{"version":"2.1.251","anchor":"keeping-another-vendor-s-thinking-text-across-a-model-upgrad","canonical_anchor":"keeping-another-vendor-s-thinking-text-across-a-model-upgrad","heading":"Keeping another vendor's thinking text across a model upgrade","tier":"soon","area":"Models","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.251\/e\/keeping-another-vendor-s-thinking-text-across-a-model-upgrad","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.251","markdown":"### Keeping another vendor's thinking text across a model upgrade\n\nReasoning text from a non-Claude model can survive a model switch, off unless enabled.\n\n**What**\n\nA setting decides whether reasoning text produced by a non-Claude model survives an upgrade to a different model instead of being discarded. It is off unless the `tengu_luminous_whistle` experiment turns it on, and `CLAUDE_CODE_LUMINOUS_WHISTLE` overrides either way. Even then it only applies when a separate precondition holds.\n\n**Details**\n\n- Decided once per session and reset on clear, resume, spare claim and remote attach.\n- Logs `api_keep_thinking_on_upgrade` when it either keeps or rejects the thinking text.\n\n**Evidence**\n\n`tengu_luminous_whistle`\n\n- Area: Models\n- Names: `CLAUDE_CODE_LUMINOUS_WHISTLE`\n- Tier: Nothing to try yet\n- Useful: 2\/5\n- Signal: 4\/5\n- Present in the build but not switched on"}