TeamClaw

TeamClaw Agent Subsystem Skill

https://github.com/Avalon-467/Teamclaw

Introduction

TeamClaw is an OpenClaw-like multi-agent sub-platform with a built-in lightweight agent (similar to OpenClaw's), featuring computer use capabilities and social platform integrations (e.g., Telegram). It can run independently without blocking the main agent, or be directly controlled by an OpenClaw agent to orchestrate the built-in OASIS collaboration platform. It also supports exposing the frontend to the public internet via Cloudflare, enabling remote visual multi-agent workflow programming from mobile devices or any browser.

TeamClaw is a versatile AI Agent service providing:

• Conversational Agent: A LangGraph-based multi-tool AI assistant supporting streaming/non-streaming conversations
• OASIS Forum: A multi-expert parallel discussion/execution engine for orchestrating multiple agents
• Scheduled Tasks: An APScheduler-based task scheduling center
• Bark Push: Mobile push notifications
• Frontend Web UI: A complete chat interface

Skill Scripts

All scripts are located in selfskill/scripts/, invoked uniformly via the run.sh entry point, all non-interactive.

selfskill/scripts/
 run.sh          # Main entry (start/stop/status/setup/add-user/configure)
 adduser.py      # Non-interactive user creation
 configure.py    # Non-interactive .env configuration management

Quick Start

All commands are executed in the project root directory.

Three-step launch flow: setup → configure → start

1. First Deployment

# Install dependencies
bash selfskill/scripts/run.sh setup

# Initialize configuration file
bash selfskill/scripts/run.sh configure --init

# Configure LLM (required)
bash selfskill/scripts/run.sh configure --batch \
  LLM_API_KEY=sk-your-key \
  LLM_BASE_URL=https://api.deepseek.com \
  LLM_MODEL=deepseek-chat

# ⚠️ Create user account (REQUIRED — without this you CANNOT log in to the Web UI or call API)
bash selfskill/scripts/run.sh add-user system MySecurePass123

⚠️ You MUST create at least one user account before starting the service!

• The Web UI login page requires username + password.
• All API calls require Authorization: Bearer <user_id>:<password> (or INTERNAL_TOKEN:<user_id>).
• If you skip this step, you will be locked out of the entire system.
• You can create multiple users. The first argument is the username, the second is the password.

2. Start / Stop / Status

bash selfskill/scripts/run.sh start     # Start in background
bash selfskill/scripts/run.sh status    # Check status
bash selfskill/scripts/run.sh stop      # Stop service

3. Bark Push vs Chatbot (Telegram/QQ) — Startup Differences

⚠️ Important for Agent/headless usage: The chatbot/setup.py script contains interactive input() prompts. When launcher.py runs in the background (via run.sh start), if chatbot/setup.py exists it will be called and block indefinitely waiting for user input. To prevent this:

1. Either remove/rename chatbot/setup.py before starting, OR
2. Pre-configure all bot tokens in .env and start bots independently (bypassing setup.py).

4. Configuration Management

# View current configuration (sensitive values masked)
bash selfskill/scripts/run.sh configure --show

# Set a single item
bash selfskill/scripts/run.sh configure PORT_AGENT 51200

# Batch set
bash selfskill/scripts/run.sh configure --batch TTS_MODEL=gemini-2.5-flash-preview-tts TTS_VOICE=charon

Configuration Options

Ports & Services

API Authentication

Method 1: User Authentication

Authorization: Bearer <user_id>:<password>

Method 2: Internal Token (for inter-service calls, recommended)

Authorization: Bearer <INTERNAL_TOKEN>:<user_id>

INTERNAL_TOKEN is auto-generated on first startup; view it via configure --show-raw.

Core API

Base URL: http://127.0.0.1:51200

Chat (OpenAI-compatible)

POST /v1/chat/completions
Authorization: Bearer <token>

{"model":"mini-timebot","messages":[{"role":"user","content":"Hello"}],"stream":true,"session_id":"my-session"}

System Trigger (internal call)

POST /system_trigger
X-Internal-Token: <INTERNAL_TOKEN>

{"user_id":"system","text":"Please execute a task","session_id":"task-001"}

Cancel Session

POST /cancel

{"user_id":"<user_id>","session_id":"<session_id>"}

OASIS Four Operating Modes (Default: Discussion Mode)

📖 Dedicated OASIS usage guide (especially for OpenClaw agent integration): OASIS_GUIDE.md

The "four modes" are two orthogonal switches:

• Discussion vs Execution: Determines whether expert output is "forum-style discussion/voting" or "workflow-style execution/deliverables".
• Synchronous vs Detach: Determines whether the caller blocks waiting for results.

