decision-toolkit 0.3.0__tar.gz → 0.4.0__tar.gz

{decision_toolkit-0.3.0 → decision_toolkit-0.4.0}/CHANGELOG.md

@@ -1,8 +1,32 @@
 # Changelog
 
-All notable changes to this project are documented here. Version `0.3.0` is
+All notable changes to this project are documented here. Version `0.4.0` is
 published on PyPI.
 
+## [0.4.0] — 2026-10-21
+
+REST variant-selection correction. Quantizations are selected through standard
+model aliases (`id@variant`), not a non-standard `variant` body field. The same
+REST process can load two variants of one base model in separate registry slots.
+
+### Fixed
+
+- Removed `variant` from System One and OpenAI request bodies; standard clients
+  now see only the public request fields.
+- Added `catalog-id@variant` model aliases to `/v1/models` and
+  `/v1/models/{id}`. The standard `model` field selects the alias.
+- Registry keys and slots are per alias, so `laya-multilingual@fp16` and
+  `laya-multilingual@fp32` load independently and concurrently.
+- Updated README, REST, variants, examples and CLI help so REST never shows a
+  variant field in a standard request body.
+
+## [0.3.1] — 2026-10-21
+
+Catalog UX patch: `dtk models list` now prints one row per variant, with
+`variant`, quantization, role, size, cache state and the exact download/select
+commands. `dtk models variants` prints both commands for every variant. No
+model, adapter or REST contract changes.
+
 ## [0.3.0] — 2026-10-21
 
 Catalog expansion: three verified ONNX decision models and eight variants.
@@ -185,6 +209,8 @@ README correction. No code or model behavior changed.
 - Typed `DecisionModel` API with lifecycle, batching, async, usage, warnings,
   normalized confidence, capabilities, structured events and atomic model store.
 
+[0.4.0]: https://pypi.org/project/decision-toolkit/0.4.0/
+[0.3.1]: https://pypi.org/project/decision-toolkit/0.3.1/
 [0.3.0]: https://pypi.org/project/decision-toolkit/0.3.0/
 [0.2.1]: https://pypi.org/project/decision-toolkit/0.2.1/
 [0.2.0]: https://pypi.org/project/decision-toolkit/0.2.0/

{decision_toolkit-0.3.0 → decision_toolkit-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: decision-toolkit
-Version: 0.3.0
+Version: 0.4.0
 Summary: Local-first toolkit for open-weights decision models: one ONNX engine, one adapter per model contract, typed choice/yes-no/score decisions with probabilities on CPU.
 Project-URL: Homepage, https://github.com/gia-uh/decision-toolkit
 Project-URL: Repository, https://github.com/gia-uh/decision-toolkit
@@ -59,7 +59,7 @@ and CLI. `dtk --help` and every subcommand help also include runnable examples.
 ## Installation
 
 ```bash
-uv pip install decision-toolkit              # library + CLI (0.3.0 on PyPI)
+uv pip install decision-toolkit              # library + CLI (0.4.0 on PyPI)
 uv pip install "decision-toolkit[onnx]"      # + onnxruntime, tokenizers (the model runtime)
 uv pip install "decision-toolkit[server]"    # + REST server (FastAPI)
 ```
@@ -67,7 +67,7 @@ uv pip install "decision-toolkit[server]"    # + REST server (FastAPI)
 The project is managed with [uv](https://docs.astral.sh/uv/) and ships a committed `uv.lock`. Published
 wheels remain compatible with `pip` for environments that do not use uv.
 
-PyPI: <https://pypi.org/project/decision-toolkit/0.3.0/>. See
+PyPI: <https://pypi.org/project/decision-toolkit/0.4.0/>. See
 [docs/RELEASE.md](https://github.com/gia-uh/decision-toolkit/blob/main/docs/RELEASE.md)
 for the Trusted Publishing flow and clean-install checks.
 
@@ -208,7 +208,7 @@ adapters (there is no generic "any ONNX" adapter).
 | `julia-1` | `julia` | **m0** — verified: 100/100 argmax parity, 329 ms | `fp32`* (618 MB) |
 | `opendecider-nano` | `opendecider` | **m0** — official build; prompt ported from pinned code (530 ms) | `q8f16`* (469 MB); `fp16` (792 MB) |
 | `laya-multilingual` | `laya` | **m0** — fused ONNX; upstream parity (37 ms) | `fp16`* (682 MB); `fp32` (1326 MB) |
-| `open-jev-deberta-v3-large` | `open-jev` | **m0** — open Jev repro; 0.854 in-domain (241 ms) | `fp16`* (884 MB); `fp32` (1758 MB); `q4` (487 MB); `q4f16` (357 MB) |
+| `open-jev-deberta-v3-large` | `open-jev` | **m0** — Open-Jev DeBERTa v3 large repro; 0.854 in-domain (241 ms) | `fp16`* (884 MB); `fp32` (1758 MB); `q4` (487 MB); `q4f16` (357 MB) |
 | `strands-decider-2b` | `strands-decider` | **m0** — reference fixture match (719 ms) | `q4f16`* (1114 MB); `q8` (1821 MB) |
 
