ai-agent-book 精选快照（<2MB 代码与文档，来自 github.com/bojieli/ai-agent-book）

chapter9/browser-use-rpa/browser-use/docs/customize/agent/all-parameters.mdx

@@ -0,0 +1,54 @@
+---
+title: "All Parameters"
+description: "Complete reference for all agent configuration options"
+icon: "sliders"
+mode: "wide"
+---
+
+## Available Parameters
+
+### Core Settings
+- `tools`: Registry of [our tools](https://github.com/browser-use/browser-use/blob/main/browser_use/tools/service.py) the agent can call. [Example for custom tools](https://github.com/browser-use/browser-use/tree/main/examples/custom-functions)
+- `browser`: Browser object where you can specify the browser settings.
+- `output_model_schema`: Pydantic model class for structured output validation. [Example](https://github.com/browser-use/browser-use/blob/main/examples/features/custom_output.py)
+
+### Vision & Processing
+- `use_vision` (default: `True`): Enable/disable vision capabilities for processing screenshots
+- `vision_detail_level` (default: `'auto'`): Screenshot detail level - `'low'`, `'high'`, or `'auto'`
+- `page_extraction_llm`: Separate LLM model for page content extraction. You can choose a small & fast model because it only needs to extract text from the page (default: same as `llm`)
+
+### Actions & Behavior
+- `initial_actions`: List of actions to run before the main task without LLM. [Example](https://github.com/browser-use/browser-use/blob/main/examples/features/initial_actions.py)
+- `max_actions_per_step` (default: `10`): Maximum actions per step, e.g. for form filling the agent can output 10 fields at once. We execute the actions until the page changes.
+- `max_failures` (default: `3`): Maximum retries for steps with errors
+- `final_response_after_failure` (default: `True`): If True, attempt to force one final model call with intermediate output after max_failures is reached
+- `use_thinking` (default: `True`): Controls whether the agent uses its internal "thinking" field for explicit reasoning steps.
+- `flash_mode` (default: `False`): Fast mode that skips evaluation, next goal and thinking and only uses memory. If `flash_mode` is enabled, it overrides `use_thinking` and disables the thinking process entirely. [Example](https://github.com/browser-use/browser-use/blob/main/examples/getting_started/05_fast_agent.py)
+
+### System Messages
+- `override_system_message`: Completely replace the default system prompt. 
+- `extend_system_message`: Add additional instructions to the default system prompt. [Example](https://github.com/browser-use/browser-use/blob/main/examples/features/custom_system_prompt.py)
+
+### File & Data Management
+- `save_conversation_path`: Path to save complete conversation history
+- `save_conversation_path_encoding` (default: `'utf-8'`): Encoding for saved conversations
+- `available_file_paths`: List of file paths the agent can access
+- `sensitive_data`: Dictionary of sensitive data to handle carefully. [Example](https://github.com/browser-use/browser-use/blob/main/examples/features/sensitive_data.py)
+
+### Visual Output
+- `generate_gif` (default: `False`): Generate GIF of agent actions. Set to `True` or string path
+- `include_attributes`: List of HTML attributes to include in page analysis
+
+### Performance & Limits
+- `max_history_items`: Maximum number of last steps to keep in the LLM memory. If `None`, we keep all steps. 
+- `llm_timeout` (default: `90`): Timeout in seconds for LLM calls
+- `step_timeout` (default: `120`): Timeout in seconds for each step
+- `directly_open_url` (default: `True`): If we detect a url in the task, we directly open it.
+
+### Advanced Options
+- `calculate_cost` (default: `False`): Calculate and track API costs
+- `display_files_in_done_text` (default: `True`): Show file information in completion messages
+
+### Backwards Compatibility
+- `controller`: Alias for `tools` for backwards compatibility.
+- `browser_session`: Alias for `browser` for backwards compatibility.

chapter9/browser-use-rpa/browser-use/docs/customize/agent/basics.mdx

@@ -0,0 +1,27 @@
+---
+title: "Basics"
+description: ""
+icon: "play"
+mode: "wide"
+---
+
+
+```python
+from browser_use import Agent, ChatOpenAI
+
+agent = Agent(
+    task="Search for latest news about AI",
+    llm=ChatOpenAI(model="gpt-4.1-mini"),
+)
+
+async def main():
+    history = await agent.run(max_steps=100)
+```
+
+- `task`: The task you want to automate.
+- `llm`: Your favorite LLM. See <a href="/customize/supported-models">Supported Models</a>.
+
+
+The agent is executed using the async `run()` method:
+
+- `max_steps` (default: `100`): Maximum number of steps an agent can take.

