AzulGarza · Oct 26, 2026 · Oct 26, 2026
diff --git a/README.md b/README.md
@@ -141,10 +141,11 @@ Some models require specific Python versions (e.g. FlowState 3.11-3.13, TabPFN &
 
 ## News
 
-Recent additions and checkpoints (newest first). See the [changelog](https://github.com/TimeCopilot/foundationforecast/blob/main/docs/changelogs/v0.1.15.md) for full release notes.
+Recent additions and checkpoints (newest first). See the [changelog](https://github.com/TimeCopilot/foundationforecast/blob/main/docs/changelogs/v0.1.16.md) for full release notes.
 
 | When | What | Checkpoint / detail |
 |------|------|---------------------|
+| Oct 2026 | [**TimeH2O**](https://huggingface.co/h2oai/timeh2o-v1) | `h2oai/timeh2o-v1`, `h2oai/timeh2o-v1-tiny` — requires `h2ofm>=0.43.0` (Python 3.12+); native `X_df`; GIFT-Eval and fev-bench CI ([v0.1.16](https://github.com/TimeCopilot/foundationforecast/blob/main/docs/changelogs/v0.1.16.md)) |
 | Oct 2026 | [**Timestral**](https://huggingface.co/collections/mistralai/timestral) | `mistralai/Timestral-{5M,28M,123M,209M}` — requires `timecopilot-timestral>=0.1.0`; native `X_df`; GIFT-Eval and fev-bench CI ([v0.1.15](https://github.com/TimeCopilot/foundationforecast/blob/main/docs/changelogs/v0.1.15.md)) |
 | Oct 2026 | [**T0 gamma**](https://huggingface.co/theforecastingcompany/t0-gamma) | `theforecastingcompany/t0-gamma` — requires `tfc-t0[torch]>=0.6.0`; GIFT-Eval and fev-bench CI ([v0.1.14](https://github.com/TimeCopilot/foundationforecast/blob/main/docs/changelogs/v0.1.14.md)) |
 | Oct 2026 | **GIFT-Eval replication for $37** | 16 models on the full benchmark, each official submission matched within 2% MASE/CRPS; new Experiments docs section ([v0.1.13](https://github.com/TimeCopilot/foundationforecast/blob/main/docs/changelogs/v0.1.13.md)) |

diff --git a/docs/changelogs/index.md b/docs/changelogs/index.md
@@ -2,6 +2,7 @@
 
 Welcome to the FoundationForecast Changelog. Here you will find a list of changes, updates, and improvements for each release. Explore the details of each version below.
 
+- [v0.1.16](v0.1.16.md)
 - [v0.1.15](v0.1.15.md)
 - [v0.1.14](v0.1.14.md)
 - [v0.1.13](v0.1.13.md)

diff --git a/docs/changelogs/v0.1.16.md b/docs/changelogs/v0.1.16.md
@@ -0,0 +1,22 @@
+### Features
+
+* **TimeH2O**: The [`TimeH2O`](https://docs.timecopilot.dev/foundationforecast/api/models/foundation/models/#foundationforecast.models.timeh2o.TimeH2O) wrapper supports H2O.ai's [`timeh2o-v1`](https://huggingface.co/h2oai/timeh2o-v1) and [`timeh2o-v1-tiny`](https://huggingface.co/h2oai/timeh2o-v1-tiny) checkpoints via `h2ofm>=0.43.0` (Python 3.12+). Native known-future covariates (`X_df`) on `timeh2o-v1`, including categorical columns encoded by `h2ofm`; arbitrary `level` / `quantiles` (levels outside the trained 0.1–0.9 grid use Gaussian-tail extrapolation); and `clip_nonnegative` / `snap_integer` options matching the published benchmark runs. The checkpoints are gated and released under a non-commercial license. See [#77](https://github.com/TimeCopilot/foundationforecast/pull/77).
+
+### Tests
+
+* **TimeH2O**: Mocked tests for quantile mapping, context truncation, covariate alignment, categorical covariates and option passthrough; a live smoke test on `timeh2o-v1-tiny`; and cross-model contract coverage for both checkpoints on Python 3.12+. See [#77](https://github.com/TimeCopilot/foundationforecast/pull/77).
+* **Benchmark CI**: GIFT-Eval (`m4_weekly`) and fev-bench (`epf_pjm`, `entsoe_1H`) subsets add `timeh2o-v1`, with the settings of the official submissions and leaderboard references. See [#77](https://github.com/TimeCopilot/foundationforecast/pull/77).
+
+### Documentation
+
+* **TimeH2O family notebook**: [`timeh2o-family` example notebook](../examples/timeh2o-family.ipynb) compares both checkpoints and the benchmark settings, and shows known-future covariates on electricity prices. See [#77](https://github.com/TimeCopilot/foundationforecast/pull/77).
+* **Model hub and README**: Document TimeH2O checkpoints, Python 3.12+ requirement, gated non-commercial license and native exog support; add H2O.ai/TimeH2O to the supported-models table.
+
+### Tooling
+
+* **Dependencies**: Add `h2ofm>=0.43.0` (Python 3.12+) and require `timecopilot-timesfm>=0.4.1`, which drops the `safetensors<0.6` cap that conflicted with `h2ofm`.
+* **Benchmark harnesses**: Models can set `python` in `models.yaml`; GIFT-Eval and fev-bench Modal runs dispatch them to a Python 3.12 image while other models stay on 3.11. Experiment lockfiles refreshed.
+
+---
+
+**Full Changelog**: https://github.com/TimeCopilot/foundationforecast/compare/v0.1.15...v0.1.16
diff --git a/experiments/fev-bench/uv.lock b/experiments/fev-bench/uv.lock
diff --git a/experiments/gift-eval/uv.lock b/experiments/gift-eval/uv.lock
diff --git a/mkdocs.yml b/mkdocs.yml
@@ -50,6 +50,7 @@ nav:
       - Contributing: contributing.md
   - Changelogs:
       - changelogs/index.md
+      - changelogs/v0.1.16.md
       - changelogs/v0.1.15.md
       - changelogs/v0.1.14.md
       - changelogs/v0.1.13.md

diff --git a/pyproject.toml b/pyproject.toml
@@ -75,7 +75,7 @@ license = "Apache-2.0"
 name = "foundationforecast"
 readme = "README.md"
 requires-python = ">=3.10"
-version = "0.1.15"
+version = "0.1.16"
 
 [project.optional-dependencies]
 plot = [

diff --git a/uv.lock b/uv.lock