enforce workflow data edge order

separate workflow control and data edges
fix: port workflow schema migration to alembic
2026-08-22 18:27:12 +00:00 · 2026-07-02 00:51:01 +08:00 · 2026-07-01 22:01:06 +08:00 · 2026-07-01 20:42:30 +08:00 · 2026-07-01 20:33:05 +08:00 · 2026-07-01 20:00:47 +08:00
298 changed files with 47215 additions and 1684 deletions
@@ -1,160 +1,105 @@
 # AGENTS.md

-This file guides code agents (Claude Code, GitHub Copilot, OpenAI Codex, etc.) working in the LangBot project. `CLAUDE.md` is a symlink to this file.
+This file guides code agents working in the LangBot main repository. `CLAUDE.md` is a symlink to this file.

-## Project Overview
+Read `ARCHITECTURE.md` before non-trivial backend, frontend, runtime, plugin, Box, MCP, persistence, or cross-repo SDK changes. This file is the working checklist; `ARCHITECTURE.md` is the system map.

-LangBot is an open-source, LLM-native instant-messaging bot development platform. It aims to provide an out-of-the-box IM bot development experience with Agent, RAG, MCP and other LLM application capabilities, supporting mainstream global IM platforms and exposing rich APIs for custom development.
+## Quick Facts

-LangBot has a comprehensive web frontend — almost every operation can be performed through it.
+- Python backend: `>=3.11,<4.0`, dependencies managed by `uv`.
+- Frontend: `web/` is Vite + React Router 7 + shadcn/ui + Tailwind, managed by `pnpm`.
+- Backend framework: Quart served by Hypercorn on `api.port`, default `5300`.
+- Frontend dev server: `web/` on `3000`, with `VITE_API_BASE_URL` pointing at the backend.
+- Plugin/Box/runtime contracts live in sibling repo `langbot-plugin-sdk`, pinned as `langbot-plugin` in `pyproject.toml`.

- **Python**: `>=3.11,<4.0`, dependencies managed by `uv`. Package version is in `pyproject.toml`.
- **Frontend**: `web/` is a **Vite + React Router 7 + shadcn/ui + Tailwind CSS** SPA, managed by `pnpm`. (Note: this is NOT Next.js — the `dev` script is `vite`.)
- **Backend framework**: Quart (the async flavour of Flask). The HTTP API and the pre-built web UI are both served by the backend on `http://127.0.0.1:5300`.
-
-## Repository Layout
-
-```
-LangBot/
-├── main.py                     # Entrypoint shim -> langbot.__main__.main()
-├── pyproject.toml              # Python project + deps (uv), pins langbot-plugin==<x.y.z>
-├── src/langbot/
-│   ├── __main__.py             # Real entrypoint, CLI args (--standalone-runtime, --standalone-box, --debug)
-│   ├── pkg/                    # Core backend package
-│   │   ├── api/                # HTTP API controllers + services (Quart)
-│   │   ├── core/               # App bootstrap, stages, task manager
-│   │   ├── platform/           # IM platform adapters, bot managers, session managers
-│   │   ├── provider/           # LLM providers, requesters, tool providers
-│   │   ├── pipeline/           # Pipelines, stages, query pool
-│   │   ├── plugin/             # Bridge connecting LangBot to the plugin runtime (see below)
-│   │   ├── box/                # Code-sandbox subsystem (Docker / nsjail / E2B backends)
-│   │   ├── skill/              # Skill subsystem
-│   │   ├── rag/ , vector/      # RAG + vector store
-│   │   ├── command/            # Built-in commands
-│   │   ├── persistence/        # ORM models + Alembic migrations (SQLite & PostgreSQL)
-│   │   ├── storage/            # Object/file storage abstractions
-│   │   ├── config/, entity/, discover/, utils/, telemetry/, survey/
-│   ├── libs/                   # Vendored SDKs (qq_official_api, wecom_api, etc.)
-│   └── templates/              # Config/component templates (e.g. templates/config.yaml)
-├── web/                        # Frontend SPA (Vite + React Router 7 + shadcn + Tailwind)
-└── docker/                     # docker-compose deployment files
-```
-
-## Development Environment Setup
-
-Full guide lives in the wiki: **["开发配置" / Dev Config](https://docs.langbot.app/zh/develop/dev-config)**. Summary:
-
-### Backend
-
-```bash
-pip install uv
-uv sync --dev          # uv creates a .venv/ for you; point your editor's interpreter at it
-uv run main.py         # serves API + web UI on http://127.0.0.1:5300
-```
-
-On first run the config file is generated at `data/config.yaml`. DB is SQLite by default (zero setup); PostgreSQL is supported. Migrations run automatically on startup.
-
-### Frontend
-
-Requires Node.js + [pnpm](https://pnpm.io/installation).
-
-```bash
-cd web
-cp .env.example .env   # Windows: copy .env.example .env
-pnpm install
-pnpm dev               # http://127.0.0.1:3000  (npm install / npm run dev also work)
-```
-
-`pnpm dev` reads `VITE_API_BASE_URL` from `web/.env` so the dev frontend can reach the backend on port `5300`. In production the frontend is pre-built into static files served by the backend on the same origin.
-
-### Code formatting
-
-The repo runs lint + format checks in CI. Install the pre-commit hooks so the same checks run locally before each commit:
+## Essential Commands

 ```bash
+uv sync --dev
+uv run main.py
 uv run pre-commit install
+
+cd web
+pnpm install
+pnpm dev
+pnpm build
 ```

-## Plugin System
-
-LangBot's plugin system (Plugin SDK, CLI `lbp`, Plugin Runtime, and the shared entity/API definitions) lives in a **separate repository**: [`langbot-plugin-sdk`](https://github.com/langbot-app/langbot-plugin-sdk). LangBot depends on it via the pinned `langbot-plugin` package in `pyproject.toml`.
-
-### Architecture (what to know inside this repo)
-
- Plugins run as independent processes managed by the **Plugin Runtime**. The Runtime supports two control transports: `stdio` and `websocket`.
- When LangBot is started directly by a user (not in a container), it spawns and connects to the Runtime over **stdio** (lightweight/personal use).
- When LangBot runs in a container, it connects to a standalone Runtime over **WebSocket** (production).
- The bridge code lives in `src/langbot/pkg/plugin/` (`connector.py`, `handler.py`).
- Relevant config (`data/config.yaml`): `plugin.runtime_ws_url` (e.g. `ws://langbot_plugin_runtime:5400/control/ws`). Start LangBot with `--standalone-runtime` to make it connect to an externally-launched Runtime over WebSocket instead of spawning one over stdio.
-
-### Debugging the Plugin Runtime / CLI / SDK
-
-This is documented in detail in the **SDK repo's `AGENTS.md`** and in the wiki page **["调试插件运行时、CLI、SDK" / Plugin Runtime](https://docs.langbot.app/zh/develop/plugin-runtime)**. The short version:
-
- Clone `LangBot` and `langbot-plugin-sdk` as siblings under one parent dir so the editor resolves shared entities.
- Start a standalone Runtime from the SDK repo: `uv run --no-sync lbp rt` (control port `5400`, debug port `5401`).
- To make LangBot use a locally-modified SDK: from the SDK dir, with LangBot's `.venv` active, run `uv pip install .`, then launch LangBot with `uv run --no-sync main.py --standalone-runtime` (keep `--no-sync` so your local SDK isn't overwritten).
-
-### Debugging the Box (sandbox) runtime
-
-The Box subsystem (`src/langbot/pkg/box/`) is the code sandbox. It picks the first available backend among **Docker / nsjail / E2B**. The standalone Box runtime is launched via the SDK CLI: `lbp box`. Backend selection details, the `lbp box` flags, and the SDK-side architecture are documented in the SDK repo's `AGENTS.md`.
-
-Relevant config (`data/config.yaml`, `box:` section): `box.enabled` (master switch — disabling it also disables the native sandbox tools, skill add/edit, and stdio-mode MCP servers), `box.backend` (`'local'` = Docker/nsjail auto-pick, or `'docker'` / `'nsjail'` / `'e2b'`; also settable via `BOX__BACKEND`), and `box.runtime.endpoint` (external Box runtime base URL, e.g. `ws://127.0.0.1:5410`; empty = local auto-managed runtime). Like the plugin runtime, LangBot can connect to an externally-launched Box runtime by setting that endpoint and starting with `--standalone-box`.
-
-> A common false "No supported sandbox backend (Docker / nsjail / E2B) is available" comes from Docker being installed and running but the current user not being in the `docker` group → `docker info` gets `permission denied` on the socket. Fix: `sudo usermod -aG docker <user>` and restart the backend in a shell that has the new group.
-
-## Development Standards
-
- LangBot is a global project: **all code comments and docstrings must be in English**, and every user-facing string must support **i18n** (`en_US` + `zh_Hans` at minimum, plus `ja_JP` where the repo already has it).
- LangBot is adopted in both toC and toB scenarios — always consider compatibility and security.
- **Commit message format**: `<type>(<scope>): <subject>`
-  - `type`: one of `feat`, `fix`, `docs`, `style`, `refactor`, `perf`, `test`, `chore`, etc.
-  - `scope`: the affected package/module/file/class.
-  - `subject`: concise description of the change.
-
-### Database migrations (Alembic)
-
-LangBot uses [Alembic](https://alembic.sqlalchemy.org/) for migrations, supporting both SQLite and PostgreSQL from a single set of scripts. Migration files live in `src/langbot/pkg/persistence/alembic/versions/`.
-
-If you change ORM model definitions, generate a migration:
+Useful focused tests:

 ```bash
-# Run from the project root (requires data/config.yaml to exist)
-uv run python -m langbot.pkg.persistence.alembic_runner autogenerate "description of your change"
+uv run pytest tests/unit_tests -q
+uv run pytest tests/integration -q
+uv run pytest tests/integration/persistence -q
+uv run pytest tests/manual/mcp_smoke.py
+
+cd web
+pnpm lint
+pnpm test:e2e
 ```

-Review and edit the generated script before committing. Migrations execute automatically on startup. `autogenerate` detects schema changes (add/drop columns, tables, type changes) but **data migrations** (e.g. mutating JSON field contents) must be hand-written into the generated script. `env.py` sets `render_as_batch=True`, so SQLite's ALTER TABLE limits are handled automatically — no need to branch per database. More in the wiki ["开发配置"](https://docs.langbot.app/zh/develop/dev-config#数据库迁移).
+Run the narrowest useful test first, then broader checks when confidence is needed.

-When writing a migration, follow these rules:
+## Where to Look

- **Revision id ≤ 32 characters.** PostgreSQL stores `alembic_version.version_num` as `varchar(32)`; a longer id raises `StringDataRightTruncationError` at runtime. Prefer short, descriptive ids like `0005_add_llm_context_length`.
- **Guard every operation against missing tables/columns.** Fresh installs build the schema via `create_all()` and then stamp the Alembic baseline, so a migration may run against a table that already has the change — or, in tests, against an empty database. Check `inspector.get_table_names()` / `inspector.get_columns(...)` before `add_column` / `drop_column`, mirroring the existing migrations.
- **Keep a single linear head.** Chain `down_revision` to the current head; do not create branches. Run the migration tests after adding one: `uv run pytest tests/integration/persistence/ -q` (the PostgreSQL test needs a running PG via `TEST_POSTGRES_URL`).
+- Architecture map: `ARCHITECTURE.md`.
+- Dev environment guide: https://docs.langbot.app/zh/develop/dev-config.
+- Plugin runtime / CLI / SDK debugging: https://docs.langbot.app/zh/develop/plugin-runtime.
+- API-key auth: `docs/API_KEY_AUTH.md`.
+- Box deep-dive notes: `docs/review/box-architecture.md` and related files.
+- In-repo skills: `skills/` is the single source of truth for LangBot agent skills.
+- SDK repo: `../langbot-plugin-sdk/` when changing shared entities, plugin APIs, action protocol, `lbp rt`, or `lbp box`.

-> **Legacy migration system (deprecated — do not extend).** The old 3.x migration system under `src/langbot/pkg/persistence/migrations/` (`DBMigration` subclasses in `dbmXXX_*.py`, run from `pkg/persistence/mgr.py`) is **frozen**. Do **not** add new `dbmXXX_*.py` files. The chain is capped at `required_database_version = 25` (`pkg/utils/constants.py`); those files only exist to upgrade pre-existing 3.x databases up to the Alembic baseline and are kept read-only. All new schema changes go through Alembic.
+## Cross-Repo SDK Work

-## Agent-Facing Surfaces (MCP + Skills)
+When changing SDK contracts used by LangBot:

-LangBot is built to be **agent-friendly**. Three surfaces let AI agents work
-with LangBot, and they MUST be kept in lockstep with the HTTP API:
+```bash
+# from langbot-plugin-sdk, with LangBot's .venv active
+uv pip install .

-1. **MCP server** — `src/langbot/pkg/api/mcp/` exposes a curated subset of the
-   API as MCP tools at `/mcp` (API-key authenticated, including the
-   `api.global_api_key` from config.yaml). `server.py` defines the tools (they
-   call the service layer directly); `mount.py` is the ASGI dispatcher.
-2. **In-repo skills** — `skills/` is the **single source of truth** for agent
-   skills (plugin/core/deploy/e2e/MCP-ops). Docs and the landing page link here
-   rather than embedding their own copies.
-3. **API-key auth** — `api.global_api_key` (config.yaml) authenticates the API
-   and MCP without a login session; see `docs/API_KEY_AUTH.md`.
+# from LangBot, preserve the locally installed SDK
+uv run --no-sync main.py
+```

-> **Maintenance rule (important).** When you add, remove, or change an HTTP API
-> endpoint that should be agent-accessible, you MUST update **both** the matching
-> MCP tool in `src/langbot/pkg/api/mcp/server.py` **and** the relevant skill under
-> `skills/` (especially `skills/skills/langbot-mcp-ops`). The API, the MCP tool
-> surface, and the skills are one system — drift between them is a bug.
+For standalone runtime debugging:

-## Some Principles
+```bash
+# in langbot-plugin-sdk
+uv run --no-sync lbp rt
+uv run --no-sync lbp box
+
+# in LangBot
+uv run --no-sync main.py --standalone-runtime
+uv run --no-sync main.py --standalone-box
+```
+
+Config keys to verify in `data/config.yaml` / `src/langbot/templates/config.yaml`:
+
+- Plugin runtime: `plugin.runtime_ws_url`, default Docker host `langbot_plugin_runtime:5400/control/ws`.
+- Box runtime: `box.enabled`, `box.backend`, `box.runtime.endpoint`, Docker host `langbot_box:5410`.
+- API/MCP auth: `api.global_api_key`.
+
+## Change Rules
+
+- HTTP API changes that should be agent-accessible must update the matching MCP tool in `src/langbot/pkg/api/mcp/server.py` and the relevant skill under `skills/` in the same pass.
+- New schema changes use Alembic under `src/langbot/pkg/persistence/alembic/versions/`; do not add legacy `dbmXXX` migrations.
+- New platform behavior belongs in platform adapters only for platform translation; pipeline/business logic belongs in `pkg/pipeline/` or services.
+- User-facing strings must support i18n (`en_US`, `zh_Hans`; include `ja_JP` where the repo already does).
+- Code comments and docstrings must be English.
+- Keep compatibility and security in mind; LangBot is used in both self-hosted/community and toB deployments.
+- Commit message format: `<type>(<scope>): <subject>`.
+
+## Runtime Pitfalls
+
+- Local stdio Plugin Runtime disconnects do not auto-reconnect; restart LangBot if that path breaks.
+- Orphan runtime processes on `5400`/`5401` commonly break plugin debugging.
+- Use `uv run --no-sync` after locally installing the SDK, or `uv` may restore the pinned package.
+- A false Box “no backend” often means Docker is running but the current user lacks Docker socket permission.
+- Do not confuse external MCP servers LangBot connects to (`pkg/provider/tools/loaders/mcp.py`) with LangBot's own `/mcp` server (`pkg/api/mcp/`).
+- `CLAUDE.md` is a symlink to this file; edit `AGENTS.md`, not the symlink.
+
+## Principles

 - Keep it simple, stupid.
 - Entities should not be multiplied unnecessarily.
@@ -0,0 +1,250 @@
+# Architecture
+
+This document is a map of LangBot's moving parts. It is intentionally more stable than a feature guide and more concrete than the README: when you need to change behavior, start here, then follow the file references into the code.
+
+For agent-specific working rules, see `AGENTS.md`. For plugin-runtime and Box-runtime implementation details, also read the sibling SDK repo: [`langbot-plugin-sdk`](https://github.com/langbot-app/langbot-plugin-sdk).
+
+## What LangBot Is
+
+LangBot is an open-source platform for building production IM bots backed by LLMs, agents, RAG, plugins, MCP tools, and a web management panel.
+
+At runtime, one LangBot process owns:
+
+- a Quart/Hypercorn HTTP service and the built web UI on `:5300`;
+- messaging-platform adapters such as Discord, Telegram, Slack, WeChat, QQ, WeCom, Lark, DingTalk, KOOK, LINE, Satori, Matrix, and HTTP/WebSocket bots;
+- a pipeline engine that turns inbound platform messages into LLM/tool/plugin work and replies;
+- persistence, storage, vector database, telemetry, monitoring, and configuration managers;
+- bridges to the Plugin Runtime and Box Runtime provided by `langbot-plugin-sdk`;
+- an MCP server at `/mcp` exposing a curated agent-facing subset of the service layer.
+
+## Repository Boundary
+
+LangBot is not a single-repo system.
+
+- `LangBot/` is the main product: backend, web UI, platform adapters, pipeline engine, HTTP API, MCP server, RAG, persistence, skills integration, and the bridge code that talks to runtimes.
+- `langbot-plugin-sdk/` is published as `langbot-plugin` and pinned in `LangBot/pyproject.toml`. It contains plugin developer APIs, shared entities, `lbp`, the Plugin Runtime (`lbp rt`), and the Box Runtime (`lbp box`).
+- Plugins import SDK APIs from `langbot_plugin.*`; the LangBot main process imports the same package for shared entities and runtime protocols.
+
+This split matters. If a change modifies SDK entities, component APIs, action protocols, `lbp rt`, or `lbp box`, verify the sibling SDK repo and install the local SDK into LangBot's virtualenv when testing cross-repo behavior.
+
+## Startup Path
+
+The process entrypoint is small and layered:
+
+1. `main.py` delegates to `langbot.__main__.main()`.
+2. `src/langbot/__main__.py` parses `--standalone-runtime`, `--standalone-box`, and `--debug`, checks dependencies, generates missing config/data files, and calls `pkg.core.boot.main()`.
+3. `pkg/core/boot.py` executes startup stages in order: `LoadConfigStage`, `GenKeysStage`, `SetupLoggerStage`, `BuildAppStage`, `ShowNotesStage`.
+4. `BuildAppStage` constructs the `Application` object by wiring managers, services, runtime connectors, and controllers.
+5. `Application.run()` starts the platform manager, query controller, HTTP controller, telemetry/cleanup loops, and plugin initialization.
+
+The central runtime object is `pkg/core/app.py::Application`. It is a service locator for long-lived managers. That is not elegant, but it is the current architectural center; most subsystems receive `ap: Application` and collaborate through it.
+
+## Top-Level Layout
+
+```text
+LangBot/
+├── main.py                         # Entrypoint shim
+├── pyproject.toml                  # Python package, deps, pinned langbot-plugin
+├── src/langbot/
+│   ├── __main__.py                 # CLI entrypoint and boot handoff
+│   ├── pkg/
+│   │   ├── core/                   # Application, boot stages, task manager
+│   │   ├── api/                    # HTTP API + MCP server mount
+│   │   ├── platform/               # IM adapters and runtime bot manager
+│   │   ├── pipeline/               # Message routing and pipeline stages
+│   │   ├── provider/               # LLM runners, model manager, tools
+│   │   ├── plugin/                 # LangBot-side Plugin Runtime connector/handler
+│   │   ├── box/                    # LangBot-side Box service/connector
+│   │   ├── skill/                  # Skill metadata/activation integration
+│   │   ├── rag/ , vector/          # Knowledge-base and vector DB integration
+│   │   ├── persistence/            # SQLAlchemy/SQLModel, Alembic, legacy migrations
+│   │   ├── storage/                # Local/S3 file storage abstraction
+│   │   └── config/, entity/, utils/, telemetry/, survey/
+│   ├── libs/                       # Vendored third-party platform SDKs
+│   └── templates/                  # Default config and component metadata
+├── web/                            # Vite + React Router + shadcn/ui + Tailwind SPA
+├── docker/                         # Deployment manifests
+├── skills/                         # In-repo agent skills, single source of truth
+└── tests/                          # Unit/integration/e2e/manual tests
+```
+
+## The Runtime Graph
+
+The most useful mental model is this graph:
+
+```text
+Platform adapter
+  → RuntimeBot
+  → MessageAggregator
+  → QueryPool
+  → Controller
+  → RuntimePipeline
+  → PipelineStage chain
+  → RequestRunner / ToolManager / PluginRuntimeConnector / BoxService
+  → response via adapter
+```
+
+The HTTP and MCP surfaces are parallel entrypoints into the same service layer:
+
+```text
+HTTP client / Web UI
+  → Quart route group
+  → api/http/service/*
+  → Application managers / persistence / runtime connectors
+
+MCP client
+  → /mcp mount
+  → api/mcp/server.py tools
+  → the same service layer directly
+```
+
+## Message Flow
+
+Inbound platform messages enter through adapter-specific SDK callbacks. The common path is:
+
+1. A platform adapter under `pkg/platform/sources/` converts platform-specific events into SDK message/event entities.
+2. `RuntimeBot` in `pkg/platform/botmgr.py` applies pipeline routing rules and either discards the message, pushes it to webhooks, or sends it to the message aggregator.
+3. `MessageAggregator` batches/normalizes messages before adding a `Query` to `QueryPool`.
+4. `Controller` in `pkg/pipeline/controller.py` selects queries subject to global pipeline concurrency and per-session concurrency.
+5. `RuntimePipeline` in `pkg/pipeline/pipelinemgr.py` runs configured pipeline stages using a responsibility-chain style executor that supports generator stages.
+6. The chat stage emits plugin events, calls a configured `RequestRunner`, handles streaming/non-streaming responses, records telemetry, and appends conversation history.
+7. Output stages send text, cards, chunks, files, or error notices back through the original platform adapter.
+
+Pipeline components are registered by decorators and package import side effects. When adding a new stage, loader, runner, or adapter, check the corresponding preregistration mechanism instead of inventing a second registry.
+
+## Platform Layer
+
+Platform code lives under `pkg/platform/`.
+
+- `botmgr.py` owns runtime bots, routing rules, event logging, webhook pushing, and adapter lifecycle.
+- `sources/` contains adapter implementations. Each adapter subclasses `langbot_plugin.api.definition.abstract.platform.adapter.AbstractMessagePlatformAdapter` from the SDK.
+- Platform entities such as `MessageChain`, `Image`, `At`, `Voice`, and events come from `langbot-plugin-sdk`, not from this repo.
+
+The platform layer should translate between external platform APIs and LangBot's shared message/event model. It should not contain LLM-provider logic or pipeline business logic.
+
+## Pipeline Layer
+
+Pipeline code lives under `pkg/pipeline/`.
+
+Important pieces:
+
+- `pool.py::QueryPool` stores pending queries and cached in-flight queries for plugin backward-compatible calls.
+- `controller.py::Controller` schedules query processing and enforces concurrency.
+- `pipelinemgr.py::RuntimePipeline` materializes database pipeline config into a runtime stage chain.
+- `process/handlers/chat.py::ChatMessageHandler` is the main LLM conversation handler.
+- Stage families include response rules, banned sessions, content filters, preprocessors, rate limits, message truncation, long text handling, response-back, command handling, and wrappers.
+
+Pipelines are configuration-driven. Prefer adding a stage or extending an existing stage family over hard-coding behavior in platform adapters.
+
+## Provider, RAG, and Tools
+
+Provider code lives under `pkg/provider/`.
+
+- `modelmgr/` manages configured model providers and requesters.
+- `runners/` implements request runners such as the local agent runner and external workflow integrations.
+- `tools/toolmgr.py` aggregates tools from native tools, plugin tools, external MCP servers, and skill-authoring tools.
+- `tools/loaders/mcp.py` is the MCP client side: external MCP servers that LangBot connects to for agent tools.
+- RAG lives across `pkg/rag/`, `pkg/vector/`, model services, and plugin KnowledgeEngine actions.
+
+Do not confuse LangBot's MCP client side with LangBot's own MCP server at `/mcp`; they are different surfaces.
+
+## Plugin System
+
+The plugin system crosses the repo boundary.
+
+In this repo:
+
+- `pkg/plugin/connector.py` connects LangBot to the Plugin Runtime over stdio or WebSocket.
+- `pkg/plugin/handler.py` exposes LangBot actions to the runtime and calls runtime actions for plugin operations.
+- `pkg/provider/tools/loaders/plugin.py` exposes plugin Tool components to LLM runners.
+- Pipeline handlers emit SDK events such as normal-message events and prompt-processing events.
+
+In `langbot-plugin-sdk`:
+
+- `src/langbot_plugin/api/` defines `BasePlugin`, component base classes, message/event entities, contexts, proxies, and manifests.
+- `src/langbot_plugin/runtime/` implements `lbp rt`, plugin discovery, dependency installation, process launching, and control/debug connections.
+- `src/langbot_plugin/entities/io/` defines the action protocol shared by LangBot, runtime, and plugin processes.
+
+The Plugin Runtime supports stdio and WebSocket control transports. Direct local LangBot runs usually spawn the runtime over stdio. Containerized/standalone deployments connect over WebSocket using `plugin.runtime_ws_url` and `--standalone-runtime`.
+
+## Box Runtime and Skills
+
+Box is the sandbox subsystem used by native agent tools, stdio MCP servers, skill authoring, and managed processes.
+
+In this repo:
+
+- `pkg/box/service.py` is the application-facing facade for exec, sessions, managed processes, skill CRUD, status, reconnects, quotas, mounts, and sandbox profiles.
+- `pkg/box/connector.py` connects to the Box Runtime over stdio, Windows subprocess+WebSocket, or remote WebSocket.
+- `pkg/provider/tools/loaders/native.py`, `mcp_stdio.py`, and skill loaders depend on Box availability.
+- `pkg/skill/manager.py` loads skills from the Box runtime, falling back to local `data/skills` when needed.
+
+In `langbot-plugin-sdk`:
+
+- `src/langbot_plugin/box/server.py` implements `lbp box` and the WebSocket endpoints on `:5410`.
+- `src/langbot_plugin/box/runtime.py` owns sandbox sessions and managed processes.
+- `backend.py`, `nsjail_backend.py`, and `e2b_backend.py` implement sandbox backends.
+- `skill_store.py` manages skill packages from the Box side.
+
+Important config keys live under `box:` in `src/langbot/templates/config.yaml`: `box.enabled`, `box.backend`, `box.runtime.endpoint`, and `box.local.*`. Start LangBot with `--standalone-box` when connecting to an externally launched Box runtime.
+
+## HTTP API, Web UI, and MCP Server
+
+`pkg/api/http/controller/main.py` builds a Quart app, registers route groups, serves the built SPA, and wraps the ASGI app with the MCP dispatcher.
+
+- HTTP route groups live under `pkg/api/http/controller/groups/`.
+- Service-layer logic lives under `pkg/api/http/service/`.
+- The built web UI is served from the frontend build path with SPA fallback.
+- The MCP server lives under `pkg/api/mcp/` and is mounted at `/mcp`.
+
+The MCP server intentionally exposes a curated subset of the API. Tools call service classes directly rather than making HTTP requests back into LangBot.
+
+Maintenance rule: when adding, removing, or changing an HTTP endpoint that should be agent-accessible, update the matching MCP tool and the relevant in-repo skill under `skills/` in the same pass.
+
+## Persistence and Configuration
+
+Persistence is centered on `pkg/persistence/mgr.py`.
+
+- SQLite is the default database; PostgreSQL is supported.
+- Models live under `pkg/entity/persistence/`.
+- Fresh schemas are created from metadata, then legacy migrations run up to the frozen 3.x baseline, then Alembic migrations run to head.
+- New schema changes should use Alembic under `pkg/persistence/alembic/versions/`; do not extend the frozen legacy migration chain.
+
+Configuration starts from `src/langbot/templates/config.yaml` and is generated into `data/config.yaml` on first run. Most long-lived managers read from `ap.instance_config.data`.
+
+## Frontend
+
+The frontend lives in `web/` and is a Vite SPA using React Router 7, shadcn/ui, Tailwind CSS, and pnpm. It is not Next.js, despite some historical filenames.
+
+In development, `pnpm dev` serves the UI on `:3000` and reads `VITE_API_BASE_URL` to call the backend on `:5300`. In production, the built frontend is packaged into the Python distribution and served by the backend.
+
+Keep frontend API behavior aligned with `pkg/api/http/service/` and route groups. User-facing strings must go through the existing i18n setup.
+
+## Agent-Facing Surfaces
+
+LangBot is deliberately agent-friendly. The agent-facing surfaces are part of the architecture, not extra docs.
+
+- `skills/` is the single source of truth for in-repo skills.
+- `pkg/api/mcp/server.py` exposes the LangBot MCP server at `/mcp`.
+- `api.global_api_key` authenticates API/MCP access without a browser login.
+- `AGENTS.md` and `ARCHITECTURE.md` tell coding agents how the repo works.
+
+When one of these changes, update the others if the behavior or contract changed. API, MCP tools, and skills are one system; drift is a bug.
+
+## Where to Change Things
+
+- New HTTP API: add/adjust a service in `pkg/api/http/service/`, a route group in `pkg/api/http/controller/groups/`, tests, and MCP/skills if agent-accessible.
+- New platform adapter: add a `pkg/platform/sources/*` adapter, component metadata/templates as needed, i18n, docs, and tests/smoke coverage.
+- New pipeline behavior: add or extend a pipeline stage family under `pkg/pipeline/`; avoid putting pipeline rules in adapters.
+- New LLM provider/requester: work under `pkg/provider/modelmgr/` and related service/UI surfaces.
+- New LLM tool source: extend `pkg/provider/tools/loaders/` and `ToolManager` intentionally.
+- New plugin component/API/protocol: change `langbot-plugin-sdk` first or in lockstep, then update LangBot bridge code.
+- New Box capability: change both `pkg/box/` and `langbot-plugin-sdk/src/langbot_plugin/box/`, plus config and tests.
+- New database schema: add an Alembic migration, not a legacy `dbmXXX` migration.
+
+## Design Biases
+
+- Keep platform translation, pipeline orchestration, provider execution, and runtime protocols separate.
+- Reuse existing registries and service layers instead of adding parallel paths.
+- Prefer small, explicit agent surfaces over exposing every internal API.
+- Treat cross-repo contracts with the SDK as public interfaces.
+- Test behavior at the narrowest useful layer first, then add integration/e2e coverage for runtime or platform changes.
@@ -5,7 +5,7 @@

 <div align="center">

-<a href="https://www.producthunt.com/products/langbot?utm_source=badge-follow&utm_medium=badge&utm_source=badge-langbot" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/follow.svg?product_id=1077185&theme=light" alt="LangBot - Production&#0045;grade&#0032;IM&#0032;bot&#0032;made&#0032;easy&#0046; | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+<a href="https://www.producthunt.com/products/langbot/launches/langbot?embed=true&amp;utm_source=badge-featured&amp;utm_medium=badge&amp;utm_campaign=badge-langbot" target="_blank" rel="noopener noreferrer"><img alt="LangBot - Easy-to-use global IM bot platform designed for the LLM era | Product Hunt" width="250" height="54" src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=979554&amp;theme=light&amp;t=1782822143403"></a>

 <h3>Production-grade platform for building agentic IM bots.</h3>
 <h4>Quickly build, debug, and ship AI bots to Slack, Discord, Telegram, WeChat, and more.</h4>
@@ -136,7 +136,7 @@ docker compose --profile all up -d
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot)                             | GPU Platform | ✅     |
 | [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758)                                                    | GPU Platform | ✅     |
 | [接口 AI](https://jiekou.ai/)                                                                                     | Gateway      | ✅     |
-| [302.AI](https://share.302.ai/SuTG99)                                                                             | Gateway      | ✅     |
+| [302.AI](https://share.302ai.cn/SuTG99)                                                                             | Gateway      | ✅     |
 | [Qiniu](https://www.qiniu.com/ai/agent)                                                                           | Gateway      | ✅     |

 [→ View all integrations](https://link.langbot.app/en/docs/features)
@@ -136,7 +136,7 @@ docker compose --profile all up -d
 | [优云智算](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | GPU 平台 | ✅ |
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | GPU 平台 | ✅ |
 | [接口 AI](https://jiekou.ai/) | 聚合平台 | ✅ |
-| [302.AI](https://share.302.ai/SuTG99) | 聚合平台 | ✅ |
+| [302.AI](https://share.302ai.cn/SuTG99) | 聚合平台 | ✅ |
 | [小马算力](https://www.tokenpony.cn/453z1) | 聚合平台 | ✅ |
 | [百宝箱Tbox](https://www.tbox.cn/open) | 智能体平台 | ✅ |
 | [七牛云Qiniu](https://www.qiniu.com/ai/agent) | 聚合平台 | ✅ |
@@ -5,7 +5,7 @@

 <div align="center">

-<a href="https://www.producthunt.com/products/langbot?utm_source=badge-follow&utm_medium=badge&utm_source=badge-langbot" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/follow.svg?product_id=1077185&theme=light" alt="LangBot - Production&#0045;grade&#0032;IM&#0032;bot&#0032;made&#0032;easy&#0046; | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+<a href="https://www.producthunt.com/products/langbot/launches/langbot?embed=true&amp;utm_source=badge-featured&amp;utm_medium=badge&amp;utm_campaign=badge-langbot" target="_blank" rel="noopener noreferrer"><img alt="LangBot - Easy-to-use global IM bot platform designed for the LLM era | Product Hunt" width="250" height="54" src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=979554&amp;theme=light&amp;t=1782822143403"></a>

 <h3>Plataforma de grado de producción para construir bots de mensajería instantánea con agentes de IA.</h3>
 <h4>Construya, depure y despliegue bots de IA rápidamente en Slack, Discord, Telegram, WeChat y más.</h4>
@@ -135,7 +135,7 @@ docker compose --profile all up -d
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | Plataforma GPU | ✅ |
 | [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | Plataforma GPU | ✅ |
 | [接口 AI](https://jiekou.ai/) | Pasarela | ✅ |
-| [302.AI](https://share.302.ai/SuTG99) | Pasarela | ✅ |
+| [302.AI](https://share.302ai.cn/SuTG99) | Pasarela | ✅ |
 | [Qiniu](https://www.qiniu.com/ai/agent) | Pasarela | ✅ |

 [→ Ver todas las integraciones](https://link.langbot.app/en/docs/features)
@@ -5,7 +5,7 @@

 <div align="center">

-<a href="https://www.producthunt.com/products/langbot?utm_source=badge-follow&utm_medium=badge&utm_source=badge-langbot" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/follow.svg?product_id=1077185&theme=light" alt="LangBot - Production&#0045;grade&#0032;IM&#0032;bot&#0032;made&#0032;easy&#0046; | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+<a href="https://www.producthunt.com/products/langbot/launches/langbot?embed=true&amp;utm_source=badge-featured&amp;utm_medium=badge&amp;utm_campaign=badge-langbot" target="_blank" rel="noopener noreferrer"><img alt="LangBot - Easy-to-use global IM bot platform designed for the LLM era | Product Hunt" width="250" height="54" src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=979554&amp;theme=light&amp;t=1782822143403"></a>

 <h3>Plateforme de niveau production pour construire des bots de messagerie instantanée avec agents IA.</h3>
 <h4>Créez, déboguez et déployez rapidement des bots IA sur Slack, Discord, Telegram, WeChat et plus.</h4>
@@ -132,7 +132,7 @@ docker compose --profile all up -d
 | [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | Passerelle | ✅ |
 | [GiteeAI](https://ai.gitee.com/) | Passerelle | ✅ |
 | [接口 AI](https://jiekou.ai/) | Passerelle | ✅ |
-| [302.AI](https://share.302.ai/SuTG99) | Passerelle | ✅ |
+| [302.AI](https://share.302ai.cn/SuTG99) | Passerelle | ✅ |
 | [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | Plateforme GPU | ✅ |
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | Plateforme GPU | ✅ |
 | [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | Plateforme GPU | ✅ |
@@ -5,7 +5,7 @@

 <div align="center">

-<a href="https://www.producthunt.com/products/langbot?utm_source=badge-follow&utm_medium=badge&utm_source=badge-langbot" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/follow.svg?product_id=1077185&theme=light" alt="LangBot - Production&#0045;grade&#0032;IM&#0032;bot&#0032;made&#0032;easy&#0046; | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+<a href="https://www.producthunt.com/products/langbot/launches/langbot?embed=true&amp;utm_source=badge-featured&amp;utm_medium=badge&amp;utm_campaign=badge-langbot" target="_blank" rel="noopener noreferrer"><img alt="LangBot - Easy-to-use global IM bot platform designed for the LLM era | Product Hunt" width="250" height="54" src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=979554&amp;theme=light&amp;t=1782822143403"></a>

 <h3>AIエージェント搭載IMボットを構築するための本番グレードプラットフォーム。</h3>
 <h4>Slack、Discord、Telegram、WeChat などに AI ボットを素早く構築、デバッグ、デプロイ。</h4>
@@ -135,7 +135,7 @@ docker compose --profile all up -d
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | GPUプラットフォーム | ✅ |
 | [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | GPUプラットフォーム | ✅ |
 | [接口 AI](https://jiekou.ai/) | ゲートウェイ | ✅ |
-| [302.AI](https://share.302.ai/SuTG99) | ゲートウェイ | ✅ |
+| [302.AI](https://share.302ai.cn/SuTG99) | ゲートウェイ | ✅ |
 | [Qiniu](https://www.qiniu.com/ai/agent) | ゲートウェイ | ✅ |

 [→ すべての統合を表示](https://link.langbot.app/en/docs/features)
@@ -5,7 +5,7 @@

 <div align="center">

-<a href="https://www.producthunt.com/products/langbot?utm_source=badge-follow&utm_medium=badge&utm_source=badge-langbot" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/follow.svg?product_id=1077185&theme=light" alt="LangBot - Production&#0045;grade&#0032;IM&#0032;bot&#0032;made&#0032;easy&#0046; | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+<a href="https://www.producthunt.com/products/langbot/launches/langbot?embed=true&amp;utm_source=badge-featured&amp;utm_medium=badge&amp;utm_campaign=badge-langbot" target="_blank" rel="noopener noreferrer"><img alt="LangBot - Easy-to-use global IM bot platform designed for the LLM era | Product Hunt" width="250" height="54" src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=979554&amp;theme=light&amp;t=1782822143403"></a>

