Google Agents Cli Adk Code

# ADK 2.0 Workflow API Cheatsheet

> **Experimental (Pre-GA)** — The Workflow API requires ADK 2.0 (`google-adk >= 2.0.0`). APIs may change before GA.
> Python only. **Incompatible with Live Streaming.** Requires **Python >= 3.11**.
>
> **WARNING:** Do NOT allow ADK 2.0 projects to share persistent storage with ADK 1.x projects — this can cause data loss or corruption.

### Upgrading a scaffolded project to ADK 2.0

Scaffolded projects pin `google-adk<2.0.0` — this must be updated before ADK 2.0 can install. Simply running `pip install --pre google-adk` or `uv add --prerelease=allow google-adk` will silently stay on 1.x.

**Step 1 — Update `pyproject.toml`:**

```toml
# Under [project] > dependencies, remove the <2.0.0 upper bound:
"google-adk>=2.0.0a1",          # was: "google-adk>=1.15.0,<2.0.0"

# If you have eval extras, update those too:
# [project.optional-dependencies]
# eval = ["google-adk[eval]>=2.0.0a1"]   # was: "google-adk[eval]>=1.15.0,<2.0.0"
```

**Step 2 — Reinstall dependencies:**

```bash
uv sync --prerelease=allow      # with uv
# or
pip install --pre -e ".[eval]"  # with pip
```

**Step 3 — Verify:**

```bash
python -c "import google.adk.workflow; print('Workflow API available')"
```

### New project (no scaffolding)

```bash
pip install --pre google-adk
# or with uv:
uv add --prerelease=allow google-adk
```

**Official docs:** [Workflows overview](https://adk.dev/workflows/index.md) ·
[Graph routes](https://adk.dev/graphs/routes/index.md) ·
[Collaboration](https://adk.dev/workflows/collaboration/index.md) ·
[Data handling](https://adk.dev/graphs/data-handling/index.md) ·
[Dynamic workflows](https://adk.dev/graphs/dynamic/index.md) ·
[Human-in-the-loop](https://adk.dev/graphs/human-input/index.md)

## 1. Core Concepts

A `Workflow` is a graph-based agent: nodes do work, edges define flow, `START` is the entry point.

```python
from google.adk.workflow import Workflow

def greet(node_input: str) -> str:
  return f"Hello, {node_input}!"

root_agent = Workflow(
    name="greeter",
    edges=[('START', greet)],
)
```

Three building blocks: **Nodes** (functions, LLM agents, tools), **Edges** (connections with optional route conditions), **START** (built-in entry receiving user input).

### Workflow Constructor

```python
root_agent = Workflow(
    name="my_workflow",
    edges=[...],                # Edge definitions (or use graph= instead)
    input_schema=None,          # Pydantic model for input validation
    rerun_on_resume=True,       # Rerun workflow on resume (default: True)
    max_concurrency=None,       # Limit parallel node execution (None = no limit)
    state_schema=None,          # Pydantic model for state validation
)
```

---

## 2. Node Types

Any "NodeLike" is accepted in edges and auto-wrapped:

| Python Object | Wrapped As | Default `rerun_on_resume` |
|--------------|-----------|------------------------|
| Function/callable | `FunctionNode` | `False` |
| `LlmAgent` | Internal `_LlmAgentWrapper` | `True` |
| Other `BaseAgent` | Internal `AgentNode` | `False` |
| `BaseTool` | Internal `_ToolNode` | `False` |
| `BaseNode` subclass | Used as-is | Per subclass |

> **Auto-wrapping is the recommended approach.** Place functions, agents, and tools directly in edges — the framework wraps them automatically. You do not need to import or use internal wrapper classes directly.

---

## 3. Function Nodes

Most common node type. Parameter resolution:

| Parameter | Source |
|-----------|--------|
| `ctx` | Workflow `Context` object |
| `node_input` | Output from predecessor node |
| Any other name | `ctx.state[param_name]` |

```python
from google.adk.agents.context import Context

def process(ctx: Context, node_input: Any, user_name: str) -> str:
  # node_input = predecessor output; user_name = ctx.state['user_name']
  # START outputs types.Content (not str) unless input_schema is set
  return f"{user_name}: {node_input}"
```

### Return Types

- **Value** -> wrapped in `Event(output=value)`, triggers