bhaskargurram-ai:fix/tool-runtime-with-basemodel-33646 - Branch - langchain-ai/langchain

fix(core): preserve injected arguments when args_schema is BaseModel

#33649

Comparing

bhaskargurram-ai:fix/tool-runtime-with-basemodel-33646

(

f0d4343

) with

master

(

ef85161

)

+18%

Improvements: 6

Untouched: 7

Skipped: 21

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

Skipped (21)

Improved

test_import_time[BaseChatModel]

libs/core/tests/benchmarks/test_imports.py

+18%

605.6 ms515.3 ms

test_import_time[PydanticOutputParser]

libs/core/tests/benchmarks/test_imports.py

+16%

604.2 ms521.6 ms

test_import_time[CallbackManager]

libs/core/tests/benchmarks/test_imports.py

+13%

523.4 ms463.5 ms

test_import_time[Runnable]

libs/core/tests/benchmarks/test_imports.py

+13%

558.5 ms495.9 ms

test_import_time[LangChainTracer]

libs/core/tests/benchmarks/test_imports.py

+12%

493.1 ms439.2 ms

test_import_time[InMemoryVectorStore]

libs/core/tests/benchmarks/test_imports.py

+11%

692.1 ms621.5 ms

Passed

test_import_time[ChatPromptTemplate]

libs/core/tests/benchmarks/test_imports.py

+10%

667.1 ms606.6 ms

test_async_callbacks_in_sync

libs/core/tests/benchmarks/test_async_callbacks.py

+10%

26 ms23.7 ms

test_import_time[Document]

libs/core/tests/benchmarks/test_imports.py

+9%

206 ms188.6 ms

test_import_time[HumanMessage]

libs/core/tests/benchmarks/test_imports.py

+9%

300.9 ms275.5 ms

test_import_time[RunnableLambda]

libs/core/tests/benchmarks/test_imports.py

+8%

541.9 ms500 ms

test_import_time[tool]

libs/core/tests/benchmarks/test_imports.py

+8%

567.1 ms526.1 ms

test_import_time[InMemoryRateLimiter]

libs/core/tests/benchmarks/test_imports.py

+6%

189.8 ms179.2 ms

Commits

Click on a commit to change the comparison range

Base

master

ef85161

+17.53%

Fix: Preserve injected arguments in _parse_input when using BaseModel When args_schema is defined as a Pydantic BaseModel, injected parameters like ToolRuntime were being filtered out. This fix preserves all fields from the original input, even those not defined in the schema. Fixes #33646

f0d4343

6 days ago

by bhaskargurram-ai

Home Terms Privacy Docs