check for `mcp_config.json` if `extensions_config.json` is not found.
         5. If not found, return None (extensions are optional).
 
         Args:
@@ -85,9 +83,8 @@ class ExtensionsConfig(BaseModel):
         Resolution order:
             1. If provided `config_path` argument, use it.
             2. If provided `DEER_FLOW_EXTENSIONS_CONFIG_PATH` environment variable, use it.
-            3. Otherwise, search the caller project root for
+            3. Otherwise, search backend/repository-root defaults for
                `extensions_config.json`, then legacy `mcp_config.json`.
-            4. Finally, search backend/repository-root defaults for monorepo compatibility.
 
         Returns:
             Path to the extensions config file if found, otherwise None.
@@ -103,10 +100,6 @@ class ExtensionsConfig(BaseModel):
                 raise FileNotFoundError(f"Extensions config file specified by environment variable `DEER_FLOW_EXTENSIONS_CONFIG_PATH` not found at {path}")
             return path
         else:
-            project_config = existing_project_file(("extensions_config.json", "mcp_config.json"))
-            if project_config is not None:
-                return project_config
-
             backend_dir = Path(__file__).resolve().parents[4]
             repo_root = backend_dir.parent
             for path in (

backend/packages/harness/deerflow/config/paths.py

@@ -3,8 +3,6 @@ import re
 import shutil
 from pathlib import Path, PureWindowsPath
 
-from deerflow.config.runtime_paths import runtime_home
-
 # Virtual path prefix seen by agents inside the sandbox
 VIRTUAL_PATH_PREFIX = "/mnt/user-data"
 
@@ -13,8 +11,9 @@ _SAFE_USER_ID_RE = re.compile(r"^[A-Za-z0-9_\-]+$")
 
 
 def _default_local_base_dir() -> Path:
-    """Return the caller project's writable DeerFlow state directory."""
-    return runtime_home()
+    """Return the repo-local DeerFlow state directory without relying on cwd."""
+    backend_dir = Path(__file__).resolve().parents[4]
+    return backend_dir / ".deer-flow"
 
 
 def _validate_thread_id(thread_id: str) -> str:
@@ -82,7 +81,7 @@ class Paths:
     BaseDir resolution (in priority order):
         1. Constructor argument `base_dir`
         2. DEER_FLOW_HOME environment variable
-        3. Caller project fallback: `{project_root}/.deer-flow`
+        3. Repo-local fallback derived from this module path: `{backend_dir}/.deer-flow`
     """
 
     def __init__(self, base_dir: str | Path | None = None) -> None:

backend/packages/harness/deerflow/config/runtime_paths.py

@@ -1,41 +0,0 @@
-"""Runtime path resolution for standalone harness usage."""
-
-import os
-from pathlib import Path
-
-
-def project_root() -> Path:
-    """Return the caller project root for runtime-owned files."""
-    if env_root := os.getenv("DEER_FLOW_PROJECT_ROOT"):
-        root = Path(env_root).resolve()
-        if not root.exists():
-            raise ValueError(f"DEER_FLOW_PROJECT_ROOT is set to '{env_root}', but the resolved path '{root}' does not exist.")
-        if not root.is_dir():
-            raise ValueError(f"DEER_FLOW_PROJECT_ROOT is set to '{env_root}', but the resolved path '{root}' is not a directory.")
-        return root
-    return Path.cwd().resolve()
-
-
-def runtime_home() -> Path:
-    """Return the writable DeerFlow state directory."""
-    if env_home := os.getenv("DEER_FLOW_HOME"):
-        return Path(env_home).resolve()
-    return project_root() / ".deer-flow"
-
-
-def resolve_path(value: str | os.PathLike[str], *, base: Path | None = None) -> Path:
-    """Resolve absolute paths as-is and relative paths against the project root."""
-    path = Path(value)
-    if not path.is_absolute():
-        path = (base or project_root()) / path
-    return path.resolve()
-
-
-def existing_project_file(names: tuple[str, ...]) -> Path | None:
-    """Return the first existing named file under the project root."""
-    root = project_root()
-    for name in names:
-        candidate = root / name
-        if candidate.is_file():
-            return candidate
-    return None

backend/packages/harness/deerflow/config/skills_config.py

@@ -1,21 +1,19 @@
-import os
 from pathlib import Path
 
 from pydantic import BaseModel, Field
 
-from deerflow.config.runtime_paths import project_root, resolve_path
+
+def _default_repo_root() -> Path:
+    """Resolve the repo root without relying on the current working directory."""
+    return Path(__file__).resolve().parents[5]
 
 
 class SkillsConfig(BaseModel):
     """Configuration for skills system"""
 
