phoenix

varize-phoenix-client-v2.8.0 scope: arize-phoenix-client Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 1mo Tracing

✓ No known CVEs patched

✓ No known CVEs patched in this version

Topics

agents ai-monitoring ai-observability aiengineering anthropic datasets

+10 more

evals langchain llamaindex llm-eval llm-evaluation llmops llms openai prompt-engineering smolagents

Summary

AI summary

Updates 2.8.0, Bug Fixes, and Miscellaneous Chores across a mixed release.

Type	Severity	Summary	CVE
Feature
Feature	Medium	add PXI playground model switching tool add PXI playground model switching tool Source: llm_adapter@2026-06-09 Confidence: high	—
Feature	Medium	add span annotation tool for agents add span annotation tool for agents Source: llm_adapter@2026-06-09 Confidence: high	—
Feature	Medium	enable provider native web search / fetch when available in agents enable provider native web search / fetch when available in agents Source: llm_adapter@2026-06-09 Confidence: high	—
Feature	Medium	stamp tool execution environment on provider metadata in agents stamp tool execution environment on provider metadata in agents Source: llm_adapter@2026-06-09 Confidence: high	—
Feature	Medium	add code-evaluator authoring for PXI add code-evaluator authoring for PXI Source: llm_adapter@2026-06-09 Confidence: high	—
Feature	Medium	implement Sandboxing and Code Evaluators enhancements implement Sandboxing and Code Evaluators enhancements Source: llm_adapter@2026-06-09 Confidence: high	—
Bugfix	Medium	drop Google top_k mapping to OpenAI top_logprobs in client drop Google top_k mapping to OpenAI top_logprobs in client Source: llm_adapter@2026-06-09 Confidence: high	—

Full changelog

add PXI playground model switching tool (#13499) (ad2013a)
agents: add span annotation tool (#13502) (4c8262c)
agents: Enable provider native web search / fetch when available (#13333) (41eb4fc)
agents: stamp tool execution environment on tool-call provider metadata (#13277) (ef421e5)
pxi: code-evaluator authoring (#13397) (cef8f13)
Sandboxing and Code Evaluators (#13290) (e294d93)

client: drop Google top_k instead of mapping it to OpenAI top_logprobs (#13640) (f98e856)

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track phoenix

Get notified when new releases ship.

About phoenix

AI Observability & Evaluation

varize-phoenix-v19.0.0 GraphQL createUserApiKey and createSystemApiKey reject API-key callers.
varize-phoenix-v18.0.0 Changes session time-range filters to use interval-overlap semantics.
varize-phoenix-v17.0.0 Adds system settings for admin-managed assistant enablement and trace recording policy
varize-phoenix-v16.0.0 Sandboxing and Code Evaluators introduce breaking changes in Phoenix v16.0.0.
varize-phoenix-v15.7.0 Removes v1 /chat route and associated code