fix(core): prevent inflated token counts when merging streaming usage_metadata
#35615Comparing
ShresthSamyak:fix-streaming-token-count
(ce9e7a3
) withmaster
(29134dc
)+2%
- Untouched
- 13
- Skipped
- 23
Unknown Walltime execution environment detected
Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data. For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.Benchmarks
36 total
test_import_time[Runnable]
libs/core/tests/benchmarks/test_imports.py+3%
538 ms*522.2 ms
test_import_time[CallbackManager]
libs/core/tests/benchmarks/test_imports.py+3%
341.3 ms*332.2 ms
test_import_time[InMemoryRateLimiter]
libs/core/tests/benchmarks/test_imports.py+3%
186 ms*181.1 ms
test_import_time[InMemoryVectorStore]
libs/core/tests/benchmarks/test_imports.py+3%
650.8 ms*634.6 ms
test_import_time[ChatPromptTemplate]
libs/core/tests/benchmarks/test_imports.py+2%
682.8 ms*666.9 ms
test_import_time[RunnableLambda]
libs/core/tests/benchmarks/test_imports.py+2%
537.2 ms*524.8 ms
test_import_time[Document]
libs/core/tests/benchmarks/test_imports.py+2%
198 ms*194.1 ms
test_import_time[tool]
libs/core/tests/benchmarks/test_imports.py+2%
587.4 ms*578.6 ms
test_import_time[BaseChatModel]
libs/core/tests/benchmarks/test_imports.py+1%
573.8 ms*565.7 ms
test_import_time[PydanticOutputParser]
libs/core/tests/benchmarks/test_imports.py+1%
583 ms*575.2 ms
test_import_time[HumanMessage]
libs/core/tests/benchmarks/test_imports.py+1%
279.1 ms*276.5 ms
test_async_callbacks_in_sync
libs/core/tests/benchmarks/test_async_callbacks.py+1%
25.6 ms*25.4 ms
test_import_time[LangChainTracer]
libs/core/tests/benchmarks/test_imports.py0%
485.8 ms*483.5 ms
The benchmarks below were skipped, so their baseline results are used instead. If they were deleted in your codebase, archive them to remove them from the performance reports.
Learn more about archiving benchmarks
Learn more about archiving benchmarks
test_create_chat_prompt_init_time
libs/partners/prompty/tests/unit_tests/test_standard.pySkipped
311.9 µs*
test_qdrant_vectorstore_init_time
libs/partners/qdrant/tests/unit_tests/test_standard.pySkipped
225 ms*
test_exa_retriever_init_time
libs/partners/exa/tests/unit_tests/test_standard.pySkipped
316.4 µs*
test_init_time
libs/partners/ollama/tests/unit_tests/test_chat_models.py::TestChatOllamaSkipped
1.6 s*
test_nomic_embeddings_init_time
libs/partners/nomic/tests/unit_tests/test_standard.pySkipped
1.5 ms*
test_init_time
libs/partners/mistralai/tests/unit_tests/test_standard.py::TestMistralStandardSkipped
9.2 ms*
test_init_time
libs/partners/xai/tests/unit_tests/test_chat_models_standard.py::TestXAIStandardSkipped
3.3 s*
test_init_time
libs/partners/perplexity/tests/unit_tests/test_chat_models_standard.py::TestPerplexityStandardSkipped
1.7 s*
test_init_time
libs/partners/anthropic/tests/unit_tests/test_standard.py::TestAnthropicBedrockStandardSkipped
1.1 ms*
test_init_time
libs/partners/deepseek/tests/unit_tests/test_chat_models.py::TestChatDeepSeekUnitSkipped
1.6 s*
test_chroma_init_time
libs/partners/chroma/tests/unit_tests/test_standard.pySkipped
60.7 ms*
test_init_time
libs/partners/fireworks/tests/unit_tests/test_standard.py::TestFireworksStandardSkipped
6.6 s*
Commits
Click on a commit to change the comparison rangeBase
master
29134dc
+3.91%
fix(core): prevent inflated token counts when merging streaming usage_metadata
26a849c
4 months ago
by ShresthSamyak-0.62%
fix(core): handle cumulative usage_metadata in streaming merges without breaking normal merge behavior
98321ca
4 months ago
by ShresthSamyak-1.42%
fix(core): correctly merge cumulative and delta usage_metadata
12ec745
4 months ago
by ShresthSamyak+21.02%
style(core): fix lint formatting
17fb544
4 months ago
by ShresthSamyak-21.05%
Merge branch 'master' into fix-streaming-token-count
ce9e7a3
4 months ago
by ShresthSamyak