-    use: str = Field(
-        default="deerflow.skills.storage.local_skill_storage:LocalSkillStorage",
-        description="Class path of the SkillStorage implementation.",
-    )
     path: str | None = Field(
         default=None,
-        description="Path to skills directory. If not specified, defaults to skills under the caller project root.",
+        description="Path to skills directory. If not specified, defaults to ../skills relative to backend directory",
     )
     container_path: str = Field(
         default="/mnt/skills",
@@ -30,11 +28,17 @@ class SkillsConfig(BaseModel):
             Path to the skills directory
         """
         if self.path:
-            # Use configured path (can be absolute or relative to project root)
-            return resolve_path(self.path)
-        if env_path := os.getenv("DEER_FLOW_SKILLS_PATH"):
-            return resolve_path(env_path)
-        return project_root() / "skills"
+            # Use configured path (can be absolute or relative)
+            path = Path(self.path)
+            if not path.is_absolute():
+                # If relative, resolve from the repo root for deterministic behavior.
+                path = _default_repo_root() / path
+            return path.resolve()
+        else:
+            # Default: ../skills relative to backend directory
+            from deerflow.skills.loader import get_skills_root_path
+
+            return get_skills_root_path()
 
     def get_skill_container_path(self, skill_name: str, category: str = "public") -> str:
         """

backend/packages/harness/deerflow/config/subagents_config.py

@@ -20,52 +20,6 @@ class SubagentOverrideConfig(BaseModel):
         ge=1,
         description="Maximum turns for this subagent (None = use global or builtin default)",
     )
-    model: str | None = Field(
-        default=None,
-        min_length=1,
-        description="Model name for this subagent (None = inherit from parent agent)",
-    )
-    skills: list[str] | None = Field(
-        default=None,
-        description="Skill names whitelist for this subagent (None = inherit all enabled skills, [] = no skills)",
-    )
-
-
-class CustomSubagentConfig(BaseModel):
-    """User-defined subagent type declared in config.yaml."""
-
-    description: str = Field(
-        description="When the lead agent should delegate to this subagent",
-    )
-    system_prompt: str = Field(
-        description="System prompt that guides the subagent's behavior",
-    )
-    tools: list[str] | None = Field(
-        default=None,
-        description="Tool names whitelist (None = inherit all tools from parent)",
-    )
-    disallowed_tools: list[str] | None = Field(
-        default_factory=lambda: ["task", "ask_clarification", "present_files"],
-        description="Tool names to deny",
-    )
-    skills: list[str] | None = Field(
-        default=None,
-        description="Skill names whitelist (None = inherit all enabled skills, [] = no skills)",
-    )
-    model: str = Field(
-        default="inherit",
-        description="Model to use - 'inherit' uses parent's model",
-    )
-    max_turns: int = Field(
-        default=50,
-        ge=1,
-        description="Maximum number of agent turns before stopping",
-    )
-    timeout_seconds: int = Field(
-        default=900,
-        ge=1,
-        description="Maximum execution time in seconds",
-    )
 
 
 class SubagentsAppConfig(BaseModel):
@@ -85,10 +39,6 @@ class SubagentsAppConfig(BaseModel):
         default_factory=dict,
         description="Per-agent configuration overrides keyed by agent name",
     )
-    custom_agents: dict[str, CustomSubagentConfig] = Field(
-        default_factory=dict,
-        description="User-defined subagent types keyed by agent name",
-    )
 
     def get_timeout_for(self, agent_name: str) -> int:
         """Get the effective timeout for a specific agent.
@@ -104,20 +54,6 @@ class SubagentsAppConfig(BaseModel):
             return override.timeout_seconds
         return self.timeout_seconds
 
-    def get_model_for(self, agent_name: str) -> str | None:
-        """Get the model override for a specific agent.
-
-        Args:
-            agent_name: The name of the subagent.
-
-        Returns:
-            Model name if overridden, None otherwise (subagent will inherit parent model).
-        """
-        override = self.agents.get(agent_name)
-        if override is not None and override.model is not None:
-            return override.model
-        return None
-
     def get_max_turns_for(self, agent_name: str, builtin_default: int) -> int:
         """Get the effective max_turns for a specific agent."""
         override = self.agents.get(agent_name)
@@ -127,20 +63,6 @@ class SubagentsAppConfig(BaseModel):
             return self.max_turns
         return builtin_default
 
