# Check if Lobster is installed
which lobster

# If not installed:
uv pip install lobster-ai
lobster init --help #to see non-interactive

lobster config-test --json

{
  "valid": true,
  "env_file": "/path/to/.env",
  "checks": {
    "llm_provider": {"status": "pass", "provider": "bedrock", "message": "Connected"},
    "ncbi_api": {"status": "pass", "has_key": true, "message": "Connected"},
    "workspace": {"status": "pass", "path": "/path/to/workspace", "message": "Writable"}
  }
}

✅ LLM Provider: bedrock (connected)
✅ NCBI API: Connected (with API key)
✅ Workspace: Writable
✅ Configuration Valid

# Show configuration values (masked)
lobster config-show

# Show subscription tier and available agents
lobster status

# Single query (non-interactive)
lobster query "<natural language request>"

# With custom workspace
lobster query --workspace /path/to/workspace "<request>"

# With reasoning mode (for complex tasks)
lobster query --reasoning "<request>"

# default session
lobster query "Search PubMed for CRISPR papers"
# Output: Session: session_20241208_150000 (use --session-id latest for follow-ups)
# then follow up with 
lobster query --session-id latest "Download the first dataset from that search"

#or use custom session id
lobster query --session-id "crispr_search_1" "Search PubMed for CRISPR papers"
#follow up with 
lobster query --session-id "crispr_search_1" "show me metadata from the first paper"

# Project 1: Cancer research
lobster query --workspace ~/cancer-project "Search for breast cancer datasets"
lobster query --workspace ~/cancer-project --session-id latest "Download the best one"

# Project 2: Immunology (separate session)
lobster query --workspace ~/immuno-project "Search for T cell datasets"
lobster query --workspace ~/immuno-project --session-id latest "Analyze that"

lobster query "Download GSE109564 and perform quality control"
lobster query "Cluster the dataset and find marker genes"
lobster query "Create UMAP visualization colored by cell type"

lobster query "Search PubMed for CRISPR screens in cancer"
lobster query "Find papers about CAR-T therapy and extract their GEO datasets"
lobster query "Get the full text and methods section for PMID:12345678"

lobster query "Search GEO for single-cell pancreatic beta cell datasets"
lobster query "Validate GSE200997 metadata for required fields: cell_type, tissue"
lobster query "Download SRA dataset SRP123456"

lobster query "Load counts.csv and run differential expression analysis"
lobster query "Perform batch correction on the loaded dataset"
lobster query "Generate volcano plot for DE results"

lobster query "Assess quality metrics for the loaded dataset"
lobster query "Filter cells with <200 genes or >8000 genes"
lobster query "Identify doublets using scrublet"

# List workspace files
ls -lh .lobster_workspace/

# Read specific outputs
cat .lobster_workspace/analysis_summary.json

# Step 1: Run analysis
lobster query --session-id "gse109564" "Download GSE109564, run QC, and cluster cells"

# Step 2: Check outputs
ls .lobster_workspace/*.h5ad
ls .lobster_workspace/*.html

# Step 3: Extract specific data
lobster query --session-id "gse109564" "Export cluster markers to CSV"

# Step 4: Use results in your code
# Results are now in .lobster_workspace/markers.csv

# Step 1: Find papers
lobster query "Search for papers about immune checkpoint inhibitors in melanoma"

# Step 2: Extract datasets
lobster query "Extract all GEO dataset IDs from the cached papers"

# Step 3: Validate datasets
lobster query "Check which datasets have cell_type and treatment metadata"

# Step 4: Download best match
lobster query "Download the dataset with most samples"

lobster query "Export the analysis pipeline as a Jupyter notebook"
# Creates a Papermill-compatible notebook in workspace

# Use custom workspace per project
lobster query --workspace ./project1-data "Analyze counts.csv"
lobster query --workspace ./project2-data "Analyze other-counts.csv"

# Use specific provider
lobster query --provider ollama "Run expensive analysis"  # Free local
lobster query --provider anthropic "Quick task"  # Fast cloud