Configuration data for an IronClaw agent session, handled by the ironclaw_client.py service.

IronClawSkills uses IronClawTools to provide skill definitions callable by IronClaw agent. IronClawToolRegistry registers tools that are used by IronClawSkills for agent skills execution. IronClawClient uses IronClawSkills definitions for agent skill execution via the IronClaw Gateway.

Manages registration of tools with the IronClaw gateway; located in backend/app/services/tool_registry.py. IronClawToolRegistry registers tools that are used by IronClawSkills for agent skills execution.

IronClawSkills uses IronClawTools to provide skill definitions callable by IronClaw agent.

Platform supports cross-file queries using standard schemas and AI mapping. No specific mention of current IT questions in messages.

Internal data analyst at Acme Corp, involved in platform development and testing, with medium influence in project decisions.

Jesper is a Copenhagen-based AI consultant and builder. Jesper is the key stakeholder responsible for approving the decision on Phase 2 Strategy Research & Decision Point Direct communicator Jesper approved progressing with AI Summary Generation and vectorize progress tracking fixes in the same session for accuracy. Direct communicator Jesper prefers the longer fix implementing vectorize progress tracking rather than just quick AI summary fixes. Jesper DevOps is responsible for executing the agent migration file 003_agent_tables.sql to enable the IronClaw agent database functionality. Jesper depends on Coolify for deploying and managing the backend container. DataLens agent is owned by Jesper. Phase 2 Strategy Research & Decision Point uses the opinion of Jesper who favors a single coherent strategy rather than patchwork in deciding file processing scope. The opinion of Jesper influences the Phase 2 Strategy Research & Decision Point by favoring one coherent strategy instead of a patchwork approach. Jesper is responsible for manually testing the IronClaw Agent Feature and verifying the deployment status. DataLens agent is owned by Jesper, an AI consultant based in Copenhagen.

The Backend discovery service depends on Join discovery mechanisms to find table relationships.

DiscoveryService uses JoinPath to represent joins between database tables for consolidation.

To ensure cross-database compatibility, the DataLens Platform uses JSON format instead of JSONB or ARRAY for storing structured data.

DataLens Development incorporates JWT authentication in its security architecture.

KeyError:0 bug in API endpoint causes blocking issues for Phase 1 batch processing

Timeout issues during query classification are mitigated by switching to keyword classification which takes under 10ms compared to prior 120s LLM classification.

The Discovery Service applies the Known keys join strategy to discover joins with 95% confidence.

Testing, Benchmarks, Polish uses KramaBench for data analysis benchmarking. The DataLens Master Implementation Plan uses KramaBench as part of data analysis benchmarks in the testing phases. Data analysis benchmarks include KramaBench as one of the benchmarking tools.

DataLens needs to adopt LangChain or LiteLLM to enable flexibility in choosing LLM providers beyond Ollama. DataLens requires using LangChain or similar to support multiple LLM providers beyond Ollama. LangChain is used within the implementation plan for chaining LLM and agent workflows. The system uses LangChain framework alongside DuckDB for data pipeline management.

The User Language Preference capability requires the Language column in users table.

The stable state of DataLens OpenClaw Integration depends on the last known good commit before timeout/skill loading changes caused regressions. The last known good commit will be reverted, pushed to master branch and auto-deployed via Coolify as the next step to restore function.

Lazy Loading Implementation is part of the PDF Infrastructure feature set to enhance user experience during large PDF uploads.

The lib/elin.py wrapper in the DataLens Project uses OpenClaw node pairing for remote invocation. The theo directory contains the lib/elin.py communication helper for DataLens.

Vanna 2.0 implements lifecycle hooks for quota checking, logging, and content filtering at request lifecycle points. Vanna 2.0 utilizes lifecycle hooks for quota checking, logging, and content filtering at request lifecycle points. Vanna 2.0 architecture uses lifecycle hooks for quota checking, logging, and content filtering