Releasesby Glypharize-phoenix-evals: v2.9.0
2.9.0 (2026-02-02) Features add FaithfulnessEvaluator and deprecate HallucinationEvaluator (fc8b1b5) add tool invocation accuracy metric (d1c89bf) evals: add missing tool_selection evaluator to both libraries (d6d1953) evals: add neutral optimization direction option (5768a14) return trace_id in Scores and improve trace decorator (a8dfb54) Bug Fixes Use...
Also shipped Feb 3, 2026Arize AI in February 2026 →
Supabase is now an official Claude connector
Supabase projects can now be connected to Claude, allowing users to manage database infrastructure through natural language instructions.
R2 - Improve Global Upload Performance with R2 Local Uploads - Now in Open Beta
Local Uploads is now available in open beta. Enable it on your R2 bucket to improve upload performance when clients upload data from a different region than your bucket. With Local Uploads enabled, object data is written to storage infrastructure near the client, then asynchronously replicated to your bucket.
SCIM user and team provisioning
Never wait for a login to secure your stack You can now automate your entire user lifecycle and team structures directly from your identity provider (IdP). By moving SCIM from public preview to general availability, we’ve removed the “first login” bottleneck, allowing centralized operators to provision, configure, and secure users before they even open the...
Nova-3 Model Update
🌐 Nova-3 Adds Support for Hebrew, Farsi, and Urdu We're excited to announce the release of new Nova-3 monolingual models for Hebrew , Farsi , and Urdu ! These additions bring industry-leading speech-to-text capabilities for users of these languages.
Agents, Workflows - Agents SDK v0.3.7: Workflows integration, synchronous state, and scheduleEvery()
The latest release of the Agents SDK ↗ brings first-class support for Cloudflare Workflows , synchronous state management, and new scheduling capabilities. Cloudflare Workflows integration Agents excel at real-time communication and state management. Workflows excel at durable execution.
Security Center - Threat actor identification with "also known as" aliases
Identifying threat actors can be challenging, because naming conventions often vary across the security industry. To simplify your research, Cloudflare Threat Events now include an Also known as field, providing a list of common aliases and industry-standard names for the groups we track.
More from phoenixEvery phoenix release →
arize-phoenix: v12.34.0
12.34.0 (2026-02-06) Features evals: add missing tool_selection evaluator to both libraries (d6d1953) Bug Fixes add enum for new prompt span kind (b93abc5) cost: update built-in model token prices (860f703) normalize message_content.text to string before rendering in MessageContentListItem (d0908aa) Documentation evals: update built-in metric pages...
arize-phoenix: v12.35.0
12.35.0 (2026-02-09) Features add Claude Opus 4.6 model to playground (3554b76) Bug Fixes add timezone validation to log_spans_dataframe (45a07bb) anthropic streaming handling for new stop events (7ac1081) arize 8.0.0 inference schema (c42ce16) cost: update built-in model token prices (cd61bd9) deps: update arize-phoenix-client to 1.28.1 (b70f1c5) Improve...
arize-phoenix: v12.33.0
12.33.0 (2026-01-28) Features oauth2: add EMAIL_ATTRIBUTE_PATH for configurable email extraction (90ab5ca) Bug Fixes move namespace package discovery before imports (e12fa87) Documentation updating phoenix nav (1e2ae4d)
arize-phoenix: v12.32.0
12.32.0 (2026-01-27) Features add phoenix-ci/SKILL.md (3686228) add tool invocation accuracy metric (d1c89bf) evals skill (68ac6fb) tracing skill (d91a52b) Bug Fixes cost: update built-in model token prices (422250a) keyboard form submission of dataset creation (7b5b680) update links to typescript documentation (5c7664d) Documentation coding agents...
arize-phoenix: v13.0.0
13.0.0 (2026-02-13) ⚠ BREAKING CHANGES dataset evaluators Features Add autocomplete to LLM eval prompt editor (2dce02c) add available tools to experiment output (f17e359) add built-in LLM evaluator configs to graphql (4c8a70f) add custom providers to model menu (41fe933) Add dataset deep link after selection from playground (06c9687) add default output...
arize-phoenix-evals: v2.10.0
2.10.0 (2026-02-13) Features add tool response handling evaluator template (0738cb9) dataset evaluators (1274b03) dataset evaluators (5f47820) dataset evaluators (cf0e09a) enable full mustache prompt templates in the server (68ba0ed) filter built-in classification evaluators by label (aa95a3f) Bug Fixes templates: simplify template formatters (1f6df01)...
arize-phoenix-client: v1.29.0
1.29.0 (2026-02-13) Features dataset evaluators (5f47820) dataset evaluators (cf0e09a)
arize-phoenix: v12.31.0
12.31.0 (2026-01-21) Features add cursor rule for creating new built-in metrics (llm classification evaluators) (d329bea) add FaithfulnessEvaluator and deprecate HallucinationEvaluator (fc8b1b5) add span_id_key to link dataset examples to traces (01eb1fb) dataset and experiment cli commands (32343ff) phoenix cli (d69eb80) Bug Fixes cost: update built-in...