@barivia/barsom-mcp 0.22.2 → 0.23.0

package/dist/audit.js

@@ -110,10 +110,12 @@ function stripAuditMeta(result) {
 function errorCodeFrom(err) {
     if (err && typeof err === "object") {
         const e = err;
+        if (e.errorCode)
+            return e.errorCode;
         if (e.httpStatus !== undefined)
             return `http_${e.httpStatus}`;
         const m = e.message ?? "";
-        const codeMatch = m.match(/error_code:\s*(\w+)/);
+        const codeMatch = m.match(/error_code[=:]\s*(\w+)/);
         if (codeMatch)
             return codeMatch[1];
     }

package/dist/deferred_feedback.js

@@ -0,0 +1,88 @@
+/**
+ * Local offline queue for send_feedback when the API or object storage is down.
+ * Persists under ~/.barivia/deferred-feedback (or BARIVIA_FEEDBACK_QUEUE_DIR).
+ * Proxies flush the queue on the next successful feedback submission.
+ */
+import fs from "node:fs/promises";
+import os from "node:os";
+import path from "node:path";
+import { randomUUID } from "node:crypto";
+export function deferredFeedbackQueueDir() {
+    const override = process.env.BARIVIA_FEEDBACK_QUEUE_DIR?.trim();
+    if (override)
+        return path.resolve(override);
+    return path.join(os.homedir(), ".barivia", "deferred-feedback");
+}
+async function ensureQueueDir() {
+    const dir = deferredFeedbackQueueDir();
+    await fs.mkdir(dir, { recursive: true });
+    return dir;
+}
+function entryPath(dir, id) {
+    return path.join(dir, `${id}.json`);
+}
+export async function enqueueDeferredFeedback(product, body, lastError) {
+    const dir = await ensureQueueDir();
+    const id = randomUUID();
+    const entry = {
+        id,
+        product,
+        created_at: new Date().toISOString(),
+        body,
+        ...(lastError ? { last_error: lastError } : {}),
+    };
+    const filePath = entryPath(dir, id);
+    await fs.writeFile(filePath, JSON.stringify(entry, null, 2), "utf8");
+    return { id, path: filePath };
+}
+export async function listDeferredFeedback(product) {
+    const dir = deferredFeedbackQueueDir();
+    let names;
+    try {
+        names = await fs.readdir(dir);
+    }
+    catch (err) {
+        if (err.code === "ENOENT")
+            return [];
+        throw err;
+    }
+    const out = [];
+    for (const name of names) {
+        if (!name.endsWith(".json"))
+            continue;
+        try {
+            const raw = await fs.readFile(path.join(dir, name), "utf8");
+            const entry = JSON.parse(raw);
+            if (product && entry.product !== product)
+                continue;
+            out.push(entry);
+        }
+        catch {
+            /* skip corrupt */
+        }
+    }
+    out.sort((a, b) => a.created_at.localeCompare(b.created_at));
+    return out;
+}
+/**
+ * Attempt to submit each queued entry via `submit`. Successful entries are deleted.
+ * Failures leave the file in place for a later retry.
