{"uid":"cap_u6SmHHsfQWrqz-DNfPLPl","slug":"agentdiet-research-digest-context-window-distiller-31bb42f7","name":"AgentDiet Research Digest — Context Window Distiller","description":"Deterministic B2A/A2A/MCP/x402/MPP/L402 execution and intelligence node at https://rag-diet.agentdiet.dev settling in USDC on Base.","url":"https://rag-diet.agentdiet.dev/v1/research-digest?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET","POST"],"type":"string"},"queryParams":{"type":"object","properties":{"query":{"type":"string"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"data":{},"status":"ok","roi_proof":{"compression_ratio_pct":91.4}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_kG80uesbm-9O23sy--ENi","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Compresses and distills a research query into a token-efficient digest, reducing context window bloat by up to 91% via RAG-based summarization","exampleAgentPrompt":"Can you run my query 'climate change impact on supply chains' through AgentDiet's research digest to get a compressed, token-efficient summary — I need to cut my context window by as much as possible before passing it downstream?","exampleUseCases":[{"title":"Token budget trimming before LLM call","prompt":"I have a research query about 'semiconductor shortage effects on EV manufacturing' and my context window is already 80% full — can you distill it into the smallest possible digest so I don't exceed my token limit?"},{"title":"A2A pipeline context handoff","prompt":"Before passing results to the next agent node, compress the research on 'quantum computing commercial timelines' using AgentDiet's digest endpoint so the downstream agent gets only the essential information."},{"title":"Cost reduction on repeated research lookups","prompt":"I keep querying 'federal reserve interest rate history' in my pipeline and it's burning tokens — can you get me a compact research digest of that topic so I can reuse it cheaply across multiple agent calls?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the compressed research digest, a 'status' field ('ok' on success), and a 'roi_proof' object showing the compression_ratio_pct achieved (e.g. 91.4%), confirming how much token reduction was accomplished.","failureModes":["Missing or empty 'query' parameter returns an error or empty digest","Payment not settled in USDC on Base results in 402 Payment Required","Invalid HTTP method (not GET or POST) returns a 400 or schema validation error","Query too vague or short may yield low compression ratio or minimal output","Service unavailability returns a non-200 status with no data"],"whenToPreferThis":"Choose this endpoint when an AI agent pipeline needs to reduce context window size before passing information to a downstream LLM or agent node, especially when token costs are a concern. It is best suited for A2A, B2A, or MCP workflows where a research query needs to be distilled into a compact, reusable digest. Prefer this over generic summarization when you need a measurable compression ratio proof and pay-per-use micropayment pricing via x402/USDC.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-22T12:43:52.647Z","isFirstParty":false,"canonicalSlug":"agentdiet-research-digest-context-window-distiller-31bb42f7"}