@vectros-ai/mcp-server 0.6.0 → 0.7.0

package/CHANGELOG.md

@@ -3,6 +3,27 @@
 All notable changes to `@vectros-ai/mcp-server` are documented here.
 This project adheres to [Semantic Versioning](https://semver.org).
 
+## 0.7.0 — 2026-07-05
+
+Text-retention control that works, and tool descriptions that tell the truth
+about it.
+
+### Added
+
+- **`storeText` works in file mode on `document_ingest`.** The flag was advertised but silently
+  dropped on file uploads; it now forwards your retention choice. Default `true` keeps the
+  extracted text available to `document_get(includeText: true)` and `document_ask`; `false`
+  discards it once indexing completes (search and the original-file download keep working).
+  Fixed at ingest — a re-ingest of the same document keeps the original choice.
+
+### Changed
+
+- **`document_update` no longer accepts `storeText`** — retention is immutable after ingest, so
+  the input was misleading (the server now rejects such updates).
+- `document_ingest`, `document_get`, and `document_update` descriptions rewritten to the real
+  retention semantics: text-mode bodies are always retained; text availability on
+  `document_get` reflects whether the text actually exists.
+
 ## 0.6.0 — 2026-07-03
 
 Curation-focused tool improvements: look records and documents up by your own

package/dist/cli-http.js

@@ -4921,7 +4921,7 @@ var DocumentsClient = class {
     return handleNonStatusCodeError(_response.error, _response.rawResponse, "DELETE", "/v1/documents/{id}");
   }
   /**
-   * Partially updates a document using an RFC 7386 JSON Merge Patch. The `payload` object is deep-merged: keys you send overwrite existing values (recursing into nested objects), a key set to `null` is deleted, and keys you omit are preserved — unlike PUT, which replaces the whole payload. Top-level fields (`title`, `storeText`, `folderId`, `schemaId`, ownership) are set when present and left unchanged when omitted; sending a top-level field as `null` is rejected. Supplying `text` re-ingests the document body (same as PUT). `indexMode` and `externalId` are immutable and rejected if present. The merged result is validated against the bound schema. Pass `expectedVersion` for optimistic concurrency (409 on conflict). Requires the `documents:u` scope.
+   * Partially updates a document using an RFC 7386 JSON Merge Patch. The `payload` object is deep-merged: keys you send overwrite existing values (recursing into nested objects), a key set to `null` is deleted, and keys you omit are preserved — unlike PUT, which replaces the whole payload. Top-level fields (`title`, `folderId`, `schemaId`, ownership) are set when present and left unchanged when omitted; sending a top-level field as `null` is rejected. Supplying `text` re-ingests the document body (same as PUT). `indexMode`, `externalId`, and `storeText` (text retention is fixed at ingest) are immutable and rejected if present. The merged result is validated against the bound schema. Pass `expectedVersion` for optimistic concurrency (409 on conflict). Requires the `documents:u` scope.
    *
    * @param {Vectros.PatchDocumentRequest} request
    * @param {DocumentsClient.RequestOptions} requestOptions - Request-specific configuration.
@@ -5173,7 +5173,7 @@ var DocumentsClient = class {
     return handleNonStatusCodeError(_response.error, _response.rawResponse, "GET", "/v1/documents/{id}/download");
   }
   /**
-   * Returns the full extracted or ingested text body for documents that were stored with `storeText=true`. Returns 404 when the document does not exist or when no text is available (because `storeText` was false, or extraction has not yet completed). Requires the `documents:r` scope.
+   * Returns the document's full text body when it is retained: always available for text-ingested documents, and for file-uploaded documents unless they were uploaded with `storeText=false` (which discards the extracted text once indexing completes — the original file remains available via `GET /{id}/download`). Returns 404 when the document does not exist, its text was not retained, or extraction has not yet completed. Requires the `documents:r` scope.
    *
    * @param {Vectros.GetDocumentTextRequest} request
    * @param {DocumentsClient.RequestOptions} requestOptions - Request-specific configuration.
@@ -8782,8 +8782,8 @@ function warnOnSuboptimalKey(key, log) {
 
 // src/build-info.ts
 var BUILD_INFO = {
-  mcpServer: true ? "0.6.0" : "dev",
-  sdk: true ? "0.32.0" : "dev"
+  mcpServer: true ? "0.7.0" : "dev",
+  sdk: true ? "0.33.0" : "dev"
 };
 