 **Only `m0` models are in the catalog.** Researched-but-unavailable models
@@ -225,7 +225,7 @@ own repo files, size and role. A `*` in the table above marks the default.
 `dtk models list` always shows every catalogued variant and what is cached:
 
 ```bash
-dtk models list                      # all variants; * = default
+dtk models list                      # one row per variant; * = default
 dtk models list --quant              # add the quantization labels
 dtk models variants gliner2.5-multi  # full details for one model
 ```
@@ -248,11 +248,11 @@ dtk models current --json          # {"current": "...", "variant": "fp32"}
 dtk decide --model gliner2.5-multi --variant fp16 --state "..." --q 'cat=choice:a|b'
 ```
 
-From Python: `DecisionModel("gliner2.5-multi", variant="fp32")`. REST selects
-the same way with `"variant": "fp32"` in the request body and returns the choice
-under `x_decision_toolkit.variant`. The variant must already be downloaded. If a
-variant is omitted, the catalog default is used unless `dtk models use` selected
-another one.
+From Python: `DecisionModel("gliner2.5-multi", variant="fp32")`. In REST,
+quantizations are **model aliases**: use `"model": "gliner2.5-multi@fp32"` in the
+standard `model` field. The base id uses the server/persisted default. There is
+no `variant` field in the request body; `/v1/models` lists both the base model
+and every alias, and two aliases can be loaded concurrently.
 
 A variant becomes default only after passing the parity gate (top-1 ≥ 99%,
 mean |Δp| ≤ 0.02, accuracy delta ≤ 1 pp against the fp32 build on a fixed

{decision_toolkit-0.3.0 → decision_toolkit-0.4.0}/README.md

@@ -21,7 +21,7 @@ and CLI. `dtk --help` and every subcommand help also include runnable examples.
 ## Installation
 
 ```bash
-uv pip install decision-toolkit              # library + CLI (0.3.0 on PyPI)
+uv pip install decision-toolkit              # library + CLI (0.4.0 on PyPI)
 uv pip install "decision-toolkit[onnx]"      # + onnxruntime, tokenizers (the model runtime)
 uv pip install "decision-toolkit[server]"    # + REST server (FastAPI)
 ```
@@ -29,7 +29,7 @@ uv pip install "decision-toolkit[server]"    # + REST server (FastAPI)
 The project is managed with [uv](https://docs.astral.sh/uv/) and ships a committed `uv.lock`. Published
 wheels remain compatible with `pip` for environments that do not use uv.
 
-PyPI: <https://pypi.org/project/decision-toolkit/0.3.0/>. See
+PyPI: <https://pypi.org/project/decision-toolkit/0.4.0/>. See
 [docs/RELEASE.md](https://github.com/gia-uh/decision-toolkit/blob/main/docs/RELEASE.md)
 for the Trusted Publishing flow and clean-install checks.
 
@@ -170,7 +170,7 @@ adapters (there is no generic "any ONNX" adapter).
 | `julia-1` | `julia` | **m0** — verified: 100/100 argmax parity, 329 ms | `fp32`* (618 MB) |
 | `opendecider-nano` | `opendecider` | **m0** — official build; prompt ported from pinned code (530 ms) | `q8f16`* (469 MB); `fp16` (792 MB) |
 | `laya-multilingual` | `laya` | **m0** — fused ONNX; upstream parity (37 ms) | `fp16`* (682 MB); `fp32` (1326 MB) |
-| `open-jev-deberta-v3-large` | `open-jev` | **m0** — open Jev repro; 0.854 in-domain (241 ms) | `fp16`* (884 MB); `fp32` (1758 MB); `q4` (487 MB); `q4f16` (357 MB) |
+| `open-jev-deberta-v3-large` | `open-jev` | **m0** — Open-Jev DeBERTa v3 large repro; 0.854 in-domain (241 ms) | `fp16`* (884 MB); `fp32` (1758 MB); `q4` (487 MB); `q4f16` (357 MB) |
 | `strands-decider-2b` | `strands-decider` | **m0** — reference fixture match (719 ms) | `q4f16`* (1114 MB); `q8` (1821 MB) |
 
 **Only `m0` models are in the catalog.** Researched-but-unavailable models
@@ -187,7 +187,7 @@ own repo files, size and role. A `*` in the table above marks the default.
 `dtk models list` always shows every catalogued variant and what is cached:
 
