mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-11 13:44:38 +00:00
feat(responses): add usage types to inference and responses APIs (#3764)
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 4s
Python Package Build Test / build (3.12) (push) Failing after 2s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Vector IO Integration Tests / test-matrix (push) Failing after 6s
Unit Tests / unit-tests (3.12) (push) Failing after 4s
Test External API and Providers / test-external (venv) (push) Failing after 6s
Unit Tests / unit-tests (3.13) (push) Failing after 4s
Python Package Build Test / build (3.13) (push) Failing after 23s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 27s
API Conformance Tests / check-schema-compatibility (push) Successful in 36s
UI Tests / ui-tests (22) (push) Successful in 55s
Pre-commit / pre-commit (push) Successful in 2m7s
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 4s
Python Package Build Test / build (3.12) (push) Failing after 2s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Vector IO Integration Tests / test-matrix (push) Failing after 6s
Unit Tests / unit-tests (3.12) (push) Failing after 4s
Test External API and Providers / test-external (venv) (push) Failing after 6s
Unit Tests / unit-tests (3.13) (push) Failing after 4s
Python Package Build Test / build (3.13) (push) Failing after 23s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 27s
API Conformance Tests / check-schema-compatibility (push) Successful in 36s
UI Tests / ui-tests (22) (push) Successful in 55s
Pre-commit / pre-commit (push) Successful in 2m7s
## Summary
Adds OpenAI-compatible usage tracking types to enable reporting token
consumption for both streaming and non-streaming responses.
## Type Definitions
**Chat Completion Usage** (inference API):
```python
class OpenAIChatCompletionUsage(BaseModel):
prompt_tokens: int
completion_tokens: int
total_tokens: int
prompt_tokens_details: OpenAIChatCompletionUsagePromptTokensDetails | None
completion_tokens_details: OpenAIChatCompletionUsageCompletionTokensDetails | None
```
**Response Usage** (responses API):
```python
class OpenAIResponseUsage(BaseModel):
input_tokens: int
output_tokens: int
total_tokens: int
input_tokens_details: OpenAIResponseUsageInputTokensDetails | None
output_tokens_details: OpenAIResponseUsageOutputTokensDetails | None
```
This matches OpenAI's usage reporting format and enables PR #3766 to
implement usage tracking in streaming responses.
Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Ashwin Bharambe
GitHub
parent
ebae0385bb
commit
aaf5036235
8 changed files with 747 additions and 0 deletions
103
docs/static/llama-stack-spec.yaml
vendored
103
docs/static/llama-stack-spec.yaml
vendored
|
|
@ -3248,6 +3248,10 @@ components:
|
|||
type: string
|
||||
description: >-
|
||||
The model that was used to generate the chat completion
|
||||
usage:
|
||||
$ref: '#/components/schemas/OpenAIChatCompletionUsage'
|
||||
description: >-
|
||||
Token usage information for the completion
|
||||
input_messages:
|
||||
type: array
|
||||
items:
|
||||
|
|
@ -3414,6 +3418,49 @@ components:
|
|||
title: OpenAIChatCompletionToolCallFunction
|
||||
description: >-
|
||||
Function call details for OpenAI-compatible tool calls.
|
||||
OpenAIChatCompletionUsage:
|
||||
type: object
|
||||
properties:
|
||||
prompt_tokens:
|
||||
type: integer
|
||||
description: Number of tokens in the prompt
|
||||
completion_tokens:
|
||||
type: integer
|
||||
description: Number of tokens in the completion
|
||||
total_tokens:
|
||||
type: integer
|
||||
description: Total tokens used (prompt + completion)
|
||||
prompt_tokens_details:
|
||||
type: object
|
||||
properties:
|
||||
cached_tokens:
|
||||
type: integer
|
||||
description: Number of tokens retrieved from cache
|
||||
additionalProperties: false
|
||||
title: >-
|
||||
OpenAIChatCompletionUsagePromptTokensDetails
|
||||
description: >-
|
||||
Token details for prompt tokens in OpenAI chat completion usage.
