What this error means
could not be parsed (retry also failed) — Opus 4.7 tool calls fail repeatedly starting 2026-05-20 is a Claude Code failure pattern reported for developers trying to claude code pro/max users running opus 4.7 encounter tool call parsing failures where retries also fail, leaving agents stuck. regression started may 20, 2026. labeled 'has repro' with detailed reproduction steps.. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.
Why this happens
Source: anthropics/claude-code#61133 (opened May 21, 2026, today). Labeled area:model, bug, has repro. Critical regression affecting all Opus 4.7 tool calls — parse errors in function calling format are not self-healing across retries. Directly impacts Pro/Max paying subscribers. Category: AI Coding Tools — model parsing failure in paid tier.
Common causes
- Source: anthropics/claude-code#61133 (opened May 21, 2026, today). Labeled area:model, bug, has repro. Critical regression affecting all Opus 4.7 tool calls — parse errors in function calling format are not self-healing across retries. Directly impacts Pro/Max paying subscribers. Category: AI Coding Tools — model parsing failure in paid tier.
Quick fixes
- Confirm the exact error signature matches
could not be parsed (retry also failed) — Opus 4.7 tool calls fail repeatedly starting 2026-05-20. - 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.