| 84b3f57f7b218c57… | The context engine and knowledge management architecture includes a KAG triple-store composed of PostgreSQL, Neo4j, and Qdrant so that knowledge can be represented across relational, graph, and vector storage layers. | active | contextual | yes | |
| ab770f89a426dde5… | When evaluating AI research papers for PYRANA relevance, reviewers should consider specific technical areas including context engine and knowledge management, agent orchestration, and code execution so that research is assessed against platform-aligned architecture concerns. | active | contextual | yes | |
| 199226f1f97d224f… | The pyrana-demo-2 frontend uses the same @pyrana/* library architecture and contains the directories client/, deploy/, docs/, frontend/, infrastructure/, and scripts/ so that its structure aligns with the broader platform conventions. | active | contextual | yes | |
| cc1acb14addb42be… | The pyrana-demo-2 frontend is a financial analysis demo on the financial-analysis-demo branch and includes PLANNING.md for financial analysis components and action items so that demo-specific planning artifacts are available with the codebase. | active | contextual | yes | |
| 5272b2cbc56c6a08… | Running pnpm run scaffold:client-page -- --route /revenue-dashboard creates both a component and a route wrapper so that new client pages can be scaffolded quickly. | active | contextual | yes | |
| 1e105d7d1388901c… | Users customize the frontend template by editing pages and views under frontend/src/client/pages/*, navigation in frontend/src/client/config/navigation.ts, and optional branding, assets, and client configs so that client-specific behavior and presentation can be tailored. | active | contextual | yes | |
| d5b1af08885b82cb… | The frontend template automatically injects core admin navigation and pre-sets the app router, layouts/providers, telemetry hooks, auth guard, and environment wiring so that foundational application structure is already configured. | active | contextual | yes | |
| 951f1ceed98051b3… | The frontend template includes @pyrana/* libraries for auth, admin, config, SDK, telemetry, types, UI, and charts so that common platform capabilities are available by default. | active | contextual | yes | |
| 80e71d0211d458f0… | The pyrana-frontend-template is a bootstrap Next.js shell for building client-facing applications, while the backend is delivered as published images in Azure Container Registry so that this repository only builds the frontend. | active | contextual | yes | |
| b5ce3059c92b8c23… | Tier 1 execution uses seccomp syscall filtering so that process isolation is strengthened at the syscall level. | active | contextual | yes | |
| 1549053fb644220f… | Execution has a 10 second timeout that is configurable per plan so that workloads are bounded in duration while allowing plan-specific adjustments. | active | contextual | yes | |
| 3035fa5d61e0ad24… | The security configuration enforces a PID limit of 50 to prevent fork bombs so that runaway process creation is constrained. | active | contextual | yes | |
| bf60cf1cd3c1d683… | Containers are limited to 128MB of memory and 0.5 CPU cores so that execution resource consumption remains bounded. | active | contextual | yes | |
| f305ccb7b791d109… | Container networking is disabled in the security model so that executed workloads cannot access external networks from inside containers. | active | contextual | yes | |
| db18422bf2c57901… | The API exposes a GET /metrics endpoint that reports concurrency metrics including active_executions, max_concurrent, and available_slots so that runtime capacity can be observed externally. | active | contextual | yes | |
| dc236ec894571bc8… | The API exposes a GET /health endpoint for Kubernetes probes so that orchestration systems can verify service health. | active | contextual | yes | |
| 90d40d25db9954fd… | The API exposes a POST /run endpoint that executes Python code and can optionally use workspace, input_files, and output_files for Azure Blob I/O so that code execution can exchange artifacts with blob storage. | active | contextual | yes | |
| 9c2b10471911a215… | The PoolStateManagerAgent consumes all events and auto-scales every 30 seconds so that pool capacity can be adjusted based on observed system activity. | active | contextual | yes | |
| 95e45ade08536d57… | The QueueOptimizerAgent polls queue depths every 1 second and activates backpressure at 80 percent so that queue overload can be controlled before saturation. | active | contextual | yes | |
| d4ebf9817a1edbc8… | The HealthMonitorAgent checks pool slot health every 10 seconds and restarts FAILED slots so that unhealthy execution capacity is automatically recovered. | active | contextual | yes | |
| f1af3addfc1de3ff… | The ResourceMonitorAgent polls /proc/meminfo every 5 seconds to track memory pressure so that the system can observe memory conditions continuously. | active | contextual | yes | |
| 5e3cde9bc11cec37… | The platform includes five background agents in its agent system so that resource usage, health, performance, queue pressure, and pool state are continuously monitored and managed during operation. | active | contextual | yes | |
| cbdd46fb6756ac4a… | Tier 1 applies seccomp syscall filtering so that low-level system calls are restricted during process-level code execution. | active | contextual | yes | |
| 0b2c9c67e625a765… | Security configuration sets a 10 second execution timeout that is configurable per plan so that runaway code is terminated while allowing plan-based timeout variation. | active | contextual | yes | |
