Context Compaction

import os
from xai_sdk import Client
from xai_sdk.chat import system, user

client = Client(api_key=os.environ["XAI_API_KEY"])

# Build up a chat normally — system prompt plus a few user/assistant turns.
# use_encrypted_content=True is recommended for reasoning models so the model's
# reasoning content from prior turns is preserved through the compaction.
chat = client.chat.create(model="grok-4.5", use_encrypted_content=True)
chat.append(system("You are a concise and knowledgeable science tutor."))

chat.append(user("What is the Higgs boson and why is it important?"))
chat.append(chat.sample())

chat.append(user("How does the Higgs mechanism actually work?"))
chat.append(chat.sample())

# ... many more turns ...

# Step 1 — compact the conversation. Pass the chat's accumulated messages
# straight into compact_context.
compact = client.chat.compact_context(
    model="grok-4.5",
    messages=chat.messages,
)
print(f"Compaction ID:    {compact.id}")
print(f"Dropped messages: {compact.dropped_message_count}")
print(f"Tokens used:      {compact.usage.total_tokens}")

# Step 2 — continue the conversation. chat.append(compact) clears the
# in-memory message list on the chat object and seeds it with just the
# compaction blob, so subsequent chat.sample() calls run on top of the
# compacted context instead of replaying the full prior history.
chat.append(compact)
chat.append(user("Based on our earlier conversation, what gives particles their mass?"))
print(chat.sample().content)

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["XAI_API_KEY"],
    base_url="https://api.x.ai/v1",
)

# Step 1 — compact the long conversation
compacted = client.responses.compact(
    model="grok-4.5",
    input=[
        {"role": "system", "content": "You are a concise and knowledgeable science tutor."},
        {"role": "user", "content": "What is the Higgs boson and why is it important?"},
        {"role": "assistant", "content": "The Higgs boson is an elementary particle..."},
        {"role": "user", "content": "How does the Higgs mechanism actually work?"},
        {"role": "assistant", "content": "The Higgs mechanism works through spontaneous symmetry breaking..."},
    ],
)

print(f"Compaction ID:    {compacted.id}")
print(f"Dropped messages: {compacted.usage.dropped_message_count}")
print(f"Output tokens:    {compacted.usage.output_tokens}")

# Step 2 — continue the conversation. Spread compacted.output into the next input.
followup = client.responses.create(
    model="grok-4.5",
    input=[
        *compacted.output,  # use the compaction item verbatim — do not modify
        {"role": "user", "content": "Based on our earlier conversation, what gives particles their mass?"},
    ],
)

print(followup.output_text)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.XAI_API_KEY,
  baseURL: "https://api.x.ai/v1",
});

// Step 1 — compact the long conversation
const compacted = await client.responses.compact({
  model: "grok-4.5",
  input: [
    { role: "system", content: "You are a concise and knowledgeable science tutor." },
    { role: "user", content: "What is the Higgs boson and why is it important?" },
    { role: "assistant", content: "The Higgs boson is an elementary particle..." },
    { role: "user", content: "How does the Higgs mechanism actually work?" },
    { role: "assistant", content: "The Higgs mechanism works through spontaneous symmetry breaking..." },
  ],
});

console.log(`Compaction ID:    ${compacted.id}`);
console.log(`Dropped messages: ${compacted.usage.dropped_message_count}`);
console.log(`Output tokens:    ${compacted.usage.output_tokens}`);

// Step 2 — continue the conversation. Spread compacted.output into the next input.
const followup = await client.responses.create({
  model: "grok-4.5",
  input: [
    ...compacted.output, // use the compaction item verbatim — do not modify
    { role: "user", content: "Based on our earlier conversation, what gives particles their mass?" },
  ],
});

console.log(followup.output_text);