@mindstudio-ai/agent 0.1.119 → 0.1.121

package/llms.txt

@@ -1903,6 +1903,9 @@ await Policies.search('ERR-7741X', { mode: 'lexical' });
 await Policies.add(buffer, { filename: 'policy.pdf', contentType: 'application/pdf', metadata: { department: 'legal' } });
 const docs = await Policies.documents();
 
+// walk a large corpus (a page at a time behind the scenes) to build your own index of it
+for await (const doc of Policies.allDocuments()) { /* doc.id, doc.metadata, doc.status */ }
+
 // introspection — what is in the corpus, and how one document was split
 const { chunkCount, pipeline } = await Policies.stats();  // counts + the config actually in effect
 const chunks = await Policies.chunks(docs[0].id);       // why a document does or doesn't match
@@ -1920,7 +1923,9 @@ Search is deterministic for a fixed corpus and configuration — same query, sam
 
 `search()` throws `index_warming` (HTTP 503) when a large corpus's index is being reloaded after an eviction — a minute or two, in the background. It means loading, not empty: tell the user the knowledge base is warming up and retry shortly. Small corpora reload inside the search and never raise it; sources on dedicated capacity are never evicted.
 
-Other methods: `stats()`, `documents()`, `chunks(documentId, {vectors?})`, `remove(documentId)`, `removeWhere(selector)`, `ensure(name?)` (rarely needed — `add` and `search` create-on-reference), and `DataSource.contentHash(bytes)` to check for an existing document before adding.
+On dedicated capacity `search()` throws `index_building` (HTTP 503) instead, while a bulk load runs and while the index is built after one: the index is built once at the end of a load rather than behind every write, and the message carries "N of M vectors indexed". Handle it like `index_warming` — the knowledge base is being built, never empty; say so and retry later.
+
+Other methods: `stats()`, `documents()` (the first thousand, or `documents({ ids })` to poll what `add` returned), `documentsPage({ cursor?, limit? })` and `allDocuments()` (walk a corpus of any size, oldest first — how an app builds its own timeline or index of a big source after ingest, in a background task), `chunks(documentId, {vectors?})`, `remove(documentId)`, `removeWhere(selector)`, `ensure(name?)` (rarely needed — `add` and `search` create-on-reference), and `DataSource.contentHash(bytes)` to check for an existing document before adding.
 
 `removeWhere({ metadata?, filename?, documentIds?, externalIdPrefix? })` removes every matching document (vectors, row and bytes) in pages of a thousand and returns `{ deleted, remaining }`. Chunk-level filter fields and an empty selector are refused; deleting a whole source is an owner operation (`remy-admin datasources delete`), not something app code does.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mindstudio-ai/agent",
-  "version": "0.1.119",
+  "version": "0.1.121",
   "description": "TypeScript SDK for MindStudio direct step execution",
   "type": "module",
   "main": "./dist/index.js",