1) Discussion Mode vs Execution Mode

Discussion Mode (discussion=true, default)

• Purpose: Multiple experts provide different perspectives, pros/cons analysis, clarify disputes, and can form consensus.
• Use case: Solution reviews, technical route selection, questions that need "why".

Execution Mode (discussion=false)

• Purpose: Use OASIS as an orchestrator to complete tasks in planned sequential/parallel order, emphasizing direct output (code/scripts/checklists/finalized plans).
• Use case: Delivery tasks with clear objectives that don't need debate.

2) Synchronous Mode vs Detach Mode

Detach (detach=true, default)

• Behavior: Returns topic_id immediately, continues running/discussing in the background; later use check_oasis_discussion(topic_id) to track progress and results.
• Use case: Most tasks, especially multi-round/multi-expert/long-running/tool-calling tasks.

Synchronous (detach=false)

• Behavior: After calling post_to_oasis, waits for completion and returns the final result directly.
• Use case: Quick tasks where you need the deliverable immediately to continue iterating.

3) Auto-selection Rules (Recommended Default Strategy)

When not explicitly specified, the following default strategy is recommended:

1. Default = Discussion + Detach

   • discussion=true
   • detach=true

2. Switch to Execution Mode when these signals appear:

   • "Give me the final version / copy-pasteable / executable script / just conclusions no discussion"
   • "Generate SOP / checklist / table step by step and finalize"

3. Switch to Synchronous Mode when these signals appear:

   • "Wait for the result / I need it now / give me the answer directly"
   • Quick single-round tasks where the deliverable is needed immediately

4) Four Combinations Quick Reference

OASIS Four Agent Types

OASIS supports four types of agents, distinguished by the name format in schedule_yaml:

Session ID Format

tag#temp#N            ExpertAgent   (stateless, direct LLM)
tag#oasis#<id>        SessionExpert (oasis-managed, stateful bot)
Title#session_id      SessionExpert (regular agent session)
tag#ext#<id>          ExternalExpert (external API, e.g. OpenClaw agent)

Special Suffix:

• Appending #new to the end of any session name forces creation of a brand new session (ID replaced with random UUID, ensuring no reuse):
  • creative#oasis#abc#new #new stripped, ID replaced with UUID
  • Assistant#my-session#new Same processing

Oasis Session Conventions:

• Oasis sessions are identified by #oasis# in session_id (e.g., creative#oasis#ab12cd34)
• Stored in the regular Agent checkpoint DB (data/agent_memory.db), no separate storage
• Auto-created on first use, no pre-creation needed
• tag part maps to preset expert configuration to find persona

YAML Example

version: 1
plan:
  # Type 1: Direct LLM (stateless, fast)
  - expert: "creative#temp#1"
  - expert: "critical#temp#2"

  # Type 2: Oasis session (stateful, with memory)
  - expert: "data#oasis#analysis01"
  - expert: "synthesis#oasis#new#new"   # Force new session

  # Type 3: Regular agent session (your existing bot)
  - expert: "Assistant#default"
  - expert: "Coder#my-project"

  # Type 4: External API (DeepSeek, GPT-4, etc.)
  # Note: api_key is auto-read from OPENCLAW_API_KEY env var; use "****" mask in YAML (never write plaintext keys)
  - expert: "deepseek#ext#ds1"

  # Type 4: OpenClaw External API (local Agent service)
  # api_key auto-resolved from OPENCLAW_API_KEY env var when set to "****"
  - expert: "coder#ext#oc1"
    api_url: "http://127.0.0.1:23001/v1/chat/completions"
    api_key: "****"              # Masked — real key read from OPENCLAW_API_KEY env var at runtime
    model: "agent:main:test1"    # agent:<agent_name>:<session>, session auto-created if not exists

  # Parallel execution
  - parallel:
      - expert: "creative#temp#1"
        instruction: "Analyze from innovation perspective"
      - expert: "critical#temp#2"
        instruction: "Analyze from risk perspective"

  # All experts speak + manual injection
  - all_experts: true
  - manual:
      author: "Moderator"
      content: "Please focus on feasibility"

DAG Mode — Dependency-Driven Parallel Execution

When the workflow has fan-in (a node has multiple predecessors) or fan-out (a node has multiple successors), use DAG mode with id and depends_on fields. The engine maximizes parallelism — each node starts as soon as all its dependencies are satisfied.

DAG YAML Example:

version: 1
repeat: false
plan:
  - id: research
    expert: "creative#temp#1"                # Root — starts immediately
  - id: analysis
    expert: "critical#temp#1"                # Root — runs in PARALLEL with research
  - id: synthesis
    expert: "synthesis#temp#1"
    depends_on: [research, analysis]         # Fan-in: waits for BOTH to complete
  - id: review
    expert: "data#temp#1"
    depends_on: [synthesis]                  # Runs after synthesis

DAG Rules:

• Every step must have a unique id field.
• depends_on is a list of step ids that must complete before this step starts. Omit for root nodes.
• The graph must be acyclic (no circular dependencies).
• Steps with no dependency relationship run in parallel automatically.
• The visual Canvas auto-detects fan-in/fan-out and generates DAG format.
• manual steps can also have id/depends_on.

External API (Type 4) Detailed Configuration

Type 4 external agents support additional configuration fields in YAML steps:

version: 1
plan:
  - expert: "#ext#analyst"
    api_url: "https://api.deepseek.com"          # Required: External API base URL (auto-completes to /v1/chat/completions)
    api_key: "****"                               # Masked — real key auto-read from OPENCLAW_API_KEY env var at runtime
    model: "deepseek-chat"                        # Optional: Model name, default gpt-3.5-turbo
    headers:                                      # Optional: Custom HTTP headers (key-value dict)
      X-Custom-Header: "value"

🔒 API Key Security: You no longer need to write plaintext API keys in YAML. Set api_key: "****" (or omit it entirely) and the system will automatically read the real key from the OPENCLAW_API_KEY environment variable at runtime. The frontend canvas also displays **** instead of the real key. If you do write a plaintext key, it will still work (backward compatible). Configuration Field Description:

OpenClaw-specific Configuration:

OpenClaw is a locally running OpenAI-compatible Agent service. After setting up OpenClaw-specific endpoints in .env, the frontend orchestration panel will auto-fill api_url and api_key when dragging in an OpenClaw expert, no manual input needed:

# Configure OpenClaw endpoint and sessions file path
bash selfskill/scripts/run.sh configure --batch \
OPENCLAW_SESSIONS_FILE=./data/sessions.json \
  OPENCLAW_API_URL=http://127.0.0.1:18789/v1/chat/completions \
  OPENCLAW_API_KEY=your-openclaw-key-if-needed

** Note:**

• OPENCLAW_SESSIONS_FILE is a prerequisite for using the OpenClaw feature and must point to the absolute path of OpenClaw's sessions.json file. The frontend orchestration panel will not load OpenClaw sessions if unconfigured.
• Path Convention: ./agents/main/sessions/sessions.json is a common path structure for OpenClaw agent sessions. This path convention allows the system to properly access and orchestrate OpenClaw agents.
• Session Management: Accessing session information is a necessary process for OpenClaw agent orchestration, enabling multi-agent workflow coordination and visual canvas operations.
• OPENCLAW_API_URL should contain the full path (including /v1/chat/completions); the system will auto-strip the suffix to generate the base URL for YAML. The api_url field in YAML only needs the base URL (e.g., http://127.0.0.1:18789); the engine auto-completes the path.
• If your OpenClaw service runs on a non-default port, be sure to modify these settings.

