NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI
PyPI, #3910 most downloaded on PyPI
LLM Observability
Latest stable
3.7.0
Last release 17 days ago
05 Nov 2026
Ships fairly regularly
a new release about every 2 weeks
Most releases are documented
notes for 53 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
2 years old
77 releases · first in 2025
Drag across the ruler to compare, or tap a release to open it.
harbor: record model parameters and agent settings in experiment metadata
Your coding agent can read these notes before it upgrades. Set up the MCP server →
annotations: add DECISION and AGENT kinds
result (#16902) (d927595)add MiniMax provider integration
phoenix.evals (#2421) (fbd4961)BedrockModel (#2425) (81a720c)server: GET /v1/model_providers no longer returns custom providers or a next_cursor, and built-in entries expose provider rather than kind + provider_
next_cursor, and built-in entries expose provider rather than kind + provider_key. Custom providers move to GET /v1/custom_model_providers. The endpoint is unreleased, so no published client is affected.pxi: enable phoenix-gql mutations by default with approval in manual mode
server: add POST /traces/transfer
release arize-phoenix-client 3.1.0
80bac51: Move @arizeai/phoenix-otel to OpenTelemetry JS 3 (@opentelemetry/sdk-trace 3.x, @opentelemetry/api 1.10) so spans created by apps on OpenTele
@arizeai/phoenix-otel to OpenTelemetry JS 3 (@opentelemetry/sdk-trace 3.x, @opentelemetry/api 1.10) so spans created by apps on OpenTelemetry JS 3 are recorded after register(). register() now returns the @opentelemetry/sdk-trace TracerProvider (still exported as the NodeTracerProvider type), which no longer has a register() method. Custom spanProcessors must come from @opentelemetry/sdk-trace and take an options object, e.g. new BatchSpanProcessor({ exporter }); BatchSpanProcessor and SimpleSpanProcessor are now re-exported from @arizeai/phoenix-otel. See the package's MIGRATION.md. A tracerProvider passed to @arizeai/phoenix-client evaluateExperiment() must now be an @opentelemetry/sdk-trace 3.x TracerProvider. register() no longer applies the OTEL_TRACES_SAMPLER, OTEL_SPAN_*, OTEL_ATTRIBUTE_*, or OTEL_BSP_* environment variables. Node.js 22.15 or newer is now required.client: add name_contains filter to Python client projects.list() (#14132) (fa79dc0), closes #14034
ui: add annotation summary to project settings
add direct server agent endpoint
add playground repetitions tool
Nothing published for this version
add PXI playground model switching tool
b00c105: Classification evaluators, including every built-in, can now run on AI SDK decision models such as openai.decisionModel("gpt-6-luna"). The la
b00c105: Classification evaluators, including every built-in, can now run on AI SDK decision models such as openai.decisionModel("gpt-6-luna"). The label comes from experimental_decide, with label probabilities (and the provider's confidence, when reported) in metadata. The rendered prompt is sent as plain text, and refusals throw the AI SDK's Experimental_DecisionRefusalError. Decide spans now record the decision state, question and answer. New exports: isDecisionModel and the DecisionModel type.
This replaces the evaluation model support from the previous release, and changes what evaluation models such as TypeSafe's Jev are sent. They now go through experimental_decide too. Message prompts are joined into plain text instead of being serialized as JSON state.
ai is pinned to 7.0.137 and @ai-sdk/otel to 1.0.137, because the decision API is experimental and has changed in patch releases, and @ai-sdk/otel depends on one exact ai version. Use @ai-sdk/openai 4.0.89 or later with OpenAI decision models. Earlier versions receive the state as JSON-encoded text instead of plain text.
b7b7dfb: Classification evaluators now accept AI SDK evaluation models such as TypeSafe's Jev. When an evaluation model is passed as model, the classi
model, the classification is routed through experimental_evaluate as a single choice question instead of generateObject. Results carry a label and score but no explanation, since evaluation models do not generate text.d67ea3f: Deprecate createDocumentRelevanceEvaluator in favor of createRetrievalRelevanceEvaluator. Rename documentText to context and the unrelated la…
createCompletenessEvaluator to judge whether every active user request in a conversation was actually completed.createDocumentRelevanceEvaluator in favor of
createRetrievalRelevanceEvaluator. Rename documentText to context and the
unrelated label to irrelevant. The deprecated factory and its types will be
removed in the next major release.client: pass through trace_id to experiment evaluators
llm_classify (#2068) (3233d56)188ce28: feat(phoenix-otel): Upgrade openinference-vercel tracing dependency to support decision model tracing
evals: deprecate evals 1.0 docs
client: add span filter params to getSpans
v1/traces HTTP endpoint to handle ExportTraceServiceRequest (3c94dea)v1/traces HTTP endpoint to handle ExportTraceServiceRequest (#1968) (3c94dea)client: add server version gating with capability requirements
client: remove deprecated client.annotations module
client.annotations has been removed. Use client.spans instead.client.annotations module (#11983) (6203c31)llm_classify and llm_generate interfaces (#1974)llm_generate (#1965) (5999133)llm_classify and llm_generate interfaces (#1974) (9fd35a1)add GET endpoints for sessions REST API
This PR was generated with Release Please. See documentation.