 ```bash
-dtk models list                      # all variants; * = default
+dtk models list                      # one row per variant; * = default
 dtk models list --quant              # add the quantization labels
 dtk models variants gliner2.5-multi  # full details for one model
 ```
@@ -210,11 +210,11 @@ dtk models current --json          # {"current": "...", "variant": "fp32"}
 dtk decide --model gliner2.5-multi --variant fp16 --state "..." --q 'cat=choice:a|b'
 ```
 
-From Python: `DecisionModel("gliner2.5-multi", variant="fp32")`. REST selects
-the same way with `"variant": "fp32"` in the request body and returns the choice
-under `x_decision_toolkit.variant`. The variant must already be downloaded. If a
-variant is omitted, the catalog default is used unless `dtk models use` selected
-another one.
+From Python: `DecisionModel("gliner2.5-multi", variant="fp32")`. In REST,
+quantizations are **model aliases**: use `"model": "gliner2.5-multi@fp32"` in the
+standard `model` field. The base id uses the server/persisted default. There is
+no `variant` field in the request body; `/v1/models` lists both the base model
+and every alias, and two aliases can be loaded concurrently.
 
 A variant becomes default only after passing the parity gate (top-1 ≥ 99%,
 mean |Δp| ≤ 0.02, accuracy delta ≤ 1 pp against the fp32 build on a fixed

{decision_toolkit-0.3.0 → decision_toolkit-0.4.0}/docs/CATALOG_PROPOSAL.md

@@ -1,8 +1,9 @@
 # Catalog proposal: three ONNX decision models
 
 **Date:** 2026-10-21  
-**Status:** implemented and verified in the working tree  
-**Scope:** add Laya multilingual, Open-Jev DeBERTa v3 large and Strands Decider 2B
+**Status:** published in `0.3.0`  
+**Scope:** add Laya multilingual, Open-Jev DeBERTa v3 large and Strands Decider 2B  
+**Release:** <https://pypi.org/project/decision-toolkit/0.3.0/>
 
 ## Executive summary
 
@@ -57,14 +58,14 @@ ONNX Runtime 1.31.0, CPU):
 |---|---|---:|
 | Laya multilingual | fp16 | 37.4 ms |
 | Laya multilingual | fp32 | 34.1 ms |
-| Open-Jev | fp16 | 241.2 ms |
-| Open-Jev | fp32 | 78.2 ms |
-| Open-Jev | q4 | 56.0 ms |
-| Open-Jev | q4f16 | 219.4 ms |
+| Open-Jev DeBERTa v3 large | fp16 | 241.2 ms |
+| Open-Jev DeBERTa v3 large | fp32 | 78.2 ms |
+| Open-Jev DeBERTa v3 large | q4 | 56.0 ms |
+| Open-Jev DeBERTa v3 large | q4f16 | 219.4 ms |
 | Strands Decider 2B | q4f16 | 719.3 ms |
 | Strands Decider 2B | q8 | 1467.2 ms |
 
-The Open-Jev 4-bit paths are size/edge choices; they are not assumed to be
+The Open-Jev DeBERTa v3 large 4-bit paths are size/edge choices; they are not assumed to be
 faster or more accurate. Strands is a 2B model and is intentionally slower
 than the other catalog entries.
 
@@ -72,7 +73,7 @@ than the other catalog entries.
 
 - **Laya multilingual:** upstream conversion reports fp32 max |Δp| 1e-4 and
   fp16 0.035 against PyTorch; local fp16/fp32 agree on the audit answers.
-- **Open-Jev:** upstream reports 0.854 in-domain and 0.690 OOD accuracy, plus
+- **Open-Jev DeBERTa v3 large:** upstream reports 0.854 in-domain and 0.690 OOD accuracy, plus
   0.022 in-domain ECE. Local fp16/fp32 agree on the published example; q4
   variants are explicitly edge builds.
 - **Strands Decider 2B:** reference fixture matches within 0.018 max
@@ -84,7 +85,7 @@ independent reproduction of the full upstream training evaluation.
 ## Quantization policy
 
