Safety ResearchAutomated release watch

arize-phoenix: v20.17.0

Arize Phoenix releases published arize-phoenix: v20.17.0. 20.17.0 (2026-09-30) Features agents: mark bash tool spans as errors on non-zero exit codes ( 16597 ) ( cd0512e ) graphql: add sort and sequenceNumbers to Dataset.experiments ( 16563 ) ( 9c14c5a ) rest: add sequence number, sort dir, and sequence numbers to list experiments ( 16574 ) ( 305e1a9 ) Bug…

Human read

Why this signal matters

Arize Phoenix releases published arize-phoenix: v20.17.0. This automated release-watch entry was generated from the project's official GitHub release feed and is kept separate from human-reviewed editorial analysis. Release notes: 20.17.0 (2026-09-30) Features agents: mark bash tool spans as errors on non-zero exit codes ( 16597 ) ( cd0512e ) graphql: add sort and sequenceNumbers to Dataset.experiments ( 16563 ) ( 9c14c5a ) rest: add sequence number, sort dir, and sequence numbers to list experiments ( 16574 ) ( 305e1a9 ) Bug Fixes agents: leave the user out of the internal GraphQL scope when no one is logged in ( 16457 ) ( 839485e ) cap graphql-core below 3.3 ( 16641 ) ( 097750c ) cost: score patterns that open with a group or end in an escaped dollar ( 16176 ) ( 6be5fe5 ) db: support SQLAlchemy 2.1 on SQLite ( 16565 ) ( 98e6618 ) experiment JSON/CSV export 500 when a run errored ( 16532 ) ( f2c83cc ), closes 16531 ingest: stop per-key merge from interleaving dual-emitted gen ai messages ( 16092 ) ( 4535030 ) otel: fix register() crash with opentelemetry-exporter-otlp-proto-http 1.45 ( 16549 ) ( 70c5051 )…

Agent parse

Actionable summary

Treat arize-phoenix: v20.17.0 as an official release signal. Inspect the linked changelog for compatibility and migration details, then run targeted tests before upgrading.

Agent usefulness
72/100
Confidence
96%
Canonical data
JSON + Markdown
Next actions

What builders should check

  • Review the official Arize Phoenix releases release notes before upgrading.
  • Check compatibility, migration, and security notes against your current agent stack.
  • Run focused regression tests before production rollout.
Classification

Tags and routing

observabilityevaluationtracing
Related signals

Continue the thread