tempest-react-sdk 0.32.0 → 0.33.0

package/dist/tabular/compact.cjs

@@ -0,0 +1,2 @@
+const e=require("./exceptions.cjs");var t=`TMC1`,n=1,r=class n{header;arrays;info;constructor(e,t,n){this.header=e,this.arrays=t,this.info=n}static async create(r,a){let o=await i(r,a),s=new Uint8Array(o);if(String.fromCharCode(...s.subarray(0,4))!==t)throw new e.CompactFormatError(`This is not a compact model file: it does not start with "${t}". A .onnx file goes through TabularPredictor instead.`);let c=new DataView(o).getUint32(4,!0),l=JSON.parse(new TextDecoder().decode(s.subarray(8,8+c)));if(l.schema_version>1)throw new e.CompactFormatError(`This file uses compact layout ${l.schema_version}, and this SDK understands 1. Upgrade tempest-react-sdk before serving it.`);let u={},d=8+c;for(let e of l.sections)u[e.name]=e.dtype===`float32`?new Float32Array(o,d,e.length):new Int32Array(o,d,e.length),d+=e.length*4;return new n(l,u,{kind:l.kind,classes:l.classes,numFeatures:l.n_features,featureNames:l.feature_names,numTrees:l.n_trees??0,isClassifier:l.task===`classification`,estimator:l.estimator})}async predict(e){let t=a(e,this.header.n_features),n=performance.now(),r=[];for(let n of e){let e=this.preprocess(n,t);r.push(this.header.kind===`linear`?this.linearScores(e):this.treeScores(e))}let{labels:i,probabilities:o}=this.finish(r);return{labels:i,probabilities:o,numRows:e.length,ms:performance.now()-n}}async dispose(){}preprocess(e,t){let n=this.header.preprocess;if(n===null)return e;let r=Array(t);for(let i=0;i<t;i+=1)r[i]=(e[i]-n.offset[i])/n.scale[i];return r}linearScores(e){let t=this.arrays.coef,n=this.arrays.intercept,r=this.header.n_features,i=this.header.n_outputs,a=Array(i);for(let o=0;o<i;o+=1){let i=n[o],s=o*r;for(let n=0;n<r;n+=1)i+=t[s+n]*e[n];a[o]=i}return a}treeScores(e){let t=this.arrays.node_feature,n=this.arrays.node_threshold,r=this.arrays.node_left,i=this.arrays.node_right,a=this.arrays.leaf_value,o=this.arrays.tree_offset,s=this.header.n_outputs,c=o.length-1,l=Array(s).fill(0);for(let u=0;u<c;u+=1){let c=o[u],d=t[c];for(;d>=0;)c=e[d]<=n[c]?r[c]:i[c],d=t[c];let f=(-1-d)*s;for(let e=0;e<s;e+=1)l[e]+=a[f+e]}for(let e=0;e<s;e+=1)l[e]=l[e]/c;return l}finish(e){let t=this.header.link,n=this.header.classes;if(t===`identity`)return{labels:e.map(e=>e[0]),probabilities:[]};let r=e.map(e=>{if(t===`sigmoid`){let t=1/(1+Math.exp(-e[0]));return[1-t,t]}if(t===`softmax`){let t=Math.max(...e),n=e.map(e=>Math.exp(e-t)),r=n.reduce((e,t)=>e+t,0);return n.map(e=>e/r)}let n=e.reduce((e,t)=>e+t,0);return n===0?[...e]:e.map(e=>e/n)}),i=this.header.class_type!==`str`;return{labels:r.map(e=>{let t=0;for(let n=1;n<e.length;n+=1)e[n]>e[t]&&(t=n);let r=n[t];return r===void 0?t:i?Number(r):r}),probabilities:r}}};async function i(t,n){if(typeof t==`string`){let r;try{r=await fetch(t,n)}catch(n){throw new e.ModelFetchError(`Could not download the model: ${t}`,{cause:n})}if(!r.ok)throw new e.ModelFetchError(`Could not download the model: ${r.status} ${r.statusText}`);return await r.arrayBuffer()}return t instanceof Uint8Array?t.buffer.slice(t.byteOffset,t.byteOffset+t.byteLength):t}function a(t,n){if(!Array.isArray(t)||t.length===0)throw new e.FeatureShapeError(`predict() needs at least one row, shaped [[f1, f2, ...]].`);let r=t[0]?.length??0,i=t.findIndex(e=>e.length!==r);if(i!==-1)throw new e.FeatureShapeError(`All rows must have the same width; row ${i} has ${t[i]?.length} values, expected ${r}.`);if(r!==n)throw new e.FeatureShapeError(`The model expects ${n} features per row, got ${r}.`);return r}exports.CompactPredictor=r,exports.SUPPORTED_COMPACT_SCHEMA=n;
+//# sourceMappingURL=compact.cjs.map

package/dist/tabular/compact.cjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"compact.cjs","names":[],"sources":["../../src/tabular/compact.ts"],"sourcesContent":["/**\n * Running a model with no inference runtime at all.\n *\n * ONNX in the browser costs a **25.6 MB WebAssembly runtime** (6.0 MB\n * gzipped) before the first prediction, while the model itself is a few\n * hundred kilobytes. For an app whose only model is tabular, that runtime\n * *is* the download — so this reader replaces it with 1.49 KB of\n * arithmetic (measured, brotli).\n *\n * A linear model is a dot product. A tree is a chain of comparisons. That\n * is the whole implementation; there is nothing here that a WebAssembly\n * kernel would do better at this size.\n *\n * The file it reads (`.tmc`, magic `TMC1`) is written by\n * `tempest-fastapi-sdk`'s `export_sklearn_to_compact`, which verifies the\n * bytes against scikit-learn's own predictions and refuses to write a file\n * that disagrees. **It is data, not code**: no `eval`, no generated\n * JavaScript, nothing a strict CSP forbids.\n *\n * The trade against {@link TabularPredictor}: ONNX covers every estimator,\n * this covers linear models and tree ensembles. Pick by what your app\n * already ships — a page that loads ONNX for vision pays nothing extra for\n * tabular ONNX.\n */\n\nimport { CompactFormatError, FeatureShapeError, ModelFetchError } from \"./exceptions\";\nimport type { FeatureRow, PredictedLabel, TabularPrediction } from \"./types\";\n\n/** Magic bytes opening every compact file. */\nconst MAGIC = \"TMC1\";\n\n/** Layout version this reader understands. */\nexport const SUPPORTED_COMPACT_SCHEMA = 1;\n\n/** What the file holds. */\nexport type CompactKind = \"linear\" | \"tree_ensemble\";\n\n/** How raw scores become probabilities. */\ntype CompactLink = \"softmax\" | \"sigmoid\" | \"normalize\" | \"identity\";\n\n/** One array stored after the header. */\ninterface CompactSection {\n    readonly name: string;\n    readonly dtype: \"float32\" | \"int32\";\n    readonly length: number;\n}\n\n/** The parsed header. */\ninterface CompactHeader {\n    readonly schema_version: number;\n    readonly kind: CompactKind;\n    readonly task: \"classification\" | \"regression\";\n    readonly link: CompactLink;\n    readonly classes: readonly string[];\n    /** How scikit-learn typed those labels: ``int``, ``float`` or ``str``. */\n    readonly class_type?: \"int\" | \"float\" | \"str\";\n    readonly n_features: number;\n    readonly n_outputs: number;\n    readonly n_trees?: number;\n    readonly estimator: string;\n    readonly feature_names: readonly string[];\n    readonly preprocess: { readonly offset: number[]; readonly scale: number[] } | null;\n    readonly sections: readonly CompactSection[];\n}\n\n/** What a loaded compact model is. */\nexport interface CompactPredictorInfo {\n    /** Which reader path the file uses. */\n    readonly kind: CompactKind;\n    /** Class labels in score-column order; empty for a regressor. */\n    readonly classes: readonly string[];\n    /** Values expected per row. */\n    readonly numFeatures: number;\n    /** Column order recorded at training time, when the export had one. */\n    readonly featureNames: readonly string[];\n    /** Trees in the ensemble; `0` for a linear model. */\n    readonly numTrees: number;\n    /** Whether the model produces class scores. */\n    readonly isClassifier: boolean;\n    /** Class name of the exported estimator. */\n    readonly estimator: string;\n}\n\n/**\n * A compact model, loaded and ready to answer.\n *\n * @example\n * ```ts\n * const predictor = await CompactPredictor.create(\"/models/risk.tmc\");\n * const { labels, probabilities } = await predictor.predict([[5.1, 3.5, 1.4, 0.2]]);\n * ```\n */\nexport class CompactPredictor {\n    private constructor(\n        private readonly header: CompactHeader,\n        private readonly arrays: Record<string, Float32Array | Int32Array>,\n        /** What is loaded. */\n        public readonly info: CompactPredictorInfo,\n    ) {}\n\n    /**\n     * Load a `.tmc` file.\n     *\n     * @param source A URL, or the bytes when the app already has them.\n     * @param requestInit `fetch` options, when `source` is a URL.\n     * @returns The loaded predictor.\n     * @throws {@link ModelFetchError} when a URL cannot be read.\n     * @throws {@link CompactFormatError} when the bytes are not a compact\n     *   model, or use a layout newer than this reader.\n     */\n    static async create(\n        source: string | ArrayBuffer | Uint8Array,\n        requestInit?: RequestInit,\n    ): Promise<CompactPredictor> {\n        const buffer = await toBuffer(source, requestInit);\n        const bytes = new Uint8Array(buffer);\n\n        if (String.fromCharCode(...bytes.subarray(0, 4)) !== MAGIC) {\n            throw new CompactFormatError(\n                \"This is not a compact model file: it does not start with \" +\n                    `\"${MAGIC}\". A .onnx file goes through TabularPredictor instead.`,\n            );\n        }\n\n        const view = new DataView(buffer);\n        const headerLength = view.getUint32(4, true);\n        const header = JSON.parse(\n            new TextDecoder().decode(bytes.subarray(8, 8 + headerLength)),\n        ) as CompactHeader;\n\n        if (header.schema_version > SUPPORTED_COMPACT_SCHEMA) {\n            throw new CompactFormatError(\n                `This file uses compact layout ${header.schema_version}, and this ` +\n                    `SDK understands ${SUPPORTED_COMPACT_SCHEMA}. Upgrade ` +\n                    \"tempest-react-sdk before serving it.\",\n            );\n        }\n\n        const arrays: Record<string, Float32Array | Int32Array> = {};\n        let cursor = 8 + headerLength;\n        for (const section of header.sections) {\n            arrays[section.name] =\n                section.dtype === \"float32\"\n                    ? new Float32Array(buffer, cursor, section.length)\n                    : new Int32Array(buffer, cursor, section.length);\n            cursor += section.length * 4;\n        }\n\n        return new CompactPredictor(header, arrays, {\n            kind: header.kind,\n            classes: header.classes,\n            numFeatures: header.n_features,\n            featureNames: header.feature_names,\n            numTrees: header.n_trees ?? 0,\n            isClassifier: header.task === \"classification\",\n            estimator: header.estimator,\n        });\n    }\n\n    /**\n     * Predict for a batch of rows.\n     *\n     * @param rows One array of feature values per row, in training column\n     *   order. A single row is still wrapped: `[[...]]`.\n     * @returns Labels, class scores when the model is a classifier, and the\n     *   call's duration.\n     * @throws {@link FeatureShapeError} when the batch is empty, ragged, or\n     *   the wrong width.\n     */\n    async predict(rows: readonly FeatureRow[]): Promise<TabularPrediction> {\n        const width = validateRows(rows, this.header.n_features);\n        const started = performance.now();\n\n        const scores: number[][] = [];\n        for (const row of rows) {\n            const prepared = this.preprocess(row, width);\n            scores.push(\n                this.header.kind === \"linear\"\n                    ? this.linearScores(prepared)\n                    : this.treeScores(prepared),\n            );\n        }\n\n        const { labels, probabilities } = this.finish(scores);\n        return {\n            labels,\n            probabilities,\n            numRows: rows.length,\n            ms: performance.now() - started,\n        };\n    }\n\n    /** Releasing nothing, so callers can swap predictors without branching. */\n    async dispose(): Promise<void> {\n        /* no runtime, nothing to release */\n    }\n\n    /**\n     * Apply the folded scaler, when the export had one.\n     *\n     * @param row The raw feature values.\n     * @param width How many there are.\n     * @returns The values the model was trained on.\n     */\n    private preprocess(row: FeatureRow, width: number): number[] {\n        const preprocess = this.header.preprocess;\n        if (preprocess === null) return row as number[];\n        const scaled = new Array<number>(width);\n        for (let index = 0; index < width; index += 1) {\n            scaled[index] =\n                ((row[index] as number) - (preprocess.offset[index] as number)) /\n                (preprocess.scale[index] as number);\n        }\n        return scaled;\n    }\n\n    /**\n     * Score one row against the coefficient matrix.\n     *\n     * @param row The prepared feature values.\n     * @returns One raw score per output.\n     */\n    private linearScores(row: readonly number[]): number[] {\n        const coef = this.arrays.coef as Float32Array;\n        const intercept = this.arrays.intercept as Float32Array;\n        const features = this.header.n_features;\n        const outputs = this.header.n_outputs;\n\n        const scores = new Array<number>(outputs);\n        for (let output = 0; output < outputs; output += 1) {\n            let total = intercept[output] as number;\n            const base = output * features;\n            for (let index = 0; index < features; index += 1) {\n                total += (coef[base + index] as number) * (row[index] as number);\n            }\n            scores[output] = total;\n        }\n        return scores;\n    }\n\n    /**\n     * Walk every tree and average what the leaves hold.\n     *\n     * A leaf is marked by a negative `feature` entry, which also carries\n     * its slot in the value array — so the walk needs no second lookup and\n     * the file stores values only for leaves.\n     *\n     * @param row The prepared feature values.\n     * @returns One averaged score per output.\n     */\n    private treeScores(row: readonly number[]): number[] {\n        const feature = this.arrays.node_feature as Int32Array;\n        const threshold = this.arrays.node_threshold as Float32Array;\n        const left = this.arrays.node_left as Int32Array;\n        const right = this.arrays.node_right as Int32Array;\n        const leaf = this.arrays.leaf_value as Float32Array;\n        const offsets = this.arrays.tree_offset as Int32Array;\n        const outputs = this.header.n_outputs;\n        const trees = offsets.length - 1;\n\n        const totals = new Array<number>(outputs).fill(0);\n        for (let tree = 0; tree < trees; tree += 1) {\n            let node = offsets[tree] as number;\n            let column = feature[node] as number;\n            while (column >= 0) {\n                node =\n                    (row[column] as number) <= (threshold[node] as number)\n                        ? (left[node] as number)\n                        : (right[node] as number);\n                column = feature[node] as number;\n            }\n            const slot = (-1 - column) * outputs;\n            for (let output = 0; output < outputs; output += 1) {\n                totals[output] += leaf[slot + output] as number;\n            }\n        }\n        for (let output = 0; output < outputs; output += 1) {\n            totals[output] = (totals[output] as number) / trees;\n        }\n        return totals;\n    }\n\n    /**\n     * Turn raw scores into labels and probabilities.\n     *\n     * @param scores One score array per row.\n     * @returns Labels and probabilities in the shape the ONNX route uses,\n     *   so an app can swap runtimes without touching its own code. That\n     *   includes the label's **type**: an integer class comes back as a\n     *   number here exactly as ONNX returns it, because two routes over one\n     *   model that disagree on `0` versus `\"0\"` break the day someone\n     *   switches.\n     */\n    private finish(scores: readonly number[][]): {\n        labels: PredictedLabel[];\n        probabilities: number[][];\n    } {\n        const link = this.header.link;\n        const classes = this.header.classes;\n\n        if (link === \"identity\") {\n            return { labels: scores.map((row) => row[0] as number), probabilities: [] };\n        }\n\n        const probabilities = scores.map((row) => {\n            if (link === \"sigmoid\") {\n                const positive = 1 / (1 + Math.exp(-(row[0] as number)));\n                return [1 - positive, positive];\n            }\n            if (link === \"softmax\") {\n                const highest = Math.max(...row);\n                const exponentiated = row.map((value) => Math.exp(value - highest));\n                const total = exponentiated.reduce((sum, value) => sum + value, 0);\n                return exponentiated.map((value) => value / total);\n            }\n            const total = row.reduce((sum, value) => sum + value, 0);\n            return total === 0 ? [...row] : row.map((value) => value / total);\n        });\n\n        const numeric = this.header.class_type !== \"str\";\n        const labels = probabilities.map((row) => {\n            let best = 0;\n            for (let index = 1; index < row.length; index += 1) {\n                if ((row[index] as number) > (row[best] as number)) best = index;\n            }\n            const label = classes[best];\n            if (label === undefined) return best;\n            return numeric ? Number(label) : label;\n        });\n\n        return { labels, probabilities };\n    }\n}\n\n/**\n * Read a source into an `ArrayBuffer`.\n *\n * @param source A URL or the bytes.\n * @param requestInit `fetch` options.\n * @returns The bytes.\n * @throws {@link ModelFetchError} when the URL cannot be read.\n */\nasync function toBuffer(\n    source: string | ArrayBuffer | Uint8Array,\n    requestInit?: RequestInit,\n): Promise<ArrayBuffer> {\n    if (typeof source === \"string\") {\n        let response: Response;\n        try {\n            response = await fetch(source, requestInit);\n        } catch (error) {\n            throw new ModelFetchError(`Could not download the model: ${source}`, {\n                cause: error,\n            });\n        }\n        if (!response.ok) {\n            throw new ModelFetchError(\n                `Could not download the model: ${response.status} ${response.statusText}`,\n            );\n        }\n        return await response.arrayBuffer();\n    }\n    if (source instanceof Uint8Array) {\n        return source.buffer.slice(\n            source.byteOffset,\n            source.byteOffset + source.byteLength,\n        ) as ArrayBuffer;\n    }\n    return source;\n}\n\n/**\n * Check a batch before predicting on it.\n *\n * @param rows The batch.\n * @param expected Features the model wants per row.\n * @returns The batch width.\n * @throws {@link FeatureShapeError} when the batch cannot be predicted on.\n */\nfunction validateRows(rows: readonly FeatureRow[], expected: number): number {\n    if (!Array.isArray(rows) || rows.length === 0) {\n        throw new FeatureShapeError(\"predict() needs at least one row, shaped [[f1, f2, ...]].\");\n    }\n    const width = rows[0]?.length ?? 0;\n    const ragged = rows.findIndex((row) => row.length !== width);\n    if (ragged !== -1) {\n        throw new FeatureShapeError(\n            `All rows must have the same width; row ${ragged} has ` +\n                `${rows[ragged]?.length} values, expected ${width}.`,\n        );\n    }\n    if (width !== expected) {\n        throw new FeatureShapeError(\n            `The model expects ${expected} features per row, got ${width}.`,\n        );\n    }\n    return width;\n}\n"],"mappings":"oCA6BA,IAAM,EAAQ,OAGD,EAA2B,EA4D3B,EAAb,MAAa,CAAiB,CAEL,OACA,OAED,KAJpB,YACI,EACA,EAEA,EACF,CAJmB,KAAA,OAAA,EACA,KAAA,OAAA,EAED,KAAA,KAAA,CACjB,CAYH,aAAa,OACT,EACA,EACyB,CACzB,IAAM,EAAS,MAAM,EAAS,EAAQ,CAAW,EAC3C,EAAQ,IAAI,WAAW,CAAM,EAEnC,GAAI,OAAO,aAAa,GAAG,EAAM,SAAS,EAAG,CAAC,CAAC,IAAM,EACjD,MAAM,IAAI,EAAA,mBACN,6DACQ,EAAM,uDAClB,EAIJ,IAAM,EAAe,IADJ,SAAS,CACL,CAAA,CAAK,UAAU,EAAG,EAAI,EACrC,EAAS,KAAK,MAChB,IAAI,YAAY,CAAC,CAAC,OAAO,EAAM,SAAS,EAAG,EAAI,CAAY,CAAC,CAChE,EAEA,GAAI,EAAO,eAAA,EACP,MAAM,IAAI,EAAA,mBACN,iCAAiC,EAAO,eAAe,2EAG3D,EAGJ,IAAM,EAAoD,CAAC,EACvD,EAAS,EAAI,EACjB,IAAK,IAAM,KAAW,EAAO,SACzB,EAAO,EAAQ,MACX,EAAQ,QAAU,UACZ,IAAI,aAAa,EAAQ,EAAQ,EAAQ,MAAM,EAC/C,IAAI,WAAW,EAAQ,EAAQ,EAAQ,MAAM,EACvD,GAAU,EAAQ,OAAS,EAG/B,OAAO,IAAI,EAAiB,EAAQ,EAAQ,CACxC,KAAM,EAAO,KACb,QAAS,EAAO,QAChB,YAAa,EAAO,WACpB,aAAc,EAAO,cACrB,SAAU,EAAO,SAAW,EAC5B,aAAc,EAAO,OAAS,iBAC9B,UAAW,EAAO,SACtB,CAAC,CACL,CAYA,MAAM,QAAQ,EAAyD,CACnE,IAAM,EAAQ,EAAa,EAAM,KAAK,OAAO,UAAU,EACjD,EAAU,YAAY,IAAI,EAE1B,EAAqB,CAAC,EAC5B,IAAK,IAAM,KAAO,EAAM,CACpB,IAAM,EAAW,KAAK,WAAW,EAAK,CAAK,EAC3C,EAAO,KACH,KAAK,OAAO,OAAS,SACf,KAAK,aAAa,CAAQ,EAC1B,KAAK,WAAW,CAAQ,CAClC,CACJ,CAEA,GAAM,CAAE,SAAQ,iBAAkB,KAAK,OAAO,CAAM,EACpD,MAAO,CACH,SACA,gBACA,QAAS,EAAK,OACd,GAAI,YAAY,IAAI,EAAI,CAC5B,CACJ,CAGA,MAAM,SAAyB,CAE/B,CASA,WAAmB,EAAiB,EAAyB,CACzD,IAAM,EAAa,KAAK,OAAO,WAC/B,GAAI,IAAe,KAAM,OAAO,EAChC,IAAM,EAAa,MAAc,CAAK,EACtC,IAAK,IAAI,EAAQ,EAAG,EAAQ,EAAO,GAAS,EACxC,EAAO,IACD,EAAI,GAAqB,EAAW,OAAO,IAC5C,EAAW,MAAM,GAE1B,OAAO,CACX,CAQA,aAAqB,EAAkC,CACnD,IAAM,EAAO,KAAK,OAAO,KACnB,EAAY,KAAK,OAAO,UACxB,EAAW,KAAK,OAAO,WACvB,EAAU,KAAK,OAAO,UAEtB,EAAa,MAAc,CAAO,EACxC,IAAK,IAAI,EAAS,EAAG,EAAS,EAAS,GAAU,EAAG,CAChD,IAAI,EAAQ,EAAU,GAChB,EAAO,EAAS,EACtB,IAAK,IAAI,EAAQ,EAAG,EAAQ,EAAU,GAAS,EAC3C,GAAU,EAAK,EAAO,GAAqB,EAAI,GAEnD,EAAO,GAAU,CACrB,CACA,OAAO,CACX,CAYA,WAAmB,EAAkC,CACjD,IAAM,EAAU,KAAK,OAAO,aACtB,EAAY,KAAK,OAAO,eACxB,EAAO,KAAK,OAAO,UACnB,EAAQ,KAAK,OAAO,WACpB,EAAO,KAAK,OAAO,WACnB,EAAU,KAAK,OAAO,YACtB,EAAU,KAAK,OAAO,UACtB,EAAQ,EAAQ,OAAS,EAEzB,EAAa,MAAc,CAAO,CAAC,CAAC,KAAK,CAAC,EAChD,IAAK,IAAI,EAAO,EAAG,EAAO,EAAO,GAAQ,EAAG,CACxC,IAAI,EAAO,EAAQ,GACf,EAAS,EAAQ,GACrB,KAAO,GAAU,GACb,EACK,EAAI,IAAuB,EAAU,GAC/B,EAAK,GACL,EAAM,GACjB,EAAS,EAAQ,GAErB,IAAM,GAAQ,GAAK,GAAU,EAC7B,IAAK,IAAI,EAAS,EAAG,EAAS,EAAS,GAAU,EAC7C,EAAO,IAAW,EAAK,EAAO,EAEtC,CACA,IAAK,IAAI,EAAS,EAAG,EAAS,EAAS,GAAU,EAC7C,EAAO,GAAW,EAAO,GAAqB,EAElD,OAAO,CACX,CAaA,OAAe,EAGb,CACE,IAAM,EAAO,KAAK,OAAO,KACnB,EAAU,KAAK,OAAO,QAE5B,GAAI,IAAS,WACT,MAAO,CAAE,OAAQ,EAAO,IAAK,GAAQ,EAAI,EAAY,EAAG,cAAe,CAAC,CAAE,EAG9E,IAAM,EAAgB,EAAO,IAAK,GAAQ,CACtC,GAAI,IAAS,UAAW,CACpB,IAAM,EAAW,GAAK,EAAI,KAAK,IAAI,CAAE,EAAI,EAAa,GACtD,MAAO,CAAC,EAAI,EAAU,CAAQ,CAClC,CACA,GAAI,IAAS,UAAW,CACpB,IAAM,EAAU,KAAK,IAAI,GAAG,CAAG,EACzB,EAAgB,EAAI,IAAK,GAAU,KAAK,IAAI,EAAQ,CAAO,CAAC,EAC5D,EAAQ,EAAc,QAAQ,EAAK,IAAU,EAAM,EAAO,CAAC,EACjE,OAAO,EAAc,IAAK,GAAU,EAAQ,CAAK,CACrD,CACA,IAAM,EAAQ,EAAI,QAAQ,EAAK,IAAU,EAAM,EAAO,CAAC,EACvD,OAAO,IAAU,EAAI,CAAC,GAAG,CAAG,EAAI,EAAI,IAAK,GAAU,EAAQ,CAAK,CACpE,CAAC,EAEK,EAAU,KAAK,OAAO,aAAe,MAW3C,MAAO,CAAE,OAVM,EAAc,IAAK,GAAQ,CACtC,IAAI,EAAO,EACX,IAAK,IAAI,EAAQ,EAAG,EAAQ,EAAI,OAAQ,GAAS,EACxC,EAAI,GAAqB,EAAI,KAAkB,EAAO,GAE/D,IAAM,EAAQ,EAAQ,GAEtB,OADI,IAAU,IAAA,GAAkB,EACzB,EAAU,OAAO,CAAK,EAAI,CACrC,CAES,EAAQ,eAAc,CACnC,CACJ,EAUA,eAAe,EACX,EACA,EACoB,CACpB,GAAI,OAAO,GAAW,SAAU,CAC5B,IAAI,EACJ,GAAI,CACA,EAAW,MAAM,MAAM,EAAQ,CAAW,CAC9C,OAAS,EAAO,CACZ,MAAM,IAAI,EAAA,gBAAgB,iCAAiC,IAAU,CACjE,MAAO,CACX,CAAC,CACL,CACA,GAAI,CAAC,EAAS,GACV,MAAM,IAAI,EAAA,gBACN,iCAAiC,EAAS,OAAO,GAAG,EAAS,YACjE,EAEJ,OAAO,MAAM,EAAS,YAAY,CACtC,CAOA,OANI,aAAkB,WACX,EAAO,OAAO,MACjB,EAAO,WACP,EAAO,WAAa,EAAO,UAC/B,EAEG,CACX,CAUA,SAAS,EAAa,EAA6B,EAA0B,CACzE,GAAI,CAAC,MAAM,QAAQ,CAAI,GAAK,EAAK,SAAW,EACxC,MAAM,IAAI,EAAA,kBAAkB,2DAA2D,EAE3F,IAAM,EAAQ,EAAK,EAAE,EAAE,QAAU,EAC3B,EAAS,EAAK,UAAW,GAAQ,EAAI,SAAW,CAAK,EAC3D,GAAI,IAAW,GACX,MAAM,IAAI,EAAA,kBACN,0CAA0C,EAAO,OAC1C,EAAK,EAAO,EAAE,OAAO,oBAAoB,EAAM,EAC1D,EAEJ,GAAI,IAAU,EACV,MAAM,IAAI,EAAA,kBACN,qBAAqB,EAAS,yBAAyB,EAAM,EACjE,EAEJ,OAAO,CACX"}

