Skip to main content Module core Copy item path Source a2a a2a_transport adaptive adaptive_chunking Adaptive chunk sizing from a rough “prefrontal” budget controller (tight → signatures, generous → full bodies). adaptive_mode_policy adaptive_thresholds agents anomaly Anomaly detection using Welford’s online algorithm for running
mean/variance and triggering alerts at >3x standard deviation. archive archive_fts artifact_index artifacts attention Convenience re-export: all attention-related modules. attention_layout_driver attention_model Heuristic attention prediction model for LLM context optimization. attention_placement U-shaped placement (primacy/recency): alternate placing ranked items at context head vs tail. autonomy_drivers bandit benchmark binary_detect bm25_index bounce_tracker buddy budget_tracker Runtime budget tracking against role limits. budgets cache call_graph ccp_session_bundle chunks_ts Tree-sitter AST-aware code chunking for semantic search. claim_extractor Claim Extraction — decomposes context pipeline outputs into verifiable claims. cli_cache client_capabilities client_constraints codebook cognitive_load Cognitive Load Theory–style scoring for code context (intrinsic / extraneous / germane). community Leiden community detection on the Property Graph. compression Convenience re-export: all compression-related modules. compression_safety compressor config consolidation_engine context Convenience re-export: all context-related modules. context_artifacts context_compiler Context Compiler – builds minimal context packages under budget constraints. context_deficit context_field Context Field Theory (CFT) – unified potential function for context items. context_handles Context Handles – sparse, lazy references to 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_package context_policies Context Policy Engine – declarative rules for context governance. context_proof context_proof_v2 ContextProofV2 — Claim-based verification schema. context_radar contracts cyclomatic Cyclomatic complexity via tree-sitter (decision-point counting). data_dir deep_queries Tree-sitter deep queries for extracting imports, call sites, and type definitions. degradation_policy dense_backend deps editor_registry embedding_index Persistent, incremental embedding index. embeddings Embedding engine for semantic code search. entropy episodic_memory Episodic Memory — persistent cross-session experiences with outcomes. error events evidence_ledger feedback filters gain gamma_cover Minimal TF-IDF chunk subset covering peers within γ bits of residual information. gotcha_tracker graph Convenience re-export: all graph-related modules. graph_context Graph-driven context loading — automatically includes related files
based on Property Graph proximity and token budgeting. graph_enricher Unified Graph Enricher — indexes Git history, tests, and knowledge into the PropertyGraph. graph_export graph_features Multi-layer graph descriptors inspired by GNN message passing:
PageRank (global importance), local clustering, HITS hubs/authorities,
and weakly-connected community ids. graph_index graph_provider handoff_ledger handoff_transfer_bundle hasher Central hashing utility using BLAKE3. heatmap home hybrid_search Hybrid search combining BM25 (lexical) with dense vector search. import_resolver Import-to-file resolution (AST-driven import strings → project paths). index_namespace index_orchestrator information_bottleneck QUITO-X–style trade-off: compress by dropping low token-entropy lines while targeting an output/input token ratio. instruction_compiler integrity Build-origin integrity verification and rebrand resistance. intent_engine intent_protocol intent_router io_boundary jsonc knowledge knowledge_bootstrap knowledge_domain Convenience re-export: all knowledge-related modules. knowledge_embedding Embedding-based Knowledge Retrieval for ctx_knowledge. knowledge_relations language_capabilities limits litm llm_feedback logging loop_detection mcp_manifest mdl_selector Minimum Description Length–style selection among abstract read modes (proxy compressed lengths). memory Convenience re-export: all memory-related modules. memory_boundary memory_consolidation Sleep-inspired consolidation for in-memory knowledge entries (NREM merge, REM prune, replay boost). memory_guard Process-level RAM guardian with adaptive eviction and hard OOM protection. memory_lifecycle Memory Lifecycle Management — consolidation, decay, compaction, archival. memory_policy mode_predictor neural Neural context compression — trained models replacing heuristic filters. output_verification pagerank PageRank computation on the Property Graph. pathjail pathutil patterns pipeline Context Pipeline pop_pruning portable_binary preservation procedural_memory Procedural Memory — recurring workflow detection and template storage. process_guard Global concurrency limiter for lean-ctx processes. profiles Context Profiles progressive_compression Progressive compression: newest segments stay verbose; older tiers lose detail under exponential budget shrink. project_hash property_graph Property Graph Engine — SQLite-backed code knowledge graph. prospective_memory protocol provider_cache Provider caching awareness — helps LLM providers cache repeated context. providers quality rabin_karp redaction roles Role-based access control for agent governance. route_extractor rules_canonical Canonical Hybrid Policy — the single source of truth for all lean-ctx rules. safety_needles sandbox sanitize search Convenience re-export: all search-related modules. semantic_cache semantic_chunks Semantic Chunking with Attention Bridges. session session_diff Session diffing — structured comparison of two session states. session_domain Convenience re-export: all session-related modules. setup_report signatures signatures_ts slo Context SLOs — configurable service level objectives for context metrics. slow_log smells Code smell detection engine. splade_retrieval SPLADE-style sparse expansion layered on BM25 candidate retrieval. startup_guard stats structural_diff Structural diff using tree-sitter chunk identities (named declarations). structural_tokenizer Structural tokenizer treating idiomatic multi-token spans as single motifs. surprise Predictive Surprise Scoring — conditional entropy relative to LLM knowledge. symbol_map task_briefing task_relevance tdd_schema telemetry Telemetry and metrics collection following OpenTelemetry GenAI conventions. terse Terse Compression Engine theme tokenizer_translation_driver tokens tool_lifecycle Shared tool lifecycle — ensures CLI and MCP paths have identical side effects. updater verification_observability version_check workflow workspace_config wrapped