[{"data":1,"prerenderedAt":676},["ShallowReactive",2],{"navigation_docs":3,"-docs-context-overview":356,"-docs-context-overview-surround":671},[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":164,"audience":358,"author":359,"authorUrl":359,"body":360,"coverIndex":359,"coverLabel":359,"coverTone":359,"date":359,"decisionStatus":359,"description":663,"excerpt":359,"extension":664,"featured":665,"historical":665,"meta":666,"navigation":667,"path":165,"readingTime":359,"scope":593,"seo":668,"sourceOfTruth":669,"status":367,"stem":166,"tags":359,"verifiedDate":368,"__hash__":670},"docs\u002Fdocs\u002F06.context\u002F01.overview.md","architect",null,{"type":361,"value":362,"toc":653},"minimark",[363,369,373,380,385,396,403,453,457,460,495,502,515,519,539,543,546,560,563,567,570,574,595,599],[364,365],"page-status",{"note":366,"status":367,"verified":368},"Caller authentication and deadline boundaries remain open","PROVISIONAL","2026-10-21",[370,371,372],"p",{},"The context assembly service is a Python gRPC process that turns a request, a directive, recent messages, and retrieved memories into model-ready context within a token budget.",[370,374,375,379],{},[376,377,378],"strong",{},"What the status means:"," the pipeline exists and has local tests. It is not accepted as production-ready. Caller authentication at the service boundary and the deadline contract remain open.",[381,382,384],"h2",{"id":383},"pipeline","Pipeline",[386,387,393],"pre",{"className":388,"code":390,"language":391,"meta":392},[389],"language-text","budget calculation\n  → parallel directive \u002F hot-memory \u002F cold-memory retrieval\n  → composite scoring\n  → relevance gate\n  → packing\n  → formatting\n  → assembled context\n","text","",[394,395,390],"code",{"__ignoreMap":392},[370,397,398,399,402],{},"The service exposes ",[394,400,401],{},"ContextAssemblyService"," with three RPCs:",[404,405,406,419],"table",{},[407,408,409],"thead",{},[410,411,412,416],"tr",{},[413,414,415],"th",{},"RPC",[413,417,418],{},"Purpose",[420,421,422,433,443],"tbody",{},[410,423,424,430],{},[425,426,427],"td",{},[394,428,429],{},"AssembleContext",[425,431,432],{},"Retrieve, rank, pack, and format context.",[410,434,435,440],{},[425,436,437],{},[394,438,439],{},"SearchMemories",[425,441,442],{},"Retrieve memories without full assembly.",[410,444,445,450],{},[425,446,447],{},[394,448,449],{},"RecordMemoryFeedback",[425,451,452],{},"Record usefulness after an outcome is known.",[381,454,456],{"id":455},"deadline-behavior","Deadline behavior",[370,458,459],{},"The configured defaults are:",[461,462,463,471,477,483,489],"ul",{},[464,465,466,467,470],"li",{},"Client\u002Fouter retrieval timeout: ",[394,468,469],{},"IBEX_CONTEXT_TIMEOUT=45ms",".",[464,472,473,474,470],{},"Server retrieval wall: ",[394,475,476],{},"IBEX_CONTEXT_DEADLINE_MS=40ms",[464,478,479,480,470],{},"Directive timeout: ",[394,481,482],{},"5ms",[464,484,485,486,470],{},"Hot-memory timeout: ",[394,487,488],{},"15ms",[464,490,491,492,470],{},"Cold-memory timeout: ",[394,493,494],{},"45ms",[370,496,497,498,501],{},"The effective retrieval wait is ",[394,499,500],{},"min(timeout, deadline)",", leaving headroom for packing and formatting under the proxy's 45ms client timeout. Slow branches are cancelled rather than allowed to consume the full budget.",[503,504,507,508,470],"callout",{"title":505,"type":506},"Known boundary gap","warning","The gRPC server logs a warning for non-loopback binds until caller authentication lands. Do not treat a reachable context port as an authenticated public API. See ",[509,510,514],"a",{"href":511,"rel":512},"https:\u002F\u002Fgithub.com\u002FRick1330\u002Fibex-harness\u002Fblob\u002Fmain\u002Fengineering\u002Fadr\u002F0071-context-grpc-degradation-deadline.md",[513],"nofollow","ADR-0071",[381,516,518],{"id":517},"budget-and-packing","Budget and packing",[461,520,521,524,527,530,533],{},[464,522,523],{},"The model capability catalog supplies context windows and tokenizer-family policy.",[464,525,526],{},"Token estimates are deliberately conservative; they are estimates, not tokenizer-exact counts.",[464,528,529],{},"The packer uses dynamic programming under a cell ceiling, then falls back to greedy packing for large candidate sets.",[464,531,532],{},"An exact-budget