-    def get_skills_for(self, agent_name: str) -> list[str] | None:
-        """Get the skills override for a specific agent.
-
-        Args:
-            agent_name: The name of the subagent.
-
-        Returns:
-            Skill names whitelist if overridden, None otherwise (subagent will inherit all enabled skills).
-        """
-        override = self.agents.get(agent_name)
-        if override is not None and override.skills is not None:
-            return override.skills
-        return None
-
 
 _subagents_config: SubagentsAppConfig = SubagentsAppConfig()
 
@@ -162,22 +84,15 @@ def load_subagents_config_from_dict(config_dict: dict) -> None:
             parts.append(f"timeout={override.timeout_seconds}s")
         if override.max_turns is not None:
             parts.append(f"max_turns={override.max_turns}")
-        if override.model is not None:
-            parts.append(f"model={override.model}")
-        if override.skills is not None:
-            parts.append(f"skills={override.skills}")
         if parts:
             overrides_summary[name] = ", ".join(parts)
 
-    custom_agents_names = list(_subagents_config.custom_agents.keys())
-
-    if overrides_summary or custom_agents_names:
+    if overrides_summary:
         logger.info(
-            "Subagents config loaded: default timeout=%ss, default max_turns=%s, per-agent overrides=%s, custom_agents=%s",
+            "Subagents config loaded: default timeout=%ss, default max_turns=%s, per-agent overrides=%s",
             _subagents_config.timeout_seconds,
             _subagents_config.max_turns,
-            overrides_summary or "none",
-            custom_agents_names or "none",
+            overrides_summary,
         )
     else:
         logger.info(

backend/packages/harness/deerflow/config/summarization_config.py

@@ -51,25 +51,6 @@ class SummarizationConfig(BaseModel):
         default=None,
         description="Custom prompt template for generating summaries. If not provided, uses the default LangChain prompt.",
     )
-    preserve_recent_skill_count: int = Field(
-        default=5,
-        ge=0,
-        description="Number of most-recently-loaded skill files to exclude from summarization. Set to 0 to disable skill preservation.",
-    )
-    preserve_recent_skill_tokens: int = Field(
-        default=25000,
-        ge=0,
-        description="Total token budget reserved for recently-loaded skill files that must be preserved across summarization.",
-    )
-    preserve_recent_skill_tokens_per_skill: int = Field(
-        default=5000,
-        ge=0,
-        description="Per-skill token cap when preserving skill files across summarization. Skill reads above this size are not rescued.",
-    )
-    skill_file_read_tool_names: list[str] = Field(
-        default_factory=lambda: ["read_file", "read", "view", "cat"],
-        description="Tool names treated as skill file reads when preserving recently-loaded skills across summarization.",
-    )
 
 
 # Global configuration instance

backend/packages/harness/deerflow/mcp/cache.py

@@ -118,13 +118,9 @@ def get_cached_mcp_tools() -> list[BaseTool]:
                 loop.run_until_complete(initialize_mcp_tools())
         except RuntimeError:
             # No event loop exists, create one
-            try:
-                asyncio.run(initialize_mcp_tools())
-            except Exception:
-                logger.exception("Failed to lazy-initialize MCP tools")
-                return []
-        except Exception:
-            logger.exception("Failed to lazy-initialize MCP tools")
+            asyncio.run(initialize_mcp_tools())
+        except Exception as e:
+            logger.error(f"Failed to lazy-initialize MCP tools: {e}")
             return []
 
     return _mcp_tools_cache or []

backend/packages/harness/deerflow/mcp/tools.py

@@ -12,7 +12,6 @@ from langchain_core.tools import BaseTool
 from deerflow.config.extensions_config import ExtensionsConfig
 from deerflow.mcp.client import build_servers_config
 from deerflow.mcp.oauth import build_oauth_tool_interceptor, get_initial_oauth_headers
-from deerflow.reflection import resolve_variable
 
 logger = logging.getLogger(__name__)
 
@@ -96,27 +95,6 @@ async def get_mcp_tools() -> list[BaseTool]:
         if oauth_interceptor is not None:
             tool_interceptors.append(oauth_interceptor)
 
-        # Load custom interceptors declared in extensions_config.json
-        # Format: "mcpInterceptors": ["pkg.module:builder_func", ...]
-        raw_interceptor_paths = (extensions_config.model_extra or {}).get("mcpInterceptors")
-        if isinstance(raw_interceptor_paths, str):
-            raw_interceptor_paths = [raw_interceptor_paths]
-        elif not isinstance(raw_interceptor_paths, list):
-            if raw_interceptor_paths is not None:
-                logger.warning(f"mcpInterceptors must be a list of strings, got {type(raw_interceptor_paths).__name__}; skipping")
-            raw_interceptor_paths = []
-        for interceptor_path in raw_interceptor_paths:
-            try:
-                builder = resolve_variable(interceptor_path)
-                interceptor = builder()
-                if callable(interceptor):
-                    tool_interceptors.append(interceptor)
-                    logger.info(f"Loaded MCP interceptor: {interceptor_path}")
-                elif interceptor is not None:
-                    logger.warning(f"Builder {interceptor_path} returned non-callable {type(interceptor).__name__}; skipping")
-            except Exception as e:
-                logger.warning(f"Failed to load MCP interceptor {interceptor_path}: {e}", exc_info=True)
-
         client = MultiServerMCPClient(servers_config, tool_interceptors=tool_interceptors, tool_name_prefix=True)
 
         # Get all tools from all servers

backend/packages/harness/deerflow/models/claude_provider.py

@@ -190,33 +190,23 @@ class ClaudeChatModel(ChatAnthropic):
             )
 
     def _apply_prompt_caching(self, payload: dict) -> None:
-        """Apply ephemeral cache_control to system, recent messages, and last tool definition.
-
-        Uses a budget of MAX_CACHE_BREAKPOINTS (4) breakpoints — the hard limit
-        enforced by both the Anthropic API and AWS Bedrock.  Breakpoints are
-        placed on the *last* eligible blocks because later breakpoints cover a
-        larger prefix and yield better cache hit rates.
-        """
-        MAX_CACHE_BREAKPOINTS = 4
-
-        # Collect candidate blocks in document order:
-        #   1. system text blocks
-        #   2. content blocks of the last prompt_cache_size messages
-        #   3. the last tool definition
-        candidates: list[dict] = []
-
-        # 1. System blocks
+        """Apply ephemeral cache_control to system and recent messages."""
+        # Cache system messages
         system = payload.get("system")
         if system and isinstance(system, list):
             for block in system:
                 if isinstance(block, dict) and block.get("type") == "text":
-                    candidates.append(block)
+                    block["cache_control"] = {"type": "ephemeral"}
         elif system and isinstance(system, str):
-            new_block: dict = {"type": "text", "text": system}
-            payload["system"] = [new_block]
-            candidates.append(new_block)
+            payload["system"] = [
+                {
+                    "type": "text",
+                    "text": system,
+                    "cache_control": {"type": "ephemeral"},
+                }
+            ]
 
-        # 2. Recent message blocks
+        # Cache recent messages
         messages = payload.get("messages", [])
         cache_start = max(0, len(messages) - self.prompt_cache_size)
         for i in range(cache_start, len(messages)):
@@ -227,21 +217,20 @@ class ClaudeChatModel(ChatAnthropic):
             if isinstance(content, list):
                 for block in content:
                     if isinstance(block, dict):
-                        candidates.append(block)
+                        block["cache_control"] = {"type": "ephemeral"}
             elif isinstance(content, str) and content:
-                new_block = {"type": "text", "text": content}
-                msg["content"] = [new_block]
-                candidates.append(new_block)
+                msg["content"] = [
+                    {
+                        "type": "text",
+                        "text": content,
+                        "cache_control": {"type": "ephemeral"},
+                    }
+                ]
 
-        # 3. Last tool definition
+        # Cache the last tool definition
         tools = payload.get("tools", [])
         if tools and isinstance(tools[-1], dict):
-            candidates.append(tools[-1])
-
-        # Apply cache_control only to the last MAX_CACHE_BREAKPOINTS candidates
-        # to stay within the API limit.
-        for block in candidates[-MAX_CACHE_BREAKPOINTS:]:
-            block["cache_control"] = {"type": "ephemeral"}
+            tools[-1]["cache_control"] = {"type": "ephemeral"}
 
     def _apply_thinking_budget(self, payload: dict) -> None:
         """Auto-allocate thinking budget (80% of max_tokens)."""

backend/packages/harness/deerflow/models/factory.py

@@ -3,7 +3,6 @@ import logging
 from langchain.chat_models import BaseChatModel
 
 from deerflow.config import get_app_config
-from deerflow.config.app_config import AppConfig
 from deerflow.reflection import resolve_class
 from deerflow.tracing import build_tracing_callbacks
 
@@ -31,23 +30,7 @@ def _vllm_disable_chat_template_kwargs(chat_template_kwargs: dict) -> dict:
     return disable_kwargs
 
 
-def _enable_stream_usage_by_default(model_use_path: str, model_settings_from_config: dict) -> None:
-    """Enable stream usage for OpenAI-compatible models unless explicitly configured.
-
-    LangChain only auto-enables ``stream_usage`` for OpenAI models when no custom
-    base URL or client is configured. DeerFlow frequently uses OpenAI-compatible
-    gateways, so token usage tracking would otherwise stay empty and the
-    TokenUsageMiddleware would have nothing to log.
-    """
-    if model_use_path != "langchain_openai:ChatOpenAI":
-        return
-    if "stream_usage" in model_settings_from_config:
-        return
-    if "base_url" in model_settings_from_config or "openai_api_base" in model_settings_from_config:
-        model_settings_from_config["stream_usage"] = True
-
-
-def create_chat_model(name: str | None = None, thinking_enabled: bool = False, *, app_config: AppConfig | None = None, **kwargs) -> BaseChatModel:
+def create_chat_model(name: str | None = None, thinking_enabled: bool = False, **kwargs) -> BaseChatModel:
     """Create a chat model instance from the config.
 
     Args:
@@ -56,7 +39,7 @@ def create_chat_model(name: str | None = None, thinking_enabled: bool = False, *
     Returns:
         A chat model instance.
     """
-    config = app_config or get_app_config()
+    config = get_app_config()
     if name is None:
         name = config.models[0].name
     model_config = config.get_model_config(name)
@@ -114,8 +97,6 @@ def create_chat_model(name: str | None = None, thinking_enabled: bool = False, *
         kwargs.pop("reasoning_effort", None)
         model_settings_from_config.pop("reasoning_effort", None)
 
-    _enable_stream_usage_by_default(model_config.use, model_settings_from_config)
-
     # For Codex Responses API models: map thinking mode to reasoning_effort
     from deerflow.models.openai_codex_provider import CodexChatModel
 
@@ -132,12 +113,6 @@ def create_chat_model(name: str | None = None, thinking_enabled: bool = False, *
         elif "reasoning_effort" not in model_settings_from_config:
             model_settings_from_config["reasoning_effort"] = "medium"
 
-    # For MindIE models: enforce conservative retry defaults.
-    # Timeout normalization is handled inside MindIEChatModel itself.
-    if getattr(model_class, "__name__", "") == "MindIEChatModel":
-        # Enforce max_retries constraint to prevent cascading timeouts.
-        model_settings_from_config["max_retries"] = model_settings_from_config.get("max_retries", 1)
-
     # Ensure stream_usage is enabled so that token usage metadata is available
     # in streaming responses.  LangChain's BaseChatOpenAI only defaults
     # stream_usage=True when no custom base_url/api_base is set, so models

backend/packages/harness/deerflow/models/mindie_provider.py

@@ -1,249 +0,0 @@
-import ast
-import html
-import json
-import re
-import uuid
-from collections.abc import Iterator
-
-import httpx
-from langchain_core.messages import AIMessage, AIMessageChunk, HumanMessage, ToolMessage
-from langchain_core.outputs import ChatGenerationChunk, ChatResult
-from langchain_openai import ChatOpenAI
-
-
-def _fix_messages(messages: list) -> list:
-    """Sanitize incoming messages for MindIE compatibility.
-
-    MindIE's chat template may fail to parse LangChain's native tool_calls
-    or ToolMessage roles, resulting in 0-token generation errors. This function
-    flattens multi-modal list contents into strings and converts tool-related
-    messages into raw text with XML tags expected by the underlying model.
-    """
-    fixed = []
-    for msg in messages:
-        # Flatten content if it's a list of blocks
-        if isinstance(msg.content, list):
-            parts = []
-            for block in msg.content:
-                if isinstance(block, str):
-                    parts.append(block)
-                elif isinstance(block, dict) and block.get("type") == "text":
-                    parts.append(block.get("text", ""))
-            text = "".join(parts)
-        else:
-            text = msg.content or ""
-
-        # Convert AIMessage with tool_calls to raw XML text format
-        if isinstance(msg, AIMessage) and getattr(msg, "tool_calls", []):
-            xml_parts = []
-            for tool in msg.tool_calls:
-                args_xml = " ".join(f"<parameter={html.escape(str(k), quote=False)}>{html.escape(v if isinstance(v, str) else json.dumps(v, ensure_ascii=False), quote=False)}</parameter>" for k, v in tool.get("args", {}).items())
-                xml_parts.append(f"<tool_call> <function={html.escape(str(tool['name']), quote=False)}> {args_xml} </function> </tool_call>")
-            full_text = f"{text}\n" + "\n".join(xml_parts) if text else "\n".join(xml_parts)
-            fixed.append(AIMessage(content=full_text.strip() or " "))
-            continue
-
-        # Wrap tool execution results in XML tags and convert to HumanMessage
-        if isinstance(msg, ToolMessage):
-            tool_result_text = f"<tool_response>\n{text}\n</tool_response>"
-            fixed.append(HumanMessage(content=tool_result_text))
-            continue
-
-        # Fallback to prevent completely empty message content
-        if not text.strip():
-            text = " "
-
-        fixed.append(msg.model_copy(update={"content": text}))
-
-    return fixed
-
-
-def _parse_xml_tool_call_to_dict(content: str) -> tuple[str, list[dict]]:
-    """Parse XML-style tool calls from model output into LangChain dicts.
-
-    Args:
-        content: The raw text output from the model.
-
-    Returns:
-        A tuple containing the cleaned text (with XML blocks removed) and
-        a list of tool call dictionaries formatted for LangChain.
-    """
-    if not isinstance(content, str) or "<tool_call>" not in content:
-        return content, []
-
-    tool_calls = []
-    clean_parts: list[str] = []
-    cursor = 0
-    for start, end, inner_content in _iter_tool_call_blocks(content):
-        clean_parts.append(content[cursor:start])
-        cursor = end
-
-        func_match = re.search(r"<function=([^>]+)>", inner_content)
-        if not func_match:
-            continue
-        function_name = html.unescape(func_match.group(1).strip())
-
-        # Ignore nested tool blocks when extracting parameters for this call.
-        # Nested `<tool_call>` sections represent separate invocations and
-        # their `<parameter>` tags must not leak into the current call args.
-        param_source_parts: list[str] = []
-        nested_cursor = 0
-        for nested_start, nested_end, _ in _iter_tool_call_blocks(inner_content):
-            param_source_parts.append(inner_content[nested_cursor:nested_start])
-            nested_cursor = nested_end
-        param_source_parts.append(inner_content[nested_cursor:])
-        param_source = "".join(param_source_parts)
-
-        args = {}
-        param_pattern = re.compile(r"<parameter=([^>]+)>(.*?)</parameter>", re.DOTALL)
-        for param_match in param_pattern.finditer(param_source):
-            key = html.unescape(param_match.group(1).strip())
-            raw_value = html.unescape(param_match.group(2).strip())
-
-            # Attempt to deserialize string values into native Python types
-            # to satisfy downstream Pydantic validation.
-            parsed_value = raw_value
-            if raw_value.startswith(("[", "{")) or raw_value in ("true", "false", "null") or raw_value.isdigit():
-                try:
-                    parsed_value = json.loads(raw_value)
-                except json.JSONDecodeError:
-                    try:
-                        parsed_value = ast.literal_eval(raw_value)
-                    except (ValueError, SyntaxError):
-                        pass
-
-            args[key] = parsed_value
-
-        tool_calls.append({"name": function_name, "args": args, "id": f"call_{uuid.uuid4().hex[:10]}"})
-    clean_parts.append(content[cursor:])
-
-    return "".join(clean_parts).strip(), tool_calls
-
-
-def _iter_tool_call_blocks(content: str) -> Iterator[tuple[int, int, str]]:
-    """Iterate `<tool_call>...</tool_call>` blocks and tolerate nesting."""
-    token_pattern = re.compile(r"</?tool_call>")
-    depth = 0
-    block_start = -1
-
-    for match in token_pattern.finditer(content):
-        token = match.group(0)
-        if token == "<tool_call>":
-            if depth == 0:
-                block_start = match.start()
-            depth += 1
-            continue
-
-        if depth == 0:
-            continue
-
-        depth -= 1
-        if depth == 0 and block_start != -1:
-            block_end = match.end()
-            inner_start = block_start + len("<tool_call>")
-            inner_end = match.start()
-            yield block_start, block_end, content[inner_start:inner_end]
-            block_start = -1
-
-
-def _decode_escaped_newlines_outside_fences(content: str) -> str:
-    """Decode literal `\\n` outside fenced code blocks."""
-    if "\\n" not in content:
-        return content
-
-    parts = re.split(r"(```[\s\S]*?```)", content)
-    for idx, part in enumerate(parts):
-        if part.startswith("```"):
-            continue
-        parts[idx] = part.replace("\\n", "\n")
-    return "".join(parts)
-
-
-class MindIEChatModel(ChatOpenAI):
-    """Chat model adapter for MindIE engine.
-
-    Addresses compatibility issues including:
-    - Flattening multimodal list contents to strings.
-    - Intercepting and parsing hardcoded XML tool calls into LangChain standard.
-    - Handling stream=True dropping choices when tools are present by falling back
-      to non-streaming generation and yielding simulated chunks.
-    - Fixing over-escaped newline characters from gateway responses.
-    """
-
-    def __init__(self, **kwargs):
-        """Normalize timeout kwargs without creating long-lived clients."""
-        connect_timeout = kwargs.pop("connect_timeout", 30.0)
-        read_timeout = kwargs.pop("read_timeout", 900.0)
-        write_timeout = kwargs.pop("write_timeout", 60.0)
-        pool_timeout = kwargs.pop("pool_timeout", 30.0)
-
-        kwargs.setdefault(
-            "timeout",
-            httpx.Timeout(
-                connect=connect_timeout,
-                read=read_timeout,
-                write=write_timeout,
-                pool=pool_timeout,
-            ),
-        )
-        super().__init__(**kwargs)
-
-    def _patch_result_with_tools(self, result: ChatResult) -> ChatResult:
-        """Apply post-generation fixes to the model result."""
-        for gen in result.generations:
-            msg = gen.message
-
-            if isinstance(msg.content, str):
-                # Keep escaped newlines inside fenced code blocks untouched.
-                msg.content = _decode_escaped_newlines_outside_fences(msg.content)
-
-                if "<tool_call>" in msg.content:
-                    clean_content, extracted_tools = _parse_xml_tool_call_to_dict(msg.content)
-
-                    if extracted_tools:
-                        msg.content = clean_content
-                        if getattr(msg, "tool_calls", None) is None:
-                            msg.tool_calls = []
-                        msg.tool_calls.extend(extracted_tools)
-        return result
-
-    def _generate(self, messages, stop=None, run_manager=None, **kwargs):
-        result = super()._generate(_fix_messages(messages), stop=stop, run_manager=run_manager, **kwargs)
-        return self._patch_result_with_tools(result)
-
-    async def _agenerate(self, messages, stop=None, run_manager=None, **kwargs):
-        result = await super()._agenerate(_fix_messages(messages), stop=stop, run_manager=run_manager, **kwargs)
-        return self._patch_result_with_tools(result)
-
-    async def _astream(self, messages, stop=None, run_manager=None, **kwargs):
-        # Route standard queries to native streaming for lower TTFB
-        if not kwargs.get("tools"):
-            async for chunk in super()._astream(_fix_messages(messages), stop=stop, run_manager=run_manager, **kwargs):
-                if isinstance(chunk.message.content, str):
-                    chunk.message.content = _decode_escaped_newlines_outside_fences(chunk.message.content)
-                yield chunk
-            return
-
-        # Fallback for tool-enabled requests:
-        # MindIE currently drops choices when stream=True and tools are present.
-        # We await the full generation and yield chunks to simulate streaming.
-        result = await self._agenerate(messages, stop=stop, run_manager=run_manager, **kwargs)
-
-        for gen in result.generations:
-            msg = gen.message
-            content = msg.content
-            standard_tool_calls = getattr(msg, "tool_calls", [])
-
-            # Yield text in chunks to allow downstream UI/Markdown parsers to render smoothly
-            if isinstance(content, str) and content:
-                chunk_size = 15
-                for i in range(0, len(content), chunk_size):
-                    chunk_text = content[i : i + chunk_size]
-                    chunk_msg = AIMessageChunk(content=chunk_text, id=msg.id, response_metadata=msg.response_metadata if i == 0 else {})
-                    yield ChatGenerationChunk(message=chunk_msg, generation_info=gen.generation_info if i == 0 else None)
-
-                if standard_tool_calls:
-                    yield ChatGenerationChunk(message=AIMessageChunk(content="", id=msg.id, tool_calls=standard_tool_calls, invalid_tool_calls=getattr(msg, "invalid_tool_calls", [])))
-            else:
-                chunk_msg = AIMessageChunk(content=content, id=msg.id, tool_calls=standard_tool_calls, invalid_tool_calls=getattr(msg, "invalid_tool_calls", []))
-                yield ChatGenerationChunk(message=chunk_msg, generation_info=gen.generation_info)

backend/packages/harness/deerflow/persistence/feedback/model.py

@@ -13,7 +13,9 @@ from deerflow.persistence.base import Base
 class FeedbackRow(Base):
     __tablename__ = "feedback"
 
-    __table_args__ = (UniqueConstraint("thread_id", "run_id", "user_id", name="uq_feedback_thread_run_user"),)
+    __table_args__ = (
+        UniqueConstraint("thread_id", "run_id", "user_id", name="uq_feedback_thread_run_user"),
+    )
 
     feedback_id: Mapped[str] = mapped_column(String(64), primary_key=True)
     run_id: Mapped[str] = mapped_column(String(64), nullable=False, index=True)

backend/packages/harness/deerflow/persistence/migrations/env.py

@@ -18,9 +18,7 @@ from deerflow.persistence.base import Base
 
 # Import all models so metadata is populated.
 try:
-    import deerflow.persistence.models as models  # register ORM models with Base.metadata
-
-    _ = models
+    import deerflow.persistence.models  # noqa: F401 — register ORM models with Base.metadata
 except ImportError:
     # Models not available — migration will work with existing metadata only.
     logging.getLogger(__name__).warning("Could not import deerflow.persistence.models; Alembic may not detect all tables")

backend/packages/harness/deerflow/runtime/checkpointer/async_provider.py

@@ -24,7 +24,7 @@ from collections.abc import AsyncIterator
 
 from langgraph.types import Checkpointer
 
-from deerflow.config.app_config import AppConfig, get_app_config
+from deerflow.config.app_config import get_app_config
 from deerflow.runtime.checkpointer.provider import (
     POSTGRES_CONN_REQUIRED,
     POSTGRES_INSTALL,
@@ -123,11 +123,11 @@ async def _async_checkpointer_from_database(db_config) -> AsyncIterator[Checkpoi
 
 
 @contextlib.asynccontextmanager
-async def make_checkpointer(app_config: AppConfig | None = None) -> AsyncIterator[Checkpointer]:
+async def make_checkpointer() -> AsyncIterator[Checkpointer]:
     """Async context manager that yields a checkpointer for the caller's lifetime.
     Resources are opened on enter and closed on exit -- no global state::
 
-        async with make_checkpointer(app_config) as checkpointer:
+        async with make_checkpointer() as checkpointer:
             app.state.checkpointer = checkpointer
 
     Yields an ``InMemorySaver`` when no checkpointer is configured in *config.yaml*.
@@ -138,17 +138,16 @@ async def make_checkpointer(app_config: AppConfig | None = None) -> AsyncIterato
     3. Default InMemorySaver
     """
 
-    if app_config is None:
-        app_config = get_app_config()
+    config = get_app_config()
 
     # Legacy: standalone checkpointer config takes precedence
-    if app_config.checkpointer is not None:
-        async with _async_checkpointer(app_config.checkpointer) as saver:
+    if config.checkpointer is not None:
+        async with _async_checkpointer(config.checkpointer) as saver:
             yield saver
             return
 
     # Unified database config
-    db_config = getattr(app_config, "database", None)
+    db_config = getattr(config, "database", None)
     if db_config is not None and db_config.backend != "memory":
         async with _async_checkpointer_from_database(db_config) as saver:
             yield saver