package/dist/tabular/compact.js

@@ -0,0 +1,121 @@
+import { CompactFormatError as e, FeatureShapeError as t, ModelFetchError as n } from "./exceptions.js";
+//#region src/tabular/compact.ts
+var r = "TMC1", i = 1, a = class t {
+	header;
+	arrays;
+	info;
+	constructor(e, t, n) {
+		this.header = e, this.arrays = t, this.info = n;
+	}
+	static async create(n, i) {
+		let a = await o(n, i), s = new Uint8Array(a);
+		if (String.fromCharCode(...s.subarray(0, 4)) !== r) throw new e(`This is not a compact model file: it does not start with "${r}". A .onnx file goes through TabularPredictor instead.`);
+		let c = new DataView(a).getUint32(4, !0), l = JSON.parse(new TextDecoder().decode(s.subarray(8, 8 + c)));
+		if (l.schema_version > 1) throw new e(`This file uses compact layout ${l.schema_version}, and this SDK understands 1. Upgrade tempest-react-sdk before serving it.`);
+		let u = {}, d = 8 + c;
+		for (let e of l.sections) u[e.name] = e.dtype === "float32" ? new Float32Array(a, d, e.length) : new Int32Array(a, d, e.length), d += e.length * 4;
+		return new t(l, u, {
+			kind: l.kind,
+			classes: l.classes,
+			numFeatures: l.n_features,
+			featureNames: l.feature_names,
+			numTrees: l.n_trees ?? 0,
+			isClassifier: l.task === "classification",
+			estimator: l.estimator
+		});
+	}
+	async predict(e) {
+		let t = s(e, this.header.n_features), n = performance.now(), r = [];
+		for (let n of e) {
+			let e = this.preprocess(n, t);
+			r.push(this.header.kind === "linear" ? this.linearScores(e) : this.treeScores(e));
+		}
+		let { labels: i, probabilities: a } = this.finish(r);
+		return {
+			labels: i,
+			probabilities: a,
+			numRows: e.length,
+			ms: performance.now() - n
+		};
+	}
+	async dispose() {}
+	preprocess(e, t) {
+		let n = this.header.preprocess;
+		if (n === null) return e;
+		let r = Array(t);
+		for (let i = 0; i < t; i += 1) r[i] = (e[i] - n.offset[i]) / n.scale[i];
+		return r;
+	}
+	linearScores(e) {
+		let t = this.arrays.coef, n = this.arrays.intercept, r = this.header.n_features, i = this.header.n_outputs, a = Array(i);
+		for (let o = 0; o < i; o += 1) {
+			let i = n[o], s = o * r;
+			for (let n = 0; n < r; n += 1) i += t[s + n] * e[n];
+			a[o] = i;
+		}
+		return a;
+	}
+	treeScores(e) {
+		let t = this.arrays.node_feature, n = this.arrays.node_threshold, r = this.arrays.node_left, i = this.arrays.node_right, a = this.arrays.leaf_value, o = this.arrays.tree_offset, s = this.header.n_outputs, c = o.length - 1, l = Array(s).fill(0);
+		for (let u = 0; u < c; u += 1) {
+			let c = o[u], d = t[c];
+			for (; d >= 0;) c = e[d] <= n[c] ? r[c] : i[c], d = t[c];
+			let f = (-1 - d) * s;
+			for (let e = 0; e < s; e += 1) l[e] += a[f + e];
+		}
+		for (let e = 0; e < s; e += 1) l[e] = l[e] / c;
+		return l;
+	}
+	finish(e) {
+		let t = this.header.link, n = this.header.classes;
+		if (t === "identity") return {
+			labels: e.map((e) => e[0]),
+			probabilities: []
+		};
+		let r = e.map((e) => {
+			if (t === "sigmoid") {
+				let t = 1 / (1 + Math.exp(-e[0]));
+				return [1 - t, t];
+			}
+			if (t === "softmax") {
+				let t = Math.max(...e), n = e.map((e) => Math.exp(e - t)), r = n.reduce((e, t) => e + t, 0);
+				return n.map((e) => e / r);
+			}
+			let n = e.reduce((e, t) => e + t, 0);
+			return n === 0 ? [...e] : e.map((e) => e / n);
+		}), i = this.header.class_type !== "str";
+		return {
+			labels: r.map((e) => {
+				let t = 0;
+				for (let n = 1; n < e.length; n += 1) e[n] > e[t] && (t = n);
+				let r = n[t];
+				return r === void 0 ? t : i ? Number(r) : r;
+			}),
+			probabilities: r
+		};
+	}
+};
+async function o(e, t) {
+	if (typeof e == "string") {
+		let r;
+		try {
+			r = await fetch(e, t);
+		} catch (t) {
+			throw new n(`Could not download the model: ${e}`, { cause: t });
+		}
+		if (!r.ok) throw new n(`Could not download the model: ${r.status} ${r.statusText}`);
+		return await r.arrayBuffer();
+	}
+	return e instanceof Uint8Array ? e.buffer.slice(e.byteOffset, e.byteOffset + e.byteLength) : e;
+}
+function s(e, n) {
+	if (!Array.isArray(e) || e.length === 0) throw new t("predict() needs at least one row, shaped [[f1, f2, ...]].");
+	let r = e[0]?.length ?? 0, i = e.findIndex((e) => e.length !== r);
+	if (i !== -1) throw new t(`All rows must have the same width; row ${i} has ${e[i]?.length} values, expected ${r}.`);
+	if (r !== n) throw new t(`The model expects ${n} features per row, got ${r}.`);
+	return r;
+}
+//#endregion
+export { a as CompactPredictor, i as SUPPORTED_COMPACT_SCHEMA };
+
+//# sourceMappingURL=compact.js.map