 - Default variants are chosen for a balance of quality, size and CPU latency:
-  Laya fp16, Open-Jev fp16, Strands q4f16.
+  Laya fp16, Open-Jev DeBERTa v3 large fp16, Strands q4f16.
 - `fp32` remains a quality variant where published.
 - `q4`/`q4f16`/`q8` are exposed, but their thresholds must be validated on the
   user's data; no silent fallback exists.
@@ -98,10 +99,11 @@ independent reproduction of the full upstream training evaluation.
    runtime checks. A larger acceptance run is still desirable.
 2. **Strands CPU cost.** q8 takes ~1.5 s per simple question; this is suitable
    for local/agentic workflows, not high-throughput serving.
-3. **Quantization drift.** Open-Jev q4 and Strands q4f16 can move near-ties;
+3. **Quantization drift.** Open-Jev DeBERTa v3 large q4 and Strands q4f16 can move near-ties;
    the model cards call this out.
-4. **Coverage.** Laya multilingual is weak on low-resource languages; Open-Jev
-   is English-only and weak on unseen score scales; Strands is a 2B model with
+4. **Coverage.** Laya multilingual is weak on low-resource languages;
+   Open-Jev DeBERTa v3 large is English-only and weak on unseen score scales;
+   Strands is a 2B model with
    its own upstream limitations.
 5. **No image/box support.** The catalog remains text-only.
 

{decision_toolkit-0.3.0 → decision_toolkit-0.4.0}/docs/CLI.md

@@ -184,10 +184,12 @@ classification or serve command overrides it for that command. If `--variant`
 is omitted, the catalog default is used unless `dtk models use` selected another
 one.
 
-`models list --json` always includes license, quant, adapter, capabilities, all
-variants, the default variant, cached variants, `current` and `current_variant`.
-The text table always shows variants and cached variants; `--license`, `--quant`
-and `--adapter` add their columns.
+`models list` text output has **one row per variant**, with `id`, `variant`,
+`quant`, `role`, `size` and `cached`, followed by the exact download/select
+commands. `--license` and `--adapter` add catalog columns; `--quant` is accepted
+for compatibility because quantization is always shown. `--json` returns the
+nested model tree: one object per model, each with its `variants` and
+`cached_variants`.
 
 See [Variants and quantization](VARIANTS.md) for the full table and cache
 layout.

