Skip to main content
AgentCompass has two concurrency layers: per-run task concurrency and process-global provider limits.

​
Per-Run Concurrency

agentcompass run \
  swebench_verified \
  mini_swe_agent \
  your-model \
  --env <env-provider> \
  --model-base-url "$MODEL_BASE_URL" \
  --model-api-key "$MODEL_API_KEY" \
  --task-concurrency 32
--task-concurrency controls how many benchmark tasks can execute in parallel for this run.

​
Provider Limits

Provider limits live in code defaults and can be overridden with runtime.provider_limits in private config files. They default to 128 per provider and cap concurrent sessions across the process, even if a run requests a higher task concurrency.
LimitControls
task_concurrencyTasks in one run.
runtime.provider_limits.<provider>Process-wide sessions for a provider.
Model endpoint rate limitExternal API throughput and retry behavior.

​
Practical Workflow

  1. Start with one sample_ids task.
  2. Increase --task-concurrency gradually.
  3. Watch model errors, provider startup time, and task timeout failures.
  4. Keep provider limits below account or cluster quotas.