{"name":"budget","slug":"budget","family":"setting","title":"Settings keys","noun":"settings key","description":"The bundled Claude API docs now describe a hard dollar spend cap that pauses a session idle.","description_source":"entry","described_by":{"version":"2.1.224","anchor":"managed-agents-sessions-can-carry-a-hard-dollar-spend-cap"},"presence":{"first_seen":"2.1.301","removed_in":"2.1.302","in_current_build":false,"newest_mined":"2.1.308","builds":1,"mined_builds":149,"first_cited":null},"aliases":[],"entries":[{"version":"2.1.275","anchor":"hook-execution-now-tracks-a-per-call-reading-budget-and-re","heading":"Hook execution now tracks a per-call 'reading budget' and records timing for hooks that never call next()","line":"Hook execution now tracks a reading budget and logs timing when a hook never calls next()","released_at":"2026-09-17 20:20:31","reason":"found in this entry's text"},{"version":"2.1.238","anchor":"refused-subagent-launches-are-recorded-with-a-reason","heading":"Refused subagent launches are recorded with a reason","line":"A turned-down subagent launch now records whether it hit the nesting cap, the concurrency cap or a budget.","released_at":"2026-08-20 18:01:54","reason":"found in this entry's text"},{"version":"2.1.224","anchor":"managed-agents-sessions-can-carry-a-hard-dollar-spend-cap","heading":"Managed Agents sessions can carry a hard dollar spend cap","line":"The bundled Claude API docs now describe a hard dollar spend cap that pauses a session idle.","released_at":"2026-08-07 01:36:32","reason":"named in this entry, found in this entry's text"},{"version":"2.1.224","anchor":"vault-ids-documented-as-create-only-and-deployments-can-be-u","heading":"vault_ids documented as create-only, and deployments can be updated","line":"Docs say vault_ids cannot change mid-session, and deployments now have an update endpoint.","released_at":"2026-08-07 01:36:32","reason":"found in this entry's text"},{"version":"2.1.163","anchor":"workflow-vm-security-hardening","heading":"Workflow VM Security Hardening","line":null,"released_at":"2026-06-04 17:56:01","reason":"found in this entry's text"}],"entries_total":5,"docs":[{"source":"api","path":"about-claude\/models\/choosing-a-model","title":"choosing-a-model","documented":false},{"source":"api","path":"about-claude\/models\/migration-guide","title":"Or, for the model with the same capabilities and no access approval requirement:","documented":false},{"source":"api","path":"about-claude\/models\/optimizing-for-cost-and-intelligence","title":"optimizing-for-cost-and-intelligence","documented":false},{"source":"api","path":"about-claude\/pricing","title":"pricing","documented":false},{"source":"api","path":"about-claude\/use-case-guides\/commerce-agents","title":"commerce-agents","documented":false},{"source":"api","path":"agents-and-tools\/agent-skills\/best-practices","title":"PDF Processing","documented":false},{"source":"api","path":"agents-and-tools\/agent-skills\/claude-api-skill","title":"claude-api-skill","documented":false},{"source":"api","path":"agents-and-tools\/tool-use\/advisor-tool","title":"advisor-tool","documented":false},{"source":"api","path":"agents-and-tools\/tool-use\/code-execution-tool","title":"code-execution-tool","documented":false},{"source":"api","path":"agents-and-tools\/tool-use\/programmatic-tool-calling","title":"Process results programmatically","documented":false}],"docs_total":12,"gates":[],"related":[],"url":"https:\/\/changelogs.core-directive.com\/reference\/setting\/budget","family_url":"https:\/\/changelogs.core-directive.com\/reference\/setting.json"}