fix(memory): cap ollama non-batch embedding concurrency

docs/.generated/config-baseline.sha256

@@ -1,4 +1,4 @@
-5ffabe5ff76d8e4a0d121e89f74f84917b919447e63bf12e0e5b0e4c0211d451  config-baseline.json
-7dcb21e47ddd5de98e2af1ecbc41e11ac0c5742819c359e6d851fbc39c0226e9  config-baseline.core.json
+0f57fb6d20b9d300c4325b227e49f17f04349b0f3c27dd218397fe7a3b5001dc  config-baseline.json
+9d1815981dc3f89d1dfdc72f0a4723d4fd5efca8e5b8a1a1cbf6a053c50c937d  config-baseline.core.json
 c4f07c228d4f07e7afafa5b600b4a80f5b26aaed7267c7287a64d04a527be8e8  config-baseline.channel.json
 6938050627f0d120109d2045b4300aa8b508b35132542db434033ed0fe3e2b3a  config-baseline.plugin.json

docs/providers/ollama.md

@@ -885,7 +885,13 @@ For the full setup and behavior details, see [Ollama Web Search](/tools/ollama-s
     {
       agents: {
         defaults: {
-          memorySearch: { provider: "ollama" },
+          memorySearch: {
+            provider: "ollama",
+            remote: {
+              // Default for Ollama. Raise on larger hosts if reindexing is too slow.
+              nonBatchConcurrency: 1,
+            },
+          },
         },
       },
     }
@@ -899,10 +905,11 @@ For the full setup and behavior details, see [Ollama Web Search](/tools/ollama-s
         defaults: {
           memorySearch: {
             provider: "ollama",
+            model: "nomic-embed-text",
             remote: {
               baseUrl: "http://gpu-box.local:11434",
-              model: "nomic-embed-text",
               apiKey: "ollama-local",
+              nonBatchConcurrency: 2,
             },
           },
         },

docs/reference/memory-config.md

@@ -386,6 +386,7 @@ Prevents re-embedding unchanged text during reindex or transcript updates.
 
 | Key                           | Type      | Default | Description                |
 | ----------------------------- | --------- | ------- | -------------------------- |
+| `remote.nonBatchConcurrency`  | `number`  | `4`     | Parallel inline embeddings |
 | `remote.batch.enabled`        | `boolean` | `false` | Enable batch embedding API |
 | `remote.batch.concurrency`    | `number`  | `2`     | Parallel batch jobs        |
 | `remote.batch.wait`           | `boolean` | `true`  | Wait for batch completion  |
@@ -394,7 +395,9 @@ Prevents re-embedding unchanged text during reindex or transcript updates.
 
 Available for `openai`, `gemini`, and `voyage`. OpenAI batch is typically fastest and cheapest for large backfills.
 
-This is separate from `sync.embeddingBatchTimeoutSeconds`, which controls inline embedding calls used by local/self-hosted providers and hosted providers when provider batch APIs are not active.
+`remote.nonBatchConcurrency` controls inline embedding calls used by local/self-hosted providers and hosted providers when provider batch APIs are not active. Ollama defaults to `1` for non-batch indexing to avoid overwhelming smaller local hosts; set a higher value on larger machines.
+
+This is separate from `sync.embeddingBatchTimeoutSeconds`, which controls the timeout for inline embedding calls.
 
 ---