{decision_toolkit-0.3.0 → decision_toolkit-0.4.0}/docs/EXAMPLES.md

@@ -165,7 +165,8 @@ curl -s http://127.0.0.1:8000/v1/decisions \
   }' | jq
 ```
 
-`variant` is a decision-toolkit extension; omit it for a standard client.
+Use the model alias `id@variant` for a specific quantization; the base id uses
+the server's default. There is no `variant` field in the request body.
 
 ### Model per request and auth
 
@@ -176,8 +177,7 @@ curl -s http://127.0.0.1:8000/v1/systemone \
   -H "Authorization: Bearer secret" \
   -H "Content-Type: application/json" \
   -d '{
-    "model": "gliner2.5-decide",
-    "variant": "q4f16",
+    "model": "gliner2.5-multi@fp32",
     "state": "I want my money back.",
     "questions": {
       "intent": {"type": "choice", "instructions": "What is the request?",

{decision_toolkit-0.3.0 → decision_toolkit-0.4.0}/docs/RELEASE.md

@@ -10,7 +10,9 @@ and selection in the CLI and documentation; `0.1.7` aligned variant selection
 across the library, CLI and REST API; `0.2.0` corrected the REST conformance
 claims and wire shapes to the published TypeSafe and OpenAI schemas; `0.2.1`
 changed the public documentation URLs to this repository's Pages site; `0.3.0`
-added the Laya multilingual, Open-Jev and Strands Decider ONNX models.
+added the Laya multilingual, Open-Jev DeBERTa v3 large and Strands Decider ONNX models; `0.3.1` made the catalog list one row per variant with exact commands; `0.4.0`
+replaced the non-standard REST `variant` body field with standard model aliases
+(`id@variant`).
 
 ## Local build and verification
 
@@ -37,7 +39,7 @@ Clean install test (no `PYTHONPATH`):
 ```bash
 uv venv --python 3.12 /tmp/dtk-wheel
 uv pip install --python /tmp/dtk-wheel/bin/python \
-  dist/decision_toolkit-0.3.0-py3-none-any.whl
+  dist/decision_toolkit-0.4.0-py3-none-any.whl
 uv pip check --python /tmp/dtk-wheel/bin/python
 /tmp/dtk-wheel/bin/dtk --version
 /tmp/dtk-wheel/bin/dtk models list --json
@@ -48,7 +50,7 @@ With inference and server extras:
 
 ```bash
 uv pip install --python /tmp/dtk-wheel/bin/python \
-  "dist/decision_toolkit-0.3.0-py3-none-any.whl[onnx,server,tracing]"
+  "dist/decision_toolkit-0.4.0-py3-none-any.whl[onnx,server,tracing]"
 /tmp/dtk-wheel/bin/dtk decide --model gliner2.5-decide ...
 /tmp/dtk-wheel/bin/dtk serve --model gliner2.5-decide --warmup --port 8016
 curl -s http://127.0.0.1:8016/health
@@ -82,8 +84,8 @@ No long-lived PyPI token is needed; the workflow uses GitHub OIDC
 4. Create and push an annotated tag:
 
    ```bash
-   git tag -a v0.3.0 -m "decision-toolkit 0.3.0"
-   git push origin v0.3.0
+   git tag -a v0.4.0 -m "decision-toolkit 0.4.0"
+   git push origin v0.4.0
    ```
 
 5. `.github/workflows/release.yml` builds once, publishes to **TestPyPI**, then
@@ -132,9 +134,9 @@ to TestPyPI without publishing to PyPI or creating a GitHub release.
 
 ## Published release
 
-`0.3.0` is published through Trusted Publishing on 2026-10-21:
+`0.4.0` is published through Trusted Publishing on 2026-10-21:
 
-<https://pypi.org/project/decision-toolkit/0.3.0/>
+<https://pypi.org/project/decision-toolkit/0.4.0/>
 
 `0.1.0` was the first release; `0.1.1` refreshed the PyPI description; `0.1.2`
 validated the OIDC TestPyPI → PyPI flow; `0.1.3` added post-publish install
@@ -144,7 +146,8 @@ published to TestPyPI only; `0.1.5` fixed TestPyPI resolution; `0.1.6` added
 complete variant/quantization visibility and CLI selection; `0.1.7` aligned
 selection across library, CLI and REST; `0.2.0` corrected the REST conformance
 claims and wire shapes; `0.2.1` changed the public documentation URLs; `0.3.0`
-added the three new ONNX decision models.
+added the three new ONNX decision models; `0.3.1` made the catalog list one row per variant; `0.4.0` moved REST variant
+selection to standard model aliases.
 
 The tag-triggered workflow remains the preferred path for future releases once
 the TestPyPI/PyPI trusted publishers and protected environments are configured.

{decision_toolkit-0.3.0 → decision_toolkit-0.4.0}/docs/REST.md

@@ -49,25 +49,25 @@ limitations listed below.
 Toolkit-only metadata is under `x_decision_toolkit`, never mixed into standard
 fields. `/v1/decision-models` is the rich, non-standard catalog endpoint.
 
-## Variants (local extension)
-
-Neither TypeSafe nor OpenAI has a `variant` request field: the public APIs select
-a model by name. Quantization is a **decision-toolkit extension**:
-
-- Request `variant` wins when a local client sends it.
-- Otherwise, a server started with `dtk serve --variant` uses that default.
-- Otherwise, the variant selected with `dtk models use` is used when the server
-  is serving the current model.
-- Otherwise, the catalog default (the `*` variant in `dtk models list`) is used.
-
-Standard clients should omit `variant`; they work with the server default. A
-standard-only integration can run one server per variant, or use the server's
-`--variant` setting. The selected variant is exposed in the namespaced
-`x_decision_toolkit.variant` extension, never in a standard field.
-`/v1/models`, `/v1/models/{id}`, `/v1/decision-models`, `/v1/info` and `/ready`
-expose the configured catalog variants, the default, cached variants, and the
-current selection. See [Variants and quantization](VARIANTS.md) for the catalog
-and download/select commands.
+## Variants as model aliases
+
+Neither TypeSafe nor OpenAI has a `variant` request field. The toolkit therefore
+publishes each quantization as a **model alias**:
+
+```json
+{"model": "gliner2.5-multi@fp32", "state": "...", "questions": {...}}
+```
+
+The `model` field is the standard field. `gliner2.5-multi` uses the server's
+default (or the persisted `dtk models use` selection); `gliner2.5-multi@fp32`
+selects that exact variant. Both aliases are listed by `/v1/models`, and the
+registry loads them in separate slots, so two variants of one base model can be
+used by the same server process.
+
+`/v1/models/gliner2.5-multi@fp32`, `/v1/decision-models`, `/v1/info` and `/ready`
