Skip to content

phoenix

varize-phoenix-v15.9.0 scope: arize-phoenix Feature

This release adds 1 notable feature for engineering teams evaluating rollout.

Published 20d Tracing
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ 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

ReleasePort's take

Light signal
editorial:auto 13d

Phoenix v15.9.0 backfills TOOL spans for agent external tool returns and fixes handling of invalid GraphQL node IDs.

Why it matters: Agents now emit complete TOOL spans for external tool performance visibility; GraphQL queries with invalid node IDs are handled gracefully. Standard maintenance upgrade.

Summary

AI summary

Backfill TOOL spans for external tool returns and fix handling of invalid GraphQL node IDs.

Changes in this release

Feature Medium

agents backfill TOOL spans for external tool returns in agent wrapper

agents backfill TOOL spans for external tool returns in agent wrapper

Source: llm_adapter@2026-05-21

Confidence: high

Bugfix Medium

agent clarify PXI remote trace sharing consent

agent clarify PXI remote trace sharing consent

Source: llm_adapter@2026-05-21

Confidence: high

Bugfix Medium

handle invalid GraphQL node ids

handle invalid GraphQL node ids

Source: llm_adapter@2026-05-21

Confidence: low

Other Medium

skills weekly audit — 2026-05-13

skills weekly audit — 2026-05-13

Source: llm_adapter@2026-05-21

Confidence: low

Full changelog

15.9.0 (2026-05-14)

Features

  • agents: backfill TOOL spans for external tool returns in agent wrapper (#13185) (4b221b9)

Bug Fixes

Documentation

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.

Sign up free

About phoenix

AI Observability & Evaluation

All releases →

Related context

Earlier breaking changes

Beta — feedback welcome: [email protected]