{"version":"2.1.286","anchor":"workflow-schema-lint-enforcement","canonical_anchor":"workflow-schema-lint-enforcement","heading":"Impossible agent schemas in workflows are handled as before","tier":"internal","area":"Workflows","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.286\/e\/workflow-schema-lint-enforcement","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.286","markdown":"### Impossible agent schemas in workflows are handled as before\n\nThe workflow check for agent output formats that can never be met behaves the same as in the previous build\n\n**What**\n\nIn workflows, an agent can be given a schema, a required shape for its output. If that shape can never be met, Claude Code stops with an error when a server setting is on, and otherwise only logs a warning. When the server sends nothing, the setting falls back to on. Apart from internal renaming, this code is the same as before.\n\n**Why**\n\nNothing about this behaviour differs for you in this release.\n\n- Flag `tengu_workflow_schema_lint_enforce`: Not enough to say (read for one account on one subscription tier against v2.1.286; this account: no value returned, anonymous baseline: no value returned, compiled default: on) These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.\n- Area: Workflows\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 0\/5"}