{"uid":"cap_qh8f6EsY71Op3FdAIuFAf","slug":"hn-pulse-agentdiet-dev-bm25-budget-controlled-web-distillation-7750e6f0","name":"BM25 Budget-Controlled Web Distillation (Context Trimmer)","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://hn-pulse.agentdiet.dev/v1/context-trimmer)","url":"https://hn-pulse.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_6CqYS-jxg6p2HyxBsHT6c","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"hn-pulse.agentdiet.dev","brandSlug":"hn-pulse-agentdiet-dev-mpp","brandBaseUrl":"https://hn-pulse.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compact, token-budgeted agent-ready content using BM25 ranking and multiple output modes.","exampleAgentPrompt":"Fetch the Stripe docs page at https://stripe.com/docs/payments and distill it in budget mode focused on 'webhook events', keeping it under 500 tokens so I can fit it in my context window.","exampleUseCases":[{"title":"Token-budget research from live URL","prompt":"Grab the content from https://openai.com/research/gpt-4 and trim it down to 300 tokens using budget mode, focusing on 'safety evaluations' — I need just the relevant bits for my agent."},{"title":"Structured data extraction from HTML","prompt":"I have raw HTML from a product listing page — can you distill it into structured tables and metadata so my agent can parse the pricing and specs easily?"},{"title":"Skeleton outline of a long article","prompt":"Fetch https://en.wikipedia.org/wiki/Large_language_model and give me a skeleton outline of the page so I can understand its structure without blowing my context window."}],"resultDescription":"Returns a status field, distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), an roi_proof object showing raw vs distilled token counts, compression ratio, and estimated LLM cost saved, plus optional billing and cache hit/miss info.","failureModes":["URL unreachable or returns non-200 — distillation fails with an error status","HTML too short or empty — minimal or no compression achieved","Token budget set below minimum (20) — validation error","BM25 query not provided in budget mode — may fall back to generic distillation","Rate limiting or payment failure — 402 response if payment not attached"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of web content before feeding it to an LLM, especially when you have a strict context window or cost budget. The BM25 budget mode is uniquely useful when you want only the most query-relevant passages from a long page, not a generic summary. Prefer this over generic scrapers when ROI proof and token savings metrics are important for your agent's cost accounting.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:10.617Z","isFirstParty":false,"canonicalSlug":"hn-pulse-agentdiet-dev-bm25-budget-controlled-web-distillation-7750e6f0"}