package/dist/tabular/compact.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"compact.js","names":[],"sources":["../../src/tabular/compact.ts"],"sourcesContent":["/**\n * Running a model with no inference runtime at all.\n *\n * ONNX in the browser costs a **25.6 MB WebAssembly runtime** (6.0 MB\n * gzipped) before the first prediction, while the model itself is a few\n * hundred kilobytes. For an app whose only model is tabular, that runtime\n * *is* the download — so this reader replaces it with 1.49 KB of\n * arithmetic (measured, brotli).\n *\n * A linear model is a dot product. A tree is a chain of comparisons. That\n * is the whole implementation; there is nothing here that a WebAssembly\n * kernel would do better at this size.\n *\n * The file it reads (`.tmc`, magic `TMC1`) is written by\n * `tempest-fastapi-sdk`'s `export_sklearn_to_compact`, which verifies the\n * bytes against scikit-learn's own predictions and refuses to write a file\n * that disagrees. **It is data, not code**: no `eval`, no generated\n * JavaScript, nothing a strict CSP forbids.\n *\n * The trade against {@link TabularPredictor}: ONNX covers every estimator,\n * this covers linear models and tree ensembles. Pick by what your app\n * already ships — a page that loads ONNX for vision pays nothing extra for\n * tabular ONNX.\n */\n\nimport { CompactFormatError, FeatureShapeError, ModelFetchError } from \"./exceptions\";\nimport type { FeatureRow, PredictedLabel, TabularPrediction } from \"./types\";\n\n/** Magic bytes opening every compact file. */\nconst MAGIC = \"TMC1\";\n\n/** Layout version this reader understands. */\nexport const SUPPORTED_COMPACT_SCHEMA = 1;\n\n/** What the file holds. */\nexport type CompactKind = \"linear\" | \"tree_ensemble\";\n\n/** How raw scores become probabilities. */\ntype CompactLink = \"softmax\" | \"sigmoid\" | \"normalize\" | \"identity\";\n\n/** One array stored after the header. */\ninterface CompactSection {\n    readonly name: string;\n    readonly dtype: \"float32\" | \"int32\";\n    readonly length: number;\n}\n\n/** The parsed header. */\ninterface CompactHeader {\n    readonly schema_version: number;\n    readonly kind: CompactKind;\n    readonly task: \"classification\" | \"regression\";\n    readonly link: CompactLink;\n    readonly classes: readonly string[];\n    /** How scikit-learn typed those labels: ``int``, ``float`` or ``str``. */\n    readonly class_type?: \"int\" | \"float\" | \"str\";\n    readonly n_features: number;\n    readonly n_outputs: number;\n    readonly n_trees?: number;\n    readonly estimator: string;\n    readonly feature_names: readonly string[];\n    readonly preprocess: { readonly offset: number[]; readonly scale: number[] } | null;\n    readonly sections: readonly CompactSection[];\n}\n\n/** What a loaded compact model is. */\nexport interface CompactPredictorInfo {\n    /** Which reader path the file uses. */\n    readonly kind: CompactKind;\n    /** Class labels in score-column order; empty for a regressor. */\n    readonly classes: readonly string[];\n    /** Values expected per row. */\n    readonly numFeatures: number;\n    /** Column order recorded at training time, when the export had one. */\n    readonly featureNames: readonly string[];\n    /** Trees in the ensemble; `0` for a linear model. */\n    readonly numTrees: number;\n    /** Whether the model produces class scores. */\n    readonly isClassifier: boolean;\n    /** Class name of the exported estimator. */\n    readonly estimator: string;\n}\n\n/**\n * A compact model, loaded and ready to answer.\n *\n * @example\n * ```ts\n * const predictor = await CompactPredictor.create(\"/models/risk.tmc\");\n * const { labels, probabilities } = await predictor.predict([[5.1, 3.5, 1.4, 0.2]]);\n * ```\n */\nexport class CompactPredictor {\n    private constructor(\n        private readonly header: CompactHeader,\n        private readonly arrays: Record<string, Float32Array | Int32Array>,\n        /** What is loaded. */\n        public readonly info: CompactPredictorInfo,\n    ) {}\n\n    /**\n     * Load a `.tmc` file.\n     *\n     * @param source A URL, or the bytes when the app already has them.\n     * @param requestInit `fetch` options, when `source` is a URL.\n     * @returns The loaded predictor.\n     * @throws {@link ModelFetchError} when a URL cannot be read.\n     * @throws {@link CompactFormatError} when the bytes are not a compact\n     *   model, or use a layout newer than this reader.\n     */\n    static async create(\n        source: string | ArrayBuffer | Uint8Array,\n        requestInit?: RequestInit,\n    ): Promise<CompactPredictor> {\n        const buffer = await toBuffer(source, requestInit);\n        const bytes = new Uint8Array(buffer);\n\n        if (String.fromCharCode(...bytes.subarray(0, 4)) !== MAGIC) {\n            throw new CompactFormatError(\n                \"This is not a compact model file: it does not start with \" +\n                    `\"${MAGIC}\". A .onnx file goes through TabularPredictor instead.`,\n            );\n        }\n\n        const view = new DataView(buffer);\n        const headerLength = view.getUint32(4, true);\n        const header = JSON.parse(\n            new TextDecoder().decode(bytes.subarray(8, 8 + headerLength)),\n        ) as CompactHeader;\n\n        if (header.schema_version > SUPPORTED_COMPACT_SCHEMA) {\n            throw new CompactFormatError(\n                `This file uses compact layout ${header.schema_version}, and this ` +\n                    `SDK understands ${SUPPORTED_COMPACT_SCHEMA}. Upgrade ` +\n                    \"tempest-react-sdk before serving it.\",\n            );\n        }\n\n        const arrays: Record<string, Float32Array | Int32Array> = {};\n        let cursor = 8 + headerLength;\n        for (const section of header.sections) {\n            arrays[section.name] =\n                section.dtype === \"float32\"\n                    ? new Float32Array(buffer, cursor, section.length)\n                    : new Int32Array(buffer, cursor, section.length);\n            cursor += section.length * 4;\n        }\n\n        return new CompactPredictor(header, arrays, {\n            kind: header.kind,\n            classes: header.classes,\n            numFeatures: header.n_features,\n            featureNames: header.feature_names,\n            numTrees: header.n_trees ?? 0,\n            isClassifier: header.task === \"classification\",\n            estimator: header.estimator,\n        });\n    }\n\n    /**\n     * Predict for a batch of rows.\n     *\n     * @param rows One array of feature values per row, in training column\n     *   order. A single row is still wrapped: `[[...]]`.\n     * @returns Labels, class scores when the model is a classifier, and the\n     *   call's duration.\n     * @throws {@link FeatureShapeError} when the batch is empty, ragged, or\n     *   the wrong width.\n     */\n    async predict(rows: readonly FeatureRow[]): Promise<TabularPrediction> {\n        const width = validateRows(rows, this.header.n_features);\n        const started = performance.now();\n\n        const scores: number[][] = [];\n        for (const row of rows) {\n            const prepared = this.preprocess(row, width);\n            scores.push(\n                this.header.kind === \"linear\"\n                    ? this.linearScores(prepared)\n                    : this.treeScores(prepared),\n            );\n        }\n\n        const { labels, probabilities } = this.finish(scores);\n        return {\n            labels,\n            probabilities,\n            numRows: rows.length,\n            ms: performance.now() - started,\n        };\n    }\n\n    /** Releasing nothing, so callers can swap predictors without branching. */\n    async dispose(): Promise<void> {\n        /* no runtime, nothing to release */\n    }\n\n    /**\n     * Apply the folded scaler, when the export had one.\n     *\n     * @param row The raw feature values.\n     * @param width How many there are.\n     * @returns The values the model was trained on.\n     */\n    private preprocess(row: FeatureRow, width: number): number[] {\n        const preprocess = this.header.preprocess;\n        if (preprocess === null) return row as number[];\n        const scaled = new Array<number>(width);\n        for (let index = 0; index < width; index += 1) {\n            scaled[index] =\n                ((row[index] as number) - (preprocess.offset[index] as number)) /\n                (preprocess.scale[index] as number);\n        }\n        return scaled;\n    }\n\n    /**\n     * Score one row against the coefficient matrix.\n     *\n     * @param row The prepared feature values.\n     * @returns One raw score per output.\n     */\n    private linearScores(row: readonly number[]): number[] {\n        const coef = this.arrays.coef as Float32Array;\n        const intercept = this.arrays.intercept as Float32Array;\n        const features = this.header.n_features;\n        const outputs = this.header.n_outputs;\n\n        const scores = new Array<number>(outputs);\n        for (let output = 0; output < outputs; output += 1) {\n            let total = intercept[output] as number;\n            const base = output * features;\n            for (let index = 0; index < features; index += 1) {\n                total += (coef[base + index] as number) * (row[index] as number);\n            }\n            scores[output] = total;\n        }\n        return scores;\n    }\n\n    /**\n     * Walk every tree and average what the leaves hold.\n     *\n     * A leaf is marked by a negative `feature` entry, which also carries\n     * its slot in the value array — so the walk needs no second lookup and\n     * the file stores values only for leaves.\n     *\n     * @param row The prepared feature values.\n     * @returns One averaged score per output.\n     */\n    private treeScores(row: readonly number[]): number[] {\n        const feature = this.arrays.node_feature as Int32Array;\n        const threshold = this.arrays.node_threshold as Float32Array;\n        const left = this.arrays.node_left as Int32Array;\n        const right = this.arrays.node_right as Int32Array;\n        const leaf = this.arrays.leaf_value as Float32Array;\n        const offsets = this.arrays.tree_offset as Int32Array;\n        const outputs = this.header.n_outputs;\n        const trees = offsets.length - 1;\n\n        const totals = new Array<number>(outputs).fill(0);\n        for (let tree = 0; tree < trees; tree += 1) {\n            let node = offsets[tree] as number;\n            let column = feature[node] as number;\n            while (column >= 0) {\n                node =\n                    (row[column] as number) <= (threshold[node] as number)\n                        ? (left[node] as number)\n                        : (right[node] as number);\n                column = feature[node] as number;\n            }\n            const slot = (-1 - column) * outputs;\n            for (let output = 0; output < outputs; output += 1) {\n                totals[output] += leaf[slot + output] as number;\n            }\n        }\n        for (let output = 0; output < outputs; output += 1) {\n            totals[output] = (totals[output] as number) / trees;\n        }\n        return totals;\n    }\n\n    /**\n     * Turn raw scores into labels and probabilities.\n     *\n     * @param scores One score array per row.\n     * @returns Labels and probabilities in the shape the ONNX route uses,\n     *   so an app can swap runtimes without touching its own code. That\n     *   includes the label's **type**: an integer class comes back as a\n     *   number here exactly as ONNX returns it, because two routes over one\n     *   model that disagree on `0` versus `\"0\"` break the day someone\n     *   switches.\n     */\n    private finish(scores: readonly number[][]): {\n        labels: PredictedLabel[];\n        probabilities: number[][];\n    } {\n        const link = this.header.link;\n        const classes = this.header.classes;\n\n        if (link === \"identity\") {\n            return { labels: scores.map((row) => row[0] as number), probabilities: [] };\n        }\n\n        const probabilities = scores.map((row) => {\n            if (link === \"sigmoid\") {\n                const positive = 1 / (1 + Math.exp(-(row[0] as number)));\n                return [1 - positive, positive];\n            }\n            if (link === \"softmax\") {\n                const highest = Math.max(...row);\n                const exponentiated = row.map((value) => Math.exp(value - highest));\n                const total = exponentiated.reduce((sum, value) => sum + value, 0);\n                return exponentiated.map((value) => value / total);\n            }\n            const total = row.reduce((sum, value) => sum + value, 0);\n            return total === 0 ? [...row] : row.map((value) => value / total);\n        });\n\n        const numeric = this.header.class_type !== \"str\";\n        const labels = probabilities.map((row) => {\n            let best = 0;\n            for (let index = 1; index < row.length; index += 1) {\n                if ((row[index] as number) > (row[best] as number)) best = index;\n            }\n            const label = classes[best];\n            if (label === undefined) return best;\n            return numeric ? Number(label) : label;\n        });\n\n        return { labels, probabilities };\n    }\n}\n\n/**\n * Read a source into an `ArrayBuffer`.\n *\n * @param source A URL or the bytes.\n * @param requestInit `fetch` options.\n * @returns The bytes.\n * @throws {@link ModelFetchError} when the URL cannot be read.\n */\nasync function toBuffer(\n    source: string | ArrayBuffer | Uint8Array,\n    requestInit?: RequestInit,\n): Promise<ArrayBuffer> {\n    if (typeof source === \"string\") {\n        let response: Response;\n        try {\n            response = await fetch(source, requestInit);\n        } catch (error) {\n            throw new ModelFetchError(`Could not download the model: ${source}`, {\n                cause: error,\n            });\n        }\n        if (!response.ok) {\n            throw new ModelFetchError(\n                `Could not download the model: ${response.status} ${response.statusText}`,\n            );\n        }\n        return await response.arrayBuffer();\n    }\n    if (source instanceof Uint8Array) {\n        return source.buffer.slice(\n            source.byteOffset,\n            source.byteOffset + source.byteLength,\n        ) as ArrayBuffer;\n    }\n    return source;\n}\n\n/**\n * Check a batch before predicting on it.\n *\n * @param rows The batch.\n * @param expected Features the model wants per row.\n * @returns The batch width.\n * @throws {@link FeatureShapeError} when the batch cannot be predicted on.\n */\nfunction validateRows(rows: readonly FeatureRow[], expected: number): number {\n    if (!Array.isArray(rows) || rows.length === 0) {\n        throw new FeatureShapeError(\"predict() needs at least one row, shaped [[f1, f2, ...]].\");\n    }\n    const width = rows[0]?.length ?? 0;\n    const ragged = rows.findIndex((row) => row.length !== width);\n    if (ragged !== -1) {\n        throw new FeatureShapeError(\n            `All rows must have the same width; row ${ragged} has ` +\n                `${rows[ragged]?.length} values, expected ${width}.`,\n        );\n    }\n    if (width !== expected) {\n        throw new FeatureShapeError(\n            `The model expects ${expected} features per row, got ${width}.`,\n        );\n    }\n    return width;\n}\n"],"mappings":";;AA6BA,IAAM,IAAQ,QAGD,IAA2B,GA4D3B,IAAb,MAAa,EAAiB;CAEL;CACA;CAED;CAJpB,YACI,GACA,GAEA,GACF;EADkB,AAHC,KAAA,SAAA,GACA,KAAA,SAAA,GAED,KAAA,OAAA;CACjB;CAYH,aAAa,OACT,GACA,GACyB;EACzB,IAAM,IAAS,MAAM,EAAS,GAAQ,CAAW,GAC3C,IAAQ,IAAI,WAAW,CAAM;EAEnC,IAAI,OAAO,aAAa,GAAG,EAAM,SAAS,GAAG,CAAC,CAAC,MAAM,GACjD,MAAM,IAAI,EACN,6DACQ,EAAM,uDAClB;EAIJ,IAAM,IAAe,IADJ,SAAS,CACL,CAAA,CAAK,UAAU,GAAG,EAAI,GACrC,IAAS,KAAK,MAChB,IAAI,YAAY,CAAC,CAAC,OAAO,EAAM,SAAS,GAAG,IAAI,CAAY,CAAC,CAChE;EAEA,IAAI,EAAO,iBAAA,GACP,MAAM,IAAI,EACN,iCAAiC,EAAO,eAAe,2EAG3D;EAGJ,IAAM,IAAoD,CAAC,GACvD,IAAS,IAAI;EACjB,KAAK,IAAM,KAAW,EAAO,UAKzB,AAJA,EAAO,EAAQ,QACX,EAAQ,UAAU,YACZ,IAAI,aAAa,GAAQ,GAAQ,EAAQ,MAAM,IAC/C,IAAI,WAAW,GAAQ,GAAQ,EAAQ,MAAM,GACvD,KAAU,EAAQ,SAAS;EAG/B,OAAO,IAAI,EAAiB,GAAQ,GAAQ;GACxC,MAAM,EAAO;GACb,SAAS,EAAO;GAChB,aAAa,EAAO;GACpB,cAAc,EAAO;GACrB,UAAU,EAAO,WAAW;GAC5B,cAAc,EAAO,SAAS;GAC9B,WAAW,EAAO;EACtB,CAAC;CACL;CAYA,MAAM,QAAQ,GAAyD;EACnE,IAAM,IAAQ,EAAa,GAAM,KAAK,OAAO,UAAU,GACjD,IAAU,YAAY,IAAI,GAE1B,IAAqB,CAAC;EAC5B,KAAK,IAAM,KAAO,GAAM;GACpB,IAAM,IAAW,KAAK,WAAW,GAAK,CAAK;GAC3C,EAAO,KACH,KAAK,OAAO,SAAS,WACf,KAAK,aAAa,CAAQ,IAC1B,KAAK,WAAW,CAAQ,CAClC;EACJ;EAEA,IAAM,EAAE,WAAQ,qBAAkB,KAAK,OAAO,CAAM;EACpD,OAAO;GACH;GACA;GACA,SAAS,EAAK;GACd,IAAI,YAAY,IAAI,IAAI;EAC5B;CACJ;CAGA,MAAM,UAAyB,CAE/B;CASA,WAAmB,GAAiB,GAAyB;EACzD,IAAM,IAAa,KAAK,OAAO;EAC/B,IAAI,MAAe,MAAM,OAAO;EAChC,IAAM,IAAa,MAAc,CAAK;EACtC,KAAK,IAAI,IAAQ,GAAG,IAAQ,GAAO,KAAS,GACxC,EAAO,MACD,EAAI,KAAqB,EAAW,OAAO,MAC5C,EAAW,MAAM;EAE1B,OAAO;CACX;CAQA,aAAqB,GAAkC;EACnD,IAAM,IAAO,KAAK,OAAO,MACnB,IAAY,KAAK,OAAO,WACxB,IAAW,KAAK,OAAO,YACvB,IAAU,KAAK,OAAO,WAEtB,IAAa,MAAc,CAAO;EACxC,KAAK,IAAI,IAAS,GAAG,IAAS,GAAS,KAAU,GAAG;GAChD,IAAI,IAAQ,EAAU,IAChB,IAAO,IAAS;GACtB,KAAK,IAAI,IAAQ,GAAG,IAAQ,GAAU,KAAS,GAC3C,KAAU,EAAK,IAAO,KAAqB,EAAI;GAEnD,EAAO,KAAU;EACrB;EACA,OAAO;CACX;CAYA,WAAmB,GAAkC;EACjD,IAAM,IAAU,KAAK,OAAO,cACtB,IAAY,KAAK,OAAO,gBACxB,IAAO,KAAK,OAAO,WACnB,IAAQ,KAAK,OAAO,YACpB,IAAO,KAAK,OAAO,YACnB,IAAU,KAAK,OAAO,aACtB,IAAU,KAAK,OAAO,WACtB,IAAQ,EAAQ,SAAS,GAEzB,IAAa,MAAc,CAAO,CAAC,CAAC,KAAK,CAAC;EAChD,KAAK,IAAI,IAAO,GAAG,IAAO,GAAO,KAAQ,GAAG;GACxC,IAAI,IAAO,EAAQ,IACf,IAAS,EAAQ;GACrB,OAAO,KAAU,IAKb,AAJA,IACK,EAAI,MAAuB,EAAU,KAC/B,EAAK,KACL,EAAM,IACjB,IAAS,EAAQ;GAErB,IAAM,KAAQ,KAAK,KAAU;GAC7B,KAAK,IAAI,IAAS,GAAG,IAAS,GAAS,KAAU,GAC7C,EAAO,MAAW,EAAK,IAAO;EAEtC;EACA,KAAK,IAAI,IAAS,GAAG,IAAS,GAAS,KAAU,GAC7C,EAAO,KAAW,EAAO,KAAqB;EAElD,OAAO;CACX;CAaA,OAAe,GAGb;EACE,IAAM,IAAO,KAAK,OAAO,MACnB,IAAU,KAAK,OAAO;EAE5B,IAAI,MAAS,YACT,OAAO;GAAE,QAAQ,EAAO,KAAK,MAAQ,EAAI,EAAY;GAAG,eAAe,CAAC;EAAE;EAG9E,IAAM,IAAgB,EAAO,KAAK,MAAQ;GACtC,IAAI,MAAS,WAAW;IACpB,IAAM,IAAW,KAAK,IAAI,KAAK,IAAI,CAAE,EAAI,EAAa;IACtD,OAAO,CAAC,IAAI,GAAU,CAAQ;GAClC;GACA,IAAI,MAAS,WAAW;IACpB,IAAM,IAAU,KAAK,IAAI,GAAG,CAAG,GACzB,IAAgB,EAAI,KAAK,MAAU,KAAK,IAAI,IAAQ,CAAO,CAAC,GAC5D,IAAQ,EAAc,QAAQ,GAAK,MAAU,IAAM,GAAO,CAAC;IACjE,OAAO,EAAc,KAAK,MAAU,IAAQ,CAAK;GACrD;GACA,IAAM,IAAQ,EAAI,QAAQ,GAAK,MAAU,IAAM,GAAO,CAAC;GACvD,OAAO,MAAU,IAAI,CAAC,GAAG,CAAG,IAAI,EAAI,KAAK,MAAU,IAAQ,CAAK;EACpE,CAAC,GAEK,IAAU,KAAK,OAAO,eAAe;EAW3C,OAAO;GAAE,QAVM,EAAc,KAAK,MAAQ;IACtC,IAAI,IAAO;IACX,KAAK,IAAI,IAAQ,GAAG,IAAQ,EAAI,QAAQ,KAAS,GAC7C,AAAK,EAAI,KAAqB,EAAI,OAAkB,IAAO;IAE/D,IAAM,IAAQ,EAAQ;IAEtB,OADI,MAAU,KAAA,IAAkB,IACzB,IAAU,OAAO,CAAK,IAAI;GACrC,CAES;GAAQ;EAAc;CACnC;AACJ;AAUA,eAAe,EACX,GACA,GACoB;CACpB,IAAI,OAAO,KAAW,UAAU;EAC5B,IAAI;EACJ,IAAI;GACA,IAAW,MAAM,MAAM,GAAQ,CAAW;EAC9C,SAAS,GAAO;GACZ,MAAM,IAAI,EAAgB,iCAAiC,KAAU,EACjE,OAAO,EACX,CAAC;EACL;EACA,IAAI,CAAC,EAAS,IACV,MAAM,IAAI,EACN,iCAAiC,EAAS,OAAO,GAAG,EAAS,YACjE;EAEJ,OAAO,MAAM,EAAS,YAAY;CACtC;CAOA,OANI,aAAkB,aACX,EAAO,OAAO,MACjB,EAAO,YACP,EAAO,aAAa,EAAO,UAC/B,IAEG;AACX;AAUA,SAAS,EAAa,GAA6B,GAA0B;CACzE,IAAI,CAAC,MAAM,QAAQ,CAAI,KAAK,EAAK,WAAW,GACxC,MAAM,IAAI,EAAkB,2DAA2D;CAE3F,IAAM,IAAQ,EAAK,EAAE,EAAE,UAAU,GAC3B,IAAS,EAAK,WAAW,MAAQ,EAAI,WAAW,CAAK;CAC3D,IAAI,MAAW,IACX,MAAM,IAAI,EACN,0CAA0C,EAAO,OAC1C,EAAK,EAAO,EAAE,OAAO,oBAAoB,EAAM,EAC1D;CAEJ,IAAI,MAAU,GACV,MAAM,IAAI,EACN,qBAAqB,EAAS,yBAAyB,EAAM,EACjE;CAEJ,OAAO;AACX"}

