simhacker/moollm/data-flow

stage/
├── ROOM.yml       # Config and processor definition
├── inbox/         # Incoming queue (FIFO)
├── outbox/        # Staged for batch throwing
└── door-next/     # Exit to next stage

processor:
  type: script
  command: "python parse.py ${input}"

processor:
  type: llm
  prompt: |
    Analyze this document:
    - Extract key entities
    - Summarize in 3 sentences

processor:
  type: hybrid
  pre_process: "extract.py ${input}"
  llm_prompt: "Analyze extracted data"
  post_process: "format.py ${output}"

uploads/              # Raw files land here
├── inbox/
│   ├── doc-001.pdf
│   └── doc-002.pdf
└── door-parser/
 
parser/               # Extract text
├── script: parse.py
└── door-analyzer/
 
analyzer/             # LLM analyzes
├── prompt: "Summarize..."
├── door-output/
└── door-errors/
 
output/               # Final results
└── inbox/
    ├── doc-001-summary.yml
    └── doc-002-summary.yml

> ENTER parser
Inbox: 2 items waiting.
 
> NEXT
Processing doc-001.pdf...
Text extracted.
 
> STAGE doc-001.txt door-analyzer
Staged.
 
> FLUSH
Throwing 2 items through door-analyzer...

routing_rules:
  - if: "priority == 'high'"
    throw_to: door-fast-track
  - if: "type == 'archive'"
    throw_to: door-archive
  - default: door-standard

batch_size: 10
on_batch_complete: |
  Combine all results
  Generate summary report
  THROW report.yml door-output