+ */
+export async function flushDeferredFeedback(product, submit) {
+    const entries = await listDeferredFeedback(product);
+    let flushed = 0;
+    const errors = [];
+    const dir = deferredFeedbackQueueDir();
+    for (const entry of entries) {
+        try {
+            await submit(entry.body);
+            await fs.unlink(entryPath(dir, entry.id)).catch(() => undefined);
+            flushed += 1;
+        }
+        catch (err) {
+            errors.push(err instanceof Error ? err.message : String(err));
+        }
+    }
+    const remaining = (await listDeferredFeedback(product)).length;
+    return { flushed, remaining, errors };
+}

package/dist/index.js

@@ -1,2 +1,2 @@
 #!/usr/bin/env node
-import{McpServer as e}from"@modelcontextprotocol/sdk/server/mcp.js";import{StdioServerTransport as t}from"@modelcontextprotocol/sdk/server/stdio.js";import{z as o}from"zod";import{getUiCapability as r,registerAppResource as s,RESOURCE_MIME_TYPE as n}from"@modelcontextprotocol/ext-apps/server";import{startVizServer as i}from"./viz-server.js";import{API_KEY as a,apiCall as l,apiRawCall as c,loadViewHtml as p,setVizPort as m,setClientSupportsMcpApps as u,CLIENT_VERSION as d}from"./shared.js";import{registerDatasetsTool as f}from"./tools/datasets.js";import{registerTrainTool as g}from"./tools/train.js";import{registerJobsTool as h,JOBS_DESCRIPTION_BASE as _}from"./tools/jobs.js";import{registerResultsTool as b}from"./tools/results.js";import{registerExploreMapTool as w,RESULTS_EXPLORER_URI as y}from"./tools/explore_map.js";import{registerAccountTool as j}from"./tools/account.js";import{registerInferenceTool as v}from"./tools/inference.js";import{registerGuideBarsomTool as x}from"./tools/guide_barsom.js";import{registerTrainingGuidanceTool as P}from"./tools/training_guidance.js";import{registerFeedbackTool as k}from"./tools/feedback.js";import{registerTrainingMonitorTool as I,TRAINING_MONITOR_URI as A}from"./tools/training_monitor.js";import{resolvePrepareTrainingPrompt as M}from"./prepare_training_prompt.js";a||(console.error("Error: BARIVIA_API_KEY not set. Set it in your MCP client config."),process.exit(1));const T=new e({name:"analytics-engine",version:d,instructions:'# Barivia Mapping Analytics Engine\n\nSelf-organizing map (SOM) analytics: project high-dimensional data to a 2D grid for clusters, gradients, and anomalies.\n\n## Workflow (short)\n\nUpload (`datasets(upload)`) → `datasets(preview)` and `datasets(analyze)` before train → submit one of `train(action=map)`, `train(action=siom_map)`, or `train(action=floop_siom)` (only if plan allows FLooP) → poll `jobs(status)` every 10–15s until `completed` → `results(get)` for metrics and figures (there is no separate analyze tool), then `results_explorer(job_id)` to browse the figures interactively. Then `jobs(compare)`, `results(download/recolor)`, or `inference` (predict / compare / project_columns / impute_column / transition_flow) as needed.\n\n**Full detail:** Call `guide_barsom_workflow` for plan-scoped tool map, training modes, async rules, optional MCP App UIs, and step-by-step SOP (from the Barivia API when online).\n\n## Tool taxonomy (one tool per stage — do not mix)\n\n| Stage | Tool(s) | Contract |\n|-------|---------|----------|\n| Data | `datasets` | upload, preview, analyze, list, **get** (status/staging), subset, add_expression, reduce_spectral, delete — ingest + feature engineering, no map |\n| Train submit | `train` | map, siom_map, impute (sparse → map + dense imputed.csv), floop_siom (entitled). Async, returns job_id. Submit only |\n| Lifecycle | `jobs` | status, list, compare (**training runs**), cancel, delete. No training/scoring here |\n| Artifacts | `results` | get (default=combined only; figures="none" for metrics-only sweeps; figures="all" or results_explorer/download for every plot), export, download, recolor (async). Read/render completed jobs |\n| Frozen-map ops | `inference` | predict (regime-aware; "compact"|"annotated"), batch_predict, impute_column (neighbor-pool