package/dist/tabular/exceptions.cjs

@@ -1,2 +1,2 @@
-var e=class extends Error{constructor(e,t){super(e,t),this.name=`TabularError`}},t=class extends e{constructor(e,t){super(e,t),this.name=`ModelLoadError`}},n=class extends e{constructor(e,t){super(e,t),this.name=`UnsupportedGraphError`}},r=class extends e{constructor(e,t){super(e,t),this.name=`FeatureShapeError`}},i=class extends e{constructor(e,t){super(e,t),this.name=`InferenceError`}},a=class extends e{constructor(e,t){super(e,t),this.name=`ModelFetchError`}};exports.FeatureShapeError=r,exports.InferenceError=i,exports.ModelFetchError=a,exports.ModelLoadError=t,exports.TabularError=e,exports.UnsupportedGraphError=n;
+var e=class extends Error{constructor(e,t){super(e,t),this.name=`TabularError`}},t=class extends e{constructor(e,t){super(e,t),this.name=`ModelLoadError`}},n=class extends e{constructor(e,t){super(e,t),this.name=`UnsupportedGraphError`}},r=class extends e{constructor(e,t){super(e,t),this.name=`CompactFormatError`}},i=class extends e{constructor(e,t){super(e,t),this.name=`FeatureShapeError`}},a=class extends e{constructor(e,t){super(e,t),this.name=`InferenceError`}},o=class extends e{constructor(e,t){super(e,t),this.name=`ModelFetchError`}};exports.CompactFormatError=r,exports.FeatureShapeError=i,exports.InferenceError=a,exports.ModelFetchError=o,exports.ModelLoadError=t,exports.TabularError=e,exports.UnsupportedGraphError=n;
 //# sourceMappingURL=exceptions.cjs.map

package/dist/tabular/exceptions.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"exceptions.cjs","names":[],"sources":["../../src/tabular/exceptions.ts"],"sourcesContent":["/**\n * Errors thrown by the tabular inference module.\n *\n * Each one exists because the underlying failure is unreadable on its own:\n * ONNX Runtime reports a missing operator registration, and the actual cause\n * is an import path chosen three files away.\n *\n * Every subclass sets `name` to a **literal** string rather than to\n * `new.target.name`. Measured in a real build: the minifier renames the\n * class, so the derived form ships as `error.name === \"t\"` — useless in a\n * log and in any consumer that branches on the name.\n */\n\n/** Base class for every error this module throws. */\nexport class TabularError extends Error {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"TabularError\";\n    }\n}\n\n/** The model bytes could not be loaded into a session. */\nexport class ModelLoadError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"ModelLoadError\";\n    }\n}\n\n/**\n * The runtime has no kernels for this graph's operators.\n *\n * Measured, and the reason this class exists: importing\n * `onnxruntime-web/webgpu` loads a WebAssembly build without the\n * `ai.onnx.ml` domain, so creating a session over any scikit-learn export\n * fails with `No Op registered for TreeEnsembleClassifier`. The message\n * names the fix, because the raw error points at the model instead of at\n * the import.\n */\nexport class UnsupportedGraphError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"UnsupportedGraphError\";\n    }\n}\n\n/** The rows do not match what the model expects. */\nexport class FeatureShapeError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"FeatureShapeError\";\n    }\n}\n\n/** The session ran but its outputs could not be read. */\nexport class InferenceError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"InferenceError\";\n    }\n}\n\n/**\n * The model bytes could not be fetched or read from the cache.\n *\n * Distinct from {@link ModelLoadError}: this one means the app is offline\n * and nothing was cached, which is a deployment problem, not a model\n * problem.\n */\nexport class ModelFetchError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"ModelFetchError\";\n    }\n}\n"],"mappings":"AAcA,IAAa,EAAb,cAAkC,KAAM,CACpC,YAAY,EAAiB,EAAwB,CACjD,MAAM,EAAS,CAAO,EACtB,KAAK,KAAO,cAChB,CACJ,EAGa,EAAb,cAAoC,CAAa,CAC7C,YAAY,EAAiB,EAAwB,CACjD,MAAM,EAAS,CAAO,EACtB,KAAK,KAAO,gBAChB,CACJ,EAYa,EAAb,cAA2C,CAAa,CACpD,YAAY,EAAiB,EAAwB,CACjD,MAAM,EAAS,CAAO,EACtB,KAAK,KAAO,uBAChB,CACJ,EAGa,EAAb,cAAuC,CAAa,CAChD,YAAY,EAAiB,EAAwB,CACjD,MAAM,EAAS,CAAO,EACtB,KAAK,KAAO,mBAChB,CACJ,EAGa,EAAb,cAAoC,CAAa,CAC7C,YAAY,EAAiB,EAAwB,CACjD,MAAM,EAAS,CAAO,EACtB,KAAK,KAAO,gBAChB,CACJ,EASa,EAAb,cAAqC,CAAa,CAC9C,YAAY,EAAiB,EAAwB,CACjD,MAAM,EAAS,CAAO,EACtB,KAAK,KAAO,iBAChB,CACJ"}
+{"version":3,"file":"exceptions.cjs","names":[],"sources":["../../src/tabular/exceptions.ts"],"sourcesContent":["/**\n * Errors thrown by the tabular inference module.\n *\n * Each one exists because the underlying failure is unreadable on its own:\n * ONNX Runtime reports a missing operator registration, and the actual cause\n * is an import path chosen three files away.\n *\n * Every subclass sets `name` to a **literal** string rather than to\n * `new.target.name`. Measured in a real build: the minifier renames the\n * class, so the derived form ships as `error.name === \"t\"` — useless in a\n * log and in any consumer that branches on the name.\n */\n\n/** Base class for every error this module throws. */\nexport class TabularError extends Error {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"TabularError\";\n    }\n}\n\n/** The model bytes could not be loaded into a session. */\nexport class ModelLoadError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"ModelLoadError\";\n    }\n}\n\n/**\n * The runtime has no kernels for this graph's operators.\n *\n * Measured, and the reason this class exists: importing\n * `onnxruntime-web/webgpu` loads a WebAssembly build without the\n * `ai.onnx.ml` domain, so creating a session over any scikit-learn export\n * fails with `No Op registered for TreeEnsembleClassifier`. The message\n * names the fix, because the raw error points at the model instead of at\n * the import.\n */\nexport class UnsupportedGraphError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"UnsupportedGraphError\";\n    }\n}\n\n/**\n * The bytes are not a compact model, or use a newer layout.\n *\n * Separate from {@link ModelLoadError} because the fix is different: a\n * `.onnx` file handed to the compact reader is a wiring mistake, not a\n * broken model.\n */\nexport class CompactFormatError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"CompactFormatError\";\n    }\n}\n\n/** The rows do not match what the model expects. */\nexport class FeatureShapeError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"FeatureShapeError\";\n    }\n}\n\n/** The session ran but its outputs could not be read. */\nexport class InferenceError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"InferenceError\";\n    }\n}\n\n/**\n * The model bytes could not be fetched or read from the cache.\n *\n * Distinct from {@link ModelLoadError}: this one means the app is offline\n * and nothing was cached, which is a deployment problem, not a model\n * problem.\n */\nexport class ModelFetchError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"ModelFetchError\";\n    }\n}\n"],"mappings":"AAcA,IAAa,EAAb,cAAkC,KAAM,CACpC,YAAY,EAAiB,EAAwB,CACjD,MAAM,EAAS,CAAO,EACtB,KAAK,KAAO,cAChB,CACJ,EAGa,EAAb,cAAoC,CAAa,CAC7C,YAAY,EAAiB,EAAwB,CACjD,MAAM,EAAS,CAAO,EACtB,KAAK,KAAO,gBAChB,CACJ,EAYa,EAAb,cAA2C,CAAa,CACpD,YAAY,EAAiB,EAAwB,CACjD,MAAM,EAAS,CAAO,EACtB,KAAK,KAAO,uBAChB,CACJ,EASa,EAAb,cAAwC,CAAa,CACjD,YAAY,EAAiB,EAAwB,CACjD,MAAM,EAAS,CAAO,EACtB,KAAK,KAAO,oBAChB,CACJ,EAGa,EAAb,cAAuC,CAAa,CAChD,YAAY,EAAiB,EAAwB,CACjD,MAAM,EAAS,CAAO,EACtB,KAAK,KAAO,mBAChB,CACJ,EAGa,EAAb,cAAoC,CAAa,CAC7C,YAAY,EAAiB,EAAwB,CACjD,MAAM,EAAS,CAAO,EACtB,KAAK,KAAO,gBAChB,CACJ,EASa,EAAb,cAAqC,CAAa,CAC9C,YAAY,EAAiB,EAAwB,CACjD,MAAM,EAAS,CAAO,EACtB,KAAK,KAAO,iBAChB,CACJ"}

package/dist/tabular/exceptions.js

@@ -13,18 +13,22 @@ var e = class extends Error {
 	}
 }, r = class extends e {
 	constructor(e, t) {
-		super(e, t), this.name = "FeatureShapeError";
+		super(e, t), this.name = "CompactFormatError";
 	}
 }, i = class extends e {
 	constructor(e, t) {
-		super(e, t), this.name = "InferenceError";
+		super(e, t), this.name = "FeatureShapeError";
 	}
 }, a = class extends e {
+	constructor(e, t) {
+		super(e, t), this.name = "InferenceError";
+	}
+}, o = class extends e {
 	constructor(e, t) {
 		super(e, t), this.name = "ModelFetchError";
 	}
 };
 //#endregion
-export { r as FeatureShapeError, i as InferenceError, a as ModelFetchError, t as ModelLoadError, e as TabularError, n as UnsupportedGraphError };
+export { r as CompactFormatError, i as FeatureShapeError, a as InferenceError, o as ModelFetchError, t as ModelLoadError, e as TabularError, n as UnsupportedGraphError };
 
