TokuiNico:fix/core-tool-args-fenced-json - Branch - langchain-ai/langchain

langchain-ai

langchain

Instrumentation

Wall Time

Blog Docs Changelog

fix(core): accept fenced JSON in tool call arguments

#33012

Comparing

TokuiNico:fix/core-tool-args-fenced-json

(

1332130

) with

master

(

90280d1

)

+2%

Untouched: 13

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.

No successful run was found on master ( f2b0afd) during the generation of this report, so 90280d1 was used instead as the comparison base. There might be some changes unrelated to this pull request in this report.

Benchmarks

Passed

test_import_time[PydanticOutputParser]

libs/core/tests/benchmarks/test_imports.py::test_import_time[PydanticOutputParser]

+4%

568.9 ms548.5 ms

test_import_time[RunnableLambda]

libs/core/tests/benchmarks/test_imports.py::test_import_time[RunnableLambda]

+3%

496.8 ms483.9 ms

test_import_time[BaseChatModel]

libs/core/tests/benchmarks/test_imports.py::test_import_time[BaseChatModel]

+2%

547 ms534.3 ms

test_import_time[tool]

libs/core/tests/benchmarks/test_imports.py::test_import_time[tool]

+2%

524.2 ms513.5 ms

test_import_time[HumanMessage]

libs/core/tests/benchmarks/test_imports.py::test_import_time[HumanMessage]

+2%

217.8 ms213.4 ms

test_import_time[InMemoryRateLimiter]

libs/core/tests/benchmarks/test_imports.py::test_import_time[InMemoryRateLimiter]

+2%

171.3 ms168.1 ms

test_import_time[InMemoryVectorStore]

libs/core/tests/benchmarks/test_imports.py::test_import_time[InMemoryVectorStore]

+2%

638.2 ms627.3 ms

test_async_callbacks_in_sync

libs/core/tests/benchmarks/test_async_callbacks.py::test_async_callbacks_in_sync

+2%

24.4 ms24 ms

test_import_time[Runnable]

libs/core/tests/benchmarks/test_imports.py::test_import_time[Runnable]

+1%

490.5 ms483.6 ms

test_import_time[LangChainTracer]

libs/core/tests/benchmarks/test_imports.py::test_import_time[LangChainTracer]

+1%

438.1 ms432.1 ms

test_import_time[Document]

libs/core/tests/benchmarks/test_imports.py::test_import_time[Document]

+1%

216.5 ms213.6 ms

test_import_time[CallbackManager]

libs/core/tests/benchmarks/test_imports.py::test_import_time[CallbackManager]

459 ms458.7 ms

test_import_time[ChatPromptTemplate]

libs/core/tests/benchmarks/test_imports.py::test_import_time[ChatPromptTemplate]

-1%

631.9 ms636.9 ms

Commits

Click on a commit to change the comparison range

Base

master

90280d1

-1.53%

fix(core): accept fenced JSON in tool call arguments via markdown-aware strict parsing\n\n- Use parse_json_markdown in parse_tool_call when partial=False (no partial fill)\n- Keep strict json.loads under the hood; incomplete JSON still errors\n- Add unit tests for normal, fenced, and incomplete JSON cases

216b95d

13 days ago

by TokuiNico

+4.48%

style(core): format imports in openai_tools parser to match project conventions

bb97fe1

13 days ago

by TokuiNico

-2.57%

fix(tests): format codes

e681bf3

13 days ago

by TokuiNico

+1.28%

Merge branch 'master' into fix/core-tool-args-fenced-json

1332130

12 days ago

by TokuiNico

Home Terms Privacy Docs