> This page is for version 0.6.0.
> 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.responses_converter

Shared Responses API ↔ Chat Completions converter.

This module contains the translation logic between OpenAI's Responses API format
and the Chat Completions API format. It is used by model servers that need to
convert between the two formats (e.g. vllm\_model, inference\_provider).

## Module Contents

### Classes

| Name                                                                               | Description                                                             |
| ---------------------------------------------------------------------------------- | ----------------------------------------------------------------------- |
| [`ResponsesConverter`](#nemo_gym-responses_converter-ResponsesConverter)           | Converts between OpenAI Responses API and Chat Completions API formats. |
| [`ResponsesConverterState`](#nemo_gym-responses_converter-ResponsesConverterState) | -                                                                       |

### Functions

| Name                                                                                                     | Description                                                                             |
| -------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------- |
| [`_align_logprobs_to_text`](#nemo_gym-responses_converter-_align_logprobs_to_text)                       | Keep the token entries that survive removing the `removed` character spans.             |
| [`_chat_logprobs_to_responses`](#nemo_gym-responses_converter-_chat_logprobs_to_responses)               | Chat choice logprobs in the shape `ResponseOutputText.logprobs` expects.                |
| [`_message_content_to_text`](#nemo_gym-responses_converter-_message_content_to_text)                     | Plain text of a chat message content (a string, or a list of text parts).               |
| [`_optional_token_count`](#nemo_gym-responses_converter-_optional_token_count)                           | Return a provider-reported token count without coercing missing/invalid values to zero. |
| [`_token_information_from_mapping`](#nemo_gym-responses_converter-_token_information_from_mapping)       | Return validated token metadata when the mapping contains it.                           |
| [`_usage_detail`](#nemo_gym-responses_converter-_usage_detail)                                           | Read one canonical nested token detail, then named provider aliases.                    |
| [`split_responses_input_output_items`](#nemo_gym-responses_converter-split_responses_input_output_items) | -                                                                                       |

### Data

[`VLLMConverter`](#nemo_gym-responses_converter-VLLMConverter)

[`VLLMConverterResponsesToChatCompletionsState`](#nemo_gym-responses_converter-VLLMConverterResponsesToChatCompletionsState)

[`_IMAGE_OUTPUT_PLACEHOLDER`](#nemo_gym-responses_converter-_IMAGE_OUTPUT_PLACEHOLDER)

[`_REPORTING_ONLY_REASONING_FIELDS`](#nemo_gym-responses_converter-_REPORTING_ONLY_REASONING_FIELDS)

[`_RESPONSE_NON_BOUNDARY_TYPES`](#nemo_gym-responses_converter-_RESPONSE_NON_BOUNDARY_TYPES)

[`_RESPONSE_OUTPUT_BOUNDARY_TYPES`](#nemo_gym-responses_converter-_RESPONSE_OUTPUT_BOUNDARY_TYPES)

[`logger`](#nemo_gym-responses_converter-logger)

### API

```python
class nemo_gym.responses_converter.ResponsesConverter()
```

**Bases:** `BaseModel`

Converts between OpenAI Responses API and Chat Completions API formats.

**`THINK_TAG_PATTERN`** `ClassVar = re.compile('<think>(.*?)</think>', re.DOTALL)`

---

**`return_token_id_information`** `bool`

---

**`uses_reasoning_parser`** `bool = True`

---

```python
nemo_gym.responses_converter.ResponsesConverter._chat_completion_to_responses_tools(
    chat_completions_tools: typing.Optional[typing.List[nemo_gym.openai_utils.NeMoGymChatCompletionToolUnionParam]]
) -> typing.List[openai.types.responses.response_create_params.ToolParam]
```

```python
nemo_gym.responses_converter.ResponsesConverter._chat_custom_tool_to_responses(
    tool: dict
) -> dict
```