 //# sourceMappingURL=exceptions.js.map

package/dist/tabular/exceptions.js.map

@@ -1 +1 @@
-{"version":3,"file":"exceptions.js","names":[],"sources":["../../src/tabular/exceptions.ts"],"sourcesContent":["/**\n * Errors thrown by the tabular inference module.\n *\n * Each one exists because the underlying failure is unreadable on its own:\n * ONNX Runtime reports a missing operator registration, and the actual cause\n * is an import path chosen three files away.\n *\n * Every subclass sets `name` to a **literal** string rather than to\n * `new.target.name`. Measured in a real build: the minifier renames the\n * class, so the derived form ships as `error.name === \"t\"` — useless in a\n * log and in any consumer that branches on the name.\n */\n\n/** Base class for every error this module throws. */\nexport class TabularError extends Error {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"TabularError\";\n    }\n}\n\n/** The model bytes could not be loaded into a session. */\nexport class ModelLoadError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"ModelLoadError\";\n    }\n}\n\n/**\n * The runtime has no kernels for this graph's operators.\n *\n * Measured, and the reason this class exists: importing\n * `onnxruntime-web/webgpu` loads a WebAssembly build without the\n * `ai.onnx.ml` domain, so creating a session over any scikit-learn export\n * fails with `No Op registered for TreeEnsembleClassifier`. The message\n * names the fix, because the raw error points at the model instead of at\n * the import.\n */\nexport class UnsupportedGraphError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"UnsupportedGraphError\";\n    }\n}\n\n/** The rows do not match what the model expects. */\nexport class FeatureShapeError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"FeatureShapeError\";\n    }\n}\n\n/** The session ran but its outputs could not be read. */\nexport class InferenceError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"InferenceError\";\n    }\n}\n\n/**\n * The model bytes could not be fetched or read from the cache.\n *\n * Distinct from {@link ModelLoadError}: this one means the app is offline\n * and nothing was cached, which is a deployment problem, not a model\n * problem.\n */\nexport class ModelFetchError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"ModelFetchError\";\n    }\n}\n"],"mappings":";AAcA,IAAa,IAAb,cAAkC,MAAM;CACpC,YAAY,GAAiB,GAAwB;EAEjD,AADA,MAAM,GAAS,CAAO,GACtB,KAAK,OAAO;CAChB;AACJ,GAGa,IAAb,cAAoC,EAAa;CAC7C,YAAY,GAAiB,GAAwB;EAEjD,AADA,MAAM,GAAS,CAAO,GACtB,KAAK,OAAO;CAChB;AACJ,GAYa,IAAb,cAA2C,EAAa;CACpD,YAAY,GAAiB,GAAwB;EAEjD,AADA,MAAM,GAAS,CAAO,GACtB,KAAK,OAAO;CAChB;AACJ,GAGa,IAAb,cAAuC,EAAa;CAChD,YAAY,GAAiB,GAAwB;EAEjD,AADA,MAAM,GAAS,CAAO,GACtB,KAAK,OAAO;CAChB;AACJ,GAGa,IAAb,cAAoC,EAAa;CAC7C,YAAY,GAAiB,GAAwB;EAEjD,AADA,MAAM,GAAS,CAAO,GACtB,KAAK,OAAO;CAChB;AACJ,GASa,IAAb,cAAqC,EAAa;CAC9C,YAAY,GAAiB,GAAwB;EAEjD,AADA,MAAM,GAAS,CAAO,GACtB,KAAK,OAAO;CAChB;AACJ"}
+{"version":3,"file":"exceptions.js","names":[],"sources":["../../src/tabular/exceptions.ts"],"sourcesContent":["/**\n * Errors thrown by the tabular inference module.\n *\n * Each one exists because the underlying failure is unreadable on its own:\n * ONNX Runtime reports a missing operator registration, and the actual cause\n * is an import path chosen three files away.\n *\n * Every subclass sets `name` to a **literal** string rather than to\n * `new.target.name`. Measured in a real build: the minifier renames the\n * class, so the derived form ships as `error.name === \"t\"` — useless in a\n * log and in any consumer that branches on the name.\n */\n\n/** Base class for every error this module throws. */\nexport class TabularError extends Error {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"TabularError\";\n    }\n}\n\n/** The model bytes could not be loaded into a session. */\nexport class ModelLoadError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"ModelLoadError\";\n    }\n}\n\n/**\n * The runtime has no kernels for this graph's operators.\n *\n * Measured, and the reason this class exists: importing\n * `onnxruntime-web/webgpu` loads a WebAssembly build without the\n * `ai.onnx.ml` domain, so creating a session over any scikit-learn export\n * fails with `No Op registered for TreeEnsembleClassifier`. The message\n * names the fix, because the raw error points at the model instead of at\n * the import.\n */\nexport class UnsupportedGraphError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"UnsupportedGraphError\";\n    }\n}\n\n/**\n * The bytes are not a compact model, or use a newer layout.\n *\n * Separate from {@link ModelLoadError} because the fix is different: a\n * `.onnx` file handed to the compact reader is a wiring mistake, not a\n * broken model.\n */\nexport class CompactFormatError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"CompactFormatError\";\n    }\n}\n\n/** The rows do not match what the model expects. */\nexport class FeatureShapeError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"FeatureShapeError\";\n    }\n}\n\n/** The session ran but its outputs could not be read. */\nexport class InferenceError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"InferenceError\";\n    }\n}\n\n/**\n * The model bytes could not be fetched or read from the cache.\n *\n * Distinct from {@link ModelLoadError}: this one means the app is offline\n * and nothing was cached, which is a deployment problem, not a model\n * problem.\n */\nexport class ModelFetchError extends TabularError {\n    constructor(message: string, options?: ErrorOptions) {\n        super(message, options);\n        this.name = \"ModelFetchError\";\n    }\n}\n"],"mappings":";AAcA,IAAa,IAAb,cAAkC,MAAM;CACpC,YAAY,GAAiB,GAAwB;EAEjD,AADA,MAAM,GAAS,CAAO,GACtB,KAAK,OAAO;CAChB;AACJ,GAGa,IAAb,cAAoC,EAAa;CAC7C,YAAY,GAAiB,GAAwB;EAEjD,AADA,MAAM,GAAS,CAAO,GACtB,KAAK,OAAO;CAChB;AACJ,GAYa,IAAb,cAA2C,EAAa;CACpD,YAAY,GAAiB,GAAwB;EAEjD,AADA,MAAM,GAAS,CAAO,GACtB,KAAK,OAAO;CAChB;AACJ,GASa,IAAb,cAAwC,EAAa;CACjD,YAAY,GAAiB,GAAwB;EAEjD,AADA,MAAM,GAAS,CAAO,GACtB,KAAK,OAAO;CAChB;AACJ,GAGa,IAAb,cAAuC,EAAa;CAChD,YAAY,GAAiB,GAAwB;EAEjD,AADA,MAAM,GAAS,CAAO,GACtB,KAAK,OAAO;CAChB;AACJ,GAGa,IAAb,cAAoC,EAAa;CAC7C,YAAY,GAAiB,GAAwB;EAEjD,AADA,MAAM,GAAS,CAAO,GACtB,KAAK,OAAO;CAChB;AACJ,GASa,IAAb,cAAqC,EAAa;CAC9C,YAAY,GAAiB,GAAwB;EAEjD,AADA,MAAM,GAAS,CAAO,GACtB,KAAK,OAAO;CAChB;AACJ"}

package/dist/tabular/manifest.cjs

@@ -1,2 +1,2 @@
-const e=require("./exceptions.cjs"),t=require("./cache.cjs"),n=require("./predictor.cjs");var r=1,i=`manifest.json`;async function a(t,n){let r=s(t),i;try{i=await fetch(r,n)}catch(t){throw new e.ModelFetchError(`Could not read the manifest at ${r}`,{cause:t})}if(!i.ok)throw new e.ModelFetchError(`Could not read the manifest at ${r}: ${i.status} ${i.statusText}`);let a=await i.json();if(typeof a?.schema_version!=`number`)throw new e.ModelFetchError(`${r} is not an edge package manifest (no schema_version).`);if(a.schema_version>1)throw new e.ModelFetchError(`The manifest at ${r} uses schema_version ${a.schema_version}, and this SDK understands 1. Upgrade tempest-react-sdk before serving this package.`);return a}async function o(e,r={}){let i=await a(e),o=`${e.endsWith(`/`)?e:`${e}/`}${i.model.file}`,s=r.cache??!0,c=s===!1?o:await t.fetchModelBytes(o,typeof s==`object`?s:{}),l=await n.TabularPredictor.create(c,{providers:r.providers,warmup:r.warmup,sessionOptions:r.sessionOptions}),u=i.output.classes;return{manifest:i,predictor:l,featureNames:i.input.feature_names,classes:u,explain:e=>e.map((e,t)=>({name:u[t]??String(t),score:e})).sort((e,t)=>t.score-e.score)}}function s(e){return e.endsWith(`.json`)?e:e.endsWith(`/`)?`${e}${i}`:`${e}/${i}`}exports.MANIFEST_FILENAME=i,exports.SUPPORTED_MANIFEST_SCHEMA=r,exports.fetchEdgeManifest=a,exports.loadEdgePackage=o;
+const e=require("./exceptions.cjs"),t=require("./cache.cjs"),n=require("./compact.cjs"),r=require("./predictor.cjs");var i=1,a=`manifest.json`;async function o(t,n){let r=u(t),i;try{i=await fetch(r,n)}catch(t){throw new e.ModelFetchError(`Could not read the manifest at ${r}`,{cause:t})}if(!i.ok)throw new e.ModelFetchError(`Could not read the manifest at ${r}: ${i.status} ${i.statusText}`);let a=await i.json();if(typeof a?.schema_version!=`number`)throw new e.ModelFetchError(`${r} is not an edge package manifest (no schema_version).`);if(a.schema_version>1)throw new e.ModelFetchError(`The manifest at ${r} uses schema_version ${a.schema_version}, and this SDK understands 1. Upgrade tempest-react-sdk before serving this package.`);return a}async function s(e,i={}){let a=await o(e),s=e.endsWith(`/`)?e:`${e}/`,u=c(a,i.runtime??`auto`),d=`${s}${l(a,u)}`,f=i.cache??!0,p=f===!1?d:await t.fetchModelBytes(d,typeof f==`object`?f:{}),m=u===`compact`?await n.CompactPredictor.create(p):await r.TabularPredictor.create(p,{providers:i.providers,warmup:i.warmup,sessionOptions:i.sessionOptions}),h=a.output.classes;return{manifest:a,predictor:m,runtime:u,featureNames:a.input.feature_names,classes:h,explain:e=>e.map((e,t)=>({name:h[t]??String(t),score:e})).sort((e,t)=>t.score-e.score)}}function c(t,n){let r=t.runtimes??[],i=r.some(e=>e.kind===`compact`);if(n===`auto`)return i?`compact`:`onnx`;if(n===`compact`&&!i)throw new e.ModelFetchError(`This package carries no compact model (${t.name} lists ${r.map(e=>e.kind).join(`, `)||`onnx`}). Re-export it with edge_pipeline(compact=True), or load it as ONNX.`);return n}function l(e,t){return(e.runtimes??[]).find(e=>e.kind===t)?.file??e.model.file}function u(e){return e.endsWith(`.json`)?e:e.endsWith(`/`)?`${e}${a}`:`${e}/${a}`}exports.MANIFEST_FILENAME=a,exports.SUPPORTED_MANIFEST_SCHEMA=i,exports.fetchEdgeManifest=o,exports.loadEdgePackage=s;
 //# sourceMappingURL=manifest.cjs.map