fill for a non-training column), compare (cohort density-diff), project_columns, transition_flow (time-ordered rows only), report. No weight updates |\n| Account | `account` | status, history, add_funds |\n| Bootstrap | `guide_barsom_workflow`, `train`, `training_guidance`, `prepare_training` prompt | orientation, submit map/siom/impute/floop, parameter hints, narrative checklist (API/tier-scoped) |\n| Explore (UI) | `results_explorer`, `training_monitor` | richer UX over the same API; `jobs(status)`+`results(get)` still suffice headless |\n| Other | `send_feedback` | only after user agrees |\n\n### Avoid these mis-routes\n- `jobs(compare)` = metrics table across **training runs** (pick best in a sweep). `inference(compare)` = density-diff of one map vs a **second dataset** (drift/cohort). Different tools.\n- Post-training map analysis (predict, compare, project_columns, impute_column, **transition_flow**) is all **inference** — not `results`. `results` is presentation/artifacts only (`recolor` stays here: it re-renders, it doesn\'t touch data).\n- Project a quantity onto the map: existing columns → `inference(project_columns)`; a formula → `datasets(add_expression, project_onto_job=<job>)`.\n\n## Async pattern\n\n- **Manual poll:** Training submits return `job_id` immediately — poll `jobs(status)` every 10–15s. **Running is not failed**; large grids or FLooP-SIOM can take many minutes. `max_nodes` (FLooP) is a total node budget, not grid side length.\n- **Often auto-polled:** `inference` actions (incl. `transition_flow`) and `results(recolor)` may wait in-proxy; if you get a `job_id`, poll `jobs(status)` the same way.\n\nCredits: jobs consume compute credits; check `account(status)` before big runs. Per-request HTTP timeout defaults to 60s (`datasets(analyze)` is async + auto-polled, so it is not bound by it); on slow networks raise `BARIVIA_FETCH_TIMEOUT_MS`. Timeouts are NOT auto-retried (avoids duplicating slow/expensive work).\n\n## Constraints\n\n- Prep ladder: `prepare_training` prompt = narrative checklist; `training_guidance` = structured hints (presets, resolved normalization/transforms, grid/epochs). Review these, then submit with `train`. Do not guess tiers or FLooP entitlement.\n- `inference(predict)`: prefer `dataset_id` for batch and for SIOM/irregular maps; single-row `rows` uses a fast path that can fail on some topologies — retry with `dataset_id`. FLooP-SIOM: if predict jobs fail while grid SIOM works, capture errors + `job_id`.\n- Column names are case-sensitive — match `datasets(preview)`.\n- Default training path is numeric/cyclic/temporal; use explicit `categorical_features` for baseline categoricals. `predict` must match the model contract.\n- After `results(recolor)`, `inference(transition_flow)`, or `inference(project_columns)`, use the **new** `job_id` returned for follow-up `results` if applicable.\n- **Large results / MCP timeouts:** For sweeps, `jobs(compare)`, or metrics-only reads use `results(action=get, figures="none")`. Default `get` inlines combined only. For every plot use `results_explorer` or `results(action=download)`, not `figures="all"` in chat unless the user wants all images inline.'});s(T,y,y,{mimeType:n},async()=>{const e=await p("results-explorer");return{contents:[{uri:y,mimeType:n,text:e??"<html><body>Results Explorer view not built yet. Run: npm run build:views</body></html>"}]}}),s(T,A,A,{mimeType:n},async()=>{const e=await p("training-monitor");return{contents:[{uri:A,mimeType:n,text:e??"<html><body>Training Monitor view not built yet.