@tokenrein/sdk 0.1.1 → 0.1.3
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/package.json +1 -1
package/README.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
Budgets, run tracing and spend reports for AI agents, in one line around your existing OpenAI
|
|
4
4
|
or Anthropic client. By default (direct mode) the client keeps calling its provider and only
|
|
5
|
-
token usage goes to [Tokenrein](
|
|
5
|
+
token usage goes to [Tokenrein](https://tokenrein.com); `mode="proxy"` sends calls through the Tokenrein
|
|
6
6
|
proxy instead. Errors: `BudgetExceeded`, `RunPaused`, `RunKilled`. Works with any
|
|
7
7
|
OpenAI-compatible provider (Gemini, Groq, Mistral, DeepSeek, OpenRouter, Ollama, ...).
|
|
8
8
|
|
|
@@ -22,7 +22,7 @@ await guard.run({ runId: 'ticket-4812', budgetUsd: 5 }, async () => {
|
|
|
22
22
|
});
|
|
23
23
|
```
|
|
24
24
|
|
|
25
|
-
Node ≥ 20 (uses `AsyncLocalStorage`). See [
|
|
25
|
+
Node ≥ 20 (uses `AsyncLocalStorage`). See [the SDK guide](https://github.com/tokenrein/tokenrein/blob/main/sdk/README.md) for the full API.
|
|
26
26
|
|
|
27
27
|
## Develop
|
|
28
28
|
|
package/package.json
CHANGED