staticmethod

```python
nemo_gym.responses_converter.ResponsesConverter._chat_to_responses_tool_choice(
    tool_choice: typing.Any
) -> typing.Any
```

```python
nemo_gym.responses_converter.ResponsesConverter._extract_reasoning_from_content(
    content: str
) -> typing.Tuple[typing.List[str], str]
```

```python
nemo_gym.responses_converter.ResponsesConverter._format_function_call(
    m: dict,
    state: nemo_gym.responses_converter.ResponsesConverterState
) -> None
```

```python
nemo_gym.responses_converter.ResponsesConverter._format_function_call_output(
    m: dict,
    state: nemo_gym.responses_converter.ResponsesConverterState,
    drop_unrepresentable_request_fields: bool = False
) -> None
```

```python
nemo_gym.responses_converter.ResponsesConverter._format_message(
    m: dict,
    state: nemo_gym.responses_converter.ResponsesConverterState,
    drop_unrepresentable_request_fields: bool = False
) -> None
```

```python
nemo_gym.responses_converter.ResponsesConverter._format_reasoning(
    m: dict,
    state: nemo_gym.responses_converter.ResponsesConverterState
) -> None
```

Collects text from 'reasoning' messages in responses api and appends it to a buffer.

This is done to group together one (or multiple) reasoning message(s) into a single,
cohesive block, later prepending it to a subsequent assistant message.
See: [https://docs.nvidia.com/nemo/gym/main/infrastructure/engineering-notes/responses-api-evolution](https://docs.nvidia.com/nemo/gym/main/infrastructure/engineering-notes/responses-api-evolution)
for background on reasoning in the Responses API.

```python
nemo_gym.responses_converter.ResponsesConverter._parse_think_tags(
    content: str
) -> typing.Tuple[typing.List[str], str]
```

classmethod

```python
nemo_gym.responses_converter.ResponsesConverter._responses_custom_tool_to_chat(
    tool: dict
) -> dict
```

staticmethod

```python
nemo_gym.responses_converter.ResponsesConverter._responses_to_chat_tool_choice(
    tool_choice: typing.Any
) -> typing.Any
```

```python
nemo_gym.responses_converter.ResponsesConverter._tool_reference_to_chat(
    tool: dict
) -> dict
```

staticmethod

```python
nemo_gym.responses_converter.ResponsesConverter._tool_reference_to_responses(
    tool: dict
) -> dict
```

staticmethod

```python
nemo_gym.responses_converter.ResponsesConverter._wrap_reasoning_in_think_tags(
    texts: typing.List[str]
) -> str
```

staticmethod

```python
nemo_gym.responses_converter.ResponsesConverter.chat_completion_to_response(
    responses_create_params: nemo_gym.openai_utils.NeMoGymResponseCreateParamsNonStreaming,
    chat_completion: nemo_gym.openai_utils.NeMoGymChatCompletion,
    preserve_envelope_id: bool = False
) -> nemo_gym.openai_utils.NeMoGymResponse
```

```python
nemo_gym.responses_converter.ResponsesConverter.chat_completion_to_responses_create_params(
    chat_completion_create_params: nemo_gym.openai_utils.NeMoGymChatCompletionCreateParamsNonStreaming
) -> nemo_gym.openai_utils.NeMoGymResponseCreateParamsNonStreaming
```

```python
nemo_gym.responses_converter.ResponsesConverter.chat_completions_messages_to_responses_items(
    messages: typing.List[typing.Dict[str, typing.Any]]
) -> typing.List[nemo_gym.openai_utils.NeMoGymResponseOutputItem]
```

```python
nemo_gym.responses_converter.ResponsesConverter.postprocess_assistant_message_dict(
    message_dict: typing.Dict[str, typing.Any],
    logprobs: typing.Any = None
) -> typing.List[nemo_gym.openai_utils.NeMoGymResponseOutputItem]
```

```python
nemo_gym.responses_converter.ResponsesConverter.postprocess_chat_response(
    choice: nemo_gym.openai_utils.NeMoGymChoice
) -> typing.List[nemo_gym.openai_utils.NeMoGymResponseOutputItem]
```

```python
nemo_gym.responses_converter.ResponsesConverter.responses_to_chat_completion_create_params(
    responses_create_params: nemo_gym.openai_utils.NeMoGymResponseCreateParamsNonStreaming,
    drop_unrepresentable_request_fields: bool = False
) -> nemo_gym.openai_utils.NeMoGymChatCompletionCreateParamsNonStreaming
```

Convert Responses create params into Chat Completions create params.