</body></html>"}]}}),x(T),w(T),I(T),f(T),g(T),h(T,_),b(T),j(T),v(T),P(T),k(T),T.prompt("info","Short orientation for the Barivia Mapping MCP. For full plan-scoped workflow, tool map, and SOP, the model should call guide_barsom_workflow. Use when the user asks what this MCP can do or how to get started.",{},()=>({messages:[{role:"user",content:{type:"text",text:["Give a concise, scannable answer (headers + bullets):","","**What it is:** MCP client to the Barivia mapping engine (2D SOM / SIOM / FLooP-SIOM when entitled) over HTTPS.","","**First step:** Call `guide_barsom_workflow` for plan-scoped bootstrap (full tool list, async rules, training modes, optional MCP Apps, SOP).","","**Core path:** `datasets(upload)` → `datasets(preview)` + `datasets(analyze)` → choose training action → poll `jobs(status)` every 10–15s until completed → `results(get)` (all main figures/metrics; no separate analyze tool) → `results_explorer(job_id)` to browse figures.","",'**Key tools:** `datasets` (data; reduce_spectral for spectra/long blocks), `train` (map/siom_map/impute/floop_siom; pass `label` for readable compare rows; preset=quick for a fast first map), `jobs` (status/list/compare/cancel/delete — lifecycle only), `results` (get/download/export/recolor; figures="none" for metrics-only), `inference` (predict; batch_predict; impute_column for topology-neighbor pool fill; compare; project_columns; transition_flow; report), `account` (status/credits/queue).',"","**Prep help:** `prepare_training` prompt (checklist) · `training_guidance` (presets/JSON hints + resolved normalization/params) — review, then submit with `train`.","","**Browse results:** `results_explorer(job_id)` is the preferred way to explore figures after a first `results(get)` glance; `training_monitor` shows live progress. Both optional — `results` + `jobs(status)` suffice headless.","","**After training:** `jobs(compare)` across runs, `results(recolor)`, `inference(project_columns)` for variables not in training, `inference(transition_flow)` only if rows are time-ordered.","","**Rules:** Running ≠ failed. Column names must match `datasets(preview)` exactly. Do not call `_fetch_figure` from chat (host/UI only); use `results(get)` or `results_explorer`.","","Offer `send_feedback` only after asking the user."].join("\n")}}]})),T.prompt("prepare_training","Narrative pre-training checklist (prompt). Use after upload and before train. Content is tier-scoped from the API when online. Prep ladder: this prompt = story checklist; training_guidance tool = JSON presets/parameter hints. Review, then submit with train.",{dataset_id:o.string().describe("Dataset ID to prepare for training")},async({dataset_id:e})=>{const t=await M(e);return{messages:[{role:"user",content:{type:"text",text:(t.used_fallback?`[offline fallback ${t.fallback_version}]\n\n`:"")+t.text}}]}});const S=new t;(async function(){try{const e=await i(l,c,p);m(e)}catch(e){process.env.BARIVIA_VIZ_PORT&&console.error("Barivia viz server failed to start:",e)}const e=T.server;e.oninitialized=()=>{const t=e.getClientCapabilities(),o=r(t);u(!!o?.mimeTypes?.includes(n))},await T.connect(S)})().catch(console.error);
+import{McpServer as e}from"@modelcontextprotocol/sdk/server/mcp.js";import{StdioServerTransport as t}from"@modelcontextprotocol/sdk/server/stdio.js";import{z as o}from"zod";import{getUiCapability as s,registerAppResource as r,RESOURCE_MIME_TYPE as n}from"@modelcontextprotocol/ext-apps/server";import{startVizServer as a}from"./viz-server.js";import{API_KEY as i,apiCall as l,apiRawCall as p,loadViewHtml as c,setVizPort as u,setClientSupportsMcpApps as d,CLIENT_VERSION as m}from"./shared.js";import{registerDatasetsTool as f}from"./tools/datasets.js";import{registerTrainTool as h}from"./tools/train.js";import{registerJobsTool as g,JOBS_DESCRIPTION_BASE as b}from"./tools/jobs.js";import{registerResultsTool as _}from"./tools/results.js";import{registerExploreMapTool as y,RESULTS_EXPLORER_URI as w}from"./tools/explore_map.js";import{registerAccountTool as v}from"./tools/account.js";import{registerInferenceTool as j}from"./tools/inference.js";import{registerGuideBarsomTool as k}from"./tools/guide_barsom.js";import{registerTrainingGuidanceTool as x}from"./tools/training_guidance.js";import{registerFeedbackTool as P}from"./tools/feedback.js";import{registerTrainingMonitorTool as A,TRAINING_MONITOR_URI as I}from"./tools/training_monitor.js";import{resolvePrepareTrainingPrompt as C}from"./prepare_training_prompt.js";i||(console.error("Error: BARIVIA_API_KEY not set. Set it in your MCP client config."),process.exit(1));const T=new e({name:"analytics-engine",version:m,instructions:'# Barivia Mapping Analytics Engine\n\nSelf-organizing map (SOM) analytics: project high-dimensional data to a 2D grid for clusters, gradients, and anomalies.