 // src/log.ts
@@ -9742,7 +9742,7 @@ function isNotAvailable(err) {
 var documentGet = ({ client, log }) => ({
   name: "document_get",
   title: "Get document metadata (and optionally text)",
-  description: "Fetch metadata for a single document \u2014 select it by its Vectros `documentId` OR by your own `externalId` + `type` (resolved for you). Pass `includeText: true` to also fetch the text body (capped at ~8K tokens; `truncated: true` flag if cut). If the document was ingested without `storeText: true`, text is unavailable \u2014 `textAvailable: false` flag is set and the agent should use `document_ask` for question-driven extraction instead. Pass `includeDownloadUrl: true` to also get a short-lived presigned `downloadUrl` for the original file (file-backed documents only). Returns the full document metadata, including its lifecycle `status` (ACTIVE, or ARCHIVED when soft-retracted from search \u2014 restorable via document_update) and its processing `indexStatus`.",
+  description: "Fetch metadata for a single document \u2014 select it by its Vectros `documentId` OR by your own `externalId` + `type` (resolved for you). Pass `includeText: true` to also fetch the text body (capped at ~8K tokens; `truncated: true` flag if cut). Text is available for every text-ingested document and for file-ingested documents unless they were uploaded with `storeText: false` (extracted text discarded after indexing) \u2014 then `textAvailable: false` is set; the original file is still retrievable via `includeDownloadUrl`. Pass `includeDownloadUrl: true` to also get a short-lived presigned `downloadUrl` for the original file (file-backed documents only). Returns the full document metadata, including its lifecycle `status` (ACTIVE, or ARCHIVED when soft-retracted from search \u2014 restorable via document_update) and its processing `indexStatus`.",
   inputSchema: inputSchema10,
   handler: async (args) => {
     const documentId = args.documentId;
@@ -9766,7 +9766,7 @@ var documentGet = ({ client, log }) => ({
           if (isNotAvailable(textErr)) {
             log.debug(
               { tool: "document_get", id },
-              "document_get text unavailable (ingested without storeText)"
+              "document_get text unavailable (not retained \u2014 storeText:false upload)"
             );
             extra = { ...extra, textAvailable: false };
           } else {
@@ -9928,7 +9928,6 @@ var inputSchema12 = {
     "New raw text body. Supplying it re-ingests the document body and re-queues it for indexing, so the search index reflects the edit (text-ingested documents only \u2014 not file-backed ones). Omit to leave the stored text unchanged. This is the in-place alternative to re-ingesting with upsert:true."
   ),
   folderId: import_zod12.z.string().optional().describe("Move the document into this folder (cannot be cleared once set)."),
-  storeText: import_zod12.z.boolean().optional().describe("Whether the raw text is stored + retrievable."),
   status: import_zod12.z.enum(["ACTIVE", "ARCHIVED"]).optional().describe(
     "Lifecycle status. `ARCHIVED` soft-retracts the document \u2014 it is pulled from search and recall but kept and recoverable; set it back to `ACTIVE` to re-index and restore it. The way to retire superseded content when the credential has no delete authority. Omit to leave unchanged."
   ),
@@ -9952,7 +9951,6 @@ var documentUpdate = ({ client, log }) => ({
     const fields = args.fields;
     const text = args.text;
     const folderId = args.folderId;
-    const storeText = args.storeText;
     const status = args.status;
     const userId = args.userId;
     const orgId = args.orgId;
@@ -9966,7 +9964,6 @@ var documentUpdate = ({ client, log }) => ({
       if (fields !== void 0) body.payload = fields;
       if (text !== void 0) body.text = text;
       if (folderId !== void 0) body.folderId = folderId;
-      if (storeText !== void 0) body.storeText = storeText;
       if (status !== void 0) body.status = status;
       if (userId !== void 0) body.userId = userId;
       if (orgId !== void 0) body.orgId = orgId;
@@ -10286,7 +10283,7 @@ var inputSchema19 = {
   // Inline text mode (mutually exclusive with filePath):
   text: import_zod18.z.string().min(1).optional().describe("Text body to ingest inline. Mutually exclusive with filePath. Either text or filePath is required."),
   storeText: import_zod18.z.boolean().optional().describe(