 <h3>AI 에이전트 IM 봇 구축을 위한 프로덕션 등급 플랫폼.</h3>
 <h4>Slack, Discord, Telegram, WeChat 등에 AI 봇을 빠르게 구축, 디버그 및 배포.</h4>
@@ -135,7 +135,7 @@ docker compose --profile all up -d
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | GPU 플랫폼 | ✅ |
 | [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | GPU 플랫폼 | ✅ |
 | [接口 AI](https://jiekou.ai/) | 게이트웨이 | ✅ |
-| [302.AI](https://share.302.ai/SuTG99) | 게이트웨이 | ✅ |
+| [302.AI](https://share.302ai.cn/SuTG99) | 게이트웨이 | ✅ |
 | [Qiniu](https://www.qiniu.com/ai/agent) | 게이트웨이 | ✅ |

 [→ 모든 통합 보기](https://link.langbot.app/en/docs/features)
@@ -5,7 +5,7 @@

 <div align="center">

-<a href="https://www.producthunt.com/products/langbot?utm_source=badge-follow&utm_medium=badge&utm_source=badge-langbot" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/follow.svg?product_id=1077185&theme=light" alt="LangBot - Production&#0045;grade&#0032;IM&#0032;bot&#0032;made&#0032;easy&#0046; | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+<a href="https://www.producthunt.com/products/langbot/launches/langbot?embed=true&amp;utm_source=badge-featured&amp;utm_medium=badge&amp;utm_campaign=badge-langbot" target="_blank" rel="noopener noreferrer"><img alt="LangBot - Easy-to-use global IM bot platform designed for the LLM era | Product Hunt" width="250" height="54" src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=979554&amp;theme=light&amp;t=1782822143403"></a>

 <h3>Платформа производственного уровня для создания агентных IM-ботов.</h3>
 <h4>Быстро создавайте, отлаживайте и развертывайте ИИ-ботов в Slack, Discord, Telegram, WeChat и других платформах.</h4>
@@ -131,7 +131,7 @@ docker compose --profile all up -d
 | [Volc Engine Ark](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | Шлюз | ✅ |
 | [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | Шлюз | ✅ |
 | [GiteeAI](https://ai.gitee.com/) | Шлюз | ✅ |
-| [302.AI](https://share.302.ai/SuTG99) | Шлюз | ✅ |
+| [302.AI](https://share.302ai.cn/SuTG99) | Шлюз | ✅ |
 | [接口 AI](https://jiekou.ai/) | Шлюз | ✅ |
 | [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | Платформа GPU | ✅ |
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | Платформа GPU | ✅ |
@@ -137,7 +137,7 @@ docker compose --profile all up -d
 | [優雲智算](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | GPU 平台 | ✅ |
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | GPU 平台 | ✅ |
 | [接口 AI](https://jiekou.ai/) | 聚合平台 | ✅ |
-| [302.AI](https://share.302.ai/SuTG99) | 聚合平台 | ✅ |
+| [302.AI](https://share.302ai.cn/SuTG99) | 聚合平台 | ✅ |
 | [Qiniu](https://www.qiniu.com/ai/agent) | 聚合平台 | ✅ |

 ### TTS（語音合成）
@@ -5,7 +5,7 @@

 <div align="center">

-<a href="https://www.producthunt.com/products/langbot?utm_source=badge-follow&utm_medium=badge&utm_source=badge-langbot" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/follow.svg?product_id=1077185&theme=light" alt="LangBot - Production&#0045;grade&#0032;IM&#0032;bot&#0032;made&#0032;easy&#0046; | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+<a href="https://www.producthunt.com/products/langbot/launches/langbot?embed=true&amp;utm_source=badge-featured&amp;utm_medium=badge&amp;utm_campaign=badge-langbot" target="_blank" rel="noopener noreferrer"><img alt="LangBot - Easy-to-use global IM bot platform designed for the LLM era | Product Hunt" width="250" height="54" src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=979554&amp;theme=light&amp;t=1782822143403"></a>

 <h3>Nền tảng cấp sản xuất để xây dựng bot IM với AI agent.</h3>
 <h4>Xây dựng, gỡ lỗi và triển khai bot AI nhanh chóng trên Slack, Discord, Telegram, WeChat và nhiều nền tảng khác.</h4>
@@ -135,7 +135,7 @@ docker compose --profile all up -d
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | Nền tảng GPU | ✅ |
 | [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | Nền tảng GPU | ✅ |
 | [接口 AI](https://jiekou.ai/) | Cổng | ✅ |
-| [302.AI](https://share.302.ai/SuTG99) | Cổng | ✅ |
+| [302.AI](https://share.302ai.cn/SuTG99) | Cổng | ✅ |
 | [Qiniu](https://www.qiniu.com/ai/agent) | Cổng | ✅ |

 [→ Xem tất cả tích hợp](https://link.langbot.app/en/docs/features)
@@ -0,0 +1,163 @@
+#!/usr/bin/env python3
+"""Compare YAML node definitions with frontend node-configs."""
+
+import yaml
+import os
+import re
+import json
+
+# 1. Parse YAML files
+yaml_dir = 'src/langbot/templates/metadata/nodes'
+yaml_nodes = {}
+
+for filename in sorted(os.listdir(yaml_dir)):
+    if filename.endswith('.yaml'):
+        filepath = os.path.join(yaml_dir, filename)
+        with open(filepath, 'r') as f:
+            data = yaml.safe_load(f)
+            node_name = data.get('name', filename.replace('.yaml', ''))
+            yaml_nodes[node_name] = {
+                'category': data.get('category', ''),
+                'inputs': [i['name'] for i in data.get('inputs', [])],
+                'outputs': [o['name'] for o in data.get('outputs', [])],
+                'config': [c['name'] for c in data.get('config', [])]
+            }
+
+# 2. Parse frontend node-configs TypeScript files
+node_configs_dir = 'web/src/app/home/workflows/components/workflow-editor/node-configs'
+
+frontend_nodes = {}
+
+def parse_ts_file(filepath):
+    """Parse a TypeScript file to extract node configurations."""
+    with open(filepath, 'r') as f:
+        content = f.read()
+    
+    # Find all node type definitions
+    # Pattern: nodeType: 'xxx'
+    node_type_pattern = r"nodeType:\s*'([^']+)'"
+    node_types = re.findall(node_type_pattern, content)
+    
+    # For each node type, extract inputs, outputs, and config
+    for node_type in node_types:
+        # Find the config object for this node type
+        # Look for the section between this nodeType and the next one or end of object
+        pattern = rf"nodeType:\s*'({re.escape(node_type)})'.*?(?=nodeType:|export\s+(const|function)|$)"
+        match = re.search(pattern, content, re.DOTALL)
+        
+        if match:
+            section = match.group(0)
+            
+            # Extract inputs
+            inputs = re.findall(r"createInput\('([^']+)'", section)
+            
+            # Extract outputs  
+            outputs = re.findall(r"createOutput\('([^']+)'", section)
+            
+            # Extract config names
+            config_names = re.findall(r"name:\s*'([^']+)'", section)
+            # Remove duplicates while preserving order
+            seen = set()
+            unique_config = []
+            for c in config_names:
+                if c not in seen:
+                    seen.add(c)
+                    unique_config.append(c)
+            
+            frontend_nodes[node_type] = {
+                'inputs': inputs,
+                'outputs': outputs,
+                'config': unique_config
+            }
+
+# Parse all config files
+for filename in os.listdir(node_configs_dir):
+    if filename.endswith('.ts') and filename != 'types.ts' and filename != 'index.ts':
+        filepath = os.path.join(node_configs_dir, filename)
+        parse_ts_file(filepath)
+
+# 3. Compare and report differences
+print("=" * 80)
+print("WORKFLOW NODE COMPARISON REPORT: YAML vs Frontend")
+print("=" * 80)
+
+all_node_types = sorted(set(list(yaml_nodes.keys()) + list(frontend_nodes.keys())))
+
+discrepancies = []
+
+for node_type in all_node_types:
+    yaml_def = yaml_nodes.get(node_type)
+    frontend_def = frontend_nodes.get(node_type)
+    
+    node_discrepancies = []
+    
+    if not yaml_def:
+        print(f"\n⚠️  {node_type}: ONLY in frontend (not in YAML)")
+        continue
+    if not frontend_def:
+        print(f"\n⚠️  {node_type}: ONLY in YAML (not in frontend)")
+        continue
+    
+    # Compare inputs
+    yaml_inputs = set(yaml_def['inputs'])
+    frontend_inputs = set(frontend_def['inputs'])
+    if yaml_inputs != frontend_inputs:
+        only_yaml = yaml_inputs - frontend_inputs
+        only_frontend = frontend_inputs - yaml_inputs
+        node_discrepancies.append({
+            'type': 'inputs',
+            'only_yaml': list(only_yaml),
+            'only_frontend': list(only_frontend)
+        })
+    
+    # Compare outputs
+    yaml_outputs = set(yaml_def['outputs'])
+    frontend_outputs = set(frontend_def['outputs'])
+    if yaml_outputs != frontend_outputs:
+        only_yaml = yaml_outputs - frontend_outputs
+        only_frontend = frontend_outputs - yaml_outputs
+        node_discrepancies.append({
+            'type': 'outputs',
+            'only_yaml': list(only_yaml),
+            'only_frontend': list(only_frontend)
+        })
+    
+    # Compare config
+    yaml_config = set(yaml_def['config'])
+    frontend_config = set(frontend_def['config'])
+    if yaml_config != frontend_config:
+        only_yaml = yaml_config - frontend_config
+        only_frontend = frontend_config - yaml_config
+        node_discrepancies.append({
+            'type': 'config',
+            'only_yaml': list(only_yaml),
+            'only_frontend': list(only_frontend)
+        })
+    
+    if node_discrepancies:
+        print(f"\n❌ {node_type} ({yaml_def['category']}): HAS DISCREPANCIES")
+        for d in node_discrepancies:
+            print(f"   {d['type']}:")
+            if d['only_yaml']:
+                print(f"     Only in YAML: {d['only_yaml']}")
+            if d['only_frontend']:
+                print(f"     Only in Frontend: {d['only_frontend']}")
+        discrepancies.append((node_type, node_discrepancies))
+    else:
+        print(f"\n✅ {node_type} ({yaml_def['category']}): OK")
+
+print(f"\n{'=' * 80}")
+print(f"SUMMARY: {len(discrepancies)} nodes with discrepancies out of {len(all_node_types)} total")
+print(f"{'=' * 80}")
+
+# Output as JSON for further processing
+output = {
+    'yaml_nodes': {k: v for k, v in yaml_nodes.items()},
+    'frontend_nodes': {k: v for k, v in frontend_nodes.items()},
+    'discrepancies': {k: v for k, v in discrepancies}
+}
+
+with open('node_comparison.json', 'w') as f:
+    json.dump(output, f, indent=2)
+
+print(f"\nDetailed comparison saved to node_comparison.json")
@@ -62,11 +62,12 @@ services:
      - TZ=Asia/Shanghai
      # Unified env-override convention: SECTION__SUBSECTION__KEY overrides the
      # matching config.yaml field (see LoadConfigStage). These map onto
-      # box.local.* and are forwarded to the Box runtime via INIT RPC.
+      # box.* and are forwarded to the Box runtime via INIT RPC.
      - BOX__LOCAL__HOST_ROOT=${LANGBOT_BOX_ROOT:-${PWD}/data/box}
      - BOX__LOCAL__DEFAULT_WORKSPACE=default
      - BOX__LOCAL__SKILLS_ROOT=skills
      - BOX__LOCAL__ALLOWED_MOUNT_ROOTS=${LANGBOT_BOX_ROOT:-${PWD}/data/box}
+      - BOX__DOCKER__CPU_LIMIT_ENABLED=${LANGBOT_BOX_DOCKER_CPU_LIMIT_ENABLED:-true}
    ports:
      - 5300:5300  # For web ui and webhook callback
      - 2280-2285:2280-2285  # For platform reverse connection
@@ -0,0 +1,575 @@
+# HTTP Bot Adapter — Design Document
+
+> Status: **Implemented** · Branch: `feat/http-bot-adapter` · Author: LangBot core
+>
+> A first-class, **standalone** message-platform adapter (`http_bot`) that lets
+> any external system (e.g. LangBot Space ticketing, an internal back-office, a
+> CRM, a custom web app) talk to a LangBot pipeline over plain HTTP — **inbound**
+> by POSTing messages in, **outbound** by receiving replies on a callback URL —
+> with full support for the pipeline's native N→1 aggregation and 1→M
+> multi-reply semantics, and **without** holding a long-lived WebSocket
+> connection.
+>
+> **Shipped in this branch:**
+> - `src/langbot/pkg/platform/sources/http_bot.yaml` — adapter manifest (auto-discovered)
+> - `src/langbot/pkg/platform/sources/http_bot.py` — `HttpBotAdapter`
+> - `src/langbot/pkg/platform/sources/http_bot_signing.py` — HMAC helpers
+> - `src/langbot/pkg/platform/sources/http_bot.svg` — icon
+> - `docs/platforms/http-bot.md` — integration guide
+> - `docs/http-bot-openapi.json` — machine-readable contract
+> - `examples/http-bot/` — Python + TypeScript reference clients
+>
+> **Final decisions (resolving the original open questions):**
+> 1. Callback URL is **config-only** — never accepted per-message (SSRF closed).
+> 2. **Session reset is provided** — `POST /bots/<uuid>/reset` keyed by `session_id`.
+> 3. Reference **clients are provided** — `examples/http-bot/client.py` + `client.ts`.
+> 4. **Sync convenience mode is included** — `POST /bots/<uuid>/sync` (opt-in, lossy).
+
+---
+
+## 1. Background & Motivation
+
+### 1.1 The concrete need
+
+LangBot Space wants to use a LangBot pipeline as the brain for **ticket
+handling**. The integration is **server-to-server**: Space's backend pushes a
+user's ticket messages into LangBot and renders LangBot's replies back into the
+ticket thread.
+
+This interaction is **not** request/response shaped:
+
+- **N → 1**: a user may fire several messages in a row ("the app crashed" …
+  "when I click export" … "here's a screenshot"). The pipeline's
+  **message aggregation** feature should debounce and merge these into one turn.
+- **1 → N**: a single turn may yield **multiple** outbound messages — a tool/
+  function call narrating progress, a plugin emitting several cards, a streamed
+  answer split into chunks.
+
+### 1.2 Why the existing options don't fit
+
+LangBot today exposes exactly one externally-reachable way to drive a pipeline
+that is **not** tied to a specific IM vendor: the **WebSocket** path
+(`/api/v1/pipelines/<uuid>/ws/connect` for dashboard debug, and
+`/api/v1/embed/<bot_uuid>/ws/connect` for the embeddable web widget).
+
+For a server-to-server integration the WebSocket path has real friction:
+
+| Problem | Detail |
+|---|---|
+| Long-lived connection | Caller must maintain a socket, heartbeats, and reconnect logic for what is fundamentally a fire-and-collect workload. |
+| Session identity | Inbound messages are keyed by the transient `connection_id` (`websocket_{connection_id}`); the caller **cannot supply a stable, business-meaningful session id** (e.g. a ticket number). Multi-ticket isolation is not expressible. |
+| Auth mismatch | The debug socket is gated by the **dashboard JWT** (must not be handed to an external service); the embed socket is gated by **Cloudflare Turnstile** (a *browser* human-check that a backend cannot satisfy). Neither is a server-to-server credential. |
+| In-memory, single-process state | Session history lives in process memory and is lost on restart. |
+
+> **Key realisation.** The N→1 / 1→M behaviour the caller wants is **not**
+> provided by WebSocket — it is provided by the **pipeline** (aggregation +
+> the adapter being free to call `reply_message` any number of times). It is
+> therefore **transport-independent**. We can deliver the exact same semantics
+> over a far lighter HTTP transport.
+
+### 1.3 Why a *new, standalone* adapter (not a refactor of an existing one)
+
+The brief is explicit: **do not reuse / fork an existing vendor adapter.** The
+vendor adapters (`lark`, `wecom`, `qqofficial`, `slack`, …) carry vendor-specific
+signature schemes, payload shapes, and message-segment mappings. Bending one of
+them into a "generic" mode would couple a public integration surface to one
+vendor's quirks and make the developer experience worse for everyone.
+
+Instead we ship `http_bot` as a clean, independent adapter whose **entire
+contract is LangBot's own** — documented, versioned, and designed front-to-back
+around *integrator* developer experience.
+
+---
+
+## 2. Goals & Non-Goals
+
+### Goals
+
+- **G1** A standalone `http_bot` adapter, selectable like any other platform
+  adapter in the dashboard, with its own config schema and docs.
+- **G2** **Inbound**: external systems POST messages to a stable LangBot URL,
+  carrying a **caller-defined `session_id`** that maps 1:1 to a LangBot session.
+- **G3** **Outbound**: LangBot delivers each reply by POSTing to a
+  caller-configured **callback URL**; one turn may produce **many** callbacks.
+- **G4** Preserve pipeline-native **N→1 aggregation** and **1→M multi-reply**.
+- **G5** Server-to-server **auth**: shared-secret HMAC request signing both
+  directions (no JWT, no Turnstile, no long-lived socket).
+- **G6** **Great DX**: copy-pasteable curl, a tiny reference client, an OpenAPI
+  fragment, idempotency, clear error envelope, and a local echo-server recipe.
+
+### Non-Goals
+
+- Not replacing or deprecating the WebSocket / embed widget path (that remains
+  the right tool for *browser*, real-time, streaming chat UIs).
+- Not a synchronous "one request → one response" RPC (explicitly rejected: it
+  cannot express 1→M; see §9 for the optional sync convenience mode).
+- No built-in message **persistence/replay** in v1 (callbacks are at-least-once
+  best-effort; durability is the caller's responsibility — see §8).
+- No multi-tenant API-key management UI in v1 (one secret per bot; see §11).
+
+---
+
+## 3. How LangBot routes a message (the parts we plug into)
+
+Understanding the existing flow is what makes this adapter cheap. A message
+flows through these stages (verified against current `master`):
+
+```
+                INBOUND                                         OUTBOUND
+ external POST ─┐                                       ┌─ reply_message()
+               ▼                                        │  reply_message_chunk()
+  POST /bots/<bot_uuid>            (unified webhook router, AuthType.NONE)
+               │  webhooks.py → adapter.handle_unified_webhook(bot_uuid, path, request)
+               ▼                                        │
+  HttpBotAdapter.handle_unified_webhook                 │  (called 0..N times
+   • verify HMAC signature                              │   per turn by the
+   • parse {session_id, message[]}                      │   pipeline / plugins)
+   • build FriendMessage / GroupMessage                 │
+   • fire registered listener  ───────────────┐        │
+               │                               │        │
+               ▼                               ▼        │
+  botmgr.on_friend_message / on_group_message           │
+   • (optional) webhook_pusher fan-out                  │
+   • msg_aggregator.add_message(...) ── N→1 debounce ──►│
+               │                                        │
+               ▼                                        │
+  query_pool → pipeline.run()  ─── invokes adapter ─────┘
+                                    reply methods 1..M times
+```
+
+Two framework facts we rely on:
+
+1. **N→1 aggregation is free.** `botmgr` hands every inbound event to
+   `self.ap.msg_aggregator.add_message(...)`, which debounces per
+   `session_id` and merges consecutive messages into one pipeline turn
+   (`pkg/pipeline/aggregator.py`). The adapter does nothing special.
+
+2. **1→M is free.** The pipeline (and any plugin in the chain) calls
+   `adapter.reply_message()` / `reply_message_chunk()` **as many times as it
+   wants** per turn. The adapter's only job is to deliver each call outward.
+   For `http_bot` that means: **one outbound callback POST per call.**
+
+3. **A unified inbound route already exists.** `WebhookRouterGroup`
+   (`pkg/api/http/controller/groups/webhooks.py`) maps
+   `POST /bots/<bot_uuid>[/<path>]` (auth `NONE`) to
+   `adapter.handle_unified_webhook(bot_uuid, path, request)`. `http_bot`
+   implements that method and is reachable **without registering any new
+   route** — it does its own signature verification, exactly like the vendor
+   webhook adapters do.
+
+> Net new code is essentially: one `http_bot.py` adapter, one `http_bot.yaml`
+> schema, signing helpers, and docs. No router, aggregator, or pipeline changes.
+
+---
+
+## 4. Architecture Overview
+
+```
+┌────────────────────┐         (1) inbound: POST signed message
+│  External system   │  ──────────────────────────────────────────────►  ┌──────────────────────┐
+│ (LangBot Space,    │         POST /bots/<bot_uuid>                      │      LangBot         │
+│  CRM, web app …)   │         X-LB-Signature, X-LB-Timestamp             │                      │
+│                    │         { session_id, message:[...] }              │  HttpBotAdapter      │
+│  - callback server │  ◄──────────────────────────────────────────────  │   (platform/sources) │
+│    (receives       │         (4) outbound: POST signed reply(s)         │                      │
+│     replies)       │         POST <callback_url>                        │  pipeline + aggregator│
+└────────────────────┘         X-LB-Signature, X-LB-Timestamp            └──────────────────────┘
+                               { session_id, sequence, is_final,
+                                 message:[...] }      (sent 1..M times)
+```
+
+- The adapter is **stateless across requests** at the HTTP layer; session
+  continuity is carried by `session_id` and resolved by LangBot's normal
+  session manager.
+- **Inbound** and **outbound** are **independent HTTP exchanges**. LangBot does
+  not answer the inbound POST with the pipeline result; it `202 Accepts` it and
+  later POSTs the reply(s) to the callback URL. This is what makes 1→M natural.
+
+---
+
+## 5. Configuration Schema (`http_bot.yaml`)
+
+Follows the existing `MessagePlatformAdapter` manifest convention (cf.
+`slack.yaml`). Fields:
+
+| field | type | required | purpose |
+|---|---|---|---|
+| `inbound_secret` | string (secret) | yes | HMAC key the **caller** uses to sign inbound POSTs; LangBot verifies. |
+| `callback_url` | string (url) | no* | Where LangBot POSTs replies. *Optional if the caller supplies `callback_url` per-message (see §6.1); a static default lives here. |
+| `outbound_secret` | string (secret) | no | HMAC key LangBot uses to sign outbound callbacks; caller verifies. Defaults to `inbound_secret` if empty. |
+| `default_session_type` | enum `person`/`group` | no | Default when a message omits `session_type`. Default `person`. |
+| `signature_required` | bool | no | If `false`, skip inbound signature check (dev only; logs a warning). Default `true`. |
+| `callback_timeout` | int (seconds) | no | Per-callback HTTP timeout. Default `15`. |
+| `callback_max_retries` | int | no | Retries on 5xx/timeout with backoff. Default `3`. |
+| `webhook_url` | webhook-url (display) | — | Read-only field rendering the inbound URL `…/bots/<bot_uuid>` for copy-paste, like other webhook adapters. |
+
+Manifest sketch (i18n labels elided for brevity):
+
+```yaml
+apiVersion: v1
+kind: MessagePlatformAdapter
+metadata:
+  name: http_bot
+  label: { en_US: "HTTP Bot", zh_Hans: "HTTP 通用接入" }
+  description:
+    en_US: "Integrate any backend over plain HTTP. Push messages in, receive replies on a callback URL. Server-to-server, no long-lived connection."
+    zh_Hans: "通过 HTTP 接入任意后端系统。推入消息、在回调地址接收回复。面向服务间集成，无需长连接。"
+  icon: http_bot.svg
+spec:
+  categories: [popular, global]
+  help_links:
+    zh: https://docs.langbot.app/zh/platforms/http-bot
+    en: https://docs.langbot.app/en/platforms/http-bot
+  config:
+    - { name: inbound_secret,       type: string, required: true,  default: "" }
+    - { name: callback_url,         type: string, required: false, default: "" }
+    - { name: outbound_secret,      type: string, required: false, default: "" }
+    - { name: default_session_type, type: select, required: false, default: "person",
+        options: [person, group] }
+    - { name: signature_required,   type: boolean, required: false, default: true }
+    - { name: callback_timeout,     type: integer, required: false, default: 15 }
+    - { name: callback_max_retries, type: integer, required: false, default: 3 }
+    - { name: webhook_url,          type: webhook-url, required: false, default: "" }
+execution:
+  python:
+    path: ./http_bot.py
+    attr: HttpBotAdapter
+```
+
+---
+
+## 6. The HTTP Contract (this is the DX surface)
+
+### 6.1 Inbound — push a message into LangBot
+
+```
+POST /bots/{bot_uuid}
+Content-Type: application/json
+X-LB-Timestamp: 1718000000
+X-LB-Signature: sha256=<hex hmac>
+X-LB-Idempotency-Key: <uuid>        # optional, dedup window
+```
+
+Body:
+
+```jsonc
+{
+  "session_id": "ticket-10293",        // REQUIRED. Caller-defined. Maps 1:1 to a LangBot session.
+  "session_type": "person",            // optional, "person" | "group"; default from config
+  "sender": {                          // optional metadata, surfaced to pipeline/plugins
+    "id": "user-5567",
+    "name": "Alice"
+  },
+  "message": [                         // REQUIRED. A LangBot MessageChain (list of segments).
+    { "type": "Plain", "text": "Export keeps failing on the dashboard." },
+    { "type": "Image", "url": "https://.../screenshot.png" }
+  ]
+}
+```
+
+Response (LangBot does **not** block on the pipeline):
+
+```jsonc
+// 202 Accepted
+{
+  "code": 0,
+  "msg": "accepted",
+  "data": {
+    "session_id": "ticket-10293",
+    "accepted_message_id": "in_01H....",   // server-assigned id for this inbound message
+    "aggregating": true                    // true if buffered by the aggregator
+  }
+}
+```
+
+**N→1 in practice.** Fire three POSTs with the same `session_id` inside the
+aggregation window → the pipeline runs **once** with the three messages merged.
+No special flag needed; this is the aggregator's default behaviour when enabled
+on the pipeline.
+
+### 6.2 Outbound — LangBot delivers replies to your callback
+
+For each `reply_message` / `reply_message_chunk` the pipeline emits, LangBot
+POSTs to `callback_url`:
+
+```
+POST {callback_url}
+Content-Type: application/json
+X-LB-Timestamp: 1718000001
+X-LB-Signature: sha256=<hex hmac over body>
+```
+
+Body:
+
+```jsonc
+{
+  "session_id": "ticket-10293",         // echoes the inbound session
+  "reply_to": "in_01H....",             // the inbound message id this answers
+  "sequence": 1,                        // 1-based ordinal within this turn (for 1→M ordering)
+  "is_final": false,                    // false for intermediate/streamed parts
+  "stream": false,                      // true when this is a streamed chunk
+  "message": [
+    { "type": "Plain", "text": "Looking into it — checking your export logs…" }
+  ],
+  "timestamp": "2026-06-22T09:00:01Z"
+}
+```
+
+**1→M in practice.** A turn that fires a function call then a final answer
+produces e.g.:
+
+```
+POST callback  → { sequence: 1, is_final: false, message: ["Checking logs…"] }
+POST callback  → { sequence: 2, is_final: false, message: ["Found 2 failed exports."] }
+POST callback  → { sequence: 3, is_final: true,  message: ["Fixed. Try again now."] }
+```
+
+The caller stitches by `session_id` + `sequence`, and knows the turn is complete
+when `is_final: true` arrives.
+
+Your callback endpoint should return `200` quickly. A non-2xx triggers retry
+with backoff (`callback_max_retries`).
+
+### 6.3 Error envelope (inbound)
+
+Consistent, machine-readable; never leak internals:
+
+```jsonc
+{ "code": 40101, "msg": "invalid signature", "data": null }
+```
+
+| HTTP | code | meaning |
+|---|---|---|
+| 202 | 0 | accepted |
+| 400 | 40001 | malformed body / missing `session_id` or `message` |
+| 401 | 40101 | bad/expired signature |
+| 403 | 40301 | bot disabled |
+| 404 | 40401 | bot_uuid not found / not an `http_bot` adapter |
+| 409 | 40901 | duplicate idempotency key (already accepted) |
+| 413 | 41301 | message too large |
+| 500 | 50001 | internal error |
+
+---
+
+## 7. Signing scheme (both directions)
+
+Symmetric, dependency-free HMAC-SHA256 — trivial to implement in any language.
+
+```
+signing_string = "{timestamp}.{raw_request_body}"
+signature      = "sha256=" + hex(HMAC_SHA256(secret, signing_string))
+```
+
+Verification rules:
+
+- Reject if `|now - timestamp| > 300s` (replay window).
+- Constant-time compare (`hmac.compare_digest`).
+- Inbound verified with `inbound_secret`; outbound signed with
+  `outbound_secret` (falls back to `inbound_secret`).
+- `signature_required: false` bypasses verification **and logs a warning** —
+  intended only for local development behind a trusted network.
+
+Reference (Python, ~6 lines):
+
+```python
+import hmac, hashlib, time
+
+def sign(secret: str, body: bytes, ts: int | None = None) -> tuple[str, str]:
+    ts = ts or int(time.time())
+    mac = hmac.new(secret.encode(), f"{ts}.".encode() + body, hashlib.sha256)
+    return str(ts), "sha256=" + mac.hexdigest()
+```
+
+---
+
+## 8. Delivery semantics & reliability
+
+- **Inbound**: `202 Accepted` means *queued*, not *processed*. Use
+  `X-LB-Idempotency-Key` to make client retries safe (dedup window, e.g. 10 min).
+- **Outbound**: **at-least-once**, best-effort. Retries on timeout/5xx with
+  exponential backoff up to `callback_max_retries`. Callbacks for one
+  `session_id` are delivered **in `sequence` order** (serialised per session);
+  across sessions they may interleave.
+- **No persistence in v1**: if LangBot restarts mid-turn, in-flight callbacks
+  may be lost. Durable replay is deferred (see §13). Callers needing exactly-once
+  should dedup on `(session_id, reply_to, sequence)`.
+- **Backpressure**: the adapter must not block the pipeline on slow callbacks —
+  outbound POSTs run on a per-session ordered queue with the configured timeout.
+
+---
+
+## 9. Optional: synchronous convenience mode (v1.1, behind a flag)
+
+Some simple callers genuinely want "POST a message, get the reply in the HTTP
+response" and don't care about streaming/multi-part. We can offer an **opt-in**
+sync endpoint that internally waits for `is_final` and **collapses** all 1→M
+parts into one array:
+
+```
+POST /bots/{bot_uuid}/sync     →    200 { session_id, message: [ ...all parts concatenated... ] }
+```
+
+Implemented by attaching a per-request future that resolves on the final reply,
+with a hard timeout. This is a **convenience wrapper** over the same machinery,
+explicitly documented as lossy for streaming/ordering. Not in v1 core.
+
+---
+
+## 10. Adapter implementation sketch (`platform/sources/http_bot.py`)
+
+Implements `AbstractMessagePlatformAdapter`. Key methods:
+
+```python
+class HttpBotAdapter(AbstractMessagePlatformAdapter):
+    listeners: dict = pydantic.Field(default_factory=dict, exclude=True)
+
+    # --- inbound -------------------------------------------------------
+    async def handle_unified_webhook(self, bot_uuid, path, request):
+        body = await request.get_body()
+        if self.config.get("signature_required", True):
+            if not self._verify(request, body):
+                return jsonify({"code": 40101, "msg": "invalid signature"}), 401
+        data = json.loads(body)
+        session_id    = data["session_id"]                 # caller-defined identity
+        session_type  = data.get("session_type", self.config.get("default_session_type", "person"))
+        chain         = MessageChain.model_validate(data["message"])
+        event         = self._build_event(session_type, session_id, data.get("sender"), chain)
+        # remember where to send replies for this session
+        self._callback_for[session_id] = data.get("callback_url") or self.config.get("callback_url")
+        # fire the registered listener → botmgr → msg_aggregator (N→1) → pipeline
+        if type(event) in self.listeners:
+            asyncio.create_task(self.listeners[type(event)](event, self))
+        return jsonify({"code": 0, "msg": "accepted",
+                        "data": {"session_id": session_id, "accepted_message_id": event.message_id}}), 202
+
+    # --- outbound (called 1..M times per turn by the pipeline) ---------
+    async def reply_message(self, message_source, message, quote_origin=False):
+        return await self._post_callback(message_source, message, is_final=True, stream=False)
+
+    async def reply_message_chunk(self, message_source, bot_message, message,
+                                  quote_origin=False, is_final=False):
+        return await self._post_callback(message_source, message, is_final=is_final, stream=True)
+
+    async def is_stream_output_supported(self) -> bool:
+        return True
+
+    def register_listener(self, event_type, func):   self.listeners[event_type] = func
+    def unregister_listener(self, event_type, func): self.listeners.pop(event_type, None)
+    async def run_async(self): pass     # nothing to poll; purely webhook-driven
+    async def kill(self): pass
+```
+
+`_post_callback` resolves the session's callback URL, assigns the next
+`sequence`, signs the body, and enqueues an ordered, retrying POST.
+
+Session→callback mapping is kept in a small in-memory dict keyed by
+`session_id` (acceptable for v1; a turn's callback URL is captured at inbound
+time so replies always have a destination even if config later changes).
+
+---
+
+## 11. Security considerations
+
+- **Inbound route is `AuthType.NONE`** at the framework level (same as all
+  webhook adapters) — the adapter **must** enforce HMAC itself. Default
+  `signature_required: true`.
+- **Timestamp window** (±300s) + idempotency key blunt replay.
+- **SSRF on callback_url**: validate scheme (`https` in prod), and consider an
+  allow-list / block of private CIDRs since LangBot initiates the POST. Document
+  this; enforce in code where feasible.
+- **Secret storage**: secrets live in the bot's `adapter_config` like every
+  other adapter credential; surfaced as `type: string`/secret in the dashboard.
+- **One secret per bot** in v1. Per-caller key rotation / multiple keys is a
+  future enhancement (§13).
+
+---
+
+## 12. Developer Experience (explicit deliverables)
+
+The whole point of a standalone adapter is that **integrating is pleasant**. v1
+ships:
+
+1. **`docs/platforms/http-bot.md`** — task-oriented integration guide:
+   create the bot → copy inbound URL → set secret → stand up a callback
+   endpoint → send first message → handle 1→M.
+2. **Copy-paste curl** for the first message (with a working signing one-liner).
+3. **Reference clients** (≤50 LOC each) in `examples/http-bot/`:
+   `client.py` (push + a Flask/Quart callback receiver) and `client.ts`.
+4. **OpenAPI fragment** `docs/http-bot-openapi.json` describing inbound +
+   callback shapes, so integrators can codegen.
+5. **Local echo recipe**: a one-command callback server that prints every
+   reply, so a developer sees N→1 and 1→M working in under five minutes.
+6. **Postman/Hoppscotch collection** (nice-to-have).
+
+DX acceptance check: *a developer who has never seen LangBot can, from the docs
+alone, push a message and observe a multi-part reply on their callback within
+10 minutes.*
+
+### Quickstart (curl)
+
+```bash
+BOT=https://your-langbot/bots/2f1c....
+SECRET=supersecret
+BODY='{"session_id":"ticket-10293","message":[{"type":"Plain","text":"hello"}]}'
+TS=$(date +%s)
+SIG="sha256=$(printf '%s.%s' "$TS" "$BODY" | openssl dgst -sha256 -hmac "$SECRET" -r | cut -d' ' -f1)"
+curl -sS -X POST "$BOT" \
+  -H "Content-Type: application/json" \
+  -H "X-LB-Timestamp: $TS" \
+  -H "X-LB-Signature: $SIG" \
+  -d "$BODY"
+```
+
+---
+
+## 13. Future work
+
+- **Durable outbound queue** (persist + replay across restarts; exactly-once).
+- **Per-caller API keys** with rotation and scopes (multi-tenant Space usage).
+- **Sync convenience endpoint** (§9) once core is stable.
+- **Server-Sent Events outbound option** for callers that *do* want a stream but
+  not a full duplex socket — single GET, server pushes chunks.
+- **Dashboard "test console"** for `http_bot` (send a message, watch callbacks)
+  mirroring the existing WebSocket debug panel.
+
+---
+
+## 14. Rollout / task breakdown
+
+| # | Task | Touches |
+|---|---|---|
+| 1 | `http_bot.yaml` manifest + icon | `platform/sources/` |
+| 2 | `HttpBotAdapter` (inbound verify, event build, outbound queue) | `platform/sources/http_bot.py` |
+| 3 | Signing helper module (shared) | `platform/sources/` or `utils/` |
+| 4 | i18n strings (en/zh/ja) | adapter yaml + web locale |
+| 5 | Integration docs `docs/platforms/http-bot.md` | `docs/` |
+| 6 | OpenAPI fragment + reference clients | `docs/`, `examples/http-bot/` |
+| 7 | Tests: signature verify, N→1 aggregation, 1→M ordering, retry | `tests/` |
+| 8 | (opt) SSRF guard for callback_url | adapter |
+
+No changes required to: the unified webhook router, the aggregator, the query
+pool, or the pipeline. That is the design's main payoff.
+
+---
+
+## 15. Resolved decisions
+
+1. **Callback URL trust** — **config-only.** The inbound message may not carry a
+   `callback_url`; replies always go to the bot-config URL. Closes the SSRF
+   vector where a leaked inbound secret could redirect replies.
+2. **Session lifecycle** — **`POST /bots/<uuid>/reset`** (body `{session_id,
+   session_type?}`) drops the matching session from the session manager; the
+   next message starts a fresh conversation. Implemented via sub-path routing in
+   `handle_unified_webhook`.
+3. **Group semantics** — for `session_type: group`, `session_id` is the group/
+   launcher id; `sender.id` (and optional `sender.group_name`) identify the
+   member. A Space ticket maps to one `session_id`.
+4. **Backpressure** — bounded per-session outbound queue (maxlen 1000); on
+   overflow the oldest reply is dropped and a warning logged, so a persistently
+   down callback can never exhaust memory.
+
+### Still open / deferred (see §13)
+
+- Durable outbound queue (persist + replay across restarts).
+- Per-caller API keys with rotation/scopes for multi-tenant Space usage.
+- SSE outbound option and a dashboard test console.
@@ -0,0 +1,713 @@
+# Workflow 系统开发者文档
+
+本文档面向 LangBot 开发者，详细介绍 Workflow 系统的技术架构、核心组件和扩展方法。
+
+## 目录
+
+- [系统架构概述](#系统架构概述)
+- [目录结构](#目录结构)
+- [核心组件](#核心组件)
+  - [后端模块](#后端模块)
+  - [前端组件](#前端组件)
+- [数据库表结构](#数据库表结构)
+- [API 接口文档](#api-接口文档)
+- [如何添加新节点类型](#如何添加新节点类型)
+- [调试功能实现](#调试功能实现)
+
+---
+
+## 系统架构概述
+
+Workflow 系统采用前后端分离架构，主要包含以下层次：
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│                      前端层 (React)                          │
+│  ┌─────────────┬──────────────┬──────────────┬───────────┐  │
+│  │ 可视化编辑器 │   节点面板    │   属性面板   │  调试器   │  │
+│  │ ReactFlow   │  NodePalette │ PropertyPanel│ Debugger  │  │
+│  └─────────────┴──────────────┴──────────────┴───────────┘  │
+├─────────────────────────────────────────────────────────────┤
+│                      API 层 (Quart)                          │
+│  ┌─────────────┬──────────────┬──────────────────────────┐  │
+│  │ Workflow API│  Debug API   │     Node Types API       │  │
+│  └─────────────┴──────────────┴──────────────────────────┘  │
+├─────────────────────────────────────────────────────────────┤
+│                     核心引擎层 (Python)                       │
+│  ┌─────────────┬──────────────┬──────────────┬───────────┐  │
+│  │ Executor    │   Registry   │    Node      │ Entities  │  │
+│  │ 执行引擎     │  节点注册表   │   节点基类   │  数据结构  │  │
+│  └─────────────┴──────────────┴──────────────┴───────────┘  │
+├─────────────────────────────────────────────────────────────┤
+│                      存储层 (SQLAlchemy)                     │
+│  ┌─────────────┬──────────────┬──────────────────────────┐  │
+│  │  Workflow   │  Executions  │        Triggers          │  │
+│  └─────────────┴──────────────┴──────────────────────────┘  │
+└─────────────────────────────────────────────────────────────┘
+```
+
+---
+
+## 目录结构
+
+### 后端代码结构
+
+```
+LangBot/src/langbot/pkg/
+├── workflow/                      # Workflow 核心模块
+│   ├── __init__.py               # 模块初始化，导出公共接口
+│   ├── entities.py               # 数据实体定义
+│   ├── executor.py               # 执行引擎
+│   ├── node.py                   # 节点基类和装饰器
+│   ├── registry.py               # 节点类型注册表
+│   └── nodes/                    # 内置节点实现
+│       ├── __init__.py           # 注册所有内置节点
+│       ├── trigger.py            # 触发节点
+│       ├── process.py            # 处理节点
+│       ├── control.py            # 控制节点
+│       └── action.py             # 动作节点
+├── entity/persistence/
+│   └── workflow.py               # 数据库模型
+├── api/http/
+│   ├── controller/groups/workflows/
+│   │   └── workflows.py          # API 路由控制器
+│   └── service/
+│       └── workflow.py           # 业务逻辑服务
+└── persistence/migrations/
+    └── dbm026_workflow_tables.py # 数据库迁移
+```
+
+### 前端代码结构
+
+```
+LangBot/web/src/app/home/workflows/
+├── page.tsx                      # Workflow 列表页
+├── WorkflowDetailContent.tsx     # 详情页内容
+├── store/
+│   └── useWorkflowStore.ts       # Zustand 状态管理
+└── components/
+    ├── workflow-editor/          # 可视化编辑器
+    │   ├── index.ts              # 导出
+    │   ├── WorkflowEditorComponent.tsx  # 主编辑器组件
+    │   ├── WorkflowNodeComponent.tsx    # 自定义节点组件
+    │   ├── NodePalette.tsx       # 节点面板
+    │   ├── PropertyPanel.tsx     # 属性面板
+    │   └── node-configs/         # 节点配置元数据
+    │       ├── types.ts          # 配置类型定义
+    │       ├── trigger-configs.ts
+    │       ├── ai-configs.ts
+    │       ├── process-configs.ts
+    │       ├── control-configs.ts
+    │       ├── action-configs.ts
+    │       ├── integration-configs.ts
+    │       └── index.ts          # 配置汇总
+    ├── workflow-debugger/        # 调试器组件
+    │   ├── index.ts
+    │   └── WorkflowDebugger.tsx
+    ├── workflow-form/            # 表单组件
+    │   └── WorkflowFormComponent.tsx
+    └── workflow-executions/      # 执行历史组件
+        └── WorkflowExecutionsTab.tsx
+```
+
+---
+
+## 核心组件
+
+### 后端模块
+
+#### 1. 执行引擎 (WorkflowExecutor)
+
+位置：[`executor.py`](../../src/langbot/pkg/workflow/executor.py)
+
+执行引擎负责工作流的实际执行，包括：
+
+- **拓扑排序**：确定节点执行顺序
+- **节点执行**：调用各节点的 execute 方法
+- **控制流处理**：处理条件分支、循环、并行执行
+- **错误处理**：支持重试机制
+
+```python
+class WorkflowExecutor:
+    async def execute(
+        self, 
+        workflow: WorkflowDefinition, 
+        context: ExecutionContext,
+        start_node_id: Optional[str] = None
+    ) -> ExecutionContext:
+        """执行工作流"""
+        # 1. 构建执行图
+        # 2. 初始化节点状态
+        # 3. 找到起始节点
+        # 4. 按拓扑顺序执行
+```
+
+**调试执行器 (DebugWorkflowExecutor)**
+
+继承自 WorkflowExecutor，增加了调试支持：
+
+- 断点支持
+- 单步执行
+- 暂停/继续
+- 实时日志
+
+```python
+class DebugWorkflowExecutor(WorkflowExecutor):
+    async def execute_debug(
+        self,
+        workflow: WorkflowDefinition,
+        context: ExecutionContext,
+        debug_state: DebugExecutionState,
+    ) -> ExecutionContext:
+        """调试模式执行"""
+```
+
+#### 2. 节点注册表 (NodeTypeRegistry)
+
+位置：[`registry.py`](../../src/langbot/pkg/workflow/registry.py)
+
+单例模式管理所有节点类型：
+
+```python
+class NodeTypeRegistry:
+    _instance: Optional['NodeTypeRegistry'] = None
+    
+    def register(self, node_type: str, node_class: type[WorkflowNode]):
+        """注册节点类型"""
+        
+    def create_instance(self, node_type: str, node_id: str, config: dict) -> WorkflowNode:
+        """创建节点实例"""
+        
+    def list_all(self) -> list[dict]:
+        """获取所有节点类型的 Schema"""
+```
+
+#### 3. 节点基类 (WorkflowNode)
+
+位置：[`node.py`](../../src/langbot/pkg/workflow/node.py)
+
+所有节点必须继承此基类：
+
+```python
+class WorkflowNode(abc.ABC):
+    # 节点元数据
+    type_name: str = ""
+    name: str = ""
+    description: str = ""
+    category: str = "misc"
+    icon: str = ""
+    
+    # 端口定义
+    inputs: list[NodePort] = []
+    outputs: list[NodePort] = []
+    
+    # 配置 Schema
+    config_schema: list[NodeConfig] = []
+    
+    @abc.abstractmethod
+    async def execute(
+        self, 
+        inputs: dict[str, Any], 
+        context: ExecutionContext
+    ) -> dict[str, Any]:
+        """执行节点逻辑"""
+        pass
+```
+
+#### 4. 数据实体 (entities.py)
+
+主要数据结构：
+
+```python
+class WorkflowDefinition:
+    """工作流定义"""
+    uuid: str
+    name: str
+    nodes: list[NodeDefinition]
+    edges: list[EdgeDefinition]
+    settings: WorkflowSettings
+    
+class ExecutionContext:
+    """执行上下文"""
+    execution_id: str
+    workflow_id: str
+    status: ExecutionStatus
+    variables: dict
+    node_states: dict[str, NodeState]
+    history: list[ExecutionStep]
+```
+
+### 前端组件
+
+#### 1. WorkflowEditorComponent
+
+主编辑器组件，基于 React Flow 实现：
+
+- **画布交互**：拖拽、缩放、平移
+- **节点连接**：自动验证端口类型
+- **撤销/重做**：基于历史记录栈
+- **复制/粘贴**：支持多选复制
+
+关键功能：
+
+```tsx
+function WorkflowEditorInner() {
+  const { nodes, edges, onNodesChange, onEdgesChange, onConnect } = useWorkflowStore();
+  
+  // 拖放添加节点
+  const onDrop = useCallback((event: React.DragEvent) => {
+    const type = event.dataTransfer.getData('application/reactflow');
+    const position = screenToFlowPosition({ x: event.clientX, y: event.clientY });
+    addNode(type, position);
+  }, []);
+  
+  // 复制粘贴
+  const handleCopy = useCallback(() => { ... }, []);
+  const handlePaste = useCallback(() => { ... }, []);
+}
+```
+
+#### 2. NodePalette
+
+节点面板组件，展示可用节点类型：
+
+```tsx
+function NodePalette() {
+  // 按类别组织节点
+  const categories = [
+    { id: 'trigger', name: '触发节点', icon: Zap },
+    { id: 'ai', name: 'AI 节点', icon: Brain },
+    { id: 'process', name: '处理节点', icon: Cpu },
+    { id: 'control', name: '控制节点', icon: GitBranch },
+    { id: 'action', name: '动作节点', icon: Send },
+    { id: 'integration', name: '集成节点', icon: Plug },
+  ];
+  
+  // 拖拽开始
+  const onDragStart = (event: React.DragEvent, nodeType: string) => {
+    event.dataTransfer.setData('application/reactflow', nodeType);
+  };
+}
+```
+
+#### 3. PropertyPanel
+
+属性面板组件，动态渲染节点配置表单：
+
+```tsx
+function PropertyPanel() {
+  const { selectedNodeId, nodes, updateNodeData } = useWorkflowStore();
+  
+  // 根据节点类型获取配置元数据
+  const selectedNode = nodes.find(n => n.id === selectedNodeId);
+  const nodeConfig = getNodeConfig(selectedNode?.data?.nodeType);
+  
+  // 动态渲染配置字段
+  return (
+    <div>
+      {nodeConfig?.fields.map(field => (
+        <ConfigField key={field.name} field={field} />
+      ))}
+    </div>
+  );
+}
+```
+
+#### 4. WorkflowDebugger
+
+调试器组件，支持实时调试：
+
+```tsx
+function WorkflowDebugger({ workflowUuid, workflow }) {
+  const [debugState, setDebugState] = useState<DebugState>('idle');
+  const [executionId, setExecutionId] = useState<string>('');
+  const [logs, setLogs] = useState<ExecutionLog[]>([]);
+  
+  // 启动调试
+  const startDebug = async () => {
+    const result = await backendClient.post(
+      `/api/v1/workflows/${workflowUuid}/debug/start`,
+      { context, variables, breakpoints }
+    );
+    setExecutionId(result.execution_id);
+  };
+  
+  // 轮询状态
+  useEffect(() => {
+    if (debugState === 'running') {
+      const interval = setInterval(fetchState, 500);
+      return () => clearInterval(interval);
+    }
+  }, [debugState]);
+}
+```
+
+#### 5. useWorkflowStore
+
+Zustand 状态管理：
+
+```typescript
+interface WorkflowState {
+  nodes: WorkflowNode[];
+  edges: WorkflowEdge[];
+  selectedNodeId: string | null;
+  history: HistoryEntry[];
+  historyIndex: number;
+  isDirty: boolean;
+  
+  // Actions
+  addNode: (type: string, position: XYPosition) => void;
+  updateNodeData: (nodeId: string, data: Partial<NodeData>) => void;
+  deleteNode: (nodeId: string) => void;
+  undo: () => void;
+  redo: () => void;
+}
+
+export const useWorkflowStore = create<WorkflowState>((set, get) => ({
+  // ... state and actions
+}));
+```
+
+---
+
+## 数据库表结构
+
+### workflows 表
+
+```sql
+CREATE TABLE workflows (
+    uuid VARCHAR(255) PRIMARY KEY,
+    name VARCHAR(255) NOT NULL,
+    description TEXT,
+    emoji VARCHAR(10) DEFAULT '🔄',
+    version INTEGER DEFAULT 1,
+    is_enabled BOOLEAN DEFAULT TRUE,
+    definition JSON NOT NULL,        -- 节点和边定义
+    global_config JSON DEFAULT '{}', -- 全局配置
+    extensions_preferences JSON,     -- 插件和 MCP 配置
+    created_at TIMESTAMP,
+    updated_at TIMESTAMP
+);
+```
+
+### workflow_versions 表
+
+```sql
+CREATE TABLE workflow_versions (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    workflow_uuid VARCHAR(255) NOT NULL,
+    version INTEGER NOT NULL,
+    definition JSON NOT NULL,
+    global_config JSON DEFAULT '{}',
+    created_at TIMESTAMP,
+    created_by VARCHAR(255),
+    UNIQUE(workflow_uuid, version)
+);
+```
+
+### workflow_executions 表
+
+```sql
+CREATE TABLE workflow_executions (
+    uuid VARCHAR(255) PRIMARY KEY,
+    workflow_uuid VARCHAR(255) NOT NULL,
+    workflow_version INTEGER NOT NULL,
+    status VARCHAR(20) NOT NULL,  -- pending/running/completed/failed/cancelled
+    trigger_type VARCHAR(50),
+    trigger_data JSON,
+    variables JSON,
+    start_time TIMESTAMP,
+    end_time TIMESTAMP,
+    error TEXT,
+    created_at TIMESTAMP
+);
+```
+
+### workflow_node_executions 表
+
+```sql
+CREATE TABLE workflow_node_executions (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    execution_uuid VARCHAR(255) NOT NULL,
+    node_id VARCHAR(100) NOT NULL,
+    node_type VARCHAR(50) NOT NULL,
+    status VARCHAR(20) NOT NULL,
+    inputs JSON,
+    outputs JSON,
+    start_time TIMESTAMP,
+    end_time TIMESTAMP,
+    error TEXT,
+    retry_count INTEGER DEFAULT 0
+);
+```
+
+### workflow_triggers 表
+
+```sql
+CREATE TABLE workflow_triggers (
+    uuid VARCHAR(255) PRIMARY KEY,
+    workflow_uuid VARCHAR(255) NOT NULL,
+    type VARCHAR(50) NOT NULL,  -- message/cron/event/webhook
+    config JSON NOT NULL,
+    is_enabled BOOLEAN DEFAULT TRUE,
+    priority INTEGER DEFAULT 0,
+    created_at TIMESTAMP,
+    updated_at TIMESTAMP
+);
+```
+
+---
+
+## API 接口文档
+
+### Workflow CRUD
+
+| 方法 | 路径 | 描述 |
+|-----|------|------|
+| GET | `/api/v1/workflows` | 获取工作流列表 |
+| POST | `/api/v1/workflows` | 创建工作流 |
+| GET | `/api/v1/workflows/:uuid` | 获取单个工作流 |
+| PUT | `/api/v1/workflows/:uuid` | 更新工作流 |
+| DELETE | `/api/v1/workflows/:uuid` | 删除工作流 |
+| POST | `/api/v1/workflows/:uuid/copy` | 复制工作流 |
+
+### 执行相关
+
+| 方法 | 路径 | 描述 |
+|-----|------|------|
+| POST | `/api/v1/workflows/:uuid/execute` | 手动执行工作流 |
+| GET | `/api/v1/workflows/:uuid/executions` | 获取执行记录 |
+
+### 版本管理
+
+| 方法 | 路径 | 描述 |
+|-----|------|------|
+| GET | `/api/v1/workflows/:uuid/versions` | 获取版本列表 |
+| POST | `/api/v1/workflows/:uuid/rollback/:version` | 回滚到指定版本 |
+
+### 调试 API
+
+| 方法 | 路径 | 描述 |
+|-----|------|------|
+| POST | `/api/v1/workflows/:uuid/debug/start` | 启动调试 |
+| POST | `/api/v1/workflows/:uuid/debug/:exec_id/pause` | 暂停执行 |
+| POST | `/api/v1/workflows/:uuid/debug/:exec_id/resume` | 继续执行 |
+| POST | `/api/v1/workflows/:uuid/debug/:exec_id/stop` | 停止执行 |
+| POST | `/api/v1/workflows/:uuid/debug/:exec_id/step` | 单步执行 |
+| GET | `/api/v1/workflows/:uuid/debug/:exec_id/state` | 获取调试状态 |
+
+### 节点类型
+
+| 方法 | 路径 | 描述 |
+|-----|------|------|
+| GET | `/api/v1/workflows/_/node-types` | 获取所有节点类型 |
+| GET | `/api/v1/workflows/_/node-types/categories` | 按类别获取节点类型 |
+
+---
+
+## 如何添加新节点类型
+
+### 步骤 1：创建节点类
+
+在 `LangBot/src/langbot/pkg/workflow/nodes/` 下创建或修改文件：
+
+```python
+from ..node import WorkflowNode, NodePort, NodeConfig, workflow_node
+from ..entities import ExecutionContext
+
+@workflow_node('my_custom_node')
+class MyCustomNode(WorkflowNode):
+    """自定义节点"""
+    
+    # 元数据
+    type_name = 'my_custom_node'
+    name = '我的自定义节点'
+    description = '这是一个自定义节点'
+    category = 'process'  # trigger/process/control/action/integration
+    icon = '🔧'
+    
+    # 输入端口
+    inputs = [
+        NodePort(name='input', type='string', description='输入数据', required=True),
+    ]
+    
+    # 输出端口
+    outputs = [
+        NodePort(name='output', type='string', description='输出数据'),
+    ]
+    
+    # 配置字段
+    config_schema = [
+        NodeConfig(
+            name='option',
+            type='select',
+            required=True,
+            options=['选项A', '选项B'],
+            description='选择一个选项'
+        ),
+        NodeConfig(
+            name='value',
+            type='string',
+            required=False,
+            default='默认值',
+            description='配置值'
+        ),
+    ]
+    
+    async def execute(
+        self, 
+        inputs: dict[str, Any], 
+        context: ExecutionContext
+    ) -> dict[str, Any]:
+        """执行节点逻辑"""
+        input_data = inputs.get('input', '')
+        option = self.get_config('option')
+        value = self.get_config('value', '')
+        
+        # 处理逻辑
+        result = f"处理: {input_data} with {option} and {value}"
+        
+        return {'output': result}
+```
+
+### 步骤 2：注册节点
+
+在 `LangBot/src/langbot/pkg/workflow/nodes/__init__.py` 中导入：
+
+```python
+from .process import (
+    CodeExecutorNode,
+    HttpRequestNode,
+    DataTransformNode,
+    MyCustomNode,  # 添加新节点
+)
+```
+
+### 步骤 3：添加前端配置
+
+在 `LangBot/web/src/app/home/workflows/components/workflow-editor/node-configs/` 目录下添加配置：
+
+```typescript
+// process-configs.ts
+export const processNodeConfigs: NodeConfigMap = {
+  // ... 其他配置
+  
+  my_custom_node: {
+    type: 'my_custom_node',
+    label: 'workflows.nodes.myCustomNode',
+    description: 'workflows.nodes.myCustomNodeDesc',
+    icon: 'Wrench',
+    category: 'process',
+    fields: [
+      {
+        name: 'option',
+        type: 'select',
+        label: 'workflows.fields.option',
+        required: true,
+        options: [
+          { value: '选项A', label: '选项 A' },
+          { value: '选项B', label: '选项 B' },
+        ],
+      },
+      {
+        name: 'value',
+        type: 'string',
+        label: 'workflows.fields.value',
+        required: false,
+        defaultValue: '默认值',
+      },
+    ],
+  },
+};
+```
+
+### 步骤 4：添加国际化
+
+在 `LangBot/web/src/i18n/locales/` 中添加翻译：
+
+```typescript
+// zh-Hans.ts
+workflows: {
+  nodes: {
+    myCustomNode: '我的自定义节点',
+    myCustomNodeDesc: '这是一个自定义节点',
+  },
+  fields: {
+    option: '选项',
+    value: '值',
+  },
+}
+```
+
+---
+
+## 调试功能实现
+
+### 后端调试状态管理
+
+```python
+class DebugExecutionState:
+    """调试执行状态"""
+    
+    def __init__(self, execution_id: str, breakpoints: list[str] = None):
+        self.execution_id = execution_id
+        self.status: str = 'running'
+        self.is_paused: bool = False
+        self.is_stopped: bool = False
+        self.breakpoints: set[str] = set(breakpoints or [])
+        self.logs: list[ExecutionLog] = []
+        self._pause_event = asyncio.Event()
+    
+    def pause(self):
+        """暂停执行"""
+        self.is_paused = True
+        self._pause_event.clear()
+    
+    def resume(self):
+        """继续执行"""
+        self.is_paused = False
+        self._pause_event.set()
+    
+    async def wait_if_paused(self):
+        """如果暂停则等待"""
+        if self.is_paused:
+            await self._pause_event.wait()
+```
+
+### 前端调试流程
+
+1. **设置断点**：点击节点设置断点
+2. **启动调试**：调用 `/debug/start` 启动调试执行
+3. **轮询状态**：定期调用 `/debug/:id/state` 获取状态
+4. **控制执行**：调用 pause/resume/step/stop 控制执行
+5. **查看日志**：实时显示执行日志和节点状态
+
+```typescript
+// 调试状态轮询
+const fetchDebugState = async () => {
+  const state = await backendClient.get(
+    `/api/v1/workflows/${workflowUuid}/debug/${executionId}/state`
+  );
+  
+  // 更新节点状态
+  setNodeStates(state.node_states);
+  
+  // 追加新日志
+  if (state.new_logs.length > 0) {
+    setLogs(prev => [...prev, ...state.new_logs]);
+  }
+  
+  // 检查完成状态
+  if (state.status === 'completed' || state.status === 'error') {
+    setDebugState('idle');
+  }
+};
+```
+
+---
+
+## 扩展阅读
+
+- [Workflow 功能设计文档](../../../plans/langbot-workflow-design.md)
+- [用户使用指南](../user-guide/workflow-guide.md)
+- [API 认证文档](../API_KEY_AUTH.md)
@@ -0,0 +1,198 @@
+{
+  "openapi": "3.0.3",
+  "info": {
+    "title": "LangBot HTTP Bot Adapter",
+    "version": "1.0.0",
+    "description": "Server-to-server HTTP integration for a LangBot pipeline. Inbound messages are POSTed to the unified webhook route; replies are delivered to a configured callback URL (one POST per reply part). All requests are HMAC-SHA256 signed. See docs/platforms/http-bot.md."
+  },
+  "paths": {
+    "/bots/{bot_uuid}": {
+      "post": {
+        "summary": "Push a message into the pipeline (fire-and-collect)",
+        "description": "Returns 202 immediately. Replies arrive asynchronously on the configured callback URL. Reuse the same session_id within the aggregation window to merge multiple messages into one turn (N->1).",
+        "parameters": [
+          { "$ref": "#/components/parameters/BotUuid" },
+          { "$ref": "#/components/parameters/Timestamp" },
+          { "$ref": "#/components/parameters/Signature" },
+          { "$ref": "#/components/parameters/Idempotency" }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": { "application/json": { "schema": { "$ref": "#/components/schemas/InboundMessage" } } }
+        },
+        "responses": {
+          "202": {
+            "description": "Accepted (queued for the pipeline)",
+            "content": { "application/json": { "schema": { "$ref": "#/components/schemas/AcceptedResponse" } } }
+          },
+          "400": { "$ref": "#/components/responses/Error" },
+          "401": { "$ref": "#/components/responses/Error" },
+          "409": { "$ref": "#/components/responses/Error" },
+          "413": { "$ref": "#/components/responses/Error" }
+        }
+      }
+    },
+    "/bots/{bot_uuid}/sync": {
+      "post": {
+        "summary": "Push a message and wait for the collapsed reply",
+        "description": "Blocking convenience mode. Waits for is_final and returns all reply parts collapsed into one array. Lossy (no sequence/streaming). One in-flight sync per session_id.",
+        "parameters": [
+          { "$ref": "#/components/parameters/BotUuid" },
+          { "$ref": "#/components/parameters/Timestamp" },
+          { "$ref": "#/components/parameters/Signature" }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": { "application/json": { "schema": { "$ref": "#/components/schemas/InboundMessage" } } }
+        },
+        "responses": {
+          "200": {
+            "description": "The collapsed reply",
+            "content": { "application/json": { "schema": { "$ref": "#/components/schemas/SyncResponse" } } }
+          },
+          "400": { "$ref": "#/components/responses/Error" },
+          "401": { "$ref": "#/components/responses/Error" }
+        }
+      }
+    },
+    "/bots/{bot_uuid}/reset": {
+      "post": {
+        "summary": "Reset a session's conversation",
+        "parameters": [
+          { "$ref": "#/components/parameters/BotUuid" },
+          { "$ref": "#/components/parameters/Timestamp" },
+          { "$ref": "#/components/parameters/Signature" }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "type": "object",
+                "required": ["session_id"],
+                "properties": {
+                  "session_id": { "type": "string" },
+                  "session_type": { "type": "string", "enum": ["person", "group"] }
+                }
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": { "description": "Reset done" },
+          "400": { "$ref": "#/components/responses/Error" },
+          "401": { "$ref": "#/components/responses/Error" }
+        }
+      }
+    }
+  },
+  "components": {
+    "parameters": {
+      "BotUuid": {
+        "name": "bot_uuid", "in": "path", "required": true,
+        "schema": { "type": "string", "format": "uuid" }
+      },
+      "Timestamp": {
+        "name": "X-LB-Timestamp", "in": "header", "required": true,
+        "description": "Unix seconds; rejected if more than +/-300s from server time.",
+        "schema": { "type": "string" }
+      },
+      "Signature": {
+        "name": "X-LB-Signature", "in": "header", "required": true,
+        "description": "sha256=<hex> of HMAC-SHA256(secret, \"{timestamp}.\" + raw_body).",
+        "schema": { "type": "string" }
+      },
+      "Idempotency": {
+        "name": "X-LB-Idempotency-Key", "in": "header", "required": false,
+        "description": "Dedup key; a repeat within the dedup window returns 409.",
+        "schema": { "type": "string" }
+      }
+    },
+    "schemas": {
+      "Segment": {
+        "type": "object",
+        "required": ["type"],
+        "properties": {
+          "type": { "type": "string", "enum": ["Plain", "Image", "Voice", "File", "At", "Quote"] },
+          "text": { "type": "string", "description": "For type=Plain." },
+          "url": { "type": "string", "description": "For media types." },
+          "base64": { "type": "string", "description": "For media types (data URI or raw base64)." }
+        }
+      },
+      "InboundMessage": {
+        "type": "object",
+        "required": ["session_id", "message"],
+        "properties": {
+          "session_id": { "type": "string", "description": "Caller-defined; maps 1:1 to a LangBot session." },
+          "session_type": { "type": "string", "enum": ["person", "group"], "default": "person" },
+          "sender": {
+            "type": "object",
+            "properties": {
+              "id": { "type": "string" },
+              "name": { "type": "string" },
+              "group_name": { "type": "string", "description": "For session_type=group." }
+            }
+          },
+          "message": { "type": "array", "items": { "$ref": "#/components/schemas/Segment" } }
+        }
+      },
+      "AcceptedResponse": {
+        "type": "object",
+        "properties": {
+          "code": { "type": "integer", "example": 0 },
+          "msg": { "type": "string", "example": "accepted" },
+          "data": {
+            "type": "object",
+            "properties": {
+              "session_id": { "type": "string" },
+              "accepted_message_id": { "type": "string", "example": "in_01H..." },
+              "aggregating": { "type": "boolean" }
+            }
+          }
+        }
+      },
+      "SyncResponse": {
+        "type": "object",
+        "properties": {
+          "code": { "type": "integer", "example": 0 },
+          "msg": { "type": "string", "example": "ok" },
+          "data": {
+            "type": "object",
+            "properties": {
+              "session_id": { "type": "string" },
+              "reply_to": { "type": "string" },
+              "message": { "type": "array", "items": { "$ref": "#/components/schemas/Segment" } }
+            }
+          }
+        }
+      },
+      "Callback": {
+        "type": "object",
+        "description": "Delivered by LangBot to your callback_url, one POST per reply part. Signed with the outbound secret.",
+        "properties": {
+          "session_id": { "type": "string" },
+          "reply_to": { "type": "string", "description": "The accepted_message_id this answers." },
+          "sequence": { "type": "integer", "description": "1-based ordinal within the turn." },
+          "is_final": { "type": "boolean", "description": "True on the last part of the turn." },
+          "stream": { "type": "boolean" },
+          "message": { "type": "array", "items": { "$ref": "#/components/schemas/Segment" } },
+          "timestamp": { "type": "string", "format": "date-time" }
+        }
+      },
+      "ErrorEnvelope": {
+        "type": "object",
+        "properties": {
+          "code": { "type": "integer", "example": 40101 },
+          "msg": { "type": "string", "example": "invalid signature: signature_mismatch" },
+          "data": { "nullable": true }
+        }
+      }
+    },
+    "responses": {
+      "Error": {
+        "description": "Error envelope",
+        "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorEnvelope" } } }
+      }
+    }
+  }
+}
@@ -0,0 +1,256 @@
+# HTTP Bot Adapter — Integration Guide
+
+Integrate **any backend system** with a LangBot pipeline over plain HTTP. Push
+messages in via a signed webhook; receive replies on a callback URL. No
+long-lived connection, full support for message **aggregation** (many inbound
+messages merged into one turn) and **multi-part replies** (one turn → many
+outbound messages).
+
+This is the right adapter for **server-to-server** integrations — ticketing
+systems, CRMs, internal tools, custom web backends. (For an in-browser,
+real-time chat widget, use the embeddable Web Page Bot instead.)
+
+> **5-minute goal:** stand up a callback receiver, send a message, and watch a
+> multi-part reply arrive — using the reference client in
+> [`examples/http-bot/`](../../examples/http-bot/).
+
+---
+
+## 1. Mental model
+
+```
+Your backend  ──(1) POST signed message──►  LangBot   /bots/<bot_uuid>
+                                            (pipeline runs: aggregate → think → reply)
+Your callback ◄─(2) POST signed reply(s)──  LangBot   one POST per reply part
+```
+
+- **(1) Inbound** is *fire-and-collect*: LangBot answers `202 Accepted`
+  immediately and does **not** return the pipeline result on that response.
+- **(2) Outbound** replies arrive later as separate signed POSTs to your
+  `callback_url`. A single turn may produce **several** callbacks (e.g. a tool
+  call narration followed by the final answer).
+- Everything is keyed by a **`session_id` you choose** (e.g. a ticket number).
+  Each `session_id` maps to one isolated LangBot conversation.
+
+---
+
+## 2. Create the bot
+
+1. In the LangBot dashboard, add a bot and choose the **HTTP Bot** platform.
+2. Fill in the config:
+
+   | Field | Required | Notes |
+   |---|---|---|
+   | **Inbound Signing Secret** | yes | Your backend signs inbound requests with this. |
+   | **Outbound Callback URL** | yes | Where LangBot POSTs replies. **Config-only** — cannot be overridden per message (SSRF protection). |
+   | **Outbound Signing Secret** | no | LangBot signs callbacks with this; defaults to the inbound secret. |
+   | **Default Session Type** | no | `person` (default) or `group`. |
+   | **Require Inbound Signature** | no | Keep `true` in production. |
+   | **Callback Timeout / Max Retries** | no | Defaults: 15s, 3 retries. |
+
+3. Bind the bot to a **pipeline** and **enable** it.
+4. Copy the **Inbound Webhook URL** shown in the config — it looks like
+   `https://your-langbot/bots/<bot_uuid>`.
+
+---
+
+## 3. The signature scheme
+
+Both directions use the same dependency-free HMAC-SHA256 scheme:
+
+```
+signing_string = "{timestamp}." + raw_body_bytes
+signature      = "sha256=" + hex(HMAC_SHA256(secret, signing_string))
+```
+
+Sent as headers:
+
+| Header | Meaning |
+|---|---|
+| `X-LB-Timestamp` | Unix seconds. Rejected if more than **±300s** from server time. |
+| `X-LB-Signature` | `sha256=<hex>` over `"{timestamp}." + body`. |
+| `X-LB-Idempotency-Key` | *(optional, inbound)* dedup key; retries with the same key return `409`. |
+
+Verify outbound callbacks the same way, using the **outbound** secret (or the
+inbound secret if you left it blank).
+
+A six-line reference implementation is in `examples/http-bot/client.py`
+(`sign()` / `verify()`); a Node/TS version is in `client.ts`.
+
+---
+
+## 4. Send your first message (curl)
+
+```bash
+BOT="https://your-langbot/bots/<bot_uuid>"
+SECRET="your-inbound-secret"
+BODY='{"session_id":"ticket-10293","message":[{"type":"Plain","text":"Export keeps failing on the dashboard."}]}'
+TS=$(date +%s)
+SIG="sha256=$(printf '%s.%s' "$TS" "$BODY" | openssl dgst -sha256 -hmac "$SECRET" -r | cut -d' ' -f1)"
+
+curl -sS -X POST "$BOT" \
+  -H "Content-Type: application/json" \
+  -H "X-LB-Timestamp: $TS" \
+  -H "X-LB-Signature: $SIG" \
+  -d "$BODY"
+# -> 202 {"code":0,"msg":"accepted","data":{"session_id":"ticket-10293","accepted_message_id":"in_...","aggregating":true}}
+```
+
+The reply(s) will be POSTed to your configured callback URL shortly after.
+
+---
+
+## 5. Inbound request format
+
+`POST /bots/{bot_uuid}`