\n\n## Workflow (short)\n\nUpload (`datasets(upload)`) → `datasets(preview)` and `datasets(analyze)` before train → submit one of `train(action=map)`, `train(action=siom_map)`, or `train(action=floop_siom)` (only if plan allows FLooP) → poll `jobs(status)` every 10–15s until `completed` → `results(get)` for metrics and figures (there is no separate analyze tool), then `results_explorer(job_id)` to browse the figures interactively. Then `jobs(compare)`, `results(download/recolor)`, or `inference` (predict / compare / project_columns / impute_column / transition_flow) as needed.\n\n**Full detail:** Call `guide_barsom_workflow` for plan-scoped tool map, training modes, async rules, optional MCP App UIs, and step-by-step SOP (from the Barivia API when online).\n\n## Tool taxonomy (one tool per stage — do not mix)\n\n| Stage | Tool(s) | Contract |\n|-------|---------|----------|\n| Data | `datasets` | upload, preview, analyze, list, **get** (status/staging), subset, add_expression, reduce_spectral, delete — ingest + feature engineering, no map |\n| Train submit | `train` | map, siom_map, impute (sparse → map + dense imputed.csv), floop_siom (entitled). Async, returns job_id. Submit only |\n| Lifecycle | `jobs` | status, list (slim + limit/cursor/status/job_type/has_results), update (label/description/tags), compare (**training runs**), cancel, delete. No training/scoring here |\n| Artifacts | `results` | get (default=combined only; figures="none" for metrics-only sweeps; figures="all" or results_explorer/download for every plot), export, download, recolor (async). Read/render completed jobs. Results catalog = `jobs(list, has_results=true)` |\n| Frozen-map ops | `inference` | predict (regime-aware; "compact"|"annotated"), batch_predict, impute_column (neighbor-pool fill for a non-training column), compare (cohort density-diff), project_columns, transition_flow (time-ordered rows only), report. No weight updates |\n| Account | `account` | status, history, **inventory** (markdown datasets+jobs overview), add_funds, **health** (API liveness via GET /health — no R2) |\n| Bootstrap | `guide_barsom_workflow`, `train`, `training_guidance`, `prepare_training` prompt | orientation, submit map/siom/impute/floop, parameter hints, narrative checklist (API/tier-scoped) |\n| Explore (UI) | `results_explorer`, `training_monitor` | richer UX over the same API; `jobs(status)`+`results(get)` still suffice headless |\n| Other | `send_feedback` | only after user agrees; queues locally if API/storage is down |\n\n### Avoid these mis-routes\n- `jobs(compare)` = metrics table across **training runs** (pick best in a sweep). `inference(compare)` = density-diff of one map vs a **second dataset** (drift/cohort). Different tools.\n- Post-training map analysis (predict, compare, project_columns, impute_column, **transition_flow**) is all **inference** — not `results`. `results` is presentation/artifacts only (`recolor` stays here: it re-renders, it doesn\'t touch data).\n- Project a quantity onto the map: existing columns → `inference(project_columns)`; a formula → `datasets(add_expression, project_onto_job=<job>)`.\n\n## Async pattern\n\n- **Manual poll:** Training submits return `job_id` immediately — poll `jobs(status)` every 10–15s. **Running is not failed**; large grids or FLooP-SIOM can take many minutes. `max_nodes` (FLooP) is a total node budget, not grid side length.\n- **Often auto-polled:** `inference` actions (incl. `transition_flow`) and `results(recolor)` may wait in-proxy; if you get a `job_id`, poll `jobs(status)` the same way.