OpenClaw model Field Format:

agent:<agent_name>:<session_name>

• agent_name: Agent name in OpenClaw, usually main
• session_name: Session name, e.g., test1, default, etc. You can enter a non-existent session name to auto-create

Examples:

• agent:main:default Use main agent's default session
• agent:main:test1 Use main agent's test1 session (auto-created if not exists)
• agent:main:code-review Use main agent's code-review session

Request Header Assembly Logic: Final request headers = Content-Type: application/json + Authorization: Bearer <api_key> (if present) + all key-value pairs from YAML headers.

x-openclaw-session-key — Deterministic OpenClaw Session Routing:

When calling an OpenClaw agent via External API (Type 4), the x-openclaw-session-key HTTP header is the key mechanism for routing requests to a specific, deterministic OpenClaw session. Without this header, OpenClaw may not correctly associate the request with the intended session.

• The frontend orchestration panel automatically sets this header when you drag an OpenClaw session onto the canvas.
• When writing YAML manually or calling the API programmatically, you must include this header in the headers field to ensure session determinism.

# Example: Connecting to a specific OpenClaw session
- expert: "coder#ext#oc1"
  api_url: "http://127.0.0.1:18789"
  api_key: "****"                                      # ← Masked; real key from OPENCLAW_API_KEY env var
  model: "agent:main:my-session"
  headers:
    x-openclaw-session-key: "agent:main:my-session"   # ← This header determines the exact OpenClaw session

The value of x-openclaw-session-key should match the model field's session identifier (format: agent:<agent_name>:<session_name>). This ensures the external request is routed to the correct OpenClaw agent session, maintaining conversation continuity and state.

Using OASIS Server Independently

The OASIS Server (port 51202) can be used independently of the Agent main service. External scripts, other services, or manual curl can directly operate all OASIS features without going through MCP tools or Agent conversations.

Independent Use Scenarios:

• Initiate multi-expert discussions/executions from external scripts
• Debug workflow orchestration
• Integrate OASIS as a microservice into other systems
• Manage experts, sessions, workflows, and other resources

Prerequisites:

• OASIS service is running (bash selfskill/scripts/run.sh start starts all services simultaneously)
• All endpoints use user_id parameter for user isolation (no Authorization header needed)

API Overview:

These endpoints share the same backend implementation as MCP tools, ensuring consistent behavior.

OASIS Discussion/Execution

POST http://127.0.0.1:51202/topics

{"question":"Discussion topic","user_id":"system","max_rounds":3,"discussion":true,"schedule_file":"...","schedule_yaml":"...","callback_url":"http://127.0.0.1:51200/system_trigger","callback_session_id":"my-session"}

Prefer using schedule_yaml to avoid repeated YAML input; this is the absolute path to the YAML workflow file, usually under /XXXXX/TeamClaw/data/user_files/username.

Externally Participating in OASIS Server via curl (Complete Methods)

The OASIS Server (port 51202), in addition to being called by MCP tools, also supports direct curl operations for external scripts or debugging. All endpoints use user_id parameter for user isolation.

1. Expert Management

# List all experts (public + user custom)
curl 'http://127.0.0.1:51202/experts?user_id=xinyuan'

# Create custom expert
curl -X POST 'http://127.0.0.1:51202/experts/user' \
  -H 'Content-Type: application/json' \
  -d '{"user_id":"xinyuan","name":"Product Manager","tag":"pm","persona":"You are an experienced product manager skilled in requirements analysis and product planning","temperature":0.7}'

# Update custom expert
curl -X PUT 'http://127.0.0.1:51202/experts/user/pm' \
  -H 'Content-Type: application/json' \
  -d '{"user_id":"xinyuan","persona":"Updated expert description"}'

# Delete custom expert
curl -X DELETE 'http://127.0.0.1:51202/experts/user/pm?user_id=xinyuan'

2. Session Management

# List OASIS-managed expert sessions (sessions containing #oasis#)
curl 'http://127.0.0.1:51202/sessions/oasis?user_id=xinyuan'

3. Workflow Management

# List user's saved workflows
curl 'http://127.0.0.1:51202/workflows?user_id=xinyuan'

# Save workflow (auto-generate layout)
curl -X POST 'http://127.0.0.1:51202/workflows' \
  -H 'Content-Type: application/json' \
  -d '{"user_id":"xinyuan","name":"trio_discussion","schedule_yaml":"version:1\nplan:\n - expert: \"creative#temp#1\"","description":"Trio discussion","save_layout":true}'

