version: '3'

tasks:
  generate:
    desc: Run templ generate
    cmds: [templ generate]
  build:
    desc: Build all binaries
    deps: [generate]
    cmds:
      - go build -o bin/jepa-fx-risk ./cmd/jepa-fx-risk
      - go build -o bin/eval ./cmd/eval
  run:
    deps: [build]
    cmds: [./bin/jepa-fx-risk]
  test:
    desc: Run all tests
    deps: [generate]
    cmds: [go test ./... -race]

  data:fetch:
    desc: "Download EUR/USD M1 from histdata (set YEARS env var)"
    cmds: [.venv/bin/python scripts/fetch_data.py]
  data:fetch:historical:
    desc: "Download EUR/USD M1 2008-2018 from histdata"
    cmds:
      - YEARS=2008,2009,2010,2011,2012,2013,2014,2015,2016,2017,2018 .venv/bin/python scripts/fetch_data.py
  data:prepare:daily:
    desc: "Rebuild eurusd_daily.parquet from all M1 zips"
    cmds: [.venv/bin/python scripts/prepare_data.py]
  data:prepare:hourly:
    desc: "Build eurusd_hourly.parquet from all M1 zips"
    cmds: [.venv/bin/python scripts/prepare_hourly.py]
  data:prepare:all:
    desc: "Build both daily and hourly parquets"
    deps: [data:prepare:daily, data:prepare:hourly]
  train:multipair:
    desc: "Train 5-pair G10 HEPA (D=256, best config, phase1_r2≈0.44)"
    cmds: [JEPA_USE_MULTIPAIR=1 JEPA_D_MODEL=256 .venv/bin/python train.py]

  data:fetch:multipair:
    desc: "Download G10 M1 data (GBPUSD/USDJPY/USDCHF/AUDUSD) 2008-2023 from histdata"
    cmds: [.venv/bin/python scripts/fetch_multipair.py]
  data:prepare:pair:
    desc: "Build {PAIR}_hourly.parquet from data/raw/{PAIR}/ (e.g. PAIR=gbpusd)"
    cmds: [PAIR={{.PAIR}} .venv/bin/python scripts/prepare_hourly.py {{.EXTRA_ARGS}}]
    vars:
      PAIR: '{{default "eurusd" .PAIR}}'
  data:prepare:multipair:
    desc: "Merge 5-pair hourly parquets into eurusd_multipair.parquet"
    cmds: [.venv/bin/python scripts/prepare_multipair.py]
  data:test:
    desc: "Run Python data pipeline tests"
    cmds: [.venv/bin/python -m pytest tests/test_prepare_hourly.py tests/test_hepa.py tests/test_multipair.py -v]

  eval:probe:
    desc: "Run linear-probe (val_vol_r2) on embeddings from metrics.json"
    cmds: [./bin/eval -metric probe]
  eval:silhouette:
    desc: "Run silhouette on embeddings vs binary HV labels"
    cmds: [./bin/eval -metric silhouette]
  eval:collapse:
    desc: "Run effective-rank collapse diagnostic"
    cmds: [./bin/eval -metric erank]
  lint:
    cmds: [golangci-lint run ./...]
  check:
    desc: Lint, vet, and test (used by CI)
    deps: [generate]
    cmds:
      - golangci-lint run ./...
      - go vet ./...
      - go test ./... -race -count=1

  context:sync:
    desc: Regenerate all harness-specific context files
    cmds:
      - bash scripts/context-sync.sh
  context:sync:claude:
    cmds: [bash scripts/context-sync.sh claude]
  context:sync:agents:
    cmds: [bash scripts/context-sync.sh agents]
  context:sync:cursor:
    cmds: [bash scripts/context-sync.sh cursor]