+
+```jsonc
+{
+  "session_id": "ticket-10293",     // REQUIRED. Your stable id. Maps 1:1 to a LangBot session.
+  "session_type": "person",         // optional: "person" | "group"; default from config
+  "sender": {                       // optional metadata, surfaced to the pipeline/plugins
+    "id": "user-5567",
+    "name": "Alice"
+  },
+  "message": [                      // REQUIRED. A LangBot MessageChain (array of segments).
+    { "type": "Plain", "text": "Export keeps failing on the dashboard." },
+    { "type": "Image", "url": "https://example.com/screenshot.png" }
+  ]
+}
+```
+
+**Message segments.** Text uses `{"type":"Plain","text":"..."}`. Images use
+`{"type":"Image","url":"..."}` (or `base64`). Other supported types: `Voice`,
+`File`, `At`, `Quote`.
+
+> Note: the callback URL is **not** accepted in the body — it is taken only from
+> bot config. This is deliberate (prevents an attacker who obtains the inbound
+> secret from redirecting replies to an arbitrary host).
+
+### Aggregation (N → 1)
+
+If your pipeline has **message aggregation** enabled, send several messages with
+the **same `session_id`** within the aggregation window and they are merged into
+**one** pipeline turn. No special flag — just reuse the `session_id`.
+
+---
+
+## 6. Outbound callback format
+
+LangBot POSTs each reply part to your `callback_url`:
+
+```jsonc
+{
+  "session_id": "ticket-10293",     // echoes the inbound session
+  "reply_to": "in_01H...",          // the accepted_message_id this answers
+  "sequence": 1,                    // 1-based ordinal within this turn
+  "is_final": false,                // true on the last part of the turn
+  "stream": false,                  // true for streamed chunks
+  "message": [ { "type": "Plain", "text": "Looking into it…" } ],
+  "timestamp": "2026-06-22T09:00:01Z"
+}
+```
+
+Your endpoint should return `2xx` quickly. Non-2xx / timeout → LangBot retries
+with exponential backoff (up to `callback_max_retries`).
+
+### Multi-part replies (1 → M)
+
+One turn may emit multiple callbacks, delivered **in `sequence` order** for a
+given session:
+
+```
+seq=1 is_final=false  "Checking your export logs…"
+seq=2 is_final=false  "Found 2 failed exports."
+seq=3 is_final=true   "Fixed — please try again."
+```
+
+Stitch by `session_id` + `sequence`; the turn is complete when
+`is_final: true` arrives.
+
+---
+
+## 7. Reset a session
+
+Start a fresh conversation for a `session_id` (drops history):
+
+```
+POST /bots/{bot_uuid}/reset
+{ "session_id": "ticket-10293", "session_type": "person" }
+→ 200 { "code":0, "msg":"reset", "data": { "session_id":"ticket-10293", "removed": true } }
+```
+
+Signed exactly like an inbound message.
+
+---
+
+## 8. Synchronous convenience mode
+
+If you don't need streaming/multi-part and just want one reply back on the same
+HTTP call, POST to `/sync`. LangBot waits for the turn to finish and returns all
+parts **collapsed** into one array:
+
+```
+POST /bots/{bot_uuid}/sync
+{ "session_id": "ticket-10293", "message": [ { "type":"Plain", "text":"hi" } ] }
+→ 200 { "code":0, "msg":"ok",
+        "data": { "session_id":"ticket-10293", "reply_to":"in_...",
+                  "message": [ {"type":"Plain","text":"..."}, ... ] } }
+```
+
+This is **lossy** (you lose `sequence` / streaming boundaries) and blocks up to
+`callback_timeout × 4` seconds. Prefer the callback model for anything
+real-time or multi-part. Only one in-flight `/sync` per `session_id`.
+
+---
+
+## 9. Error envelope
+
+```jsonc
+{ "code": 40101, "msg": "invalid signature: signature_mismatch", "data": null }
+```
+
+| HTTP | code | meaning |
+|---|---|---|
+| 202 | 0 | accepted |
+| 400 | 40001 | malformed body / missing `session_id` or `message` |
+| 401 | 40101 | bad/expired signature |
+| 409 | 40901 | duplicate idempotency key |
+| 413 | 41301 | message too large (>1 MiB) |
+| 500 | 50001 | internal error |
+
+---
+
+## 10. Try it end-to-end in 5 minutes
+
+```bash
+cd examples/http-bot
+pip install flask requests
+
+# Terminal 1 — your callback receiver (point the bot's callback_url here, e.g. via a tunnel):
+python client.py serve --port 8900 --secret SHARED_SECRET
+
+# Terminal 2 — push a message:
+python client.py push \
+  --url https://your-langbot/bots/<bot_uuid> \
+  --secret SHARED_SECRET \
+  --session ticket-1 \
+  --text "hello"
+```
+
+Watch Terminal 1 print each reply part (`[part ]` / `[FINAL]`) with its
+sequence number — that's 1→M working, signatures verified.
+
+A machine-readable contract is in
+[`docs/http-bot-openapi.json`](../http-bot-openapi.json).
+
+---
+
+## 11. Security checklist
+
+- Keep **Require Inbound Signature** on in production.
+- Use **HTTPS** callback URLs; the URL is config-only (no per-message override).
+- Treat the secrets like passwords; rotate via the dashboard.
+- The inbound route is unauthenticated at the framework level **by design** —
+  security comes entirely from the HMAC signature, so never disable it on a
+  public deployment.
@@ -0,0 +1,196 @@
+# MCP Resources PR #2215 Review
+
+> 更新日期: 2026-06-29
+> 分支: `mcp_resources`
+> PR: langbot-app/LangBot#2215
+> 主题: MCP Resources 在 LangBot 中的产品价值、AgentRunner 集成方式与后续架构方向
+
+## 结论
+
+PR #2215 对 LangBot 有明确价值：它补齐了 MCP 协议中 Resources 这一重要能力，让 MCP server 不再只暴露 tools，也可以暴露文档、代码片段、配置、日志、图片等上下文资源。管理端可以发现和预览资源，Agent 也可以通过当前实现按需列出和读取资源。
+
+但当前 AgentRunner 层的接入方式更接近一个可用的第一阶段方案，而不是最终架构。现在 MCP Resources 被包装成两个 synthetic tools：
+
+- `langbot_mcp_list_resources`
+- `langbot_mcp_read_resource`
+
+这让模型可以通过 function calling 主动探索资源，落地成本低，也复用了已有 `ToolManager` / `LocalAgentRunner` 的工具调用链路。不过从 MCP 规范和主流实现来看，Resources 更适合作为一种一等上下文来源，而不是长期隐藏在工具列表里。
+
+建议保留当前 synthetic tools 作为探索能力，同时把后续主线设计调整为：MCP Resources 是 pipeline / conversation / message 级别可选择、可固定、可审计的上下文输入。
+
+## 当前实现判断
+
+当前 AgentRunner 集成路径如下：
+
+```text
+Pipeline 绑定 MCP server
+  -> query.variables['_pipeline_bound_mcp_servers']
+  -> Preproc 为 local-agent 加载工具
+  -> ToolManager.get_all_tools()
+  -> MCPLoader 注入 synthetic resource tools
+  -> LocalAgentRunner 将工具 schema 传给模型
+  -> 模型发起 list/read tool call
+  -> ToolManager.execute_func_call()
+  -> MCPLoader 调 MCP session.list_resources/read_resource
+  -> tool result 回灌给模型
+```
+
+这个路径的优点是：
+
+- 复用现有工具调用机制，改动范围小。
+- Agent 可以按需探索资源，不需要每轮预先读取所有资源。
+- 可以沿用 pipeline 绑定的 MCP server 范围，避免越权读取未绑定 server。
+- 对已有 MCP tools 行为影响较小。
+
+主要问题是：
+
+- Resources 在语义上被降级成 tools，和 MCP 规范里的 resource primitive 不完全一致。
+- 模型必须先理解并主动调用 `list/read`，资源不会自然成为上下文。
+- pipeline 不能配置“默认携带某些资源”或“本轮附加某些资源”。
+- UI 资源 tab 目前是管理端预览能力，和 Agent 上下文选择没有打通。
+- 对 blob、图片、大文件、结构化资源的处理还比较粗糙。
+- 缺少 resource templates、订阅更新、缓存、chunk、token budget、trace 与审计策略。
+
+## 主流项目做法
+
+### MCP 官方规范
+
+MCP Resources 是 server 暴露上下文数据的协议能力。规范没有要求 resources 必须以 tool call 形式给模型使用，而是把如何选择、过滤、读取和纳入上下文交给 Host application。
+
+这意味着比较正统的集成方式是：LangBot 作为 Host，在 pipeline、会话或消息层决定哪些 resources 进入模型上下文。
+
+参考: https://modelcontextprotocol.io/specification/2025-06-18/server/resources
+
+### VS Code Copilot
+
+VS Code 把 MCP Resources 做成 chat context 的一部分。用户可以通过 `Add Context > MCP Resources` 或命令浏览 MCP resources，并把选中的资源附加到一次 chat request。
+
+这是目前最值得 LangBot 参考的产品形态：资源不是模型工具，而是用户和 Host 可控的上下文附件。
+
+参考: https://code.visualstudio.com/docs/agent-customization/mcp-servers
+
+### Anthropic SDK
+
+Anthropic 的 client-side MCP helpers 提供资源读取和转换能力，例如把 MCP resource 转为 Claude message content 或 file。也就是说，应用先读取 resource，再显式放进模型消息。
+
+这同样是 application-owned context injection，而不是把 resource 伪装成模型工具。
+
+参考: https://platform.claude.com/docs/en/agents-and-tools/mcp-connector
+
+### LangChain MCP Adapters
+
+LangChain 把 MCP Resources 更像 data loader / document input 来处理，可以把资源加载成 `Blob`，再进入 LangChain 的文档、检索或上下文处理链路。
+
+这说明 Resources 很适合作为知识源、文档源或上下文源，而不只是即时工具调用。
+
+参考: https://docs.langchain.com/oss/python/langchain/mcp
+
+### OpenAI Agents SDK
+
+OpenAI Agents SDK 主路径仍偏向 MCP tools，但底层 MCP server API 已经有 `list_resources`、`list_resource_templates`、`read_resource` 等能力。当前形态说明 resources 是 client 能力，但并未默认变成 agent-visible tools。
+
+参考: https://openai.github.io/openai-agents-python/mcp/
+
+### Cline
+
+Cline 会拉取 MCP tools、resources、resourceTemplates、prompts，并通过类似 `access_mcp_resource` 的内置访问方式让模型读取资源。这个方向和 LangBot 当前 synthetic tools 比较接近。
+
+这种模式适合让 Agent 自主探索，但更像 Host 自定义的模型访问协议，不应成为唯一集成路径。
+
+参考: https://github.com/cline/cline/blob/main/src/services/mcp/McpHub.ts
+
+## 建议架构方向
+
+### 1. 保留探索型工具
+
+保留当前两个 synthetic tools：
+
+- `langbot_mcp_list_resources`
+- `langbot_mcp_read_resource`
+
+它们适合处理“用户没有显式选择资源，但 Agent 判断需要探索 MCP server 上下文”的场景。后续可以优化工具描述、返回格式、资源大小限制和错误信息。
+
+### 2. 增加一等 Resource Context
+
+新增一个 Host 层资源上下文概念，例如：
+
+```text
+PipelineResourceBinding
+ConversationResourceAttachment
+MessageResourceAttachment
+```
+
+Preproc 或独立的 `ResourceContextProvider` 在模型调用前读取这些资源，按 MIME 类型、大小、token budget 转为模型可消费的上下文。
+
+### 3. 打通 UI 与 Agent 上下文
+
+当前 MCP 详情页的 Resources tab 可以继续作为资源发现和预览入口。建议增加操作：
+
+- 添加到本轮上下文
+- 固定到当前 pipeline
+- 固定到当前 bot / conversation
+- 查看资源读取历史和错误
+
+这样 UI 资源管理能力才能真正影响 Agent 行为。
+
+### 4. 支持 resource templates
+
+MCP resource templates 允许 server 暴露参数化资源，例如：
+
+```text
+repo://{owner}/{repo}/file/{path}
+log://{service}/{date}
+```
+
+LangBot 后续应支持模板发现、参数填写、实例化和绑定。否则只能使用静态 resources，覆盖面会受限。
+
+### 5. 增加资源处理策略
+
+建议补齐：
+
+- 文本资源 token budget 与截断策略。
+- 大文件 chunk 与摘要策略。
+- 图片/blob 的模型能力判断与 fallback。
+- MIME 类型白名单与安全限制。
+- 缓存与过期策略。
+- `resources/listChanged` 或订阅更新。
+- resource read trace，便于审计 Agent 读取了什么上下文。
+
+## 推荐落地顺序
+
+### Phase 1: 完成当前 PR 可用性
+
+- 保留 synthetic tools。
+- 明确文档说明当前 Agent 集成是 tool-mediated。
+- 完善资源工具描述，降低模型误用概率。
+- 给 read/list 增加大小限制和更清晰的 MIME 处理。
+- 前端 Resources tab 与 Tools tab 分离，保持管理端清晰。
+
+### Phase 2: 做 Host-owned context attachments
+
+- 在 pipeline 或 conversation 层新增 resource attachment 配置。
+- Preproc 读取已绑定 resources，注入模型上下文。
+- UI 支持“添加到上下文 / 固定到 pipeline”。
+- 记录每轮实际注入的 resource URI 和 token 消耗。
+
+### Phase 3: 做完整 MCP Resources 能力
+
+- 支持 resource templates。
+- 支持资源订阅更新。
+- 支持 chunk、summary、RAG 化接入。
+- 为 DifyAgentRunner、LocalAgentRunner 等不同 runner 定义统一资源上下文接口。
+
+## 最终建议
+
+PR #2215 可以作为 MCP Resources 的第一阶段实现继续推进。它让 LangBot 快速拥有“资源发现、预览、按需读取”的闭环，也给 Agent 探索资源提供了可运行路径。
+
+但在正式设计上，不建议把 “Resources == Tools” 固化为长期抽象。LangBot 更应该把 MCP Resources 定位为上下文来源，与 tools、prompts、knowledge base 并列：
+
+```text
+Tools      -> Agent 可以执行的动作
+Resources  -> Host/用户/Agent 可以选择的上下文数据
+Prompts    -> 可复用的任务模板
+Knowledge  -> 可检索、可索引的长期知识
+```
+
+这样既尊重 MCP 协议语义，也能让 LangBot 在 Agent 工作流、企业知识接入和多 MCP server 管理上走得更稳。
@@ -0,0 +1,425 @@
+# Workflow 用户指南
+
+本文档帮助您了解和使用 LangBot 的 Workflow（工作流）功能，通过可视化方式构建自动化的对话处理流程。
+
+## 目录
+
+- [功能介绍](#功能介绍)
+- [快速入门](#快速入门)
+- [节点类型说明](#节点类型说明)
+- [编辑器使用指南](#编辑器使用指南)
+- [调试功能](#调试功能)
+- [常见问题解答](#常见问题解答)
+
+---
+
+## 功能介绍
+
+### 什么是 Workflow？
+
+Workflow（工作流）是 LangBot 提供的可视化自动化编排系统。通过拖拽节点、连接边的方式，您可以：
+
+- 📝 **构建复杂的对话流程**：使用条件分支、循环等控制节点
+- 🤖 **调用 AI 能力**：集成 LLM、知识库检索、参数提取
+- 🔗 **连接外部服务**：集成 Dify、n8n、Coze 等平台
+- ⚡ **自动化任务执行**：消息触发、定时触发、Webhook 触发
+
+### Workflow vs Pipeline
+
+| 对比项 | Pipeline | Workflow |
+|-------|----------|----------|
+| 配置方式 | 表单配置 | 可视化拖拽 |
+| 流程控制 | 线性执行 | 支持分支、循环、并行 |
+| 适用场景 | 简单对话 | 复杂流程 |
+| 学习曲线 | 低 | 中等 |
+
+---
+
+## 快速入门
+
+### 第一步：创建 Workflow
+
+1. 在侧边栏点击 **Workflow** 进入工作流列表
+2. 点击右上角 **创建工作流** 按钮
+3. 填写基本信息：
+   - **名称**：给工作流起一个描述性的名字
+   - **描述**：可选，说明工作流的用途
+   - **图标**：选择一个 emoji 作为标识
+
+### 第二步：添加节点
+
+进入编辑器后，左侧是节点面板，中间是画布区域，右侧是属性面板。
+
+1. **添加触发节点**：从左侧面板拖拽一个"消息触发"节点到画布
+2. **添加 AI 节点**：拖拽一个"LLM 调用"节点
+3. **添加回复节点**：拖拽一个"回复消息"节点
+
+### 第三步：连接节点
+
+1. 将鼠标悬停在触发节点的输出端口（右侧小圆点）
+2. 按住鼠标拖拽到 LLM 节点的输入端口（左侧小圆点）
+3. 同样方式连接 LLM 节点和回复节点
+
+```
+[消息触发] ──▶ [LLM 调用] ──▶ [回复消息]
+```
+
+### 第四步：配置节点
+
+点击 LLM 调用节点，在右侧属性面板配置：
+
+- **运行方式**：选择"本地 Agent"
+- **系统提示词**：描述 AI 的角色和行为
+- **模型**：选择要使用的 LLM 模型
+
+点击回复消息节点配置：
+
+- **消息内容**：设置为 `{{nodes.llm_call.outputs.response}}`（引用 LLM 输出）
+
+### 第五步：保存并绑定
+
+1. 点击工具栏的 **保存** 按钮
+2. 返回 Bot 配置页面
+3. 在 Bot 的绑定设置中选择 **Workflow**，然后选择刚创建的工作流
+
+恭喜！您已经创建了第一个 Workflow。
+
+---
+
+## 节点类型说明
+
+### 触发节点 (Trigger)
+
+触发节点是工作流的入口，定义何时启动执行。
+
+| 节点 | 说明 | 输出 |
+|-----|------|------|
+| 消息触发 | 收到消息时触发 | message, sender_id, platform |
+| 定时触发 | 按 Cron 表达式定时触发 | timestamp |
+| Webhook 触发 | 收到 HTTP 请求时触发 | request_body, headers |
+| 事件触发 | 系统事件触发 | event_type, event_data |
+
+**消息触发配置示例**：
+
+```yaml
+触发条件:
+  - 关键词匹配: ["帮助", "help"]
+  - 平台: ["wechat", "qq"]
+```
+
+### AI 节点
+
+AI 节点用于调用各种 AI 能力。
+
+| 节点 | 说明 | 典型用途 |
+|-----|------|---------|
+| LLM 调用 | 调用大语言模型 | 生成回复、理解意图 |
+| 问题分类器 | 对用户问题分类 | 路由到不同处理分支 |
+| 参数提取器 | 从文本提取结构化数据 | 提取订单号、日期等 |
+| 知识库检索 | 查询知识库 | RAG 增强回复 |
+
+**LLM 调用配置示例**：
+
+```yaml
+运行方式: 本地 Agent
+模型: gpt-4
+系统提示词: |
+  你是一个友好的客服助手。
+  请根据用户的问题提供帮助。
+温度: 0.7
+最大 Token 数: 2000
+```
+
+### 处理节点 (Process)
+
+处理节点用于数据处理和外部调用。
+
+| 节点 | 说明 | 典型用途 |
+|-----|------|---------|
+| 代码执行 | 执行 Python/JavaScript 代码 | 数据处理、格式转换 |
+| HTTP 请求 | 发送 HTTP 请求 | 调用外部 API |
+| 数据转换 | JSON/模板转换 | 数据格式化 |
+
+**HTTP 请求配置示例**：
+
+```yaml
+URL: https://api.example.com/data
+方法: POST
+请求头:
+  Content-Type: application/json
+  Authorization: Bearer {{variables.api_key}}
+请求体: |
+  {"query": "{{message.content}}"}
+```
+
+### 控制节点 (Control)
+
+控制节点用于流程控制。
+
+| 节点 | 说明 | 用途 |
+|-----|------|------|
+| 条件分支 | 二选一分支 | if-else 逻辑 |
+| 多路分支 | 多选一分支 | switch-case 逻辑 |
+| 循环 | 遍历数组 | 批量处理 |
+| 并行 | 同时执行多分支 | 并发处理 |
+| 等待 | 暂停执行 | 延时处理 |
+| 合并 | 合并多个分支 | 汇总结果 |
+
+**条件分支配置示例**：
+
+```yaml
+条件表达式: "{{nodes.classifier.outputs.category}}" == "complaint"
+真分支: 投诉处理
+假分支: 普通咨询
+```
+
+### 动作节点 (Action)
+
+动作节点执行具体操作。
+
+| 节点 | 说明 | 用途 |
+|-----|------|------|
+| 发送消息 | 主动发送消息 | 通知、推送 |
+| 回复消息 | 回复当前消息 | 对话回复 |
+| 存储数据 | 保存数据到存储 | 持久化 |
+| 调用 Pipeline | 调用现有 Pipeline | 复用现有流程 |
+
+**回复消息配置示例**：
+
+```yaml
+消息内容: |
+  感谢您的咨询！
+  
+  {{nodes.llm_call.outputs.response}}
+  
+  如有其他问题，随时联系我。
+```
+
+### 集成节点 (Integration)
+
+集成节点连接外部平台。
+
+| 节点 | 说明 | 平台 |
+|-----|------|------|
+| Dify 工作流 | 调用 Dify 应用 | Dify |
+| Dify 知识库 | 查询 Dify 知识库 | Dify |
+| n8n 工作流 | 调用 n8n 流程 | n8n |
+| Langflow | 调用 Langflow 流程 | Langflow |
+| Coze Bot | 调用扣子 Bot | Coze |
+
+**Dify 工作流配置示例**：
+
+```yaml
+API 地址: https://api.dify.ai/v1
+API Key: sk-xxxxx
+应用类型: workflow
+同步对话历史: true
+```
+
+---
+
+## 编辑器使用指南
+
+### 画布操作
+
+| 操作 | 方式 |
+|-----|------|
+| 平移画布 | 按住鼠标中键/空格+左键 拖拽 |
+| 缩放画布 | 鼠标滚轮 / 工具栏按钮 |
+| 框选多个节点 | 按住 Shift + 拖拽框选 |
+| 适应视图 | 点击工具栏"适应"按钮 |
+
+### 节点操作
+
+| 操作 | 方式 |
+|-----|------|
+| 添加节点 | 从左侧面板拖拽到画布 |
+| 移动节点 | 点击节点拖拽 |
+| 删除节点 | 选中后按 Delete / 点击工具栏删除 |
+| 复制节点 | 选中后 Ctrl+C / 工具栏复制 |
+| 粘贴节点 | Ctrl+V / 工具栏粘贴 |
+
+### 连接操作
+
+| 操作 | 方式 |
+|-----|------|
+| 创建连接 | 从输出端口拖拽到输入端口 |
+| 删除连接 | 点击连接线后按 Delete |
+| 选中连接 | 点击连接线 |
+
+### 快捷键
+
+| 快捷键 | 功能 |
+|-------|------|
+| Ctrl + Z | 撤销 |
+| Ctrl + Shift + Z | 重做 |
+| Ctrl + C | 复制 |
+| Ctrl + V | 粘贴 |
+| Delete | 删除选中 |
+| Ctrl + S | 保存 |
+
+### 工具栏功能
+
+```
+[撤销] [重做] | [放大] [缩小] [适应] | [复制] [粘贴] [删除] | [保存] [调试]
+```
+
+---
+
+## 调试功能
+
+### 启动调试
+
+1. 点击工具栏的 **调试** 按钮
+2. 在调试面板中配置初始数据：
+   - **输入消息**：模拟用户发送的消息
+   - **会话 ID**：可选，用于测试会话变量
+   - **变量**：设置初始变量值
+
+3. 点击 **开始调试** 按钮
+
+### 调试控制
+
+| 按钮 | 功能 |
+|-----|------|
+| ▶️ 开始/继续 | 开始或继续执行 |
+| ⏸️ 暂停 | 暂停执行 |
+| ⏹️ 停止 | 停止执行 |
+| ⏭️ 单步 | 执行下一个节点 |
+
+### 断点
+
+- **设置断点**：点击节点上的断点图标
+- **断点触发**：执行到断点时自动暂停
+- **查看状态**：在暂停时查看节点的输入输出
+
+### 执行日志
+
+调试面板下方显示实时日志：
+
+```
+[INFO] 2024-01-15 10:30:00 - Starting debug execution
+[INFO] 2024-01-15 10:30:00 - Executing node: message_trigger
+[DEBUG] 2024-01-15 10:30:00 - Node inputs: {"message": "你好"}
+[INFO] 2024-01-15 10:30:01 - Node completed in 50ms
+[INFO] 2024-01-15 10:30:01 - Executing node: llm_call
+...
+```
+
+### 节点状态颜色
+
+| 颜色 | 状态 |
+|-----|------|
+| 灰色 | 待执行 |
+| 蓝色 | 执行中 |
+| 绿色 | 已完成 |
+| 红色 | 失败 |
+| 黄色 | 已跳过 |
+
+---
+
+## 常见问题解答
+
+### Q1：如何在节点间传递数据？
+
+使用表达式语法引用其他节点的输出：
+
+```
+{{nodes.节点ID.outputs.输出名称}}
+```
+
+例如：
+- `{{nodes.llm_call.outputs.response}}` - 引用 LLM 节点的响应
+- `{{nodes.http_request.outputs.body}}` - 引用 HTTP 请求的响应体
+
+### Q2：如何使用变量？
+
+Workflow 支持三种变量类型：
+
+1. **工作流变量**：`{{variables.变量名}}`
+2. **会话变量**：`{{conversation_variables.变量名}}`
+3. **消息上下文**：`{{message.content}}`、`{{message.sender_id}}`
+
+### Q3：条件分支如何写条件表达式？
+
+支持以下运算符：
+
+- 比较：`==`, `!=`, `>`, `<`, `>=`, `<=`
+- 逻辑：`and`, `or`, `not`
+- 包含：`in`
+
+示例：
+```python
+# 字符串比较
+"{{nodes.classifier.outputs.intent}}" == "purchase"
+
+# 数值比较
+{{nodes.extractor.outputs.amount}} > 1000
+
+# 包含检查
+"退款" in "{{message.content}}"
+```
+
+### Q4：如何处理错误？
+
+1. **节点级重试**：在节点配置中设置重试次数
+2. **全局错误处理**：在 Workflow 设置中配置错误处理策略
+3. **条件分支**：使用条件节点检查上一节点的状态
+
+### Q5：如何查看执行历史？
+
+1. 进入 Workflow 详情页
+2. 点击 **执行历史** 标签
+3. 查看每次执行的状态、耗时、输入输出
+
+### Q6：Workflow 可以被多个 Bot 使用吗？
+
+是的。一个 Workflow 可以被多个 Bot 绑定使用，但每个 Bot 只能绑定一个处理单元（Pipeline 或 Workflow）。
+
+### Q7：如何复制现有的 Workflow？
+
+在 Workflow 列表页，点击工作流卡片右上角的菜单，选择"复制"即可创建副本。
+
+### Q8：支持版本回滚吗？
+
+支持。每次保存都会创建新版本。在 Workflow 详情页可以查看版本历史并回滚到指定版本。
+
+---
+
+## 最佳实践
+
+### 1. 合理命名
+
+- 为节点和 Workflow 使用描述性名称
+- 使用统一的命名规范
+
+### 2. 模块化设计
+
+- 将复杂流程拆分为多个小 Workflow
+- 使用"调用 Pipeline"节点复用现有流程
+
+### 3. 错误处理
+
+- 为关键节点设置重试机制
+- 使用条件分支处理异常情况
+- 添加日志记录便于排查问题
+
+### 4. 测试先行
+
+- 使用调试功能充分测试
+- 准备多种测试场景
+- 检查边界情况
+
+### 5. 性能优化
+
+- 避免不必要的节点
+- 使用并行节点提高效率
+- 合理设置超时时间
+
+---
+
+## 更多资源
+
+- [开发者文档](../development/workflow-system.md)
+- [设计文档](../../../plans/langbot-workflow-design.md)
+- [API 文档](../service-api-openapi.json)
@@ -0,0 +1,75 @@
+# HTTP Bot Adapter — Reference Clients
+
+> English | [中文](./README.zh.md)
+
+Minimal, dependency-light clients for the LangBot **HTTP Bot** platform adapter.
+They show the whole loop: signing a request, pushing a message, and receiving
+multi-part replies on a callback endpoint.
+
+Full guide: [docs.langbot.app — HTTP Bot](https://docs.langbot.app/en/usage/platforms/http-bot).
+Machine-readable contract: [`docs/http-bot-openapi.json`](../../docs/http-bot-openapi.json).
+
+## Files
+
+| File | What it is |
+|---|---|
+| `playground.py` | **Interactive browser debug console** — a single-file web app you open in a browser to chat with a running `http_bot` bot and watch signing / 202 / callbacks live. Zero extra deps. |
+| `client.py` | Python client + Flask callback receiver (`pip install flask requests`). |
+| `client.ts` | TypeScript/Node 18+ client + callback receiver, **zero deps** (`npx tsx client.ts`). |
+
+All three implement the identical HMAC-SHA256 scheme
+(`sha256=hex(HMAC(secret, "{timestamp}." + body))`) — verified byte-for-byte
+against the adapter.
+
+## Interactive playground (recommended first run)
+
+A self-contained web console: type a message in your browser, it is signed and
+POSTed to a **running** `http_bot` bot, and the bot's replies stream back into
+the page — with a debug panel showing the signature, the `202` ack, and each
+callback's `sequence` / signature-verification.
+
+```bash
+# From the LangBot repo root, with the backend already running:
+PUBLIC_IP=<your-host-ip> ./.venv/bin/python examples/http-bot/playground.py
+# then open  http://<your-host-ip>:8920/
+```
+
+On startup it reads the LangBot API key + the `http_bot` bot from
+`data/langbot.db`, and configures that bot (inbound/outbound secret +
+`callback_url`) to point back at itself via the LangBot API — the bot reloads
+live, no restart needed. Requirements: an enabled `http_bot` bot bound to a
+working pipeline, and port `8920` reachable from your browser.
+
+Env knobs: `PUBLIC_IP` (default `127.0.0.1`), `PLAYGROUND_PORT` (default `8920`).
+
+## Headless clients
+
+```bash
+# Python — Terminal 1: callback receiver (your callback_url target)
+python client.py serve --port 8900 --secret SHARED_SECRET
+
+# Python — Terminal 2: push a message
+python client.py push --url https://your-langbot/bots/<BOT_UUID> \
+    --secret SHARED_SECRET --session ticket-1 --text "hello"
+
+# blocking sync mode
+python client.py sync  --url https://your-langbot/bots/<BOT_UUID> \
+    --secret SHARED_SECRET --session ticket-1 --text "hello"
+
+# reset a session
+python client.py reset --url https://your-langbot/bots/<BOT_UUID> \
+    --secret SHARED_SECRET --session ticket-1
+```
+
+```bash
+# TypeScript (Node 18+)
+npx tsx client.ts serve 8900 SHARED_SECRET
+npx tsx client.ts push  https://your-langbot/bots/<BOT_UUID> SHARED_SECRET ticket-1 "hello"
+```
+
+When the bot replies, the receiver prints each part with its `sequence` and an
+`[FINAL]` marker on the last one — that's the 1→M multi-reply model in action.
+
+> The bot's `callback_url` must be reachable from LangBot. For local testing,
+> expose your receiver with a tunnel (cloudflared / ngrok) and set that URL in
+> the bot config.
@@ -0,0 +1,71 @@
+# HTTP Bot 适配器 —— 参考客户端
+
+> [English](./README.md) | 中文
+
+面向 LangBot **HTTP Bot** 平台适配器的极简、低依赖客户端示例。
+它们完整展示了整条链路:对请求签名、推送一条消息、在回调端点接收
+1→M 的多段回复。
+
+完整指南:[docs.langbot.app —— HTTP Bot](https://docs.langbot.app/zh/usage/platforms/http-bot)。
+机器可读的接口契约:[`docs/http-bot-openapi.json`](../../docs/http-bot-openapi.json)。
+
+## 文件清单
+
+| 文件 | 是什么 |
+|---|---|
+| `playground.py` | **浏览器交互式调试台** —— 单文件 Web 应用,在浏览器里和一个运行中的 `http_bot` bot 对话,实时观察签名 / 202 / 回调。零额外依赖。 |
+| `client.py` | Python 客户端 + Flask 回调接收端(`pip install flask requests`)。 |
+| `client.ts` | TypeScript/Node 18+ 客户端 + 回调接收端,**零依赖**(`npx tsx client.ts`)。 |
+
+三者实现完全一致的 HMAC-SHA256 签名方案
+(`sha256=hex(HMAC(secret, "{timestamp}." + body))`)—— 已与适配器逐字节比对验证。
+
+## 交互式 playground(推荐先跑这个)
+
+一个自包含的 Web 控制台:在浏览器里输入消息,它会被签名并 POST 给一个
+**运行中**的 `http_bot` bot,bot 的回复会流式回到页面上 —— 调试面板会显示
+签名、`202` 确认,以及每条回调的 `sequence` / 签名验证结果。
+
+```bash
+# 在 LangBot 仓库根目录、后端已启动的前提下:
+PUBLIC_IP=<你的主机IP> ./.venv/bin/python examples/http-bot/playground.py
+# 然后打开  http://<你的主机IP>:8920/
+```
+
+启动时它会从 `data/langbot.db` 读取 LangBot API key 和 `http_bot` bot,
+并通过 LangBot API 把该 bot 配好(入站/出站密钥 + `callback_url`)指回自己 ——
+bot 会热加载,无需重启。前提:有一个已启用、绑定了可用 pipeline 的
+`http_bot` bot,且端口 `8920` 能从你的浏览器访问到。
+
+可调环境变量:`PUBLIC_IP`(默认 `127.0.0.1`)、`PLAYGROUND_PORT`(默认 `8920`)。
+
+## 无头客户端
+
+```bash
+# Python —— 终端 1:回调接收端(你的 callback_url 指向它)
+python client.py serve --port 8900 --secret SHARED_SECRET
+
+# Python —— 终端 2:推送一条消息
+python client.py push --url https://your-langbot/bots/<BOT_UUID> \
+    --secret SHARED_SECRET --session ticket-1 --text "hello"
+
+# 阻塞式同步模式
+python client.py sync  --url https://your-langbot/bots/<BOT_UUID> \
+    --secret SHARED_SECRET --session ticket-1 --text "hello"
+
+# 重置一个会话
+python client.py reset --url https://your-langbot/bots/<BOT_UUID> \
+    --secret SHARED_SECRET --session ticket-1
+```
+
+```bash
+# TypeScript(Node 18+)
+npx tsx client.ts serve 8900 SHARED_SECRET
+npx tsx client.ts push  https://your-langbot/bots/<BOT_UUID> SHARED_SECRET ticket-1 "hello"
+```
+
+当 bot 回复时,接收端会逐条打印,带上各自的 `sequence`,并在最后一条标记
+`[FINAL]` —— 这就是 1→M 多段回复模型的实际效果。
+
+> bot 的 `callback_url` 必须能从 LangBot 访问到。本地测试时,可用隧道
+> (cloudflared / ngrok)把你的接收端暴露出去,并把那个 URL 填进 bot 配置。
@@ -0,0 +1,167 @@
+#!/usr/bin/env python3
+"""LangBot HTTP Bot adapter — reference client (Python).
+
+Two things in one file:
+
+1. ``push()`` / ``push_sync()`` — send a message into a LangBot ``http_bot`` bot.
+2. A tiny Flask callback receiver that verifies signatures and prints replies,
+   so you can watch N->1 aggregation and 1->M multi-reply working live.
+
+Usage
+-----
+    pip install flask requests
+
+    # Terminal 1 — start the callback receiver (this is your callback_url):
+    python client.py serve --port 8900 --secret SHARED_SECRET
+
+    # Terminal 2 — push a message (async; reply lands on the receiver):
+    python client.py push \
+        --url   https://your-langbot/bots/<BOT_UUID> \
+        --secret SHARED_SECRET \
+        --session ticket-10293 \
+        --text "Export keeps failing on the dashboard."
+
+    # Or push and block for the collapsed reply (sync convenience mode):
+    python client.py sync --url https://your-langbot/bots/<BOT_UUID> \
+        --secret SHARED_SECRET --session ticket-10293 --text "hi"
+
+The signing scheme is HMAC-SHA256 over ``"{timestamp}." + raw_body``; see
+``sign()`` below — it is intentionally tiny and easy to port.
+"""
+
+from __future__ import annotations
+
+import argparse
+import hashlib
+import hmac
+import json
+import sys
+import time
+import uuid
+
+HEADER_TIMESTAMP = 'X-LB-Timestamp'
+HEADER_SIGNATURE = 'X-LB-Signature'
+HEADER_IDEMPOTENCY = 'X-LB-Idempotency-Key'
+REPLAY_WINDOW = 300
+
+
+def sign(secret: str, body: bytes, timestamp: int | None = None) -> tuple[str, str]:
+    """Return (timestamp, signature) for *body*."""
+    ts = str(timestamp if timestamp is not None else int(time.time()))
+    mac = hmac.new(secret.encode(), f'{ts}.'.encode() + body, hashlib.sha256)
+    return ts, 'sha256=' + mac.hexdigest()
+
+
+def verify(secret: str, body: bytes, timestamp: str | None, signature: str | None) -> bool:
+    """Verify an inbound signature (used by the callback receiver)."""
+    if not timestamp or not signature:
+        return False
+    try:
+        if abs(int(time.time()) - int(float(timestamp))) > REPLAY_WINDOW:
+            return False
+    except ValueError:
+        return False
+    _, expected = sign(secret, body, int(float(timestamp)))
+    return hmac.compare_digest(expected, signature)
+
+
+def _post(url: str, secret: str, payload: dict, idempotency: bool = True):
+    import requests
+
+    body = json.dumps(payload, ensure_ascii=False).encode()
+    ts, sig = sign(secret, body)
+    headers = {
+        'Content-Type': 'application/json',
+        HEADER_TIMESTAMP: ts,
+        HEADER_SIGNATURE: sig,
+    }
+    if idempotency:
+        headers[HEADER_IDEMPOTENCY] = uuid.uuid4().hex
+    resp = requests.post(url, data=body, headers=headers, timeout=30)
+    print(f'-> {resp.status_code} {resp.text}')
+    return resp
+
+
+def push(url: str, secret: str, session: str, text: str, session_type: str = 'person'):
+    """Fire-and-collect: returns 202 immediately; reply arrives on your callback."""
+    payload = {
+        'session_id': session,
+        'session_type': session_type,
+        'message': [{'type': 'Plain', 'text': text}],
+    }
+    return _post(url.rstrip('/'), secret, payload)
+
+
+def push_sync(url: str, secret: str, session: str, text: str, session_type: str = 'person'):
+    """Blocking convenience: POST to /sync and get the collapsed reply back."""
+    payload = {
+        'session_id': session,
+        'session_type': session_type,
+        'message': [{'type': 'Plain', 'text': text}],
+    }
+    resp = _post(url.rstrip('/') + '/sync', secret, payload, idempotency=False)
+    return resp
+
+
+def reset(url: str, secret: str, session: str, session_type: str = 'person'):
+    """Reset a session's conversation (next message starts fresh)."""
+    payload = {'session_id': session, 'session_type': session_type}
+    return _post(url.rstrip('/') + '/reset', secret, payload, idempotency=False)
+
+
+def serve(port: int, secret: str):
+    """Run a callback receiver that verifies signatures and prints replies."""
+    from flask import Flask, request
+
+    app = Flask(__name__)
+
+    @app.route('/', methods=['POST'])
+    def recv():
+        raw = request.get_data()
+        ok = verify(secret, raw, request.headers.get(HEADER_TIMESTAMP), request.headers.get(HEADER_SIGNATURE))
+        if not ok:
+            print('!! signature verification FAILED — rejecting')
+            return {'error': 'bad signature'}, 401
+        data = json.loads(raw)
+        text_parts = [c.get('text', '') for c in data.get('message', []) if c.get('type') == 'Plain']
+        marker = 'FINAL' if data.get('is_final') else 'part '
+        print(
+            f'[{marker}] session={data["session_id"]} seq={data["sequence"]} '
+            f'reply_to={data.get("reply_to")}: {" ".join(text_parts)}'
+        )
+        return {'ok': True}
+
+    print(f'callback receiver listening on http://0.0.0.0:{port}/  (Ctrl-C to stop)')
+    app.run(host='0.0.0.0', port=port)
+
+
+def main(argv=None):
+    p = argparse.ArgumentParser(description='LangBot HTTP Bot reference client')
+    sub = p.add_subparsers(dest='cmd', required=True)
+
+    sp = sub.add_parser('serve', help='run the callback receiver')
+    sp.add_argument('--port', type=int, default=8900)
+    sp.add_argument('--secret', required=True)
+
+    for name in ('push', 'sync', 'reset'):
+        c = sub.add_parser(name)
+        c.add_argument('--url', required=True, help='https://host/bots/<BOT_UUID>')
+        c.add_argument('--secret', required=True)
+        c.add_argument('--session', required=True)
+        c.add_argument('--session-type', default='person', choices=['person', 'group'])
+        if name != 'reset':
+            c.add_argument('--text', required=True)
+
+    args = p.parse_args(argv)
+    if args.cmd == 'serve':
+        serve(args.port, args.secret)
+    elif args.cmd == 'push':
+        push(args.url, args.secret, args.session, args.text, args.session_type)
+    elif args.cmd == 'sync':
+        push_sync(args.url, args.secret, args.session, args.text, args.session_type)
+    elif args.cmd == 'reset':
+        reset(args.url, args.secret, args.session, args.session_type)
+
+
+if __name__ == '__main__':
+    sys.exit(main())
@@ -0,0 +1,123 @@
+/**
+ * LangBot HTTP Bot adapter — reference client (TypeScript / Node 18+).
+ *
+ * Zero runtime dependencies (uses global `fetch`, `crypto`, and `http`).
+ *
+ *   - `push()`      : fire-and-collect; reply lands on your callback URL.
+ *   - `pushSync()`  : POST /sync and await the collapsed reply.
+ *   - `reset()`     : reset a session's conversation.
+ *   - `startReceiver()` : a callback server that verifies signatures and logs
+ *                         replies, so you can watch N->1 and 1->M live.
+ *
+ * Run the demos:
+ *   npx tsx client.ts serve   8900 SHARED_SECRET
+ *   npx tsx client.ts push    https://host/bots/<UUID> SHARED_SECRET ticket-1 "hello"
+ *   npx tsx client.ts sync    https://host/bots/<UUID> SHARED_SECRET ticket-1 "hello"
+ *   npx tsx client.ts reset   https://host/bots/<UUID> SHARED_SECRET ticket-1
+ */
+
+import { createHmac, randomUUID, timingSafeEqual } from 'node:crypto';
+import { createServer } from 'node:http';
+
+const HEADER_TIMESTAMP = 'X-LB-Timestamp';
+const HEADER_SIGNATURE = 'X-LB-Signature';
+const HEADER_IDEMPOTENCY = 'X-LB-Idempotency-Key';
+const REPLAY_WINDOW = 300;
+
+/** Compute the `sha256=<hex>` signature over `"{ts}." + body`. */
+export function sign(secret: string, body: Buffer | string, timestamp?: number): [string, string] {
+  const ts = String(timestamp ?? Math.floor(Date.now() / 1000));
+  const buf = typeof body === 'string' ? Buffer.from(body) : body;
+  const mac = createHmac('sha256', secret).update(Buffer.concat([Buffer.from(`${ts}.`), buf])).digest('hex');
+  return [ts, `sha256=${mac}`];
+}
+
+/** Verify an inbound signature (used by the callback receiver). */
+export function verify(secret: string, body: Buffer, timestamp?: string, signature?: string): boolean {
+  if (!timestamp || !signature) return false;
+  if (Math.abs(Math.floor(Date.now() / 1000) - Number(timestamp)) > REPLAY_WINDOW) return false;
+  const [, expected] = sign(secret, body, Number(timestamp));
+  const a = Buffer.from(expected);
+  const b = Buffer.from(signature);
+  return a.length === b.length && timingSafeEqual(a, b);
+}
+
+interface Segment { type: string; text?: string; url?: string; [k: string]: unknown }
+
+async function post(url: string, secret: string, payload: object, idempotency = true) {
+  const body = Buffer.from(JSON.stringify(payload));
+  const [ts, sig] = sign(secret, body);
+  const headers: Record<string, string> = {
+    'Content-Type': 'application/json',
+    [HEADER_TIMESTAMP]: ts,
+    [HEADER_SIGNATURE]: sig,
+  };
+  if (idempotency) headers[HEADER_IDEMPOTENCY] = randomUUID();
+  const resp = await fetch(url, { method: 'POST', headers, body });
+  const text = await resp.text();
+  console.log(`-> ${resp.status} ${text}`);
+  return { status: resp.status, text };
+}
+
+/** Fire-and-collect: 202 now, reply later on your callback URL. */
+export function push(url: string, secret: string, session: string, text: string, sessionType = 'person') {
+  return post(url.replace(/\/$/, ''), secret, {
+    session_id: session,
+    session_type: sessionType,
+    message: [{ type: 'Plain', text }] as Segment[],
+  });
+}
+
+/** Blocking convenience: POST /sync, get the collapsed reply. */
+export function pushSync(url: string, secret: string, session: string, text: string, sessionType = 'person') {
+  return post(`${url.replace(/\/$/, '')}/sync`, secret, {
+    session_id: session,
+    session_type: sessionType,
+    message: [{ type: 'Plain', text }] as Segment[],
+  }, false);
+}
+
+/** Reset a session's conversation. */
+export function reset(url: string, secret: string, session: string, sessionType = 'person') {
+  return post(`${url.replace(/\/$/, '')}/reset`, secret, { session_id: session, session_type: sessionType }, false);
+}
+
+/** Run a callback receiver that verifies signatures and prints replies. */
+export function startReceiver(port: number, secret: string) {
+  const server = createServer((req, res) => {
+    if (req.method !== 'POST') { res.writeHead(405).end(); return; }
+    const chunks: Buffer[] = [];
+    req.on('data', (c) => chunks.push(c));
+    req.on('end', () => {
+      const raw = Buffer.concat(chunks);
+      const ok = verify(secret, raw, req.headers[HEADER_TIMESTAMP.toLowerCase()] as string,
+        req.headers[HEADER_SIGNATURE.toLowerCase()] as string);
+      if (!ok) {
+        console.log('!! signature verification FAILED — rejecting');
+        res.writeHead(401, { 'Content-Type': 'application/json' }).end(JSON.stringify({ error: 'bad signature' }));
+        return;
+      }
+      const data = JSON.parse(raw.toString());
+      const parts = (data.message as Segment[]).filter((c) => c.type === 'Plain').map((c) => c.text).join(' ');
+      const marker = data.is_final ? 'FINAL' : 'part ';
+      console.log(`[${marker}] session=${data.session_id} seq=${data.sequence} reply_to=${data.reply_to}: ${parts}`);
+      res.writeHead(200, { 'Content-Type': 'application/json' }).end(JSON.stringify({ ok: true }));
+    });
+  });
+  server.listen(port, () => console.log(`callback receiver listening on http://0.0.0.0:${port}/  (Ctrl-C to stop)`));
+}
+
+// --- CLI ---
+const [cmd, ...rest] = process.argv.slice(2);
+if (cmd === 'serve') {
+  startReceiver(Number(rest[0] ?? 8900), rest[1] ?? 'SHARED_SECRET');
+} else if (cmd === 'push') {
+  push(rest[0], rest[1], rest[2], rest[3]);
+} else if (cmd === 'sync') {
+  pushSync(rest[0], rest[1], rest[2], rest[3]);
+} else if (cmd === 'reset') {
+  reset(rest[0], rest[1], rest[2]);
+} else if (cmd) {
+  console.error(`unknown command: ${cmd}`);
+  process.exit(1);
+}
@@ -0,0 +1,349 @@
+#!/usr/bin/env python3
+"""LangBot HTTP Bot — interactive playground (public, browser-based).
+
+This is a REAL end-to-end demo against the RUNNING LangBot instance on this
+host. It is NOT a mock and NOT an in-process import: every message you type in
+the browser is signed and POSTed to the live `http_bot` bot at
+http://127.0.0.1:5300/bots/<uuid>, and the bot's replies come back to this
+server's /callback endpoint over real HTTP, then stream to your browser via SSE.
+
+What it does on startup:
+  1. Reads the LangBot API key + the http_bot bot from data/langbot.db.
+  2. Configures the bot via the LangBot API (PUT /api/v1/platform/bots/<uuid>):
+     sets inbound_secret + outbound_secret + callback_url to point back here.
+     (LangBot reloads the bot live — no server restart needed.)
+  3. Serves a chat page on 0.0.0.0:<PORT> so you can open it from the internet.
+
+Run:  ./.venv/bin/python examples/http-bot/playground.py
+Then open:  http://<this-host-public-ip>:<PORT>/
+"""
+
+from __future__ import annotations
+
+import asyncio
+import json
+import os
+import sqlite3
+import sys
+
+REPO = os.path.abspath(os.path.join(os.path.dirname(__file__), '..', '..'))
+sys.path.insert(0, os.path.join(REPO, 'src'))
+
+from aiohttp import web  # noqa: E402
+import aiohttp  # noqa: E402
+
+from langbot.pkg.platform.sources import http_bot_signing as sg  # noqa: E402
+
+# ---- config -----------------------------------------------------------------
+LANGBOT_BASE = 'http://127.0.0.1:5300'
+DB_PATH = os.path.join(REPO, 'data', 'langbot.db')
+PUBLIC_IP = os.environ.get('PUBLIC_IP', '127.0.0.1')
+PORT = int(os.environ.get('PLAYGROUND_PORT', '8920'))
+SECRET = 'playground-shared-secret'
+
+# SSE subscribers: list of asyncio.Queue
+subscribers: list[asyncio.Queue] = []
+
+
+def db_lookup() -> tuple[str, str]:
+    """Return (api_key, http_bot_uuid) from the LangBot DB."""
+    db = sqlite3.connect(DB_PATH)
+    db.row_factory = sqlite3.Row
+    api_key = db.execute('SELECT key FROM api_keys LIMIT 1').fetchone()['key']
+    bot = db.execute("SELECT uuid FROM bots WHERE adapter='http_bot' LIMIT 1").fetchone()
+    if not bot:
+        raise SystemExit('No http_bot bot found. Create one in the WebUI first.')
+    return api_key, bot['uuid']
+
+
+async def configure_bot(api_key: str, bot_uuid: str, callback_url: str):
+    """Point the live bot at this playground via the LangBot API.
+
+    update_bot() runs a raw SQL UPDATE with whatever keys we send, so we send a
+    MINIMAL payload: only adapter_config (built from scratch, not read back —
+    the GET masks secrets). LangBot reloads + reruns the bot live.
+    """
+    cfg = {
+        'inbound_secret': SECRET,
+        'outbound_secret': SECRET,
+        'callback_url': callback_url,
+        'signature_required': True,
+        'default_session_type': 'person',
+        'callback_timeout': 15,
+        'callback_max_retries': 3,
+    }
+    async with aiohttp.ClientSession() as s:
+        async with s.put(
+            f'{LANGBOT_BASE}/api/v1/platform/bots/{bot_uuid}',
+            headers={'Authorization': f'Bearer {api_key}', 'Content-Type': 'application/json'},
+            json={'adapter_config': cfg},
+        ) as r:
+            txt = await r.text()
+            print(f'[configure] PUT adapter_config -> {r.status} {txt[:200]}')
+            return r.status < 400
+
+
+async def broadcast(event: dict):
+    for q in list(subscribers):
+        try:
+            q.put_nowait(event)
+        except Exception:
+            pass
+
+
+# ---- HTTP handlers ----------------------------------------------------------
+async def index(request: web.Request):
+    return web.Response(text=PAGE, content_type='text/html')
+
+
+async def send(request: web.Request):
+    """Browser -> here -> signed POST -> live LangBot bot."""
+    body_in = await request.json()
+    session_id = body_in.get('session_id') or 'playground-1'
+    text = body_in.get('text', '')
+    bot_uuid = request.app['bot_uuid']
+
+    payload = {
+        'session_id': session_id,
+        'sender': {'id': 'browser-user', 'name': 'You'},
+        'message': [{'type': 'Plain', 'text': text}],
+    }
+    raw = json.dumps(payload, ensure_ascii=False).encode()
+    ts, sig = sg.sign(SECRET, raw)
+    url = f'{LANGBOT_BASE}/bots/{bot_uuid}'
+
+    # echo what we send to the browser timeline
+    await broadcast(
+        {'dir': 'out', 'kind': 'request', 'session_id': session_id, 'text': text, 'url': url, 'sig': sig[:24] + '…'}
+    )
+
+    async with aiohttp.ClientSession() as s:
+        async with s.post(
+            url,
+            data=raw,
+            headers={
+                'Content-Type': 'application/json',
+                sg.HEADER_TIMESTAMP: ts,
+                sg.HEADER_SIGNATURE: sig,
+            },
+        ) as r:
+            status = r.status
+            try:
+                jr = await r.json()
+            except Exception:
+                jr = {'raw': await r.text()}
+    await broadcast({'dir': 'in', 'kind': 'ack', 'status': status, 'data': jr})
+    return web.json_response({'status': status, 'data': jr})
+
+
+async def callback(request: web.Request):
+    """Live LangBot bot -> here. Verify signature, stream to browser."""
+    raw = await request.read()
+    ok, why = sg.verify(SECRET, raw, request.headers.get(sg.HEADER_TIMESTAMP), request.headers.get(sg.HEADER_SIGNATURE))
+    data = json.loads(raw)
+    text = ' '.join(c.get('text', '') for c in data.get('message', []) if c.get('type') == 'Plain')
+    await broadcast(
+        {
+            'dir': 'in',
+            'kind': 'reply',
+            'session_id': data.get('session_id'),
+            'sequence': data.get('sequence'),
+            'is_final': data.get('is_final'),
+            'sig_ok': ok,
+            'sig_why': why,
+            'text': text,
+        }
+    )
+    return web.json_response({'ok': True})
+
+
+async def events(request: web.Request):
+    """SSE stream to the browser."""
+    resp = web.StreamResponse(
+        headers={
+            'Content-Type': 'text/event-stream',
+            'Cache-Control': 'no-cache',
+            'Connection': 'keep-alive',
+            'Access-Control-Allow-Origin': '*',
+        }
+    )
+    await resp.prepare(request)
+    q: asyncio.Queue = asyncio.Queue()
+    subscribers.append(q)
+    try:
+        await resp.write(b': connected\n\n')
+        while True:
+            try:
+                ev = await asyncio.wait_for(q.get(), timeout=15)
+                await resp.write(f'data: {json.dumps(ev, ensure_ascii=False)}\n\n'.encode())
+            except asyncio.TimeoutError:
+                await resp.write(b': ping\n\n')
+    except (asyncio.CancelledError, ConnectionResetError):
+        pass
+    finally:
+        if q in subscribers:
+            subscribers.remove(q)
+    return resp
+
+
+PAGE = r"""<!doctype html>
+<html lang="zh"><head><meta charset="utf-8"/>
+<meta name="viewport" content="width=device-width,initial-scale=1"/>
+<title>LangBot HTTP Bot · 调试台</title>
+<style>
+  :root{
+    --bg:#f7f8fa; --panel:#ffffff; --line:#e8eaed; --ink:#1f2329; --mut:#8a909a;
+    --brand:#2563eb; --brand-soft:#eef3ff; --ok:#16a34a; --bad:#dc2626; --code:#f3f4f6;
+  }
+  *{box-sizing:border-box}
+  html,body{height:100%}
+  body{margin:0;background:var(--bg);color:var(--ink);
+    font:14px/1.6 -apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,"PingFang SC","Microsoft YaHei",sans-serif}
+  .top{height:52px;background:var(--panel);border-bottom:1px solid var(--line);
+    display:flex;align-items:center;gap:10px;padding:0 18px}
+  .logo{width:26px;height:26px;border-radius:7px;background:var(--brand);display:grid;place-items:center;color:#fff;font-weight:700;font-size:14px}
+  .top b{font-size:15px} .top .ver{font-size:12px;color:var(--mut)}
+  .dot{width:8px;height:8px;border-radius:50%;background:#cbd2dc;display:inline-block;margin-right:5px;vertical-align:middle}
+  .dot.on{background:var(--ok)} .dot.off{background:var(--bad)}
+  .conn{margin-left:auto;font-size:12px;color:var(--mut)}
+  .wrap{max-width:1080px;margin:0 auto;padding:18px;display:grid;grid-template-columns:1fr 360px;gap:16px}
+  @media(max-width:880px){.wrap{grid-template-columns:1fr}}
+  .card{background:var(--panel);border:1px solid var(--line);border-radius:12px;display:flex;flex-direction:column;min-height:0}
+  .card h3{margin:0;padding:12px 16px;font-size:13px;font-weight:600;color:#4b5563;border-bottom:1px solid var(--line);display:flex;align-items:center;gap:8px}
+  .chat{height:62vh}
+  .msgs{flex:1;overflow:auto;padding:16px;display:flex;flex-direction:column;gap:12px}
+  .row{display:flex;flex-direction:column;gap:4px;max-width:82%}
+  .row.me{align-self:flex-end;align-items:flex-end}
+  .row.bot{align-self:flex-start}
+  .bub{padding:9px 13px;border-radius:12px;white-space:pre-wrap;word-break:break-word}
+  .me .bub{background:var(--brand);color:#fff;border-bottom-right-radius:3px}
+  .bot .bub{background:#f1f3f6;color:var(--ink);border-bottom-left-radius:3px}
+  .meta{font-size:11px;color:var(--mut)}
+  .meta .ok{color:var(--ok)} .meta .bad{color:var(--bad)}
+  .sys{align-self:center;font-size:12px;color:var(--mut);background:#f1f3f6;border-radius:8px;padding:4px 12px}
+  .bar{display:flex;gap:8px;padding:12px;border-top:1px solid var(--line)}
+  .bar input{flex:1;border:1px solid var(--line);border-radius:9px;padding:10px 12px;font-size:14px;outline:none}
+  .bar input:focus{border-color:var(--brand);box-shadow:0 0 0 3px var(--brand-soft)}
+  .bar button{background:var(--brand);color:#fff;border:0;border-radius:9px;padding:0 18px;font-size:14px;font-weight:500;cursor:pointer}
+  .bar button:disabled{opacity:.5;cursor:default}
+  .side{height:62vh}
+  .kv{padding:12px 16px;border-bottom:1px solid var(--line);font-size:12px}
+  .kv .k{color:var(--mut)} .kv .v{color:var(--ink);word-break:break-all}
+  .kv code{background:var(--code);border-radius:5px;padding:1px 5px;font-size:11px}
+  .sessrow{display:flex;align-items:center;gap:8px;padding:10px 16px;border-bottom:1px solid var(--line);font-size:12px}
+  .sessrow input{flex:1;border:1px solid var(--line);border-radius:7px;padding:5px 8px;font-size:12px}
+  .sessrow button{border:1px solid var(--line);background:#fff;border-radius:7px;padding:5px 9px;font-size:12px;cursor:pointer;color:#4b5563}
+  .trace{flex:1;overflow:auto;padding:10px 12px;font:11px/1.55 ui-monospace,SFMono-Regular,Menlo,monospace}
+  .ev{padding:6px 8px;border-radius:7px;margin-bottom:6px;border:1px solid var(--line)}
+  .ev .t{font-weight:600;font-size:10px;letter-spacing:.3px;text-transform:uppercase}
+  .ev.out{background:#f5f8ff;border-color:#dbe6ff}.ev.out .t{color:var(--brand)}
+  .ev.ack{background:#f4f6f8}.ev.ack .t{color:#6b7280}
+  .ev.reply{background:#f1faf3;border-color:#cdeed6}.ev.reply .t{color:var(--ok)}
+  .ev pre{margin:3px 0 0;white-space:pre-wrap;word-break:break-all;color:#374151}
+</style></head>
+<body>
+<div class="top">
+  <div class="logo">L</div>
+  <b>HTTP Bot 调试台</b><span class="ver">examples/http-bot</span>
+  <span class="conn"><span class="dot off" id="cdot"></span><span id="conn">连接中…</span></span>
+</div>
+<div class="wrap">
+  <!-- chat -->
+  <div class="card chat">
+    <h3>对话 · 真实发往运行中的 http_bot</h3>
+    <div class="msgs" id="msgs"></div>
+    <div class="bar">
+      <input id="msg" placeholder="输入消息,回车发送…" autofocus/>
+      <button id="send">发送</button>
+    </div>
+  </div>
+  <!-- debug -->
+  <div class="card side">
+    <h3>调试信息</h3>
+    <div class="kv"><span class="k">入站地址</span><br><span class="v"><code id="endpoint">/bots/&lt;uuid&gt;</code></span></div>
+    <div class="kv"><span class="k">签名</span> <span class="v">HMAC-SHA256 · <code>X-LB-Signature</code></span></div>
+    <div class="sessrow">
+      <span class="k">会话</span>
+      <input id="sid" value="playground-1"/>
+      <button id="reset">新会话</button>
+    </div>
+    <div class="trace" id="trace"></div>
+  </div>
+</div>
+<script>
+const $=s=>document.querySelector(s);
+const msgs=$('#msgs'),trace=$('#trace'),inp=$('#msg'),btn=$('#send'),
+      conn=$('#conn'),cdot=$('#cdot'),sidIn=$('#sid');
+function el(c){const d=document.createElement('div');d.className=c;return d}
+function atBottom(n){n.scrollTop=n.scrollHeight}
+function bubble(side,text,metaHtml){
+  const r=el('row '+side),b=el('bub');b.textContent=text;r.appendChild(b);
+  if(metaHtml){const m=el('meta');m.innerHTML=metaHtml;r.appendChild(m)}
+  msgs.appendChild(r);atBottom(msgs)}
+function sys(t){const d=el('sys');d.textContent=t;msgs.appendChild(d);atBottom(msgs)}
+function logEv(kind,title,obj){
+  const e=el('ev '+kind),t=el('t');t.textContent=title;e.appendChild(t);
+  if(obj!==undefined){const p=document.createElement('pre');
+    p.textContent=typeof obj==='string'?obj:JSON.stringify(obj,null,2);e.appendChild(p)}
+  trace.appendChild(e);atBottom(trace)}
+
+const es=new EventSource('/events');
+es.onopen=()=>{conn.textContent='SSE 已连接';cdot.className='dot on'};
+es.onerror=()=>{conn.textContent='SSE 断开,重连…';cdot.className='dot off'};
+es.onmessage=e=>{const ev=JSON.parse(e.data);
+  if(ev.kind==='request'){
+    if(ev.endpoint)$('#endpoint').textContent=ev.url||ev.endpoint;
+    logEv('out','出站 · 已签名 POST',{url:ev.url,session_id:ev.session_id,'X-LB-Signature':ev.sig});
+  }else if(ev.kind==='ack'){
+    const id=ev.data&&ev.data.data&&ev.data.data.accepted_message_id;
+    sys(`LangBot 已接收 · HTTP ${ev.status}`);
+    logEv('ack','入站确认 202',{status:ev.status,accepted_message_id:id||'-'});
+  }else if(ev.kind==='reply'){
+    const sig=ev.sig_ok?'<span class=ok>验签通过</span>':'<span class=bad>验签失败</span>';
+    bubble('bot',ev.text,`seq=${ev.sequence} · ${ev.is_final?'<b>FINAL</b>':'中间段'} · ${sig}`);
+    logEv('reply',`回调 · seq ${ev.sequence}${ev.is_final?' · FINAL':''}`,
+      {session_id:ev.session_id,sequence:ev.sequence,is_final:ev.is_final,sig_ok:ev.sig_ok,text:ev.text});
+  }};
+
+async function send(){
+  const t=inp.value.trim();if(!t)return;inp.value='';btn.disabled=true;
+  bubble('me',t,'已签名 → POST /bots/&lt;uuid&gt;');
+  try{await fetch('/send',{method:'POST',headers:{'Content-Type':'application/json'},
+    body:JSON.stringify({session_id:sidIn.value.trim()||'playground-1',text:t})});}
+  catch(e){sys('发送失败:'+e)}
+  btn.disabled=false;inp.focus();}
+btn.onclick=send;inp.addEventListener('keydown',e=>{if(e.key==='Enter')send()});
+$('#reset').onclick=()=>{sidIn.value='playground-'+Math.random().toString(36).slice(2,7);
+  sys('已切换到新会话 '+sidIn.value);};
+sys('调试台就绪 · 每条消息都会真实发往运行中的 http_bot,右侧可观察签名 / 202 / 回调全过程。');
+</script>
+</body></html>"""
+
+
+async def main():
+    api_key, bot_uuid = db_lookup()
+    callback_url = f'http://{PUBLIC_IP}:{PORT}/callback'
+    print(f'[init] http_bot uuid = {bot_uuid}')
+    print(f'[init] callback_url  = {callback_url}')
+    ok = await configure_bot(api_key, bot_uuid, callback_url)
+    if not ok:
+        print('[warn] bot config update failed; check the API key / payload shape')
+
+    app = web.Application()
+    app['bot_uuid'] = bot_uuid
+    app.router.add_get('/', index)
+    app.router.add_post('/send', send)
+    app.router.add_post('/callback', callback)
+    app.router.add_get('/events', events)
+
+    runner = web.AppRunner(app)
+    await runner.setup()
+    site = web.TCPSite(runner, '0.0.0.0', PORT)
+    await site.start()
+    print(f'\n  ▶ 打开:  http://{PUBLIC_IP}:{PORT}/\n')
+    while True:
+        await asyncio.sleep(3600)
+
+
+if __name__ == '__main__':
+    asyncio.run(main())
@@ -0,0 +1,48 @@
+# Page Bot Adapter — Embed Demo
+
+> English | [中文](./README.zh.md)
+
+A single self-contained HTML page that demos the LangBot **Page Bot**
+(`web_page_bot`) embeddable chat widget — the one you drop onto any website with
+a single `<script>` tag.
+
+Full guide: [docs.langbot.app — Page Bot](https://docs.langbot.app/en/usage/platforms/webpage).
+
+## Files
+
+| File | What it is |
+|---|---|
+| `index.html` | **Browser demo** — open it, point it at a running LangBot instance + a Page Bot you created, and it loads the live embed widget so you can chat with the bot exactly as a site visitor would. Zero deps, no build step. |
+
+## How to use
+
+1. In the LangBot WebUI, create a bot with the **Page Bot** (`页面机器人`)
+   adapter and bind it to a working pipeline. Copy its **bot UUID** from the
+   generated embed code.
+2. Open `index.html` in a browser. Any of these work:
+   - double-click the file, or
+   - serve the folder: `python3 -m http.server 8930` then open
+     `http://localhost:8930/examples/web-page-bot/`.
+3. Fill in:
+   - **LangBot base URL** — where your instance is reachable from the browser
+     (e.g. `http://localhost:5300`, or your public address).
+   - **Page Bot UUID** — from step 1.
+   - **Widget title** — optional, sets the `data-title` attribute.
+4. Click **Load widget**. A floating chat bubble appears in the bottom-right
+   corner — click it and chat.
+
+The page also renders the exact `<script>` snippet you'd paste into your own
+site (before `</body>`), and updates it live as you edit the fields.
+
+## What it demonstrates
+
+- The embed contract: `<script data-title="…" src="<base>/api/v1/embed/<uuid>/widget.js"></script>`.
+- `widget.js` is served by LangBot pre-configured for that bot UUID — title,
+  bubble icon, language and optional Cloudflare Turnstile protection all come
+  from the bot's config, no page changes needed.
+- Messages travel over a WebSocket to the bot's bound pipeline; replies stream
+  back into the bubble.
+
+> The widget loads `widget.js` from your LangBot instance, so the **base URL
+> must be reachable from the browser** you open this page in. If LangBot runs on
+> a server, use its public address instead of `localhost`.
@@ -0,0 +1,44 @@
+# 页面机器人适配器 —— 嵌入演示
+
+> [English](./README.md) | 中文
+
+一个自包含的单文件 HTML 页面，用于演示 LangBot **页面机器人**
+(`web_page_bot`) 的可嵌入聊天组件 —— 也就是你用一行 `<script>` 标签就能放到任意
+网站上的那个组件。
+
+完整指南：[docs.langbot.app —— 页面机器人](https://docs.langbot.app/zh/usage/platforms/webpage)。
+
+## 文件清单
+
+| 文件 | 是什么 |
+|---|---|
+| `index.html` | **浏览器演示页** —— 打开它，填上一个运行中的 LangBot 实例地址 + 你创建的页面机器人，它就会加载真实的嵌入组件，让你像网站访客一样和机器人对话。零依赖，无需构建。 |
+
+## 使用方法
+
+1. 在 LangBot WebUI 中，用 **页面机器人**（`web_page_bot`）适配器创建一个机器人，
+   并绑定一个可用的流水线。从生成的嵌入代码里复制它的 **机器人 UUID**。
+2. 在浏览器中打开 `index.html`，以下任一方式皆可：
+   - 直接双击该文件；或
+   - 起一个静态服务：`python3 -m http.server 8930`，然后打开
+     `http://localhost:8930/examples/web-page-bot/`。
+3. 填写：
+   - **LangBot base URL** —— 你的实例在该浏览器中可访问的地址
+     （例如 `http://localhost:5300`，或你的公网地址）。
+   - **页面机器人 UUID** —— 第 1 步里复制的。
+   - **组件标题** —— 可选，对应 `data-title` 属性。
+4. 点击 **Load widget**。页面右下角会出现一个浮动聊天气泡 —— 点开即可对话。
+
+页面还会实时渲染出你需要粘贴到自己网站（放在 `</body>` 前）的那段 `<script>`
+代码，并随着你编辑输入框同步更新。
+
+## 它演示了什么
+
+- 嵌入契约：`<script data-title="…" src="<base>/api/v1/embed/<uuid>/widget.js"></script>`。
+- `widget.js` 由 LangBot 针对该机器人 UUID 预配置后下发 —— 标题、气泡图标、语言
+  以及可选的 Cloudflare Turnstile 防护，全部来自机器人配置，无需改动页面。
+- 消息通过 WebSocket 发往机器人绑定的流水线，回复流式回到气泡中。
+
+> 组件会从你的 LangBot 实例加载 `widget.js`，因此 **base URL 必须能从你打开本页
+> 的浏览器访问到**。如果 LangBot 部署在服务器上，请用它的公网地址而非
+> `localhost`。
@@ -0,0 +1,205 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="utf-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1" />
+<title>LangBot Page Bot · Embed Demo</title>
+<style>
+  :root {
+    --bg: #f7f8fa; --panel: #ffffff; --line: #e8eaed; --ink: #1f2329;
+    --mut: #8a909a; --brand: #2563eb; --brand-soft: #eef3ff;
+    --ok: #16a34a; --bad: #dc2626; --code: #f3f4f6;
+  }
+  * { box-sizing: border-box; }
+  html, body { height: 100%; }
+  body {
+    margin: 0; background: var(--bg); color: var(--ink);
+    font: 14px/1.6 -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto,
+      "PingFang SC", "Microsoft YaHei", sans-serif;
+  }
+  .top {
+    height: 52px; background: var(--panel); border-bottom: 1px solid var(--line);
+    display: flex; align-items: center; gap: 10px; padding: 0 18px;
+  }
+  .logo {
+    width: 26px; height: 26px; border-radius: 7px; background: var(--brand);
+    display: grid; place-items: center; color: #fff; font-weight: 700; font-size: 14px;
+  }
+  .top b { font-size: 15px; }
+  .top .ver { font-size: 12px; color: var(--mut); }
+  .wrap { max-width: 760px; margin: 0 auto; padding: 28px 18px 80px; }
+  .hero h1 { margin: 8px 0 6px; font-size: 22px; }
+  .hero p { margin: 0 0 4px; color: var(--mut); }
+  .card {
+    background: var(--panel); border: 1px solid var(--line); border-radius: 12px;
+    padding: 20px; margin-top: 20px;
+  }
+  .card h3 {
+    margin: 0 0 14px; font-size: 14px; font-weight: 600; color: #4b5563;
+    display: flex; align-items: center; gap: 8px;
+  }
+  .card h3 .num {
+    width: 20px; height: 20px; border-radius: 50%; background: var(--brand-soft);
+    color: var(--brand); display: grid; place-items: center; font-size: 12px; font-weight: 700;
+  }
+  .field { margin-bottom: 14px; }
+  .field:last-child { margin-bottom: 0; }
+  .field label { display: block; font-size: 12px; color: var(--mut); margin-bottom: 5px; }
+  .field input {
+    width: 100%; border: 1px solid var(--line); border-radius: 9px;
+    padding: 10px 12px; font-size: 14px; outline: none; font-family: inherit;
+  }
+  .field input:focus { border-color: var(--brand); box-shadow: 0 0 0 3px var(--brand-soft); }
+  .hint { font-size: 12px; color: var(--mut); margin-top: 5px; }
+  .hint code { background: var(--code); border-radius: 5px; padding: 1px 5px; font-size: 11px; }
+  .actions { display: flex; gap: 10px; margin-top: 18px; align-items: center; }
+  button {
+    border: 0; border-radius: 9px; padding: 10px 18px; font-size: 14px;
+    font-weight: 500; cursor: pointer; font-family: inherit;
+  }
+  .btn-primary { background: var(--brand); color: #fff; }
+  .btn-primary:disabled { opacity: .5; cursor: default; }
+  .btn-ghost { background: #fff; border: 1px solid var(--line); color: #4b5563; }
+  .status { font-size: 13px; color: var(--mut); }
+  .status .ok { color: var(--ok); }
+  .status .bad { color: var(--bad); }
+  pre {
+    background: #0f172a; color: #e2e8f0; border-radius: 10px; padding: 14px 16px;
+    overflow: auto; font: 12px/1.6 ui-monospace, SFMono-Regular, Menlo, monospace;
+    margin: 0;
+  }
+  .snippet-row { position: relative; }
+  .snippet-row .copy {
+    position: absolute; top: 10px; right: 10px; background: rgba(255,255,255,.12);
+    color: #fff; border: 0; border-radius: 7px; padding: 5px 10px; font-size: 12px; cursor: pointer;
+  }
+  ul.steps { margin: 0; padding-left: 18px; color: #4b5563; }
+  ul.steps li { margin-bottom: 6px; }
+</style>
+</head>
+<body>
+<div class="top">
+  <div class="logo">L</div>
+  <b>Page Bot · Embed Demo</b>
+  <span class="ver">examples/web-page-bot</span>
+</div>
+
+<div class="wrap">
+  <div class="hero">
+    <h1>Try the LangBot Page Bot widget</h1>
+    <p>Point this page at a running LangBot instance and a <strong>Page Bot</strong> you created,</p>
+    <p>then load the live embed widget below to chat with it — exactly as your site visitors would.</p>
+  </div>
+
+  <div class="card">
+    <h3><span class="num">1</span> Connect your Page Bot</h3>
+    <div class="field">
+      <label for="base">LangBot base URL</label>
+      <input id="base" placeholder="http://localhost:5300" value="http://localhost:5300" />
+      <div class="hint">The address where your LangBot instance is reachable from this browser. No trailing slash.</div>
+    </div>
+    <div class="field">
+      <label for="uuid">Page Bot UUID</label>
+      <input id="uuid" placeholder="xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" />
+      <div class="hint">Create a bot with the <code>Page Bot</code> adapter in the WebUI, then copy its UUID from the embed code.</div>
+    </div>
+    <div class="field">
+      <label for="title">Widget title (optional)</label>
+      <input id="title" placeholder="LangBot" value="LangBot" />
+    </div>
+    <div class="actions">
+      <button id="load" class="btn-primary">Load widget</button>
+      <button id="unload" class="btn-ghost">Remove widget</button>
+      <span class="status" id="status">Not loaded.</span>
+    </div>
+  </div>
+
+  <div class="card">
+    <h3><span class="num">2</span> The embed snippet</h3>
+    <p style="margin:0 0 12px;color:var(--mut)">This is exactly what you paste into your own site (before <code>&lt;/body&gt;</code>). It updates as you edit the fields above.</p>
+    <div class="snippet-row">
+      <button class="copy" id="copy">Copy</button>
+      <pre id="snippet">&lt;script data-title="LangBot" src="http://localhost:5300/api/v1/embed/&lt;bot-uuid&gt;/widget.js"&gt;&lt;/script&gt;</pre>
+    </div>
+  </div>
+
+  <div class="card">
+    <h3><span class="num">3</span> How it works</h3>
+    <ul class="steps">
+      <li>The <code>&lt;script&gt;</code> tag pulls <code>widget.js</code> from your LangBot instance, pre-configured for that bot UUID.</li>
+      <li>A floating chat bubble appears in the bottom-right corner of the page.</li>
+      <li>Messages travel over a WebSocket to the bot's bound pipeline; replies stream back into the bubble.</li>
+      <li>Title, bubble icon, language and optional Cloudflare Turnstile protection are all set in the bot's config — no page changes needed.</li>
+    </ul>
+  </div>
+</div>
+
+<script>
+  var $ = function (s) { return document.querySelector(s); };
+  var baseEl = $("#base"), uuidEl = $("#uuid"), titleEl = $("#title"),
+      statusEl = $("#status"), snippetEl = $("#snippet");
+  var WIDGET_ID = "langbot-embed-demo-script";
+
+  function clean(v) { return (v || "").trim().replace(/\/+$/, ""); }
+
+  function buildSrc() {
+    var base = clean(baseEl.value) || "http://localhost:5300";
+    var uuid = uuidEl.value.trim() || "<bot-uuid>";
+    return base + "/api/v1/embed/" + uuid + "/widget.js";
+  }
+
+  function refreshSnippet() {
+    var title = titleEl.value.trim() || "LangBot";
+    var src = buildSrc();
+    snippetEl.textContent =
+      '<script data-title="' + title + '" src="' + src + '"><\/script>';
+  }
+
+  function setStatus(html) { statusEl.innerHTML = html; }
+
+  function removeWidget() {
+    var old = document.getElementById(WIDGET_ID);
+    if (old) old.remove();
+    // The widget injects its own DOM (bubble + panel). Clear the common containers it creates.
+    document.querySelectorAll('[id^="langbot-"]').forEach(function (n) {
+      if (n.id !== WIDGET_ID) n.remove();
+    });
+  }
+
+  function loadWidget() {
+    var uuid = uuidEl.value.trim();
+    var uuidRe = /^[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}$/i;
+    if (!uuidRe.test(uuid)) {
+      setStatus('<span class="bad">Enter a valid bot UUID first.</span>');
+      return;
+    }
+    removeWidget();
+    var s = document.createElement("script");
+    s.id = WIDGET_ID;
+    s.setAttribute("data-title", titleEl.value.trim() || "LangBot");
+    s.src = buildSrc();
+    s.onload = function () {
+      setStatus('<span class="ok">Widget loaded — look bottom-right.</span>');
+    };
+    s.onerror = function () {
+      setStatus('<span class="bad">Failed to load widget.js — check the base URL and that the bot is enabled.</span>');
+    };
+    document.body.appendChild(s);
+    setStatus("Loading…");
+  }
+
+  $("#load").onclick = loadWidget;
+  $("#unload").onclick = function () {
+    removeWidget();
+    setStatus("Widget removed.");
+  };
+  $("#copy").onclick = function () {
+    navigator.clipboard.writeText(snippetEl.textContent).then(function () {
+      var b = $("#copy"); b.textContent = "Copied"; setTimeout(function () { b.textContent = "Copy"; }, 1200);
+    });
+  };
+  [baseEl, uuidEl, titleEl].forEach(function (el) { el.addEventListener("input", refreshSnippet); });
+  refreshSnippet();
+</script>
+</body>
+</html>
@@ -1,6 +1,6 @@
 [project]
 name = "langbot"
-version = "4.10.2"
+version = "4.10.4"
 description = "Production-grade platform for building agentic IM bots"
 readme = "README.md"
 license-files = ["LICENSE"]
@@ -70,7 +70,7 @@ dependencies = [
    "chromadb>=1.0.0,<2.0.0",
    "qdrant-client (>=1.15.1,<2.0.0)",
    "pyseekdb==1.1.0.post3",
-    "langbot-plugin==0.4.5",
+    "langbot-plugin @ file:///home/qinjunyan/code/projects/langbot/langbot-plugin-sdk",
    "asyncpg>=0.30.0",
    "line-bot-sdk>=3.19.0",
    "matrix-nio>=0.25.2",
@@ -42,6 +42,38 @@ MyPlugin/