4. Layout Generation

# Generate layout from YAML
curl -X POST 'http://127.0.0.1:51202/layouts/from-yaml' \
  -H 'Content-Type: application/json' \
  -d '{"user_id":"xinyuan","yaml_source":"version:1\nplan:\n - expert: \"creative#temp#1\"","layout_name":"trio_layout"}'

5. Discussion/Execution

# Create discussion topic (synchronous, wait for conclusion)
curl -X POST 'http://127.0.0.1:51202/topics' \
  -H 'Content-Type: application/json' \
  -d '{"user_id":"xinyuan","question":"Discussion topic","max_rounds":3,"schedule_yaml":"version:1\nplan:\n - expert: \"creative#temp#1\"","discussion":true}'

# Create discussion topic (async, returns topic_id)
curl -X POST 'http://127.0.0.1:51202/topics' \
  -H 'Content-Type: application/json' \
  -d '{"user_id":"xinyuan","question":"Discussion topic","max_rounds":3,"schedule_yaml":"version:1\nplan:\n - expert: \"creative#temp#1\"","discussion":true,"callback_url":"http://127.0.0.1:51200/system_trigger","callback_session_id":"my-session"}'

# View discussion details
curl 'http://127.0.0.1:51202/topics/{topic_id}?user_id=xinyuan'

# Get discussion conclusion (blocking wait)
curl 'http://127.0.0.1:51202/topics/{topic_id}/conclusion?user_id=xinyuan&timeout=300'

# Cancel discussion
curl -X DELETE 'http://127.0.0.1:51202/topics/{topic_id}?user_id=xinyuan'

# List all discussion topics
curl 'http://127.0.0.1:51202/topics?user_id=xinyuan'

6. Real-time Stream

# SSE real-time update stream (discussion mode)
curl 'http://127.0.0.1:51202/topics/{topic_id}/stream?user_id=xinyuan'

Storage Locations:

• Workflows (YAML): data/user_files/{user}/oasis/yaml/{file}.yaml (canvas layouts are converted from YAML in real-time, no longer stored as separate layout JSON)
• User custom experts: data/oasis_user_experts/{user}.json
• Discussion records: data/oasis_topics/{user}/{topic_id}.json

Note: These endpoints share the same backend implementation as MCP tools list_oasis_experts, add_oasis_expert, update_oasis_expert, delete_oasis_expert, list_oasis_sessions, set_oasis_workflow, list_oasis_workflows, yaml_to_layout, post_to_oasis, check_oasis_discussion, cancel_oasis_discussion, list_oasis_topics, ensuring consistent behavior.

Example Configuration Reference

Below is an actual running configuration example (sensitive info redacted):

bash selfskill/scripts/run.sh configure --init
bash selfskill/scripts/run.sh configure --batch \
  LLM_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxx4c74 \
  LLM_BASE_URL=https://deepseek.com \
  LLM_MODEL=deepseek-chat \
  LLM_VISION_SUPPORT=true \
  TTS_MODEL=gemini-2.5-flash-preview-tts \
  TTS_VOICE=charon \
  PORT_AGENT=51200 \
  PORT_SCHEDULER=51201 \
  PORT_OASIS=51202 \
  PORT_FRONTEND=51209 \
  PORT_BARK=58010 \
  OPENCLAW_API_URL=http://127.0.0.1:18789/v1/chat/completions \
  OPENAI_STANDARD_MODE=false
bash selfskill/scripts/run.sh add-user system <your-password>

Output after configure --show:

  PORT_SCHEDULER=51201
  PORT_AGENT=51200
  PORT_FRONTEND=51209
  PORT_OASIS=51202
  OASIS_BASE_URL=http://127.0.0.1:51202
  PORT_BARK=58010
  INTERNAL_TOKEN=f1aa****57e7          # Auto-generated, do not leak
  LLM_API_KEY=sk-7****4c74
  LLM_BASE_URL=https://deepseek.com
  LLM_MODEL=deepseek-chat
  LLM_VISION_SUPPORT=true
  TTS_MODEL=gemini-2.5-flash-preview-tts
  TTS_VOICE=charon
  OPENAI_STANDARD_MODE=false

Note: INTERNAL_TOKEN is auto-generated on first startup; PUBLIC_DOMAIN / BARK_PUBLIC_URL are auto-written by the tunnel; no manual configuration needed.

