PHASE2_SCOPE_DECISION.md contains research outputs related to Phase 2. Phase 2 research outputs include LOAD_STRATEGY.md as a component of research. Phase 2 research outputs include IMPLEMENTATION_PLAN.md as a component of research. Phase 2 research outputs include the Memory research document as part of the documentation. Phase 2 research outputs include the Memory decision point document as part of the documentation. Phase 2 research outputs include PHASE2_IMPLEMENTATION_PLAN.md as part of the documentation. Phase 2 research outputs include PHASE2_LOAD_STRATEGY.md as part of the documentation. Phase 2 research outputs contain PHASE2_SCOPE_DECISION.md. Phase 2 research outputs include SOUL.md in the research documents.

Phase 2 Strategy involves using Opus 4.6 to generate PHASE2_UNIFIED_STRATEGY.md and Sonnet 4.6 for PHASE2_IMPLEMENTATION_PLAN.md. The decision depends on processing status and Excel tables loaded during Phase 1, with Jesper responsible for approval. Currently running old code, the backend services await code update for full functionality.

Develop and deploy SvelteKit i18n framework, translate UI strings to Danish, load language from user settings, and ensure UI reflects preference.

Phase A Schema Graph Construction implements the creation of the Schema Graph representing join relationships and clustering of tables.

Phase A includes the batch upload and enhanced AI cataloging as part of the batch upload pipeline implementation. The batch upload pipeline includes Phase A which is batch upload plus enhanced AI cataloging.

Phase B Intelligent Retrieval implements the Query Enhancer for entity extraction and relevant table identification for queries. Phase B involving the smart auto-processing pipeline with Qdrant is part of the smart processing UX model.

Phase C Integration modifies Backend Application Services to use consolidated views for query analysis within the DataLens System. Phase C, the unified question interface, is part of the smart processing UX model for DataLens.

Documentation detailing the GPU-focused document extraction system, protocols, and deployment procedures, aligned with recent implementation efforts.

A requirement doc that summarizes a GPU-first document extraction system, its architecture, and performance expectations for DataLens Phase 2.

The plan outlines a phased approach for MVP to ambitious features, starting with a 5-7 day MVP deployment, based on research and decision memos. PHASE2_IMPLEMENTATION_PLAN.md provides go/no-go recommendation and effort analysis for Phase 2 file types processing PHASE2_SCOPE_DECISION.md includes PHASE2_IMPLEMENTATION_PLAN.md as part of the Phase 2 research outputs. Phase 2 research outputs include PHASE2_IMPLEMENTATION_PLAN.md as part of the documentation. Sonnet 4.6 created the PHASE2_IMPLEMENTATION_PLAN.md containing the go/no-go recommendation and effort versus value analysis. The PHASE2_UNIFIED_STRATEGY.md and PHASE2_IMPLEMENTATION_PLAN.md documents contain complementary research outputs informing Phase 2 implementation decisions.

This document details the load strategy for Phase 2, referencing file naming conventions and strategic decisions in the implementation documentation. PHASE2_SCOPE_DECISION.md includes PHASE2_LOAD_STRATEGY.md as part of the Phase 2 research outputs. Phase 2 research outputs include PHASE2_LOAD_STRATEGY.md as part of the documentation.

PHASE2_SCOPE_DECISION.md contains a comparison between MVP and Ambitious options. PHASE2_SCOPE_DECISION.md includes the Memory research document dated 2026-02-24. PHASE2_SCOPE_DECISION.md includes the Memory decision point document dated 2026-02-25. PHASE2_SCOPE_DECISION.md contains research outputs related to Phase 2. PHASE2_SCOPE_DECISION.md contains the LOAD_STRATEGY.md design element. PHASE2_SCOPE_DECISION.md contains the IMPLEMENTATION_PLAN.md design element. PHASE2_SCOPE_DECISION.md recommends starting with the MVP option for 5-7 days, intending to expand to Ambitious if policy questions arise. PHASE2_SCOPE_DECISION.md document defines the side-by-side comparison and decision points of the Phase 2 Strategy Research & Decision Point PHASE2_SCOPE_DECISION.md includes IMPLEMENTATION_PLAN.md as part of the Phase 2 research outputs. PHASE2_SCOPE_DECISION.md includes the Memory research document as part of the Phase 2 research outputs. PHASE2_SCOPE_DECISION.md includes the Memory decision point document as part of the Phase 2 research outputs. PHASE2_SCOPE_DECISION.md includes PHASE2_IMPLEMENTATION_PLAN.md as part of the Phase 2 research outputs. PHASE2_SCOPE_DECISION.md includes PHASE2_LOAD_STRATEGY.md as part of the Phase 2 research outputs. Phase 2 research outputs contain PHASE2_SCOPE_DECISION.md. Opus 4.6 created the PHASE2_SCOPE_DECISION.md which compares MVP vs Ambitious approaches, provides timeline, risk analyses, and file type strategies.

