Releasesby Glypharize-phoenix: v15.11.0
15.11.0 (2026-05-19) Features agents: Generative UI rendering within agent chats (645d7a5) Bug Fixes devops: tolerate missing pnpm-lock.yaml in oidc-server build and dev-mock-llm (4332255) server: handle empty header values in custom provider config (a329946)
Also shipped May 19, 2026Arize AI in May 2026 →
Gemini 3.1 Flash Lite Now Available
gemini-3.1-flash-lite is now available as a managed Google LLM in the Voice Agent API. This Standard tier model replaces the preview version. Set the model in your agent configuration: { "agent": { "think": { "provider": { "type": "google", "model": "gemini-3.1-flash-lite", "temperature": 0.5 } } } }
Deprecations
- gemini-3.1-flash-lite-preview is deprecated and will be removed on May 26, 2025. Migrate to gemini-3.1-flash-lite . For more details on Gemini model deprecations, see Google's Gemini deprecations page . For the full list of supported models and pricing tiers, see the Voice Agent LLM Models documentation .
DigitalOcean Kubernetes (DOKS) now supports single sign-on (SSO) with OIDC in public preview
DigitalOcean Kubernetes (DOKS) now supports single sign-on (SSO) with OIDC in public preview. You can authenticate users to your Kubernetes clusters through an identity provider like Auth0, JumpCloud, Keycloak, or Okta, instead of using …
Screenshot thumbnails for browser checks in Synthetic Monitoring Timepoint Explorer
When debugging browser check failures like “timeout waiting for a selector”, you previously had to rely on text logs alone to understand what the browser rendered. Now, with screenshot thumbnails in the Timepoint Explorer and ad-hoc test panel, you can see exactly what the page looked like at the moment the check ran.
Search volume for AI Visibility [Beta]
Description: AI Visibility now includes Search Volume so you can prioritize topics and prompts based on real demand, not just where your brand appears. Use it to identify high-volume content opportunities and focus optimization where it matters most. Where: Access via AI Visibility → Prompts tab, Topic-level visibility, and When: Open beta, available now.
Cog 0.20.0
New features cog run command. The cog predict command has been renamed to cog run with full backward compatibility. cog predict still works as an alias. ( #3015 ) Model refs for cog push and weights commands. You can now reference models by name (e.g., r8.im/user/model ) instead of full image URLs when pushing or managing weights.
More from phoenixEvery phoenix release →
arize-phoenix: v16.0.0
16.0.0 (2026-05-21) MIGRATION.md ⚠ BREAKING CHANGES - Sandboxing and Code Evaluators Features Phoenix now lets you compose evaluation strategies in code. Most eval tooling hands you a fixed menu of judge templates. Real evaluation is rarely that tidy. Code Evaluators enable you to build evaluation criteria the way you want.
arize-phoenix: v15.12.0
15.12.0 (2026-05-21) Features agents: stamp tool execution environment on tool-call provider metadata (ef421e5) ui: submit elicitation responses with Enter key (c74574d) Bug Fixes app: prevent nested spans table scrolling (af751b6) app: route PXI markdown links through router (7490254) cost: update built-in model token prices (eceff55) playground: block...
arize-phoenix: v15.10.0
15.10.0 (2026-05-15) Features add trace feedback toolbar to session turns (1bd96b9) agents: curate agent model menu (de8c915) border and divider cleanup with improved w storybook support (acd1626) cap agent session retention (1c28249) pxi button styles and thinking glyph animation (4766244) trace: convert OTel GenAI semconv attrs to OpenInference (6248d20)...
arize-phoenix-client: v2.7.0
2.7.0 (2026-05-15) Features agents: add /agents/{agent_id}/sessions/{session_id}/summary endpoint (419c3a0) agents: Playground manipulation tools w/ confirmation (37dc417) agents: rip v1 /chat route and associated code (71ceeb3) app: type frontend REST calls against the OpenAPI schema (590669d) cap agent session retention (1c28249) client: support ATIF v1.7...
arize-phoenix: v15.9.0
15.9.0 (2026-05-14) Features agents: backfill TOOL spans for external tool returns in agent wrapper (4b221b9) Bug Fixes agent: clarify PXI remote trace sharing consent (f5da114) handle invalid GraphQL node ids (35c8f3d) Documentation skills: weekly audit , 2026-05-13 (8349361)
arize-phoenix: v15.8.0
15.8.0 (2026-05-13) Features agents: populate project_sessions for /chat and /summary traces (11275b4) playground: Add Anthropic and Google thinking controls (c132f0c) pxi tool layout rebalancing (d8d5322) Bug Fixes cost: update built-in model token prices (dde26f6) prevent prototype pollution in DatasetPreviewTable (f0a2f9e) validate projection expressions...
arize-phoenix: v15.7.0
15.7.0 (2026-05-13) Features add trace user feedback annotations (3797110) agents: rip v1 /chat route and associated code (71ceeb3) make session turn messages expandable (f898dc0) session-tagged identifiers for open/axial coding workflows (6dceb10) ui: move toasts to top-center with sonner-style stacking (1cc1ce7) Bug Fixes keep PXI send button in stop mode...
arize-phoenix: v16.2.0
16.2.0 (2026-05-26) Features agents: Make assistant accessible over modal overlays (7b6af22) Bug Fixes confine token counts to LLM spans at ingestion (5d4f34f)