◆ AI OBSERVABILITY

Arize Phoenix

AI Observability & Evaluation

source ↗ website ↗ rss ↗ last repo push Aug 22, 2026

import { createClient } from '@arizeai/phoenix-client';
import { deletePrompt } from '@arizeai/phoenix-client/prompts';

const client = createClient();
await deletePrompt(client, { name: 'my-rag-prompt' });
import { createClient } from '@arizeai/phoenix-client';
import { deletePrompt } from '@arizeai/phoenix-client/prompts';

const client = createClient();
await deletePrompt(client, { promptId: 'UHJvbXB0OjEyMw==' });
px setup mcp --agent claude
claude mcp add --transport http phoenix https://your-phoenix-host/mcp
result = await call_tool("executeSql", {"sql": """
  SELECT COUNT(DISTINCT t.id) AS n
  FROM span_annotations sa
  JOIN spans s ON s.id = sa.span_rowid
  JOIN traces t ON t.id = s.trace_rowid
  JOIN projects p ON p.id = t.project_rowid
  WHERE p.name = '<your-project>'
    AND sa.name = '<annotation-name>'
    AND sa.score = 1.0
"""})
return result["rows"]
curl -X POST http://localhost:6006/traces/transfer -H 'Authorization: Bearer <token>' -H 'Content-Type: application/json' -d '{}'
spans = client.get_spans(span_ids=["abc123", "def456"])
curl -X POST http://localhost:6006/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model": "gpt-4o", "messages": [{"role": "user", "content": "Hello"}]}'
spans = client.get_spans(span_ids=["abc123", "def456"])
spans = client.get_spans(span_ids=["abc123", "def456"])
px setup mcp
px setup
matching = client.projects.list(name_contains="prod")
PHOENIX_HOST=0.0.0.0
PHOENIX_PORT=6006
PHOENIX_SQL_DATABASE_URL=sqlite:///phoenix.db
curl -X GET 'https://<phoenix-host>/v1/projects?name_contains=prod' -H 'Authorization: Bearer <token>'
python -m phoenix.server.main --dev
export PHOENIX_AGENTS_DISABLE_BASH=true
curl -X GET 'https://<phoenix-host>/agents/<agent_id>/sessions/<session_id>/summary' -H 'Authorization: Bearer <token>'
curl -X GET 'https://<phoenix-host>/agents/<agent_id>/sessions/<session_id>/summary' -H 'Authorization: Bearer <token>'
curl -X POST http://localhost:6006/v1/traces \
  -H 'Content-Type: application/x-protobuf' \
  -H 'x-project-name: my-agent-project' \
  --data-binary @traces.pb
curl -L http://localhost:6006/redirects/projects/my-llm-project
phoenix serve --dev
curl -X GET https://<phoenix-host>/v1/user \
  -H 'Authorization: Bearer <api-key>'
curl -X DELETE https://<phoenix-host>/prompt_versions/<version-id>/tags/production
curl -X DELETE https://<phoenix-host>/prompts/<prompt_identifier>
curl -s -H 'Authorization: Bearer <token>' https://<phoenix-host>/v1/user
phoenix db migrate
spans = client.spans.get_spans(trace_ids=["abc123", "def456"])
spans = client.spans.get_spans(parent_id="span-789")
export PHOENIX_ALLOWED_PROVIDERS=openai,anthropic
export PHOENIX_HIDDEN_PROVIDERS=azure,cohere
GET /v1/spans?parent_id=<span_id>
curl -X GET 'https://<phoenix-host>/v1/spans?trace_id=<trace_id>' \
  -H 'Authorization: Bearer <api-key>'
export PHOENIX_MIGRATE_INDEX_CONCURRENTLY=true
px api graphql
from phoenix.evals import FaithfulnessEvaluator

evaluator = FaithfulnessEvaluator(model=model)
results = evaluator.evaluate(input=query, response=answer, context=retrieved_docs)
EMAIL_ATTRIBUTE_PATH=user.contact.email
from phoenix.evals import FaithfulnessEvaluator