repair step handles bucket rounding.",[464,534,535,538],{},[394,536,537],{},"AssemblyOptions"," exposes weights and caps. The weight fields are a forward contract; they do not override the memory relevance gate yet.",[381,540,542],{"id":541},"formatting-and-prompt-safety","Formatting and prompt safety",[370,544,545],{},"Memory content is untrusted data. The formatter:",[461,547,548,551,554,557],{},[464,549,550],{},"Escapes attribute values and body text so a memory cannot forge closing tags.",[464,552,553],{},"Opens each memory element with a per-assembly nonce.",[464,555,556],{},"Serializes only; it never parses memory markup.",[464,558,559],{},"Keeps directive, history, memory, and tool sections ordered and clearly delimited.",[370,561,562],{},"Memory content must never be interpreted as instructions by the proxy or model runtime.",[381,564,566],{"id":565},"degradation","Degradation",[370,568,569],{},"The proxy may proceed without context if retrieval or assembly fails. The intended behavior is directive-only or history-only context, with the failure recorded in metrics and traces. This fallback is part of the local behavior; it is not a measured hosted SLO.",[381,571,573],{"id":572},"current-limits","Current limits",[461,575,576,579,582,585,588],{},[464,577,578],{},"Caller authentication and principal propagation at the context boundary are incomplete.",[464,580,581],{},"The deadline configuration and caller expectations have a known discrepancy.",[464,583,584],{},"Composite scoring still uses an interim schema until all components are wired.",[464,586,587],{},"No hosted p99 or end-to-end assembly SLO is published.",[464,589,590,591,594],{},"The context service is ",[376,592,593],{},"provisional",", not a stable public integration contract.",[381,596,598],{"id":597},"evidence","Evidence",[461,600,601,609,617,625,633,641,647],{},[464,602,603,608],{},[509,604,607],{"href":605,"rel":606},"https:\u002F\u002Fgithub.com\u002FRick1330\u002Fibex-harness\u002Fblob\u002Fmain\u002Fengineering\u002Fadr\u002F0038-context-assembly-service.md",[513],"ADR-0038"," — service contract.",[464,610,611,616],{},[509,612,615],{"href":613,"rel":614},"https:\u002F\u002Fgithub.com\u002FRick1330\u002Fibex-harness\u002Fblob\u002Fmain\u002Fengineering\u002Fadr\u002F0067-context-capability-catalog-generate-and-diff.md",[513],"ADR-0067"," — capability catalog.",[464,618,619,624],{},[509,620,623],{"href":621,"rel":622},"https:\u002F\u002Fgithub.com\u002FRick1330\u002Fibex-harness\u002Fblob\u002Fmain\u002Fengineering\u002Fadr\u002F0068-composite-relevance-gate.md",[513],"ADR-0068"," — relevance gate.",[464,626,627,632],{},[509,628,631],{"href":629,"rel":630},"https:\u002F\u002Fgithub.com\u002FRick1330\u002Fibex-harness\u002Fblob\u002Fmain\u002Fengineering\u002Fadr\u002F0069-context-packer-dp-knapsack.md",[513],"ADR-0069"," — packer.",[464,634,635,640],{},[509,636,639],{"href":637,"rel":638},"https:\u002F\u002Fgithub.com\u002FRick1330\u002Fibex-harness\u002Fblob\u002Fmain\u002Fengineering\u002Fadr\u002F0070-context-formatter-ordering-nonce.md",[513],"ADR-0070"," — formatter and nonce.",[464,642,643,646],{},[509,644,514],{"href":511,"rel":645},[513]," — deadlines and degradation.",[464,648,649,652],{},[509,650,651],{"href":58},"Status ledger"," — current claim boundary.",{"title":392,"searchDepth":654,"depth":654,"links":655},2,[656,657,658,659,660,661,662],{"id":383,"depth":654,"text":384},{"id":455,"depth":654,"text":456},{"id":517,"depth":654,"text":518},{"id":541,"depth":654,"text":542},{"id":565,"depth":654,"text":566},{"id":572,"depth":654,"text":573},{"id":597,"depth":654,"text":598},"Bounded retrieval, ranking, packing, formatting, and degradation for agent context.","md",false,{},true,{"title":164,"description":663},"services\u002Fcontext; packages\u002Fproto\u002Fproto\u002Fibex\u002Fcontext\u002Fv1\u002Fcontext.proto","mrFzQwLKFCl12x7n6NFRiHV9XAeB3F7wc3xi4_tebAA",[672,674],{"title":158,"path":159,"stem":160,"description":673,"children":-1},"Budgeting, parallel retrieval, ranking, packing, formatting, and safe degradation for LLM context.",{"title":168,"path":169,"stem":170,"description":675,"children":-1},"How retrieved memories become a bounded, deterministic context block without exceeding the model budget.",1792875070769]