+expose the alias, variant, default, cached state and current selection. The
+response metadata under `x_decision_toolkit.variant` is an extension; the
+request body remains standard. See [Variants and quantization](VARIANTS.md).
 
 ## System One (TypeSafe API schema 0.2.0)
 

{decision_toolkit-0.3.0 → decision_toolkit-0.4.0}/docs/VARIANTS.md

@@ -18,23 +18,23 @@ have not passed the catalog gates are not exposed as variants.
 A `*` marks the default variant. It is used when `--variant` is omitted and no
 other variant was selected with `dtk models use`.
 
-| Model | Variant | Quantization | Size | Role |
-| --- | --- | --- | ---: | --- |
-| `gliner2.5-multi` | `fp16` * | fp16 encoder + fp32 classifier | 577.1 MB | default |
-| `gliner2.5-multi` | `fp32` | fp32 encoder + fp32 classifier | 1131.9 MB | quality |
-| `gliner2.5-decide` | `q4f16` * | q4/fp16 | 523.5 MB | default |
-| `laya` | `q8` * | int8 | 527.9 MB | default |
-| `julia-1` | `fp32` * | fp32 | 618.2 MB | default |
-| `opendecider-nano` | `q8f16` * | int8/fp16 | 468.8 MB | default |
-| `opendecider-nano` | `fp16` | fp16 | 791.9 MB | quality |
-| `laya-multilingual` | `fp16` * | fp16 | 681.8 MB | default |
-| `laya-multilingual` | `fp32` | fp32 | 1325.6 MB | quality |
-| `open-jev-deberta-v3-large` | `fp16` * | fp16 | 883.5 MB | default |
-| `open-jev-deberta-v3-large` | `fp32` | fp32 | 1757.9 MB | quality |
-| `open-jev-deberta-v3-large` | `q4` | q4 | 486.7 MB | edge |
-| `open-jev-deberta-v3-large` | `q4f16` | q4/fp16 | 357.0 MB | edge |
-| `strands-decider-2b` | `q4f16` * | q4/fp16 | 1113.6 MB | default |
-| `strands-decider-2b` | `q8` | int8 | 1821.4 MB | quality |
+| Model | Variant | Quantization | Size | Role | Download |
+| --- | --- | --- | ---: | --- | --- |
+| `gliner2.5-multi` | `fp16` * | fp16 encoder + fp32 classifier | 577.1 MB | default | `dtk models download gliner2.5-multi --variant fp16` |
+| `gliner2.5-multi` | `fp32` | fp32 encoder + fp32 classifier | 1131.9 MB | quality | `dtk models download gliner2.5-multi --variant fp32` |
+| `gliner2.5-decide` | `q4f16` * | q4/fp16 | 523.5 MB | default | `dtk models download gliner2.5-decide --variant q4f16` |
+| `laya` | `q8` * | int8 | 527.9 MB | default | `dtk models download laya --variant q8` |
+| `julia-1` | `fp32` * | fp32 | 618.2 MB | default | `dtk models download julia-1 --variant fp32` |
+| `opendecider-nano` | `q8f16` * | int8/fp16 | 468.8 MB | default | `dtk models download opendecider-nano --variant q8f16` |
+| `opendecider-nano` | `fp16` | fp16 | 791.9 MB | quality | `dtk models download opendecider-nano --variant fp16` |
+| `laya-multilingual` | `fp16` * | fp16 | 681.8 MB | default | `dtk models download laya-multilingual --variant fp16` |
+| `laya-multilingual` | `fp32` | fp32 | 1325.6 MB | quality | `dtk models download laya-multilingual --variant fp32` |
+| `open-jev-deberta-v3-large` | `fp16` * | fp16 | 883.5 MB | default | `dtk models download open-jev-deberta-v3-large --variant fp16` |
+| `open-jev-deberta-v3-large` | `fp32` | fp32 | 1757.9 MB | quality | `dtk models download open-jev-deberta-v3-large --variant fp32` |
+| `open-jev-deberta-v3-large` | `q4` | q4 | 486.7 MB | edge | `dtk models download open-jev-deberta-v3-large --variant q4` |
+| `open-jev-deberta-v3-large` | `q4f16` | q4/fp16 | 357.0 MB | edge | `dtk models download open-jev-deberta-v3-large --variant q4f16` |
+| `strands-decider-2b` | `q4f16` * | q4/fp16 | 1113.6 MB | default | `dtk models download strands-decider-2b --variant q4f16` |
+| `strands-decider-2b` | `q8` | int8 | 1821.4 MB | quality | `dtk models download strands-decider-2b --variant q8` |
 
 Models with a single row have only one catalogued, verified build. That does
 not mean other conversions do not exist upstream; it means they have not passed
@@ -45,8 +45,8 @@ the parity, hash and license gates for this catalog.
 The same catalog variant is used by the library, CLI and REST API. Selection
 precedence is:
 
-1. an explicit per-call/per-request variant (`DecisionModel(..., variant=...)`,
-   `--variant`, or `"variant"` in a REST body);
+1. an explicit per-call variant in the library or CLI
+   (`DecisionModel(..., variant=...)`, `--variant`);
 2. the CLI/server configuration (`dtk models use`, or `dtk serve --variant`);
 3. the catalog default marked with `*`.
 
@@ -54,17 +54,18 @@ precedence is:
 | --- | --- | --- |
 | Library | `DecisionModel("gliner2.5-multi", variant="fp32")` | persisted variant for the current model, else catalog default |
 | CLI | `--variant fp32` | variant selected by `dtk models use`, else catalog default |
-| REST (local extension) | `"variant": "fp32"` in the request body | server `--variant`, else persisted variant for the current model, else catalog default |
+| REST | `"model": "gliner2.5-multi@fp32"` (model alias) | base model id; server `--variant`/persisted default |
 
 `DecisionModel.variant` and the CLI report the selected variant (`id@variant` in
 `dtk models current`). REST responses expose it under the namespaced
 `x_decision_toolkit.variant` extension; `/v1/decision-models` includes
 `current` and `current_variant`, plus all `variants` and `cached_variants`.
-`variant` is **not** part of TypeSafe or OpenAI; standard clients should omit it
-and rely on the server's `--variant`/persisted default. A server started with
+`variant` is **not** part of TypeSafe or OpenAI, and standard REST clients must
+not send it. They select only `model`; the local server chooses the quantization
+from `--variant` or the persisted default. A server started with
 `--model`/`--variant` reports that default in `/v1/info` and `/ready`.
 
-The variant must have been downloaded before a library call or REST request
+The variant must have been downloaded before a library call or REST alias
 loads it. An unknown variant returns a model-not-found error; a known but
 missing cache entry returns a model-not-downloaded error.
 
@@ -87,12 +88,15 @@ dtk models variants opendecider-nano --json
 Example:
 
