dataset_name = "openswe-reviewer-v1"
experiment_prefix = "openswe-review-confidence"
max_concurrency = 5

# LangSmith tracing project for eval runs. Keeps eval traces out of the
# deployment's production project.
langsmith_project = "open-swe-evals"

# Leave blank to use LANGGRAPH_URL or local dev.
langgraph_url = ""
assistant_id = "reviewer"
# models: openai:gpt-5.5, anthropic:claude-opus-4-8, google_genai:gemini-3.5-flash
model_id = "google_genai:gemini-3.5-flash"
reasoning_effort = "medium"

# score_mode:
# - "all_findings" — score every add_finding the agent emits (no gating).
# - "surfaced_findings" — only findings that pass the production severity
#   threshold and cap.
score_mode = "all_findings"
severity_threshold = "medium"
cap = 4