\n\nCredits: jobs consume compute credits; check `account(status)` before big runs. Per-request HTTP timeout defaults to 60s (`datasets(analyze)` is async + auto-polled, so it is not bound by it); on slow networks raise `BARIVIA_FETCH_TIMEOUT_MS`. Timeouts are NOT auto-retried (avoids duplicating slow/expensive work).\n\n## Org inventory recipe\n\nTo rebuild a durable markdown overview of an org (datasets + jobs):\n1. `account(action=inventory)` — preferred one-shot (datasets name/id/rows/cols/description/tags + slim recent jobs).\n2. Or compose: `datasets(list)` + `jobs(action=list, limit=50)` (page with `cursor` / filter with `status` / `job_type` / `has_results=true` for a results catalog).\n3. Set `description` + `tags` on `datasets(upload|update)` and `train(...)` / `jobs(update)` so duplicates stay navigable.\n\n## API briefly unavailable (pause, do not crash)\nIf tools return `api_unreachable` / gateway HTML / slim `error_code` lines: summarize in **one calm sentence** — never paste Cloudflare HTML. The proxy already burst-retried (**3** tries, ~**2s** apart); honor `retry_after_sec` (~**30**) before another round. Use `account(action=health)` (no R2). Local downloads and prior results stay usable; `send_feedback` queues under `~/.barivia/deferred-feedback` and flushes when the API returns. Do not start large uploads/trains until `account(status)` or health looks healthy again.\n\n## Constraints\n\n- **Do not auto-subset:** Never call `datasets(subset)` or `sample_n` unless the user explicitly asks for a filter, slice, or random sample. Train and analyze on the uploaded `dataset_id` at full row count — GPU staging/prepare handles hundreds of thousands of rows quickly; silent downsampling hides real prepare/train behavior and wastes scale demos. Use small named fixtures (e.g. sample.csv, periodic_load) only when the user or runbook names them.\n- Prep ladder: `prepare_training` prompt = narrative checklist; `training_guidance` = structured hints (presets, resolved normalization/transforms, grid/epochs). Review these, then submit with `train`. Do not guess tiers or FLooP entitlement.\n- `inference(predict)`: prefer `dataset_id` for batch and for SIOM/irregular maps; single-row `rows` uses a fast path that can fail on some topologies — retry with `dataset_id`. FLooP-SIOM: if predict jobs fail while grid SIOM works, capture errors + `job_id`.\n- Column names are case-sensitive — match `datasets(preview)`.\n- Default training path is numeric/cyclic/temporal; use explicit `categorical_features` for baseline categoricals. `predict` must match the model contract.\n- After `results(recolor)`, `inference(transition_flow)`, or `inference(project_columns)`, use the **new** `job_id` returned for follow-up `results` if applicable.\n- **Large results / MCP timeouts:** For sweeps, `jobs(compare)`, or metrics-only reads use `results(action=get, figures="none")`. Default `get` inlines combined only. For every plot use `results_explorer` or `results(action=download)`, not `figures="all"` in chat unless the user wants all images inline.\n\n## UI delivery (heterogeneous MCP clients)\n\nHosts differ (Cursor, Claude Desktop, CLI agents): some embed MCP App panels; others list `ui://` but never mount them (expected on some Cursor builds); others are text-only. Tool results **always lead with a standalone localhost URL** — that is the intended fallback, not a broken App.\n\n| Tier | When | Agent should |\n|------|------|--------------|\n| **embedded** | Client advertises MCP Apps | Let the panel render **and** surface the standalone localhost URL from tool output / `ui_delivery.urls` (hosts often list Apps but do not mount). |\n| **localhost** | No MCP Apps; viz server running | Post the markdown link from tool output to the user (never broken workspace paths). Re-post after job completes if needed. |\n| **inline_image** | No Apps / override `inline` | Summarize metrics; inline raster (combined.png, learning curve) is attached automatically — show it in the reply. |\n| **text_only** | Viz server down | Use `jobs(status)` + `results(get)`; no panel or localhost link. |\n\nEvery `training_monitor` / `results_explorer` response includes a structured `ui_delivery` block (`delivery`, `urls`, `hint_for_agent`). Follow `hint_for_agent` without user prompting. Standalone viz pages cross-link monitor ↔ results for the same `job_id`.