 ```text
-id                 variants        cached
-gliner2.5-multi    fp16*, fp32     fp16
-gliner2.5-decide   q4f16*          q4f16
-opendecider-nano   q8f16*, fp16    q8f16
-
-* default variant. Use `dtk models variants <id>` for details and install commands.
+id                variant  quant    role     size       cached
+gliner2.5-multi   fp16*    fp16     default  577.1 MB   ✓
+gliner2.5-multi   fp32     fp32     quality  1131.9 MB  ✓
+gliner2.5-decide  q4f16*   q4/fp16  default  523.5 MB   ✓
+laya              q8*      int8     default  527.9 MB   ✓
+
+* default variant.
+download: dtk models download <id> --variant <name>
+select:   dtk models use <id> --variant <name>
 ```
 
 ## Download a different quantization
@@ -159,14 +163,18 @@ from decision_toolkit import DecisionModel
 model = DecisionModel("gliner2.5-multi", variant="fp32")
 ```
 
-From REST, send the variant in the request body:
+For REST, select a quantization through the standard `model` field using the
+alias `id@variant`:
 
 ```json
-{"model": "gliner2.5-multi", "variant": "fp32", "state": "...",
- "questions": {"cat": {"type": "choice", "instructions": "What kind?",
-                       "criteria": {"meeting": null, "other": null}}}}
+{"model": "gliner2.5-multi@fp32", "state": "...", "questions": {}}
 ```
 
+The base id (`gliner2.5-multi`) uses the server `--variant`/persisted default.
+`/v1/models` lists base models and every alias, and the registry can hold two
+aliases of the same base model in separate slots. Do not add a `variant` field
+to the request body.
+
 The variant must already be downloaded. If you name an unknown variant, the
 error lists the catalogued choices, for example:
 

{decision_toolkit-0.3.0 → decision_toolkit-0.4.0}/docs/models/open-jev-deberta-v3-large.md

@@ -65,7 +65,7 @@ and re-check thresholds. See [Variants and quantization](../VARIANTS.md).
   (upstream in-domain 0.85 vs OOD 0.69).
 - Score on unseen level sets is weak in the upstream evaluation.
 - It chooses among supplied options; it cannot generate explanations.
-- This is an independent open-jev reproduction, not an official TypeSafe model.
+- This is an independent Open-Jev DeBERTa v3 large reproduction, not an official TypeSafe model.
 