package/dist/tabular/manifest.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"manifest.cjs","names":[],"sources":["../../src/tabular/manifest.ts"],"sourcesContent":["/**\n * Reading an edge package published by `tempest-fastapi-sdk`.\n *\n * `edge_pipeline` writes a directory — the graph, a gzipped copy, a drift\n * baseline and a `manifest.json` — and the browser is one of its two\n * intended consumers. The manifest is what turns a `.onnx` URL into\n * something a UI can use: the **column order** the model was trained on,\n * the class names behind `probabilities[2]`, and a version to compare\n * against what is already cached.\n *\n * That column order is the field worth loading a manifest for. A model fed\n * the right features in the wrong order answers confidently and wrongly,\n * and no runtime check catches it.\n *\n * The contract is pinned by `schema_version`. Unknown fields are ignored\n * rather than rejected, so a package written by a newer SDK still loads.\n */\n\nimport { fetchModelBytes, type ModelCacheOptions } from \"./cache\";\nimport { ModelFetchError } from \"./exceptions\";\nimport { TabularPredictor } from \"./predictor\";\nimport type { TabularPredictorOptions } from \"./types\";\n\n/** Manifest schema version this reader was written against. */\nexport const SUPPORTED_MANIFEST_SCHEMA = 1;\n\n/** Fixed filename inside a package directory. */\nexport const MANIFEST_FILENAME = \"manifest.json\";\n\n/** The graph file and how to check you got it whole. */\nexport interface ManifestModelFile {\n    readonly file: string;\n    readonly sha256: string;\n    readonly bytes: number;\n    readonly gzip_file: string | null;\n    readonly gzip_bytes: number | null;\n    readonly opset: number;\n    readonly dtype: string;\n}\n\n/** What the graph expects per row. */\nexport interface ManifestInput {\n    readonly name: string;\n    readonly features: number;\n    /** Column order used at training time. */\n    readonly feature_names: readonly string[];\n}\n\n/** What the graph answers. */\nexport interface ManifestOutput {\n    readonly is_classifier: boolean;\n    readonly label_output: string;\n    readonly probability_output: string | null;\n    /** Class labels in score-column order. */\n    readonly classes: readonly string[];\n}\n\n/** The package manifest, as written by `edge_pipeline`. */\nexport interface EdgeManifest {\n    readonly schema_version: number;\n    readonly name: string;\n    readonly version: string;\n    readonly created_at: string;\n    readonly sdk_version: string;\n    readonly estimator: string;\n    readonly model: ManifestModelFile;\n    readonly input: ManifestInput;\n    readonly output: ManifestOutput;\n    readonly verified: boolean | null;\n    readonly baseline_file: string | null;\n    readonly baseline_samples: number;\n}\n\n/** A package loaded and ready to answer. */\nexport interface LoadedEdgePackage {\n    /** What was published. */\n    readonly manifest: EdgeManifest;\n    /** The running model. */\n    readonly predictor: TabularPredictor;\n    /** Column order the rows must follow. */\n    readonly featureNames: readonly string[];\n    /** Class names behind each probability column. */\n    readonly classes: readonly string[];\n    /**\n     * Map a prediction's scores onto class names.\n     *\n     * @param probabilities One row of scores.\n     * @returns Name/score pairs, highest first.\n     */\n    readonly explain: (probabilities: readonly number[]) => { name: string; score: number }[];\n}\n\n/** Options for {@link loadEdgePackage}. */\nexport interface LoadEdgePackageOptions extends TabularPredictorOptions {\n    /** Cache the model bytes for offline use. `true` by default. */\n    readonly cache?: boolean | ModelCacheOptions;\n}\n\n/**\n * Read a package's manifest.\n *\n * Cheap: it is a few hundred bytes, so an app can check for a new version\n * without downloading a model it may already have.\n *\n * @example\n * ```ts\n * const manifest = await fetchEdgeManifest(\"/models/risk/\");\n * if (manifest.version !== localStorage.getItem(\"risk-version\")) {\n *     // a new model was published\n * }\n * ```\n *\n * @param directoryUrl URL of the package directory, with or without a\n *   trailing slash. A full URL to the manifest file also works.\n * @param requestInit `fetch` options.\n * @returns The parsed manifest.\n * @throws {@link ModelFetchError} when the manifest cannot be read, or when\n *   its `schema_version` is newer than this reader understands — loading it\n *   anyway would risk misreading the field that defines column order.\n */\nexport async function fetchEdgeManifest(\n    directoryUrl: string,\n    requestInit?: RequestInit,\n): Promise<EdgeManifest> {\n    const url = manifestUrl(directoryUrl);\n    let response: Response;\n    try {\n        response = await fetch(url, requestInit);\n    } catch (error) {\n        throw new ModelFetchError(`Could not read the manifest at ${url}`, {\n            cause: error,\n        });\n    }\n    if (!response.ok) {\n        throw new ModelFetchError(\n            `Could not read the manifest at ${url}: ${response.status} ${response.statusText}`,\n        );\n    }\n\n    const manifest = (await response.json()) as EdgeManifest;\n    if (typeof manifest?.schema_version !== \"number\") {\n        throw new ModelFetchError(`${url} is not an edge package manifest (no schema_version).`);\n    }\n    if (manifest.schema_version > SUPPORTED_MANIFEST_SCHEMA) {\n        throw new ModelFetchError(\n            `The manifest at ${url} uses schema_version ${manifest.schema_version}, ` +\n                `and this SDK understands ${SUPPORTED_MANIFEST_SCHEMA}. Upgrade ` +\n                \"tempest-react-sdk before serving this package.\",\n        );\n    }\n    return manifest;\n}\n\n/**\n * Load a whole edge package: manifest, model, and the names to read it by.\n *\n * @example\n * ```ts\n * const pkg = await loadEdgePackage(\"/models/risk/\");\n *\n * console.log(pkg.featureNames); // [\"age\", \"income\", \"tenure\", \"score\", \"visits\"]\n *\n * const { probabilities } = await pkg.predictor.predict([[41, 5200, 3, 0.82, 12]]);\n * console.log(pkg.explain(probabilities[0]!)); // [{ name: \"approved\", score: 0.91 }, ...]\n * ```\n *\n * @param directoryUrl URL of the package directory.\n * @param options Predictor options plus caching.\n * @returns The loaded package.\n * @throws {@link ModelFetchError} when the manifest or model cannot be read.\n */\nexport async function loadEdgePackage(\n    directoryUrl: string,\n    options: LoadEdgePackageOptions = {},\n): Promise<LoadedEdgePackage> {\n    const manifest = await fetchEdgeManifest(directoryUrl);\n    const base = directoryUrl.endsWith(\"/\") ? directoryUrl : `${directoryUrl}/`;\n    const modelUrl = `${base}${manifest.model.file}`;\n\n    const cache = options.cache ?? true;\n    const source =\n        cache === false\n            ? modelUrl\n            : await fetchModelBytes(modelUrl, typeof cache === \"object\" ? cache : {});\n\n    const predictor = await TabularPredictor.create(source, {\n        providers: options.providers,\n        warmup: options.warmup,\n        sessionOptions: options.sessionOptions,\n    });\n\n    const classes = manifest.output.classes;\n    return {\n        manifest,\n        predictor,\n        featureNames: manifest.input.feature_names,\n        classes,\n        explain: (probabilities: readonly number[]) =>\n            probabilities\n                .map((score, index) => ({\n                    name: classes[index] ?? String(index),\n                    score,\n                }))\n                .sort((a, b) => b.score - a.score),\n    };\n}\n\n/**\n * Resolve a directory URL to its manifest file.\n *\n * @param directoryUrl The package directory, or the manifest itself.\n * @returns The manifest URL.\n */\nfunction manifestUrl(directoryUrl: string): string {\n    if (directoryUrl.endsWith(\".json\")) return directoryUrl;\n    return directoryUrl.endsWith(\"/\")\n        ? `${directoryUrl}${MANIFEST_FILENAME}`\n        : `${directoryUrl}/${MANIFEST_FILENAME}`;\n}\n"],"mappings":"0FAwBA,IAAa,EAA4B,EAG5B,EAAoB,gBA6FjC,eAAsB,EAClB,EACA,EACqB,CACrB,IAAM,EAAM,EAAY,CAAY,EAChC,EACJ,GAAI,CACA,EAAW,MAAM,MAAM,EAAK,CAAW,CAC3C,OAAS,EAAO,CACZ,MAAM,IAAI,EAAA,gBAAgB,kCAAkC,IAAO,CAC/D,MAAO,CACX,CAAC,CACL,CACA,GAAI,CAAC,EAAS,GACV,MAAM,IAAI,EAAA,gBACN,kCAAkC,EAAI,IAAI,EAAS,OAAO,GAAG,EAAS,YAC1E,EAGJ,IAAM,EAAY,MAAM,EAAS,KAAK,EACtC,GAAI,OAAO,GAAU,gBAAmB,SACpC,MAAM,IAAI,EAAA,gBAAgB,GAAG,EAAI,sDAAsD,EAE3F,GAAI,EAAS,eAAA,EACT,MAAM,IAAI,EAAA,gBACN,mBAAmB,EAAI,uBAAuB,EAAS,eAAe,qFAG1E,EAEJ,OAAO,CACX,CAoBA,eAAsB,EAClB,EACA,EAAkC,CAAC,EACT,CAC1B,IAAM,EAAW,MAAM,EAAkB,CAAY,EAE/C,EAAW,GADJ,EAAa,SAAS,GAAG,EAAI,EAAe,GAAG,EAAa,KAC9C,EAAS,MAAM,OAEpC,EAAQ,EAAQ,OAAS,GACzB,EACF,IAAU,GACJ,EACA,MAAM,EAAA,gBAAgB,EAAU,OAAO,GAAU,SAAW,EAAQ,CAAC,CAAC,EAE1E,EAAY,MAAM,EAAA,iBAAiB,OAAO,EAAQ,CACpD,UAAW,EAAQ,UACnB,OAAQ,EAAQ,OAChB,eAAgB,EAAQ,cAC5B,CAAC,EAEK,EAAU,EAAS,OAAO,QAChC,MAAO,CACH,WACA,YACA,aAAc,EAAS,MAAM,cAC7B,UACA,QAAU,GACN,EACK,KAAK,EAAO,KAAW,CACpB,KAAM,EAAQ,IAAU,OAAO,CAAK,EACpC,OACJ,EAAE,CAAC,CACF,MAAM,EAAG,IAAM,EAAE,MAAQ,EAAE,KAAK,CAC7C,CACJ,CAQA,SAAS,EAAY,EAA8B,CAE/C,OADI,EAAa,SAAS,OAAO,EAAU,EACpC,EAAa,SAAS,GAAG,EAC1B,GAAG,IAAe,IAClB,GAAG,EAAa,GAAG,GAC7B"}
+{"version":3,"file":"manifest.cjs","names":[],"sources":["../../src/tabular/manifest.ts"],"sourcesContent":["/**\n * Reading an edge package published by `tempest-fastapi-sdk`.\n *\n * `edge_pipeline` writes a directory — the graph, a gzipped copy, a drift\n * baseline and a `manifest.json` — and the browser is one of its two\n * intended consumers. The manifest is what turns a `.onnx` URL into\n * something a UI can use: the **column order** the model was trained on,\n * the class names behind `probabilities[2]`, and a version to compare\n * against what is already cached.\n *\n * That column order is the field worth loading a manifest for. A model fed\n * the right features in the wrong order answers confidently and wrongly,\n * and no runtime check catches it.\n *\n * The contract is pinned by `schema_version`. Unknown fields are ignored\n * rather than rejected, so a package written by a newer SDK still loads.\n */\n\nimport { fetchModelBytes, type ModelCacheOptions } from \"./cache\";\nimport { CompactPredictor } from \"./compact\";\nimport { ModelFetchError } from \"./exceptions\";\nimport { TabularPredictor } from \"./predictor\";\nimport type { FeatureRow, TabularPrediction, TabularPredictorOptions } from \"./types\";\n\n/** Manifest schema version this reader was written against. */\nexport const SUPPORTED_MANIFEST_SCHEMA = 1;\n\n/** Fixed filename inside a package directory. */\nexport const MANIFEST_FILENAME = \"manifest.json\";\n\n/** The graph file and how to check you got it whole. */\nexport interface ManifestModelFile {\n    readonly file: string;\n    readonly sha256: string;\n    readonly bytes: number;\n    readonly gzip_file: string | null;\n    readonly gzip_bytes: number | null;\n    readonly opset: number;\n    readonly dtype: string;\n}\n\n/** What the graph expects per row. */\nexport interface ManifestInput {\n    readonly name: string;\n    readonly features: number;\n    /** Column order used at training time. */\n    readonly feature_names: readonly string[];\n}\n\n/** What the graph answers. */\nexport interface ManifestOutput {\n    readonly is_classifier: boolean;\n    readonly label_output: string;\n    readonly probability_output: string | null;\n    /** Class labels in score-column order. */\n    readonly classes: readonly string[];\n}\n\n/**\n * Where the packaged model came from, when it came from an existing\n * artifact.\n *\n * Present when the package was built with `edge_pipeline_from_pickle`: the\n * `.pkl` never reaches the browser (a pickle is a Python program, not\n * data), but its name and digest travel in the manifest, so a model\n * answering in a tab can be traced back to the file that produced it.\n */\nexport interface ManifestSource {\n    readonly file: string;\n    readonly kind: string;\n    readonly sha256: string;\n    readonly bytes: number;\n    readonly sklearn_version: string;\n    readonly warnings: readonly string[];\n}\n\n/**\n * One file in the package a runtime can load.\n *\n * A package may carry the same model twice — as ONNX, which any runtime\n * reads at the cost of a 25.6 MB WebAssembly download, and as the compact\n * format, which needs no runtime. The list is what lets the browser pick\n * by what it already ships.\n */\nexport interface ManifestRuntime {\n    readonly kind: \"onnx\" | \"compact\" | string;\n    readonly file: string;\n    readonly bytes: number;\n    readonly gzip_file: string | null;\n    readonly gzip_bytes: number | null;\n    readonly sha256: string;\n}\n\n/** The package manifest, as written by `edge_pipeline`. */\nexport interface EdgeManifest {\n    readonly schema_version: number;\n    readonly name: string;\n    readonly version: string;\n    readonly created_at: string;\n    readonly sdk_version: string;\n    readonly estimator: string;\n    readonly model: ManifestModelFile;\n    readonly input: ManifestInput;\n    readonly output: ManifestOutput;\n    readonly verified: boolean | null;\n    /** Every file a runtime can load. Absent on packages written before v0.194. */\n    readonly runtimes?: readonly ManifestRuntime[];\n    /** Absent on packages built straight from a fitted estimator. */\n    readonly source?: ManifestSource;\n    readonly baseline_file: string | null;\n    readonly baseline_samples: number;\n}\n\n/** Which reader served the package. */\nexport type TabularRuntime = \"onnx\" | \"compact\";\n\n/** A package loaded and ready to answer. */\nexport interface LoadedEdgePackage {\n    /** What was published. */\n    readonly manifest: EdgeManifest;\n    /** The running model, whichever runtime read it. */\n    readonly predictor: PredictorLike;\n    /** Which reader was used. */\n    readonly runtime: TabularRuntime;\n    /** Column order the rows must follow. */\n    readonly featureNames: readonly string[];\n    /** Class names behind each probability column. */\n    readonly classes: readonly string[];\n    /**\n     * Map a prediction's scores onto class names.\n     *\n     * @param probabilities One row of scores.\n     * @returns Name/score pairs, highest first.\n     */\n    readonly explain: (probabilities: readonly number[]) => { name: string; score: number }[];\n}\n\n/**\n * The shape both readers share.\n *\n * `TabularPredictor` (ONNX) and `CompactPredictor` (runtime-free) answer\n * with the same object, so an app can switch routes without touching a\n * line of its own code.\n */\nexport interface PredictorLike {\n    predict(rows: readonly FeatureRow[]): Promise<TabularPrediction>;\n    dispose(): Promise<void>;\n}\n\n/** Options for {@link loadEdgePackage}. */\nexport interface LoadEdgePackageOptions extends TabularPredictorOptions {\n    /** Cache the model bytes for offline use. `true` by default. */\n    readonly cache?: boolean | ModelCacheOptions;\n    /**\n     * Which reader to use.\n     *\n     * `\"auto\"` (the default) takes the compact form when the package has\n     * one, because it answers without downloading a WebAssembly runtime.\n     * Force `\"onnx\"` when the app already ships ONNX for something else —\n     * then the runtime is already paid for and ONNX covers more estimators.\n     */\n    readonly runtime?: TabularRuntime | \"auto\";\n}\n\n/**\n * Read a package's manifest.\n *\n * Cheap: it is a few hundred bytes, so an app can check for a new version\n * without downloading a model it may already have.\n *\n * @example\n * ```ts\n * const manifest = await fetchEdgeManifest(\"/models/risk/\");\n * if (manifest.version !== localStorage.getItem(\"risk-version\")) {\n *     // a new model was published\n * }\n * ```\n *\n * @param directoryUrl URL of the package directory, with or without a\n *   trailing slash. A full URL to the manifest file also works.\n * @param requestInit `fetch` options.\n * @returns The parsed manifest.\n * @throws {@link ModelFetchError} when the manifest cannot be read, or when\n *   its `schema_version` is newer than this reader understands — loading it\n *   anyway would risk misreading the field that defines column order.\n */\nexport async function fetchEdgeManifest(\n    directoryUrl: string,\n    requestInit?: RequestInit,\n): Promise<EdgeManifest> {\n    const url = manifestUrl(directoryUrl);\n    let response: Response;\n    try {\n        response = await fetch(url, requestInit);\n    } catch (error) {\n        throw new ModelFetchError(`Could not read the manifest at ${url}`, {\n            cause: error,\n        });\n    }\n    if (!response.ok) {\n        throw new ModelFetchError(\n            `Could not read the manifest at ${url}: ${response.status} ${response.statusText}`,\n        );\n    }\n\n    const manifest = (await response.json()) as EdgeManifest;\n    if (typeof manifest?.schema_version !== \"number\") {\n        throw new ModelFetchError(`${url} is not an edge package manifest (no schema_version).`);\n    }\n    if (manifest.schema_version > SUPPORTED_MANIFEST_SCHEMA) {\n        throw new ModelFetchError(\n            `The manifest at ${url} uses schema_version ${manifest.schema_version}, ` +\n                `and this SDK understands ${SUPPORTED_MANIFEST_SCHEMA}. Upgrade ` +\n                \"tempest-react-sdk before serving this package.\",\n        );\n    }\n    return manifest;\n}\n\n/**\n * Load a whole edge package: manifest, model, and the names to read it by.\n *\n * @example\n * ```ts\n * const pkg = await loadEdgePackage(\"/models/risk/\");\n *\n * console.log(pkg.featureNames); // [\"age\", \"income\", \"tenure\", \"score\", \"visits\"]\n *\n * const { probabilities } = await pkg.predictor.predict([[41, 5200, 3, 0.82, 12]]);\n * console.log(pkg.explain(probabilities[0]!)); // [{ name: \"approved\", score: 0.91 }, ...]\n * ```\n *\n * @param directoryUrl URL of the package directory.\n * @param options Predictor options plus caching.\n * @returns The loaded package.\n * @throws {@link ModelFetchError} when the manifest or model cannot be read.\n */\nexport async function loadEdgePackage(\n    directoryUrl: string,\n    options: LoadEdgePackageOptions = {},\n): Promise<LoadedEdgePackage> {\n    const manifest = await fetchEdgeManifest(directoryUrl);\n    const base = directoryUrl.endsWith(\"/\") ? directoryUrl : `${directoryUrl}/`;\n    const runtime = chooseRuntime(manifest, options.runtime ?? \"auto\");\n    const file = fileFor(manifest, runtime);\n    const modelUrl = `${base}${file}`;\n\n    const cache = options.cache ?? true;\n    const source =\n        cache === false\n            ? modelUrl\n            : await fetchModelBytes(modelUrl, typeof cache === \"object\" ? cache : {});\n\n    const predictor: PredictorLike =\n        runtime === \"compact\"\n            ? await CompactPredictor.create(source)\n            : await TabularPredictor.create(source, {\n                  providers: options.providers,\n                  warmup: options.warmup,\n                  sessionOptions: options.sessionOptions,\n              });\n\n    const classes = manifest.output.classes;\n    return {\n        manifest,\n        predictor,\n        runtime,\n        featureNames: manifest.input.feature_names,\n        classes,\n        explain: (probabilities: readonly number[]) =>\n            probabilities\n                .map((score, index) => ({\n                    name: classes[index] ?? String(index),\n                    score,\n                }))\n                .sort((a, b) => b.score - a.score),\n    };\n}\n\n/**\n * Decide which reader serves this package.\n *\n * @param manifest The package manifest.\n * @param requested What the caller asked for.\n * @returns The runtime to use.\n * @throws {@link ModelFetchError} when the package does not carry the\n *   requested form — asking for a compact model that was never written\n *   should say so, not silently download 25 MB of WebAssembly instead.\n */\nfunction chooseRuntime(manifest: EdgeManifest, requested: TabularRuntime | \"auto\"): TabularRuntime {\n    const available = manifest.runtimes ?? [];\n    const hasCompact = available.some((entry) => entry.kind === \"compact\");\n\n    if (requested === \"auto\") return hasCompact ? \"compact\" : \"onnx\";\n    if (requested === \"compact\" && !hasCompact) {\n        throw new ModelFetchError(\n            `This package carries no compact model (${manifest.name} lists ` +\n                `${available.map((entry) => entry.kind).join(\", \") || \"onnx\"}). ` +\n                \"Re-export it with edge_pipeline(compact=True), or load it as ONNX.\",\n        );\n    }\n    return requested;\n}\n\n/**\n * Find the file a runtime reads.\n *\n * @param manifest The package manifest.\n * @param runtime The chosen runtime.\n * @returns The filename inside the package directory.\n */\nfunction fileFor(manifest: EdgeManifest, runtime: TabularRuntime): string {\n    const entry = (manifest.runtimes ?? []).find((item) => item.kind === runtime);\n    return entry?.file ?? manifest.model.file;\n}\n\n/**\n * Resolve a directory URL to its manifest file.\n *\n * @param directoryUrl The package directory, or the manifest itself.\n * @returns The manifest URL.\n */\nfunction manifestUrl(directoryUrl: string): string {\n    if (directoryUrl.endsWith(\".json\")) return directoryUrl;\n    return directoryUrl.endsWith(\"/\")\n        ? `${directoryUrl}${MANIFEST_FILENAME}`\n        : `${directoryUrl}/${MANIFEST_FILENAME}`;\n}\n"],"mappings":"qHAyBA,IAAa,EAA4B,EAG5B,EAAoB,gBA8JjC,eAAsB,EAClB,EACA,EACqB,CACrB,IAAM,EAAM,EAAY,CAAY,EAChC,EACJ,GAAI,CACA,EAAW,MAAM,MAAM,EAAK,CAAW,CAC3C,OAAS,EAAO,CACZ,MAAM,IAAI,EAAA,gBAAgB,kCAAkC,IAAO,CAC/D,MAAO,CACX,CAAC,CACL,CACA,GAAI,CAAC,EAAS,GACV,MAAM,IAAI,EAAA,gBACN,kCAAkC,EAAI,IAAI,EAAS,OAAO,GAAG,EAAS,YAC1E,EAGJ,IAAM,EAAY,MAAM,EAAS,KAAK,EACtC,GAAI,OAAO,GAAU,gBAAmB,SACpC,MAAM,IAAI,EAAA,gBAAgB,GAAG,EAAI,sDAAsD,EAE3F,GAAI,EAAS,eAAA,EACT,MAAM,IAAI,EAAA,gBACN,mBAAmB,EAAI,uBAAuB,EAAS,eAAe,qFAG1E,EAEJ,OAAO,CACX,CAoBA,eAAsB,EAClB,EACA,EAAkC,CAAC,EACT,CAC1B,IAAM,EAAW,MAAM,EAAkB,CAAY,EAC/C,EAAO,EAAa,SAAS,GAAG,EAAI,EAAe,GAAG,EAAa,GACnE,EAAU,EAAc,EAAU,EAAQ,SAAW,MAAM,EAE3D,EAAW,GAAG,IADP,EAAQ,EAAU,CACJ,IAErB,EAAQ,EAAQ,OAAS,GACzB,EACF,IAAU,GACJ,EACA,MAAM,EAAA,gBAAgB,EAAU,OAAO,GAAU,SAAW,EAAQ,CAAC,CAAC,EAE1E,EACF,IAAY,UACN,MAAM,EAAA,iBAAiB,OAAO,CAAM,EACpC,MAAM,EAAA,iBAAiB,OAAO,EAAQ,CAClC,UAAW,EAAQ,UACnB,OAAQ,EAAQ,OAChB,eAAgB,EAAQ,cAC5B,CAAC,EAEL,EAAU,EAAS,OAAO,QAChC,MAAO,CACH,WACA,YACA,UACA,aAAc,EAAS,MAAM,cAC7B,UACA,QAAU,GACN,EACK,KAAK,EAAO,KAAW,CACpB,KAAM,EAAQ,IAAU,OAAO,CAAK,EACpC,OACJ,EAAE,CAAC,CACF,MAAM,EAAG,IAAM,EAAE,MAAQ,EAAE,KAAK,CAC7C,CACJ,CAYA,SAAS,EAAc,EAAwB,EAAoD,CAC/F,IAAM,EAAY,EAAS,UAAY,CAAC,EAClC,EAAa,EAAU,KAAM,GAAU,EAAM,OAAS,SAAS,EAErE,GAAI,IAAc,OAAQ,OAAO,EAAa,UAAY,OAC1D,GAAI,IAAc,WAAa,CAAC,EAC5B,MAAM,IAAI,EAAA,gBACN,0CAA0C,EAAS,KAAK,SACjD,EAAU,IAAK,GAAU,EAAM,IAAI,CAAC,CAAC,KAAK,IAAI,GAAK,OAAO,sEAErE,EAEJ,OAAO,CACX,CASA,SAAS,EAAQ,EAAwB,EAAiC,CAEtE,OADe,EAAS,UAAY,CAAC,EAAA,CAAG,KAAM,GAAS,EAAK,OAAS,CAC9D,CAAA,EAAO,MAAQ,EAAS,MAAM,IACzC,CAQA,SAAS,EAAY,EAA8B,CAE/C,OADI,EAAa,SAAS,OAAO,EAAU,EACpC,EAAa,SAAS,GAAG,EAC1B,GAAG,IAAe,IAClB,GAAG,EAAa,GAAG,GAC7B"}

