Releasesby Glypharize-phoenix: v12.33.0
12.33.0 (2026-01-28) Features oauth2: add EMAIL_ATTRIBUTE_PATH for configurable email extraction (90ab5ca) Bug Fixes move namespace package discovery before imports (e12fa87) Documentation updating phoenix nav (1e2ae4d)
Also shipped Jan 28, 2026Arize AI in January 2026 →
Build dashboard widgets for your Metrics - Open Beta
Create dashboard widgets directly from your Metrics queries
Enhanced Discount Function configuration with Admin UI extensions
Admin UI extensions for Discount Functions can now interact with the selected discount method and manage discount classes, letting you customize the discount configuration experience directly within the Shopify admin. This is a non-breaking change that adds new functionality to existing discount UI extensions.
Workers AI - Launching FLUX.2 [klein] 9B on Workers AI
We have partnered with Black Forest Labs (BFL) again to bring their optimized FLUX.2 [klein] 9B model to Workers AI. This distilled model offers enhanced quality compared to the 4B variant, while maintaining cost-effective pricing.
Figma for Google Chat
The Figma for Google Workspace add-on now works with Google Chat, so you can stay on top of your Figma and FigJam work.
Enhance account security with multi-factor authentication
Protect your data and control access to your New Relic organization by enabling multi-factor authentication (MFA). This feature allows administrators to add an essential layer of security to authentication domains, ensuring that users provide two or more verification factors to gain access.
More from phoenixEvery phoenix release →
arize-phoenix: v12.32.0
12.32.0 (2026-01-27) Features add phoenix-ci/SKILL.md (3686228) add tool invocation accuracy metric (d1c89bf) evals skill (68ac6fb) tracing skill (d91a52b) Bug Fixes cost: update built-in model token prices (422250a) keyboard form submission of dataset creation (7b5b680) update links to typescript documentation (5c7664d) Documentation coding agents...
arize-phoenix-evals: v2.9.0
2.9.0 (2026-02-02) Features add FaithfulnessEvaluator and deprecate HallucinationEvaluator (fc8b1b5) add tool invocation accuracy metric (d1c89bf) evals: add missing tool_selection evaluator to both libraries (d6d1953) evals: add neutral optimization direction option (5768a14) return trace_id in Scores and improve trace decorator (a8dfb54) Bug Fixes Use...
arize-phoenix: v12.31.0
12.31.0 (2026-01-21) Features add cursor rule for creating new built-in metrics (llm classification evaluators) (d329bea) add FaithfulnessEvaluator and deprecate HallucinationEvaluator (fc8b1b5) add span_id_key to link dataset examples to traces (01eb1fb) dataset and experiment cli commands (32343ff) phoenix cli (d69eb80) Bug Fixes cost: update built-in...
arize-phoenix-client: v1.28.0
1.28.0 (2026-01-21) Features add FaithfulnessEvaluator and deprecate HallucinationEvaluator (fc8b1b5) add span_id_key to link dataset examples to traces (01eb1fb) This PR was generated with Release Please. See documentation.
arize-phoenix: v12.34.0
12.34.0 (2026-02-06) Features evals: add missing tool_selection evaluator to both libraries (d6d1953) Bug Fixes add enum for new prompt span kind (b93abc5) cost: update built-in model token prices (860f703) normalize message_content.text to string before rendering in MessageContentListItem (d0908aa) Documentation evals: update built-in metric pages...
arize-phoenix: v12.35.0
12.35.0 (2026-02-09) Features add Claude Opus 4.6 model to playground (3554b76) Bug Fixes add timezone validation to log_spans_dataframe (45a07bb) anthropic streaming handling for new stop events (7ac1081) arize 8.0.0 inference schema (c42ce16) cost: update built-in model token prices (cd61bd9) deps: update arize-phoenix-client to 1.28.1 (b70f1c5) Improve...
arize-phoenix: v12.30.0
12.30.0 (2026-01-15) Features Add AttributesJSONBlock component for enhanced JSON attribute display (0c2426b) add text block and json block icons for attribute string expansion (cb938e8) Bug Fixes preserve reasoning_effort and other invocation parameters (e1cf433) Preserve response format during model updates in playground store (8f50e27) Store correct...
arize-phoenix: v13.0.0
13.0.0 (2026-02-13) ⚠ BREAKING CHANGES dataset evaluators Features Add autocomplete to LLM eval prompt editor (2dce02c) add available tools to experiment output (f17e359) add built-in LLM evaluator configs to graphql (4c8a70f) add custom providers to model menu (41fe933) Add dataset deep link after selection from playground (06c9687) add default output...