\n\n**Env overrides:** `BARIVIA_UI_DELIVERY=auto|apps|localhost|inline` (default `auto`). `BARIVIA_VIZ_PORT` pins the localhost viz port across proxy restarts. **Diagnostics:** `account(action=status)` reports detected MCP Apps support, viz port, and active tier.'});r(T,w,w,{mimeType:n},async()=>{const e=await c("results-explorer");return{contents:[{uri:w,mimeType:n,text:e??"<html><body>Results Explorer view not built yet. Run: npm run build:views</body></html>"}]}}),r(T,I,I,{mimeType:n},async()=>{const e=await c("training-monitor");return{contents:[{uri:I,mimeType:n,text:e??"<html><body>Training Monitor view not built yet.</body></html>"}]}}),k(T),y(T),A(T),f(T),h(T),g(T,b),_(T),v(T),j(T),x(T),P(T),T.prompt("info","Short orientation for the Barivia Mapping MCP. For full plan-scoped workflow, tool map, and SOP, the model should call guide_barsom_workflow. Use when the user asks what this MCP can do or how to get started.",{},()=>({messages:[{role:"user",content:{type:"text",text:["Give a concise, scannable answer (headers + bullets):","","**What it is:** MCP client to the Barivia mapping engine (2D SOM / SIOM / FLooP-SIOM when entitled) over HTTPS.","","**First step:** Call `guide_barsom_workflow` for plan-scoped bootstrap (full tool list, async rules, training modes, optional MCP Apps, SOP).","","**Core path:** `datasets(upload)` → `datasets(preview)` + `datasets(analyze)` → choose training action → poll `jobs(status)` every 10–15s until completed → `results(get)` (all main figures/metrics; no separate analyze tool) → `results_explorer(job_id)` to browse figures.","",'**Key tools:** `datasets` (data; reduce_spectral for spectra/long blocks), `train` (map/siom_map/impute/floop_siom; pass `label` for readable compare rows; preset=quick for a fast first map), `jobs` (status/list/compare/cancel/delete — lifecycle only), `results` (get/download/export/recolor; figures="none" for metrics-only), `inference` (predict; batch_predict; impute_column for topology-neighbor pool fill; compare; project_columns; transition_flow; report), `account` (status/credits/queue).',"","**Prep help:** `prepare_training` prompt (checklist) · `training_guidance` (presets/JSON hints + resolved normalization/params) — review, then submit with `train`.","","**Browse results:** `results_explorer(job_id)` is the preferred way to explore figures after a first `results(get)` glance; `training_monitor` shows live progress. Both optional — `results` + `jobs(status)` suffice headless.","","**After training:** `jobs(compare)` across runs, `results(recolor)`, `inference(project_columns)` for variables not in training, `inference(transition_flow)` only if rows are time-ordered.","","**Rules:** Running ≠ failed. Column names must match `datasets(preview)` exactly. Do not auto-subset — never call `datasets(subset)` / `sample_n` unless the user explicitly asks; train on the full uploaded `dataset_id`. Do not call `_fetch_figure` from chat (host/UI only); use `results(get)` or `results_explorer`.","","Offer `send_feedback` only after asking the user."].join("\n")}}]})),T.prompt("prepare_training","Narrative pre-training checklist (prompt). Use after upload and before train. Content is tier-scoped from the API when online. Prep ladder: this prompt = story checklist; training_guidance tool = JSON presets/parameter hints. Review, then submit with train.",{dataset_id:o.string().describe("Dataset ID to prepare for training")},async({dataset_id:e})=>{const t=await C(e);return{messages:[{role:"user",content:{type:"text",text:(t.used_fallback?`[offline fallback ${t.fallback_version}]\n\n`:"")+t.text}}]}});const M=new t;(async function(){try{const e=await a(l,p,c);u(e)}catch(e){process.env.BARIVIA_VIZ_PORT&&console.error("Barivia viz server failed to start:",e)}const e=T.server;e.oninitialized=()=>{const t=e.getClientCapabilities(),o=s(t);d(!!o?.mimeTypes?.includes(n))},await T.connect(M)})().catch(console.error);

