Refinery changelog

​

December 2025

• Docs: New essentials/routing-lifecycle.mdx — five-state Mermaid flowchart of every request from received → logged.
• Docs: New essentials/sandbox-isolation.mdx — negative-guarantee table for tenant / Custom Router / AgentOpt sandbox / provider-key boundaries.
• Docs: New essentials/optimizer-comparison.mdx — GEPA vs MIPROv2, when to prefer each, winner-selection rule, cost model.
• API: POST /completions endpoint reference published.
• Docs site: Restructured into two tabs — Refinery and Foundry. Brand standardized to IronLabs.
• Domain: Docs site moved to docs.ironlabs.ai.

​

November 2025

• Released: Custom Router. Train and deploy your own LLM router on your data via RouterTrainer. Python SDK + Node SDK.
• Released: Prompt Optimization. Run GEPA + MIPROv2 in parallel against your dataset; winner picked automatically. PromptOptimizer.fit(...).
• Released: AgentOpt. Closed-loop agent optimization. Upload agent.py with EDITABLE / FIXED markers, an eval.py, and a dataset; Foundry’s optimizer rewrites the agent across iterations and returns the best-scoring version.
• SDK: New cookbooks shipped alongside each feature — custom_router_cookbook.ipynb, prompt_optimization_cookbook.ipynb, agentopt_notebook.ipynb.

​

Older releases