DataLens Orchestrator uses the OpenClaw memory system for conversation state management.

OpenClaw node is a component or server related to OpenClaw system. The DataLens Project uses OpenClaw node pairing for communication between theo and elin servers. The lib/elin.py wrapper in the DataLens Project uses OpenClaw node pairing for remote invocation. The DataLens Master Implementation Plan leverages the OpenClaw node deployed on the agent server for agent orchestration and skill execution. The implementation plan depends on a stable OpenClaw node connection which should be reconnected if needed.

DataLens Project integrates OpenClaw node pairing to connect theo and elin via SSH tunnel.

The decision is to implement Option A which involves reverting to the last known good commit and deploying it to resolve current issues with DataLens OpenClaw Integration. The stable state of DataLens OpenClaw Integration depends on the last known good commit before timeout/skill loading changes caused regressions. DataLens OpenClaw Integration is preparing deployment by reverting code and pushing to master branch, with deployment expected to follow automatically with Coolify. Claude successfully responded in Danish with a streaming response about the budget database during a previous successful session of DataLens OpenClaw Integration on March 23, 2026, 20:36.

IronClaw Gateway depends on OpenClaw Skill API on the agent server to run ringfenced executor skills safely. theo Backend uses the OpenClaw Skill API via HTTP on elin to execute ringfenced database queries safely for the agent. OpenClaw Skill API queries DuckDB which contains 473 extracted budget tables for analytical data. OpenClaw Skill API references PostgreSQL database for metadata of the 132 budget files. DataLens Skill development involves creating an OpenClaw skill following best practices.

theo Backend communicates via HTTP with OpenClaw Skill API at elin:8002 to execute ringfenced SQL queries securely. OpenClaw Skill API depends on DuckDB that holds the 473 extracted budget tables for fast in-memory querying. OpenClaw Skill API depends on PostgreSQL which stores metadata for the 132 budget files. The DataLens Skill capability uses the OpenClaw skill framework to manage conversation state and skill execution.

The openclaw user owns and operates the OpenClaw agent service on the agent server to enforce least privilege security and service isolation.

Backend API uses OpenClaw Gateway WebSocket client to communicate with OpenClaw Gateway for agent chat operations. Backend API uses OpenClaw Gateway WebSocket client to communicate with OpenClaw Gateway for agent chat operations.

OpenClawHttpClient in the backend integrates with OpenClaw Gateway for WebSocket streaming communication Agent Chat interface uses OpenClawHttpClient component for communication with agent backend EmbeddingService integrates with OpenClawHttpClient to use Ollama on elin GPU for embedding computations. IronClawClient depends on OpenClawHttpClient for streaming communication with OpenClaw Gateway. OpenClawHttpClient serves as a WebSocket client alternative implementation to the HTTP-based IronClawClient for streaming agent responses.

Streaming event generated by OpenClaw Gateway, streamed via openclaw_http_client.py.

Pandas uses openpyxl for Excel file exporting and processing.

Generate a strong 32-byte hex secret key for system security. DataLens Platform deployment requires using openssl rand -hex 32 to generate a session signing key (SECRET_KEY).

DataLens depends on the Ops Engineer to review and approve deployment requests. Ops Engineer approves deployments listed in DEPLOYMENT_QUEUE.md and authorizes execution. Ops Engineer controls deployment execution of DataLens and is responsible for safe deployment procedures.

The ops user owns and runs the Skill API on the agent server, handling ringfenced SQL execution isolated from the OpenClaw agent service.

The decision is to implement Option A which involves reverting to the last known good commit and deploying it to resolve current issues with DataLens OpenClaw Integration.

DataLens spawns Opus sub-agent for system design decisions, complex refactoring, ambiguous requirements, or high-stakes decisions. DataLens Agent (Opus) developed the project goal field design proposal. Phase 2 Strategy Research & Decision Point involves the use of Opus 4.6 agent for generating PHASE2_UNIFIED_STRATEGY.md document DataLens agent spawns Opus sub-agent to handle system design decisions, complex refactoring, ambiguous requirements, and high-stakes decisions. Opus 4.6 created the PHASE2_UNIFIED_STRATEGY.md which contains pipeline design, tool justifications, and question-to-data mapping. Opus 4.6 and Sonnet 4.6 together were used to triangulate decision for the Phase 2 strategy due to GPT-5.2 unavailability. Opus 4.6 created the PHASE2_SCOPE_DECISION.md which compares MVP vs Ambitious approaches, provides timeline, risk analyses, and file type strategies. Opus 4.6 recommends text extraction from all 48 PDFs with OCR only where relevant due to medium-high ROI and 2-3 hours effort estimation. Opus 4.6 recommends parsing all DOCX files if policy questions are real; otherwise selectively processing top 20, valuing DOCX as having high ROI for 3-4 hours effort. Opus 4.6 recommends processing all 3 PPTX files due to low cost and consistent summary value. Opus 4.6 recommends processing all 2 MSG files as they provide governance signals. Opus 4.6 recommends the MVP approach as a minimum viable product completing 25 of 35 analytical questions in 5 to 7 days with selective ingestion. Opus 4.6 recommends against full 153-file load due to complexity and risk, suggesting a phased selective ingestion instead. Opus analysis investigates the behavior of agent_skills.py process_message() to diagnose async exception issues.

Organization physical table includes multiple User entities representing users belonging to an organization. Project physical table represents projects that belong to an Organization entity. Organization physical table contains User physical table as members belonging to the organization. Organizations have users tables which store information about users belonging to the organization. Organizations contain projects tables which list all projects under the organization.

The Frontend Components include the OutlierHighlight.svelte UI component for displaying anomaly detection information. The OutlierHighlight.svelte UI component is part of the Full Findings Visualization Layer showing anomaly detection displays. The OutlierHighlight.svelte UI component is part of the Full Findings Visualization Layer showing anomaly detection displays.

Comprehensive E2E test strategy using Playwright, covering core workflows, UX interactions, performance, and data validation, successfully completed and documented.

The Extraction pipeline in the DataLens Platform uses pandas for data manipulation and loading extracted data. Pandas uses openpyxl for Excel file exporting and processing. Lux-api depends on pandas for auto-visualization features.