package/dist/inventory_format.js

@@ -0,0 +1,69 @@
+/** Shared markdown inventory formatting for account(inventory) / jobs list. */
+export function formatTags(tags) {
+    if (!Array.isArray(tags) || tags.length === 0)
+        return "";
+    return tags.map((t) => String(t)).filter(Boolean).join(", ");
+}
+export function formatDatasetInventoryLine(ds) {
+    const id = String(ds.id ?? "");
+    const name = String(ds.name ?? "");
+    const rows = ds.rows != null ? Number(ds.rows) : "?";
+    const cols = ds.cols != null ? Number(ds.cols) : "?";
+    const st = ds.status != null ? String(ds.status) : "ready";
+    const statusBit = st !== "ready" ? ` | status=${st}` : "";
+    const desc = ds.description != null && String(ds.description).trim() !== ""
+        ? ` — ${String(ds.description).trim()}`
+        : "";
+    const tags = formatTags(ds.tags);
+    const tagsBit = tags ? ` [${tags}]` : "";
+    return `${name} (${id}) — ${rows}×${cols}${statusBit}${tagsBit}${desc}`;
+}
+export function formatJobInventoryLine(job) {
+    const id = String(job.id ?? "");
+    const st = String(job.status ?? "");
+    const label = job.label != null && job.label !== "" ? String(job.label) : null;
+    const jt = job.job_type != null ? String(job.job_type) : "?";
+    const ds = job.dataset_id != null ? String(job.dataset_id) : "";
+    const created = job.created_at != null ? String(job.created_at) : "";
+    const result = job.result_ref != null && String(job.result_ref) !== "" ? "yes" : "no";
+    const tags = formatTags(job.tags);
+    const tagsBit = tags ? ` [${tags}]` : "";
+    const desc = job.description != null && String(job.description).trim() !== ""
+        ? ` — ${String(job.description).trim()}`
+        : "";
+    const head = label ? `${label} (id: ${id})` : `id: ${id}`;
+    return `${head} — ${st} | type=${jt} | dataset=${ds} | created=${created} | result=${result}${tagsBit}${desc}`;
+}
+export function extractJobsList(data) {
+    if (Array.isArray(data)) {
+        return { jobs: data, next_cursor: null };
+    }
+    if (data && typeof data === "object") {
+        const obj = data;
+        const jobs = Array.isArray(obj.jobs) ? obj.jobs : [];
+        const next = obj.next_cursor != null && String(obj.next_cursor) !== ""
+            ? String(obj.next_cursor)
+            : null;
+        return { jobs, next_cursor: next };
+    }
+    return { jobs: [], next_cursor: null };
+}
+export function buildJobsListQuery(opts) {
+    const qs = new URLSearchParams();
+    if (opts.dataset_id)
+        qs.set("dataset_id", opts.dataset_id);
+    if (opts.status)
+        qs.set("status", opts.status);
+    if (opts.job_type)
+        qs.set("job_type", opts.job_type);
+    if (opts.has_results)
+        qs.set("has_results", "true");
+    if (opts.limit != null)
+        qs.set("limit", String(opts.limit));
+    if (opts.cursor)
+        qs.set("cursor", opts.cursor);
+    if (opts.fields)
+        qs.set("fields", opts.fields);
+    const s = qs.toString();
+    return s ? `/v1/jobs?${s}` : "/v1/jobs";
+}

package/dist/prepare_training_prompt.js

@@ -2,6 +2,7 @@ import { apiCall } from "./shared.js";
 export const PREPARE_TRAINING_FALLBACK_VERSION = "2026.07-offline";
 const FALLBACK_LINES = [
     "Before upload: for train(action=map) ensure training columns have no NaNs; for train(action=impute) missing cells in training columns are OK (plain numeric only).",
+    "Do not auto-subset: never call datasets(subset) or sample_n unless the user explicitly asks — train on the full uploaded dataset_id.",
     'Please run datasets(action=preview, dataset_id="{id}") to inspect columns, then datasets(action=analyze, dataset_id="{id}") to see which columns and temporal periods are most informative.',
     "Choose the training path:",
     '- train(action=map, dataset_id="{id}", ...) for complete-case data',