package/dist/tabular/manifest.js

@@ -1,10 +1,11 @@
 import { ModelFetchError as e } from "./exceptions.js";
 import { fetchModelBytes as t } from "./cache.js";
-import { TabularPredictor as n } from "./predictor.js";
+import { CompactPredictor as n } from "./compact.js";
+import { TabularPredictor as r } from "./predictor.js";
 //#region src/tabular/manifest.ts
-var r = 1, i = "manifest.json";
-async function a(t, n) {
-	let r = s(t), i;
+var i = 1, a = "manifest.json";
+async function o(t, n) {
+	let r = u(t), i;
 	try {
 		i = await fetch(r, n);
 	} catch (t) {
@@ -16,27 +17,37 @@ async function a(t, n) {
 	if (a.schema_version > 1) throw new e(`The manifest at ${r} uses schema_version ${a.schema_version}, and this SDK understands 1. Upgrade tempest-react-sdk before serving this package.`);
 	return a;
 }
-async function o(e, r = {}) {
-	let i = await a(e), o = `${e.endsWith("/") ? e : `${e}/`}${i.model.file}`, s = r.cache ?? !0, c = s === !1 ? o : await t(o, typeof s == "object" ? s : {}), l = await n.create(c, {
-		providers: r.providers,
-		warmup: r.warmup,
-		sessionOptions: r.sessionOptions
-	}), u = i.output.classes;
+async function s(e, i = {}) {
+	let a = await o(e), s = e.endsWith("/") ? e : `${e}/`, u = c(a, i.runtime ?? "auto"), d = `${s}${l(a, u)}`, f = i.cache ?? !0, p = f === !1 ? d : await t(d, typeof f == "object" ? f : {}), m = u === "compact" ? await n.create(p) : await r.create(p, {
+		providers: i.providers,
+		warmup: i.warmup,
+		sessionOptions: i.sessionOptions
+	}), h = a.output.classes;
 	return {
-		manifest: i,
-		predictor: l,
-		featureNames: i.input.feature_names,
-		classes: u,
+		manifest: a,
+		predictor: m,
+		runtime: u,
+		featureNames: a.input.feature_names,
+		classes: h,
 		explain: (e) => e.map((e, t) => ({
-			name: u[t] ?? String(t),
+			name: h[t] ?? String(t),
 			score: e
 		})).sort((e, t) => t.score - e.score)
 	};
 }
-function s(e) {
-	return e.endsWith(".json") ? e : e.endsWith("/") ? `${e}${i}` : `${e}/${i}`;
+function c(t, n) {
+	let r = t.runtimes ?? [], i = r.some((e) => e.kind === "compact");
+	if (n === "auto") return i ? "compact" : "onnx";
+	if (n === "compact" && !i) throw new e(`This package carries no compact model (${t.name} lists ${r.map((e) => e.kind).join(", ") || "onnx"}). Re-export it with edge_pipeline(compact=True), or load it as ONNX.`);
+	return n;
+}
+function l(e, t) {
+	return (e.runtimes ?? []).find((e) => e.kind === t)?.file ?? e.model.file;
+}
+function u(e) {
+	return e.endsWith(".json") ? e : e.endsWith("/") ? `${e}${a}` : `${e}/${a}`;
 }
 //#endregion
-export { i as MANIFEST_FILENAME, r as SUPPORTED_MANIFEST_SCHEMA, a as fetchEdgeManifest, o as loadEdgePackage };
+export { a as MANIFEST_FILENAME, i as SUPPORTED_MANIFEST_SCHEMA, o as fetchEdgeManifest, s as loadEdgePackage };
 
