{"uid":"cap_HIz378cOz4Kk4gAzfMYW6","slug":"hn-pulse-agentdiet-dev-spa-markdown-reader-bm25-budget-controlled-web-7ff569da","name":"SPA Markdown Reader — BM25 Budget-Controlled Web Distiller","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/spa-markdown-reader)","url":"https://hn-pulse.agentdiet.dev/v1/spa-markdown-reader?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_eVXo_COP5Bv0_WROxbrAF","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 a URL or accepts raw HTML and distills it into clean Markdown, structured JSON, a skeleton outline, or a BM25-ranked token-budget excerpt","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into clean markdown using budget mode focused on the query 'payment intents', keeping it under 2000 tokens.","exampleUseCases":[{"title":"LLM context-window budget extraction","prompt":"Pull the content from https://openai.com/research/gpt-4 and give me only the parts most relevant to 'multimodal capabilities' — keep it under 1500 tokens using budget mode."},{"title":"Documentation page to clean Markdown","prompt":"Convert the raw HTML of this Next.js docs page into clean markdown so I can paste it into my agent's context — use markdown mode and strip all the navigation and footer junk."},{"title":"Structured metadata extraction from product page","prompt":"Fetch https://aws.amazon.com/ec2/pricing/ and extract the pricing tables and key metadata as structured JSON — use structured mode."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, structured JSON tables, 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. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL unreachable or returns non-200 — fetch fails with error status","JavaScript-heavy SPA with no server-side rendering may return empty or incomplete content","BM25 budget mode with very small max_tokens may truncate critical content","Invalid or missing 'url' field returns validation error (url is required)","Payment failure via x402 protocol blocks execution","Token budget too small (< 20) rejected by schema validation"],"whenToPreferThis":"Choose this endpoint when you need to feed webpage content into an LLM and want automatic token compression, BM25 relevance ranking, or structured extraction — especially useful when the raw page is too large for your context window. Prefer over generic scrapers when you need the ROI/token-savings metrics or need BM25 query-focused excerpts. The budget mode is uniquely suited for agents that must stay within strict token limits.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:07.919Z","isFirstParty":false,"canonicalSlug":"hn-pulse-agentdiet-dev-spa-markdown-reader-bm25-budget-controlled-web-7ff569da"}