{"uid":"cap_uOAPhsTy38Daw0Fov5jdY","slug":"shopify-spy-agentdiet-dev-context-trimmer-url-html-distiller-with-50ff549e","name":"Context Trimmer: URL & HTML Distiller with BM25 Budget Control","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://shopify-spy.agentdiet.dev/v1/context-trimmer)","url":"https://shopify-spy.agentdiet.dev/v1/context-trimmer?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","required":["url"],"properties":{"url":{"type":"string","minLength":1,"description":"Target webpage URL to fetch and distill (or builtin://stripe-docs)"},"html":{"type":"string","description":"Optional raw HTML string to distill directly without fetching"},"mode":{"enum":["markdown","structured","skeleton","budget"],"type":"string","default":"markdown","description":"Distillation mode"},"query":{"type":"string","description":"BM25 focus query when mode=budget"},"max_tokens":{"type":"integer","minimum":20,"description":"Strict token budget ceiling when mode=budget"}}},"responseSchema":{"type":"object","required":["status","roi_proof","data"],"properties":{"data":{"type":"object","description":"Distilled Markdown, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt."},"cache":{"type":"object","properties":{"status":{"enum":["HIT","MISS"],"type":"string"},"cache_key":{"type":"string"},"latency_ms":{"type":"number"}}},"status":{"type":"string","description":"Execution status ('ok')"},"billing":{"type":"object","properties":{"agent_id":{"type":"string"},"payment_method":{"type":"string"},"fee_charged_usd":{"type":"number"}}},"roi_proof":{"type":"object","properties":{"raw_tokens":{"type":"integer"},"tokens_saved":{"type":"integer"},"roi_multiplier":{"type":"number"},"distilled_tokens":{"type":"integer"},"llm_cost_saved_usd":{"type":"number"},"compression_ratio_pct":{"type":"number"}}}}},"example":null,"exampleRequest":null,"tags":[],"displayCostAmount":"0.001","displayCostAsset":"USD","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.001/call","primary":{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_yeevfJgJR7B6If0kWeRzV","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"shopify-spy.agentdiet.dev","brandSlug":"shopify-spy-agentdiet-dev-mpp","brandBaseUrl":"https://shopify-spy.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into compact, agent-ready tokens using BM25-ranked budget control with a configurable token ceiling","exampleAgentPrompt":"Fetch https://stripe.com/docs/api/charges and distill it into budget mode, focusing on 'payment intents refund flow', keeping it under 800 tokens so I can fit it in my prompt without wasting context.","exampleUseCases":[{"title":"Stripe docs agent context fitting","prompt":"Grab the Stripe documentation page at builtin://stripe-docs and distill it in budget mode with the query 'webhook signature verification' — keep it under 600 tokens so my agent can reason over it without blowing the context window."},{"title":"Competitor product page analysis","prompt":"Take this raw HTML from a Shopify store product page and distill it into structured mode so I can extract the pricing tables and metadata cleanly — here's the HTML: <html>...</html>."},{"title":"Research article skeleton extraction","prompt":"Distill https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) into skeleton mode so I get just the headings and outline without all the body text flooding my context."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd — giving the agent quantified proof of how much context and cost was saved. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","Raw HTML is empty or malformed — distillation may produce minimal or no output","max_tokens set too low (below 20) — rejected by schema validation","BM25 query provided without mode=budget — query may be ignored","Rate limiting or payment failure via x402 — 402 response requiring payment","Token budget too tight for meaningful extraction — output may be truncated or empty"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to process web pages or HTML within a strict token budget, especially when LLM context window costs matter. It is superior to generic scrapers when you need BM25-ranked relevance filtering (mode=budget with a query) to surface only the most pertinent content. Prefer it over raw fetch-and-pass approaches when working with long documentation pages, product pages, or research articles where most content is noise. The ROI proof output makes it especially useful in cost-conscious agentic pipelines.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:30.980Z","isFirstParty":false,"canonicalSlug":"shopify-spy-agentdiet-dev-context-trimmer-url-html-distiller-with-50ff549e"}