{"version":"2.1.133","anchor":"reasoning-effort-exposed-to-hooks-and-bash","canonical_anchor":"reasoning-effort-exposed-to-hooks-and-bash","heading":"Reasoning Effort Exposed to Hooks and Bash","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.133\/e\/reasoning-effort-exposed-to-hooks-and-bash","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.133","markdown":"### Reasoning Effort Exposed to Hooks and Bash\n\nHook authors get structured reasoning-effort information for tool-use lifecycle hooks, and Bash receives the active value as `CLAUDE_EFFORT` when the model supports effort.\n\n**Usage**\n\n`echo \"$CLAUDE_EFFORT\"` **Details** - Hook input now includes an optional `effort.level` field. - The value reflects the active effort level after any model-specific downgrade. - The field is present for tool-use contexts such as `PreToolUse`, `PostToolUse`, `Stop`, and `SubagentStop`, but absent for session-lifecycle hooks and models without effort support. **Evidence** Hook schema and Bash environment wiring (search for `\"Reasoning effort applied to the current turn\"` and `\"Active effort level for the current turn\"`)."}