Typical Usage Flow

cd /home/avalon/TeamClaw

# First-time configuration
bash selfskill/scripts/run.sh setup
bash selfskill/scripts/run.sh configure --init
bash selfskill/scripts/run.sh configure --batch LLM_API_KEY=sk-xxx LLM_BASE_URL=https://api.deepseek.com LLM_MODEL=deepseek-chat
bash selfskill/scripts/run.sh add-user system MyPass123

# Start
bash selfskill/scripts/run.sh start

# Call API
curl -X POST http://127.0.0.1:51200/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer system:MyPass123" \
  -d '{"model":"mini-timebot","messages":[{"role":"user","content":"Hello"}],"stream":false,"session_id":"default"}'

# Stop
bash selfskill/scripts/run.sh stop

Important Notes

• All skill scripts are in selfskill/scripts/, not affecting original project functionality

• Process management via PID files, start supports idempotent calls

• Do not leak INTERNAL_TOKEN

• Log path: logs/launcher.log

• Be sure to tell users how to open the visual interface and how to log in to the account for discussions

• The OpenClaw session file path can be inferred from the example path and current skill path. If you are an OpenClaw agent, be sure to complete the full OpenClaw-related configuration

TeamClaw Agent Skill

TeamClaw OpenClaw Agent OpenClaw Agent computer use Telegram agent OpenClaw agent OASIS Agent Cloudflare Agent

TeamClaw AI Agent

• ** Agent** LangGraph AI /
• **OASIS **/ Agent
• **** APScheduler
• **Bark **
• ** Web UI**

Skill

selfskill/scripts/ run.sh ****

selfskill/scripts/
 run.sh          # start/stop/status/setup/add-user/configure
 adduser.py      # 
 configure.py    #  .env 

****setup configure start

1.

# 
bash selfskill/scripts/run.sh setup

# 
bash selfskill/scripts/run.sh configure --init

#  LLM
bash selfskill/scripts/run.sh configure --batch \
  LLM_API_KEY=sk-your-key \
  LLM_BASE_URL=https://api.deepseek.com \
  LLM_MODEL=deepseek-chat

# 
bash selfskill/scripts/run.sh add-user system MySecurePass123

2. //

bash selfskill/scripts/run.sh start     # 
bash selfskill/scripts/run.sh status    # 
bash selfskill/scripts/run.sh stop      # 

3.

# 
bash selfskill/scripts/run.sh configure --show

# 
bash selfskill/scripts/run.sh configure PORT_AGENT 51200

# 
bash selfskill/scripts/run.sh configure --batch TTS_MODEL=gemini-2.5-flash-preview-tts TTS_VOICE=charon

API

1

Authorization: Bearer <user_id>:<password>

2 Token

Authorization: Bearer <INTERNAL_TOKEN>:<user_id>

INTERNAL_TOKEN configure --show-raw

API

Base URL: http://127.0.0.1:51200

OpenAI

POST /v1/chat/completions
Authorization: Bearer <token>

{"model":"mini-timebot","messages":[{"role":"user","content":""}],"stream":true,"session_id":"my-session"}

POST /system_trigger
X-Internal-Token: <INTERNAL_TOKEN>

{"user_id":"system","text":"","session_id":"task-001"}

POST /cancel

{"user_id":"<user_id>","session_id":"<session_id>"}

OASIS

📖 专注 OASIS 使用的独立指引文档（尤其是 OpenClaw agent 集成）: OASIS_GUIDE.md

""

• ** vs "/""/("> - ** vs detach

1) vs

discussion=true

• ""

discussion=false

• OASIS ////

2) vs detach

detach=true

• topic_id/ check_oasis_discussion(topic_id)

detach=false

• post_to_oasis
• /

3)

1. ** = + **

   • discussion=true
   • detach=true

2. ---

• " / / / "
• " SOP / / "

• " / / / "
• /

4)

OASIS

OASIS **** schedule_yaml name

Session ID

tag#temp#N            ExpertAgent   (, LLM)
tag#oasis#<id>        SessionExpert (oasis, bot)
Title#session_id      SessionExpert (agent session)
tag#ext#<id>          ExternalExpert (APIopenclaw agent)

