v0.0.32

Features

• TimesFM 3.0 foundation model: Added support for google/timesfm-3.0-pytorch via foundationforecast>=0.1.3. Use the existing TimesFM class with the 3.0 repo id; no API changes are required in TimeCopilot.

  import pandas as pd
  from timecopilot.models.foundation.timesfm import TimesFM
  
  df = pd.read_csv(
      "https://timecopilot.s3.amazonaws.com/public/data/air_passengers.csv",
      parse_dates=["ds"],
  )
  
  model = TimesFM(
      repo_id="google/timesfm-3.0-pytorch",
      alias="TimesFM-3",
      context_length=2048,
  )
  fcst_df = model.forecast(df, h=12, freq="MS")

  License note: TimesFM 3.0 pretrained weights are non-commercial; TimesFM 1.0–2.5 checkpoints remain Apache-2.0.

• TimesFM family notebook: Added timesfm-family example notebook comparing TimesFM 1.0, 2.0, 2.5, and 3.0 with supported prediction intervals.

Dependencies

• Bumped foundationforecast from >=0.1.2 to >=0.1.3 (includes timecopilot-timesfm>=0.4.0 and the _TimesFMV3 backend).

---

Full Changelog: v0.0.31...v0.0.32