PHASE2_UNIFIED_STRATEGY.md defines the pipeline design and tool justifications for processing Phase 2 file types Opus 4.6 created the PHASE2_UNIFIED_STRATEGY.md which contains pipeline design, tool justifications, and question-to-data mapping. The PHASE2_UNIFIED_STRATEGY.md and PHASE2_IMPLEMENTATION_PLAN.md documents contain complementary research outputs informing Phase 2 implementation decisions.

The plan calls for testing the full pipeline from upload to query and insight generation.

The DataLens DS-STAR Implementation Plan includes the Planner component for creating extraction plans. Planner produces multi-step extraction plans for data processing.

DS-STAR Intelligence includes the PlannerAgent component. The plan contains the Planner Agent that creates multi-step extraction plans based on the data catalog. PlannerAgent is a part of the DS-STAR pipeline. DS-STAR Orchestrator has PlannerAgent as a step in its workflow DSStarOrchestrator uses the planner agent in its extraction strategy creation DS-STAR Orchestrator has PlannerAgent as a step in its workflow DSStarOrchestrator uses the planner agent in its extraction strategy creation DS-STAR Intelligence capability encompasses the PlannerAgent component for document analysis and strategy creation. The DS-STAR pipeline includes the PlannerAgent component. The Planner Agent is part of the DataLens DS-STAR Implementation Plan to generate multi-step extraction plans. The DS-STAR Intelligence Layer includes the PlannerAgent component. DS-STAR Intelligence includes the PlannerAgent that analyzes files and creates extraction strategies using Ollama. Planner Agent uses the data catalog generated by FileAnalyzer as input.

The Platform Backend uses a multi-tenant PostgreSQL schema to support data modeling and authentication. The Platform Backend implements bearer token authentication for session management and user access. The Platform Backend integrates the DS-STAR FileAnalyzer for automatic cataloging of uploaded files. The Platform Backend extracts data into DuckDB tables for analysis and query execution. The Platform Backend implements a natural language query endpoint to generate and execute SQL queries from user questions. The Platform Backend is built as a FastAPI app exposing API endpoints for auth, projects, files, extraction, and analysis. The Platform Backend uses DS-STAR subprocess calls to implement cataloging, extraction, and SQL generation features. Ollama provides the qwen3-coder-next and nomic-embed-text models integrated into the Platform Backend for AI-powered text-to-SQL and document embedding. Qdrant is integrated into the Platform Backend for storage and retrieval of document vectors supporting Document RAG. The Platform Backend depends on Redis 7 for future background job management and caching, although it is not yet implemented. The Docker Compose Stack includes the Platform Backend service as one of its containers alongside PostgreSQL and Redis. Coolify is the deployment platform intended to host the Platform Backend service and its supporting infrastructure. The Platform Backend depends on DS-STAR FileAnalyzer to perform automatic cataloging immediately after file upload.

Playwright is used for end-to-end testing to validate User interactions and the platform's functionality. The npm dev dependency @playwright/test uses the bits-ui component as part of the frontend dependency set in the project.

Comprehensive end-to-end testing covering user flows, API, front-end, back-end, and system performance, ensuring high test coverage and quality. The E2E Test Suite includes Playwright tests for the Data Discovery feature. Playwright tests are part of the E2E Test Suite used to validate the Data Discovery Feature. Playwright E2E tests validate the functionality and integration of the Data Discovery system in DataLens. The frontend tests discovery-svgv.spec.ts are part of the Playwright E2E test suite for the Discovery feature. Frontend tests test-agent-e2e.spec.ts are included in the Playwright E2E test suite to validate the IronClaw agent feature. Playwright E2E tests use the test user admin@exerun.com for authentication and functional validation. DataLens Project includes Playwright E2E tests for frontend and user flows to verify platform completeness. The Discovery feature is validated by Playwright E2E tests to ensure functionality.

Playwright testing framework is used to end-to-end test and validate the functionalities of the Datalens SVGV Budget Platform. The E2E Test Suite comprises Playwright tests to validate the Data Discovery workflow.

Plotly is used for generating interactive data visualizations in DataLens, supporting various chart types and rendering in findings and reports.

Policy questions are addressed within the broader DataLens scope; no specific summary update provided in messages. Start MVP plan is recommended to be started before expanding to address Policy Questions if needed. Expansion to Ambitious plan involves adding support for Policy Questions.

Policy Researcher is a DS-STAR agent specialized in policy and compliance question answering. Agent Selector directs queries to the Policy Researcher agent