@barivia/barsom-mcp 0.9.0 → 0.10.0

package/dist/shared.js

@@ -19,7 +19,7 @@ export const RETRYABLE_STATUS = new Set([502, 503, 504]);
  * X-Barsom-Client-Version so the server can annotate tool guidance with the
  * wrapper version each action requires. Keep in sync with package.json on bump.
  */
-export const CLIENT_VERSION = "0.9.0";
+export const CLIENT_VERSION = "0.10.0";
 /** User-facing links; keep aligned with barivia.se / api.barivia.se. */
 export const PUBLIC_SITE_ORIGIN = "https://barivia.se";
 /** Poll window for datasets(add_expression) / derive jobs (server-side work can exceed 30s). */

package/dist/tools/jobs.js

@@ -8,6 +8,7 @@ export const JOBS_DESCRIPTION_BASE = `Manage and inspect jobs.
 | list | Finding job IDs, checking what is pending/completed, reviewing hyperparameters. Response includes job_type (train_map, report, recolor, project, transition_flow, compare, predict, impute_column, annotated_dataset, reduce_spectral) to filter or display. |
 | compare | Picking the best training run from a set of completed jobs |
 | train_map | Submitting a new map training job — returns job_id for polling |
+| train_impute | Sparse training data: train a map AND impute missing cells in one job (accelerated missSOM) — returns map + imputed.csv |
 | train_siom_map | Submitting a self-interacting map training job — same map flow with SIOM coverage control |
 | train_floop_siom | Submitting a FLooP-SIOM job (growing manifold; default topology=free / CHL) — requires Premium or Enterprise plan (all_algorithms) |
 | train_floop_chain | Deprecated alias for train_floop_siom — same behavior; prefer train_floop_siom |
@@ -31,6 +32,7 @@ ESCALATION (action=status):
   - NaN error: user must clean the dataset
 
