Anthropic fixes Claude Code quality regressions and resets usage limits for subscribers

ClaudeDevsClaudeDevs

· Updated

Anthropic released a post-mortem identifying three issues in the Claude Code and Agent SDK harness that caused recent quality slips. While the underlying models remained stable, the update highlights how orchestration layers can degrade performance even when the AI itself is unchanged.

Anthropic released a post-mortem addressing reports that Claude Code quality had declined. The investigation identified three issues within the tool's harness and the Agent SDK—the orchestration layer managing model-environment interactions. All identified bugs are now resolved in version 2.1.116 or later.

This regression confirms that reports of models getting dumber are often rooted in implementation rather than weights. Because Claude Code follows the same agentic architecture as other Anthropic tools, the slip also impacted Cowork. The fix restores the high-speed navigation and reasoning capabilities users expect.

Subscribers should update immediately to benefit from the fixes and a reset of their usage limits. The stabilization follows recent ecosystem expansions like external application triggers for Claude Desktop. To prevent future regressions, Anthropic is expanding its internal evaluation suites and dogfooding configurations that mirror user setups.

View the full update on anthropic.com
ClaudeDevs
ClaudeDevs
@ClaudeDevs
X

Over the past month, some of you reported Claude Code's quality had slipped. We investigated, and published a post-mortem on the three issues we found. All are fixed in v2.1.116+ and we’ve reset usage limits for all subscribers.

1.3kretweets21klikes
View on X

Still wondering? A few quick answers below.

Anthropic identified three specific issues within the Claude Code harness and the Agent SDK. These regressions were rooted in the orchestration layer—the system that manages how the AI interacts with tools and codebases—rather than the models themselves. Because Cowork runs on the same SDK, it was also impacted by these performance slips.

To restore performance, you must update to version 2.1.116 or later. Anthropic confirmed that all three identified issues are resolved in this release. Users can check their current version in the terminal and update to the latest build to ensure they are using the corrected Agent SDK and system prompt configurations.

No, the underlying Claude models and the Claude API were not affected by these issues. The quality decline was strictly caused by the Agent SDK harness and the way the tool orchestrated model actions. The models themselves did not change, and their raw performance remains stable outside of the Claude Code environment.

Anthropic is implementing stricter internal dogfooding by using configurations that exactly match those of their users. They are also creating a broader set of evaluations to test system prompt changes in isolation. These process improvements are designed to catch orchestration and harness issues before they reach the public production environment.

Yes, Anthropic has reset usage limits for all subscribers to compensate for the period of degraded performance. This reset allows users to resume their workflows without being penalized for the extra tokens or attempts used while the tool was experiencing the identified quality regressions in the Agent SDK and harness.

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

Share this update