 //# sourceMappingURL=manifest.js.map

package/dist/tabular/manifest.js.map

@@ -1 +1 @@
-{"version":3,"file":"manifest.js","names":[],"sources":["../../src/tabular/manifest.ts"],"sourcesContent":["/**\n * Reading an edge package published by `tempest-fastapi-sdk`.\n *\n * `edge_pipeline` writes a directory — the graph, a gzipped copy, a drift\n * baseline and a `manifest.json` — and the browser is one of its two\n * intended consumers. The manifest is what turns a `.onnx` URL into\n * something a UI can use: the **column order** the model was trained on,\n * the class names behind `probabilities[2]`, and a version to compare\n * against what is already cached.\n *\n * That column order is the field worth loading a manifest for. A model fed\n * the right features in the wrong order answers confidently and wrongly,\n * and no runtime check catches it.\n *\n * The contract is pinned by `schema_version`. Unknown fields are ignored\n * rather than rejected, so a package written by a newer SDK still loads.\n */\n\nimport { fetchModelBytes, type ModelCacheOptions } from \"./cache\";\nimport { ModelFetchError } from \"./exceptions\";\nimport { TabularPredictor } from \"./predictor\";\nimport type { TabularPredictorOptions } from \"./types\";\n\n/** Manifest schema version this reader was written against. */\nexport const SUPPORTED_MANIFEST_SCHEMA = 1;\n\n/** Fixed filename inside a package directory. */\nexport const MANIFEST_FILENAME = \"manifest.json\";\n\n/** The graph file and how to check you got it whole. */\nexport interface ManifestModelFile {\n    readonly file: string;\n    readonly sha256: string;\n    readonly bytes: number;\n    readonly gzip_file: string | null;\n    readonly gzip_bytes: number | null;\n    readonly opset: number;\n    readonly dtype: string;\n}\n\n/** What the graph expects per row. */\nexport interface ManifestInput {\n    readonly name: string;\n    readonly features: number;\n    /** Column order used at training time. */\n    readonly feature_names: readonly string[];\n}\n\n/** What the graph answers. */\nexport interface ManifestOutput {\n    readonly is_classifier: boolean;\n    readonly label_output: string;\n    readonly probability_output: string | null;\n    /** Class labels in score-column order. */\n    readonly classes: readonly string[];\n}\n\n/** The package manifest, as written by `edge_pipeline`. */\nexport interface EdgeManifest {\n    readonly schema_version: number;\n    readonly name: string;\n    readonly version: string;\n    readonly created_at: string;\n    readonly sdk_version: string;\n    readonly estimator: string;\n    readonly model: ManifestModelFile;\n    readonly input: ManifestInput;\n    readonly output: ManifestOutput;\n    readonly verified: boolean | null;\n    readonly baseline_file: string | null;\n    readonly baseline_samples: number;\n}\n\n/** A package loaded and ready to answer. */\nexport interface LoadedEdgePackage {\n    /** What was published. */\n    readonly manifest: EdgeManifest;\n    /** The running model. */\n    readonly predictor: TabularPredictor;\n    /** Column order the rows must follow. */\n    readonly featureNames: readonly string[];\n    /** Class names behind each probability column. */\n    readonly classes: readonly string[];\n    /**\n     * Map a prediction's scores onto class names.\n     *\n     * @param probabilities One row of scores.\n     * @returns Name/score pairs, highest first.\n     */\n    readonly explain: (probabilities: readonly number[]) => { name: string; score: number }[];\n}\n\n/** Options for {@link loadEdgePackage}. */\nexport interface LoadEdgePackageOptions extends TabularPredictorOptions {\n    /** Cache the model bytes for offline use. `true` by default. */\n    readonly cache?: boolean | ModelCacheOptions;\n}\n\n/**\n * Read a package's manifest.\n *\n * Cheap: it is a few hundred bytes, so an app can check for a new version\n * without downloading a model it may already have.\n *\n * @example\n * ```ts\n * const manifest = await fetchEdgeManifest(\"/models/risk/\");\n * if (manifest.version !== localStorage.getItem(\"risk-version\")) {\n *     // a new model was published\n * }\n * ```\n *\n * @param directoryUrl URL of the package directory, with or without a\n *   trailing slash. A full URL to the manifest file also works.\n * @param requestInit `fetch` options.\n * @returns The parsed manifest.\n * @throws {@link ModelFetchError} when the manifest cannot be read, or when\n *   its `schema_version` is newer than this reader understands — loading it\n *   anyway would risk misreading the field that defines column order.\n */\nexport async function fetchEdgeManifest(\n    directoryUrl: string,\n    requestInit?: RequestInit,\n): Promise<EdgeManifest> {\n    const url = manifestUrl(directoryUrl);\n    let response: Response;\n    try {\n        response = await fetch(url, requestInit);\n    } catch (error) {\n        throw new ModelFetchError(`Could not read the manifest at ${url}`, {\n            cause: error,\n        });\n    }\n    if (!response.ok) {\n        throw new ModelFetchError(\n            `Could not read the manifest at ${url}: ${response.status} ${response.statusText}`,\n        );\n    }\n\n    const manifest = (await response.json()) as EdgeManifest;\n    if (typeof manifest?.schema_version !== \"number\") {\n        throw new ModelFetchError(`${url} is not an edge package manifest (no schema_version).`);\n    }\n    if (manifest.schema_version > SUPPORTED_MANIFEST_SCHEMA) {\n        throw new ModelFetchError(\n            `The manifest at ${url} uses schema_version ${manifest.schema_version}, ` +\n                `and this SDK understands ${SUPPORTED_MANIFEST_SCHEMA}. Upgrade ` +\n                \"tempest-react-sdk before serving this package.\",\n        );\n    }\n    return manifest;\n}\n\n/**\n * Load a whole edge package: manifest, model, and the names to read it by.\n *\n * @example\n * ```ts\n * const pkg = await loadEdgePackage(\"/models/risk/\");\n *\n * console.log(pkg.featureNames); // [\"age\", \"income\", \"tenure\", \"score\", \"visits\"]\n *\n * const { probabilities } = await pkg.predictor.predict([[41, 5200, 3, 0.82, 12]]);\n * console.log(pkg.explain(probabilities[0]!)); // [{ name: \"approved\", score: 0.91 }, ...]\n * ```\n *\n * @param directoryUrl URL of the package directory.\n * @param options Predictor options plus caching.\n * @returns The loaded package.\n * @throws {@link ModelFetchError} when the manifest or model cannot be read.\n */\nexport async function loadEdgePackage(\n    directoryUrl: string,\n    options: LoadEdgePackageOptions = {},\n): Promise<LoadedEdgePackage> {\n    const manifest = await fetchEdgeManifest(directoryUrl);\n    const base = directoryUrl.endsWith(\"/\") ? directoryUrl : `${directoryUrl}/`;\n    const modelUrl = `${base}${manifest.model.file}`;\n\n    const cache = options.cache ?? true;\n    const source =\n        cache === false\n            ? modelUrl\n            : await fetchModelBytes(modelUrl, typeof cache === \"object\" ? cache : {});\n\n    const predictor = await TabularPredictor.create(source, {\n        providers: options.providers,\n        warmup: options.warmup,\n        sessionOptions: options.sessionOptions,\n    });\n\n    const classes = manifest.output.classes;\n    return {\n        manifest,\n        predictor,\n        featureNames: manifest.input.feature_names,\n        classes,\n        explain: (probabilities: readonly number[]) =>\n            probabilities\n                .map((score, index) => ({\n                    name: classes[index] ?? String(index),\n                    score,\n                }))\n                .sort((a, b) => b.score - a.score),\n    };\n}\n\n/**\n * Resolve a directory URL to its manifest file.\n *\n * @param directoryUrl The package directory, or the manifest itself.\n * @returns The manifest URL.\n */\nfunction manifestUrl(directoryUrl: string): string {\n    if (directoryUrl.endsWith(\".json\")) return directoryUrl;\n    return directoryUrl.endsWith(\"/\")\n        ? `${directoryUrl}${MANIFEST_FILENAME}`\n        : `${directoryUrl}/${MANIFEST_FILENAME}`;\n}\n"],"mappings":";;;;AAwBA,IAAa,IAA4B,GAG5B,IAAoB;AA6FjC,eAAsB,EAClB,GACA,GACqB;CACrB,IAAM,IAAM,EAAY,CAAY,GAChC;CACJ,IAAI;EACA,IAAW,MAAM,MAAM,GAAK,CAAW;CAC3C,SAAS,GAAO;EACZ,MAAM,IAAI,EAAgB,kCAAkC,KAAO,EAC/D,OAAO,EACX,CAAC;CACL;CACA,IAAI,CAAC,EAAS,IACV,MAAM,IAAI,EACN,kCAAkC,EAAI,IAAI,EAAS,OAAO,GAAG,EAAS,YAC1E;CAGJ,IAAM,IAAY,MAAM,EAAS,KAAK;CACtC,IAAI,OAAO,GAAU,kBAAmB,UACpC,MAAM,IAAI,EAAgB,GAAG,EAAI,sDAAsD;CAE3F,IAAI,EAAS,iBAAA,GACT,MAAM,IAAI,EACN,mBAAmB,EAAI,uBAAuB,EAAS,eAAe,qFAG1E;CAEJ,OAAO;AACX;AAoBA,eAAsB,EAClB,GACA,IAAkC,CAAC,GACT;CAC1B,IAAM,IAAW,MAAM,EAAkB,CAAY,GAE/C,IAAW,GADJ,EAAa,SAAS,GAAG,IAAI,IAAe,GAAG,EAAa,KAC9C,EAAS,MAAM,QAEpC,IAAQ,EAAQ,SAAS,IACzB,IACF,MAAU,KACJ,IACA,MAAM,EAAgB,GAAU,OAAO,KAAU,WAAW,IAAQ,CAAC,CAAC,GAE1E,IAAY,MAAM,EAAiB,OAAO,GAAQ;EACpD,WAAW,EAAQ;EACnB,QAAQ,EAAQ;EAChB,gBAAgB,EAAQ;CAC5B,CAAC,GAEK,IAAU,EAAS,OAAO;CAChC,OAAO;EACH;EACA;EACA,cAAc,EAAS,MAAM;EAC7B;EACA,UAAU,MACN,EACK,KAAK,GAAO,OAAW;GACpB,MAAM,EAAQ,MAAU,OAAO,CAAK;GACpC;EACJ,EAAE,CAAC,CACF,MAAM,GAAG,MAAM,EAAE,QAAQ,EAAE,KAAK;CAC7C;AACJ;AAQA,SAAS,EAAY,GAA8B;CAE/C,OADI,EAAa,SAAS,OAAO,IAAU,IACpC,EAAa,SAAS,GAAG,IAC1B,GAAG,IAAe,MAClB,GAAG,EAAa,GAAG;AAC7B"}
+{"version":3,"file":"manifest.js","names":[],"sources":["../../src/tabular/manifest.ts"],"sourcesContent":["/**\n * Reading an edge package published by `tempest-fastapi-sdk`.\n *\n * `edge_pipeline` writes a directory — the graph, a gzipped copy, a drift\n * baseline and a `manifest.json` — and the browser is one of its two\n * intended consumers. The manifest is what turns a `.onnx` URL into\n * something a UI can use: the **column order** the model was trained on,\n * the class names behind `probabilities[2]`, and a version to compare\n * against what is already cached.\n *\n * That column order is the field worth loading a manifest for. A model fed\n * the right features in the wrong order answers confidently and wrongly,\n * and no runtime check catches it.\n *\n * The contract is pinned by `schema_version`. Unknown fields are ignored\n * rather than rejected, so a package written by a newer SDK still loads.\n */\n\nimport { fetchModelBytes, type ModelCacheOptions } from \"./cache\";\nimport { CompactPredictor } from \"./compact\";\nimport { ModelFetchError } from \"./exceptions\";\nimport { TabularPredictor } from \"./predictor\";\nimport type { FeatureRow, TabularPrediction, TabularPredictorOptions } from \"./types\";\n\n/** Manifest schema version this reader was written against. */\nexport const SUPPORTED_MANIFEST_SCHEMA = 1;\n\n/** Fixed filename inside a package directory. */\nexport const MANIFEST_FILENAME = \"manifest.json\";\n\n/** The graph file and how to check you got it whole. */\nexport interface ManifestModelFile {\n    readonly file: string;\n    readonly sha256: string;\n    readonly bytes: number;\n    readonly gzip_file: string | null;\n    readonly gzip_bytes: number | null;\n    readonly opset: number;\n    readonly dtype: string;\n}\n\n/** What the graph expects per row. */\nexport interface ManifestInput {\n    readonly name: string;\n    readonly features: number;\n    /** Column order used at training time. */\n    readonly feature_names: readonly string[];\n}\n\n/** What the graph answers. */\nexport interface ManifestOutput {\n    readonly is_classifier: boolean;\n    readonly label_output: string;\n    readonly probability_output: string | null;\n    /** Class labels in score-column order. */\n    readonly classes: readonly string[];\n}\n\n/**\n * Where the packaged model came from, when it came from an existing\n * artifact.\n *\n * Present when the package was built with `edge_pipeline_from_pickle`: the\n * `.pkl` never reaches the browser (a pickle is a Python program, not\n * data), but its name and digest travel in the manifest, so a model\n * answering in a tab can be traced back to the file that produced it.\n */\nexport interface ManifestSource {\n    readonly file: string;\n    readonly kind: string;\n    readonly sha256: string;\n    readonly bytes: number;\n    readonly sklearn_version: string;\n    readonly warnings: readonly string[];\n}\n\n/**\n * One file in the package a runtime can load.\n *\n * A package may carry the same model twice — as ONNX, which any runtime\n * reads at the cost of a 25.6 MB WebAssembly download, and as the compact\n * format, which needs no runtime. The list is what lets the browser pick\n * by what it already ships.\n */\nexport interface ManifestRuntime {\n    readonly kind: \"onnx\" | \"compact\" | string;\n    readonly file: string;\n    readonly bytes: number;\n    readonly gzip_file: string | null;\n    readonly gzip_bytes: number | null;\n    readonly sha256: string;\n}\n\n/** The package manifest, as written by `edge_pipeline`. */\nexport interface EdgeManifest {\n    readonly schema_version: number;\n    readonly name: string;\n    readonly version: string;\n    readonly created_at: string;\n    readonly sdk_version: string;\n    readonly estimator: string;\n    readonly model: ManifestModelFile;\n    readonly input: ManifestInput;\n    readonly output: ManifestOutput;\n    readonly verified: boolean | null;\n    /** Every file a runtime can load. Absent on packages written before v0.194. */\n    readonly runtimes?: readonly ManifestRuntime[];\n    /** Absent on packages built straight from a fitted estimator. */\n    readonly source?: ManifestSource;\n    readonly baseline_file: string | null;\n    readonly baseline_samples: number;\n}\n\n/** Which reader served the package. */\nexport type TabularRuntime = \"onnx\" | \"compact\";\n\n/** A package loaded and ready to answer. */\nexport interface LoadedEdgePackage {\n    /** What was published. */\n    readonly manifest: EdgeManifest;\n    /** The running model, whichever runtime read it. */\n    readonly predictor: PredictorLike;\n    /** Which reader was used. */\n    readonly runtime: TabularRuntime;\n    /** Column order the rows must follow. */\n    readonly featureNames: readonly string[];\n    /** Class names behind each probability column. */\n    readonly classes: readonly string[];\n    /**\n     * Map a prediction's scores onto class names.\n     *\n     * @param probabilities One row of scores.\n     * @returns Name/score pairs, highest first.\n     */\n    readonly explain: (probabilities: readonly number[]) => { name: string; score: number }[];\n}\n\n/**\n * The shape both readers share.\n *\n * `TabularPredictor` (ONNX) and `CompactPredictor` (runtime-free) answer\n * with the same object, so an app can switch routes without touching a\n * line of its own code.\n */\nexport interface PredictorLike {\n    predict(rows: readonly FeatureRow[]): Promise<TabularPrediction>;\n    dispose(): Promise<void>;\n}\n\n/** Options for {@link loadEdgePackage}. */\nexport interface LoadEdgePackageOptions extends TabularPredictorOptions {\n    /** Cache the model bytes for offline use. `true` by default. */\n    readonly cache?: boolean | ModelCacheOptions;\n    /**\n     * Which reader to use.\n     *\n     * `\"auto\"` (the default) takes the compact form when the package has\n     * one, because it answers without downloading a WebAssembly runtime.\n     * Force `\"onnx\"` when the app already ships ONNX for something else —\n     * then the runtime is already paid for and ONNX covers more estimators.\n     */\n    readonly runtime?: TabularRuntime | \"auto\";\n}\n\n/**\n * Read a package's manifest.\n *\n * Cheap: it is a few hundred bytes, so an app can check for a new version\n * without downloading a model it may already have.\n *\n * @example\n * ```ts\n * const manifest = await fetchEdgeManifest(\"/models/risk/\");\n * if (manifest.version !== localStorage.getItem(\"risk-version\")) {\n *     // a new model was published\n * }\n * ```\n *\n * @param directoryUrl URL of the package directory, with or without a\n *   trailing slash. A full URL to the manifest file also works.\n * @param requestInit `fetch` options.\n * @returns The parsed manifest.\n * @throws {@link ModelFetchError} when the manifest cannot be read, or when\n *   its `schema_version` is newer than this reader understands — loading it\n *   anyway would risk misreading the field that defines column order.\n */\nexport async function fetchEdgeManifest(\n    directoryUrl: string,\n    requestInit?: RequestInit,\n): Promise<EdgeManifest> {\n    const url = manifestUrl(directoryUrl);\n    let response: Response;\n    try {\n        response = await fetch(url, requestInit);\n    } catch (error) {\n        throw new ModelFetchError(`Could not read the manifest at ${url}`, {\n            cause: error,\n        });\n    }\n    if (!response.ok) {\n        throw new ModelFetchError(\n            `Could not read the manifest at ${url}: ${response.status} ${response.statusText}`,\n        );\n    }\n\n    const manifest = (await response.json()) as EdgeManifest;\n    if (typeof manifest?.schema_version !== \"number\") {\n        throw new ModelFetchError(`${url} is not an edge package manifest (no schema_version).`);\n    }\n    if (manifest.schema_version > SUPPORTED_MANIFEST_SCHEMA) {\n        throw new ModelFetchError(\n            `The manifest at ${url} uses schema_version ${manifest.schema_version}, ` +\n                `and this SDK understands ${SUPPORTED_MANIFEST_SCHEMA}. Upgrade ` +\n                \"tempest-react-sdk before serving this package.\",\n        );\n    }\n    return manifest;\n}\n\n/**\n * Load a whole edge package: manifest, model, and the names to read it by.\n *\n * @example\n * ```ts\n * const pkg = await loadEdgePackage(\"/models/risk/\");\n *\n * console.log(pkg.featureNames); // [\"age\", \"income\", \"tenure\", \"score\", \"visits\"]\n *\n * const { probabilities } = await pkg.predictor.predict([[41, 5200, 3, 0.82, 12]]);\n * console.log(pkg.explain(probabilities[0]!)); // [{ name: \"approved\", score: 0.91 }, ...]\n * ```\n *\n * @param directoryUrl URL of the package directory.\n * @param options Predictor options plus caching.\n * @returns The loaded package.\n * @throws {@link ModelFetchError} when the manifest or model cannot be read.\n */\nexport async function loadEdgePackage(\n    directoryUrl: string,\n    options: LoadEdgePackageOptions = {},\n): Promise<LoadedEdgePackage> {\n    const manifest = await fetchEdgeManifest(directoryUrl);\n    const base = directoryUrl.endsWith(\"/\") ? directoryUrl : `${directoryUrl}/`;\n    const runtime = chooseRuntime(manifest, options.runtime ?? \"auto\");\n    const file = fileFor(manifest, runtime);\n    const modelUrl = `${base}${file}`;\n\n    const cache = options.cache ?? true;\n    const source =\n        cache === false\n            ? modelUrl\n            : await fetchModelBytes(modelUrl, typeof cache === \"object\" ? cache : {});\n\n    const predictor: PredictorLike =\n        runtime === \"compact\"\n            ? await CompactPredictor.create(source)\n            : await TabularPredictor.create(source, {\n                  providers: options.providers,\n                  warmup: options.warmup,\n                  sessionOptions: options.sessionOptions,\n              });\n\n    const classes = manifest.output.classes;\n    return {\n        manifest,\n        predictor,\n        runtime,\n        featureNames: manifest.input.feature_names,\n        classes,\n        explain: (probabilities: readonly number[]) =>\n            probabilities\n                .map((score, index) => ({\n                    name: classes[index] ?? String(index),\n                    score,\n                }))\n                .sort((a, b) => b.score - a.score),\n    };\n}\n\n/**\n * Decide which reader serves this package.\n *\n * @param manifest The package manifest.\n * @param requested What the caller asked for.\n * @returns The runtime to use.\n * @throws {@link ModelFetchError} when the package does not carry the\n *   requested form — asking for a compact model that was never written\n *   should say so, not silently download 25 MB of WebAssembly instead.\n */\nfunction chooseRuntime(manifest: EdgeManifest, requested: TabularRuntime | \"auto\"): TabularRuntime {\n    const available = manifest.runtimes ?? [];\n    const hasCompact = available.some((entry) => entry.kind === \"compact\");\n\n    if (requested === \"auto\") return hasCompact ? \"compact\" : \"onnx\";\n    if (requested === \"compact\" && !hasCompact) {\n        throw new ModelFetchError(\n            `This package carries no compact model (${manifest.name} lists ` +\n                `${available.map((entry) => entry.kind).join(\", \") || \"onnx\"}). ` +\n                \"Re-export it with edge_pipeline(compact=True), or load it as ONNX.\",\n        );\n    }\n    return requested;\n}\n\n/**\n * Find the file a runtime reads.\n *\n * @param manifest The package manifest.\n * @param runtime The chosen runtime.\n * @returns The filename inside the package directory.\n */\nfunction fileFor(manifest: EdgeManifest, runtime: TabularRuntime): string {\n    const entry = (manifest.runtimes ?? []).find((item) => item.kind === runtime);\n    return entry?.file ?? manifest.model.file;\n}\n\n/**\n * Resolve a directory URL to its manifest file.\n *\n * @param directoryUrl The package directory, or the manifest itself.\n * @returns The manifest URL.\n */\nfunction manifestUrl(directoryUrl: string): string {\n    if (directoryUrl.endsWith(\".json\")) return directoryUrl;\n    return directoryUrl.endsWith(\"/\")\n        ? `${directoryUrl}${MANIFEST_FILENAME}`\n        : `${directoryUrl}/${MANIFEST_FILENAME}`;\n}\n"],"mappings":";;;;;AAyBA,IAAa,IAA4B,GAG5B,IAAoB;AA8JjC,eAAsB,EAClB,GACA,GACqB;CACrB,IAAM,IAAM,EAAY,CAAY,GAChC;CACJ,IAAI;EACA,IAAW,MAAM,MAAM,GAAK,CAAW;CAC3C,SAAS,GAAO;EACZ,MAAM,IAAI,EAAgB,kCAAkC,KAAO,EAC/D,OAAO,EACX,CAAC;CACL;CACA,IAAI,CAAC,EAAS,IACV,MAAM,IAAI,EACN,kCAAkC,EAAI,IAAI,EAAS,OAAO,GAAG,EAAS,YAC1E;CAGJ,IAAM,IAAY,MAAM,EAAS,KAAK;CACtC,IAAI,OAAO,GAAU,kBAAmB,UACpC,MAAM,IAAI,EAAgB,GAAG,EAAI,sDAAsD;CAE3F,IAAI,EAAS,iBAAA,GACT,MAAM,IAAI,EACN,mBAAmB,EAAI,uBAAuB,EAAS,eAAe,qFAG1E;CAEJ,OAAO;AACX;AAoBA,eAAsB,EAClB,GACA,IAAkC,CAAC,GACT;CAC1B,IAAM,IAAW,MAAM,EAAkB,CAAY,GAC/C,IAAO,EAAa,SAAS,GAAG,IAAI,IAAe,GAAG,EAAa,IACnE,IAAU,EAAc,GAAU,EAAQ,WAAW,MAAM,GAE3D,IAAW,GAAG,IADP,EAAQ,GAAU,CACJ,KAErB,IAAQ,EAAQ,SAAS,IACzB,IACF,MAAU,KACJ,IACA,MAAM,EAAgB,GAAU,OAAO,KAAU,WAAW,IAAQ,CAAC,CAAC,GAE1E,IACF,MAAY,YACN,MAAM,EAAiB,OAAO,CAAM,IACpC,MAAM,EAAiB,OAAO,GAAQ;EAClC,WAAW,EAAQ;EACnB,QAAQ,EAAQ;EAChB,gBAAgB,EAAQ;CAC5B,CAAC,GAEL,IAAU,EAAS,OAAO;CAChC,OAAO;EACH;EACA;EACA;EACA,cAAc,EAAS,MAAM;EAC7B;EACA,UAAU,MACN,EACK,KAAK,GAAO,OAAW;GACpB,MAAM,EAAQ,MAAU,OAAO,CAAK;GACpC;EACJ,EAAE,CAAC,CACF,MAAM,GAAG,MAAM,EAAE,QAAQ,EAAE,KAAK;CAC7C;AACJ;AAYA,SAAS,EAAc,GAAwB,GAAoD;CAC/F,IAAM,IAAY,EAAS,YAAY,CAAC,GAClC,IAAa,EAAU,MAAM,MAAU,EAAM,SAAS,SAAS;CAErE,IAAI,MAAc,QAAQ,OAAO,IAAa,YAAY;CAC1D,IAAI,MAAc,aAAa,CAAC,GAC5B,MAAM,IAAI,EACN,0CAA0C,EAAS,KAAK,SACjD,EAAU,KAAK,MAAU,EAAM,IAAI,CAAC,CAAC,KAAK,IAAI,KAAK,OAAO,sEAErE;CAEJ,OAAO;AACX;AASA,SAAS,EAAQ,GAAwB,GAAiC;CAEtE,QADe,EAAS,YAAY,CAAC,EAAA,CAAG,MAAM,MAAS,EAAK,SAAS,CAC9D,CAAA,EAAO,QAAQ,EAAS,MAAM;AACzC;AAQA,SAAS,EAAY,GAA8B;CAE/C,OADI,EAAa,SAAS,OAAO,IAAU,IACpC,EAAa,SAAS,GAAG,IAC1B,GAAG,IAAe,MAClB,GAAG,EAAa,GAAG;AAC7B"}

package/dist/tabular.cjs

@@ -1 +1 @@
-Object.defineProperty(exports,Symbol.toStringTag,{value:`Module`});const e=require("./tabular/assets.cjs"),t=require("./tabular/exceptions.cjs"),n=require("./tabular/cache.cjs"),r=require("./tabular/predictor.cjs"),i=require("./tabular/manifest.cjs"),a=require("./tabular/use-tabular-predictor.cjs");exports.DEFAULT_MODEL_CACHE=n.DEFAULT_MODEL_CACHE,exports.DEFAULT_TABULAR_PROVIDERS=r.DEFAULT_TABULAR_PROVIDERS,exports.FeatureShapeError=t.FeatureShapeError,exports.InferenceError=t.InferenceError,exports.MANIFEST_FILENAME=i.MANIFEST_FILENAME,exports.ModelFetchError=t.ModelFetchError,exports.ModelLoadError=t.ModelLoadError,exports.ORT_WASM_ASSETS=e.ORT_WASM_ASSETS,exports.SUPPORTED_MANIFEST_SCHEMA=i.SUPPORTED_MANIFEST_SCHEMA,exports.TabularError=t.TabularError,exports.TabularPredictor=r.TabularPredictor,exports.UnsupportedGraphError=t.UnsupportedGraphError,exports.cacheModelBytes=n.cacheModelBytes,exports.clearModelCache=n.clearModelCache,exports.configureOrtAssets=e.configureOrtAssets,exports.fetchEdgeManifest=i.fetchEdgeManifest,exports.fetchModelBytes=n.fetchModelBytes,exports.isModelCached=n.isModelCached,exports.loadEdgePackage=i.loadEdgePackage,exports.ortAssetUrls=e.ortAssetUrls,exports.useTabularPredictor=a.useTabularPredictor;
+Object.defineProperty(exports,Symbol.toStringTag,{value:`Module`});const e=require("./tabular/assets.cjs"),t=require("./tabular/exceptions.cjs"),n=require("./tabular/cache.cjs"),r=require("./tabular/compact.cjs"),i=require("./tabular/predictor.cjs"),a=require("./tabular/manifest.cjs"),o=require("./tabular/use-tabular-predictor.cjs");exports.CompactFormatError=t.CompactFormatError,exports.CompactPredictor=r.CompactPredictor,exports.DEFAULT_MODEL_CACHE=n.DEFAULT_MODEL_CACHE,exports.DEFAULT_TABULAR_PROVIDERS=i.DEFAULT_TABULAR_PROVIDERS,exports.FeatureShapeError=t.FeatureShapeError,exports.InferenceError=t.InferenceError,exports.MANIFEST_FILENAME=a.MANIFEST_FILENAME,exports.ModelFetchError=t.ModelFetchError,exports.ModelLoadError=t.ModelLoadError,exports.ORT_WASM_ASSETS=e.ORT_WASM_ASSETS,exports.SUPPORTED_COMPACT_SCHEMA=r.SUPPORTED_COMPACT_SCHEMA,exports.SUPPORTED_MANIFEST_SCHEMA=a.SUPPORTED_MANIFEST_SCHEMA,exports.TabularError=t.TabularError,exports.TabularPredictor=i.TabularPredictor,exports.UnsupportedGraphError=t.UnsupportedGraphError,exports.cacheModelBytes=n.cacheModelBytes,exports.clearModelCache=n.clearModelCache,exports.configureOrtAssets=e.configureOrtAssets,exports.fetchEdgeManifest=a.fetchEdgeManifest,exports.fetchModelBytes=n.fetchModelBytes,exports.isModelCached=n.isModelCached,exports.loadEdgePackage=a.loadEdgePackage,exports.ortAssetUrls=e.ortAssetUrls,exports.useTabularPredictor=o.useTabularPredictor;