@barivia/barmesh-mcp 0.2.0 → 0.2.1

package/dist/shared.js

@@ -4,6 +4,10 @@
  * remains a thin HTTPS client to the same Barivia API (no domain logic here).
  */
 import fs from "node:fs/promises";
+import { createReadStream } from "node:fs";
+import { createGzip } from "node:zlib";
+import { createHash } from "node:crypto";
+import { Readable } from "node:stream";
 import path from "node:path";
 import { fileURLToPath } from "node:url";
 import { logInfo } from "./logger.js";
@@ -16,10 +20,49 @@ export const FETCH_TIMEOUT_MS = parseInt(process.env.BARIVIA_FETCH_TIMEOUT_MS ??
 export const MAX_RETRIES = 2;
 export const RETRYABLE_STATUS = new Set([502, 503, 504]);
 /** Single source of truth for the proxy version. Keep in sync with package.json on bump. */
-export const CLIENT_VERSION = "0.2.0";
+export const CLIENT_VERSION = "0.2.1";
 export const PUBLIC_SITE_ORIGIN = "https://barivia.se";
 /** Large per-cell CSV uploads may exceed the default fetch timeout. */
 export const UPLOAD_DATASET_TIMEOUT_MS = 180_000;
+/** Files at/above this size use the presigned direct-to-R2 streaming upload path. */
+export const LARGE_UPLOAD_BYTES = 64 * 1024 * 1024; // 64 MB
+/** Timeout for a direct presigned PUT of a large (gzipped) file to R2. */
+export const PRESIGNED_PUT_TIMEOUT_MS = 30 * 60_000; // 30 min
+/** Poll window for the async stage_dataset job. */
+export const POLL_STAGE_MAX_MS = 30 * 60_000; // 30 min
+/** Streaming SHA-256 of a file (idempotency key) without reading it into memory. */
+export async function streamFileSha256(srcPath) {
+    return new Promise((resolve, reject) => {
+        const h = createHash("sha256");
+        const s = createReadStream(srcPath);
+        s.on("data", (chunk) => h.update(chunk));
+        s.on("end", () => resolve(h.digest("hex")));
+        s.on("error", reject);
+    });
+}
+/** Stream a local file through gzip directly to a presigned PUT URL (e.g. R2). */
+export async function putPresignedStream(url, srcPath, contentType, timeoutMs = PRESIGNED_PUT_TIMEOUT_MS) {
+    const gz = createReadStream(srcPath).pipe(createGzip());
+    const webStream = Readable.toWeb(gz);
+    const controller = new AbortController();
+    const timer = setTimeout(() => controller.abort(), timeoutMs);
+    try {
+        const resp = await fetch(url, {
+            method: "PUT",
+            body: webStream,
+            headers: { "Content-Type": contentType },
+            duplex: "half",
+            signal: controller.signal,
+        });
+        if (!resp.ok) {
+            const t = await resp.text().catch(() => "");
+            throw new Error(`Presigned upload failed: HTTP ${resp.status} ${t.slice(0, 200)}`);
+        }
+    }
+    finally {
+        clearTimeout(timer);
+    }
+}
 // ---------------------------------------------------------------------------
 // Fetch helpers
 // ---------------------------------------------------------------------------

package/dist/tools/datasets.js

@@ -1,8 +1,9 @@
 import { gzipSync } from "node:zlib";
 import { z } from "zod";
 import fs from "node:fs/promises";
+import path from "node:path";
 import { registerAuditedTool } from "../audit.js";
-import { apiCall, resolveFilePathForUpload, textResult, UPLOAD_DATASET_TIMEOUT_MS, } from "../shared.js";
+import { apiCall, resolveFilePathForUpload, textResult, pollUntilComplete, UPLOAD_DATASET_TIMEOUT_MS, LARGE_UPLOAD_BYTES, PRESIGNED_PUT_TIMEOUT_MS, POLL_STAGE_MAX_MS, streamFileSha256, putPresignedStream, } from "../shared.js";
 export function registerDatasetsTool(server) {
     registerAuditedTool(server, "barmesh_datasets", `Upload, preview, or list the combined per-cell mesh CSV used for convergence analysis.
 
@@ -30,6 +31,36 @@ ESCALATION: If preview shows a feature column as non-numeric, fix the extraction
             let body;
             if (file_path && file_path.length > 0) {
                 const resolved = await resolveFilePathForUpload(file_path, server);
+                const ext = path.extname(resolved).toLowerCase();
+                if (ext !== ".csv" && ext !== ".tsv") {
+                    throw new Error("Only .csv and .tsv files can be uploaded as datasets.");
+                }
+                const HARD_MAX_BYTES = 5 * 1024 * 1024 * 1024; // 5 GB
+                const stat = await fs.stat(resolved);
+                if (stat.size > HARD_MAX_BYTES) {
+                    throw new Error(`File too large (${(stat.size / 1024 / 1024 / 1024).toFixed(2)} GB). Maximum upload size is 5 GB.`);
+                }
+                if (stat.size >= LARGE_UPLOAD_BYTES) {
+                    const idem = await streamFileSha256(resolved);
+                    const init = (await apiCall("POST", "/v1/datasets/upload-url", { name, size_bytes: stat.size }, { "Idempotency-Key": idem }));
+                    const datasetId = (init.dataset_id ?? init.id);
+                    if (init.idempotent_replay) {
+                        return textResult({ id: datasetId, status: init.status, idempotent_replay: true,
+                            suggested_next_step: `barmesh_datasets(action=preview, dataset_id=${datasetId})` });
+                    }
+                    await putPresignedStream(init.upload_url, resolved, init.content_type ?? "application/octet-stream", PRESIGNED_PUT_TIMEOUT_MS);
+                    const fin = (await apiCall("POST", `/v1/datasets/${datasetId}/finalize`, {}));
+                    const jobId = (fin.id ?? fin.job_id);
+                    const poll = await pollUntilComplete(jobId, POLL_STAGE_MAX_MS);
+                    if (poll.status === "failed") {
+                        return textResult({ id: datasetId, status: "failed", error: poll.error ?? "staging failed" });
+                    }
+                    const ready = poll.status === "completed";
+                    return textResult({ id: datasetId, status: ready ? "ready" : "staging", job_id: jobId,
+                        suggested_next_step: ready
+                            ? `barmesh_datasets(action=preview, dataset_id=${datasetId})`
+                            : `Still staging; poll jobs(action=status, job_id="${jobId}").` });
+                }
                 body = await fs.readFile(resolved, "utf-8");
             }
             else if (csv_data && csv_data.length > 0) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@barivia/barmesh-mcp",
-  "version": "0.2.0",
+  "version": "0.2.1",
   "description": "barmesh MCP proxy — SOM-based CFD mesh-convergence and Richardson/GCI analysis on the Barivia cloud API",
   "keywords": [
     "mcp",