> ## Documentation Index
> Fetch the complete documentation index at: https://sdk.observability.getonex.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Change Log

| Version | Date          | Notes                                                                                                                     |
| ------- | ------------- | ------------------------------------------------------------------------------------------------------------------------- |
| 0.1.29  | February 2026 | Sampling & throughput control; logits/probabilities capture; GPT attention instrumentation. See details below.            |
| 0.1.0   | December 2025 | Initial release: SDK documentation scaffolding (MkDocs Material), request/response instrumentation, Dockerized docs site. |

## 0.1.29 (February 2026)

* **Sampling & throughput control**
  * `sample_rate` (0.0–1.0): fraction of requests to export (e.g. `0.1` = 10%); per-request sampling by `request_id`.
  * `max_requests_per_minute`: cap on batch export requests per 60-second sliding window to avoid overloading the platform.
  * Config: top-level or in `config`; see [Configuration](configuration#sampling-and-throughput-control).

* **Logits / probabilities capture**
  * `capture_logits` and `capture_probabilities` (default `False`): optional capture of model logits and softmax probabilities for Uncertainty, Calibration, and Confidence assessments.
  * `logits_sample_size`: max number of values in the sample (default 64) to limit payload size.
  * When enabled, the main `output` field is serialized without the raw logits tensor; logits/probabilities are in dedicated fields. See [Configuration](configuration#logits-and-probabilities-capture).

* **GPT attention**
  * Attention instrumentation for GPT-2–style models with the same attention metrics as BERT/ViT (entropy per head, max/mean attention, head agreement).
  * Requires calling the model with `output_attentions=True` for attention weights to be available.
  * Enables **Attention Health** assessment for GPT; see [Integration Guide](integration-guide#attention-metrics-bert-gpt-vit).