-    "If true (default), the text body is stored alongside the index so document_get(includeText:true) can retrieve it later. Set false to index only \u2014 saves storage cost on large corpora but document_get(includeText) will return textAvailable:false."
+    "Whether the document's text is retained after indexing (default true). Applies to BOTH modes and is fixed at ingest time. Text mode: the ingested body is always retained (this flag is effectively always true \u2014 the body is the document). File mode: true keeps the extracted text retrievable via document_get(includeText:true) and usable by document_ask; false discards the extracted text once indexing completes \u2014 search still works and the original file remains downloadable, but includeText returns textAvailable:false and document_ask is unavailable."
   ),
   // File upload mode (mutually exclusive with text; stdio-transport-only):
   filePath: import_zod18.z.string().min(1).optional().describe(
@@ -10302,7 +10299,7 @@ var inputSchema19 = {
 var documentIngest = ({ client, log, transport, ingestRoot }) => ({
   name: "document_ingest",
   title: "Ingest a new document (text body or file upload)",
-  description: "Create a new document in your Vectros tenant. Two modes:\n  \u2022 Text mode: pass `text` (string body). Single-call. Use for crawled content, notes, generated text.\n  \u2022 File mode: pass `filePath` (local path on the MCP server's host machine). STDIO-TRANSPORT ONLY \u2014 rejected on HTTP transport. MCP server reads the bytes, requests a presigned upload URL, and PUTs them. Returns when the upload is accepted (indexStatus: PENDING_INDEX); poll with `document_get` until indexStatus is INDEXED.\nEither `text` or `filePath` must be present; both is an error. Idempotent by `externalId` (re-ingest returns the existing document, not a duplicate). To UPDATE an existing document instead \u2014 re-index an edited body \u2014 pass `upsert:true` with the same `externalId` (and the same `schemaId`); this is the re-sync primitive for keeping a knowledge base current. Pass `schemaId` + `payload` for a typed, lookup-queryable document (records parity). indexMode defaults to HYBRID for untyped documents (omit to inherit a bound schema's default). storeText defaults to true (set false to skip storing the text body).",
+  description: "Create a new document in your Vectros tenant. Two modes:\n  \u2022 Text mode: pass `text` (string body). Single-call. Use for crawled content, notes, generated text.\n  \u2022 File mode: pass `filePath` (local path on the MCP server's host machine). STDIO-TRANSPORT ONLY \u2014 rejected on HTTP transport. MCP server reads the bytes, requests a presigned upload URL, and PUTs them. Returns when the upload is accepted (indexStatus: PENDING_INDEX); poll with `document_get` until indexStatus is INDEXED.\nEither `text` or `filePath` must be present; both is an error. Idempotent by `externalId` (re-ingest returns the existing document, not a duplicate). To UPDATE an existing document instead \u2014 re-index an edited body \u2014 pass `upsert:true` with the same `externalId` (and the same `schemaId`); this is the re-sync primitive for keeping a knowledge base current. Pass `schemaId` + `payload` for a typed, lookup-queryable document (records parity). indexMode defaults to HYBRID for untyped documents (omit to inherit a bound schema's default). storeText defaults to true and is fixed at ingest: in file mode, false discards the extracted text after indexing (search + file download keep working; text retrieval and document_ask do not). Text-mode bodies are always retained.",
   inputSchema: inputSchema19,
   handler: async (args) => {
     const title = args.title;
@@ -10342,14 +10339,12 @@ var documentIngest = ({ client, log, transport, ingestRoot }) => ({
     };
     try {
       if (text) {
-        const storeText = args.storeText ?? true;
         const result = await client.documents.ingestDocument({
           upsert,
           body: {
             title,
             text,
             indexMode,
-            storeText,
             ...common
           }
         });
@@ -10380,11 +10375,13 @@ var documentIngest = ({ client, log, transport, ingestRoot }) => ({
       }
       const fileName = (0, import_node_path.basename)(safePath);
       const fileType = args.fileType ?? inferMimeType(safePath);
+      const storeTextFile = args.storeText ?? true;
       const upload = await client.documents.uploadDocument({
         upsert,
         fileName,
         fileType,
         indexMode,
+        storeText: storeTextFile,
         ...common
       });
       const uploadUrl = upload?.uploadUrl;