{"uid":"cap_nRSA7FgjLt6qhYTegLNc4","slug":"workflows-agentdiet-dev-context-compress-bm25-budget-controlled-web-b689a822","name":"Context Compress: BM25 Budget-Controlled Web Distillation","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://workflows.agentdiet.dev/v1/context-compress)","url":"https://workflows.agentdiet.dev/v1/context-compress?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_AZ-NMUe2zJGmjzlbspcMO","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"workflows.agentdiet.dev","brandSlug":"workflows-agentdiet-dev-mpp","brandBaseUrl":"https://workflows.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compact, token-efficient agent-ready content using BM25-ranked budget control","exampleAgentPrompt":"Fetch and distill https://stripe.com/docs/payments into compact markdown using budget mode, focused on the query 'payment intents', with a max of 500 tokens.","exampleUseCases":[{"title":"Token-budget scrape for RAG pipeline","prompt":"Distill https://openai.com/pricing into budget mode with the query 'GPT-4o cost per token' and keep it under 300 tokens — I need it tight for my retrieval pipeline."},{"title":"Stripe docs skeleton for agent onboarding","prompt":"Can you pull the Stripe docs from builtin://stripe-docs and give me a skeleton outline so my agent can navigate the structure without burning a ton of context?"},{"title":"Competitor pricing page extraction","prompt":"Grab https://www.notion.so/pricing and distill it into structured tables — I want the plan names, prices, and feature differences in a clean JSON format."}],"resultDescription":"Returns a distilled representation of the webpage or HTML in the chosen mode (markdown, structured JSON, skeleton outline, or BM25 budget excerpt), along with ROI proof showing raw vs. distilled token counts, compression ratio, estimated LLM cost saved, and optional cache/billing metadata.","failureModes":["URL is unreachable or returns a non-200 status — distillation fails with a fetch error","Raw HTML is malformed or empty — may return minimal or empty distilled output","max_tokens set too low (below 20) — validation error","mode=budget used without a query parameter — BM25 ranking has no focus term","Payment not fulfilled (x402) — request blocked until payment completed","Idempotency-Key conflict — prior in-flight request with same key may block retry"],"whenToPreferThis":"Choose this endpoint when you need to reduce token consumption from web pages or raw HTML before passing content to an LLM, especially when working within strict context budgets. The BM25 budget mode is uniquely suited when you have a specific query and need only the most relevant excerpt. Prefer over generic scrapers when you need ROI proof of compression gains or when integrating with x402/MCP-based payment workflows.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:16.721Z","isFirstParty":false,"canonicalSlug":"workflows-agentdiet-dev-context-compress-bm25-budget-controlled-web-b689a822"}