{"schemaVersion":"2026-07-21.signal.v2","id":"live-2762d29b38f483b5839e","title":"Instructor v1.16.0","slug":"instructor-v1-16-0-instructor-v1-16-0-b5839e","url":"https://www.niubiagent.com/signals/instructor-v1-16-0-instructor-v1-16-0-b5839e","jsonUrl":"https://www.niubiagent.com/api/posts/instructor-v1-16-0-instructor-v1-16-0-b5839e.json","markdownUrl":"https://www.niubiagent.com/content/instructor-v1-16-0-instructor-v1-16-0-b5839e","summaryHuman":"Instructor releases published Instructor v1.16.0. Added - Bedrock native structured outputs : Add explicit Mode.JSON SCHEMA and Mode.TOOLS STRICT support through Converse outputConfig.textFormat and strict tool schemas, with recursive schema normalization and a boto3 1.42.42 minimum. Model selection remains caller-controlled. ( 2515…","summaryAgent":"Treat Instructor v1.16.0 as an official release signal. Inspect the linked changelog for compatibility and migration details, then run targeted tests before upgrading.","category":"model-behavior","tags":["structured-output","validation","llm"],"sourceName":"Instructor releases","sourceUrl":"https://github.com/567-labs/instructor/releases/tag/v1.16.0","publishedAt":"2026-08-27T15:33:36Z","curatedAt":"2026-09-18T23:04:03.312Z","confidence":0.96,"agentUsefulness":82,"sponsorIds":[],"language":"en","contentMode":"release-watch","verifiedAt":"2026-09-19T00:17:43.868Z","changeType":"release","actionItems":["Review the official Instructor releases release notes before upgrading.","Check compatibility, migration, and security notes against your current agent stack.","Run focused regression tests before production rollout."],"body":"Instructor releases published Instructor v1.16.0. This release-watch entry was generated from the project's official GitHub release feed and is kept separate from human-reviewed editorial analysis. Release notes: Added - Bedrock native structured outputs : Add explicit Mode.JSON SCHEMA and Mode.TOOLS STRICT support through Converse outputConfig.textFormat and strict tool schemas, with recursive schema normalization and a boto3 1.42.42 minimum. Model selection remains caller-controlled. ( 2515 (https://github.com/567-labs/instructor/pull/2515), 2084 (https://github.com/567-labs/instructor/issues/2084), 2086 (https://github.com/567-labs/instructor/pull/2086)) - Validation retry budgets : Add positive cumulative token budget limits for structured non-streaming retries, immutable completion:usage snapshots, sync/async cutoff parity, and stable cumulative usage metadata. Valid responses still win after crossing the budget. When a budget is configured, a failed attempt with unavailable usage stops before another provider call. ( 2512 (https://github.com/567-labs/instructor/pull/2512), 2391…","sponsors":[]}