<!-- CURSOR_SUMMARY -->
add parameter for deleting project after deleting experiment
## 1.29.0 (2026-02-13) ### Features * dataset evaluators (5f47820) * dataset evaluators
add timezone validation to log_spans_dataframe
add FaithfulnessEvaluator and deprecate HallucinationEvaluator
This PR was generated with Release Please. See documentation.
<!-- CURSOR_SUMMARY -->
use context.span_id column when DataFrame has integer index
update reasoning_effort options for openai
Add span note function to python client
This PR was generated with Release Please. See documentation.
<!-- CURSOR_SUMMARY -->
splits: Allow split assignment from dataset upload
add evaluation helpers to easily pull rag spans
## 1.24.0 (2025-11-19) ### Features * switch client to be Apache 2.0
## 1.23.0 (2025-11-12) ### Features * Experiment retries
80bac51: Move @arizeai/phoenix-otel to OpenTelemetry JS 3 (@opentelemetry/sdk-trace 3.x, @opentelemetry/api 1.10) so spans created by apps on OpenTele
@arizeai/phoenix-otel to OpenTelemetry JS 3 (@opentelemetry/sdk-trace 3.x, @opentelemetry/api 1.10) so spans created by apps on OpenTelemetry JS 3 are recorded after register(). register() now returns the @opentelemetry/sdk-trace TracerProvider (still exported as the NodeTracerProvider type), which no longer has a register() method. Custom spanProcessors must come from @opentelemetry/sdk-trace and take an options object, e.g. new BatchSpanProcessor({ exporter }); BatchSpanProcessor and SimpleSpanProcessor are now re-exported from @arizeai/phoenix-otel. See the package's MIGRATION.md. A tracerProvider passed to @arizeai/phoenix-client evaluateExperiment() must now be an @opentelemetry/sdk-trace 3.x TracerProvider. register() no longer applies the OTEL_TRACES_SAMPLER, OTEL_SPAN_*, OTEL_ATTRIBUTE_*, or OTEL_BSP_* environment variables. Node.js 22.15 or newer is now required.This PR was generated with Release Please. See documentation.
<!-- CURSOR_SUMMARY -->
1e47750: Add px dataset-versions list with cursor pagination, optional limits, and pretty, JSON, and raw output.
px dataset-versions list <dataset-identifier> with cursor pagination, optional limits, and pretty, JSON, and raw output.This PR was generated with Release Please. See documentation.
<!-- CURSOR_SUMMARY -->
974be43: Add px prompt-versions list with cursor pagination, optional limits, and pretty, JSON, and raw output. Show creation dates when supported by
px prompt-versions list <prompt-identifier> with cursor pagination, optional limits, and pretty, JSON, and raw output. Show creation dates when supported by the server.### Patch Changes - Updated dependencies [ead7dd8] - @arizeai/phoenix-client@7.18.0
9e7a797: Accept DECISION and AGENT as annotator kinds for span, document, trace, session and experiment run annotations. In px, --annotator-kind on an
DECISION and AGENT as annotator kinds for span, document, trace, session and experiment run annotations. In px, --annotator-kind on annotate and the *-annotations delete commands accepts both. Phoenix servers that predate these kinds reject them.### Patch Changes - Updated dependencies [2b73847] - @arizeai/phoenix-client@7.11.0
### Patch Changes - Updated dependencies [c839254] - @arizeai/phoenix-client@7.10.0
bf047af: Add Meta (Muse Spark models) as a built-in OpenAI-compatible model provider (META).
META).experiment task function backward compatibility for the example argument
58b7017: Add Z.ai (GLM models) as a built-in OpenAI-compatible model provider (ZAI).
ZAI).python phoenix-client delete span method
Remove reference to experiment evaluators in client docstrings
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
One column per month.