[{"data":1,"prerenderedAt":638},["ShallowReactive",2],{"navigation_docs":3,"-docs-intelligence":356,"-docs-intelligence-surround":633},[4,8,34,64,90,139,157,171,193,227,241,266,312,334],{"title":5,"path":6,"stem":7},"Documentation","\u002Fdocs","docs\u002Findex",{"title":9,"path":10,"stem":11,"children":12},"Getting started","\u002Fdocs\u002Fgetting-started","docs\u002F01.getting-started\u002Findex",[13,14,18,22,26,30],{"title":9,"path":10,"stem":11},{"title":15,"path":16,"stem":17},"Introduction","\u002Fdocs\u002Fgetting-started\u002Fintroduction","docs\u002F01.getting-started\u002F01.introduction",{"title":19,"path":20,"stem":21},"Concepts","\u002Fdocs\u002Fgetting-started\u002Fconcepts","docs\u002F01.getting-started\u002F02.concepts",{"title":23,"path":24,"stem":25},"Quickstart (5 minutes)","\u002Fdocs\u002Fgetting-started\u002Fquickstart","docs\u002F01.getting-started\u002F03.quickstart",{"title":27,"path":28,"stem":29},"Local development","\u002Fdocs\u002Fgetting-started\u002Flocal-development","docs\u002F01.getting-started\u002F04.local-development",{"title":31,"path":32,"stem":33},"FAQ","\u002Fdocs\u002Fgetting-started\u002Ffaq","docs\u002F01.getting-started\u002F05.faq",{"title":35,"path":36,"stem":37,"children":38},"Architecture","\u002Fdocs\u002Farchitecture","docs\u002F02.architecture\u002Findex",[39,40,44,48,52,56,60],{"title":35,"path":36,"stem":37},{"title":41,"path":42,"stem":43},"Architecture overview","\u002Fdocs\u002Farchitecture\u002Foverview","docs\u002F02.architecture\u002F01.overview",{"title":45,"path":46,"stem":47},"Services","\u002Fdocs\u002Farchitecture\u002Fservices","docs\u002F02.architecture\u002F02.services",{"title":49,"path":50,"stem":51},"Request lifecycle","\u002Fdocs\u002Farchitecture\u002Frequest-lifecycle","docs\u002F02.architecture\u002F03.request-lifecycle",{"title":53,"path":54,"stem":55},"Data model","\u002Fdocs\u002Farchitecture\u002Fdata-model","docs\u002F02.architecture\u002F04.data-model",{"title":57,"path":58,"stem":59},"Status and evidence","\u002Fdocs\u002Farchitecture\u002Fstatus-and-evidence","docs\u002F02.architecture\u002F05.status-and-evidence",{"title":61,"path":62,"stem":63},"Target architecture and authority","\u002Fdocs\u002Farchitecture\u002Ftarget-architecture","docs\u002F02.architecture\u002F06.target-architecture",{"title":65,"path":66,"stem":67,"children":68},"Auth","\u002Fdocs\u002Fauth","docs\u002F03.auth\u002Findex",[69,70,74,78,82,86],{"title":65,"path":66,"stem":67},{"title":71,"path":72,"stem":73},"Overview","\u002Fdocs\u002Fauth\u002Foverview","docs\u002F03.auth\u002F01.overview",{"title":75,"path":76,"stem":77},"Organization and agent model","\u002Fdocs\u002Fauth\u002Forg-project-model","docs\u002F03.auth\u002F02.org-project-model",{"title":79,"path":80,"stem":81},"Issuing API keys","\u002Fdocs\u002Fauth\u002Fissuing-api-keys","docs\u002F03.auth\u002F03.issuing-api-keys",{"title":83,"path":84,"stem":85},"Multi-tenant RLS","\u002Fdocs\u002Fauth\u002Fmulti-tenant-rls","docs\u002F03.auth\u002F04.multi-tenant-rls",{"title":87,"path":88,"stem":89},"Operator sessions and step-up","\u002Fdocs\u002Fauth\u002Foperator-sessions","docs\u002F03.auth\u002F05.operator-sessions",{"title":91,"path":92,"stem":93,"children":94},"Proxy","\u002Fdocs\u002Fproxy","docs\u002F04.proxy\u002Findex",[95,96,99,103,107,111,115,119,123,127,131,135],{"title":91,"path":92,"stem":93},{"title":71,"path":97,"stem":98},"\u002Fdocs\u002Fproxy\u002Foverview","docs\u002F04.proxy\u002F01.overview",{"title":100,"path":101,"stem":102},"Authentication","\u002Fdocs\u002Fproxy\u002Fauthentication","docs\u002F04.proxy\u002F02.authentication",{"title":104,"path":105,"stem":106},"Request