Skip to main content
Opik Documentation

Search documentation

Type to search this documentation.

On this pageOverview

Changelog

Stay current on Agent Optimizer updates. Each entry below reflects a version bump in sdks/opik_optimizer/pyproject.toml on main. The compare links jump straight to the commits that landed in that release. As Opik is a monorepo, you will see other non-optimizer related changes in the commit links below.

Highlights: Full public, production-ready release designed to work alongside Optimization Studio. MCP/tool optimization is temporarily removed in 3.0.03.0.1 due to compatibility reasons.

  • First fully native multi-agent and multi-prompt optimization support end-to-end across optimizers.
  • Specific reasoning models separate from training supported across all optimizers.
  • Multimodal optimization supported across all optimizers.
  • Pass@k evaluation across all optimizers via the n parameter and selection policies.
  • Full refactor and normalization of all optimizers for simpler code and better performance.
Date Version Highlights
2026-02-24 3.1.0 Reintroduced MCP/tool optimization across optimizers, added optimizer benchmark runtime/engine refactor, improved multi-metric span wiring and fail-fast scoring behavior, and added Python 3.14 support. Commits →
2026-01-28 3.0.1 Suppress noisy Hugging Face notebook warnings, fix HotpotQA multihop agent with new LiteLLM calls + JSON mode, map missing error enum so UI shows “Error”, HRPO rich output fixes and performance improvements, sanitize attachment spans to prevent output errors, fix HRPO async in notebooks.
2026-01-26 3.0.0 Major rewrite: native multi-agent/multi-prompt optimization, reasoning model support, pass@k evaluation, and optimizer refactor. Breaking change: MCP-based optimizers removed. Commits →

Highlights: Introduced new optimizers including HRPO and GEPA, tool optimization and expanding coverage beyond early prompt-only workflows. Breaking change includes dropping MIPRO in favour of GEPA.

Date Version Highlights
2026-01-22 2.3.12 Fixes for optimizer breaking issues. Commits →
2026-01-06 2.3.11 Fixed hierarchical optimizer reason handling and numeric equals. Commits →
2025-12-24 2.3.10 Added missing model parameter in HRPO. Commits →
2025-12-19 2.3.9 Fixed hierarchical optimizer recreating optimizations when ID is provided. Commits →
2025-12-15 2.3.8 Fixed Evolutionary Optimizer with OpenAI Responses API, added validation in GEPA, updated multimodal example. Commits →
2025-12-15 2.3.7 Renamed Hierarchical optimizer to HAPO, fixed MetaPrompt inheritance, lint cleanup. Commits →
2025-12-02 2.3.6 Bumped opik_optimizer, added optimization_id skip, cost/latency metrics, GEPA API/log fixes. Commits →
2025-11-24 2.3.5 Version mismatch fix and Few-Shot Optimizer improvements. Commits →
2025-11-24 2.3.4 Optimizer tests, benchmarks, and MetaPrompt improvements. Commits →
2025-11-22 2.3.3 Benchmarks refactor, fixed validation dataset support in Few-Shot Optimizer. Commits →
2025-11-21 2.3.2 Agent examples fixes. Commits →
2025-11-21 2.3.1 Fixed validation datasets, refactored optimizers to dedicated prompts modules. Commits →
2025-11-21 2.3.0 Validation dataset support, better logging and eval traces, optimizer version bump. Commits →
2025-11-21 2.2.7 Cache/speed improvements for e2e and workflows, GEPA adapter fixes. Commits →
2025-11-20 2.2.6 Refactored Datasets API. Commits →
2025-11-20 2.2.5 Ensured OptimizableAgent support, minor fixes. Commits →
2025-11-19 2.2.4 Added multimodal optimization e2e test. Commits →
2025-11-19 2.2.3 Manifest-based task support, extra benchmark datasets. Commits →
2025-11-18 2.2.2 Multimodal input support for HRPO, algorithms package refactor, custom run names. Commits →
2025-11-08 2.2.1 Removed cache, added MCP agent prompt, benchmarks, fixed GEPA e2e tests. Commits →
2025-10-23 2.2.0 Public method refactor and optimizer cleanup. Commits →
2025-10-23 2.1.3 Multi-metric optimization objectives, HRPO logging improvements, public method refactor. Commits →
2025-10-11 2.1.2 Fixed missing optimizer names across metadata. Commits →
2025-10-10 2.1.1 Introduced the Hierarchical Reflective Optimizer. Commits →
2025-10-09 2.1.0 Pinned LiteLLM, shipped optimizer API docs, added parameter-only tuning. Commits →
2025-10-02 2.0.1 Added GEPA dependency and test package init files. Commits →
2025-10-01 2.0.0 Updated pyproject.toml for v2.0 release. Commits →

Highlights: Initial research release for testing early internal optimizers MetaPrompter, Evolutionary and support for MIPRO.

Date Version Highlights
2025-10-01 1.1.0 Optimizer MCP with EO, signature refactor, docs and dotfiles for optimizer release. Commits →
2025-09-24 1.0.6 Initial optimizer packaging cleanup. Commit →
Suggest an edit

Propose a replacement for this page. The site team reviews it before applying any changes.

Export
Documentation menu