| 27f7a61fcf3c4df8… | The security model sets a 10 second execution timeout that is configurable per plan so that code runs are bounded by default while allowing plan-based overrides. | active | contextual | yes | |
| f92cbd2abfb05c84… | The security model enforces a PID limit of 50 to prevent fork bombs so that runaway process creation is blocked. | active | contextual | yes | |
| 217092c93fea77dd… | The security model limits memory to 128MB and CPU to 0.5 cores so that code execution remains resource constrained. | active | contextual | yes | |
| e8926069a26f2608… | The security model disables network access in containers so that executed code cannot communicate externally from containerized environments. | active | contextual | yes | |
| 9f26227c36c61b70… | The API exposes GET /metrics for concurrency metrics including active_executions, max_concurrent, and available_slots so that clients and operators can inspect execution capacity and usage. | active | contextual | yes | |
| 685a95e34f6e99ea… | The API exposes GET /health for Kubernetes probes so that orchestration systems can verify service health. | active | contextual | yes | |
| 2c64276d176daa8a… | The API exposes POST /run to execute Python code with optional workspace, input_files, and output_files parameters for Azure Blob I/O so that code execution can exchange files through blob storage. | active | contextual | yes | |
| ea53d8eeba06084c… | The PoolStateManagerAgent consumes all events and auto-scales every 30 seconds so that pool capacity can adjust in response to system activity. | active | contextual | yes | |
| 3155f80f68819ea7… | The QueueOptimizerAgent polls queue depths every 1 second and activates backpressure at 80 percent so that queue growth can be controlled before saturation occurs. | active | contextual | yes | |
| 1237650ab90bf1ea… | The PerformanceAnalyzerAgent maintains a rolling window of 200 samples per tier and computes P50, P95, and P99 metrics so that execution performance can be summarized by latency percentiles. | active | contextual | yes | |
| 2e15b5e2cea2b7ab… | The HealthMonitorAgent checks pool slot health every 10 seconds and restarts FAILED slots so that unhealthy execution slots are recovered automatically. | active | contextual | yes | |
| 2ae56ae87bb99671… | The ResourceMonitorAgent polls /proc/meminfo every 5 seconds and tracks memory pressure so that the system can observe memory conditions continuously in the background. | active | contextual | yes | |
| 37d70a567af1e87f… | The code classifier determines execution complexity as LIGHT, STANDARD, or HEAVY based on imports present, code size, timeout, file I/O, and output file count so that submitted code can be routed to an appropriate execution tier. | active | contextual | yes | |
| 67d28d2710978e69… | The Gold subscription plan includes all tiers, allows file I/O, data-science libraries, and ML or GPU libraries, permits unlimited concurrency, and sets a maximum timeout of 600 seconds. | active | contextual | yes | |
| 0f473c0619dc73d3… | The Silver subscription plan includes Tiers 1 and 2, allows file I/O and data-science libraries, excludes ML or GPU libraries, permits 20 concurrent executions, and sets a maximum timeout of 120 seconds. | active | contextual | yes | |
| f87a64fa11147911… | The Bronze subscription plan includes Tier 1 only, disallows file I/O, excludes data-science and ML or GPU libraries, permits 5 concurrent executions, and sets a maximum timeout of 30 seconds so that entry-level usage remains constrained. | active | contextual | yes | |
| 5ff0f3a29caedbf9… | Tier 3 uses on-demand Firecracker microVMs, has no stated pool size, targets under 2 seconds P99 latency, provides VM-level isolation, and is intended for ML training, GPU workloads, and system dependencies. | active | contextual | yes | |
| be4844a12ebb87fb… | Tier 2 uses pre-warmed Docker containers based on python:3.11-slim, maintains a pool size of 5 with a 2 to 10 range, targets under 500 milliseconds P99 latency, provides container-level isolation, and supports pandas, numpy, CSV or Parquet I/O, and data pipelines. | active | contextual | yes | |
| 444fb0cff93b448f… | Tier 1 uses forked Python subprocesses with seccomp, maintains a pool size of 20 with a 5 to 40 range, targets under 100 milliseconds P99 latency, provides process-level isolation, and is intended for arithmetic, strings, and simple algorithms. | active | contextual | yes | |
| a9971aee143d04f4… | The tiered code interpreter architecture replaces a legacy single-tier Firecracker VM approach with three execution tiers mapped to subscription plans so that execution environments align with plan capabilities. | active | contextual | yes | |
| d864eb379be3e361… | The code interpreter executes Python code in isolated environments so that AI agents can generate structured JSON data programmatically with execution separated by runtime boundaries. | active | contextual | yes | |
| f42a579bf76c9956… | The CORTEX_LEARNING_ENABLED flag controls Q-value learning so that learning behavior based on Q-values can be enabled separately from other CORTEX features. | active | contextual | yes | |
| bf81d568a13840c4… | The CORTEX_AMBIENT_ENABLED flag controls the ambient research cycle so that background ambient research behavior can be toggled independently. | active | contextual | yes | |
| a772eb1ad77bb0d6… | The CORTEX_RETRIEVAL_INCLUDE_DYNAMIC_RESULTS flag enables Strategy 3, identified as Text2Cypher, so that retrieval can include dynamically generated graph-query results. | active | contextual | yes | |
| e6042c48c428cee5… | The CORTEX_ENABLED flag acts as the master switch so that the overall CORTEX capability can be enabled or disabled centrally. | active | contextual | yes | |
| 940691cd2e8ac7bf… | All CORTEX feature flags default to off so that advanced CORTEX capabilities remain disabled unless explicitly enabled. | active | contextual | yes | |
| 402b54d43ea04409… | The Qdrant payload filters include set_names, related_node_ids, and is_rank0_set_names so that vector queries can be constrained by set membership, graph linkage, and rank-0 status. | active | contextual | yes | |
| 5d8cc6ee53ff6407… | The Qdrant vector storage defines collections named docs_{region}, user_memory_{region}, and session_memory_{region} so that document, user memory, and session memory vectors are partitioned by region. | active | contextual | yes | |
| 97419c2dda9b2b78… | The vector storage layer uses Qdrant with the all-mpnet-base-v2 embedding model at 768 dimensions so that stored documents and memories share a consistent vector representation. | active | contextual | yes | |
| d8a0e1fca728f162… | The graph schema uses an IN_SET edge from CxU to set membership so that context units can be grouped into named sets within the graph. | active | contextual | yes | |
| 844197e101cccbd9… | The graph schema uses a DERIVED_FROM edge from one CxU to another so that lineage between derived and source context units is preserved. | active | contextual | yes | |
| 6037ec5a3223a6e9… | The graph schema uses a PRODUCED edge from AgentRun to CxU so that the system can track which agent execution generated each context unit. | active | contextual | yes | |
| 07f29a93a2761a01… | The graph schema uses a BELONGS_TO edge from child to parent in the hierarchy so that parent-child organizational relationships are encoded directly in the graph. | active | contextual | yes | |
| 31cbe8a398a948cd… | The graph schema uses a CONTEXT_FOR edge from CxU to an entity with dimension, q_value, and is_rank0 properties so that contextual relevance and ranking metadata can be attached to entity relationships. | active | contextual | yes | |
| b35aeaa8790da794… | The Neo4j graph schema defines memory nodes as MemoryNode with TEMPORAL_NEXT, SEMANTIC_SIMILAR, and REFERENCED relationships so that memory connections can be represented across time, semantics, and references. | active | contextual | yes | |
| 537d6e22e8a27c69… | The Neo4j graph schema defines agent nodes as AgentRun, ActionItem, and Analysis so that agent activity and outputs can be modeled as first-class graph entities. | active | contextual | yes | |
| c83827c217fd2139… | The Neo4j graph schema defines hierarchy nodes as Company, Pillar, Group, BusinessUnit, VirtualBusinessUnit, and CrossUnit so that organizational structure can be represented explicitly in the graph. | active | contextual | yes | |
| 60781454f58133cc… | The DraftCXU data model includes supporting_quotes as a list, knowledge_type as an enum, claim_type as an enum, is_assumption as a boolean, parent_assumption_ids as a list, keywords as a list, and confidence as a float from 0.0 to 1.0 so that metadata and provenance are preserved. | active | contextual | yes | |
| 3a7ca3a3261ffc9e… | The DraftCXU data model stores a claim as a standalone assertion between 15 and 70 words so that each extracted unit remains atomic and understandable without additional source context. | active | contextual | yes | |
| f542b1076fcc7bae… | The CXU data model defines a DraftCXU object with a cxu_id string formatted as "1220" plus a SHA-256 hex value, producing a 68-character identifier so that each CXU has a standardized unique ID. | active | contextual | yes | |
| b3c316cc82b5fde8… | The `IN_SET` edge represents CxU to Set membership so that context units can belong to named sets in the graph. | active | contextual | yes | |
| 004782dd0d3f8955… | The `DERIVED_FROM` edge connects one CxU to another CxU for lineage so that derivation relationships between context units are preserved. | active | contextual | yes | |
| 7f5de3fd96b8a7d9… | The `BELONGS_TO` edge connects a child node to its parent in the hierarchy so that hierarchical organizational relationships are represented in the graph. | active | contextual | yes | |
| ecf67483f25f81d3… | The `CONTEXT_FOR` edge connects a CxU to an entity and carries the properties `dimension`, `q_value`, and `is_rank0` so that contextual relevance and ranking metadata are stored on the relationship. | active | contextual | yes | |
| 3cb14a11d17dbf59… | The Neo4j graph schema defines memory nodes as MemoryNode with relationships TEMPORAL_NEXT, SEMANTIC_SIMILAR, and REFERENCED so that memory connections can be modeled explicitly. | active | contextual | yes | |
| 9166ed6e3d4bfef6… | A DraftCXU includes a `confidence` field of type float ranging from 0.0 to 1.0 so that extraction certainty can be represented numerically. | active | contextual | yes | |
| 0200b798593ee8e7… | A DraftCXU includes a `keywords` list field so that important retrieval terms can be stored with the context unit. | active | contextual | yes | |
| de11e75eab547562… | A DraftCXU includes a `parent_assumption_ids` list field so that assumptions can reference parent assumptions for lineage or dependency tracking. | active | contextual | yes | |
| 83704c959440b1a4… | A DraftCXU includes an `is_assumption` boolean field so that the system can mark whether a context unit is treated as an assumption. | active | contextual | yes | |
| 718df32478c5b6f7… | A DraftCXU has a `claim_type` enum field for values such as definition, requirement, and procedure so that the form of the claim is explicitly labeled. | active | contextual | yes | |