routing","\u002Fdocs\u002Fproxy\u002Frequest-routing","docs\u002F04.proxy\u002F03.request-routing",{"title":108,"path":109,"stem":110},"Sessions","\u002Fdocs\u002Fproxy\u002Fsessions","docs\u002F04.proxy\u002F04.sessions",{"title":112,"path":113,"stem":114},"Directives","\u002Fdocs\u002Fproxy\u002Fdirectives","docs\u002F04.proxy\u002F05.directives",{"title":116,"path":117,"stem":118},"Idempotency and budgets","\u002Fdocs\u002Fproxy\u002Fidempotency-and-budgets","docs\u002F04.proxy\u002F06.idempotency-and-budgets",{"title":120,"path":121,"stem":122},"Rate limiting","\u002Fdocs\u002Fproxy\u002Frate-limiting","docs\u002F04.proxy\u002F07.rate-limiting",{"title":124,"path":125,"stem":126},"Provider adapters","\u002Fdocs\u002Fproxy\u002Fprovider-adapters","docs\u002F04.proxy\u002F08.provider-adapters",{"title":128,"path":129,"stem":130},"Auth caching","\u002Fdocs\u002Fproxy\u002Fauth-caching","docs\u002F04.proxy\u002F09.auth-caching",{"title":132,"path":133,"stem":134},"Configuration","\u002Fdocs\u002Fproxy\u002Fconfiguration","docs\u002F04.proxy\u002F10.configuration",{"title":136,"path":137,"stem":138},"Provider routing and resilience","\u002Fdocs\u002Fproxy\u002Fprovider-routing-and-resilience","docs\u002F04.proxy\u002F11.provider-routing-and-resilience",{"title":140,"path":141,"stem":142,"children":143},"Memory","\u002Fdocs\u002Fmemory","docs\u002F05.memory\u002Findex",[144,145,149,153],{"title":140,"path":141,"stem":142},{"title":146,"path":147,"stem":148},"Memory overview","\u002Fdocs\u002Fmemory\u002Foverview","docs\u002F05.memory\u002F01.overview",{"title":150,"path":151,"stem":152},"Write path","\u002Fdocs\u002Fmemory\u002Fwrite-path","docs\u002F05.memory\u002F02.write-path",{"title":154,"path":155,"stem":156},"Search and lifecycle","\u002Fdocs\u002Fmemory\u002Fsearch-and-lifecycle","docs\u002F05.memory\u002F03.search-and-lifecycle",{"title":158,"path":159,"stem":160,"children":161},"Context","\u002Fdocs\u002Fcontext","docs\u002F06.context\u002Findex",[162,163,167],{"title":158,"path":159,"stem":160},{"title":164,"path":165,"stem":166},"Assembly pipeline","\u002Fdocs\u002Fcontext\u002Foverview","docs\u002F06.context\u002F01.overview",{"title":168,"path":169,"stem":170},"Ranking and packing","\u002Fdocs\u002Fcontext\u002Franking-and-packing","docs\u002F06.context\u002F02.ranking-and-packing",{"title":172,"path":173,"stem":174,"children":175},"Intelligence","\u002Fdocs\u002Fintelligence","docs\u002F07.intelligence\u002Findex",[176,177,181,185,189],{"title":172,"path":173,"stem":174},{"title":178,"path":179,"stem":180},"Workers","\u002Fdocs\u002Fintelligence\u002Fworkers","docs\u002F07.intelligence\u002F01.workers",{"title":182,"path":183,"stem":184},"Extraction","\u002Fdocs\u002Fintelligence\u002Fextraction","docs\u002F07.intelligence\u002F02.extraction",{"title":186,"path":187,"stem":188},"Embedder","\u002Fdocs\u002Fintelligence\u002Fembedder","docs\u002F07.intelligence\u002F03.embedder",{"title":190,"path":191,"stem":192},"Extraction evaluation","\u002Fdocs\u002Fintelligence\u002Fevaluation","docs\u002F07.intelligence\u002F04.evaluation",{"title":194,"path":195,"stem":196,"children":197},"API reference","\u002Fdocs\u002Fapi-reference","docs\u002F08.api-reference\u002Findex",[198,199,203,207,211,215,219,223],{"title":194,"path":195,"stem":196},{"title":200,"path":201,"stem":202},"Chat completions","\u002Fdocs\u002Fapi-reference\u002Fchat-completions","docs\u002F08.api-reference\u002F01.chat-completions",{"title":204,"path":205,"stem":206},"Responses","\u002Fdocs\u002Fapi-reference\u002Fresponses","docs\u002F08.api-reference\u002F02.responses",{"title":208,"path":209,"stem":210},"Errors","\u002Fdocs\u002Fapi-reference\u002Ferrors","docs\u002F08.api-reference\u002F03.errors",{"title":212,"path":213,"stem":214},"Health and metrics","\u002Fdocs\u002Fapi-reference\u002Fproxy-health","docs\u002F08.api-reference\u002F04.proxy-health",{"title":216,"path":217,"stem":218},"HTTP route inventory","\u002Fdocs\u002Fapi-reference\u002Fhttp-routes","docs\u002F08.api-reference\u002F05.http-routes",{"title":220,"path":221,"stem":222},"Management API","\u002Fdocs\u002Fapi-reference\u002Fmanagement-api","docs\u002F08.api-reference\u002F06.management-api",{"title":224,"path":225,"stem":226},"Auth gRPC (ValidateToken, ValidateAgent)","\u002Fdocs\u002Fapi-reference\u002Fauth-grpc","docs\u002F08.api-reference\u002F07.auth-grpc",{"title":228,"path":229,"stem":230,"children":231},"MCP","\u002Fdocs\u002Fmcp","docs\u002F09.mcp\u002Findex",[232,233,237],{"title":228,"path":229,"stem":230},{"title":234,"path":235,"stem":236},"Memory server","\u002Fdocs\u002Fmcp\u002Fmemory-server","docs\u002F09.mcp\u002F01.memory-server",{"title":238,"path":239,"stem":240},"Operator gateway","\u002Fdocs\u002Fmcp\u002Foperator-gateway","docs\u002F09.mcp\u002F02.operator-gateway",{"title":242,"path":243,"stem":244,"children":245},"Security","\u002Fdocs\u002Fsecurity","docs\u002F10.security\u002Findex",[246,247,251,254,258,262],{"title":242,"path":243,"stem":244},{"title":248,"path":249,"stem":250},"Security overview","\u002Fdocs\u002Fsecurity\u002Foverview","docs\u002F10.security\u002F01.overview",{"title":100,"path":252,"stem":253},"\u002Fdocs\u002Fsecurity\u002Fauthentication","docs\u002F10.security\u002F02.authentication",{"title":255,"path":256,"stem":257},"Tenant isolation","\u002Fdocs\u002Fsecurity\u002Ftenant-isolation","docs\u002F10.security\u002F03.tenant-isolation",{"title":259,"path":260,"stem":261},"Secrets and keys","\u002Fdocs\u002Fsecurity\u002Fsecrets-and-keys","docs\u002F10.security\u002F04.secrets-and-keys",{"title":263,"path":264,"stem":265},"Prompt injection","\u002Fdocs\u002Fsecurity\u002Fprompt-injection","docs\u002F10.security\u002F05.prompt-injection",{"title":267,"path":268,"stem":269,"children":270},"Operations","\u002Fdocs\u002Foperations","docs\u002F11.operations\u002Findex",[271,272,276,280,284,288,292,296,300,304,308],{"title":267,"path":268,"stem":269},{"title":273,"path":274,"stem":275},"Observability","\u002Fdocs\u002Foperations\u002Fobservability","docs\u002F11.operations\u002F01.observability",{"title":277,"path":278,"stem":279},"Traces and ClickHouse","\u002Fdocs\u002Foperations\u002Ftraces-and-clickhouse","docs\u002F11.operations\u002F02.traces-and-clickhouse",{"title":281,"path":282,"stem":283},"Health checks","\u002Fdocs\u002Foperations\u002Fhealth-checks","docs\u002F11.operations\u002F03.health-checks",{"title":285,"path":286,"stem":287},"Incident response","\u002Fdocs\u002Foperations\u002Fincident-response","docs\u002F11.operations\u002F04.incident-response",{"title":289,"path":290,"stem":291},"Troubleshooting","\u002Fdocs\u002Foperations\u002Ftroubleshooting","docs\u002F11.operations\u002F05.troubleshooting",{"title":293,"path":294,"stem":295},"Billing and budgets","\u002Fdocs\u002Foperations\u002Fbilling-and-budgets","docs\u002F11.operations\u002F06.billing-and-budgets",{"title":297,"path":298,"stem":299},"Evidence and relay","\u002Fdocs\u002Foperations\u002Fevidence-and-relay","docs\u002F11.operations\u002F07.evidence-and-relay",{"title":301,"path":302,"stem":303},"Console","\u002Fdocs\u002Foperations\u002Fconsole","docs\u002F11.operations\u002F08.console",{"title":305,"path":306,"stem":307},"Failure modes and recovery","\u002Fdocs\u002Foperations\u002Ffailure-and-recovery","docs\u002F11.operations\u002F09.failure-and-recovery",{"title":309,"path":310,"stem":311},"Data lifecycle and deletion","\u002Fdocs\u002Foperations\u002Fdata-lifecycle-and-deletion","docs\u002F11.operations\u002F10.data-lifecycle-and-deletion",{"title":313,"path":314,"stem":315,"children":316},"Deployment","\u002Fdocs\u002Fdeployment","docs\u002F12.deployment\u002Findex",[317,318,322,326,330],{"title":313,"path":314,"stem":315},{"title":319,"path":320,"stem":321},"Docker Compose (dev)","\u002Fdocs\u002Fdeployment\u002Fdocker-compose","docs\u002F12.deployment\u002F01.docker-compose",{"title":323,"path":324,"stem":325},"Environment variables","\u002Fdocs\u002Fdeployment\u002Fenvironment-variables","docs\u002F12.deployment\u002F02.environment-variables",{"title":327,"path":328,"stem":329},"Kubernetes","\u002Fdocs\u002Fdeployment\u002Fkubernetes","docs\u002F12.deployment\u002F03.kubernetes",{"title":331,"path":332,"stem":333},"Production readiness","\u002Fdocs\u002Fdeployment\u002Fproduction-readiness","docs\u002F12.deployment\u002F04.production-readiness",{"title":335,"path":336,"stem":337,"children":338},"Reference","\u002Fdocs\u002Freference","docs\u002F13.reference\u002Findex",[339,340,344,348,352],{"title":335,"path":336,"stem":337},{"title":341,"path":342,"stem":343},"Glossary","\u002Fdocs\u002Freference\u002Fglossary","docs\u002F13.reference\u002F01.glossary",{"title":345,"path":346,"stem":347},"Roadmap and gates","\u002Fdocs\u002Freference\u002Froadmap","docs\u002F13.reference\u002F02.roadmap",{"title":349,"path":350,"stem":351},"Architecture decisions","\u002Fdocs\u002Freference\u002Fadr","docs\u002F13.reference\u002F03.adr",{"title":353,"path":354,"stem":355},"Compatibility and versioning","\u002Fdocs\u002Freference\u002Fcompatibility","docs\u002F13.reference\u002F04.compatibility",{"id":357,"title":172,"audience":358,"author":359,"authorUrl":359,"body":360,"coverIndex":359,"coverLabel":359,"coverTone":359,"date":359,"decisionStatus":359,"description":624,"excerpt":359,"extension":625,"featured":626,"historical":626,"meta":627,"navigation":628,"path":173,"readingTime":359,"scope":629,"seo":630,"sourceOfTruth":631,"status":371,"stem":174,"tags":359,"verifiedDate":372,"__hash__":632},"docs\u002Fdocs\u002F07.intelligence\u002Findex.md","operator",null,{"type":361,"value":362,"toc":616},"minimark",[363,367,373,378,403,407,514,518,587,606,610],[364,365,366],"p",{},"The intelligence layer runs work that must not block the proxy: session extraction, memory writes, embeddings, organization deletion, billing reconciliation, maintenance, and MCP audit fan-out.",[368,369],"page-status",{"note":370,"status":371,"verified":372},"Several tasks are implemented; queue durability and exactly-once projection are not certified","PROVISIONAL","2026-10-21",[374,375,377],"h2",{"id":376},"pages","Pages",[379,380,381,388,393,398],"ul",{},[382,383,384,387],"li",{},[385,386,178],"a",{"href":179}," — queues, task families, dead letters, and enqueue admission.",[382,389,390,392],{},[385,391,182],{"href":183}," — provider adapters, quality evaluation, and manual vLLM limits.",[382,394,395,397],{},[385,396,186],{"href":187}," — CPU stub, TEI, hosted backends, and readiness geometry.",[382,399,400,402],{},[385,401,190],{"href":191}," — gold set, cassette replay, contract gates, and regression limits.",[374,404,406],{"id":405},"what-is-implemented","What is implemented",[408,409,410,426],"table",{},[411,412,413],"thead",{},[414,415,416,420,423],"tr",{},[417,418,419],"th",{},"Capability",[417,421,422],{},"Status",[417,424,425],{},"Boundary",[427,428,429,441,451,473,483,493,503],"tbody",{},[414,430,431,435,438],{},[432,433,434],"td",{},"Session extraction and memory writes",[432,436,437],{},"IMPLEMENTED",[432,439,440],{},"Cassette and unit evidence; live vLLM is manual",[414,442,443,446,448],{},[432,444,445],{},"OpenAI and vLLM extraction providers",[432,447,437],{},[432,449,450],{},"vLLM has no CI GPU runner",[414,452,453,468,470],{},[432,454,455,456,460,461,460,464,467],{},"Embedding profiles (",[457,458,459],"code",{},"cpu",", ",[457,462,463],{},"gpu",[457,465,466],{},"hosted",")",[432,469,437],{},[432,471,472],{},"CPU stub is not a quality model",[414,474,475,478,480],{},[432,476,477],{},"Organization deletion orchestration",[432,479,437],{},[432,481,482],{},"Full deletion certification remains open",[414,484,485,488,490],{},[432,486,487],{},"Billing reconciliation and rollups",[432,489,437],{},[432,491,492],{},"Hosted reconciliation evidence open",[414,494,495,498,500],{},[432,496,497],{},"Dead-letter persistence, metrics, OTel",[432,499,437],{},[432,501,502],{},"Alert rules exist; runbook practice is separate",[414,504,505,508,511],{},[432,506,507],{},"Scheduled maintenance sweep",[432,509,510],{},"DEFERRED",[432,512,513],{},"Registered as a no-op, not business logic",[374,515,517],{"id":516},"queue-layout","Queue layout",[408,519,520,533],{},[411,521,522],{},[414,523,524,527,530],{},[417,525,526],{},"Queue",[417,528,529],{},"Purpose",[417,531,532],{},"Priority",[427,534,535,548,561,574],{},[414,536,537,542,545],{},[432,538,539],{},[457,540,541],{},"extraction",[432,543,544],{},"Session turns to memories",[432,546,547],{},"First",[414,549,550,555,558],{},[432,551,552],{},[457,553,554],{},"embedding",[432,556,557],{},"Async vector work",[432,559,560],{},"Second",[414,562,563,568,571],{},[432,564,565],{},[457,566,567],{},"maintenance",[432,569,570],{},"Beat sweeps and housekeeping",[432,572,573],{},"Third",[414,575,576,581,584],{},[432,577,578],{},[457,579,580],{},"mcp_audit",[432,582,583],{},"MCP tool-call audit fan-out",[432,585,586],{},"Last",[364,588,589,590,593,594,597,598,601,602,605],{},"Redis DB allocation is deliberate: cache ",[457,591,592],{},"0",", Celery broker ",[457,595,596],{},"1",", rate limiting ",[457,599,600],{},"2",", results ",[457,603,604],{},"3",". Do not collapse them into one database.",[374,607,609],{"id":608},"non-negotiable-boundary","Non-negotiable boundary",[364,611,612,613,615],{},"A queued task is not a completed effect. Extraction can be retried, enqueue can be idempotent, and dead letters can be persisted, but the system does not currently claim exactly-once projection into every downstream store. Read ",[385,614,297],{"href":298}," before treating an async side effect as durable.",{"title":617,"searchDepth":618,"depth":618,"links":619},"",2,[620,621,622,623],{"id":376,"depth":618,"text":377},{"id":405,"depth":618,"text":406},{"id":516,"depth":618,"text":517},{"id":608,"depth":618,"text":609},"Asynchronous workers, extraction, embeddings, deletion orchestration, and billing rollups.","md",false,{},true,"provisional",{"title":172,"description":624},"services\u002Fworker; services\u002Fembedder; engineering\u002Farchitecture-v2\u002F18-gap-register.md","-rpDl_Xmfdlwbd6ZaZKL-j2KXr9TZXdE6c5mAeQrrog",[634,636],{"title":168,"path":169,"stem":170,"description":635,"children":-1},"How retrieved memories become a bounded, deterministic context block without exceeding the model budget.",{"title":178,"path":179,"stem":180,"description":637,"children":-1},"Celery queues, task lifecycle, dead letters, enqueue admission, and operational limits.",1792875076186]