✓ PASS

litellm 1.105.5

usage.stream-final-chunk · anthropic

Requirements

Id	Level	Status	Evidence
usage-reported	MUST	SATISFIED	usage.input=25 (primary); truth.usage.input=25; usage.output=12 (primary); truth.usage.output=12

What the provider sent

Finish: stop
Raw finish: end_turn
Text: Air scatters blue light more strongly.
Tool calls: []
Usage: { "alternatives": {}, "cached_input": null, "input": 25, "output": 12, "raw": { "input_tokens": 25, "output_tokens": 12 }, "reasoning": null, "total": 37 }
Stream completed: true
Error: null

Wire excerpt

status: 200
content-type: text/event-stream
body (sse):
event: message_start
data: {"type": "message_start", "message": {"id": "msg_01Aq9w938a90dw8q", "type": "message", "role": "assistant", "content": [], "model": "claude-sonnet-5-5", "stop_reason": null, "stop_sequence": null, "usage": {"input_tokens": 25, "output_tokens": 1}}}


event: content_block_start
data: {"type": "content_block_start", "index": 0, "content_block": {"type": "text", "text": ""}}


event: ping
data: {"type": "ping"}


event: content_block_delta
data: {"type": "content_block_delta", "index": 0, "delta": {"type": "text_delta", "text": "Air "}}


event: content_block_delta
data: {"type": "content_block_delta", "index": 0, "delta": {"type": "text_delta", "text": "scatters blue light more strongly."}}


event: content_block_stop
data: {"type": "content_block_stop", "index": 0}


event: message_delta
data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"output_tokens":12}}


event: message_stop
data: {"type": "message_stop"}

What the library reported

Outcome

returned

Finish

{
  "raw": "stop",
  "source": "choices[0].finish_reason",
  "surface": "primary",
  "value": "stop"
}

Text

Value: Air scatters blue light more strongly.
Surface: primary

Tool calls

[]

Usage

{
  "cached_input": 0,
  "input": 25,
  "output": 12,
  "reasoning": 0,
  "surface": {
    "cached_input": "primary",
    "input": "primary",
    "output": "primary",
    "reasoning": "primary",
    "total": "primary"
  },
  "total": 37
}

Stream

{
  "chunks_seen": 4,
  "completed": null,
  "used": true
}

Error

null

Unsupported reason

null

Full observation JSON

{
  "elapsed_ms": 361.7961881682277,
  "error": null,
  "finish": {
    "raw": "stop",
    "source": "choices[0].finish_reason",
    "surface": "primary",
    "value": "stop"
  },
  "format": "wiretruth.observation/v1",
  "library": {
    "api": "litellm.completion",
    "language": "python",
    "name": "litellm",
    "version": "1.105.5"
  },
  "notes": [],
  "outcome": "returned",
  "stream": {
    "chunks_seen": 4,
    "completed": null,
    "used": true
  },
  "structured": {
    "attempted": false,
    "returned_as_success": false,
    "value": null
  },
  "text": {
    "surface": "primary",
    "value": "Air scatters blue light more strongly."
  },
  "tool_calls": [],
  "unsupported_reason": null,
  "usage": {
    "cached_input": 0,
    "input": 25,
    "output": 12,
    "reasoning": 0,
    "surface": {
      "cached_input": "primary",
      "input": "primary",
      "output": "primary",
      "reasoning": "primary",
      "total": "primary"
    },
    "total": 37
  }
}

Fixture

documented anthropic/usage.stream-final-chunk

Provenance	Value
Source	https://platform.claude.com/docs/en/build-with-claude/streaming#basic-streaming-request
Notes	Documented shapes, not a recording. Message envelope and stop fields follow handling-stop-reasons; content blocks follow thinking/streaming and handle-tool-calls. Model changed to claude-sonnet-5-5; IDs and scenario text are filled in. Token counts are illustrative, filled in to include thinking within the requested output limit, not measured. Based on the basic Hello stream, changing model and text to the scenario. Initial usage has input_tokens 25 and output_tokens 1; final cumulative output_tokens is filled in as 12. Adaptive thinking is assumed skipped; no cache fields were present in the base example. SSE names, JSON shapes, field order and spaced text/thinking events follow streaming examples; the compact message_delta follows Streaming request with tool use. Fragment boundaries and counts are filled in. Signature placeholder is copied literally from the signature_delta example; empty thinking_delta follows the documented omitted display flow.

Provenance

Value

Source

https://platform.claude.com/docs/en/build-with-claude/streaming#basic-streaming-request

Notes

Documented shapes, not a recording. Message envelope and stop fields follow handling-stop-reasons; content blocks follow thinking/streaming and handle-tool-calls. Model changed to claude-sonnet-5-5; IDs and scenario text are filled in. Token counts are illustrative, filled in to include thinking within the requested output limit, not measured. Based on the basic Hello stream, changing model and text to the scenario. Initial usage has input_tokens 25 and output_tokens 1; final cumulative output_tokens is filled in as 12. Adaptive thinking is assumed skipped; no cache fields were present in the base example. SSE names, JSON shapes, field order and spaced text/thinking events follow streaming examples; the compact message_delta follows Streaming request with tool use. Fragment boundaries and counts are filled in. Signature placeholder is copied literally from the signature_delta example; empty thinking_delta follows the documented omitted display flow.

Reproduce

wiretruth serve anthropic/usage.stream-final-chunk

Plain-library snippet from the shim manifest.

litellm.completion(model='anthropic/' + model, api_base=WIRETRUTH_BASE_URL_ANTHROPIC, api_key=WIRETRUTH_API_KEY); host root, LiteLLM appends /v1/messages

Upstream

No matching upstream report.

History

Version	Grade
1.105.5	✓ PASS
1.105.1	✓ PASS