chapter9/browser-use-rpa/browser-use/docs/customize/agent/output-format.mdx

@@ -0,0 +1,45 @@
+---
+title: "Output Format"
+description: ""
+icon: "arrow-right-to-bracket"
+mode: "wide"
+---
+
+## Agent History
+
+The `run()` method returns an `AgentHistoryList` object with the complete execution history:
+
+```python
+history = await agent.run()
+
+# Access useful information
+history.urls()                    # List of visited URLs
+history.screenshot_paths()        # List of screenshot paths  
+history.screenshots()             # List of screenshots as base64 strings
+history.action_names()            # Names of executed actions
+history.extracted_content()       # List of extracted content from all actions
+history.errors()                  # List of errors (with None for steps without errors)
+history.model_actions()           # All actions with their parameters
+history.model_outputs()           # All model outputs from history
+history.last_action()             # Last action in history
+
+# Analysis methods
+history.final_result()            # Get the final extracted content (last step)
+history.is_done()                 # Check if agent completed successfully
+history.is_successful()           # Check if agent completed successfully (returns None if not done)
+history.has_errors()              # Check if any errors occurred
+history.model_thoughts()          # Get the agent's reasoning process (AgentBrain objects)
+history.action_results()          # Get all ActionResult objects from history
+history.action_history()          # Get truncated action history with essential fields
+history.number_of_steps()         # Get the number of steps in the history
+history.total_duration_seconds()  # Get total duration of all steps in seconds
+
+# Structured output (when using output_model_schema)
+history.structured_output         # Property that returns parsed structured output
+```
+
+See all helper methods in the [AgentHistoryList source code](https://github.com/browser-use/browser-use/blob/main/browser_use/agent/views.py#L301).
+
+## Structured Output
+
+For structured output, use the `output_model_schema` parameter with a Pydantic model. [Example](https://github.com/browser-use/browser-use/blob/main/examples/features/custom_output.py).

chapter9/browser-use-rpa/browser-use/docs/customize/agent/prompting-guide.mdx

@@ -0,0 +1,92 @@
+---
+title: "Prompting Guide"
+description: "Tips and tricks "
+icon: "lightbulb"
+---
+
+Prompting can trasticly improve performance and solve existing limitations of the library.
+
+### 1. Be Specific vs Open-Ended
+
+**✅ Specific (Recommended)**
+```python
+task = """
+1. Go to https://quotes.toscrape.com/
+2. Use extract_structured_data action with the query "first 3 quotes with their authors"
+3. Save results to quotes.csv using write_file action
+4. Do a google search for the first quote and find when it was written
+"""
+```
+
+**❌ Open-Ended**
+```python
+task = "Go to web and make money"
+```
+
+### 2. Name Actions Directly
+
+When you know exactly what the agent should do, reference actions by name:
+
+```python
+task = """
+1. Use search_google action to find "Python tutorials"
+2. Use click_element_by_index to open first result in a new tab   
+3. Use scroll action to scroll down 2 pages
+4. Use extract_structured_data to extract the names of the first 5 items 
+5. Wait for 2 seconds if the page is not loaded, refresh it and wait 10 sec
+6. Use send_keys action with "Tab Tab ArrowDown Enter" 
+"""
+```
+
+See [Available Tools](/customize/tools/available) for the complete list of actions.
+
+
+### 3. Handle interaction problems via keyboard navigation
+
+Sometimes buttons can't be clicked (you found a bug in the library - open an issue). 
+Good news - often you can work around it with keyboard navigation!
+
+```python
+task = """
+If the submit button cannot be clicked:
+1. Use send_keys action with "Tab Tab Enter" to navigate and activate
+2. Or use send_keys with "ArrowDown ArrowDown Enter" for form submission
+"""
+```
+
+
+
+
+### 4. Custom Actions Integration
+
+```python
+# When you have custom actions
+@controller.action("Get 2FA code from authenticator app")
+async def get_2fa_code():
+    # Your implementation
+    pass
+
+task = """
+Login with 2FA:
+1. Enter username/password
+2. When prompted for 2FA, use get_2fa_code action
+3. NEVER try to extract 2FA codes from the page manually
+4. ALWAYS use the get_2fa_code action for authentication codes
+"""
+```
+
+### 5. Error Recovery
+
+```python
+task = """
+Robust data extraction:
+1. Go to openai.com to find their CEO
+2. If navigation fails due to anti-bot protection:
+   - Use google search to find the CEO
+3. If page times out, use go_back and try alternative approach
+"""
+```
+
+
+
+The key to effective prompting is being specific about actions.

