@mindstudio-ai/agent 0.1.149 → 0.1.151
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +2 -2
- package/dist/cli.js +30 -19
- package/dist/index.d.ts +144 -23
- package/dist/index.js +23 -12
- package/dist/index.js.map +1 -1
- package/dist/postinstall.js +30 -19
- package/llms.txt +52 -21
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -599,8 +599,8 @@ const agent = new MindStudioAgent({
|
|
|
599
599
|
|
|
600
600
|
Handled automatically:
|
|
601
601
|
|
|
602
|
-
- **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 (
|
|
603
|
-
- **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
|
|
602
|
+
- **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 (50 in flight)
|
|
603
|
+
- **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 5,000 calls in any 5 minutes; past that the server answers 429, and once the retries are spent the call throws `rate_limit_exceeded`
|
|
604
604
|
|
|
605
605
|
Every result includes `$rateLimitRemaining` so you can throttle proactively.
|
|
606
606
|
|