| 4c870393a8c9ef12… | Security configuration enforces a PID limit of 50 so that fork bombs are prevented during code execution. | active | contextual | yes | |
| 575d640c2031bfbe… | Security configuration limits memory to 128MB and CPU to 0.5 cores so that code execution remains resource constrained within the interpreter environment. | active | contextual | yes | |
| e8a8a0d896c8b11f… | Security configuration disables network access in containers so that code executed inside containerized environments cannot communicate over the network. | active | contextual | yes | |
| 3139c8ac00c5ece1… | The GET /metrics API endpoint exposes concurrency metrics including active_executions, max_concurrent, and available_slots so that clients and operators can inspect execution capacity and usage. | active | contextual | yes | |
| da6abe40f9027820… | The POST /run API endpoint executes Python code and optionally accepts workspace, input_files, and output_files for Azure Blob I/O so that clients can run code with associated file-based inputs and outputs. | active | contextual | yes | |
| ae037c8b45035841… | The PoolStateManagerAgent consumes all events and auto-scales every 30 seconds so that execution pool capacity can adjust automatically in response to system activity. | active | contextual | yes | |
| 82dbe359cec7d527… | The QueueOptimizerAgent polls queue depths every 1 second and activates backpressure at 80 percent so that queue overload can be mitigated before saturation occurs. | active | contextual | yes | |
| 5647f440ea7ae150… | The PerformanceAnalyzerAgent maintains a rolling window of 200 samples per tier and computes P50, P95, and P99 metrics so that execution performance can be analyzed by tier over recent activity. | active | contextual | yes | |
| f905bc8aff008acf… | The 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 | |
| bc7538c06ba4eaa3… | The Gold subscription plan permits all tiers, allows file I/O, data-science libraries, and ML or GPU libraries, supports unlimited concurrency, and sets a maximum timeout of 600 seconds. | active | contextual | yes | |
| e5df39c4bc79046f… | The Silver subscription plan permits Tier 1 and Tier 2 execution, allows file I/O and data-science libraries, disallows ML or GPU libraries, allows up to 20 concurrent executions, and sets a maximum timeout of 120 seconds. | active | contextual | yes | |
| 21ac18c9365d2a2d… | The Bronze subscription plan permits only Tier 1 execution, disallows file I/O, data-science libraries, and ML or GPU libraries, allows up to 5 concurrent executions, and sets a maximum timeout of 30 seconds. | active | contextual | yes | |
| 8a87e120e44d926c… | Tier 2 uses pre-warmed python:3.11-slim Docker containers, 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 | |
| 6ed7e86a06858ea4… | The tiered architecture replaces a legacy single-tier Firecracker VM approach with three execution tiers mapped to subscription plans so that execution environments align with customer plan levels. | active | contextual | yes | |
| 8e9719e85ae1119f… | The code interpreter executes Python code in isolated environments and is designed for AI agents to generate structured JSON data programmatically so that agent workflows can run code safely and produce machine-readable outputs. | active | contextual | yes | |
| 35be45e90e8e84c8… | CORTEX_LEARNING_ENABLED controls Q-value learning so that the platform’s learning behavior remains disabled until this feature flag is explicitly enabled. | active | contextual | yes | |
| 96646f1721d60c1e… | CORTEX_AMBIENT_ENABLED controls the ambient research cycle so that background research behavior can be activated only when this feature flag is enabled. | active | contextual | yes | |
| 59cffc13a3a5e376… | CORTEX_RETRIEVAL_INCLUDE_DYNAMIC_RESULTS enables Strategy 3, identified as Text2Cypher, so that retrieval can include dynamically generated graph-query results when the flag is turned on. | active | contextual | yes | |
| 2113c4955493cf98… | CORTEX_ENABLED serves as the master switch for CORTEX functionality so that the platform can globally enable or disable the feature set from a single flag. | active | contextual | yes | |
| ee0b86d6f70584d7… | Qdrant payload filters include set_names, related_node_ids, and is_rank0_set_names so that vector queries can be constrained by set membership, related graph nodes, and rank-0 set flags. | active | contextual | yes | |
| 2cd9c97b017c01f5… | Qdrant vector storage uses region-scoped collections named docs_{region}, user_memory_{region}, and session_memory_{region} so that document, user memory, and session memory vectors are separated by region. | active | contextual | yes | |
| 043c40626e39d34d… | Vector storage uses the all-mpnet-base-v2 embedding model with 768 dimensions so that stored documents and memories can be represented as fixed-length vectors for retrieval. | active | contextual | yes | |
| 46a43d9c8b3f1d51… | The IN_SET edge records membership from a CxU to a set so that context units can be grouped into named collections within the graph model. | active | contextual | yes | |
| 1b6b0afc67625d79… | The DERIVED_FROM edge connects one CxU to another so that lineage between derived and source context units can be preserved in the graph. | active | contextual | yes | |
| 3f1f15fa9b005763… | The PRODUCED edge links an AgentRun to a CxU so that the system can record which agent execution generated a specific context unit. | active | contextual | yes | |
| cc19bc72c54ef18a… | The BELONGS_TO edge links a child node to its parent in the hierarchy so that the organizational tree can be traversed and maintained within the graph. | active | contextual | yes | |