Обработка причин остановки

{
  "id": "msg_01234",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Here's the answer to your question..."
    }
  ],
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 100,
    "output_tokens": 50
  }
}

from anthropic import Anthropic

client = Anthropic()
response = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
)
if response.stop_reason == "end_turn":
    # Process the complete response
    print(response.content[0].text)

# INCORRECT: Adding text immediately after tool_result
messages = [
    {"role": "user", "content": "Calculate the sum of 1234 and 5678"},
    {
        "role": "assistant",
        "content": [
            {
                "type": "tool_use",
                "id": "toolu_123",
                "name": "calculator",
                "input": {"operation": "add", "a": 1234, "b": 5678},
            }
        ],
    },
    {
        "role": "user",
        "content": [
            {"type": "tool_result", "tool_use_id": "toolu_123", "content": "6912"},
            {
                "type": "text",
                "text": "Here's the result",  # Don't add text after tool_result
            },
        ],
    },
]

# CORRECT: Send tool results directly without additional text
messages = [
    {"role": "user", "content": "Calculate the sum of 1234 and 5678"},
    {
        "role": "assistant",
        "content": [
            {
                "type": "tool_use",
                "id": "toolu_123",
                "name": "calculator",
                "input": {"operation": "add", "a": 1234, "b": 5678},
            }
        ],
    },
    {
        "role": "user",
        "content": [
            {"type": "tool_result", "tool_use_id": "toolu_123", "content": "6912"}
        ],
    },  # Just the tool_result, no additional text
]


# If you still get empty responses after fixing the above:
def handle_empty_response(client, messages):
    response = client.messages.create(
        model="claude-opus-4-7", max_tokens=1024, messages=messages
    )

    # Check if response is empty
    if response.stop_reason == "end_turn" and not response.content:
        # INCORRECT: Don't just retry with the empty response
        # This won't work because Claude already decided it's done

        # CORRECT: Add a continuation prompt in a NEW user message
        messages.append({"role": "user", "content": "Please continue"})

        response = client.messages.create(
            model="claude-opus-4-7", max_tokens=1024, messages=messages
        )

    return response

# Request with limited tokens
response = client.messages.create(
    model="claude-opus-4-7",
    max_tokens=10,
    messages=[{"role": "user", "content": "Explain quantum physics"}],
)

if response.stop_reason == "max_tokens":
    # Response was truncated
    print("Response was cut off at token limit")
    # Consider making another request to continue

response = client.messages.create(
    model="claude-opus-4-7",
    max_tokens=1024,
    stop_sequences=["END", "STOP"],
    messages=[{"role": "user", "content": "Generate text until you say END"}],
)

if response.stop_reason == "stop_sequence":
    print(f"Stopped at sequence: {response.stop_sequence}")

from anthropic import Anthropic

client = Anthropic()
weather_tool = {
    "name": "get_weather",
    "description": "Get the current weather in a given location",
    "input_schema": {
        "type": "object",
        "properties": {
            "location": {"type": "string", "description": "City and state"},
        },
        "required": ["location"],
    },
}


def execute_tool(name, tool_input):
    """Execute a tool and return the result."""
    return f"Weather in {tool_input.get('location', 'unknown')}: 72°F"


response = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    tools=[weather_tool],
    messages=[{"role": "user", "content": "What's the weather?"}],
)

if response.stop_reason == "tool_use":
    # Extract and execute the tool
    for content in response.content:
        if content.type == "tool_use":
            result = execute_tool(content.name, content.input)
            # Return result to Claude for final response

response = client.messages.create(
    model="claude-opus-4-7",
    max_tokens=1024,
    tools=[{"type": "web_search_20250305", "name": "web_search"}],
    messages=[{"role": "user", "content": "Search for latest AI news"}],
)

if response.stop_reason == "pause_turn":
    # Continue the conversation by sending the response back
    messages = [
        {"role": "user", "content": original_query},
        {"role": "assistant", "content": response.content},
    ]
    continuation = client.messages.create(
        model="claude-opus-4-7",
        messages=messages,
        tools=[{"type": "web_search_20250305", "name": "web_search"}],
    )

response = client.messages.create(
    model="claude-opus-4-7",
    max_tokens=1024,
    messages=[{"role": "user", "content": "[Unsafe request]"}],
)

if response.stop_reason == "refusal":
    # Claude declined to respond
    print("Claude was unable to process this request")
    # Consider rephrasing or modifying the request