• session #new ** session**ID UUID
• creative#oasis#abc#new #new ID UUID
• #my-session#new

**Oasis session **

• Oasis session session_id #oasis# creative#oasis#ab12cd34
• Agent checkpoint DBdata/agent_memory.db
• tag

YAML

version: 1
plan:
  # Type 1: Direct LLM
  - expert: "creative#temp#1"
  - expert: "critical#temp#2"

  # Type 2: Oasis session
  - expert: "data#oasis#analysis01"
  - expert: "synthesis#oasis#new#new"   # session

  # Type 3: Regular agent sessionbot
  - expert: "#default"
  - expert: "Coder#my-project"

  # Type 4: External APIDeepSeek, GPT-4
  # 注意：api_key 自动从 OPENCLAW_API_KEY 环境变量读取；YAML 中使用 "****" 掩码（切勿写入明文密钥）
  - expert: "deepseek#ext#ds1"

  # Type 4: OpenClaw External API Agent 
  # api_key 从 OPENCLAW_API_KEY 环境变量自动读取，YAML 中使用 "****" 掩码
  - expert: "coder#ext#oc1"
    api_url: "http://127.0.0.1:23001/v1/chat/completions"
    api_key: "****"              # 掩码 — 运行时自动从 OPENCLAW_API_KEY 环境变量读取真实密钥
    model: "agent:main:test1"    # agent:<agent_name>:<session>session 

  # 
  - parallel:
      - expert: "creative#temp#1"
        instruction: ""
      - expert: "critical#temp#2"
        instruction: ""

  #  + 
  - all_experts: true
  - manual:
      author: ""
      content: ""

DAG 模式 — 依赖驱动的并行执行

当工作流存在 fan-in（一个节点有多个前驱）或 fan-out（一个节点有多个后继）时，使用带 id 和 depends_on 字段的 DAG 模式。引擎会最大化并行——每个节点在所有依赖完成后立即启动，无需等待无关节点。

DAG YAML 示例：

version: 1
repeat: false
plan:
  - id: research
    expert: "creative#temp#1"                # 根节点 — 立即启动
  - id: analysis
    expert: "critical#temp#1"                # 根节点 — 与 research 并行运行
  - id: synthesis
    expert: "synthesis#temp#1"
    depends_on: [research, analysis]         # Fan-in：等待两者都完成
  - id: review
    expert: "data#temp#1"
    depends_on: [synthesis]                  # synthesis 完成后执行

DAG 规则：

• 每个步骤必须有唯一的 id 字段。
• depends_on 是该步骤启动前必须完成的步骤 id 列表。根节点不需要此字段。
• 图必须无环（禁止循环依赖）。
• 没有依赖关系的步骤自动并行执行。
• 可视化画布自动检测 fan-in/fan-out 并生成 DAG 格式。
• manual 步骤同样支持 id/depends_on。

External API (Type 4)

Type 4 agent YAML

version: 1
plan:
  - expert: "#ext#analyst"
    api_url: "https://api.deepseek.com"          #  API  base URL /v1/chat/completions
    api_key: "****"                               # 掩码 — 运行时自动从 OPENCLAW_API_KEY 环境变量读取真实密钥
    model: "deepseek-chat"                        #  gpt-3.5-turbo
    headers:                                      #  HTTP key-value 
      X-Custom-Header: "value"

🔒 API Key 安全机制：YAML 中无需再写入明文 API Key。设置 api_key: "****"（或完全省略）即可，系统运行时会自动从 OPENCLAW_API_KEY 环境变量读取真实密钥。前端画布也仅显示 **** 而非真实密钥。如果你仍然写入明文密钥，也能正常工作（向后兼容）。

**OpenClaw **

OpenClaw OpenAI Agent .env OpenClaw endpoint OpenClaw **** api_url api_key

#  OpenClaw endpoint  sessions 
bash selfskill/scripts/run.sh configure --batch \
OPENCLAW_SESSIONS_FILE=./data/sessions.json \
  OPENCLAW_API_URL=http://127.0.0.1:18789/v1/chat/completions \
  OPENCLAW_API_KEY=your-openclaw-key-if-needed