evaluator = FaithfulnessEvaluator(model=model)
results = evaluator.evaluate(dataframe=df)
from phoenix.evals import OpenAIModel

model = OpenAIModel(
    model="gpt-4o",
    sync_client_kwargs={"timeout": 30},
    async_client_kwargs={"timeout": 60},
)
auth:
  secret:
    valueFrom:
      secretKeyRef:
        name: phoenix-auth-secret
        key: secret-key
additionalEnv:
  - name: OPENAI_API_KEY
    valueFrom:
      secretKeyRef:
        name: openai-secret
        key: api-key
import phoenix as px
px.launch_app(root_path="/phoenix")
import asyncio
import phoenix.evals as evals

async def my_async_eval_fn(input):
    # async call to an LLM or scoring service
    return {"score": 1.0, "label": "correct"}

evaluator = evals.create_evaluator(my_async_eval_fn)
from phoenix.evals import evaluate_dataframe

results = evaluate_dataframe(df, evaluators=[my_evaluator])
import phoenix as px

client = px.Client()
client.delete_span(span_id="<span_id>")
import phoenix as px

client = px.Client()
datasets = client.list_datasets()
export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317
# PHOENIX_COLLECTOR_ENDPOINT is not set; Phoenix now picks up the OTel standard var automatically
export OTEL_EXPORTER_OTLP_ENDPOINT=https://your-otel-collector:4318
python your_instrumented_app.py
from phoenix.client import Client

client = Client()
spans = client.get_spans()
import phoenix as px

client = px.Client()
spans = client.get_spans(project_name="my-project")
print(spans)
import phoenix as px

client = px.Client()
df = client.get_span_annotations_dataframe(project_name="my-project")
import phoenix as px

client = px.Client()
df = client.get_span_annotations_dataframe(project_name="my-project")
print(df.head())
from phoenix.client import Client
from phoenix.client.resources.spans import SpanQuery

client = Client()
query = SpanQuery().where("span_kind == 'LLM'")
df = client.get_spans_dataframe(query=query)
from phoenix.client import Client
from phoenix.client.dsl import SpanQuery

client = Client()
query = SpanQuery()
df = client.get_spans_dataframe(query=query, project_name='my-project')
print(df.head())
curl -f http://localhost:6006/readyz
export PHOENIX_ADMIN_SECRET=my-secret-value
phoenix serve
export PHOENIX_DB_ALLOCATED_STORAGE_CAPACITY_GIB=20
phoenix serve
curl -X GET 'http://localhost:6006/prompts' -H 'Accept: application/json'
curl -X GET 'http://localhost:6006/prompts/<id>/versions' -H 'Accept: application/json'
import phoenix as px

client = px.Client()
experiments = client.list_experiments()
run_experiment(dataset, task=my_task, concurrency=10)
evaluate_experiment(experiment, evaluators=[my_evaluator], concurrency=5)
import phoenix as px
from phoenix.evals import create_evaluator

@create_evaluator
def my_evaluator(output, expected):
    return output.strip() == expected.strip()
import phoenix as px
from phoenix.evals import create_evaluator

@create_evaluator
def exact_match(output, reference):  # 'reference' is an alias for 'expected'
    return output.strip() == reference.strip()
import phoenix as px

px.log_traces(trace_dataset=trace_dataset)
import phoenix as px

dataset = px.TraceDataset(dataframe)
px.log_traces(trace_dataset=dataset)
from phoenix.evals import MistralAIModel

model = MistralAIModel(
    model="mistral-large-latest",
    response_format={"type": "json_object"}
)
from phoenix.evals import MistralAIModel

model = MistralAIModel(response_format={"type": "json_object"})
PHOENIX_PROJECT_NAME=my-rag-pipeline python app.py
pip install arize-phoenix[evals]
import phoenix as px

client = px.Client()
client.log_evaluations(evals_dataframe)
import phoenix as px

client = px.Client()
evaluations = client.get_evaluations()
print(evaluations)
import phoenix as px

client = px.Client()
df = client.get_spans_dataframe()
print(df.head())
export PHOENIX_WORKING_DIR=/data/phoenix
python -m phoenix.server.main serve
import phoenix as px

session = px.launch_app(evaluations=[my_eval_dataframe])
import phoenix.evals as evals

results = evals.run_evals(
    dataframe=df,
    evaluators=[evals.QAEvaluator(model=model)],
    provide_explanation=True,
    use_function_calling_if_available=True,
)
llm_generate(dataframe=df, template=my_template, model=model, output_parser=my_parser)
from phoenix.trace.openai import OpenAIInstrumentor

