Claude API: structured outputs support expands, and older models keep getting retired.
Production users: pin versions and stop ignoring deprecation notes.
What changed
• Structured outputs support expanded to additional Claude variants
• Model deprecations continue (older models retired or scheduled to retire)
• Docs + console experience is being consolidated for developers
Who it affects
• API users
• Anyone shipping Claude in production
• RAG/agents teams
What to do now
• Pin model versions in production (avoid surprise changes)
• Track deprecation notices and set upgrade windows
• Prefer structured outputs for tool-calling and pipelines
Related updates
Agent failures are mostly tool wiring, not model 'intelligence'.
Your agent isn't dumb. Your glue code is.
GPT-5.2 pushes harder on real work: code, tools, long context.
More useful for shipping work, especially with structure.
Claude Opus 4.5 leans into coding + agents, with stronger robustness.
Better for serious coding + agent work, especially when you wire it properly.
Prompt injection defenses are maturing (but still not bulletproof).
Defenses improved but aren't magic—implement defense-in-depth.