Releasesby Ibisarize-phoenix: v20.23.0
UpdatetodayUnverifiedAdded Oct 16, 2026
20.23.0 (2026-10-16) Features server: export server logs over OTLP (add77bf) Bug Fixes playground: forward Bedrock tool results directly as text (15355fd) Documentation add Atomic Agents tracing integration (fe5e933) Add Phoenix release notes , 2026-10-14 (97c4b2a)
Topics: AI agents, Observability
More phoenix releases
Every phoenix releasearize-phoenix: v20.22.0
20.22.0 (2026-10-15) Features playground: add Meta muse-wonder-1.0 and gemini-4-argon (d5168d1) Bug Fixes oauth2: preserve SameSite=Strict cookies on server-owned return_url after IdP sign-in (c332b0c) Documentation add Claude Managed Agents tracing docs (54fe899) add standalone release note for the Harbor plugin (fe4a06b)
arize-phoenix-sqlean: v0.2.0
0.2.0 (2026-10-12) Features phoenix-sqlean: bundle SQLite 3.54.0 and support Python 3.15 (fff25bc)
arize-phoenix: v20.21.0
20.21.0 (2026-10-11) Features assign a random gradient to projects created by ingestion (8946f7a) cost-tracking: support Mistral AI model pricing (0e33736), closes #16878 Bug Fixes agents: upgrade pydantic-ai for CVE-2026-107286 (3cdb004) deps: update arize-phoenix-evals to 3.9.2 (e8aa1ea) playground: sync built-in model prices and model lists (35f86e5)...
arize-phoenix: v20.20.0
20.20.0 (2026-10-08) Features harbor: prompt hill-climb task on a text-to-SQL dataset (bd78550) mcp/sql: allowlist the annotation, evaluator, prompt, split and job tables (a37b841) mcp: add GraphQL schema, query, and mutation tools (9351580) playground: add claude-haiku-5-5 and remove retired Anthropic models (b978e7c) pxi: make PXI's MCP code mode...
arize-phoenix: v20.19.0
20.19.0 (2026-10-01) Features datagen: send each recorded application to its own project (d99a4db) tracing: add the DECISION span kind across the platform (43d1a54) Bug Fixes honor external resources flag for WASM and UI (7a71a21) Documentation remove legacy evaluation cookbooks (4506880)
arize-phoenix: v20.18.0
20.18.0 (2026-09-30) Features tracing: show eval results in the trace tree (2516fdb)
arize-phoenix: v20.17.0
20.17.0 (2026-09-30) Features agents: mark bash tool spans as errors on non-zero exit codes (cd0512e) graphql: add sort and sequenceNumbers to Dataset.experiments (9c14c5a) rest: add sequence_number, sort_dir, and sequence_numbers to list_experiments (305e1a9) Bug Fixes agents: leave the user out of the internal GraphQL scope when no one is logged in...
arize-phoenix: v20.16.0
20.16.0 (2026-09-23) Features add gpt-6-sol, gpt-6-luna, and claude-opus-5-5 to the cost tables and the playground (59d09f4) js: add dataset split write helpers (aab229f) js: add secrets management helper (c282563) spans: sort the span list endpoint by start_time (03f62e1) Bug Fixes agents: close out the PXI turn trace when a server tool raises (3a3d57b)...
Also shipped on Oct 16, 2026
Arize AI in October 20262026.10.08
Make a voice you already have speak another language or accent, with the same speaker. Call POST /voice-generator/localize on a flagship or custom voice, pick an accent, and get candidates back in seconds to audition and convert like Voice Design candidates. GET /voice-generator/available-accents lists the accents you can target.
Unified Login for SendGrid Marketplace Customers
SendGrid marketplace customers can now take advantage of the Unified Login feature that lets you create a Twilio login for every individual user accessing your SendGrid account. This provides a more secure access pattern with the ability to define permissions for each user instead of a single, shared admin permission set.
Spot slow and flaky tests faster from your test suite Summary
Your test suite's Summary page now brings together more of the data you need to keep your suite healthy and fast, so you can see where time is going and where reliability is slipping without digging through individual tests.
Know when the Buildkite CLI is done or needs you, without watching its tab
You can now see when bk preflight or bk build watch finishes or needs you, without switching back to its tab. From Buildkite CLI v3.64.0 , bk tells your terminal what it's doing, so a terminal that supports it can show you while you work somewhere else.
READ METADATA privilege support for compliance security profile standards
The READ METADATA privilege now supports all compliance security profile standards supported by Databricks and is available by default for workspaces with the compliance security profile enabled. For a full list of supported compliance standards, see Compliance security profile .
- Images and bounding boxes in prompt_jev() : prompt_jev() can now classify and score images
- Images and bounding boxes in prompt_jev() : prompt_jev() can now classify and score images. Pass PNG or JPEG images as BLOBs, for example loaded from a URL with read_blob , and ask questions about what's in them.