arize-phoenix: v19.6.0
19.6.0 (2026-07-24) Features client: add span_ids filter to get_spans in python and typescript clients (df7057a) ui: download selected spans or traces as OTLP JSON (4b4ad21) Bug Fixes deps: update arize-phoenix-evals to 3.3.0 (181adc8) ui: consistent span-detail input/output cards + session view polish (33c94e6) ui: extend session annotation panel to full...
Also shipped Jul 24, 2026Arize AI in July 2026 →
Skill and plugin sharing in CoCo (Public Preview)
Skill and plugin sharing is now available in public preview. Share, discover, and govern CoCo skills and plugins across your Snowflake account. Publish them as Cortex Extension objects that teammates can find and install, with administrator certification, access control, and usage telemetry. For more information, see Share skills and plugins .
Governed tags system table is in Beta
The system.tags.governed_tags system table is in Beta . This table contains a record for each governed tag key in your account, including customer-created and system-generated tags. Use it to programmatically determine which tags in your account are governed. See Governed tags system table reference .
Git CLI commands in Git folders are now in Public Preview
Git CLI commands in Git folders are now in Public Preview . Git folders that you create from the UI automatically get Git CLI access when your workspace is eligible, so you can run standard Git commands such as git stash , interactive rebase, pre-commit hooks, Git submodules, and Large File Storage (LFS) directly from a Databricks terminal.
Diagnose and fix Lakebase issues with Genie, using telemetry in Unity Catalog (Beta)
Lakebase adds AI-assisted troubleshooting: database issues and early warnings are surfaced to you with Insights , and you can then investigate and fix them conversationally with Genie . Both draw on database telemetry captured to Unity Catalog. See Observability .
Knowledge Catalog governance workflows for data product access in preview
Governance workflows add automated controls for data product access management through a request-review mechanism.
Claude Opus 5 launches with a 1M token context window at $5 / $25 per MTok
Claude Opus 5 improves on Opus 4.8 with a 1M token context window, 128k max output and thinking on by default, at the same $5 / $25 per MTok price. It is available on the Claude API, Bedrock, Google Cloud and Microsoft Foundry.
More from phoenixEvery phoenix release →
arize-phoenix: v19.5.0
19.5.0 (2026-07-23) Features add evaluation metrics aggregation APIs (ad41a4d) agents: online trace evals with tool_count_per_turn and user_friction (bdff4b5) api: expose dataset example source span (e0cf022) evals: add toxicity gallery template with input/output-agnostic benchmark (1082155) playground: add Gemini 3.6 Flash and 3.5 Flash-lite support...
arize-phoenix-evals: v3.3.0
3.3.0 (2026-07-23) Features evals: add toxicity gallery template with input/output-agnostic benchmark (1082155)
arize-phoenix: v19.4.0
19.4.0 (2026-07-22) Features components: align span kind icon and timeline bar colors with token treatment (51cf276) components: make IDBadge the consolidated click-to-copy ID element (9445683) js: upgrade phoenix-otel to openinference-vercel v3 for AI SDK v7 spans (30f0827) tracing: redesign span header into identity and meta rows (b1a6359) Bug Fixes...
arize-phoenix: v19.8.0
19.8.0 (2026-07-27) Features agent: add Claude Opus 5 to the curated model list (381dcb1) playground: register Claude Opus 5 (7f65b94) Bug Fixes cost: update built-in model token prices (c269af8) deps: exclude broken bashkit 0.14.2 to unbreak 3.14 installs (ba2c10d) focus styles (0ba4c4b) server: fall back to text for invalid span mime types (a6f91d5)...
arize-phoenix: v19.7.0
19.7.0 (2026-07-27) Features add span detail downloads (a61a86c) dsl: add parent_span is None root-span predicate to span filter DSL (89e54b5) dsl: analyze root-span scope, stop applying it twice (aa9254e) pytest: evaluator trace isolation and experiment metadata for the pytest plugin (d81ee21) ui: add SegmentedControl component (649b061) ui...
arize-phoenix-evals: v3.2.0
3.2.0 (2026-07-21) Features evals: add user friction evaluator (1ae1a39) Bug Fixes evals: improve user friction prompt (115d3f2) evals: skip LiteLLM on Python 3.14 (bc9b533) Documentation fill small feature-gap docs across evals, tracing, playground, and packages (e5764b3)
arize-phoenix: v19.9.0
19.9.0 (2026-07-28) Features charts: keep chart panels readable at narrow widths (1af5b91) trace: expand or collapse all span info sections at once (632e2c4) Bug Fixes clarify empty span annotation tool input (2931734) preserve floating agent location on new chat. (6d87936) server: isolate MCP code-mode execution in subprocesses (ed25b59)
arize-phoenix: v19.10.0
19.10.0 (2026-07-28) Features add experiment evaluation metrics charts (661cf9e) breakdown token charts by sub-type (4e161f7) charts: reorder selected charts by dragging in the chart menu (3599c77), closes #14793 experiments: collapse experiment table rows to a single line (e0c97cd) sandbox: add Monty provider with shared runtime (342b229) show cost and...