# -----------------------------------------------------------------------------
# MINIMAL workflow — the canonical "run a backtest" template for the skill.
#
# Every traced backtest runs through a workflow YAML like this one via
# rd_run_workflow, so the `record` blocks write MLflow artifacts to disk
# (<lake>/mlruns/<exp_id>/<run_id>). The traced experiment's ref id IS the
# mlflow run id returned by rd_run_workflow.
#
# Trigger:
#   rd_run_workflow config_path=examples/workflow_minimal.yaml \
#       experiment_name=tac-rd-minimal
# -----------------------------------------------------------------------------
{%- set LAKE = TAC_LAKE_DIR %}

qlib_init:
    provider_uri: "{{ LAKE }}"
    region: us
    expression_cache: null
    dataset_cache: null

    calendar_provider:
        class: tac_qlib.data.providers.LakeCalendarProvider
        kwargs: { lake_root: "{{ LAKE }}", market: US }
    instrument_provider:
        class: tac_qlib.data.providers.LakeInstrumentProvider
        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
    feature_provider:
        class: tac_qlib.data.providers.LakeFeatureProvider
        kwargs: { lake_root: "{{ LAKE }}", market: US }

    exp_manager:
        class: MLflowExpManager
        module_path: qlib.workflow.expm
        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-minimal" }

task:
    model:
        class: LGBModel
        module_path: qlib.contrib.model.gbdt
        kwargs:
            loss: mse
            learning_rate: 0.05
            num_leaves: 15
            n_estimators: 200
            colsample_bytree: 0.8
            subsample: 0.8
            subsample_freq: 1
            reg_alpha: 0.01
            reg_lambda: 0.01

    dataset:
        class: DatasetH
        module_path: qlib.data.dataset
        kwargs:
            handler:
                class: TACHandler
                module_path: tac_qlib.contrib.data.handler
                kwargs:
                    instruments: AAPL,MSFT,QQQ,IVV,SMH,TLT
                    start_time: 2026-03-01
                    end_time: 2026-08-06
                    fit_start_time: 2026-03-01
                    fit_end_time: 2026-05-31
                    freq: day
                    lake_root: "{{ LAKE }}"
                    market: US
                    label: "Ref($close,-6)/Ref($close,-1)-1"
            segments:
                train: [2026-03-01, 2026-05-31]
                valid: [2026-06-01, 2026-06-30]
                test:  [2026-07-01, 2026-08-06]

    # Record block — REQUIRED. Each entry writes one artifact family to mlruns:
    #   SignalRecord    pred.pkl + label.pkl
    #   SigAnaRecord    IC / Rank IC series + long-short group returns
    #   PortAnaRecord   backtest report / positions / risk
    record:
        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
        - class: SigAnaRecord
          module_path: qlib.workflow.record_temp
          kwargs: { ana_long_short: true, ann_scaler: 252 }
        - class: PortAnaRecord
          module_path: qlib.workflow.record_temp
          kwargs:
              config:
                  strategy:
                      class: TopkDropoutStrategy
                      module_path: qlib.contrib.strategy
                      kwargs:
                          signal: "<PRED>"
                          topk: 2
                          n_drop: 1
                          only_tradable: true
                          risk_degree: 0.95
                  backtest:
                      start_time: 2026-07-01
                      end_time: 2026-08-06
                      account: 1000000
                      benchmark: QQQ
                      exchange_kwargs:
                          codes: AAPL,MSFT,QQQ,IVV,SMH,TLT
                          deal_price: $close
                          freq: day
                          open_cost: 0.0005
                          close_cost: 0.0015
                          min_cost: 5.0
              risk_analysis_freq: 1d