 Each component has a `.yaml` (metadata) and `.py` (implementation).

+## README & i18n convention (enforced on the marketplace)
+
+A plugin published to LangBot Space serves a localized README on its detail page.
+The resolver (`langbot-space` `PluginService.GetPluginREADME`) works like this:
+
+- **Root `README.md` MUST be in English.** It is the default and the fallback —
+  when no per-language README matches the viewer's locale, the page serves the
+  root `README.md`. A non-English root README makes the English/default view show
+  the wrong language.
+- **All other languages live under `readme/README_{lang}.md`** — e.g.
+  `readme/README_zh_Hans.md`, `readme/README_ja_JP.md`. The 8 supported locales:
+  `en_US, zh_Hans, zh_Hant, ja_JP, th_TH, vi_VN, es_ES, ru_RU`.
+- `manifest.yaml` `metadata.label` / `metadata.description` should carry the same
+  8-locale i18n set (`repository` must be a real, alive URL).
+
+```
+MyPlugin/
+├── manifest.yaml
+├── README.md                   # English (default + fallback) — REQUIRED, must be English
+└── readme/
+    ├── README_zh_Hans.md
+    ├── README_zh_Hant.md
+    ├── README_ja_JP.md
+    ├── README_th_TH.md
+    ├── README_vi_VN.md
+    ├── README_es_ES.md
+    └── README_ru_RU.md
+```
+
+`manifest.yaml` (incl. `repository`) is the source of truth — the marketplace
+syncs from it, so edit the package and re-publish rather than patching live data.
+
 ## Critical SDK Pitfalls

 ### 1. MessageChain is a RootModel — iterate directly
@@ -439,7 +471,7 @@ async def on_msg(event_context: context.EventContext):
        if isinstance(component, platform_message.Plain):
            text_parts.append(component.text)
    text = "".join(text_parts).strip()
-    
+
    if should_handle(text):
        event_context.prevent_default()
        event_context.prevent_postorder()
@@ -1,3 +1,5 @@
 """LangBot - Production-grade platform for building agentic IM bots"""

-__version__ = '4.10.2'
+from importlib.metadata import version
+
+__version__ = version('langbot')
@@ -1,6 +1,9 @@
 from __future__ import annotations

+from langbot.pkg.utils import constants
+
 from .. import group
+from .box_visibility import should_hide_box_runtime_status


@group.group_class('box', '/api/v1/box')
@@ -9,6 +12,7 @@ class BoxRouterGroup(group.RouterGroup):
        @self.route('/status', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
        async def _() -> str:
            status = await self.ap.box_service.get_status()
+            status['hidden'] = should_hide_box_runtime_status(constants.edition, status.get('enabled'))
            return self.success(data=status)

        @self.route('/sessions', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
@@ -0,0 +1,5 @@
+from __future__ import annotations
+
+
+def should_hide_box_runtime_status(edition: str, box_enabled: bool | None) -> bool:
+    return edition == 'cloud' and box_enabled is False
@@ -62,16 +62,24 @@ class EmbedRouterGroup(group.RouterGroup):
        """Resolve *bot_uuid* to ``(runtime_bot, pipeline_uuid)``.

