"""Final provider usage must survive progressive and partial backend frames. The OpenAI-via-backend stream path is fed cumulative usage snapshots: a provider may repeat `usage` on several content chunks with climbing counts before its terminal frame. Accounting must record the LAST snapshot, not the first nonzero one, and a frame that omits a counter must leave that counter alone rather than resetting it to zero. """ import asyncio import json from types import SimpleNamespace import pytest from headroom.proxy.handlers.streaming import StreamingMixin @pytest.mark.parametrize("responses", [False, True], ids=["chat", "responses"]) @pytest.mark.parametrize( ("last", "expected"), [ ( { "input_tokens": 13, "output_tokens": 5, "input_tokens_details": {"cached_tokens": 9, "cache_write_tokens": 1}, }, (13, 5, 9, 1), ), ({"output_tokens": 5}, (10, 5, 2, 3)), ( { "input_tokens": 0, "output_tokens": 0, "input_tokens_details": {"cached_tokens": 0, "cache_write_tokens": 0}, }, (0, 0, 0, 0), ), ({}, (10, 1, 2, 3)), ], ids=["latest-snapshot", "partial", "explicit-zero", "absent"], ) def test_backend_stream_records_latest_present_usage(responses, last, expected): initial = { "input_tokens": 10, "output_tokens": 1, "input_tokens_details": {"cached_tokens": 2, "cache_write_tokens": 3}, } def frame(usage): if responses: data = {"response": {"usage": usage}} else: names = { "input_tokens": "prompt_tokens", "output_tokens": "completion_tokens", "input_tokens_details": "prompt_tokens_details", } data = {"usage": {names[key]: value for key, value in usage.items()}} return f"data: {json.dumps(data)}\n\n" class Backend: name = "openai" async def stream_openai_message(self, body, headers): yield frame(initial) yield 'data: {"choices":[{"delta":{"content":"answer"}}]}\n\n' yield frame(last) yield "data: [DONE]\n\n" class Handler(StreamingMixin): config = SimpleNamespace(ccr_inject_tool=False) anthropic_backend = Backend() async def _record_request_outcome(self, outcome): self.outcome = outcome handler = Handler() async def consume(): response = await handler._stream_openai_via_backend( {"messages": []}, {}, "model", "request", 0.0, 10, 10, 0, [], {}, 0.0 ) async for _ in response.body_iterator: pass asyncio.run(consume()) outcome = handler.outcome assert outcome.status_code == 200 assert ( outcome.provider_input_tokens, outcome.output_tokens, outcome.cache_read_tokens, outcome.cache_write_tokens, ) == expected assert outcome.cache_inferred is False