# Request with maximum tokens to get as much as possible
response = client.messages.create(
    model="claude-opus-4-7",
    max_tokens=64000,  # Practical non-streaming ceiling (Opus 4.7 supports 128K with streaming)
    messages=[
        {"role": "user", "content": "Large input that uses most of context window..."}
    ],
)

if response.stop_reason == "model_context_window_exceeded":
    # Response hit context window limit before max_tokens
    print("Response reached model's context window limit")
    # The response is still valid but was limited by context window

def handle_response(response):
    if response.stop_reason == "tool_use":
        return handle_tool_use(response)
    elif response.stop_reason == "max_tokens":
        return handle_truncation(response)
    elif response.stop_reason == "model_context_window_exceeded":
        return handle_context_limit(response)
    elif response.stop_reason == "pause_turn":
        return handle_pause(response)
    elif response.stop_reason == "refusal":
        return handle_refusal(response)
    else:
        # Handle end_turn and other cases
        return response.content[0].text

def handle_truncated_response(response):
    if response.stop_reason in ["max_tokens", "model_context_window_exceeded"]:
        # Option 1: Warn the user about the specific limit
        if response.stop_reason == "max_tokens":
            message = "[Response truncated due to max_tokens limit]"
        else:
            message = "[Response truncated due to context window limit]"
        return f"{response.content[0].text}\n\n{message}"

        # Option 2: Continue generation
        messages = [
            {"role": "user", "content": original_prompt},
            {"role": "assistant", "content": response.content[0].text},
        ]
        continuation = client.messages.create(
            model="claude-opus-4-7",
            max_tokens=1024,
            messages=messages + [{"role": "user", "content": "Please continue"}],
        )
        return response.content[0].text + continuation.content[0].text

def handle_server_tool_conversation(client, user_query, tools, max_continuations=5):
    """
    Handle server tool conversations that may require multiple continuations.

    The server runs a sampling loop when executing server tools. If the loop
    reaches its iteration limit, the API returns pause_turn. Continue the
    conversation by sending the response back to let Claude finish.
    """
    messages = [{"role": "user", "content": user_query}]

    for _ in range(max_continuations):
        response = client.messages.create(
            model="claude-opus-4-7", messages=messages, tools=tools
        )

        if response.stop_reason != "pause_turn":
            # Claude finished processing - return the final response
            return response

        # pause_turn: replace the full message list to maintain alternating roles
        messages = [
            {"role": "user", "content": user_query},
            {"role": "assistant", "content": response.content},
        ]

    # Reached max continuations - return the last response
    return response

import anthropic
from anthropic import Anthropic

client = Anthropic()

try:
    response = client.messages.create(
        model="claude-sonnet-4-20250514",
        max_tokens=1024,
        messages=[{"role": "user", "content": "Hello!"}],
    )

    # Handle successful response with stop_reason
    if response.stop_reason == "max_tokens":
        print("Response was truncated")

except anthropic.APIError as e:
    # Handle actual errors
    if e.status_code == 429:
        print("Rate limit exceeded")
    elif e.status_code == 500:
        print("Server error")

from anthropic import Anthropic

client = Anthropic()

with client.messages.stream(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
) as stream:
    for event in stream:
        if event.type == "message_delta":
            stop_reason = event.delta.stop_reason
            if stop_reason:
                print(f"Stream ended with: {stop_reason}")

def complete_tool_workflow(client, user_query, tools):
    messages = [{"role": "user", "content": user_query}]

    while True:
        response = client.messages.create(
            model="claude-opus-4-7", messages=messages, tools=tools
        )

        if response.stop_reason == "tool_use":
            # Execute tools and continue
            tool_results = execute_tools(response.content)
            messages.append({"role": "assistant", "content": response.content})
            messages.append({"role": "user", "content": tool_results})
        else:
            # Final response
            return response

def get_complete_response(client, prompt, max_attempts=3):
    messages = [{"role": "user", "content": prompt}]
    full_response = ""

    for _ in range(max_attempts):
        response = client.messages.create(
            model="claude-opus-4-7", messages=messages, max_tokens=4096
        )

        full_response += response.content[0].text

        if response.stop_reason != "max_tokens":
            break

        # Continue from where it left off
        messages = [
            {"role": "user", "content": prompt},
            {"role": "assistant", "content": full_response},
            {"role": "user", "content": "Please continue from where you left off."},
        ]

    return full_response

def get_max_possible_tokens(client, prompt):
    """
    Get as many tokens as possible within the model's context window
    without needing to calculate input token count
    """
    response = client.messages.create(
        model="claude-opus-4-7",
        messages=[{"role": "user", "content": prompt}],
        max_tokens=64000,  # Practical non-streaming ceiling (Opus 4.7 supports 128K with streaming)
    )

    if response.stop_reason == "model_context_window_exceeded":
        # Got the maximum possible tokens given input size
        print(
            f"Generated {response.usage.output_tokens} tokens (context limit reached)"
        )
    elif response.stop_reason == "max_tokens":
        # Got exactly the requested tokens
        print(f"Generated {response.usage.output_tokens} tokens (max_tokens reached)")
    else:
        # Natural completion
        print(f"Generated {response.usage.output_tokens} tokens (natural completion)")

    return response.content[0].text