OpenAIInstrumentor().instrument()
from phoenix.trace.langchain import LangChainInstrumentor

LangChainInstrumentor().instrument()
from phoenix.trace.trace_dataset import TraceDataset

dataset = TraceDataset.from_spans(spans)
import phoenix as px

ds = px.Dataset.from_open_inference(open_inference_df)
px.launch_app(primary=ds)
Schema(
    tag_column_names=[
        "rouge_score",
    ],
    prompt_column_names=EmbeddingColumnNames(
        vector_column_name="document_vector", raw_data_column_name="document"
    ),
    response_column_names=EmbeddingColumnNames(
        vector_column_name="summary_vector", raw_data_column_name="summary"
    ),
)
Schema(
    tag_column_names=[
        "bleu_score",
        "rouge_score",
    ],
    prompt_column_names=EmbeddingColumnNames(
        vector_column_name="document_vector", raw_data_column_name="document"
    ),
    response_column_names=EmbeddingColumnNames(
        vector_column_name="summary_vector", raw_data_column_name="summary"
    ),
)

Summary

Arize Phoenix is an open-source AI observability tool that provides LLM observability through tracing and evals, and it is available for self-hosting. It is designed for application developers and sits in the observability space, drawing functional comparison to tools like Grafana Tempo. The project documentation indicates it has continuous activity with multiple contributors.

AI Observability & Evaluation

What Arize Phoenix answers

What types of evaluation can be performed?

It provides capabilities for evaluation, beyond just tracing.

What data sources does it analyze?

It consumes tracing and evaluation data.

How is the observability data structured?

It integrates with OpenTelemetry standards.

What level of insight into LLM behavior does it provide?

It offers observability through tracing and evals for LLMs.

Where does the analysis of performance happen?

It supports monitoring of model performance.

What are the boundaries of its visibility?

It focuses on the observability of LLM interactions.

Command line

composed command

option surface across analysed releases

options at that release added, per release removed, per release

option	found in	since	description

Values are placeholders taken from each option’s declared default. Nothing is executed here — the output shown is a recording of a run that already happened.

Release history

docs update Aug 30, 2026 · issue 011

Arize Phoenix adds a PII Detection pre-built metric to screen conversation records for personally identifiable information.
- ›Adds a PII Detection pre-built metric that screens conversation records for personally identifiable information.
@arizeai/[email protected] Aug 29, 2026 · issue 011

Adds deletePrompt helper to the phoenix-client prompts subpath, calling DELETE /v1/prompts/{prompt_identifier}.
└──▷ GET THIS VERSION
```
$ git clone --branch @arizeai/[email protected] https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout @arizeai/[email protected]
```
└──▷ USE IT
Delete an entire prompt (and all its versions, tags, and labels) by name when retiring a deprecated prompt from production.
javascript
```
import { createClient } from '@arizeai/phoenix-client';
import { deletePrompt } from '@arizeai/phoenix-client/prompts';

const client = createClient();
await deletePrompt(client, { name: 'my-rag-prompt' });
```
Delete a prompt by its ID when the name is unknown but the ID was captured from a previous getPrompt call.
javascript
```
import { createClient } from '@arizeai/phoenix-client';
import { deletePrompt } from '@arizeai/phoenix-client/prompts';

const client = createClient();
await deletePrompt(client, { promptId: 'UHJvbXB0OjEyMw==' });
```
- ›Adds deletePrompt helper to the prompts subpath, accepting a { name } or { promptId } selector (matching getPrompt style) and calling DELETE /v1/prompts/{prompt_identifier} on Phoenix server >= 13.20.0; deletion cascades to all prompt versions, version tags, and labels.
- ›Exports a PromptIdentifier type from types/prompts representing the prompt-level selector union ({ name } or { promptId }).
└──▷ BREAKING ON UPGRADE
- !Version-level selectors ({ versionId }, { name, tag }) passed to deletePrompt are rejected rather than widened to the whole prompt.
launch-20260827-6d38217a Aug 27, 2026 · issue 009