---

• OPENCLAW_SESSIONS_FILE OpenClaw **** OpenClaw sessions.json OpenClaw sessions
• Path Convention: ./agents/main/sessions/sessions.json OpenClaw agent sessions OpenClaw agents
• Session Management: Accessing session information is a necessary process for OpenClaw agent orchestration, enabling multi-agent workflow coordination and visual canvas operations.
• OPENCLAW_API_URL **** /v1/chat/completions base URL YAMLYAML api_url base URL http://127.0.0.1:18789
• OpenClaw

**OpenClaw model **

agent:<agent_name>:<session_name>

• agent_nameOpenClaw agent main

• session_name test1``default ** session **

• agent:main:default main agent default session

• agent:main:test1 main agent test1 session

• agent:main:code-review main agent code-review session

= Content-Type: application/json + Authorization: Bearer <api_key> + YAML headers

x-openclaw-session-key —— OpenClaw 确定性 Session 路由：

通过 External API（Type 4）调用 OpenClaw agent 时，x-openclaw-session-key HTTP header 是将请求路由到指定 OpenClaw session 的关键机制。缺少此 header，OpenClaw 可能无法正确关联到目标 session。

• 前端编排面板在拖拽 OpenClaw session 到画布时会自动设置此 header。
• 手动编写 YAML 或通过 API 调用时，必须在 headers 字段中包含此 header 以确保 session 的确定性。

# 示例：连接到指定的 OpenClaw session
- expert: "coder#ext#oc1"
  api_url: "http://127.0.0.1:18789"
  api_key: "****"                                      # ← 掩码；真实密钥从 OPENCLAW_API_KEY 环境变量读取
  model: "agent:main:my-session"
  headers:
    x-openclaw-session-key: "agent:main:my-session"   # ← 此 header 决定了目标 OpenClaw session

x-openclaw-session-key 的值应与 model 字段的 session 标识符一致（格式：agent:<agent_name>:<session_name>）。这确保外部请求被路由到正确的 OpenClaw agent session，保持对话连续性和状态。

OASIS Server

OASIS Server 51202** Agent ** curl OASIS MCP Agent

• /
• workflow
• OASIS
• workflow

• OASIS bash selfskill/scripts/run.sh start
• user_id Authorization header

**API **

MCP

OASIS /

POST http://127.0.0.1:51202/topics

{"question":"","user_id":"system","max_rounds":3,"discussion":true,"schedule_file":"...","schedule_yaml":"...","callback_url":"http://127.0.0.1:51200/system_trigger","callback_session_id":"my-session"}

schedule_yamlyamlyaml/XXXXX/TeamClaw/data/user_files/username

curl OASIS

OASIS 51202 MCP curl user_id

1.

#  + 
curl 'http://127.0.0.1:51202/experts?user_id=xinyuan'

# 
curl -X POST 'http://127.0.0.1:51202/experts/user' \
  -H 'Content-Type: application/json' \
  -d '{"user_id":"xinyuan","name":"","tag":"pm","persona":"","temperature":0.7}'

# 
curl -X PUT 'http://127.0.0.1:51202/experts/user/pm' \
  -H 'Content-Type: application/json' \
  -d '{"user_id":"xinyuan","persona":""}'

# 
curl -X DELETE 'http://127.0.0.1:51202/experts/user/pm?user_id=xinyuan'

2.

#  OASIS  #oasis#  session
curl 'http://127.0.0.1:51202/sessions/oasis?user_id=xinyuan'

3. Workflow

#  workflows
curl 'http://127.0.0.1:51202/workflows?user_id=xinyuan'

#  workflow layout
curl -X POST 'http://127.0.0.1:51202/workflows' \
  -H 'Content-Type: application/json' \
  -d '{"user_id":"xinyuan","name":"trio_discussion","schedule_yaml":"version:1\nplan:\n - expert: \"creative#temp#1\"","description":"","save_layout":true}'

4. Layout

#  YAML  layout
curl -X POST 'http://127.0.0.1:51202/layouts/from-yaml' \
  -H 'Content-Type: application/json' \
  -d '{"user_id":"xinyuan","yaml_source":"version:1\nplan:\n - expert: \"creative#temp#1\"","layo

…(truncated)