 action=train_map / train_siom_map: Submits a grid-map training job. Returns job_id — poll with jobs(action=status, job_id=...).
+action=train_impute: Submits missing-tolerant map training on a dataset with holes in the feature matrix. Use when many cells are missing across training columns; use inference(impute_column) instead when you already have a complete-case map and need to fill one held-out column. Plain numeric columns only (no cyclic/temporal/categorical). Returns map artifacts plus imputed.csv (dense matrix). Same grid/epochs/backend params as train_map.
   Presets: quick | standard | refined | high_res — use preset=... for grid/epochs/batch defaults; call training_guidance for details.
   Presets refined/high_res may use GPU. On CPU-only hosts pass backend=cpu. API expects strings "cpu" | "gpu" | "gpu_graphs" (no colon). Future backends (e.g. non-CUDA) may be added under the same contract.
   normalize: "auto" (default) = scale only non-cyclic features; "all" = scale every feature. Use "auto" when using cyclic_features.
@@ -224,7 +226,7 @@ export function buildTrainMapParams(args, presets) {
 export function registerJobsTool(server, description) {
     server.tool("jobs", description, {
         action: z
-            .enum(["status", "list", "compare", "cancel", "delete", "train_map", "train_siom_map", "train_floop_siom", "train_floop_chain", "batch_predict", "run_baseline_study"])
+            .enum(["status", "list", "compare", "cancel", "delete", "train_map", "train_impute", "train_siom_map", "train_floop_siom", "train_floop_chain", "batch_predict", "run_baseline_study"])
             .describe("status: check progress; list: see all jobs; compare: metrics table; cancel: stop job; delete: remove job + files; train_map: submit standard map training; train_siom_map: submit SIOM map training; train_floop_siom: submit FLooP-SIOM (preferred); train_floop_chain: deprecated alias for train_floop_siom; batch_predict: submit multiple predict jobs at once; run_baseline_study: auto-configure and train a baseline SOM"),
         job_id: z
             .string()
@@ -306,6 +308,8 @@ export function registerJobsTool(server, description) {
         output_dpi: z.enum(["standard", "retina", "print"]).optional().default("retina"),
         colormap: z.string().optional(),
         row_range: z.tuple([z.number().int().min(1), z.number().int().min(1)]).optional(),
+        cv_folds: z.number().int().min(0).max(20).optional()
+            .describe("train_impute only: held-out MAE/RMSE/R2 per column (0=off, 2..20) → quality.csv"),
         gamma: z.preprocess((v) => (v !== undefined && v !== null && typeof v === "string") ? parseFloat(v) : v, z.number().optional()),
         gamma_f: z.preprocess((v) => (v !== undefined && v !== null && typeof v === "string") ? parseFloat(v) : v, z.number().optional()),
         siom_decay: z.preprocess((v) => (v !== undefined && v !== null && typeof v === "string") ? parseFloat(v) : v, z.number().optional()),
@@ -361,8 +365,8 @@ export function registerJobsTool(server, description) {
             const jid = String(data.id ?? "");
             return { content: [{ type: "text", text: `Baseline study submitted. Job ID: ${jid}\nGrid size: ${side}x${side}\nNormalization: MAD\n\nPoll with jobs(action=status, job_id="${jid}") until complete, then retrieve with results(action=get, job_id="${jid}"). Optional: training_monitor(job_id="${jid}") for a visual panel—not required.` }] };
         }
-        if (action === "train_map" || action === "train_siom_map") {
-            const { preset, grid_x, grid_y, epochs, model, periodic, columns, cyclic_features, temporal_features, feature_weights, transforms, auto_log_transforms, time_delay_embeddings, categorical_features, normalize, sigma_f, learning_rate, batch_size, quality_metrics, backend, output_format, output_dpi, colormap, row_range, gamma, gamma_f, siom_decay, siom_penalty, penalty_alpha, reset_per_epoch, siom_feature_geometry, siom_qe_backend, siom_qe_batch_size, label, } = args;
+        if (action === "train_map" || action === "train_siom_map" || action === "train_impute") {
+            const { preset, grid_x, grid_y, epochs, model, periodic, columns, cyclic_features, temporal_features, feature_weights, transforms, auto_log_transforms, time_delay_embeddings, categorical_features, normalize, sigma_f, learning_rate, batch_size, quality_metrics, backend, output_format, output_dpi, colormap, row_range, gamma, gamma_f, siom_decay, siom_penalty, penalty_alpha, reset_per_epoch, siom_feature_geometry, siom_qe_backend, siom_qe_batch_size, label, cv_folds, } = args;
             let PRESETS = {};
             try {
                 PRESETS = await fetchTrainingPresets();
@@ -375,7 +379,7 @@ export function registerJobsTool(server, description) {
                 }
             }
             if (!dataset_id)
-                throw new Error("jobs(train_map) requires dataset_id");
+                throw new Error(`jobs(${action}) requires dataset_id`);
             const { params, paramSummary, effectiveGrid } = buildTrainMapParams({
                 preset, grid_x, grid_y, epochs, model, periodic, columns, cyclic_features,
                 temporal_features, feature_weights, transforms, auto_log_transforms,
@@ -383,6 +387,18 @@ export function registerJobsTool(server, description) {
                 normalize, sigma_f, learning_rate, batch_size, quality_metrics, backend,
                 output_format, output_dpi, colormap, row_range,
             }, PRESETS);
+            if (action === "train_impute") {
+                params._job_type = "train_impute";
+                if (cv_folds !== undefined)
+                    params.cv_folds = cv_folds;
+                // Plain numeric path only — strip unsupported keys if caller passed them
+                delete params.cyclic_features;
+                delete params.temporal_features;
+                delete params.categorical_features;
+                delete params.transforms;
+                delete params.auto_log_transforms;
+                delete params.time_delay_embeddings;
+            }
             if (action === "train_siom_map") {
                 params._job_type = "train_siom";
                 if (gamma !== undefined)
@@ -415,7 +431,9 @@ export function registerJobsTool(server, description) {
                 submitBody.label = label;
             const data = (await apiCall("POST", "/v1/jobs", submitBody));
             const newJobId = data.id;
-            const variantPrefix = action === "train_siom_map" ? "variant=siom" : "variant=som";
+            const variantPrefix = action === "train_siom_map" ? "variant=siom"
+                : action === "train_impute" ? "variant=train_impute"
+                    : "variant=som";
             data.effective_params = `${variantPrefix}, ${paramSummary}`;
             try {
                 const sys = (await apiCall("GET", "/v1/system/info"));
@@ -426,7 +444,7 @@ export function registerJobsTool(server, description) {
                 let msg = `Job submitted (${variantPrefix}, ${paramSummary}). `;
                 if (waitMinutes > 1)
                     msg += `You are #${pending + 1} in queue. Estimated wait: ~${waitMinutes} min. `;
-                msg += `Poll with jobs(action=status, job_id="${newJobId}"). When status is completed, use results(action=get, job_id="${newJobId}") to view the map and metrics.`;
+                msg += `Poll with jobs(action=status, job_id="${newJobId}"). When status is completed, use results(action=get, job_id="${newJobId}") to view the map${action === "train_impute" ? " and imputed.csv" : ""} and metrics.`;
                 msg += ` Optional: training_monitor(job_id="${newJobId}") for charts—not required.`;
                 if (effectiveGrid && totalRows > 0 && effectiveGrid[0] * effectiveGrid[1] > totalRows * 0.75) {
                     msg += ` Note: Grid may be large for ${totalRows} rows (consider grid=auto for fewer dead nodes).`;
@@ -434,7 +452,7 @@ export function registerJobsTool(server, description) {
                 data.message = msg;
             }
             catch {
-                let msg = `Job submitted (${variantPrefix}, ${paramSummary}). Poll with jobs(action=status, job_id="${newJobId}"). When status is completed, use results(action=get, job_id="${newJobId}") to view the map and metrics.`;
+                let msg = `Job submitted (${variantPrefix}, ${paramSummary}). Poll with jobs(action=status, job_id="${newJobId}"). When status is completed, use results(action=get, job_id="${newJobId}") to view the map${action === "train_impute" ? " and imputed.csv" : ""} and metrics.`;
                 msg += ` Optional: training_monitor(job_id="${newJobId}") for charts—not required.`;
                 if (effectiveGrid && totalRows > 0 && effectiveGrid[0] * effectiveGrid[1] > totalRows * 0.75) {
                     msg += ` Note: Grid may be large for ${totalRows} rows (consider grid=auto for fewer dead nodes).`;

package/dist/tools/results.js

@@ -393,7 +393,7 @@ NOT FOR: Jobs that haven't completed. Use jobs(action=status) to check first.`,
                             return "";
                         return `Columns not used in training: ${excluded.join(", ")}. You can project them onto this map with inference(action=project_columns, job_id=${job_id}, dataset_id=<dataset_id>, columns=[${excluded.map((c) => `"${c}"`).join(", ")}]) to see how they distribute across the topology. If you ran datasets(action=analyze) before training, any columns it recommended as "project later" are especially good candidates.`;
                     })(),
-                    ...((jobType === "train_som" || jobType === "train_siom") ? ["", `Next: results(action=export, export_type=training_log) for learning curve; results(action=download) to save figures; jobs(action=compare, job_ids=[...]) to compare runs; inference(action=predict) to score new data; inference(action=project_columns) to project other variables onto the map.`] : []),
+                    ...((jobType === "train_som" || jobType === "train_siom" || jobType === "train_impute") ? ["", `Next: results(action=export, export_type=training_log) for learning curve; results(action=download) to save figures${jobType === "train_impute" ? " (includes imputed.csv)" : ""}; jobs(action=compare, job_ids=[...]) to compare runs; inference(action=predict) to score new data; inference(action=project_columns) to project other variables onto the map.`] : []),
                 ].filter((l) => l !== "").join("\n");
                 content.push({ type: "text", text: textSummary });
                 const imagesToFetch = getResultsImagesToFetch(jobType, summary, figures, include_individual);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@barivia/barsom-mcp",
-  "version": "0.9.0",
+  "version": "0.10.0",
   "description": "barSOM MCP proxy — connect any MCP client to the barSOM cloud API for Self-Organizing Map analytics",
   "keywords": [
     "mcp",