fix(sdk): gate reasoning effort by runtime allowlist

This commit is contained in:
radioflyer28
2026-05-13 22:27:15 -04:00
parent c20f714d68
commit 810778e137
7 changed files with 80 additions and 6 deletions

View File

@@ -980,7 +980,7 @@ The intent is the same as the Claude profile tiers -- use a stronger model for p
When `runtime` is set, profile tiers (`opus`/`sonnet`/`haiku`) resolve to runtime-native model IDs instead of Claude aliases. This lets a single shared `.planning/config.json` work cleanly across Claude and Codex.
`resolve-model` JSON output includes `reasoning_effort` when it is defined by the same runtime tier that selected the model. Runtime adapters may pass that value to child-agent launch calls that support it; runtimes without explicit support omit it.
`resolve-model` JSON output includes `reasoning_effort` when the runtime tier resolved for the agent (after phase-type overrides) defines a `reasoning_effort`. Runtime adapters may pass that value to child-agent launch calls that support it; runtimes without explicit support omit it.
**Built-in tier maps:**