Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Python agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript
docs: mark HeadroomClient provider as required, not auto-detected (#3832)
Anton Dziatkovskiid06f96fbda14
diff --git a/docs/content/docs/api-reference.mdx b/docs/content/docs/api-reference.mdxindex d6cf14651..3fdaa9d4d 100644--- a/docs/content/docs/api-reference.mdx+++ b/docs/content/docs/api-reference.mdx@@ -41,7 +41,7 @@ const client = new HeadroomClient({<TypeTable type={{original_client: { type: 'OpenAI | Anthropic', description: 'The underlying LLM client', default: 'Required' },- provider: { type: 'Provider', description: 'Token counting provider', default: 'Auto-detected' },+ provider: { type: 'Provider', description: 'Token counting provider', default: 'Required' },default_mode: { type: '"audit" | "optimize"', description: 'Default compression mode', default: '"audit"' },store_url: { type: 'str | None', description: 'Storage URL for metrics database', default: 'None' },config: { type: 'HeadroomConfig | None', description: 'Compression and cache alignment settings (set config.smart_crusher / config.cache_aligner)', default: 'Default config' },