|
||||
completion_tokens_details:
|
||||
type: object
|
||||
properties:
|
||||
reasoning_tokens:
|
||||
type: integer
|
||||
description: >-
|
||||
Number of tokens used for reasoning (o1/o3 models)
|
||||
additionalProperties: false
|
||||
title: >-
|
||||
OpenAIChatCompletionUsageCompletionTokensDetails
|
||||
description: >-
|
||||
Token details for output tokens in OpenAI chat completion usage.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- prompt_tokens
|
||||
- completion_tokens
|
||||
- total_tokens
|
||||
title: OpenAIChatCompletionUsage
|
||||
description: >-
|
||||
Usage information for OpenAI chat completion.
|
||||
OpenAIChoice:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -3945,6 +3992,10 @@ components:
|
|||
type: string
|
||||
description: >-
|
||||
The model that was used to generate the chat completion
|
||||
usage:
|
||||
$ref: '#/components/schemas/OpenAIChatCompletionUsage'
|
||||
description: >-
|
||||
Token usage information for the completion
|
||||
additionalProperties: false
|
||||
required:
|
||||
- id
|
||||
|
|
@ -3980,6 +4031,10 @@ components:
|
|||
type: string
|
||||
description: >-
|
||||
The model that was used to generate the chat completion
|
||||
usage:
|
||||
$ref: '#/components/schemas/OpenAIChatCompletionUsage'
|
||||
description: >-
|
||||
Token usage information (typically included in final chunk with stream_options)
|
||||
additionalProperties: false
|
||||
required:
|
||||
- id
|
||||
|
|
@ -4060,6 +4115,10 @@ components:
|
|||
type: string
|
||||
description: >-
|
||||
The model that was used to generate the chat completion
|
||||
usage:
|
||||
$ref: '#/components/schemas/OpenAIChatCompletionUsage'
|
||||
description: >-
|
||||
Token usage information for the completion
|
||||
input_messages:
|
||||
type: array
|
||||
items:
|
||||
|
|
@ -5700,6 +5759,10 @@ components:
|
|||
type: string
|
||||
description: >-
|
||||
(Optional) Truncation strategy applied to the response
|
||||
usage:
|
||||
$ref: '#/components/schemas/OpenAIResponseUsage'
|
||||
description: >-
|
||||
(Optional) Token usage information for the response
|
||||
input:
|
||||
type: array
|
||||
items:
|
||||
|
|
@ -5791,6 +5854,42 @@ components:
|
|||
title: OpenAIResponseText
|
||||
description: >-
|
||||
Text response configuration for OpenAI responses.
|
||||
OpenAIResponseUsage:
|
||||
type: object
|
||||
properties:
|
||||
input_tokens:
|
||||
type: integer
|
||||
description: Number of tokens in the input
|
||||
output_tokens:
|
||||
type: integer
|
||||
description: Number of tokens in the output
|
||||
total_tokens:
|
||||
type: integer
|
||||
description: Total tokens used (input + output)
|
||||
input_tokens_details:
|
||||
type: object
|
||||
properties:
|
||||
cached_tokens:
|
||||
type: integer
|
||||
description: Number of tokens retrieved from cache
|
||||
additionalProperties: false
|
||||
description: Detailed breakdown of input token usage
|
||||
output_tokens_details:
|
||||
type: object
|
||||
properties:
|
||||
reasoning_tokens:
|
||||
type: integer
|
||||
description: >-
|
||||
Number of tokens used for reasoning (o1/o3 models)
|
||||
additionalProperties: false
|
||||
description: Detailed breakdown of output token usage
|
||||
additionalProperties: false
|
||||
required:
|
||||
- input_tokens
|
||||
- output_tokens
|
||||
- total_tokens
|
||||
title: OpenAIResponseUsage
|
||||
description: Usage information for OpenAI response.
|
||||
ResponseShieldSpec:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -6117,6 +6216,10 @@ components:
|
|||
type: string
|
||||
description: >-
|
||||
(Optional) Truncation strategy applied to the response
|
||||
usage:
|
||||
$ref: '#/components/schemas/OpenAIResponseUsage'
|
||||
description: >-
|
||||
(Optional) Token usage information for the response
|
||||
additionalProperties: false
|
||||
required:
|
||||
- created_at
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue