Source Intelligence

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

All of v2.1.169 Home All releases olderv2.1.168 v2.1.170newer

Refusal Continuation — Silent Retry with Fallback Model [In Development]

What

When the model refuses a request for safety reasons, Claude Code will silently retry with a designated fallback model. If the fallback model responds successfully, the conversation continues as if nothing happened; if the fallback also refuses, the refusal is shown normally.

Status

Feature-flagged. Gated by a server-side refusal_fallback_prompt feature flag that must be present in the account's beta header list.

Details
  • A refusalFallbackModelLatch tracks which fallback model was activated and what the previous model override was, so the model is restored after the retry turn
  • The detection function fTK() returns false unless On8() (refusal continuation enabled) AND refusal_fallback_prompt is absent from the beta list
  • Infrastructure includes latch set/clear/update functions and a refusalFallbackOccurred flag for telemetry
Evidence

Gated by server-side flag (search for "refusal_fallback_prompt") — fTK() at line ~122285, refusalFallbackModelLatch state at line ~2551

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

See this entry in the whole of v2.1.169 →