How a Single API Field Can Save Days of Debugging Truncated LLM Outputs

When a large language model returns an incomplete response, the root cause is almost always visible in a field most developers overlook: finish_reason in OpenAI-compatible APIs and stop_reason in Anthropic's. Both fields are populated on every non-streaming response and indicate exactly why generation stopped, yet most integrations never check them. Common stop reasons include length or max_tokens for budget overruns, content_filter for safety interventions, and tool_calls for mid-task tool invocations — each requiring a different fix rather than a blind retry. Developers are advised to assert valid stop reasons at the API boundary so that errors surface at their true source instead of propagating as unrelated parser failures. Tracking the distribution of stop reasons over time also serves as a low-cost diagnostic metric, revealing issues like undersized output budgets, policy filter activity, or transport-level stream drops.