Anthropic released a model update and thousands of carefully configured OpenClaw agents stopped working overnight.
When Anthropic released Sonnet 4.6, thousands of OpenClaw users discovered that their carefully tuned agent configurations were suddenly incompatible. Agents that had been running reliably for weeks began hallucinating, ignoring instructions, and entering infinite loops. The issue was subtle: the new model's longer context window and different instruction-following characteristics changed how it interpreted existing system prompts. Users who had optimized their prompts for Sonnet 4.5's behavior found those same prompts produced wildly different results with 4.6.
AFFECTED USERS: ~5,000
The Actual Culprit
OpenClaw auto-updated to the latest model without version pinning. Agent prompts that were tuned for one model's behavior became unreliable with the new version's different instruction-following characteristics.
Auto-upgrading to 'latest' means your agent's behavior is at the mercy of someone else's release schedule.
Model updates are not backward compatible for prompt behavior. Test your agents against new versions before switching.
If a small change in model behavior breaks your agent, your prompts are too brittle and need structural improvement.
Loading comments...