 ## Usage
 

{decision_toolkit-0.3.0 → decision_toolkit-0.4.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "decision-toolkit"
-version = "0.3.0"
+version = "0.4.0"
 description = "Local-first toolkit for open-weights decision models: one ONNX engine, one adapter per model contract, typed choice/yes-no/score decisions with probabilities on CPU."
 readme = "README.md"
 requires-python = ">=3.12"

{decision_toolkit-0.3.0 → decision_toolkit-0.4.0}/src/decision_toolkit/__init__.py

@@ -7,7 +7,7 @@ questions with a calibrated probability for every option, on CPU.
 
 from __future__ import annotations
 
-__version__ = "0.3.0"
+__version__ = "0.4.0"
 
 from .adapters import register_adapter
 from .calibration import brier_score, expected_calibration_error, threshold_sweep

{decision_toolkit-0.3.0 → decision_toolkit-0.4.0}/src/decision_toolkit/catalog.py

@@ -703,6 +703,23 @@ def get(model_id: str) -> CatalogModel | None:
     return CATALOG_BY_ID.get(model_id)
 
 
+def parse_alias(model_id: str) -> tuple[str, str | None]:
+    """Split a REST model alias ``catalog-id@variant``.
+
+    Plain ids and non-catalog paths are returned unchanged. This is the
+    standard-compatible way to select a quantization: the OpenAI/TypeSafe
+    ``model`` field remains a single string; no non-standard ``variant`` body
+    field is needed.
+    """
+    if "@" not in model_id:
+        return model_id, None
+    base, variant_name = model_id.rsplit("@", 1)
+    model = get(base)
+    if model is not None and any(variant.name == variant_name for variant in model.variants):
+        return base, variant_name
+    return model_id, None
+
+
 def select_variant(model: CatalogModel, name: str | None = None) -> Variant:
     """Choose a variant by name, or the model's default."""
     if name is None:
@@ -732,5 +749,6 @@ __all__ = [
     "ModelInfo",
     "Variant",
     "get",
+    "parse_alias",
     "select_variant",
 ]

{decision_toolkit-0.3.0 → decision_toolkit-0.4.0}/src/decision_toolkit/cli.py

@@ -709,35 +709,43 @@ def _cmd_models(args: argparse.Namespace) -> int:
         if as_json:
             _json_out(payloads)
             return EXIT_OK
-        headers = ["", "id", "variants"]
+        headers = ["", "id", "variant", "quant", "role", "size", "cached"]
         if args.show_adapter:
-            headers.append("adapter")
+            headers.insert(2, "adapter")
         if args.show_license:
-            headers.append("license")
-        if args.show_quant:
-            headers.append("quant")
-        headers.append("cached")
+            headers.insert(3, "license")
         rows = []
         for model, payload in zip(catalog.CATALOG, payloads):
             default = model.default_variant
-            variants = ", ".join(
-                f"{variant.name}*" if variant is default else variant.name
-                for variant in model.variants
-            ) or "—"
-            row: list[Any] = ["★" if model.id == current else " ", model.id, variants]
-            if args.show_adapter:
-                row.append(model.adapter)
-            if args.show_license:
-                row.append(model.license)
-            if args.show_quant:
-                row.append(
-                    ", ".join(variant.quant for variant in model.variants) or "—"
+            cached_variants = set(payload["cached_variants"])
+            if not model.variants:
+                rows.append(["", model.id, "—", "—", "—", "—", "—"])
+                continue
+            for variant in model.variants:
+                is_current = model.id == current and (
+                    current_variant == variant.name
+                    if current_variant is not None
+                    else variant is default
                 )
-            cached_label = ", ".join(payload["cached_variants"]) or "—"
-            row.append(cached_label)
-            rows.append(row)
+                label = f"{variant.name}*" if variant is default else variant.name
+                row: list[Any] = [
+                    "★" if is_current else "",
+                    model.id,
+                    label,
+                    variant.quant,
+                    variant.role,
+                    f"{variant.size_mb:.1f} MB",
+                    "✓" if variant.name in cached_variants else "",
+                ]
+                if args.show_adapter:
+                    row.insert(2, model.adapter)
+                if args.show_license:
+                    row.insert(3, model.license)
+                rows.append(row)
         _print_table(headers, rows)
-        print("\n* default variant. Use `dtk models variants <id>` for details and install commands.")
+        print("\n* default variant.")
+        print("download: dtk models download <id> --variant <name>")
+        print("select:   dtk models use <id> --variant <name>")
         return EXIT_OK
 
     if command == "variants":
@@ -777,6 +785,10 @@ def _cmd_models(args: argparse.Namespace) -> int:
                 f"           download: dtk models download {model.id} "
                 f"--variant {variant.name}"
             )
+            print(
+                f"           use:      dtk models use {model.id} "
+                f"--variant {variant.name}"
+            )
         if not model.variants:
             print("  (no downloadable ONNX variant yet)")
         else: