> This page is for version 0.3.0.
> For other versions, use one of these documentation indexes:
> - Main (default): https://docs.nvidia.com/nemo/gym/main/llms.txt
> - 0.7.0: https://docs.nvidia.com/nemo/gym/v0.7.0/llms.txt
> - 0.6.0: https://docs.nvidia.com/nemo/gym/v0.6.0/llms.txt
> - 0.5.1: https://docs.nvidia.com/nemo/gym/v0.5.1/llms.txt
> - 0.5.0: https://docs.nvidia.com/nemo/gym/v0.5.0/llms.txt
> - 0.4.0: https://docs.nvidia.com/nemo/gym/v0.4.0/llms.txt
> - 0.3.0: https://docs.nvidia.com/nemo/gym/v0.3.0/llms.txt
> - 0.2.1: https://docs.nvidia.com/nemo/gym/v0.2.1/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/gym/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/gym/_mcp/server.

# nemo_gym.models.token_capture.completion

Token-free evidence from the response actually served by the model gateway.

## Module Contents

### Functions

| Name                                                                                           | Description                                                                |
| ---------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------- |
| [`completion_items`](#nemo_gym-models-token_capture-completion-completion_items)               | Describe served output without reinterpreting Chat text as reasoning.      |
| [`completion_metadata`](#nemo_gym-models-token_capture-completion-completion_metadata)         | Read existing dialect completion fields; never infer success from absence. |
| [`output_item_fingerprint`](#nemo_gym-models-token_capture-completion-output_item_fingerprint) | Reuse dialect-neutral visible fingerprints and exact reasoning evidence.   |
| [`output_validation_item`](#nemo_gym-models-token_capture-completion-output_validation_item)   | Keep original text used by output detectors, excluding transport arrays.   |

### Data

[`__getattr__`](#nemo_gym-models-token_capture-completion-__getattr__)

### API

```python
nemo_gym.models.token_capture.completion.completion_items(
    response: dict[str, typing.Any]
) -> list[dict]
```

Describe served output without reinterpreting Chat text as reasoning.

```python
nemo_gym.models.token_capture.completion.completion_metadata(
    response: dict[str, typing.Any]
) -> tuple[nemo_gym.models.token_capture.staging.records.CompletionStatus, str | None]
```

Read existing dialect completion fields; never infer success from absence.

```python
nemo_gym.models.token_capture.completion.output_item_fingerprint(
    item: dict[str, typing.Any]
) -> str
```

Reuse dialect-neutral visible fingerprints and exact reasoning evidence.

```python
nemo_gym.models.token_capture.completion.output_validation_item(
    item: dict[str, typing.Any]
) -> nemo_gym.models.token_capture.staging.records.OutputValidationItem
```

Keep original text used by output detectors, excluding transport arrays.

```python
nemo_gym.models.token_capture.completion.__getattr__ = moved_names_getattr(__name__)
```