Context Compression

Synthra’s context compression engine intelligently manages conversation context windows. Automatically triggered when approaching token limits.

Compression Strategies

FIFO (First In, First Out)

Removes oldest messages. Simple and fast (under 10ms).

agent.setContextConfig({
  retentionPolicy: 'fifo',
  maxTokens: 4096
});

Priority-Based

Removes lowest priority messages. Ideal for complex conversations (under 30ms).

agent.setContextConfig({
  retentionPolicy: 'priority',
  maxTokens: 8192
});

Semantic Retention

Removes redundant content using embeddings. Best for long-form content (under 50ms).

agent.setContextConfig({
  retentionPolicy: 'semantic',
  maxTokens: 16384
});

Token Limits

Tier	Context Window	Compression Threshold
Free	4,096 tokens	80% (3,277 tokens)
Pro	8,192 tokens	80% (6,554 tokens)
Enterprise	32,768 tokens	85% (27,853 tokens)

Manual Compression

await agent.compressContext(session.id);

const stats = await agent.getCompressionStats(session.id);
console.log(`Removed: ${stats.messagesRemoved}`);
console.log(`Saved: ${stats.tokensSaved} tokens`);

Best Practices

Scenario	Strategy
Customer support	FIFO
Multi-turn conversations	Priority
Content generation	Semantic

Compression is non-destructive when archiving is enabled. Removed messages can be retrieved from the archive.

Semantic compression adds 20-30ms latency. Use FIFO or priority for latency-sensitive applications.

GETTING STARTED

CORE FEATURES

INTEGRATIONS

ABOUT

Context Compression

Compression Strategies

FIFO (First In, First Out)

Priority-Based

Semantic Retention

Token Limits

Manual Compression

Best Practices

​Compression Strategies

​FIFO (First In, First Out)

​Priority-Based

​Semantic Retention

​Token Limits

​Manual Compression

​Best Practices

Compression Strategies

FIFO (First In, First Out)

Priority-Based

Semantic Retention

Token Limits

Manual Compression

Best Practices