A Responses field with no Chat Completions representation raises `NotImplementedError`,
so the caller can route the request to a server that serves Responses natively. With
`drop_unrepresentable_request_fields` the reporting-only fields are removed from the
request instead and the conversion proceeds: a non-empty `include` (every value; an
empty one is already treated as absent), `reasoning.summary` and
`reasoning.generate_summary`, and a message `phase`. An image part in a tool's output
becomes the text placeholder `_IMAGE_OUTPUT_PLACEHOLDER`, which does replace that part
of the prompt. Every other unrepresentable field, `reasoning.context` included, is still
refused.

```python
class nemo_gym.responses_converter.ResponsesConverterState()
```

**Bases:** `BaseModel`

**`assistant_item_buffered`** `bool = False`

---

**`content_buffer`** `str = ''`

---

**`messages`** `List[NeMoGymChatCompletionMessageParam] = Field(default_factory=list)`

---

**`refusal_buffer`** `str = ''`

---

**`return_token_id_information`** `bool`

---

**`token_information`** `Optional[TokenIDLogProbMixin] = None`

---

**`tool_calls_buffer`** `List[NeMoGymChatCompletionMessageToolCallParam] = Field(default_factory=list)`

---

```python
nemo_gym.responses_converter.ResponsesConverterState.flush_assistant() -> None
```

```python
nemo_gym.responses_converter._align_logprobs_to_text(
    logprobs: typing.Optional[typing.List[typing.Dict[str, typing.Any]]],
    original: str,
    removed: typing.List[typing.Tuple[int, int]]
) -> typing.Optional[typing.List[typing.Dict[str, typing.Any]]]
```

Keep the token entries that survive removing the `removed` character spans.

Reasoning extraction shortens the output text; its logprobs must shrink with it or
they describe different text. The kept positions come from the removal itself, never
from searching for the answer text, which may also occur inside the reasoning. If the
tokens do not reconstruct `original` the alignment is unknowable and the logprobs
are dropped rather than misattributed.

```python
nemo_gym.responses_converter._chat_logprobs_to_responses(
    logprobs: typing.Any
) -> typing.Optional[typing.List[typing.Dict[str, typing.Any]]]
```

Chat choice logprobs in the shape `ResponseOutputText.logprobs` expects.

Same field names on both sides; the Responses models require `bytes` to be
iterable where chat allows null.

```python
nemo_gym.responses_converter._message_content_to_text(
    content: typing.Any
) -> str
```

Plain text of a chat message content (a string, or a list of text parts).

```python
nemo_gym.responses_converter._optional_token_count(
    value: typing.Any
) -> typing.Optional[int]
```

Return a provider-reported token count without coercing missing/invalid values to zero.

```python
nemo_gym.responses_converter._token_information_from_mapping(
    value: typing.Dict[str, typing.Any]
) -> typing.Optional[nemo_gym.openai_utils.TokenIDLogProbMixin]
```

Return validated token metadata when the mapping contains it.

```python
nemo_gym.responses_converter._usage_detail(
    usage: typing.Any,
    detail_group: str,
    detail_name: str,
    top_level_aliases: str = ()
) -> typing.Optional[int]
```

Read one canonical nested token detail, then named provider aliases.

```python
nemo_gym.responses_converter.split_responses_input_output_items(
    items: typing.List[nemo_gym.openai_utils.NeMoGymResponseOutputItem]
) -> typing.Tuple[typing.List[nemo_gym.openai_utils.NeMoGymResponseOutputItem], typing.List[nemo_gym.openai_utils.NeMoGymResponseOutputItem]]
```

```python
nemo_gym.responses_converter.VLLMConverter = ResponsesConverter
```

```python
nemo_gym.responses_converter.VLLMConverterResponsesToChatCompletionsState = ResponsesConverterState
```

```python
nemo_gym.responses_converter._IMAGE_OUTPUT_PLACEHOLDER = '[image omitted from tool output]'
```

```python
nemo_gym.responses_converter._REPORTING_ONLY_REASONING_FIELDS = ('summary', 'generate_summary')
```

```python
nemo_gym.responses_converter._RESPONSE_NON_BOUNDARY_TYPES: frozenset[str] = frozenset({'additional_tools', 'apply_patch_call_output', 'compaction', 'compact...
```

```python
nemo_gym.responses_converter._RESPONSE_OUTPUT_BOUNDARY_TYPES = frozenset({'code_interpreter_call', 'computer_call', 'custom_tool_call', 'file_s...
```

```python
nemo_gym.responses_converter.logger = logging.getLogger(__name__)
```