Skip to main content Module core Copy item path Source a2a active_inference Active Inference Preload — predictive context loading. addons Addon ecosystem: community extensions for lean-ctx (#858). anchor Hash-anchored line identifiers — the shared spine of anchored editing
(epic #1008 / GL#1009). anomaly Anomaly detection using Welford’s online algorithm for running
mean/variance and triggering alerts at >3x standard deviation. anti_interrupt Anti-Interruption Score (F7) — cognitive impact metrics beyond token savings. archive attention_context Attention-Weighted Context Assembly. attention_model Heuristic attention prediction model for LLM context optimization. audit_trail auto_mode_resolver benchmark_compare billing Commercial-plane billing substrate (billing-plane-v1): plans, entitlements,
and usage metering derived from the signed savings ledger. Never gates local.
Commercial-plane billing substrate (billing-plane-v1, EPIC 13.6). bm25_index cache capabilities capsule_transport Local reference transport for authenticated OCLA A2A capsule delivery (P11). cognitive Cognitive Budget Allocator (F3) — Miller’s Law for LLM context. compliance Framework compliance mappings + coverage reports (GL #424, H3 Epic A). compliance_report Signed CISO compliance report (GL #677) — “the deliverable a CISO shows
auditors”. compressor config conformance Conformance & reproducibility scorecard (conformance-v1, EPIC 12.17). consolidation Consolidation engine for provider data — hippocampal sleep replay. content_chunk Universal content chunk — the atomic unit of the Context Engine. context_capsule Payload-free, delta-capable contract for multi-agent context handoffs. context_column Context Column — the cortical column abstraction for data source pipelines. context_field Context Field Theory (CFT) – unified potential function for context items. context_ir context_ledger context_os context_overlay Reversible context overlays — user/policy manipulations that modify
context items without changing source files (“synaptic modulation”). context_policies Context Policy Engine – declarative rules for context governance. context_prefetch Predictive Context Prefetch (F2) — trajectory-based preloading. context_radar contracts crash_log Persistent crash log for panic diagnosability. cross_source_edges Cross-source graph edges — connects external data to code via the graph index. cross_source_hints Cross-source hints — lateral connections between cortical columns. data_dir degradation_policy editor_registry embeddings Embedding engine for semantic code search. entropy eval_ab Deterministic with/without output-quality eval (#232). eval_harness Retrieval evaluation harness for lean-ctx hybrid search. events evidence_bundle Evidence bundle generator (evidence-bundle-v1, GL #425, H3 Epic A). extension_registry Pluggable read-modes, compressors, and chunkers (extension-registry-v1). feedback finops_export FinOps cost/savings export (GL #402): CloudZero CBF, Vantage, FOCUS CSV. free_energy_budget Free-Energy Budget — optimal context allocation under token constraints. gotcha_tracker graph_context Graph-driven context loading — automatically includes related files
based on Property Graph proximity and token budgeting. graph_expand On-Demand Graph Expansion (F6) — k-hop subgraph extraction. graph_export graph_index graph_provider hasher Central hashing utility using BLAKE3. hebbian_cache Hebbian Co-Access Cache with Boltzmann-Temperature Eviction. hnsw Lightweight HNSW (Hierarchical Navigable Small World) index for approximate nearest neighbors. homeostasis Homeostatic Memory Guard — Proactive multi-level resource management. hybrid_search Hybrid search combining BM25 (lexical) with dense vector search. ib Task-aware Information Bottleneck compression (F1). index_orchestrator input_filters Inbound content filters (GL #675) — the input side of the Great Filter. intent_protocol io_health jsonc knowledge knowledge_embedding Embedding-based Knowledge Retrieval for ctx_knowledge. knowledge_provider_extract Knowledge auto-extraction from provider data (issues, PRs, DB schemas). knowledge_relations locomo LoCoMo memory benchmark (#291). loop_detection mcp_catalog MCP Tool-Catalog Federation (#210) — Engine pillar . mcp_manifest mdl_mode MDL Read Mode (F8) — structural descriptions for compact code representation. memory_policy memory_scheduler FSRS-based Context Memory Scheduler (F5). multiscale_index Renormalization-Inspired Multi-Scale Indexing. ocla Open Context & Token Lifecycle Architecture (OCLA) public OSS contract. ocp Open Context Protocol (OCP) v0.1 export adapter. openapi OpenAPI 3.0 document for the public /v1 surface, generated from a single
in-code endpoint inventory (endpointshttp_server; the SSOT lives here so it stays compiled and
drift-tested without the http-server feature. path_resolve Shared path-resolution for tool handlers. pathjail paths Typed XDG base-directory resolvers for lean-ctx (GH #408 / GL #602). pathutil patterns plugins policy Context Policy Packs v1 — Policies-as-Code (GL #489). predictive_coding Predictive Coding for mode outputs — send only prediction errors (deltas). predictive_prefetch Predictive Prefetch via Free Energy Minimization. property_graph Property Graph Engine — SQLite-backed code knowledge graph. protocol provider_bandit Provider Bandit — Thompson Sampling for provider selection. providers reference_docs Generated reference documentation. rule_artifacts The committed LEAN-CTX.md rule artifacts as (relative_path, content)
pairs — the single source shared by the regenerator (gen_rules example)
and the drift gate (tests/rules_drift.rs) so the project copy and the
rust/ copy can never disagree. rules_canonical Canonical rules source — single source of truth for all lean-ctx guidance. saliency Saliency Map — information-theoretic chunk ranking and deduplication. savings_ledger Verified Savings Ledger (G1) — the per-event, auditable counterfactual store. scorecard Reproducible scorecard (#211): one command → compression savings + retrieval
recall/MRR + latency over a fixed, deterministic scenario matrix. search_index Resident line-search index for ctx_search (Phase 1 of the efficiency epic). search_reranking Post-RRF Reranking Pipeline for code-aware search. sensitivity Per-item sensitivity model with a uniform policy floor (#212). server_capabilities GET /v1/capabilities — runtime discovery of what this lean-ctx instance
supports, so any client (any language) can branch on real features instead
of trial calls. The HTTP route lives in http_server; the payload builder
lives here so it stays compiled (and drift-tested) without the
http-server feature.session session_token setup_report shell_allowlist Shell allowlist with AST-based command parsing. sidecar_transport signatures Signature extraction — regex fallback layer. spreading_activation Spreading activation — associative retrieval over a weighted graph. startup_guard stats stigmergy Stigmergic Agent Coordination (F9) — ant-colony-inspired signals. symbol_map task_relevance tdd_schema telemetry Telemetry and metrics collection following OpenTelemetry GenAI conventions. terse Terse Compression Engine tokens tool_profiles verbosity Behavioral Verbosity Learning (F10) — adaptive compression recommendations. wasserstein Wasserstein Token Allocator (F4) — Optimal Transport for context budgets. web Web & research context layer. workflow