Compactação

curl https://api.anthropic.com/v1/messages \
     --header "x-api-key: $ANTHROPIC_API_KEY" \
     --header "anthropic-version: 2023-06-01" \
     --header "anthropic-beta: compact-2026-01-12" \
     --header "content-type: application/json" \
     --data \
'{
    "model": "claude-opus-4-6",
    "max_tokens": 4096,
    "messages": [
        {
            "role": "user",
            "content": "Help me build a website"
        }
    ],
    "context_management": {
        "edits": [
            {
                "type": "compact_20260112"
            }
        ]
    }
}'

response = client.beta.messages.create(
    betas=["compact-2026-01-12"],
    model="claude-opus-4-6",
    max_tokens=4096,
    messages=messages,
    context_management={
        "edits": [
            {
                "type": "compact_20260112",
                "trigger": {"type": "input_tokens", "value": 150000},
            }
        ]
    },
)

response = client.beta.messages.create(
    betas=["compact-2026-01-12"],
    model="claude-opus-4-6",
    max_tokens=4096,
    messages=messages,
    context_management={
        "edits": [
            {
                "type": "compact_20260112",
                "instructions": "Focus on preserving code snippets, variable names, and technical decisions.",
            }
        ]
    },
)

response = client.beta.messages.create(
    betas=["compact-2026-01-12"],
    model="claude-opus-4-6",
    max_tokens=4096,
    messages=messages,
    context_management={
        "edits": [{"type": "compact_20260112", "pause_after_compaction": True}]
    },
)

# Check if compaction triggered a pause
if response.stop_reason == "compaction":
    # Response contains only the compaction block
    messages.append({"role": "assistant", "content": response.content})

    # Continue the request
    response = client.beta.messages.create(
        betas=["compact-2026-01-12"],
        model="claude-opus-4-6",
        max_tokens=4096,
        messages=messages,
        context_management={"edits": [{"type": "compact_20260112"}]},
    )

# After receiving a response with a compaction block
messages.append({"role": "assistant", "content": response.content})

# Continue the conversation
messages.append({"role": "user", "content": "Now add error handling"})

response = client.beta.messages.create(
    betas=["compact-2026-01-12"],
    model="claude-opus-4-6",
    max_tokens=4096,
    messages=messages,
    context_management={"edits": [{"type": "compact_20260112"}]},
)

import anthropic

client = anthropic.Anthropic()

with client.beta.messages.stream(
    betas=["compact-2026-01-12"],
    model="claude-opus-4-6",
    max_tokens=4096,
    messages=messages,
    context_management={"edits": [{"type": "compact_20260112"}]},
) as stream:
    for event in stream:
        if event.type == "content_block_start":
            if event.content_block.type == "compaction":
                print("Compaction started...")
            elif event.content_block.type == "text":
                print("Text response started...")

        elif event.type == "content_block_delta":
            if event.delta.type == "compaction_delta":
                print(f"Compaction complete: {len(event.delta.content)} chars")
            elif event.delta.type == "text_delta":
                print(event.delta.text, end="", flush=True)

    # Get the final accumulated message
    message = stream.get_final_message()
    messages.append({"role": "assistant", "content": message.content})

response = client.beta.messages.create(
    betas=["compact-2026-01-12"],
    model="claude-opus-4-6",
    max_tokens=4096,
    system=[
        {
            "type": "text",
            "text": "You are a helpful coding assistant...",
            "cache_control": {
                "type": "ephemeral"
            },  # Cache the system prompt separately
        }
    ],
    messages=messages,
    context_management={"edits": [{"type": "compact_20260112"}]},
)

count_response = client.beta.messages.count_tokens(
    betas=["compact-2026-01-12"],
    model="claude-opus-4-6",
    messages=messages,
    context_management={"edits": [{"type": "compact_20260112"}]},
)

print(f"Current tokens: {count_response.input_tokens}")
print(f"Original tokens: {count_response.context_management.original_input_tokens}")

import anthropic

client = anthropic.Anthropic()

messages: list[dict] = []


def chat(user_message: str) -> str:
    messages.append({"role": "user", "content": user_message})

    response = client.beta.messages.create(
        betas=["compact-2026-01-12"],
        model="claude-opus-4-6",
        max_tokens=4096,
        messages=messages,
        context_management={
            "edits": [
                {
                    "type": "compact_20260112",
                    "trigger": {"type": "input_tokens", "value": 100000},
                }
            ]
        },
    )

    # Append response (compaction blocks are automatically included)
    messages.append({"role": "assistant", "content": response.content})

    # Return the text content
    return next(block.text for block in response.content if block.type == "text")


# Run a long conversation
print(chat("Help me build a Python web scraper"))
print(chat("Add support for JavaScript-rendered pages"))
print(chat("Now add rate limiting and error handling"))
# ... continue as long as needed

import anthropic
from typing import Any

client = anthropic.Anthropic()

messages: list[dict[str, Any]] = []


def chat(user_message: str) -> str:
    messages.append({"role": "user", "content": user_message})

    response = client.beta.messages.create(
        betas=["compact-2026-01-12"],
        model="claude-opus-4-6",
        max_tokens=4096,
        messages=messages,
        context_management={
            "edits": [
                {
                    "type": "compact_20260112",
                    "trigger": {"type": "input_tokens", "value": 100000},
                    "pause_after_compaction": True,
                }
            ]
        },
    )

    # Check if compaction occurred and paused
    if response.stop_reason == "compaction":
        # Get the compaction block from the response
        compaction_block = response.content[0]

        # Preserve the last 2 messages (1 user + 1 assistant turn)
        # by including them after the compaction block
        preserved_messages = messages[-2:] if len(messages) >= 2 else messages

        # Build new message list: compaction + preserved messages
        new_assistant_content = [compaction_block]
        messages_after_compaction = [
            {"role": "assistant", "content": new_assistant_content}
        ] + preserved_messages

        # Continue the request with the compacted context + preserved messages
        response = client.beta.messages.create(
            betas=["compact-2026-01-12"],
            model="claude-opus-4-6",
            max_tokens=4096,
            messages=messages_after_compaction,
            context_management={"edits": [{"type": "compact_20260112"}]},
        )

        # Update our message list to reflect the compaction
        messages.clear()
        messages.extend(messages_after_compaction)

    # Append the final response
    messages.append({"role": "assistant", "content": response.content})

    # Return the text content
    return next(block.text for block in response.content if block.type == "text")


# Run a long conversation
print(chat("Help me build a Python web scraper"))
print(chat("Add support for JavaScript-rendered pages"))
print(chat("Now add rate limiting and error handling"))
# ... continue as long as needed