@mindstudio-ai/agent 0.1.133 → 0.1.134

package/README.md

@@ -599,9 +599,8 @@ const agent = new MindStudioAgent({
 
 Handled automatically:
 
-- **Concurrency queue** — requests beyond the server's concurrent limit are queued and proceed as slots open up
-- **Auto-retry on 429** — rate-limited responses are retried using the `Retry-After` header (default: 3 retries, configurable via `maxRetries`)
-- **Call cap** — internal tokens are capped at 500 calls per execution
+- **Concurrency queue** — requests beyond the server's concurrent limit are queued and proceed as slots open up. A step holds its slot until it finishes. Inside a MindStudio app each method execution has its own queue, matching the server's per-execution limit (10 in flight)
+- **Auto-retry on 429** — rate-limited responses are retried using the `Retry-After` header (default: 3 retries, configurable via `maxRetries`). An app's method execution may make 500 calls in any 5 minutes; past that the server answers 429, and once the retries are spent the call throws `rate_limit_exceeded`
 
 Every result includes `$rateLimitRemaining` so you can throttle proactively.
 
@@ -625,7 +624,7 @@ try {
 } catch (err) {
   if (err instanceof MindStudioError) {
     console.error(err.message); // Human-readable message
-    console.error(err.code); // "invalid_step_config", "api_error", "call_cap_exceeded", etc.
+    console.error(err.code); // "invalid_step_config", "api_error", "rate_limit_exceeded", etc.
     console.error(err.status); // HTTP status (400, 401, 429, etc.)
     console.error(err.details); // Raw API error body
   }