# pipeline.yaml: a multi-task workflow.
#
#   horus run pipeline.yaml
#
# ingest -> validate -> { text features, image features } -> train -> report
#
# It fans out into two parallel feature stages and merges back at training, so
# the dependency graph is diamond-shaped. The `sleep`s let you watch the live
# TUI advance. Artifacts are passed between tasks with `$id` substitution (the
# on-target path), and the `edges` at the bottom declare both the ordering and
# the artifact routing. `skip_if_complete: false` makes every run actually
# execute (handy for a demo).
name: pipeline
kind: horus_workflow

tasks:
  - id: ingest
    name: Ingest data
    kind: horus_task
    skip_if_complete: false
    target: { kind: local, working_directory: "./horus-work" }
    runtime:
      kind: command
      command: "mkdir -p \"$$(dirname $raw)\"\nsleep 1\necho 'rows: 1000' > $raw\n"
    executor:
      kind: shell
    outputs:
      - { kind: file, id: raw, path: "./horus-out/raw.txt" }

  - id: validate
    name: Validate schema
    kind: horus_task
    skip_if_complete: false
    target: { kind: local, working_directory: "./horus-work" }
    runtime:
      kind: command
      command: "sleep 1\ncat $raw > $valid\necho 'validated: true' >> $valid\n"
    executor:
      kind: shell
    inputs:
      - { kind: file, id: raw, path: "./horus-out/raw.txt" }
    outputs:
      - { kind: file, id: valid, path: "./horus-out/valid.txt" }

  - id: features_text
    name: Text features
    kind: horus_task
    skip_if_complete: false
    target: { kind: local, working_directory: "./horus-work" }
    runtime:
      kind: command
      command: "sleep 2\ncat $valid > $feat_text\necho 'text_features: 256' >> $feat_text\n"
    executor:
      kind: shell
    inputs:
      - { kind: file, id: valid, path: "./horus-out/valid.txt" }
    outputs:
      - { kind: file, id: feat_text, path: "./horus-out/feat_text.txt" }

  - id: features_image
    name: Image features
    kind: horus_task
    skip_if_complete: false
    target: { kind: local, working_directory: "./horus-work" }
    runtime:
      kind: command
      command: "sleep 2\ncat $valid > $feat_image\necho 'image_features: 512' >> $feat_image\n"
    executor:
      kind: shell
    inputs:
      - { kind: file, id: valid, path: "./horus-out/valid.txt" }
    outputs:
      - { kind: file, id: feat_image, path: "./horus-out/feat_image.txt" }

  - id: train
    name: Train model
    kind: horus_task
    skip_if_complete: false
    target: { kind: local, working_directory: "./horus-work" }
    resources:
      cpus: 8
      gpus: 2
      memory_gb: 32
      walltime: "01:00:00"
    runtime:
      kind: command
      command: "sleep 3\ncat $feat_text $feat_image > $model\necho 'model: trained' >> $model\n"
    executor:
      kind: shell
    inputs:
      - { kind: file, id: feat_text, path: "./horus-out/feat_text.txt" }
      - { kind: file, id: feat_image, path: "./horus-out/feat_image.txt" }
    outputs:
      - { kind: file, id: model, path: "./horus-out/model.txt" }

  - id: report
    name: Write report
    kind: horus_task
    skip_if_complete: false
    target: { kind: local, working_directory: "./horus-work" }
    runtime:
      kind: command
      command: "sleep 1\necho '=== REPORT ===' > $report\ncat $model >> $report\n"
    executor:
      kind: shell
    inputs:
      - { kind: file, id: model, path: "./horus-out/model.txt" }
    outputs:
      - { kind: file, id: report, path: "./horus-out/report.txt" }

# Edges are the sole source of truth for ordering and the dependency DAG.
edges:
  - { source: ingest,         source_output: raw,        target: validate,       target_input: raw }
  - { source: validate,       source_output: valid,      target: features_text,  target_input: valid }
  - { source: validate,       source_output: valid,      target: features_image, target_input: valid }
  - { source: features_text,  source_output: feat_text,  target: train,          target_input: feat_text }
  - { source: features_image, source_output: feat_image, target: train,          target_input: feat_image }
  - { source: train,          source_output: model,      target: report,         target_input: model }