chapter9/browser-use-rpa/browser-use/docs/customize/agent/supported-models.mdx

@@ -0,0 +1,254 @@
+---
+title: "Supported Models"
+description: "Choose your favorite LLM"
+icon: "robot"
+
+---
+
+### Recommendations
+
+- Best accuracy: `O3`
+- Fastest: `llama4` on groq
+- Balanced: fast + cheap + clever: `gemini-2.5-flash` or `gpt-4.1-mini`
+
+
+### OpenAI [example](https://github.com/browser-use/browser-use/blob/main/examples/models/gpt-4.1.py)
+
+`O3` model is recommended for best performance.
+
+```python
+from browser_use import Agent, ChatOpenAI
+
+# Initialize the model
+llm = ChatOpenAI(
+    model="o3",
+)
+
+# Create agent with the model
+agent = Agent(
+    task="...", # Your task here
+    llm=llm
+)
+```
+
+Required environment variables:
+
+```bash .env
+OPENAI_API_KEY=
+```
+
+<Info>
+  You can use any OpenAI compatible model by passing the model name to the
+  `ChatOpenAI` class using a custom URL (or any other parameter that would go
+  into the normal OpenAI API call).
+</Info>
+
+### Anthropic [example](https://github.com/browser-use/browser-use/blob/main/examples/models/claude-4-sonnet.py)
+
+```python
+from browser_use import Agent, ChatAnthropic
+
+# Initialize the model
+llm = ChatAnthropic(
+    model="claude-sonnet-4-0",
+)
+
+# Create agent with the model
+agent = Agent(
+    task="...", # Your task here
+    llm=llm
+)
+```
+
+And add the variable:
+
+```bash .env
+ANTHROPIC_API_KEY=
+```
+
+### Azure OpenAI [example](https://github.com/browser-use/browser-use/blob/main/examples/models/azure_openai.py)
+
+```python
+from browser_use import Agent, ChatAzureOpenAI
+from pydantic import SecretStr
+import os
+
+# Initialize the model
+llm = ChatAzureOpenAI(
+    model="o4-mini",
+)
+
+# Create agent with the model
+agent = Agent(
+    task="...", # Your task here
+    llm=llm
+)
+```
+
+Required environment variables:
+
+```bash .env
+AZURE_OPENAI_ENDPOINT=https://your-endpoint.openai.azure.com/
+AZURE_OPENAI_API_KEY=
+```
+
+### Gemini [example](https://github.com/browser-use/browser-use/blob/main/examples/models/gemini.py)
+
+> [!IMPORTANT] `GEMINI_API_KEY` was the old environment var name, it should be called `GOOGLE_API_KEY` as of 2025-05.
+
+```python
+from browser_use import Agent, ChatGoogle
+from dotenv import load_dotenv
+
+# Read GOOGLE_API_KEY into env
+load_dotenv()
+
+# Initialize the model
+llm = ChatGoogle(model='gemini-2.5-flash')
+
+# Create agent with the model
+agent = Agent(
+    task="Your task here",
+    llm=llm
+)
+```
+
+Required environment variables:
+
+```bash .env
+GOOGLE_API_KEY=
+```
+
+### AWS Bedrock [example](https://github.com/browser-use/browser-use/blob/main/examples/models/aws.py)
+
+AWS Bedrock provides access to multiple model providers through a single API. We support both a general AWS Bedrock client and provider-specific convenience classes.
+
+#### General AWS Bedrock (supports all providers)
+
+```python
+from browser_use import Agent, ChatAWSBedrock
+
+# Works with any Bedrock model (Anthropic, Meta, AI21, etc.)
+llm = ChatAWSBedrock(
+    model="anthropic.claude-3-5-sonnet-20240620-v1:0",  # or any Bedrock model
+    aws_region="us-east-1",
+)
+
+# Create agent with the model
+agent = Agent(
+    task="Your task here",
+    llm=llm
+)
+```
+
+#### Anthropic Claude via AWS Bedrock (convenience class)
+
+```python
+from browser_use import Agent, ChatAnthropicBedrock
+
+# Anthropic-specific class with Claude defaults
+llm = ChatAnthropicBedrock(
+    model="anthropic.claude-3-5-sonnet-20240620-v1:0",
+    aws_region="us-east-1",
+)
+
+# Create agent with the model
+agent = Agent(
+    task="Your task here",
+    llm=llm
+)
+```
+
+#### AWS Authentication
+
+Required environment variables:
+
+```bash .env
+AWS_ACCESS_KEY_ID=
+AWS_SECRET_ACCESS_KEY=
+AWS_DEFAULT_REGION=us-east-1
+```
+
+You can also use AWS profiles or IAM roles instead of environment variables. The implementation supports:
+
+- Environment variables (`AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, `AWS_DEFAULT_REGION`)
+- AWS profiles and credential files
+- IAM roles (when running on EC2)
+- Session tokens for temporary credentials
+- AWS SSO authentication (`aws_sso_auth=True`)
+
+## Groq [example](https://github.com/browser-use/browser-use/blob/main/examples/models/llama4-groq.py)
+
+```python
+from browser_use import Agent, ChatGroq
+
+llm = ChatGroq(model="meta-llama/llama-4-maverick-17b-128e-instruct")
+
+agent = Agent(
+    task="Your task here",
+    llm=llm
+)
+```
+
+Required environment variables:
+
+```bash .env
+GROQ_API_KEY=
+```
+
+## Ollama
+
+1. Install Ollama: https://github.com/ollama/ollama
+2. Run `ollama serve` to start the server 
+3. In a new terminal, install the model you want to use: `ollama pull llama3.1:8b` (this has 4.9GB)
+
+```python
+from browser_use import Agent, ChatOllama
+
+llm = ChatOllama(model="llama3.1:8b")
+```
+
+## Langchain
+
+[Example](https://github.com/browser-use/browser-use/blob/main/examples/models/langchain) on how to use Langchain with Browser Use.
+
+## Qwen [example](https://github.com/browser-use/browser-use/blob/main/examples/models/qwen.py)
+
+Currently, only `qwen-vl-max` is recommended for Browser Use. Other Qwen models, including `qwen-max`, have issues with the action schema format.
+Smaller Qwen models may return incorrect action schema formats (e.g., `actions: [{"go_to_url": "google.com"}]` instead of `[{"go_to_url": {"url": "google.com"}}]`). If you want to use other models, add concrete examples of the correct action format to your prompt.
+
+```python
+from browser_use import Agent, ChatOpenAI
+from dotenv import load_dotenv
+import os
+
+load_dotenv()
+
+# Get API key from https://modelstudio.console.alibabacloud.com/?tab=playground#/api-key
+api_key = os.getenv('ALIBABA_CLOUD')
+base_url = 'https://dashscope-intl.aliyuncs.com/compatible-mode/v1'
+
+llm = ChatOpenAI(model='qwen-vl-max', api_key=api_key, base_url=base_url)
+
+agent = Agent(
+    task="Your task here",
+    llm=llm,
+    use_vision=True
+)
+```
+
+Required environment variables:
+
+```bash .env
+ALIBABA_CLOUD=
+```
+
+
+## Other models (DeepSeek, Novita, X...)
+
+We support all other models that can be called via OpenAI compatible API. We are open to PRs for more providers.
+
+**Examples available:**
+- [DeepSeek](https://github.com/browser-use/browser-use/blob/main/examples/models/deepseek-chat.py)
+- [Novita](https://github.com/browser-use/browser-use/blob/main/examples/models/novita.py)
+- [OpenRouter](https://github.com/browser-use/browser-use/blob/main/examples/models/openrouter.py)