What this error means
API Error: 400 Could not process image is a Claude Code failure pattern reported for developers trying to fix claude code 400 could not process image crash on valid screenshots. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.
Why this happens
Valid 1080x2640 PNG screenshots (~250KB) from adb shell screencap cause 400 error when loaded into context. Agent sessions crash, tool_uses counter continues but output replaced by error. Related to issues #47976 and #55767 but different root cause.
Common causes
- Valid PNG screenshots captured by agents (e.g., via adb screencap) are rejected by the multimodal API with 400 error. The entire agent task crashes ungracefully, partial work is lost, and the agent's result is replaced by the error string. No client-side resize or graceful degradation.
- Valid 1080x2640 PNG screenshots (~250KB) from adb shell screencap cause 400 error when loaded into context. Agent sessions crash, tool_uses counter continues but output replaced by error. Related to issues #47976 and #55767 but different root cause.
Quick fixes
- Confirm the exact error signature matches
API Error: 400 Could not process image. - Check the Claude Code account, local tool state, and provider configuration involved in the failing workflow.
- Compare the failing environment with a known working setup, then change one configuration value at a time.
Platform/tool-specific checks
- Verify the command, editor, extension, or API client that produced the error.
- Compare local settings with CI, deployment, or editor-level settings when the error appears in only one environment.
- Avoid deleting credentials, local model data, or project settings until the failing scope is clear.
Step-by-step troubleshooting
- Capture the exact error message and the command, editor action, or request that triggered it.
- Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
- Review the source evidence below and compare it with your environment.
- Apply one change at a time and rerun the smallest failing action.
- Keep the working fix documented for the team or deployment environment.
How to prevent it
- Keep provider/tool configuration documented.
- Record non-secret diagnostics such as tool version, provider name, model name, and command path.
- Add a lightweight check before CI or production workflows depend on the tool.