Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
Python calibrationclassificationdecision-modelhuggingfacejevmodernbertmultilingualnlppythonpytorchroutingtyped-decisionszero-shot
release: 0.4.8
Nandakishor4ac226d5ee88
diff --git a/README.md b/README.mdindex b1e4b90f..01468027 100644--- a/README.md+++ b/README.md@@ -94,30 +94,31 @@ The shipped checkpoints work zero-shot, but fine-tuning on decisions from your o**[nandhakishorm.github.io/laya](https://nandhakishorm.github.io/laya/)**: guides for [prediction hooks](https://nandhakishorm.github.io/laya/hooks/), [schema-driven decisions](https://nandhakishorm.github.io/laya/structured/), [Docker](https://nandhakishorm.github.io/laya/docker/) and [LangChain and LangGraph](https://nandhakishorm.github.io/laya/langchain/), plus a full [API reference](https://nandhakishorm.github.io/laya/reference/).-## What's new in 0.4.7--* **`laya-ts` reports `act_probability` the way Python does.** The port softmaxed the action row a- second time inside the decoder, so a row the reference reads as 0.9 came back as 0.6899. It is- normalised once, at the model boundary (#1195). The same port now honours a question's- `option_order` end to end, validating it as a permutation and un-permuting the answer (#1196),- reads a temperature as `float()` does rather than as `Number()` does, so a `[2]` or a `" "` in a- checkpoint config no longer loads as a real temperature (#1192, #1191), and cleans an email body- on Python's Unicode character classes instead of JavaScript's ASCII-ish ones (#1188).-* **A checkpoint or calibration file that ships `true` where a temperature belongs is named.**- `float(True)` is exactly the neutral 1.0 the clamp installs for it, so the old diagnostic compared- the two numbers and said nothing; `lang_temperatures` overrides now report a clamped value for- their language too (#1190, #1208). A calibration JSON whose `version` is `1.9` is refused instead- of truncated to 1, which used to skip the checkpoint-identity check (#1202).-* **Large choices have two more routes.** `laya_tournament` answers them over MCP by elimination- with no embedding pass (#1178), and `LAYA_TOURNAMENT_GROUP` now covers- `POST /v1/systemone/batch` as well as `/v1/systemone` (#1204). For a labelled set,- `laya.evals_tournament.evaluate_tournament` says whether a miss lost the gold label during- elimination or among the finalists (#1175).-* **An interactive session exits with the code its requests earned.** `laya < requests.txt` used to- exit 0 with every answer missing (#1184), and `laya-evals run --json`/`--markdown` to a path it- cannot write is exit 2 with a diagnostic, not exit 1 with a traceback (#1171).-* **The Go port decodes answers.** `laya-go` gains the question schema, sequence building and answer- decoding, with goldens regenerated from Python in CI (#1169).+## What's new in 0.4.8++* **`laya-go` runs the model.** `agent.Open`, `Predict`, `PredictBatch` and `PredictLong` answer+ typed questions over an `infer.Session`, and a nested `laya-go/onnx` module (its own `go.mod`,+ cgo) runs a fused `laya.onnx` on ONNX Runtime 1.29+. The main module stays standard library+ only: `go test ./...` there compiles no cgo, and `CGO_ENABLED=0` builds `onnx` too, where+ `Open` returns `ErrNoCGO`. The goldens are regenerated from Python in CI (#1222, #1233).+* **A gate parameter that decides nothing is refused.** `--max ece=inf`, `--min accuracy=-inf` and+ `--tolerance METRIC=1e999` passed every measurement and still exited 0, which is the code that+ means the gate ran (#1225). A baseline that is not a metric name to number map, or that has no+ metrics at all, now raises instead of being subtracted through, and `"choice_accuracy": true`+ no longer compares as 100% (#1223). A report `laya-evals` cannot read is exit 2, not a traceback+ and exit 1 (#1230). `bins` and `min_bucket_n` are positive integers (#1228), and `ece_score`+ refuses a `bins` it cannot histogram, which used to return the perfect 0.0 (#1232).+* **`laya-serve` reads a blank `LAYA_*` value as unset**, which is what a `.env` line or a Compose+ `KEY=` with nothing after it writes; `LAYA_PRELOAD=` was getting lazy loading nobody asked for+ (#1226). A bad `LAYA_LOG_LEVEL` exits with a message naming the accepted values instead of a+ `KeyError` from inside uvicorn (#1227).+* **Schema-driven decisions read two more shapes correctly.** A non-array `enum` is a+ `SchemaError` naming the path, where a bare string silently split into per-character options+ (#1220), and a single-value boolean constraint such as `Literal[True]` stays a one-option choice+ instead of becoming a noul that could answer `False` (#1235).+* **`laya.jev_confidence` refuses a negative probability** rather than returning a number outside+ `[0, 1]`, so the range is now a property of the function (#1238). `setup_laya.sh` detects the+ platform and hands off to a Linux or macOS script (#1234).Earlier releases are in the [GitHub releases](https://github.com/NandhaKishorM/laya/releases).diff --git a/laya/__init__.py b/laya/__init__.pyindex e067f6cc..3fb89c6a 100644--- a/laya/__init__.py+++ b/laya/__init__.py@@ -35,7 +35,7 @@ from .presets import (from .router import DEFAULT_MODELS, RouteDecision, Routerfrom .structured import DecisionResult, decide, decide_batch-__version__ = "0.4.7"+__version__ = "0.4.8"# Routing, language detection and email cleaning are pure Python. The torch-backed names are# resolved lazily so that `import laya` -- and therefore `from laya import Router` ordiff --git a/nix/package.nix b/nix/package.nixindex fbb2322c..fbf5564a 100644--- a/nix/package.nix+++ b/nix/package.nix@@ -12,7 +12,7 @@ let# side, where tests/test_packaging.py compares all three declarations (this one,# pyproject.toml and laya.__version__) and fails CI when they diverge. Nothing# did, which is how this sat at 0.3.4 while the package reached 0.3.20.- version = "0.4.7";+ version = "0.4.8";src = ../.;format = "setuptools";propagatedBuildInputs = with python3Packages; [diff --git a/pyproject.toml b/pyproject.tomlindex 9cbbe85d..c992923e 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"[project]name = "laya"-version = "0.4.7"+version = "0.4.8"description = "Fast, non-autoregressive System 1 decision engine with calibrated probabilities"readme = "README.md"requires-python = ">=3.10"