        Returns ``(None, None)`` when the bot does not exist, is not a
-        ``web_page_bot``, is disabled, or has no pipeline bound.
+        ``web_page_bot``, is disabled, or has no pipeline/workflow bound.
        """
        for bot in self.ap.platform_mgr.bots:
            if (
                bot.bot_entity.uuid == bot_uuid
                and bot.bot_entity.adapter == 'web_page_bot'
                and bot.bot_entity.enable
-                and bot.bot_entity.use_pipeline_uuid
            ):
-                return bot, bot.bot_entity.use_pipeline_uuid
+                # Check for workflow binding first
+                binding_type = getattr(bot.bot_entity, 'binding_type', 'pipeline') or 'pipeline'
+                binding_uuid = getattr(bot.bot_entity, 'binding_uuid', None)
+
+                if binding_type == 'workflow' and binding_uuid:
+                    # For workflow binding, return workflow UUID
+                    return bot, binding_uuid
+                elif bot.bot_entity.use_pipeline_uuid:
+                    # For pipeline binding, return pipeline UUID
+                    return bot, bot.bot_entity.use_pipeline_uuid
        return None, None

    def _get_bot_config(self, bot_uuid: str) -> dict:
@@ -86,6 +86,10 @@ class PipelinesRouterGroup(group.RouterGroup):
                        'available_plugins': plugins,
                        'bound_mcp_servers': extensions_prefs.get('mcp_servers', []),
                        'available_mcp_servers': mcp_servers,
+                        'bound_mcp_resources': extensions_prefs.get('mcp_resources', []),
+                        'mcp_resource_agent_read_enabled': extensions_prefs.get(
+                            'mcp_resource_agent_read_enabled', True
+                        ),
                        'bound_skills': extensions_prefs.get('skills', []),
                        'available_skills': available_skills,
                    }
@@ -99,6 +103,8 @@ class PipelinesRouterGroup(group.RouterGroup):
                bound_plugins = json_data.get('bound_plugins', [])
                bound_mcp_servers = json_data.get('bound_mcp_servers', [])
                bound_skills = json_data.get('bound_skills', [])
+                bound_mcp_resources = json_data.get('bound_mcp_resources')
+                mcp_resource_agent_read_enabled = json_data.get('mcp_resource_agent_read_enabled')

                await self.ap.pipeline_service.update_pipeline_extensions(
                    pipeline_uuid,
@@ -108,6 +114,8 @@ class PipelinesRouterGroup(group.RouterGroup):
                    enable_all_mcp_servers,
                    bound_skills=bound_skills,
                    enable_all_skills=enable_all_skills,
+                    bound_mcp_resources=bound_mcp_resources,
+                    mcp_resource_agent_read_enabled=mcp_resource_agent_read_enabled,
                )

                return self.success()
@@ -18,7 +18,6 @@ class BotsRouterGroup(group.RouterGroup):
        @self.route('/<bot_uuid>', methods=['GET', 'PUT', 'DELETE'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
        async def _(bot_uuid: str) -> str:
            if quart.request.method == 'GET':
-                # 返回运行时信息，包括webhook地址等
                bot = await self.ap.bot_service.get_runtime_bot_info(bot_uuid)
                if bot is None:
                    return self.http_status(404, -1, 'bot not found')
@@ -37,30 +36,21 @@ class BotsRouterGroup(group.RouterGroup):
            from_index = json_data.get('from_index', -1)
            max_count = json_data.get('max_count', 10)
            logs, total_count = await self.ap.bot_service.list_event_logs(bot_uuid, from_index, max_count)
-            return self.success(
-                data={
-                    'logs': logs,
-                    'total_count': total_count,
-                }
-            )
+            return self.success(data={'logs': logs, 'total_count': total_count})

        @self.route('/<bot_uuid>/send_message', methods=['POST'], auth_type=group.AuthType.API_KEY)
        async def _(bot_uuid: str) -> str:
-            """Send message to a specific target via bot"""
            json_data = await quart.request.json
            target_type = json_data.get('target_type')
            target_id = json_data.get('target_id')
            message_chain_data = json_data.get('message_chain')

-            # Validate required fields
            if not target_type:
                return self.http_status(400, -1, 'target_type is required')
            if not target_id:
                return self.http_status(400, -1, 'target_id is required')
            if not message_chain_data:
                return self.http_status(400, -1, 'message_chain is required')
-
-            # Validate target_type
            if target_type not in ['person', 'group']:
                return self.http_status(400, -1, 'target_type must be either "person" or "group"')

@@ -72,3 +62,29 @@ class BotsRouterGroup(group.RouterGroup):

                traceback.print_exc()
                return self.http_status(500, -1, f'Failed to send message: {str(e)}')
+
+        # ============ Bot Admins ============
+
+        @self.route('/<bot_uuid>/admins', methods=['GET', 'POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _(bot_uuid: str) -> str:
+            if quart.request.method == 'GET':
+                admins = await self.ap.bot_service.get_bot_admins(bot_uuid)
+                return self.success(data={'admins': admins})
+            elif quart.request.method == 'POST':
+                json_data = await quart.request.json
+                launcher_type = json_data.get('launcher_type', '').strip()
+                launcher_id = str(json_data.get('launcher_id', '')).strip()
+                if not launcher_type or not launcher_id:
+                    return self.http_status(400, -1, 'launcher_type and launcher_id are required')
+                try:
+                    admin_id = await self.ap.bot_service.add_bot_admin(bot_uuid, launcher_type, launcher_id)
+                    return self.success(data={'id': admin_id})
+                except Exception as e:
+                    return self.http_status(409, -1, str(e))
+
+        @self.route(
+            '/<bot_uuid>/admins/<int:admin_id>', methods=['DELETE'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY
+        )
+        async def _(bot_uuid: str, admin_id: int) -> str:
+            await self.ap.bot_service.delete_bot_admin(bot_uuid, admin_id)
+            return self.success()
@@ -2,6 +2,7 @@ from __future__ import annotations

 import quart
 import traceback
+from urllib.parse import unquote


 from ... import group
@@ -66,3 +67,50 @@ class MCPRouterGroup(group.RouterGroup):
            server_data = await quart.request.json
            task_id = await self.ap.mcp_service.test_mcp_server(server_name=server_name, server_data=server_data)
            return self.success(data={'task_id': task_id})
+
+        @self.route('/servers/<server_name>/resources', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def _(server_name: str) -> str:
+            """Get resources from an MCP server"""
+            server_name = unquote(server_name)
+            try:
+                resources = await self.ap.mcp_service.get_mcp_server_resources(server_name)
+                templates = await self.ap.mcp_service.get_mcp_server_resource_templates(server_name)
+                runtime_info = await self.ap.mcp_service.get_runtime_info(server_name)
+                return self.success(
+                    data={
+                        'resources': resources,
+                        'resource_templates': templates,
+                        'resource_capabilities': (runtime_info or {}).get('resource_capabilities', {}),
+                    }
+                )
+            except Exception as e:
+                return self.http_status(500, -1, f'Failed to get resources: {str(e)}')
+
+        @self.route('/servers/<server_name>/resource-templates', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def _(server_name: str) -> str:
+            """Get resource templates from an MCP server"""
+            server_name = unquote(server_name)
+            try:
+                templates = await self.ap.mcp_service.get_mcp_server_resource_templates(server_name)
+                return self.success(data={'resource_templates': templates})
+            except Exception as e:
+                return self.http_status(500, -1, f'Failed to get resource templates: {str(e)}')
+
+        @self.route('/servers/<server_name>/resources/read', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _(server_name: str) -> str:
+            """Read a resource from an MCP server"""
+            server_name = unquote(server_name)
+            data = await quart.request.json
+            uri = data.get('uri')
+            if not uri:
+                return self.http_status(400, -1, 'URI is required')
+            try:
+                envelope = await self.ap.mcp_service.read_mcp_server_resource_envelope(
+                    server_name,
+                    uri,
+                    max_bytes=data.get('max_bytes'),
+                    include_blob=bool(data.get('include_blob', False)),
+                )
+                return self.success(data=envelope)
+            except Exception as e:
+                return self.http_status(500, -1, f'Failed to read resource: {str(e)}')
@@ -1,5 +1,7 @@
 from __future__ import annotations

+import quart
+
 from ... import group


@@ -9,25 +11,41 @@ class ToolsRouterGroup(group.RouterGroup):
        @self.route('', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
        async def _() -> str:
            """获取所有可用工具列表"""
-            tools = await self.ap.tool_mgr.get_all_tools()
+            pipeline_uuid = quart.request.args.get('pipeline_uuid') or quart.request.args.get('pipeline_id')
+            bound_plugins: list[str] | None = None
+            bound_mcp_servers: list[str] | None = None

-            tool_list = []
-            for tool in tools:
-                tool_list.append(
-                    {
-                        'name': tool.name,
-                        'description': tool.description,
-                        'human_desc': tool.human_desc,
-                        'parameters': tool.parameters,
-                    }
-                )
+            if pipeline_uuid:
+                pipeline = await self.ap.pipeline_service.get_pipeline(pipeline_uuid)
+                if pipeline is None:
+                    return self.http_status(404, -1, 'pipeline not found')

-            return self.success(data={'tools': tool_list})
+                extensions_prefs = pipeline.get('extensions_preferences', {}) or {}
+                if not extensions_prefs.get('enable_all_plugins', True):
+                    bound_plugins = [
+                        f'{plugin.get("author", "")}/{plugin.get("name", "")}'
+                        for plugin in extensions_prefs.get('plugins', [])
+                        if isinstance(plugin, dict) and plugin.get('name')
+                    ]
+                if not extensions_prefs.get('enable_all_mcp_servers', True):
+                    bound_mcp_servers = [
+                        server for server in (extensions_prefs.get('mcp_servers', []) or []) if isinstance(server, str)
+                    ]
+
+            return self.success(
+                data={
+                    'tools': await self.ap.tool_mgr.get_tool_catalog(
+                        bound_plugins,
+                        bound_mcp_servers,
+                        include_skill_authoring=True,
+                    )
+                }
+            )

        @self.route('/<tool_name>', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
        async def _(tool_name: str) -> str:
            """获取特定工具详情"""
-            tools = await self.ap.tool_mgr.get_all_tools()
+            tools = await self.ap.tool_mgr.get_all_tools(include_skill_authoring=True)

            for tool in tools:
                if tool.name == tool_name:
@@ -1,3 +1,5 @@
+import base64
+
 import quart

 from .. import group
@@ -30,6 +32,50 @@ class SurveyRouterGroup(group.RouterGroup):
                return self.fail(2, 'Failed to submit response')
            return self.fail(3, 'Survey not available')

+        @self.route('/feedback', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _feedback(user_email: str) -> str:
+            """Submit on-demand user feedback from the sidebar."""
+            json_data = await quart.request.get_json(silent=True) or {}
+            content = str(json_data.get('content', '')).strip()
+            attachments = json_data.get('attachments', [])
+
+            if not content:
+                return self.fail(1, 'content required')
+            if len(content) > 5000:
+                return self.fail(2, 'content too long')
+            if not isinstance(attachments, list):
+                return self.fail(3, 'attachments must be an array')
+            if len(attachments) > 3:
+                return self.fail(4, 'too many attachments')
+
+            normalized_attachments = []
+            for item in attachments:
+                if not isinstance(item, dict):
+                    continue
+                data_url = str(item.get('data_url', ''))
+                mime_type = str(item.get('mime_type', ''))[:128]
+                name = str(item.get('name', ''))[:255]
+                if not data_url.startswith('data:image/'):
+                    continue
+                try:
+                    payload = data_url.split(',', 1)[1]
+                    if len(base64.b64decode(payload, validate=True)) > 1024 * 1024:
+                        return self.fail(5, 'attachment too large')
+                except Exception:
+                    return self.fail(5, 'attachment too large')
+                normalized_attachments.append({'name': name, 'mime_type': mime_type, 'data_url': data_url})
+
+            if self.ap.survey:
+                ok = await self.ap.survey.submit_feedback(
+                    content=content,
+                    attachments=normalized_attachments,
+                    user_email=user_email,
+                )
+                if ok:
+                    return self.success()
+                return self.fail(6, 'Failed to submit feedback')
+            return self.fail(7, 'Survey not available')
+
        @self.route('/dismiss', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
        async def _dismiss() -> str:
            """Dismiss survey."""
@@ -195,6 +195,13 @@ class UserRouterGroup(group.RouterGroup):
        @self.route('/set-password', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
        async def _(user_email: str) -> str:
            """Set password for Space account (first time) or change password"""
+            # Check if modifying login info is allowed
+            allow_modify_login_info = self.ap.instance_config.data.get('system', {}).get(
+                'allow_modify_login_info', True
+            )
+            if not allow_modify_login_info:
+                return self.http_status(403, -1, 'Modifying login info is disabled')
+
            json_data = await quart.request.json
            new_password = json_data.get('new_password')
            current_password = json_data.get('current_password')
@@ -0,0 +1,5 @@
+# Workflow router group
+from .workflows import WorkflowsRouterGroup, ExecutionsRouterGroup
+from .websocket_chat import WorkflowWebSocketChatRouterGroup
+
+__all__ = ['WorkflowsRouterGroup', 'ExecutionsRouterGroup', 'WorkflowWebSocketChatRouterGroup']
@@ -0,0 +1,260 @@
+"""Workflow WebSocket聊天路由 - 支持工作流调试的双向实时通信"""
+
+import asyncio
+import datetime
+import json
+import logging
+
+import quart
+
+from ... import group
+from ......platform.sources.websocket_manager import ws_connection_manager
+
+logger = logging.getLogger(__name__)
+
+
+@group.group_class('workflow_websocket_chat', '/api/v1/workflows/<workflow_uuid>/ws')
+class WorkflowWebSocketChatRouterGroup(group.RouterGroup):
+    async def initialize(self) -> None:
+        @self.quart_app.websocket(self.path + '/connect')
+        async def workflow_websocket_connect(workflow_uuid: str):
+            """
+            建立工作流WebSocket连接
+
+            URL参数:
+                - workflow_uuid: 工作流UUID
+                - session_type: 会话类型 (person/group)
+            """
+            try:
+                session_type = quart.websocket.args.get('session_type', 'person')
+                logger.info(
+                    'Workflow WebSocket connect request received',
+                    extra={
+                        'workflow_uuid': workflow_uuid,
+                        'session_type': session_type,
+                        'path': quart.websocket.path,
+                        'query_string': quart.websocket.query_string.decode('utf-8', errors='ignore'),
+                        'remote_addr': getattr(quart.websocket, 'remote_addr', None),
+                        'user_agent': quart.websocket.headers.get('User-Agent', ''),
+                        'host': quart.websocket.headers.get('Host', ''),
+                        'origin': quart.websocket.headers.get('Origin', ''),
+                    },
+                )
+
+                if session_type not in ['person', 'group']:
+                    await quart.websocket.send(
+                        json.dumps({'type': 'error', 'message': 'session_type must be person or group'})
+                    )
+                    return
+
+                websocket_adapter = self.ap.platform_mgr.websocket_proxy_bot.adapter
+
+                if not websocket_adapter:
+                    logger.warning(
+                        'Workflow WebSocket adapter missing',
+                        extra={
+                            'workflow_uuid': workflow_uuid,
+                            'session_type': session_type,
+                        },
+                    )
+                    await quart.websocket.send(json.dumps({'type': 'error', 'message': 'WebSocket adapter not found'}))
+                    return
+
+                connection = await ws_connection_manager.add_connection(
+                    websocket=quart.websocket._get_current_object(),
+                    pipeline_uuid=workflow_uuid,
+                    session_type=session_type,
+                    metadata={'user_agent': quart.websocket.headers.get('User-Agent', ''), 'is_workflow': True},
+                )
+
+                await quart.websocket.send(
+                    json.dumps(
+                        {
+                            'type': 'connected',
+                            'connection_id': connection.connection_id,
+                            'workflow_uuid': workflow_uuid,
+                            'session_type': session_type,
+                            'timestamp': connection.created_at.isoformat(),
+                        }
+                    )
+                )
+
+                logger.debug(
+                    f'Workflow WebSocket connection established: {connection.connection_id} '
+                    f'(workflow={workflow_uuid}, session_type={session_type})'
+                )
+
+                receive_task = asyncio.create_task(self._handle_receive(connection, websocket_adapter))
+                send_task = asyncio.create_task(self._handle_send(connection))
+
+                try:
+                    await asyncio.gather(receive_task, send_task)
+                except Exception as e:
+                    logger.error(f'Workflow WebSocket task execution error: {e}')
+                finally:
+                    await ws_connection_manager.remove_connection(connection.connection_id)
+                    logger.debug(f'Workflow WebSocket connection cleaned: {connection.connection_id}')
+
+            except Exception as e:
+                logger.error(
+                    'Workflow WebSocket connection error',
+                    exc_info=True,
+                    extra={
+                        'workflow_uuid': workflow_uuid,
+                        'session_type': quart.websocket.args.get('session_type', 'person'),
+                        'path': quart.websocket.path,
+                        'query_string': quart.websocket.query_string.decode('utf-8', errors='ignore'),
+                        'remote_addr': getattr(quart.websocket, 'remote_addr', None),
+                    },
+                )
+                try:
+                    await quart.websocket.send(json.dumps({'type': 'error', 'message': str(e)}))
+                except Exception as send_error:
+                    logger.debug(
+                        'Failed to send error message to workflow websocket client',
+                        exc_info=True,
+                        extra={
+                            'workflow_uuid': workflow_uuid,
+                            'send_error': str(send_error),
+                        },
+                    )
+
+        @self.route('/messages/<session_type>', methods=['GET'])
+        async def get_messages(workflow_uuid: str, session_type: str) -> str:
+            """获取工作流消息历史"""
+            try:
+                if session_type not in ['person', 'group']:
+                    return self.http_status(400, -1, 'session_type must be person or group')
+
+                websocket_adapter = self.ap.platform_mgr.websocket_proxy_bot.adapter
+
+                if not websocket_adapter:
+                    return self.http_status(404, -1, 'WebSocket adapter not found')
+
+                messages = websocket_adapter.get_websocket_messages(workflow_uuid, session_type)
+
+                return self.success(data={'messages': messages})
+
+            except Exception as e:
+                return self.http_status(500, -1, f'Internal server error: {str(e)}')
+
+        @self.route('/reset/<session_type>', methods=['POST'])
+        async def reset_session(workflow_uuid: str, session_type: str) -> str:
+            """重置工作流会话"""
+            try:
+                if session_type not in ['person', 'group']:
+                    return self.http_status(400, -1, 'session_type must be person or group')
+
+                websocket_adapter = self.ap.platform_mgr.websocket_proxy_bot.adapter
+
+                if not websocket_adapter:
+                    return self.http_status(404, -1, 'WebSocket adapter not found')
+
+                websocket_adapter.reset_session(workflow_uuid, session_type)
+
+                return self.success(data={'message': 'Session reset successfully'})
+
+            except Exception as e:
+                return self.http_status(500, -1, f'Internal server error: {str(e)}')
+
+        @self.route('/connections', methods=['GET'])
+        async def get_connections(workflow_uuid: str) -> str:
+            """获取当前工作流连接统计"""
+            try:
+                stats = ws_connection_manager.get_stats()
+                connections = await ws_connection_manager.get_connections_by_pipeline(workflow_uuid)
+
+                return self.success(
+                    data={
+                        'stats': stats,
+                        'connections': [
+                            {
+                                'connection_id': conn.connection_id,
+                                'session_type': conn.session_type,
+                                'created_at': conn.created_at.isoformat(),
+                                'last_active': conn.last_active.isoformat(),
+                                'is_active': conn.is_active,
+                            }
+                            for conn in connections
+                        ],
+                    }
+                )
+
+            except Exception as e:
+                return self.http_status(500, -1, f'Internal server error: {str(e)}')
+
+        @self.route('/broadcast', methods=['POST'])
+        async def broadcast_message(workflow_uuid: str) -> str:
+            """向所有工作流连接广播消息"""
+            try:
+                data = await quart.request.get_json()
+                message = data.get('message')
+
+                if not message:
+                    return self.http_status(400, -1, 'message is required')
+
+                broadcast_data = {
+                    'type': 'broadcast',
+                    'message': message,
+                    'timestamp': datetime.datetime.now().isoformat(),
+                }
+
+                await ws_connection_manager.broadcast_to_pipeline(workflow_uuid, broadcast_data)
+
+                return self.success(data={'message': 'Broadcast sent successfully'})
+
+            except Exception as e:
+                return self.http_status(500, -1, f'Internal server error: {str(e)}')
+
+    async def _handle_receive(self, connection, websocket_adapter):
+        """处理接收消息的任务"""
+        try:
+            while connection.is_active:
+                message = await quart.websocket.receive()
+
+                await ws_connection_manager.update_activity(connection.connection_id)
+
+                try:
+                    data = json.loads(message)
+                    message_type = data.get('type', 'message')
+
+                    if message_type == 'ping':
+                        await connection.send_queue.put(
+                            {'type': 'pong', 'timestamp': datetime.datetime.now().isoformat()}
+                        )
+
+                    elif message_type == 'message':
+                        logger.debug(f'收到工作流消息: {data} from {connection.connection_id}')
+                        await websocket_adapter.handle_websocket_message(connection, data)
+
+                    elif message_type == 'disconnect':
+                        logger.debug(f'Client disconnected: {connection.connection_id}')
+                        break
+
+                    else:
+                        logger.warning(f'Unknown message type: {message_type}')
+
+                except json.JSONDecodeError:
+                    logger.error(f'Invalid JSON message: {message}')
+                    await connection.send_queue.put({'type': 'error', 'message': 'Invalid JSON format'})
+
+        except Exception as e:
+            logger.error(f'Receive message error: {e}', exc_info=True)
+        finally:
+            connection.is_active = False
+
+    async def _handle_send(self, connection):
+        """处理发送消息的任务"""
+        try:
+            while connection.is_active:
+                try:
+                    message = await asyncio.wait_for(connection.send_queue.get(), timeout=1.0)
+                    await quart.websocket.send(json.dumps(message))
+
+                except asyncio.TimeoutError:
+                    continue
+
+        except Exception as e:
+            logger.error(f'Send message error: {e}', exc_info=True)
+        finally:
+            connection.is_active = False
@@ -0,0 +1,484 @@
+from __future__ import annotations
+
+import quart
+
+from ... import group
+from ....service.workflow import WorkflowExecutionFailedError
+
+
+@group.group_class('workflows', '/api/v1/workflows')
+class WorkflowsRouterGroup(group.RouterGroup):
+    """Workflow API router group"""
+
+    async def initialize(self) -> None:
+        # Workflow CRUD
+        @self.route('', methods=['GET', 'POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _() -> str:
+            if quart.request.method == 'GET':
+                sort_by = quart.request.args.get('sort_by', 'created_at')
+                sort_order = quart.request.args.get('sort_order', 'DESC')
+                enabled_only = quart.request.args.get('enabled_only', 'false').lower() == 'true'
+                return self.success(
+                    data={'workflows': await self.ap.workflow_service.get_workflows(sort_by, sort_order, enabled_only)}
+                )
+            elif quart.request.method == 'POST':
+                json_data = await quart.request.json
+                workflow_uuid = await self.ap.workflow_service.create_workflow(json_data)
+                return self.success(data={'uuid': workflow_uuid})
+
+        # Get node types (available nodes for the editor)
+        @self.route('/_/node-types', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _() -> str:
+            return self.success(
+                data={
+                    'node_types': await self.ap.workflow_service.get_node_types(),
+                    'categories': await self.ap.workflow_service.get_node_types_by_category_meta(),
+                }
+            )
+
+        # Get node types by category
+        @self.route('/_/node-types/categories', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _() -> str:
+            return self.success(data={'categories': await self.ap.workflow_service.get_node_types_by_category()})
+
+        # Single workflow operations
+        @self.route(
+            '/<workflow_uuid>', methods=['GET', 'PUT', 'DELETE'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY
+        )
+        async def _(workflow_uuid: str) -> str:
+            if quart.request.method == 'GET':
+                workflow = await self.ap.workflow_service.get_workflow(workflow_uuid)
+                if workflow is None:
+                    return self.http_status(404, -1, 'workflow not found')
+                return self.success(data={'workflow': workflow})
+            elif quart.request.method == 'PUT':
+                json_data = await quart.request.json
+                try:
+                    await self.ap.workflow_service.update_workflow(workflow_uuid, json_data)
+                    return self.success()
+                except ValueError as e:
+                    return self.http_status(404, -1, str(e))
+            elif quart.request.method == 'DELETE':
+                await self.ap.workflow_service.delete_workflow(workflow_uuid)
+                return self.success()
+            return self.http_status(405, -1, 'method not allowed')
+
+        # Publish workflow (enable)
+        @self.route('/<workflow_uuid>/publish', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _(workflow_uuid: str) -> str:
+            try:
+                await self.ap.workflow_service.publish_workflow(workflow_uuid)
+                return self.success()
+            except ValueError as e:
+                return self.http_status(404, -1, str(e))
+
+        # Unpublish workflow (disable)
+        @self.route('/<workflow_uuid>/unpublish', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _(workflow_uuid: str) -> str:
+            try:
+                await self.ap.workflow_service.unpublish_workflow(workflow_uuid)
+                return self.success()
+            except ValueError as e:
+                return self.http_status(404, -1, str(e))
+
+        # Copy workflow
+        @self.route('/<workflow_uuid>/copy', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _(workflow_uuid: str) -> str:
+            try:
+                new_uuid = await self.ap.workflow_service.copy_workflow(workflow_uuid)
+                return self.success(data={'uuid': new_uuid})
+            except ValueError as e:
+                return self.http_status(404, -1, str(e))
+
+        # Execute workflow manually
+        @self.route('/<workflow_uuid>/execute', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _(workflow_uuid: str) -> str:
+            json_data = await quart.request.json or {}
+            trigger_data = json_data.get('trigger_data', {})
+            session_id = json_data.get('session_id')
+            user_id = json_data.get('user_id')
+            bot_id = json_data.get('bot_id')
+
+            try:
+                execution_id = await self.ap.workflow_service.execute_workflow(
+                    workflow_uuid,
+                    trigger_type='manual',
+                    trigger_data=trigger_data,
+                    session_id=session_id,
+                    user_id=user_id,
+                    bot_id=bot_id,
+                )
+                return self.success(data={'execution_id': execution_id})
+            except ValueError as e:
+                return self.http_status(404, -1, str(e))
+            except WorkflowExecutionFailedError as e:
+                return self.http_status(500, -1, e.message)
+
+        # Get workflow executions
+        @self.route('/<workflow_uuid>/executions', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _(workflow_uuid: str) -> str:
+            limit = int(quart.request.args.get('limit', 50))
+            offset = int(quart.request.args.get('offset', 0))
+            executions = await self.ap.workflow_service.get_executions(
+                workflow_uuid=workflow_uuid, limit=limit, offset=offset
+            )
+            return self.success(data=executions)
+
+        @self.route(
+            '/<workflow_uuid>/executions/<execution_uuid>',
+            methods=['GET'],
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
+        )
+        async def _(workflow_uuid: str, execution_uuid: str) -> str:
+            execution = await self.ap.workflow_service.get_execution(execution_uuid)
+            if execution is None:
+                return self.http_status(404, -1, 'execution not found')
+            if execution.get('workflow_uuid') != workflow_uuid:
+                return self.http_status(404, -1, 'execution not found in workflow')
+            return self.success(data={'execution': execution})
+
+        # Get workflow versions
+        @self.route('/<workflow_uuid>/versions', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _(workflow_uuid: str) -> str:
+            versions = await self.ap.workflow_service.get_versions(workflow_uuid)
+            return self.success(data={'versions': versions})
+
+        # Rollback to a specific version
+        @self.route(
+            '/<workflow_uuid>/rollback/<int:version>', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY
+        )
+        async def _(workflow_uuid: str, version: int) -> str:
+            try:
+                await self.ap.workflow_service.rollback_to_version(workflow_uuid, version)
+                return self.success()
+            except ValueError as e:
+                return self.http_status(404, -1, str(e))
+
+        # Workflow extensions (plugins and MCP servers)
+        @self.route(
+            '/<workflow_uuid>/extensions', methods=['GET', 'PUT'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY
+        )
+        async def _(workflow_uuid: str) -> str:
+            if quart.request.method == 'GET':
+                workflow = await self.ap.workflow_service.get_workflow(workflow_uuid)
+                if workflow is None:
+                    return self.http_status(404, -1, 'workflow not found')
+
+                # Get available plugins and MCP servers
+                pipeline_component_kinds = ['Command', 'EventListener', 'Tool']
+                plugins = await self.ap.plugin_connector.list_plugins(component_kinds=pipeline_component_kinds)
+                mcp_servers = await self.ap.mcp_service.get_mcp_servers(contain_runtime_info=True)
+
+                extensions_prefs = workflow.get('extensions_preferences', {})
+                return self.success(
+                    data={
+                        'enable_all_plugins': extensions_prefs.get('enable_all_plugins', True),
+                        'enable_all_mcp_servers': extensions_prefs.get('enable_all_mcp_servers', True),
+                        'bound_plugins': extensions_prefs.get('plugins', []),
+                        'available_plugins': plugins,
+                        'bound_mcp_servers': extensions_prefs.get('mcp_servers', []),
+                        'available_mcp_servers': mcp_servers,
+                    }
+                )
+            elif quart.request.method == 'PUT':
+                json_data = await quart.request.json
+                enable_all_plugins = json_data.get('enable_all_plugins', True)
+                enable_all_mcp_servers = json_data.get('enable_all_mcp_servers', True)
+                bound_plugins = json_data.get('bound_plugins', [])
+                bound_mcp_servers = json_data.get('bound_mcp_servers', [])
+
+                try:
+                    await self.ap.workflow_service.update_workflow_extensions(
+                        workflow_uuid, bound_plugins, bound_mcp_servers, enable_all_plugins, enable_all_mcp_servers
+                    )
+                    return self.success()
+                except ValueError as e:
+                    return self.http_status(404, -1, str(e))
+            return self.http_status(405, -1, 'method not allowed')
+
+        # Debug API - Start debug execution
+        @self.route('/<workflow_uuid>/debug/start', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _(workflow_uuid: str) -> str:
+            json_data = await quart.request.json or {}
+            context = json_data.get('context', {})
+            variables = json_data.get('variables', {})
+            breakpoints = json_data.get('breakpoints', [])
+
+            try:
+                execution_id = await self.ap.workflow_service.start_debug_execution(
+                    workflow_uuid, context=context, variables=variables, breakpoints=breakpoints
+                )
+                return self.success(data={'execution_id': execution_id})
+            except ValueError as e:
+                return self.http_status(404, -1, str(e))
+
+        # Debug API - Pause execution
+        @self.route(
+            '/<workflow_uuid>/debug/<execution_uuid>/pause',
+            methods=['POST'],
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
+        )
+        async def _(workflow_uuid: str, execution_uuid: str) -> str:
+            try:
+                await self.ap.workflow_service.pause_debug_execution(workflow_uuid, execution_uuid)
+                return self.success()
+            except ValueError as e:
+                return self.http_status(404, -1, str(e))
+
+        # Debug API - Resume execution
+        @self.route(
+            '/<workflow_uuid>/debug/<execution_uuid>/resume',
+            methods=['POST'],
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
+        )
+        async def _(workflow_uuid: str, execution_uuid: str) -> str:
+            try:
+                await self.ap.workflow_service.resume_debug_execution(workflow_uuid, execution_uuid)
+                return self.success()
+            except ValueError as e:
+                return self.http_status(404, -1, str(e))
+
+        # Debug API - Step execution
+        @self.route(
+            '/<workflow_uuid>/debug/<execution_uuid>/step',
+            methods=['POST'],
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
+        )
+        async def _(workflow_uuid: str, execution_uuid: str) -> str:
+            try:
+                result = await self.ap.workflow_service.step_debug_execution(workflow_uuid, execution_uuid)
+                return self.success(data=result)
+            except ValueError as e:
+                return self.http_status(404, -1, str(e))
+
+        # Debug API - Stop execution
+        @self.route(
+            '/<workflow_uuid>/debug/<execution_uuid>/stop',
+            methods=['POST'],
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
+        )
+        async def _(workflow_uuid: str, execution_uuid: str) -> str:
+            try:
+                await self.ap.workflow_service.stop_debug_execution(workflow_uuid, execution_uuid)
+                return self.success()
+            except ValueError as e:
+                return self.http_status(404, -1, str(e))
+
+        # Debug API - Get debug state
+        @self.route(
+            '/<workflow_uuid>/debug/<execution_uuid>/state',
+            methods=['GET'],
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
+        )
+        async def _(workflow_uuid: str, execution_uuid: str) -> str:
+            try:
+                state = await self.ap.workflow_service.get_debug_state(workflow_uuid, execution_uuid)
+                return self.success(data=state)
+            except ValueError as e:
+                return self.http_status(404, -1, str(e))
+
+        # Get execution logs
+        @self.route(
+            '/<workflow_uuid>/executions/<execution_uuid>/logs',
+            methods=['GET'],
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
+        )
+        async def _(workflow_uuid: str, execution_uuid: str) -> str:
+            limit = int(quart.request.args.get('limit', 100))
+            offset = int(quart.request.args.get('offset', 0))
+            try:
+                result = await self.ap.workflow_service.get_execution_logs(workflow_uuid, execution_uuid, limit, offset)
+                return self.success(data=result)
+            except ValueError as e:
+                return self.http_status(404, -1, str(e))
+
+        # Rerun execution
+        @self.route(
+            '/<workflow_uuid>/executions/<execution_uuid>/rerun',
+            methods=['POST'],
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
+        )
+        async def _(workflow_uuid: str, execution_uuid: str) -> str:
+            try:
+                new_execution_id = await self.ap.workflow_service.rerun_execution(workflow_uuid, execution_uuid)
+                return self.success(data={'execution_uuid': new_execution_id})
+            except ValueError as e:
+                return self.http_status(404, -1, str(e))
+
+        # Get workflow statistics
+        @self.route('/<workflow_uuid>/stats', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _(workflow_uuid: str) -> str:
+            try:
+                stats = await self.ap.workflow_service.get_workflow_stats(workflow_uuid)
+                return self.success(data=stats)
+            except ValueError as e:
+                return self.http_status(404, -1, str(e))
+
+        # LLM Node Performance Test Endpoint
+        # Tests each step of LLM node execution with detailed timing
+        @self.route('/_/test/llm-node', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _() -> str:
+            """Test LLM node performance with detailed step-by-step timing.
+            
+            Request body:
+            {
+                "model_uuid": "uuid-of-model",
+                "system_prompt": "optional system prompt",
+                "user_prompt": "test message",
+                "temperature": 0.7,
+                "max_tokens": 100
+            }
+            
+            Response includes timing for each step:
+            - model_fetch: Time to get model from model_mgr
+            - prompt_build: Time to build messages
+            - llm_call: Time for actual LLM invocation
+            - total: Total time
+            - usage: Token usage information
+            """
+            import time
+            
+            json_data = await quart.request.json
+            if not json_data:
+                return self.http_status(400, -1, 'Request body is required')
+            
+            model_uuid = json_data.get('model_uuid', '')
+            if not model_uuid:
+                return self.http_status(400, -1, 'model_uuid is required')
+            
+            user_prompt = json_data.get('user_prompt', 'test')
+            system_prompt = json_data.get('system_prompt', '')
+            temperature = json_data.get('temperature')
+            max_tokens = json_data.get('max_tokens', 0)
+            
+            timings = {}
+            errors = []
+            
+            # Step 1: Model fetch
+            t_start = time.perf_counter()
+            try:
+                runtime_model = await self.ap.model_mgr.get_model_by_uuid(model_uuid)
+                timings['model_fetch_ms'] = round((time.perf_counter() - t_start) * 1000, 2)
+                timings['model_found'] = True
+                timings['model_name'] = runtime_model.model_entity.name if runtime_model else None
+            except Exception as e:
+                timings['model_fetch_ms'] = round((time.perf_counter() - t_start) * 1000, 2)
+                timings['model_found'] = False
+                errors.append(f'Model fetch failed: {str(e)}')
+                return self.http_status(400, -1, {
+                    'error': errors[0],
+                    'timings': timings,
+                })
+            
+            # Step 2: Build messages
+            t_start = time.perf_counter()
+            import langbot_plugin.api.entities.builtin.provider.message as provider_message
+            messages = []
+            if system_prompt:
+                messages.append(provider_message.Message(role='system', content=system_prompt))
+            messages.append(provider_message.Message(role='user', content=user_prompt))
+            timings['prompt_build_ms'] = round((time.perf_counter() - t_start) * 1000, 2)
+            
+            # Step 3: Build extra args
+            extra_args = {}
+            if temperature is not None:
+                extra_args['temperature'] = float(temperature)
+            if max_tokens and int(max_tokens) > 0:
+                extra_args['max_tokens'] = int(max_tokens)
+            
+            # Step 4: LLM call
+            t_start = time.perf_counter()
+            try:
+                result_message = await runtime_model.provider.invoke_llm(
+                    query=None,
+                    model=runtime_model,
+                    messages=messages,
+                    funcs=None,
+                    extra_args=extra_args,
+                )
+                timings['llm_call_ms'] = round((time.perf_counter() - t_start) * 1000, 2)
+                timings['llm_call_success'] = True
+                
+                # Extract response text
+                response_text = ''
+                if isinstance(result_message.content, str):
+                    response_text = result_message.content
+                elif isinstance(result_message.content, list):
+                    for elem in result_message.content:
+                        if hasattr(elem, 'text') and elem.text:
+                            response_text += elem.text
+                        elif isinstance(elem, str):
+                            response_text += elem
+                
+                timings['response_length'] = len(response_text)
+                timings['response_preview'] = response_text[:200]
+                
+                # Extract usage
+                usage = {'prompt_tokens': 0, 'completion_tokens': 0, 'total_tokens': 0}
+                if hasattr(result_message, 'usage') and result_message.usage:
+                    u = result_message.usage
+                    usage = {
+                        'prompt_tokens': getattr(u, 'prompt_tokens', 0) or 0,
+                        'completion_tokens': getattr(u, 'completion_tokens', 0) or 0,
+                        'total_tokens': getattr(u, 'total_tokens', 0) or 0,
+                    }
+                timings['usage'] = usage
+                
+            except Exception as e:
+                timings['llm_call_ms'] = round((time.perf_counter() - t_start) * 1000, 2)
+                timings['llm_call_success'] = False
+                errors.append(f'LLM call failed: {str(e)}')
+            
+            # Calculate total
+            timings['total_ms'] = round(sum([
+                timings.get('model_fetch_ms', 0),
+                timings.get('prompt_build_ms', 0),
+                timings.get('llm_call_ms', 0),
+            ]), 2)
+            
+            # Add breakdown percentage
+            if timings['total_ms'] > 0:
+                timings['breakdown'] = {
+                    'model_fetch_pct': round(timings.get('model_fetch_ms', 0) / timings['total_ms'] * 100, 1),
+                    'prompt_build_pct': round(timings.get('prompt_build_ms', 0) / timings['total_ms'] * 100, 1),
+                    'llm_call_pct': round(timings.get('llm_call_ms', 0) / timings['total_ms'] * 100, 1),
+                }
+            
+            if errors:
+                timings['errors'] = errors
+            
+            return self.success(data={'test_result': timings})
+
+
+@group.group_class('executions', '/api/v1/executions')
+class ExecutionsRouterGroup(group.RouterGroup):
+    """Workflow execution API router group"""
+
+    async def initialize(self) -> None:
+        # Get all executions (across all workflows)
+        @self.route('', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _() -> str:
+            limit = int(quart.request.args.get('limit', 50))
+            offset = int(quart.request.args.get('offset', 0))
+            status = quart.request.args.get('status')
+            executions = await self.ap.workflow_service.get_executions(limit=limit, offset=offset, status=status)
+            return self.success(data=executions)
+
+        # Get single execution
+        @self.route('/<execution_uuid>', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _(execution_uuid: str) -> str:
+            execution = await self.ap.workflow_service.get_execution(execution_uuid)
+            if execution is None:
+                return self.http_status(404, -1, 'execution not found')
+            return self.success(data={'execution': execution})
+
+        # Cancel execution
+        @self.route('/<execution_uuid>/cancel', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _(execution_uuid: str) -> str:
+            try:
+                await self.ap.workflow_service.cancel_execution(execution_uuid)
+                return self.success()
+            except ValueError as e:
+                return self.http_status(404, -1, str(e))
+            except RuntimeError as e:
+                return self.http_status(400, -1, str(e))
@@ -17,6 +17,7 @@ from .groups import platform as groups_platform
 from .groups import pipelines as groups_pipelines
 from .groups import knowledge as groups_knowledge
 from .groups import resources as groups_resources
+from .groups import workflows as groups_workflows
 from ...mcp.mount import MCPMount

 importutil.import_modules_in_pkg(groups)
@@ -25,6 +26,7 @@ importutil.import_modules_in_pkg(groups_platform)
 importutil.import_modules_in_pkg(groups_pipelines)
 importutil.import_modules_in_pkg(groups_knowledge)
 importutil.import_modules_in_pkg(groups_resources)
+importutil.import_modules_in_pkg(groups_workflows)


 class HTTPController:
@@ -99,16 +99,23 @@ class BotService:
        # TODO: 检查配置信息格式
        bot_data['uuid'] = str(uuid.uuid4())

-        # bind the most recently updated pipeline if any exist
+        # Set default binding_type if not provided
+        if 'binding_type' not in bot_data:
+            bot_data['binding_type'] = 'pipeline'
+
+        # checkout the default pipeline (for backward compatibility)
        result = await self.ap.persistence_mgr.execute_async(
-            sqlalchemy.select(persistence_pipeline.LegacyPipeline)
-            .order_by(persistence_pipeline.LegacyPipeline.updated_at.desc())
-            .limit(1)
+            sqlalchemy.select(persistence_pipeline.LegacyPipeline).where(
+                persistence_pipeline.LegacyPipeline.is_default == True
+            )
        )
        pipeline = result.first()
        if pipeline is not None:
            bot_data['use_pipeline_uuid'] = pipeline.uuid
            bot_data['use_pipeline_name'] = pipeline.name
+            # Also set binding_uuid for new unified binding model
+            if 'binding_uuid' not in bot_data:
+                bot_data['binding_uuid'] = pipeline.uuid

        await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(persistence_bot.Bot).values(bot_data))

@@ -120,26 +127,45 @@ class BotService:

    async def update_bot(self, bot_uuid: str, bot_data: dict) -> None:
        """Update bot"""
-        update_data = bot_data.copy()
+        if 'uuid' in bot_data:
+            del bot_data['uuid']

-        if 'uuid' in update_data:
-            del update_data['uuid']
+        # Handle binding_type and binding_uuid for the new unified binding model
+        # If binding_type is explicitly set to 'workflow', skip pipeline validation
+        binding_type = bot_data.get('binding_type')

-        # set use_pipeline_name
-        if 'use_pipeline_uuid' in update_data:
+        # set use_pipeline_name (for backward compatibility with 'pipeline' binding_type)
+        # Only validate pipeline when binding_type is 'pipeline' or not set (default to pipeline)
+        if 'use_pipeline_uuid' in bot_data and binding_type != 'workflow':
            result = await self.ap.persistence_mgr.execute_async(
                sqlalchemy.select(persistence_pipeline.LegacyPipeline).where(
-                    persistence_pipeline.LegacyPipeline.uuid == update_data['use_pipeline_uuid']
+                    persistence_pipeline.LegacyPipeline.uuid == bot_data['use_pipeline_uuid']
                )
            )
            pipeline = result.first()
            if pipeline is not None:
-                update_data['use_pipeline_name'] = pipeline.name
+                bot_data['use_pipeline_name'] = pipeline.name
+                # Also sync to binding_uuid if binding_type is 'pipeline' or not set
+                if binding_type is None or binding_type == 'pipeline':
+                    bot_data['binding_uuid'] = bot_data['use_pipeline_uuid']
+                    bot_data['binding_type'] = 'pipeline'
            else:
-                raise Exception('Pipeline not found')
+                # Only raise error if binding_type is explicitly 'pipeline' or not set
+                if binding_type is None or binding_type == 'pipeline':
+                    raise Exception('Pipeline not found')
+                # If binding_type is 'workflow', just clear the use_pipeline_uuid
+                bot_data['use_pipeline_uuid'] = None
+                bot_data['use_pipeline_name'] = None
+
+        # If binding_uuid is set directly (for workflow), clear pipeline fields
+        if 'binding_uuid' in bot_data and binding_type == 'workflow':
+            # For workflow binding, clear pipeline-related fields to avoid confusion
+            bot_data['binding_type'] = 'workflow'
+            bot_data['use_pipeline_uuid'] = None
+            bot_data['use_pipeline_name'] = None

        await self.ap.persistence_mgr.execute_async(
-            sqlalchemy.update(persistence_bot.Bot).values(update_data).where(persistence_bot.Bot.uuid == bot_uuid)
+            sqlalchemy.update(persistence_bot.Bot).values(bot_data).where(persistence_bot.Bot.uuid == bot_uuid)
        )
        await self.ap.platform_mgr.remove_bot(bot_uuid)

@@ -199,3 +225,35 @@ class BotService:

        # Send message via adapter
        await runtime_bot.adapter.send_message(target_type, str(target_id), message_chain)
+
+    # ============ Bot Admins ============
+
+    async def get_bot_admins(self, bot_uuid: str) -> list[dict]:
+        from ....entity.persistence import bot as persistence_bot
+
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_bot.BotAdmin).where(persistence_bot.BotAdmin.bot_uuid == bot_uuid)
+        )
+        return [{'id': r.id, 'launcher_type': r.launcher_type, 'launcher_id': r.launcher_id} for r in result.all()]
+
+    async def add_bot_admin(self, bot_uuid: str, launcher_type: str, launcher_id: str) -> int:
+        from ....entity.persistence import bot as persistence_bot
+
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.insert(persistence_bot.BotAdmin).values(
+                bot_uuid=bot_uuid,
+                launcher_type=launcher_type,
+                launcher_id=launcher_id,
+            )
+        )
+        return result.inserted_primary_key[0]
+
+    async def delete_bot_admin(self, bot_uuid: str, admin_id: int) -> None:
+        from ....entity.persistence import bot as persistence_bot
+
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.delete(persistence_bot.BotAdmin).where(
+                persistence_bot.BotAdmin.bot_uuid == bot_uuid,
+                persistence_bot.BotAdmin.id == admin_id,
+            )
+        )
@@ -136,6 +136,32 @@ class MCPService:
            if server_name in self.ap.tool_mgr.mcp_tool_loader.sessions:
                await self.ap.tool_mgr.mcp_tool_loader.remove_mcp_server(server_name)

+    async def get_mcp_server_resources(self, server_name: str) -> list[dict]:
+        """Get resources from a specific MCP server."""
+        return await self.ap.tool_mgr.mcp_tool_loader.get_resources(server_name)
+
+    async def get_mcp_server_resource_templates(self, server_name: str) -> list[dict]:
+        """Get resource templates from a specific MCP server."""
+        return await self.ap.tool_mgr.mcp_tool_loader.get_resource_templates(server_name)
+
+    async def read_mcp_server_resource_envelope(
+        self,
+        server_name: str,
+        uri: str,
+        *,
+        max_bytes: int | None = None,
+        include_blob: bool = False,
+    ) -> dict:
+        """Read a resource from a specific MCP server with metadata."""
+        kwargs = {'include_blob': include_blob, 'source': 'ui_preview'}
+        if max_bytes is not None:
+            kwargs['max_bytes'] = max_bytes
+        return await self.ap.tool_mgr.mcp_tool_loader.read_resource_envelope(server_name, uri, **kwargs)
+
+    async def read_mcp_server_resource(self, server_name: str, uri: str) -> list[dict]:
+        """Read a resource from a specific MCP server."""
+        return await self.ap.tool_mgr.mcp_tool_loader.read_resource(server_name, uri)
+
    async def test_mcp_server(self, server_name: str, server_data: dict) -> int:
        """测试 MCP 服务器连接并返回任务 ID"""

@@ -73,6 +73,20 @@ class PipelineService:

        return self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)

+    async def get_pipeline_by_name(self, pipeline_name: str) -> dict | None:
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_pipeline.LegacyPipeline).where(
+                persistence_pipeline.LegacyPipeline.name == pipeline_name
+            )
+        )
+
+        pipeline = result.first()
+
+        if pipeline is None:
+            return None
+
+        return self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
+
    async def create_pipeline(self, pipeline_data: dict, default: bool = False) -> str:
        from ....utils import paths as path_utils

@@ -100,6 +114,8 @@ class PipelineService:
                'enable_all_mcp_servers': True,
                'plugins': [],
                'mcp_servers': [],
+                'mcp_resources': [],
+                'mcp_resource_agent_read_enabled': True,
            }

        await self.ap.persistence_mgr.execute_async(
@@ -193,6 +209,8 @@ class PipelineService:
                    'enable_all_mcp_servers': True,
                    'plugins': [],
                    'mcp_servers': [],
+                    'mcp_resources': [],
+                    'mcp_resource_agent_read_enabled': True,
                }
            ),
        }
@@ -217,6 +235,8 @@ class PipelineService:
        enable_all_mcp_servers: bool = True,
        bound_skills: list[str] = None,
        enable_all_skills: bool = True,
+        bound_mcp_resources: list[dict] = None,
+        mcp_resource_agent_read_enabled: bool | None = None,
    ) -> None:
        """Update the bound plugins and MCP servers for a pipeline"""
        # Get current pipeline
@@ -236,10 +256,14 @@ class PipelineService:
        extensions_preferences['enable_all_mcp_servers'] = enable_all_mcp_servers
        extensions_preferences['enable_all_skills'] = enable_all_skills
        extensions_preferences['plugins'] = bound_plugins
+        if mcp_resource_agent_read_enabled is not None:
+            extensions_preferences['mcp_resource_agent_read_enabled'] = mcp_resource_agent_read_enabled
        if bound_mcp_servers is not None:
            extensions_preferences['mcp_servers'] = bound_mcp_servers
        if bound_skills is not None:
            extensions_preferences['skills'] = bound_skills
+        if bound_mcp_resources is not None:
+            extensions_preferences['mcp_resources'] = bound_mcp_resources

        await self.ap.persistence_mgr.execute_async(
            sqlalchemy.update(persistence_pipeline.LegacyPipeline)
@@ -20,6 +20,15 @@ class UserService:
    def __init__(self, ap: app.Application) -> None:
        self.ap = ap
        self._create_user_lock = asyncio.Lock()
+        self._password_hash_lock = asyncio.Semaphore(1)
+
+    async def _hash_password(self, password: str) -> str:
+        async with self._password_hash_lock:
+            return await asyncio.to_thread(argon2.PasswordHasher().hash, password)
+
+    async def _verify_password(self, hashed_password: str, password: str) -> None:
+        async with self._password_hash_lock:
+            await asyncio.to_thread(argon2.PasswordHasher().verify, hashed_password, password)

    async def is_initialized(self) -> bool:
        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(user.User).limit(1))
@@ -28,9 +37,7 @@ class UserService:
        return result_list is not None and len(result_list) > 0

    async def create_user(self, user_email: str, password: str) -> None:
-        ph = argon2.PasswordHasher()
-
-        hashed_password = ph.hash(password)
+        hashed_password = await self._hash_password(password)

        await self.ap.persistence_mgr.execute_async(
            sqlalchemy.insert(user.User).values(user=user_email, password=hashed_password, account_type='local')
@@ -69,9 +76,7 @@ class UserService:
        if not user_obj.password:
            raise ValueError('请使用 Space 账户登录')

-        ph = argon2.PasswordHasher()
-
-        ph.verify(user_obj.password, password)
+        await self._verify_password(user_obj.password, password)

        return await self.generate_jwt_token(user_email)

@@ -93,17 +98,13 @@ class UserService:
        return jwt.decode(token, jwt_secret, algorithms=['HS256'])['user']

    async def reset_password(self, user_email: str, new_password: str) -> None:
-        ph = argon2.PasswordHasher()
-
-        hashed_password = ph.hash(new_password)
+        hashed_password = await self._hash_password(new_password)

        await self.ap.persistence_mgr.execute_async(
            sqlalchemy.update(user.User).where(user.User.user == user_email).values(password=hashed_password)
        )

    async def change_password(self, user_email: str, current_password: str, new_password: str) -> None:
-        ph = argon2.PasswordHasher()
-
        user_obj = await self.get_user_by_email(user_email)
        if user_obj is None:
            raise ValueError('User not found')
@@ -111,9 +112,9 @@ class UserService:
        if not user_obj.password:
            raise ValueError('No local password set, please set a password first')

-        ph.verify(user_obj.password, current_password)
+        await self._verify_password(user_obj.password, current_password)

-        hashed_password = ph.hash(new_password)
+        hashed_password = await self._hash_password(new_password)

        await self.ap.persistence_mgr.execute_async(
            sqlalchemy.update(user.User).where(user.User.user == user_email).values(password=hashed_password)
@@ -232,7 +233,6 @@ class UserService:

    async def set_password(self, user_email: str, new_password: str, current_password: str | None = None) -> None:
        """Set or change password for a user"""
-        ph = argon2.PasswordHasher()
        user_obj = await self.get_user_by_email(user_email)

        if user_obj is None:
@@ -243,9 +243,9 @@ class UserService:
        if has_password:
            if not current_password:
                raise ValueError('Current password is required')
-            ph.verify(user_obj.password, current_password)
+            await self._verify_password(user_obj.password, current_password)

-        hashed_password = ph.hash(new_password)
+        hashed_password = await self._hash_password(new_password)
        await self.ap.persistence_mgr.execute_async(
            sqlalchemy.update(user.User).where(user.User.user == user_email).values(password=hashed_password)
        )
@@ -82,7 +82,6 @@ class BoxService:
        return self._enabled

    async def initialize(self):
-        self._ensure_default_workspace()
        if not self._enabled:
            # Disabled by config: do NOT connect to a remote runtime, do NOT
            # fork a stdio subprocess. Every consumer of box_service should
@@ -99,6 +98,7 @@ class BoxService:
                await self._runtime_connector.initialize()
            else:
                await self.client.initialize()
+            self._ensure_default_workspace()
            self._available = True
            self._connector_error = ''
            self.ap.logger.info(
@@ -1152,6 +1152,9 @@ class BoxService:
        if self.default_workspace is None:
            return

+        if not self.shares_filesystem_with_box:
+            return
+
        if os.path.isdir(self.default_workspace):
            return

@@ -1176,7 +1179,7 @@ class BoxService:
            return

        host_path = os.path.realpath(spec.host_path)
-        if not os.path.isdir(host_path):
+        if self.shares_filesystem_with_box and not os.path.isdir(host_path):
            raise BoxValidationError('host_path must point to an existing directory on the host')

        if not self.allowed_mount_roots:
@@ -84,7 +84,17 @@ class CommandManager:

        privilege = 1

-        if f'{query.launcher_type.value}_{query.launcher_id}' in self.ap.instance_config.data['admins']:
+        import sqlalchemy as _sa
+        from ..entity.persistence.bot import BotAdmin as _BotAdmin
+
+        _admins = await self.ap.persistence_mgr.execute_async(
+            _sa.select(_BotAdmin).where(
+                _BotAdmin.bot_uuid == (query.bot_uuid or ''),
+                _BotAdmin.launcher_type == query.launcher_type.value,
+                _BotAdmin.launcher_id == str(query.launcher_id),
+            )
+        )
+        if _admins.first() is not None:
            privilege = 2

        ctx = command_context.ExecuteContext(
@@ -32,6 +32,7 @@ from ..api.http.service import mcp as mcp_service
 from ..api.http.service import apikey as apikey_service
 from ..api.http.service import webhook as webhook_service
 from ..api.http.service import monitoring as monitoring_service
+from ..api.http.service import workflow as workflow_service
 from ..api.http.service import skill as skill_service
 from ..api.http.service import maintenance as maintenance_service
 from ..discover import engine as discover_engine
@@ -153,6 +154,8 @@ class Application:

    webhook_service: webhook_service.WebhookService = None

+    workflow_service: workflow_service.WorkflowService = None
+
    telemetry: telemetry_module.TelemetryManager = None

    survey: survey_module.SurveyManager = None
@@ -255,6 +258,22 @@ class Application:
                    scopes=[core_entities.LifecycleControlScope.APPLICATION],
                )

+            async def workflow_execution_cleanup_loop():
+                check_interval_seconds = 60
+                while True:
+                    try:
+                        cancelled = await self.workflow_service.cleanup_stale_executions()
+                        if cancelled > 0:
+                            self.logger.info(f'Workflow execution auto-cleanup: cancelled {cancelled} stale executions')
+                    except Exception as e:
+                        self.logger.warning(f'Workflow execution auto-cleanup error: {e}')
+                    await asyncio.sleep(check_interval_seconds)
+
+            self.task_mgr.create_task(
+                workflow_execution_cleanup_loop(),
+                name='workflow-execution-cleanup',
+                scopes=[core_entities.LifecycleControlScope.APPLICATION],
+            )
            # Start storage/log maintenance task if enabled
            storage_cleanup_cfg = self.instance_config.data.get('storage', {}).get('cleanup', {})
            if storage_cleanup_cfg.get('enabled', True) and self.maintenance_service is not None:
@@ -29,6 +29,7 @@ from ...api.http.service import mcp as mcp_service
 from ...api.http.service import apikey as apikey_service
 from ...api.http.service import webhook as webhook_service
 from ...api.http.service import monitoring as monitoring_service
+from ...api.http.service import workflow as workflow_service
 from ...api.http.service import skill as skill_service
 from ...skill import manager as skill_mgr
 from ...api.http.service import maintenance as maintenance_service
@@ -89,6 +90,9 @@ class BuildAppStage(stage.BootingStage):
        webhook_service_inst = webhook_service.WebhookService(ap)
        ap.webhook_service = webhook_service_inst

+        workflow_service_inst = workflow_service.WorkflowService(ap)
+        ap.workflow_service = workflow_service_inst
+
        skill_service_inst = skill_service.SkillService(ap)
        ap.skill_service = skill_service_inst

@@ -231,3 +231,34 @@ class LoadConfigStage(stage.BootingStage):
        ap.pipeline_config_meta_safety = await load_resource_yaml_template_data('metadata/pipeline/safety.yaml')
        ap.pipeline_config_meta_ai = await load_resource_yaml_template_data('metadata/pipeline/ai.yaml')
        ap.pipeline_config_meta_output = await load_resource_yaml_template_data('metadata/pipeline/output.yaml')
+
+        # Load workflow node metadata from YAML files. YAML is the source of
+        # truth for workflow editor metadata; Python classes provide execution
+        # logic and are bound through the registry.
+        from langbot.pkg.workflow.metadata import NodeMetadataLoader
+        from langbot.pkg.workflow.registry import NodeTypeRegistry
+
+        workflow_metadata_loader = NodeMetadataLoader()
+        workflow_node_count = await workflow_metadata_loader.load_core_metadata()
+        ap.workflow_node_configs = workflow_metadata_loader.get_all_metadata()
+        ap.workflow_node_metadata_loader = workflow_metadata_loader
+
+        workflow_registry = NodeTypeRegistry.instance()
+        for node_config in ap.workflow_node_configs.values():
+            workflow_registry.register_metadata(node_config, source=node_config.get('_source', 'core'))
+
+        # Auto-discover and register workflow nodes using discovery engine
+        if hasattr(ap, 'discover') and ap.discover is not None:
+            workflow_registry.discover_nodes(ap.discover)
+
+        workflow_load_errors = workflow_metadata_loader.get_load_errors()
+        if workflow_load_errors:
+            print(f'Workflow node metadata load errors: {len(workflow_load_errors)}')
+            for error in workflow_load_errors:
+                print(f"  - {error.get('file')}: {error.get('error')}")
+
+        print(
+            f'Loaded {workflow_node_count} workflow node metadata files; '
+            f'registered {workflow_registry.metadata_count()} metadata definitions, '
+            f'{workflow_registry.count()} node types'
+        )
@@ -304,3 +304,65 @@ class ComponentDiscoveryEngine:
            if component.kind == kind:
                result.append(component)
        return result
+
+    def discover_workflow_nodes(self, nodes_dir: str) -> typing.List[typing.Type]:
+        """Discover workflow node classes from a directory of Python modules.
+        
+        Scans all .py files in the given directory, imports them, and collects
+        classes that are subclasses of WorkflowNode.
+        
+        Args:
+            nodes_dir: Directory path like 'pkg/workflow/nodes/'
+            
+        Returns:
+            List of WorkflowNode subclasses found
+        """
+        from langbot.pkg.workflow.node import WorkflowNode
+        
+        node_classes: typing.List[typing.Type[WorkflowNode]] = []
+        
+        # Normalize path
+        if nodes_dir.endswith('/'):
+            nodes_dir = nodes_dir[:-1]
+        
+        # Import the nodes package to trigger all module imports
+        module_path = nodes_dir.replace('/', '.').replace('\\', '.')
+        package_path = module_path
+        
+        try:
+            # Import the package __init__ to trigger submodule imports
+            importlib.import_module(f'langbot.{package_path}')
+        except ImportError:
+            self.ap.logger.warning(f'Failed to import workflow nodes package: langbot.{package_path}')
+        
+        # Since workflow/__init__.py is empty, explicitly import all .py files in the nodes directory
+        import os
+        # engine.py is in langbot/pkg/discover/, nodes are in langbot/pkg/workflow/nodes/
+        nodes_abs_path = os.path.abspath(os.path.join(os.path.dirname(__file__), '..', 'workflow', 'nodes'))
+        if os.path.isdir(nodes_abs_path):
+            for filename in os.listdir(nodes_abs_path):
+                if filename.endswith('.py') and not filename.startswith('_'):
+                    module_name = filename[:-3]
+                    try:
+                        importlib.import_module(f'langbot.{package_path}.{module_name}')
+                    except ImportError as e:
+                        self.ap.logger.warning(f'Failed to import workflow node module: {module_name}: {e}')
+        
+        # Now collect all WorkflowNode subclasses from sys.modules
+        import sys
+        prefix = f'langbot.{package_path}.'
+        for mod_name, mod in sys.modules.items():
+            if mod_name.startswith(prefix) and mod is not None:
+                for attr_name in dir(mod):
+                    attr = getattr(mod, attr_name)
+                    if (
+                        isinstance(attr, type)
+                        and issubclass(attr, WorkflowNode)
+                        and attr is not WorkflowNode
+                        and hasattr(attr, 'type_name')
+                        and attr.type_name
+                    ):
+                        if attr not in node_classes:
+                            node_classes.append(attr)
+        
+        return node_classes
@@ -3,6 +3,20 @@ import sqlalchemy
 from .base import Base


+class BotAdmin(Base):
+    """Bot admin — a launcher that has admin privilege for a specific bot's commands"""
+
+    __tablename__ = 'bot_admins'
+
+    id = sqlalchemy.Column(sqlalchemy.Integer, primary_key=True, autoincrement=True)
+    bot_uuid = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    launcher_type = sqlalchemy.Column(sqlalchemy.String(64), nullable=False)
+    launcher_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    created_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, server_default=sqlalchemy.func.now())
+
+    __table_args__ = (sqlalchemy.UniqueConstraint('bot_uuid', 'launcher_type', 'launcher_id', name='uq_bot_admin'),)
+
+
 class Bot(Base):
    """Bot"""

@@ -17,6 +31,13 @@ class Bot(Base):
    use_pipeline_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
    use_pipeline_uuid = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
    pipeline_routing_rules = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, server_default='[]')
+
+    # New unified binding fields
+    # binding_type: 'pipeline' or 'workflow'
+    binding_type = sqlalchemy.Column(sqlalchemy.String(32), nullable=False, server_default='pipeline')
+    # binding_uuid: UUID of the bound Pipeline or Workflow
+    binding_uuid = sqlalchemy.Column(sqlalchemy.String(64), nullable=True)
+
    created_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, server_default=sqlalchemy.func.now())
    updated_at = sqlalchemy.Column(
        sqlalchemy.DateTime,
@@ -26,7 +26,14 @@ class LegacyPipeline(Base):
    extensions_preferences = sqlalchemy.Column(
        sqlalchemy.JSON,
        nullable=False,
-        default={'enable_all_plugins': True, 'enable_all_mcp_servers': True, 'plugins': [], 'mcp_servers': []},
+        default={
+            'enable_all_plugins': True,
+            'enable_all_mcp_servers': True,
+            'plugins': [],
+            'mcp_servers': [],
+            'mcp_resources': [],
+            'mcp_resource_agent_read_enabled': True,
+        },
    )


@@ -0,0 +1,126 @@
+"""Workflow persistence entities"""
+
+import sqlalchemy
+
+from .base import Base
+
+
+class Workflow(Base):
+    """Workflow definition"""
+
+    __tablename__ = 'workflows'
+
+    uuid = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True, unique=True)
+    name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    description = sqlalchemy.Column(sqlalchemy.Text, nullable=True)
+    emoji = sqlalchemy.Column(sqlalchemy.String(10), nullable=True, default='🔄')
+    version = sqlalchemy.Column(sqlalchemy.Integer, nullable=False, default=1)
+    is_enabled = sqlalchemy.Column(sqlalchemy.Boolean, nullable=False, default=True)
+
+    # Workflow definition stored as JSON
+    # Contains: nodes, edges, variables, settings
+    definition = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default={})
+
+    # Global config (inherited from Pipeline capabilities)
+    # Contains: safety, output configs
+    global_config = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default={})
+
+    # Extensions preferences (same as Pipeline)
+    extensions_preferences = sqlalchemy.Column(
+        sqlalchemy.JSON,
+        nullable=False,
+        default={'enable_all_plugins': True, 'enable_all_mcp_servers': True, 'plugins': [], 'mcp_servers': []},
+    )
+
+    created_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, server_default=sqlalchemy.func.now())
+    updated_at = sqlalchemy.Column(
+        sqlalchemy.DateTime,
+        nullable=False,
+        server_default=sqlalchemy.func.now(),
+        onupdate=sqlalchemy.func.now(),
+    )
+
+
+class WorkflowVersion(Base):
+    """Workflow version history"""
+
+    __tablename__ = 'workflow_versions'
+
+    id = sqlalchemy.Column(sqlalchemy.Integer, primary_key=True, autoincrement=True)
+    workflow_uuid = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, index=True)
+    version = sqlalchemy.Column(sqlalchemy.Integer, nullable=False)
+    definition = sqlalchemy.Column(sqlalchemy.JSON, nullable=False)
+    global_config = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default={})
+    created_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, server_default=sqlalchemy.func.now())
+    created_by = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
+
+    __table_args__ = (sqlalchemy.UniqueConstraint('workflow_uuid', 'version', name='uq_workflow_version'),)
+
+
+class WorkflowTrigger(Base):
+    """Workflow trigger configuration"""
+
+    __tablename__ = 'workflow_triggers'
+
+    uuid = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True, unique=True)
+    workflow_uuid = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, index=True)
+    type = sqlalchemy.Column(sqlalchemy.String(50), nullable=False)  # message, cron, event, webhook
+    config = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default={})
+    is_enabled = sqlalchemy.Column(sqlalchemy.Boolean, nullable=False, default=True)
+    priority = sqlalchemy.Column(sqlalchemy.Integer, nullable=False, default=0)
+    created_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, server_default=sqlalchemy.func.now())
+    updated_at = sqlalchemy.Column(
+        sqlalchemy.DateTime,
+        nullable=False,
+        server_default=sqlalchemy.func.now(),
+        onupdate=sqlalchemy.func.now(),
+    )
+
+
+class WorkflowExecution(Base):
+    """Workflow execution record"""
+
+    __tablename__ = 'workflow_executions'
+
+    uuid = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True, unique=True)
+    workflow_uuid = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, index=True)
+    workflow_version = sqlalchemy.Column(sqlalchemy.Integer, nullable=False)
+    status = sqlalchemy.Column(sqlalchemy.String(20), nullable=False)  # pending, running, completed, failed, cancelled
+    trigger_type = sqlalchemy.Column(sqlalchemy.String(50), nullable=True)
+    trigger_data = sqlalchemy.Column(sqlalchemy.JSON, nullable=True)
+    variables = sqlalchemy.Column(sqlalchemy.JSON, nullable=True)
+    start_time = sqlalchemy.Column(sqlalchemy.DateTime, nullable=True)
+    end_time = sqlalchemy.Column(sqlalchemy.DateTime, nullable=True)
+    error = sqlalchemy.Column(sqlalchemy.Text, nullable=True)
+    created_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, server_default=sqlalchemy.func.now())
+
+
+class WorkflowNodeExecution(Base):
+    """Workflow node execution record"""
+
+    __tablename__ = 'workflow_node_executions'
+
+    id = sqlalchemy.Column(sqlalchemy.Integer, primary_key=True, autoincrement=True)
+    execution_uuid = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, index=True)
+    node_id = sqlalchemy.Column(sqlalchemy.String(100), nullable=False)
+    node_type = sqlalchemy.Column(sqlalchemy.String(50), nullable=False)
+    status = sqlalchemy.Column(sqlalchemy.String(20), nullable=False)  # pending, running, completed, failed, skipped
+    inputs = sqlalchemy.Column(sqlalchemy.JSON, nullable=True)
+    outputs = sqlalchemy.Column(sqlalchemy.JSON, nullable=True)
+    start_time = sqlalchemy.Column(sqlalchemy.DateTime, nullable=True)
+    end_time = sqlalchemy.Column(sqlalchemy.DateTime, nullable=True)
+    error = sqlalchemy.Column(sqlalchemy.Text, nullable=True)
+    retry_count = sqlalchemy.Column(sqlalchemy.Integer, nullable=False, default=0)
+
+
+class ScheduledJob(Base):
+    """Scheduled job for cron triggers"""
+
+    __tablename__ = 'workflow_scheduled_jobs'
+
+    uuid = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True, unique=True)
+    trigger_uuid = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, index=True)
+    cron_expression = sqlalchemy.Column(sqlalchemy.String(100), nullable=True)
+    next_run_time = sqlalchemy.Column(sqlalchemy.DateTime, nullable=True)
+    last_run_time = sqlalchemy.Column(sqlalchemy.DateTime, nullable=True)
+    is_enabled = sqlalchemy.Column(sqlalchemy.Boolean, nullable=False, default=True)
@@ -0,0 +1,84 @@
+"""add bot_admins table and migrate config admins
+
+Revision ID: 0007_add_bot_admins
+Revises: 0006_normalize_mcp_remote_mode
+Create Date: 2026-06-26
+"""
+
+import sqlalchemy as sa
+from alembic import op
+
+revision = '0007_add_bot_admins'
+down_revision = '0006_normalize_mcp_remote_mode'
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    conn = op.get_bind()
+    if 'bot_admins' in sa.inspect(conn).get_table_names():
+        return
+    op.create_table(
+        'bot_admins',
+        sa.Column('id', sa.Integer, primary_key=True, autoincrement=True),
+        sa.Column('bot_uuid', sa.String(255), nullable=False),
+        sa.Column('launcher_type', sa.String(64), nullable=False),
+        sa.Column('launcher_id', sa.String(255), nullable=False),
+        sa.Column('created_at', sa.DateTime, nullable=False, server_default=sa.func.now()),
+        sa.UniqueConstraint('bot_uuid', 'launcher_type', 'launcher_id', name='uq_bot_admin'),
+    )
+
+    # Migrate old config-based admins into the first bot (best-effort)
+    inspector = sa.inspect(conn)
+    tables = inspector.get_table_names()
+
+    if 'bots' not in tables:
+        return
+
+    # Read the first bot uuid
+    row = conn.execute(sa.text('SELECT uuid FROM bots ORDER BY created_at LIMIT 1')).first()
+    if row is None:
+        return
+    first_bot_uuid = row[0]
+
+    # Read instance_config metadata key that holds the admins list
+    if 'metadata' not in tables:
+        return
+    meta_row = conn.execute(sa.text("SELECT value FROM metadata WHERE key = 'instance_config'")).first()
+    if meta_row is None:
+        return
+
+    import json
+
+    try:
+        cfg = json.loads(meta_row[0])
+    except Exception:
+        return
+
+    admins = cfg.get('admins', [])
+    for entry in admins:
+        parts = entry.split('_', 1)
+        if len(parts) != 2:
+            continue
+        launcher_type, launcher_id = parts
+        try:
+            conn.execute(
+                sa.text(
+                    'INSERT OR IGNORE INTO bot_admins (bot_uuid, launcher_type, launcher_id) VALUES (:bu, :lt, :li)'
+                ),
+                {'bu': first_bot_uuid, 'lt': launcher_type, 'li': launcher_id},
+            )
+        except Exception:
+            pass
+
+    # Remove admins key from stored config
+    if 'admins' in cfg:
+        del cfg['admins']
+        conn.execute(
+            sa.text("UPDATE metadata SET value = :v WHERE key = 'instance_config'"),
+            {'v': json.dumps(cfg)},
+        )
+
+
+def downgrade() -> None:
+    op.drop_table('bot_admins')
@@ -0,0 +1,95 @@
+"""add mcp resource preferences to pipelines
+
+Revision ID: 0008_mcp_resource_prefs
+Revises: 0007_add_bot_admins
+Create Date: 2026-06-30
+"""
+
+from __future__ import annotations
+
+import json
+from typing import Any
+
+import sqlalchemy as sa
+from alembic import op
+
+revision = '0008_mcp_resource_prefs'
+down_revision = '0007_add_bot_admins'
+branch_labels = None
+depends_on = None
+
+
+_PIPELINE_TABLE = sa.table(
+    'legacy_pipelines',
+    sa.column('uuid', sa.String(255)),
+    sa.column('extensions_preferences', sa.JSON()),
+)
+
+
+def _has_extensions_preferences_table(conn: sa.Connection) -> bool:
+    inspector = sa.inspect(conn)
+    if 'legacy_pipelines' not in inspector.get_table_names():
+        return False
+    columns = {column['name'] for column in inspector.get_columns('legacy_pipelines')}
+    return 'extensions_preferences' in columns
+
+
+def _decode_preferences(value: Any) -> dict[str, Any]:
+    if value is None:
+        return {}
+    if isinstance(value, dict):
+        return dict(value)
+    if isinstance(value, str):
+        try:
+            decoded = json.loads(value)
+        except json.JSONDecodeError:
+            return {}
+        if isinstance(decoded, dict):
+            return decoded
+    return {}
+
+
+def _update_preferences(conn: sa.Connection, uuid: str, preferences: dict[str, Any]) -> None:
+    conn.execute(
+        _PIPELINE_TABLE.update().where(_PIPELINE_TABLE.c.uuid == uuid).values(extensions_preferences=preferences)
+    )
+
+
+def upgrade() -> None:
+    conn = op.get_bind()
+    if not _has_extensions_preferences_table(conn):
+        return
+
+    rows = conn.execute(sa.select(_PIPELINE_TABLE.c.uuid, _PIPELINE_TABLE.c.extensions_preferences)).all()
+    for uuid, raw_preferences in rows:
+        preferences = _decode_preferences(raw_preferences)
+        changed = False
+
+        if 'mcp_resources' not in preferences:
+            preferences['mcp_resources'] = []
+            changed = True
+        if 'mcp_resource_agent_read_enabled' not in preferences:
+            preferences['mcp_resource_agent_read_enabled'] = True
+            changed = True
+
+        if changed:
+            _update_preferences(conn, uuid, preferences)
+
+
+def downgrade() -> None:
+    conn = op.get_bind()
+    if not _has_extensions_preferences_table(conn):
+        return
+
+    rows = conn.execute(sa.select(_PIPELINE_TABLE.c.uuid, _PIPELINE_TABLE.c.extensions_preferences)).all()
+    for uuid, raw_preferences in rows:
+        preferences = _decode_preferences(raw_preferences)
+        changed = False
+
+        for key in ('mcp_resources', 'mcp_resource_agent_read_enabled'):
+            if key in preferences:
+                preferences.pop(key)
+                changed = True
+
+        if changed:
+            _update_preferences(conn, uuid, preferences)
@@ -0,0 +1,207 @@
+"""add workflow tables and bot binding fields
+
+Revision ID: 0009_add_workflow_tables
+Revises: 0008_mcp_resource_prefs
+Create Date: 2026-07-01
+"""
+
+from __future__ import annotations
+
+import sqlalchemy as sa
+from alembic import op
+
+revision = '0009_add_workflow_tables'
+down_revision = '0008_mcp_resource_prefs'
+branch_labels = None
+depends_on = None
+
+
+def _table_exists(conn: sa.Connection, table_name: str) -> bool:
+    return table_name in sa.inspect(conn).get_table_names()
+
+
+def _has_column(conn: sa.Connection, table_name: str, column_name: str) -> bool:
+    if not _table_exists(conn, table_name):
+        return False
+    return column_name in {column['name'] for column in sa.inspect(conn).get_columns(table_name)}
+
+
+def _has_index_for_columns(conn: sa.Connection, table_name: str, columns: tuple[str, ...]) -> bool:
+    if not _table_exists(conn, table_name):
+        return False
+    for index in sa.inspect(conn).get_indexes(table_name):
+        if tuple(index.get('column_names') or ()) == columns:
+            return True
+    return False
+
+
+def _ensure_index(conn: sa.Connection, table_name: str, index_name: str, columns: list[str]) -> None:
+    if _has_index_for_columns(conn, table_name, tuple(columns)):
+        return
+    op.create_index(index_name, table_name, columns)
+
+
+def _create_workflow_tables(conn: sa.Connection) -> None:
+    if not _table_exists(conn, 'workflows'):
+        op.create_table(
+            'workflows',
+            sa.Column('uuid', sa.String(255), primary_key=True),
+            sa.Column('name', sa.String(255), nullable=False),
+            sa.Column('description', sa.Text(), nullable=True),
+            sa.Column('emoji', sa.String(10), nullable=True),
+            sa.Column('version', sa.Integer(), nullable=False, server_default='1'),
+            sa.Column('is_enabled', sa.Boolean(), nullable=False, server_default=sa.true()),
+            sa.Column('definition', sa.JSON(), nullable=False, server_default=sa.text("'{}'")),
+            sa.Column('global_config', sa.JSON(), nullable=False, server_default=sa.text("'{}'")),
+            sa.Column(
+                'extensions_preferences',
+                sa.JSON(),
+                nullable=False,
+                server_default=sa.text(
+                    '\'{"enable_all_plugins": true, "enable_all_mcp_servers": true, "plugins": [], "mcp_servers": []}\''
+                ),
+            ),
+            sa.Column('created_at', sa.DateTime(), nullable=False, server_default=sa.func.now()),
+            sa.Column('updated_at', sa.DateTime(), nullable=False, server_default=sa.func.now()),
+        )
+
+    if not _table_exists(conn, 'workflow_versions'):
+        op.create_table(
+            'workflow_versions',
+            sa.Column('id', sa.Integer(), primary_key=True, autoincrement=True),
+            sa.Column('workflow_uuid', sa.String(255), nullable=False),
+            sa.Column('version', sa.Integer(), nullable=False),
+            sa.Column('definition', sa.JSON(), nullable=False),
+            sa.Column('global_config', sa.JSON(), nullable=False, server_default=sa.text("'{}'")),
+            sa.Column('created_at', sa.DateTime(), nullable=False, server_default=sa.func.now()),
+            sa.Column('created_by', sa.String(255), nullable=True),
+            sa.UniqueConstraint('workflow_uuid', 'version', name='uq_workflow_version'),
+        )
+
+    if not _table_exists(conn, 'workflow_triggers'):
+        op.create_table(
+            'workflow_triggers',
+            sa.Column('uuid', sa.String(255), primary_key=True),
+            sa.Column('workflow_uuid', sa.String(255), nullable=False),
+            sa.Column('type', sa.String(50), nullable=False),
+            sa.Column('config', sa.JSON(), nullable=False, server_default=sa.text("'{}'")),
+            sa.Column('is_enabled', sa.Boolean(), nullable=False, server_default=sa.true()),
+            sa.Column('priority', sa.Integer(), nullable=False, server_default='0'),
+            sa.Column('created_at', sa.DateTime(), nullable=False, server_default=sa.func.now()),
+            sa.Column('updated_at', sa.DateTime(), nullable=False, server_default=sa.func.now()),
+        )
+
+    if not _table_exists(conn, 'workflow_executions'):
+        op.create_table(
+            'workflow_executions',
+            sa.Column('uuid', sa.String(255), primary_key=True),
+            sa.Column('workflow_uuid', sa.String(255), nullable=False),
+            sa.Column('workflow_version', sa.Integer(), nullable=False),
+            sa.Column('status', sa.String(20), nullable=False),
+            sa.Column('trigger_type', sa.String(50), nullable=True),
+            sa.Column('trigger_data', sa.JSON(), nullable=True),
+            sa.Column('variables', sa.JSON(), nullable=True),
+            sa.Column('start_time', sa.DateTime(), nullable=True),
+            sa.Column('end_time', sa.DateTime(), nullable=True),
+            sa.Column('error', sa.Text(), nullable=True),
+            sa.Column('created_at', sa.DateTime(), nullable=False, server_default=sa.func.now()),
+        )
+
+    if not _table_exists(conn, 'workflow_node_executions'):
+        op.create_table(
+            'workflow_node_executions',
+            sa.Column('id', sa.Integer(), primary_key=True, autoincrement=True),
+            sa.Column('execution_uuid', sa.String(255), nullable=False),
+            sa.Column('node_id', sa.String(100), nullable=False),
+            sa.Column('node_type', sa.String(50), nullable=False),
+            sa.Column('status', sa.String(20), nullable=False),
+            sa.Column('inputs', sa.JSON(), nullable=True),
+            sa.Column('outputs', sa.JSON(), nullable=True),
+            sa.Column('start_time', sa.DateTime(), nullable=True),
+            sa.Column('end_time', sa.DateTime(), nullable=True),
+            sa.Column('error', sa.Text(), nullable=True),
+            sa.Column('retry_count', sa.Integer(), nullable=False, server_default='0'),
+        )
+
+    if not _table_exists(conn, 'workflow_scheduled_jobs'):
+        op.create_table(
+            'workflow_scheduled_jobs',
+            sa.Column('uuid', sa.String(255), primary_key=True),
+            sa.Column('trigger_uuid', sa.String(255), nullable=False),
+            sa.Column('cron_expression', sa.String(100), nullable=True),
+            sa.Column('next_run_time', sa.DateTime(), nullable=True),
+            sa.Column('last_run_time', sa.DateTime(), nullable=True),
+            sa.Column('is_enabled', sa.Boolean(), nullable=False, server_default=sa.true()),
+        )
+
+    _ensure_index(conn, 'workflow_versions', 'ix_workflow_versions_workflow_uuid', ['workflow_uuid'])
+    _ensure_index(conn, 'workflow_triggers', 'ix_workflow_triggers_workflow_uuid', ['workflow_uuid'])
+    _ensure_index(conn, 'workflow_executions', 'ix_workflow_executions_workflow_uuid', ['workflow_uuid'])
+    _ensure_index(
+        conn,
+        'workflow_node_executions',
+        'ix_workflow_node_executions_execution_uuid',
+        ['execution_uuid'],
+    )
+    _ensure_index(conn, 'workflow_scheduled_jobs', 'ix_workflow_scheduled_jobs_trigger_uuid', ['trigger_uuid'])
+
+
+def _add_bot_binding_fields(conn: sa.Connection) -> None:
+    if not _table_exists(conn, 'bots'):
+        return
+
+    if not _has_column(conn, 'bots', 'binding_type'):
+        op.add_column(
+            'bots',
+            sa.Column('binding_type', sa.String(32), nullable=False, server_default='pipeline'),
+        )
+
+    if not _has_column(conn, 'bots', 'binding_uuid'):
+        op.add_column('bots', sa.Column('binding_uuid', sa.String(64), nullable=True))
+
+    conn.execute(
+        sa.text("""
+        UPDATE bots
+        SET binding_uuid = use_pipeline_uuid
+        WHERE use_pipeline_uuid IS NOT NULL
+          AND use_pipeline_uuid != ''
+          AND (binding_uuid IS NULL OR binding_uuid = '')
+        """)
+    )
+    conn.execute(
+        sa.text("""
+        UPDATE bots
+        SET binding_type = 'pipeline'
+        WHERE binding_uuid IS NOT NULL
+          AND binding_uuid != ''
+          AND (binding_type IS NULL OR binding_type = '')
+        """)
+    )
+
+
+def upgrade() -> None:
+    conn = op.get_bind()
+    _create_workflow_tables(conn)
+    _add_bot_binding_fields(conn)
+
+
+def downgrade() -> None:
+    conn = op.get_bind()
+
+    if _has_column(conn, 'bots', 'binding_uuid'):
+        with op.batch_alter_table('bots') as batch_op:
+            batch_op.drop_column('binding_uuid')
+    if _has_column(conn, 'bots', 'binding_type'):
+        with op.batch_alter_table('bots') as batch_op:
+            batch_op.drop_column('binding_type')
+
+    for table_name in (
+        'workflow_scheduled_jobs',
+        'workflow_node_executions',
+        'workflow_executions',
+        'workflow_triggers',
+        'workflow_versions',
+        'workflows',
+    ):
+        if _table_exists(conn, table_name):
+            op.drop_table(table_name)
@@ -32,7 +32,7 @@ class MonitoringHelper:
        """Record the start of query processing, returns message_id"""
        try:
            # Check if session exists, if not, record session start
-            session_id = f'{query.launcher_type}_{query.launcher_id}'
+            session_id = f'{query.launcher_type.value if hasattr(query.launcher_type, "value") else query.launcher_type}_{query.launcher_id}'

            # Get sender name from message event
            sender_name = None
@@ -137,7 +137,7 @@ class MonitoringHelper:
    ):
        """Record bot response message to monitoring"""
        try:
-            session_id = f'{query.launcher_type}_{query.launcher_id}'
+            session_id = f'{query.launcher_type.value if hasattr(query.launcher_type, "value") else query.launcher_type}_{query.launcher_id}'

            # Get sender name from message event
            sender_name = None
@@ -202,7 +202,7 @@ class MonitoringHelper:
    ) -> str:
        """Record query processing error, returns message_id"""
        try:
-            session_id = f'{query.launcher_type}_{query.launcher_id}'
+            session_id = f'{query.launcher_type.value if hasattr(query.launcher_type, "value") else query.launcher_type}_{query.launcher_id}'

            # Get sender name from message event
            sender_name = None
@@ -268,7 +268,7 @@ class MonitoringHelper:
    ):
        """Record LLM call"""
        try:
-            session_id = f'{query.launcher_type}_{query.launcher_id}'
+            session_id = f'{query.launcher_type.value if hasattr(query.launcher_type, "value") else query.launcher_type}_{query.launcher_id}'

            await ap.monitoring_service.record_llm_call(
                bot_id=bot_id,
@@ -13,7 +13,7 @@ import langbot_plugin.api.entities.builtin.platform.message as platform_message
 import langbot_plugin.api.entities.builtin.platform.events as platform_events
 import langbot_plugin.api.entities.events as events
 from ..utils import importutil
-from .config_coercion import coerce_pipeline_config
+from .config import coerce_pipeline_config

 import langbot_plugin.api.entities.builtin.provider.session as provider_session
 import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
@@ -96,6 +96,15 @@ class RuntimePipeline:
        extensions_prefs = pipeline_entity.extensions_preferences or {}
        self.enable_all_plugins = extensions_prefs.get('enable_all_plugins', True)
        self.enable_all_mcp_servers = extensions_prefs.get('enable_all_mcp_servers', True)
+        local_agent_config = (pipeline_entity.config or {}).get('ai', {}).get('local-agent', {})
+        self.mcp_resource_attachments = local_agent_config.get(
+            'mcp-resources',
+            extensions_prefs.get('mcp_resources', []),
+        )
+        self.mcp_resource_agent_read_enabled = local_agent_config.get(
+            'mcp-resource-agent-read-enabled',
+            extensions_prefs.get('mcp_resource_agent_read_enabled', True),
+        )

        if self.enable_all_plugins:
            # None indicates to use all available plugins
@@ -116,6 +125,8 @@ class RuntimePipeline:
        # Store bound plugins and MCP servers in query for filtering
        query.variables['_pipeline_bound_plugins'] = self.bound_plugins
        query.variables['_pipeline_bound_mcp_servers'] = self.bound_mcp_servers
+        query.variables['_pipeline_mcp_resource_attachments'] = self.mcp_resource_attachments
+        query.variables['_pipeline_mcp_resource_agent_read_enabled'] = self.mcp_resource_agent_read_enabled

        # Record query start for monitoring
        try:
@@ -178,7 +189,7 @@ class RuntimePipeline:
                bot_name = query.variables.get('_monitoring_bot_name', 'Unknown')
                pipeline_name = query.variables.get('_monitoring_pipeline_name', 'Unknown')
                message_id = query.variables.get('_monitoring_message_id', '')
-                session_id = f'{query.launcher_type}_{query.launcher_id}'
+                session_id = f'{query.launcher_type.value if hasattr(query.launcher_type, "value") else query.launcher_type}_{query.launcher_id}'

                # Update message status to error
                if message_id:
@@ -284,9 +295,9 @@ class RuntimePipeline:
        # Record query start and store message_id
        message_id = ''
        try:
-            from . import monitoring_helper
+            from . import monitor

-            message_id = await monitoring_helper.MonitoringHelper.record_query_start(
+            message_id = await monitor.MonitoringHelper.record_query_start(
                ap=self.ap,
                query=query,
                bot_id=query.bot_uuid or 'unknown',
@@ -338,7 +349,7 @@ class RuntimePipeline:
            # Record query success only if no error occurred during processing
            if not query.variables.get('_monitoring_has_error', False):
                try:
-                    await monitoring_helper.MonitoringHelper.record_query_success(
+                    await monitor.MonitoringHelper.record_query_success(
                        ap=self.ap,
                        message_id=message_id,
                        query=query,
@@ -348,7 +359,7 @@ class RuntimePipeline:

                # Record bot response message
                try:
-                    await monitoring_helper.MonitoringHelper.record_query_response(
+                    await monitor.MonitoringHelper.record_query_response(
                        ap=self.ap,
                        query=query,
                        bot_id=query.bot_uuid or 'unknown',
@@ -367,9 +378,9 @@ class RuntimePipeline:

            # Record query error
            try:
-                from . import monitoring_helper
+                from . import monitor

-                await monitoring_helper.MonitoringHelper.record_query_error(
+                await monitor.MonitoringHelper.record_query_error(
                    ap=self.ap,
                    query=query,
                    bot_id=query.bot_uuid or 'unknown',
@@ -384,7 +395,8 @@ class RuntimePipeline:

        finally:
            self.ap.logger.debug(f'Query {query.query_id} processed')
-            del self.ap.query_pool.cached_queries[query.query_id]
+            # Use pop with default to avoid KeyError if query was never cached
+            self.ap.query_pool.cached_queries.pop(query.query_id, None)


 class PipelineManager:
@@ -0,0 +1,274 @@
+from __future__ import annotations
+
+import traceback
+import weakref
+from dataclasses import dataclass, field
+from typing import Any
+
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+import langbot_plugin.api.entities.builtin.platform.message as platform_message
+
+
+@dataclass(frozen=True)
+class PluginResponseSource:
+    plugin: dict[str, str]
+    event_name: str | None = None
+    is_approximate: bool = False
+
+
+@dataclass
+class QueryDiagnosticState:
+    pending_by_chain_id: dict[int, list[PluginResponseSource]] = field(default_factory=dict)
+    by_response_index: dict[int, list[PluginResponseSource]] = field(default_factory=dict)
+    finalizer: weakref.finalize | None = None
+
+
+_QUERY_STATES: dict[int, QueryDiagnosticState] = {}
+
+
+def record_plugin_response_source(
+    query: pipeline_query.Query,
+    response_index: int,
+    response_sources: list[dict[str, Any]] | None,
+    emitted_plugins: list[dict[str, Any]] | None = None,
+    event_name: str | None = None,
+) -> None:
+    plugin_sources = _build_plugin_sources(response_sources, emitted_plugins, event_name)
+    if not plugin_sources:
+        return
+    state = _get_or_create_query_state(query)
+    state.by_response_index[response_index] = plugin_sources
+
+
+def record_last_plugin_response_source(
+    query: pipeline_query.Query,
+    response_sources: list[dict[str, Any]] | None,
+    emitted_plugins: list[dict[str, Any]] | None = None,
+    event_name: str | None = None,
+) -> None:
+    record_plugin_response_source(
+        query,
+        len(query.resp_message_chain) - 1,
+        response_sources,
+        emitted_plugins,
+        event_name,
+    )
+
+
+def record_pending_plugin_response_source(
+    query: pipeline_query.Query,
+    message_chain: platform_message.MessageChain,
+    response_sources: list[dict[str, Any]] | None,
+    emitted_plugins: list[dict[str, Any]] | None = None,
+    event_name: str | None = None,
+) -> None:
+    plugin_sources = _build_plugin_sources(response_sources, emitted_plugins, event_name)
+    if not plugin_sources:
+        return
+    state = _get_or_create_query_state(query)
+    state.pending_by_chain_id[id(message_chain)] = plugin_sources
+
+
+def consume_pending_plugin_response_source(
+    query: pipeline_query.Query,
+    message_chain: platform_message.MessageChain,
+    response_index: int,
+) -> None:
+    state = _get_query_state(query)
+    if state is None:
+        return
+    source = state.pending_by_chain_id.pop(id(message_chain), None)
+    if source is None:
+        return
+    state.by_response_index[response_index] = source
+
+
+def clear_response_source(query: pipeline_query.Query, response_index: int) -> None:
+    state = _get_query_state(query)
+    if state is None:
+        return
+    state.by_response_index.pop(response_index, None)
+    _discard_query_state_if_empty(query)
+
+
+async def notify_response_delivery_failure(
+    ap: Any,
+    query: pipeline_query.Query,
+    response_index: int,
+    message_chain: platform_message.MessageChain,
+    error: Exception,
+) -> None:
+    try:
+        plugin_refs = _get_response_sources(query, response_index)
+        if not plugin_refs:
+            return
+        connector = getattr(ap, 'plugin_connector', None)
+        if connector is None or not hasattr(connector, 'notify_plugin_diagnostic'):
+            return
+        for source in plugin_refs:
+            payload = _build_delivery_failure_payload(
+                plugin_ref=source.plugin,
+                event_name=source.event_name,
+                is_approximate=source.is_approximate,
+                query=query,
+                response_index=response_index,
+                message_chain=message_chain,
+                error=error,
+            )
+            try:
+                await connector.notify_plugin_diagnostic(payload)
+            except Exception as diag_error:
+                _debug(ap, f'Plugin diagnostic forwarding failed: {diag_error}')
+    except Exception as diag_error:
+        _debug(ap, f'Plugin diagnostic forwarding skipped: {diag_error}')
+
+
+def get_emitted_plugins(event_ctx: Any) -> list[dict[str, Any]]:
+    emitted_plugins = getattr(event_ctx, '_emitted_plugins', [])
+    return emitted_plugins if isinstance(emitted_plugins, list) else []
+
+
+def get_response_sources(event_ctx: Any) -> list[dict[str, Any]] | None:
+    event_attrs = vars(event_ctx)
+    if '_response_sources' not in event_attrs:
+        return None
+    response_sources = event_attrs['_response_sources']
+    return response_sources if isinstance(response_sources, list) else []
+
+
+def _get_or_create_query_state(query: pipeline_query.Query) -> QueryDiagnosticState:
+    query_key = id(query)
+    state = _QUERY_STATES.get(query_key)
+    if state is not None:
+        return state
+
+    state = QueryDiagnosticState()
+    try:
+        state.finalizer = weakref.finalize(query, _discard_query_state, query_key)
+    except TypeError:
+        state.finalizer = None
+    _QUERY_STATES[query_key] = state
+    return state
+
+
+def _get_query_state(query: pipeline_query.Query) -> QueryDiagnosticState | None:
+    return _QUERY_STATES.get(id(query))
+
+
+def _discard_query_state(query_key: int) -> None:
+    _QUERY_STATES.pop(query_key, None)
+
+
+def _discard_query_state_if_empty(query: pipeline_query.Query) -> None:
+    query_key = id(query)
+    state = _QUERY_STATES.get(query_key)
+    if state is None:
+        return
+    if state.pending_by_chain_id or state.by_response_index:
+        return
+    if state.finalizer is not None:
+        state.finalizer.detach()
+    _discard_query_state(query_key)
+
+
+def _get_response_sources(
+    query: pipeline_query.Query,
+    response_index: int,
+) -> list[PluginResponseSource]:
+    state = _get_query_state(query)
+    if state is None:
+        return []
+    return state.by_response_index.get(response_index, [])
+
+
+def _extract_plugin_ref(plugin: Any) -> dict[str, str] | None:
+    manifest = plugin.get('manifest') if isinstance(plugin, dict) else None
+    metadata = manifest.get('metadata') if isinstance(manifest, dict) else None
+    if not isinstance(metadata, dict):
+        return None
+    author = metadata.get('author')
+    name = metadata.get('name')
+    if not author or not name:
+        return None
+    return {'author': str(author), 'name': str(name)}
+
+
+def _extract_response_source_plugin_ref(source: Any) -> dict[str, str] | None:
+    if not isinstance(source, dict):
+        return None
+    if source.get('kind') != 'reply_message_chain':
+        return None
+    plugin_ref = source.get('plugin')
+    if not isinstance(plugin_ref, dict):
+        return None
+    author = plugin_ref.get('author')
+    name = plugin_ref.get('name')
+    if not author or not name:
+        return None
+    return {'author': str(author), 'name': str(name)}
+
+
+def _build_plugin_sources(
+    response_sources: list[dict[str, Any]] | None,
+    emitted_plugins: list[dict[str, Any]] | None,
+    event_name: str | None,
+) -> list[PluginResponseSource]:
+    if response_sources is not None:
+        plugin_refs = [_extract_response_source_plugin_ref(source) for source in response_sources]
+        return [
+            PluginResponseSource(plugin=plugin, event_name=event_name) for plugin in plugin_refs if plugin is not None
+        ]
+
+    if emitted_plugins:
+        plugin_refs = [_extract_plugin_ref(plugin) for plugin in emitted_plugins]
+        return [
+            PluginResponseSource(plugin=plugin, event_name=event_name, is_approximate=True)
+            for plugin in plugin_refs
+            if plugin is not None
+        ]
+    return []
+
+
+def _debug(ap: Any, message: str) -> None:
+    logger = getattr(ap, 'logger', None)
+    if logger is not None:
+        logger.debug(message)
+
+
+def _build_delivery_failure_payload(
+    plugin_ref: dict[str, str],
+    event_name: str | None,
+    is_approximate: bool,
+    query: pipeline_query.Query,
+    response_index: int,
+    message_chain: platform_message.MessageChain,
+    error: Exception,
+) -> dict[str, Any]:
+    details: dict[str, Any] = {
+        'message_component_types': [component.__class__.__name__ for component in message_chain],
+        'message_preview': str(message_chain)[:200],
+    }
+    if is_approximate:
+        details['attribution_warning'] = (
+            'This diagnostic was delivered to all plugins that handled the event because the '
+            'plugin runtime did not report the exact reply_message_chain source.'
+        )
+
+    return {
+        'level': 'ERROR',
+        'code': 'response_delivery_failed',
+        'message': 'Failed to deliver a plugin-provided response message.',
+        'plugin': plugin_ref,
+        'query': {
+            'query_id': query.query_id,
+            'event_name': event_name or query.message_event.__class__.__name__,
+            'stage': query.current_stage_name or 'SendResponseBackStage',
+            'response_index': response_index,
+        },
+        'details': details,
+        'delivery': {
+            'error_type': error.__class__.__name__,
+            'error_message': str(error),
+            'traceback': traceback.format_exception_only(type(error), error)[-1].strip(),
+        },
+    }
@@ -25,6 +25,21 @@ class PreProcessor(stage.PipelineStage):
        - use_funcs
    """

+    @staticmethod
+    def _filter_selected_tools(
+        tools: list,
+        local_agent_config: dict,
+    ) -> list:
+        if local_agent_config.get('enable-all-tools', True) is not False:
+            return tools
+
+        selected_tools = local_agent_config.get('tools', [])
+        if not isinstance(selected_tools, list):
+            return []
+
+        selected_tool_names = {tool for tool in selected_tools if isinstance(tool, str)}
+        return [tool for tool in tools if tool.name in selected_tool_names]
+
    async def process(
        self,
        query: pipeline_query.Query,
@@ -32,6 +47,7 @@ class PreProcessor(stage.PipelineStage):
    ) -> entities.StageProcessResult:
        """Process"""
        selected_runner = query.pipeline_config['ai']['runner']['runner']
+        local_agent_config = query.pipeline_config.get('ai', {}).get('local-agent', {})
        include_skill_authoring = (
            selected_runner == 'local-agent' and getattr(self.ap, 'skill_service', None) is not None
        )
@@ -43,7 +59,7 @@ class PreProcessor(stage.PipelineStage):
        if selected_runner == 'local-agent':
            # Read model config — new format is { primary: str, fallbacks: [str] },
            # but handle legacy plain string for backward compatibility
-            model_config = query.pipeline_config['ai']['local-agent'].get('model', {})
+            model_config = local_agent_config.get('model', {})
            if isinstance(model_config, str):
                # Legacy format: plain UUID string
                primary_uuid = model_config
@@ -113,11 +129,14 @@ class PreProcessor(stage.PipelineStage):
                    # Get bound plugins and MCP servers for filtering tools
                    bound_plugins = query.variables.get('_pipeline_bound_plugins', None)
                    bound_mcp_servers = query.variables.get('_pipeline_bound_mcp_servers', None)
-                    query.use_funcs = await self.ap.tool_mgr.get_all_tools(
+                    include_mcp_resource_tools = query.variables.get('_pipeline_mcp_resource_agent_read_enabled', True)
+                    all_tools = await self.ap.tool_mgr.get_all_tools(
                        bound_plugins,
                        bound_mcp_servers,
                        include_skill_authoring=include_skill_authoring,
+                        include_mcp_resource_tools=include_mcp_resource_tools,
                    )
+                    query.use_funcs = self._filter_selected_tools(all_tools, local_agent_config)

                    self.ap.logger.debug(f'Bound plugins: {bound_plugins}')
                    self.ap.logger.debug(f'Bound MCP servers: {bound_mcp_servers}')
@@ -128,11 +147,14 @@ class PreProcessor(stage.PipelineStage):
            if not query.use_funcs and query.variables.get('_fallback_model_uuids'):
                bound_plugins = query.variables.get('_pipeline_bound_plugins', None)
                bound_mcp_servers = query.variables.get('_pipeline_bound_mcp_servers', None)
-                query.use_funcs = await self.ap.tool_mgr.get_all_tools(
+                include_mcp_resource_tools = query.variables.get('_pipeline_mcp_resource_agent_read_enabled', True)
+                all_tools = await self.ap.tool_mgr.get_all_tools(
                    bound_plugins,
                    bound_mcp_servers,
                    include_skill_authoring=include_skill_authoring,
+                    include_mcp_resource_tools=include_mcp_resource_tools,
                )
+                query.use_funcs = self._filter_selected_tools(all_tools, local_agent_config)

        sender_name = ''

--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
RockChinQ	59538fd5cd	enforce workflow data edge order	2026-07-02 00:51:01 +08:00
RockChinQ	235b33c335	separate workflow control and data edges	2026-07-01 22:01:06 +08:00
RockChinQ	c588f9dfc1	fix: port workflow schema migration to alembic	2026-07-01 20:42:30 +08:00
RockChinQ	d770de7f7f	Merge remote-tracking branch 'origin/master' into feat/workflow # Conflicts: # pyproject.toml # src/langbot/pkg/api/http/controller/main.py # src/langbot/pkg/core/app.py # src/langbot/pkg/core/stages/build_app.py # src/langbot/pkg/provider/modelmgr/requester.py # uv.lock # web/package-lock.json # web/package.json # web/pnpm-lock.yaml # web/src/app/home/components/dynamic-form/DynamicFormComponent.tsx # web/src/app/home/components/dynamic-form/DynamicFormItemComponent.tsx # web/src/app/home/components/home-sidebar/HomeSidebar.tsx # web/src/app/infra/entities/api/index.ts # web/src/app/infra/http/BackendClient.ts # web/src/i18n/locales/en-US.ts # web/src/i18n/locales/es-ES.ts # web/src/i18n/locales/ja-JP.ts # web/src/i18n/locales/ru-RU.ts # web/src/i18n/locales/th-TH.ts # web/src/i18n/locales/vi-VN.ts # web/src/i18n/locales/zh-Hans.ts # web/src/i18n/locales/zh-Hant.ts # web/src/router.tsx	2026-07-01 20:33:05 +08:00
彼方	cc7a13158e	fix(aiocqhttp): resolve group member metadata (#2298 ) * fix(aiocqhttp): resolve group member metadata * style: ruff format	2026-07-01 20:00:47 +08:00
RockChinQ	7de7c7f714	docs: update Product Hunt badge to featured	2026-06-30 08:23:55 -04:00
Junyan Qin	85923e3d7b	fix(migrations): shorten mcp resource revision id	2026-06-30 19:39:23 +08:00
Junyan Qin	c7c6c5dc51	fix(i18n): add skill tools tooltip translations	2026-06-30 19:37:57 +08:00
Junyan Qin	b056646696	fix(migrations): add mcp resource preferences	2026-06-30 19:36:04 +08:00
advancer-young	096ec1a8ce	feat(mcp): support mcp resources (#2215 ) * feat(mcp): support mcp resources * feat(web): split MCP resources into tab * docs: add MCP resources PR review * feat(mcp): productionize resource support * feat(mcp): scope local agent tools and resources * fix(web): gate space embedding models behind login * fix(web): prevent clipped space model CTA * test: update preproc resource tool expectations * fix(web): expose skill authoring tools in selector --------- Co-authored-by: yang.xiang <yang.xiang@advancegroup.com> Co-authored-by: Hyu <chenhyu@proton.me> Co-authored-by: Junyan Qin <rockchinq@gmail.com>	2026-06-30 19:16:30 +08:00
RockChinQ	2618e06492	docs: update 302.AI referral link to share.302ai.cn	2026-06-30 05:10:17 -04:00
彼方	5c8c0eb17b	test: use package import paths (#2297 )	2026-06-30 10:51:34 +08:00
彼方	ccc51522cf	fix(aiocqhttp): normalize base64 media payloads (#2296 ) * fix(aiocqhttp): normalize image and voice base64 payloads * fix(aiocqhttp): support file messages from base64 payloads * test(aiocqhttp): use package import path	2026-06-30 10:51:09 +08:00
彼方	6a99a83f2d	chore(scripts): mark scripts executable (#2295 )	2026-06-30 10:50:26 +08:00
Hyu	ebab5343cf	fix(i18n): add bots.admins keys to all locale files (#2292 ) Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>	2026-06-27 17:38:30 +08:00
Hyu	b97cc800d3	feat(platform): migrate bot admins from config.yaml to database (#2289 ) * feat(platform): migrate bot admins from config.yaml to database - Add BotAdmin ORM model (bot_admins table) scoped per bot_uuid - Add Alembic migration 0007 to create table and migrate legacy config admins - Remove top-level admins key from config.yaml template - Add GET/POST/DELETE /api/v1/platform/bots/<uuid>/admins endpoints - Update cmdmgr privilege check to query bot_admins table (bot-scoped) - Add BotAdminsPanel frontend component in bot detail sessions tab - Add i18n keys (zh-Hans, en-US) * fix(ci): ruff/prettier format, fix test_importutil assertion * fix(ci): prettier format BackendClient.ts and i18n locales * fix(ci): eslint-prettier fix BackendClient.ts single-param formatting * refactor: move admin management into session monitor, fix session_id enum format - Remove standalone admins tab, replace with BotAdminsDialog in session monitor - Add admin toggle button inline in chat header next to Active status - Add BotAdminsDialog component with useBotAdmins hook - Fix session_id written as LauncherTypes.PERSON_xxx instead of person_xxx (monitoring_helper.py x4, pipelinemgr.py x1 missing .value on launcher_type) - Fix duplicate platform/person label in session list and chat header - Migrate existing malformed session_id records in DB --------- Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>	2026-06-27 17:18:19 +08:00
彼方	48905ea080	feat(plugin): report deferred response delivery failures (#2287 ) * feat(plugin): report deferred response delivery failures * style: fix ruff format issues in plugin_diagnostics and test_handler_actions --------- Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>	2026-06-26 23:45:10 +08:00
Hyu	ddb77fc43c	fix(api): guard /set-password with allow_modify_login_info (#2288 ) The /change-password and /bind-space endpoints already refuse when system.allow_modify_login_info is false, but /set-password did not, leaving a path to alter login credentials on locked-down deployments (e.g. public demo instances). Apply the same guard. Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>	2026-06-26 16:35:50 +08:00
huanghuoguoguo	5b2826fa49	Add performance and reliability QA gates (#2283 ) * Add performance and reliability QA gates * test(skills): prepare user path performance gate * test(skills): add debug chat load gate * test(skills): extend fake provider load profiles * test(skills): add debug chat timing and isolation probes * test(skills): clarify manual QA perf gates	2026-06-25 21:02:44 +08:00
Hyu	20636ac432	Merge pull request #2284 from langbot-app/fix/api-password-thread-offload fix(api): offload password hashing from event loop	2026-06-25 20:31:44 +08:00
Hyu	af42602547	Merge pull request #2285 from langbot-app/fix/monitoring-null-payloads fix(monitoring): tolerate null API payloads	2026-06-25 20:26:25 +08:00
dadachann	53b20e2b13	fix(monitoring): tolerate null API payloads Normalize monitoring API responses before rendering so empty or error payloads with data:null cannot crash the dashboard. Also guard chart, token, and box session arrays before reading length/map.	2026-06-25 08:22:01 -04:00
dadachann	1242dc2d21	fix(api): offload password hashing from event loop	2026-06-25 06:29:16 -04:00
RockChinQ	04628d93cb	docs: add architecture guide for agents	2026-06-25 04:17:19 -04:00
RockChinQ	9c22a1521c	fix(box): defer separated workspace ownership to runtime	2026-06-25 00:09:40 -04:00
RockChinQ	c8d5039580	feat(box): expose Docker CPU limit toggle	2026-06-24 23:31:53 -04:00
dadachann	85d8d9304e	fix(web): keep feedback dialog interactive	2026-06-24 10:10:19 -04:00
Hyu	76471af179	feat(web): add sidebar feedback popover Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>	2026-06-24 16:43:50 +08:00
RockChinQ	59b2a7cd51	fix(monitoring): hide disabled box status on cloud	2026-06-23 06:40:05 -04:00
RockChinQ	a43978ff24	chore(release): bump version to 4.10.4	2026-06-22 21:15:53 -04:00
RockChinQ	e3417dd20b	fix(release): derive package version from metadata	2026-06-22 21:10:33 -04:00
RockChinQ	2982e7c553	chore(release): bump version to 4.10.3	2026-06-22 11:12:15 -04:00
RockChinQ	e1e14e9269	chore(deps): bump langbot-plugin to 0.4.6	2026-06-22 11:08:08 -04:00
Junyan Chin	1c128a1524	docs(skills/langbot-plugin-dev): document marketplace README i18n convention (root README.md must be English; other langs in readme/)	2026-06-22 02:39:15 -04:00
RockChinQ	8ad1203fd5	docs(examples): add web-page-bot embed demo, drop stray test-embed.html Move the Page Bot (web_page_bot) embed test page out of the repo root into examples/web-page-bot/ as a proper, LangBot-styled demo: a self-contained index.html that loads the live widget.js against a running instance, plus bilingual READMEs mirroring examples/http-bot/.	2026-06-22 02:17:26 -04:00
Junyan Chin	144bec371c	feat(platform): standalone HTTP Bot adapter (server-to-server) (#2274 ) * docs(platform): add HTTP Bot adapter design (RFC) Standalone server-to-server HTTP adapter for driving a pipeline from external systems (LangBot Space ticketing et al). Inbound via the existing unified webhook route; outbound via signed callback POSTs. Preserves pipeline-native N->1 aggregation and 1->M multi-reply without a long-lived WebSocket. No core changes required (router/aggregator/pipeline untouched). * feat(platform): add standalone HTTP Bot adapter A first-class, vendor-neutral message-platform adapter (http_bot) for server-to-server integrations (LangBot Space ticketing et al). Drives a pipeline over plain HTTP with no long-lived connection: - Inbound: signed POST to the existing unified webhook route /bots/<uuid>, carrying a caller-defined session_id mapped to the LangBot launcher id via get_launcher_id -> per-session isolation. Preserves pipeline-native N->1 aggregation for free. - Outbound: each reply_message / reply_message_chunk becomes one signed callback POST to the config-only callback_url, delivered in per-session sequence order with retry/backoff -> 1->M multi-reply. - Sub-paths: /reset (drop a session) and /sync (block for the collapsed reply). - Auth: symmetric HMAC-SHA256 both directions (timestamp + replay window), no JWT/Turnstile, no socket. Decisions: callback URL is config-only (SSRF closed); reset + sync shipped; Python + TS reference clients shipped (signing verified byte-identical 3-way). No core changes: the unified webhook router, aggregator, query pool and pipeline are untouched. Adapter is auto-discovered from platform/sources/. Adds: src/langbot/pkg/platform/sources/http_bot.{py,yaml,svg} src/langbot/pkg/platform/sources/http_bot_signing.py docs/platforms/http-bot.md, docs/http-bot-openapi.json examples/http-bot/{client.py,client.ts,README.md} Updates docs/HTTP_BOT_ADAPTER_DESIGN.md (status: implemented). * docs(examples): add interactive HTTP Bot playground (browser debug console) A single-file aiohttp web app (examples/http-bot/playground.py) that lets you chat with a RUNNING http_bot bot from the browser and watch the protocol live: signed inbound POST -> 202 ack -> 1->M signed callbacks streamed back via SSE, with a debug panel showing the signature, HTTP status, and per-callback sequence/verification. Light LangBot-styled UI. On startup it reads the API key + http_bot bot from data/langbot.db and points the bot's callback_url + secrets back at itself via the LangBot API (live reload, no restart). README updated with a playground section. * docs(examples): add Chinese README for http-bot reference clients * style(platform): use </> code icon for http_bot adapter logo * docs(examples): point http-bot guide links to docs.langbot.app * style(platform): make http_bot icon a transparent monochrome </> so WebUI tints it like other adapters * Revert to colorful </> badge for http_bot icon (WebUI renders it as-is)	2026-06-22 13:38:00 +08:00
Typer_Body	417cca016c	cold	2026-06-05 22:35:57 +08:00
Typer_Body	cb0cc4d06a	cold	2026-06-05 21:20:46 +08:00
Typer_Body	cb0bb44db8	update	2026-06-05 02:49:09 +08:00
Typer_Body	6609bebeec	platfrom	2026-06-04 03:13:32 +08:00
Typer_Body	192b69b0fb	fix	2026-06-02 02:29:35 +08:00
Typer_Body	543fbd8ca0	new	2026-06-02 02:08:07 +08:00
Typer_Body	804448b6cd	yaml	2026-05-27 00:24:07 +08:00
Typer_Body	5d4e40459f	shit	2026-05-26 02:28:01 +08:00
Typer_Body	b5c43cc113	new nofe、、	2026-05-23 03:21:31 +08:00
Typer_Body	8ebfcd963a	new node	2026-05-23 02:58:17 +08:00
Typer_Body	127198675e	end3	2026-05-23 01:31:42 +08:00
Typer_Body	44fb188994	end1	2026-05-23 01:00:10 +08:00
Typer_Body	265385a563	end	2026-05-23 00:51:24 +08:00
Typer_Body	253cc6cbea	shit	2026-05-22 02:07:48 +08:00
Typer_Body	f99d3022e8	Merge master into feat/workflow: resolve conflicts by keeping workflow branch changes	2026-05-21 00:51:09 +08:00
Typer_Body	5c5614667a	change	2026-05-20 02:49:44 +08:00
Typer_Body	313d553271	bezier	2026-05-18 02:00:31 +08:00
Typer_Body	bb7db53447	backend	2026-05-18 01:47:13 +08:00
Typer_Body	27c0d344bf	unified standard	2026-05-16 00:09:57 +08:00
Typer_Body	c088dc114f	clean the shit of ai	2026-05-15 02:11:21 +08:00
Typer_Body	37c74b0622	update icon i18n	2026-05-15 01:05:29 +08:00
Typer_Body	c9f7911efe	update	2026-05-08 01:27:45 +08:00
Typer_Body	75fdfe6806	ruff	2026-05-08 00:56:27 +08:00
Typer_Body	eb9f38b102	针对已被移除的路由规则功能的。根据 botmgr.py:74-100 中的注释，路由规则已被移除，Bot 现在直接绑定到 Pipeline 或 Workflow。	2026-05-08 00:53:35 +08:00
Typer_Body	fc40d3c949	ruff	2026-05-07 23:33:54 +08:00
Typer_Body	d176a448e0	Merge remote-tracking branch 'origin/master' into feat/workflow	2026-05-07 00:57:56 +08:00
Typer_Body	ada4c30f85	1111	2026-05-06 01:03:34 +08:00
Typer_Body	32c9eaff45	还是修不好	2026-05-05 16:16:33 +08:00
Typer_Body	9706ee2d53	没修好	2026-05-05 16:16:04 +08:00
Typer_Body	e7c9bc69d3	后端没修完版	2026-05-05 15:08:04 +08:00