{"name":"CLAUDE_CODE_WORKFLOW_PROMPT_PROVENANCE","slug":"claude-code-workflow-prompt-provenance","family":"env","title":"Environment variables","noun":"environment variable","description":"Workflow runs now label whether a person or a schedule triggered them, and quote the request.","description_source":"entry","described_by":{"version":"2.1.242","anchor":"workflow-tasks-can-relay-the-triggering-request-in-a-labelle"},"presence":{"first_seen":null,"removed_in":null,"in_current_build":false,"newest_mined":"2.1.308","builds":0,"mined_builds":149,"first_cited":{"version":"2.1.277","released_at":"2026-09-18 16:22:26","spans":2}},"aliases":[],"entries":[{"version":"2.1.277","anchor":"new-claude-code-workflow-prompt-provenance-env-var-replaces","heading":"New CLAUDE_CODE_WORKFLOW_PROMPT_PROVENANCE env var replaces CLAUDE_CODE_DAPPER_LAGOON, backed by tengu_bubbly_harbor and made synchronous","line":"Workflow prompt provenance now read from CLAUDE_CODE_WORKFLOW_PROMPT_PROVENANCE and made synchronous","released_at":"2026-09-18 16:22:26","reason":"found in this entry's text"},{"version":"2.1.242","anchor":"workflow-tasks-can-relay-the-triggering-request-in-a-labelle","heading":"Workflow tasks can relay the triggering request in a labelled frame","line":"Workflow runs now label whether a person or a schedule triggered them, and quote the request.","released_at":"2026-08-24 19:16:14","reason":"named in this entry, found in this entry's text"}],"entries_total":2,"docs":[],"docs_total":0,"gates":[],"related":[{"name":"CLAUDE_CODE_WORKFLOW_MAX_CONCURRENT_AGENTS","slug":"claude-code-workflow-max-concurrent-agents","description":"Workflow tool's concurrent-agent limit can now be overridden with an environment variable"},{"name":"CLAUDE_CODE_WORKFLOW_PREFIX_STAGGER_MS","slug":"claude-code-workflow-prefix-stagger-ms","description":"Parallel workflow agents stagger their first call to share cache; tune with an env var."},{"name":"CLAUDE_CODE_WORKFLOW_SIZE_WARNING_AGENTS","slug":"claude-code-workflow-size-warning-agents","description":"Agent-count threshold for the `Large workflow` warning: it shows when a workflow schedules more agents than this. It takes precedence over a cap from the `workflowSizeGuideline` setting, the `tengu_ochre_gantry` flag's `agents` value and the default `25`; a value that is not a positive number is ignored. The warning is not computed while ultracode is active or when that flag has `enabled: false`, and it also fires on the separate token threshold."},{"name":"CLAUDE_CODE_WORKFLOW_SIZE_WARNING_TOKENS","slug":"claude-code-workflow-size-warning-tokens","description":"Token threshold for the `Large workflow` warning on a running workflow. The warning fires when the tokens used so far, or a projection of average tokens per started agent (`70000` before any agent has started) times the number of scheduled agents, exceeds it. Default is the `tokens` field of the `tengu_ochre_gantry` flag, else `1500000`; an unset, non-numeric or `0` value uses the default, and no warning is computed while ultracode is active or when that flag has `enabled: false`."},{"name":"CLAUDE_CODE_WORKFLOW_SUBAGENT_MODEL","slug":"claude-code-workflow-subagent-model","description":"Setting `CLAUDE_CODE_WORKFLOW_SUBAGENT_MODEL` chooses which model subagents use during a workflow run, separately from other subagents"},{"name":"CLAUDE_CODE_WORKFLOWS","slug":"claude-code-workflows","description":"Environment flags are now parsed centrally, so values are compared to explicit true or false."}],"url":"https:\/\/changelogs.core-directive.com\/reference\/env\/claude-code-workflow-prompt-provenance","family_url":"https:\/\/changelogs.core-directive.com\/reference\/env.json"}