Skip to content

fix(mcp): reasoning.effort 'minimal' incompatible with gpt-5.4-mini #1378

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
daniel-rudaev wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix(mcp): reasoning.effort 'minimal' incompatible with gpt-5.4-mini #1378

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions mcp_server/docker/Dockerfile.standalone
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,14 @@ RUN sed -i '/\[tool\.uv\.sources\]/,/graphiti-core/d' pyproject.toml && \
RUN --mount=type=cache,target=/root/.cache/uv \
uv sync --no-group dev

# Patch graphiti-core: reasoning.effort 'minimal' is not supported by newer
# OpenAI models (gpt-5.4-mini etc). Change default to 'low'.
# See: https://github.com/getzep/graphiti/issues/902
RUN sed -i "s/DEFAULT_REASONING = 'minimal'/DEFAULT_REASONING = 'low'/" \
.venv/lib/python*/site-packages/graphiti_core/llm_client/openai_base_client.py && \
find .venv/lib/python*/site-packages/graphiti_core/ -name '__pycache__' -type d -exec rm -rf {} + 2>/dev/null; \
python -m compileall .venv/lib/python*/site-packages/graphiti_core/ -q || true

# Store graphiti-core version
RUN echo "${GRAPHITI_CORE_VERSION}" > /app/mcp/.graphiti-core-version

Expand Down
2 changes: 1 addition & 1 deletion mcp_server/src/services/factories.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,7 +133,7 @@ def create(config: LLMConfig) -> LLMClient:

# Only pass reasoning/verbosity parameters for reasoning models (gpt-5 family)
if is_reasoning_model:
return OpenAIClient(config=llm_config, reasoning='minimal', verbosity='low')
return OpenAIClient(config=llm_config, reasoning='low', verbosity='low')
else:
# For non-reasoning models, explicitly pass None to disable these parameters
return OpenAIClient(config=llm_config, reasoning=None, verbosity=None)
Expand Down
Loading