Phoenix 20.2.0 adds built-in MCP server with describeSqlSchema and executeSql tools so agents can query traces with SQL at ~17x lower cost.
└──▷ TRY IT
Point Claude Code at your Phoenix MCP server so it can query traces with SQL — one command writes the client config.
```
$ px setup mcp --agent claude
```
Manually add the Phoenix MCP server to Claude Code when you prefer an explicit one-liner over the px helper.
```
$ claude mcp add --transport http phoenix https://your-phoenix-host/mcp
```
Use executeSql inside a code-mode program to count distinct traces with a high-impact error annotation — the aggregation runs in the database, not in model context.
python
```
result = await call_tool("executeSql", {"sql": """
  SELECT COUNT(DISTINCT t.id) AS n
  FROM span_annotations sa
  JOIN spans s ON s.id = sa.span_rowid
  JOIN traces t ON t.id = s.trace_rowid
  JOIN projects p ON p.id = t.project_rowid
  WHERE p.name = '<your-project>'
    AND sa.name = '<annotation-name>'
    AND sa.score = 1.0
"""})
return result["rows"]
```
- ›Adds describeSqlSchema and executeSql MCP tools to Phoenix's built-in MCP server (available from v20.2.0), letting coding agents query trace telemetry with read-only SQL instead of paging spans through model context.
- ›Enables code mode by default on the remote MCP server: the agent writes a Python program, Phoenix runs it in a restricted Monty sandbox server-side, and only the final result (not intermediate rows) reaches the model.
- ›Adds px setup mcp --agent <client> CLI command to auto-generate MCP client config for Claude Code (claude), Codex (codex), Cursor (cursor), Gemini (gemini), OpenCode (opencode), and VS Code (vscode).
- ›SQL execution pipeline parses agent-written SQL into a structured AST, restricts to approved telemetry tables and columns, rebuilds a fresh statement, and applies a SQLite authorizer or Postgres query-plan check before running — capped by runtime, row count, and result size.
arize-phoenix-v20.4.0 Aug 26, 2026 · issue 008

Phoenix 20.4.0 adds a retrieval relevance evaluator, new REST endpoints for model providers and project retention, and an in-process MCP toolset.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v20.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v20.4.0
```
- ›Adds GET /v1/model_providers REST endpoint exposing built-in model provider entries with a provider field.
- ›Adds PATCH /projects/{project_identifier}/retention REST endpoint to configure per-project trace retention policies.
- ›Adds a retrieval relevance evaluator to the evals module for scoring RAG retrieval quality.
- ›Adds an in-process Phoenix MCP toolset for agent workflows, enabling direct tool calls into Phoenix without a network hop.
- ›Adds gemini-3.7-flash as a supported model in the Playground.
+4 moreshow less
- ›Enables phoenix-gql mutations by default with approval in PXI manual mode.
- ›Replaces PXI client-action tools with browser-action meta-tools for more flexible agent interactions.
- ›Adds AI Query support for the trace filter DSL, letting users generate filter expressions using natural language.
- ›Supports recording Harbor jobs in Phoenix via the client.
└──▷ BREAKING ON UPGRADE
- !GET /v1/model_providers no longer returns custom providers or a next_cursor field; built-in entries now expose a provider field instead of kind and provider_key. Custom providers are now served by GET /v1/custom_model_providers.
arize-phoenix-client-v3.3.0 Aug 22, 2026 · issue 004

PXI (Phoenix Intelligence) now enables GraphQL mutations by default with user approval in manual mode.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v3.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v3.3.0
```
- ›Enables phoenix-gql mutations by default in PXI (Phoenix Intelligence) manual mode, requiring user approval before execution.
arize-phoenix-evals-v3.5.0 Aug 21, 2026 · issue 004

Arize Phoenix Evals 3.5.0 adds a new retrieval relevance evaluator for RAG pipeline assessment.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v3.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v3.5.0
```
- ›Adds a retrieval relevance evaluator to benchmark how well retrieved documents match queries in RAG pipelines.
arize-phoenix-v20.3.0 Aug 17, 2026 · issue -002

Arize Phoenix v20.3.0 adds an expression filter DSL for querying traces.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v20.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v20.3.0
```
- ›Adds an expression filter DSL for traces, enabling structured query filtering over trace data.
arize-phoenix-v20.3.0 Aug 17, 2026 · issue 002

Phoenix v20.3.0 adds an expression filter DSL for querying traces.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v20.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v20.3.0
```
- ›Introduces an expression filter DSL for traces, enabling programmatic filtering of trace data with structured query expressions.
arize-phoenix-client-v3.2.0 Aug 14, 2026 · issue -005

Arize Phoenix client 3.2.0 adds a new POST /traces/transfer endpoint for transferring traces server-side.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v3.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v3.2.0
```
- ›Adds POST /traces/transfer API endpoint to transfer traces between projects or destinations on the server.
arize-phoenix-client-v3.2.0 Aug 14, 2026 · issue 002

Arize Phoenix client v3.2.0 adds a POST /traces/transfer endpoint for moving traces between projects.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v3.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v3.2.0
```
- ›Adds POST /traces/transfer endpoint to the server for transferring traces.
arize-phoenix-v20.2.0 Aug 13, 2026 · issue -006

Phoenix agents now emit machine-readable approval decisions on gated PXI tools.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v20.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v20.2.0
```
- ›Agents emit a machine-readable approval decision on gated PXI tools, enabling automated handling of human-in-the-loop approval gates.
arize-phoenix-v20.2.0 Aug 13, 2026 · issue 002

Phoenix 20.2.0 emits machine-readable approval decisions on gated PXI tools for agent workflows.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v20.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v20.2.0
```
- ›Adds machine-readable approval decision output on gated PXI (Phoenix Intelligence) tools, enabling automated agent pipelines to programmatically act on tool-gate outcomes.
arize-phoenix-v20.1.0 Aug 12, 2026 · issue -007

Phoenix v20.1.0 adds JWT client assertion for OAuth2, a trace-transfer endpoint, and refined evaluation metric chart controls.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v20.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v20.1.0
```
- ›Adds POST /traces/transfer endpoint to move traces between projects or environments.
- ›Supports JWT client assertion as an authentication method for OAuth2 login flows.
- ›Refines evaluation metric chart layout and controls in the UI.
arize-phoenix-v20.1.0 Aug 12, 2026 · issue 002

Phoenix 20.1.0 adds JWT client assertion for OAuth2 login and a new POST /traces/transfer server endpoint.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v20.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v20.1.0
```
└──▷ TRY IT
Transfer traces from one project to another programmatically via the new server endpoint.
```
$ curl -X POST http://localhost:6006/traces/transfer -H 'Authorization: Bearer <token>' -H 'Content-Type: application/json' -d '{}'
```
- ›Adds POST /traces/transfer API endpoint to the Phoenix server for transferring traces between projects or destinations.
- ›Supports JWT client assertion for OAuth2 login flows, enabling machine-to-machine authentication without interactive credentials.
- ›Refines the evaluation metric chart layout and controls in the UI for improved readability and usability.
arize-phoenix-client-v3.1.0 Aug 11, 2026 · issue -008

Arize Phoenix Client 3.1.0 adds agent session persistence.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v3.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v3.1.0
```
- ›Adds agent session persistence, enabling agent state to be saved and resumed across interactions.
arize-phoenix-v20.0.0 Aug 11, 2026 · issue -008

Phoenix v20 adds agent session persistence, trace_annotations span filter DSL support, and google-genai formatter replacement.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v20.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v20.0.0
```
- ›Supports trace_annotations in the span filter DSL for server-side filtering of spans by their annotations.
- ›Replaces the google-generativeai formatter with the google-genai formatter in the client.
- ›Adds agent session persistence, enabling multi-turn agent sessions to be stored and resumed.
- ›Adds semantic coloring to project metric tooltips in the UI.
└──▷ BREAKING ON UPGRADE
- !The google-generativeai formatter is replaced by the google-genai formatter; any client code relying on the old formatter will break on upgrade. See MIGRATION.md for details.
arize-phoenix-v20.0.0 Aug 11, 2026 · issue 002

Phoenix v20.0.0 adds agent session persistence, trace_annotations span filter support, and a google-genai formatter replacement.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v20.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v20.0.0
```
- ›Supports trace_annotations in the span filter DSL on the server, enabling spans to be filtered by their annotation data.
- ›Replaces the google-generativeai formatter with the google-genai formatter in the client for Google LLM instrumentation.
- ›Adds agent session persistence, allowing agent session state to be retained across interactions.
- ›Adds semantic coloring to project metric tooltips in the UI for clearer metric interpretation.
arize-phoenix-client-v3.0.0 Aug 11, 2026 · issue -008

Phoenix client v3 adds REST endpoints for API keys, experiment tags, dataset splits, and an OpenAI-compatible chat completions proxy.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v3.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v3.0.0
```
- ›Adds span_ids filter parameter to get_spans in the Python and TypeScript clients, enabling targeted span retrieval by ID.
- ›Adds REST CRUD endpoints for user and system API keys with a unified authority model.
- ›Adds REST endpoints for setting tags on experiments.
- ›Adds dataset split create, update, and delete REST endpoints.
- ›Adds a REST endpoint for prompt metadata updates.
+7 moreshow less
- ›Adds support for updating prompt description and metadata via the client.
- ›Adds an OpenAI-compatible v1/chat/completions proxy endpoint with server-side credentials, enabling LLM calls without exposing client-side API keys.
- ›Makes PHOENIX_ENDPOINT the canonical API-access environment variable in the JavaScript client.
- ›Adds evaluator trace isolation and experiment metadata support to the pytest plugin.
- ›Moves PXI agent tracing server-side, reducing client-side instrumentation overhead.
- ›Exposes dataset example source span via the API.
- ›Replaces the google-generativeai formatter with the google-genai formatter in the client.
└──▷ BREAKING ON UPGRADE
- !The google-generativeai formatter has been replaced with google-genai; any code or configuration depending on the google-generativeai formatter will break on upgrade.
arize-phoenix-client-v3.0.0 Aug 11, 2026 · issue 002

Phoenix client v3 adds span_ids filter, REST endpoints for API keys, experiment tags, dataset splits, and an OpenAI-compatible chat completions proxy.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v3.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v3.0.0
```
└──▷ USE IT
Fetch only a specific set of spans by ID — useful when you already know which spans to inspect from a trace.
python
```
spans = client.get_spans(span_ids=["abc123", "def456"])
```
Route LLM calls through Phoenix's OpenAI-compatible proxy to capture traces without changing client code.
```
$ curl -X POST http://localhost:6006/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model": "gpt-4o", "messages": [{"role": "user", "content": "Hello"}]}'
```
- ›Adds span_ids filter parameter to get_spans in the Python and TypeScript clients, enabling retrieval of specific spans by ID.
- ›Adds REST CRUD endpoints for user and system API keys with a unified authority model.
- ›Adds REST endpoints for setting tags on experiments.
- ›Adds dataset split create/update/delete REST endpoints.
- ›Adds a REST endpoint for prompt metadata updates.
+6 moreshow less
- ›Supports updating prompt description and metadata via the client.
- ›Adds an OpenAI-compatible v1/chat/completions proxy endpoint on the server with server-side credentials, enabling drop-in use of Phoenix as an LLM gateway.
- ›Moves PXI (Phoenix Intelligence) agent tracing server-side.
- ›Makes PHOENIX_ENDPOINT the canonical API-access environment variable for the JavaScript client.
- ›Adds evaluator trace isolation and experiment metadata support to the pytest plugin.
- ›Updates the Google GenAI formatter from google-generativeai to google-genai.
└──▷ BREAKING ON UPGRADE
- !The google-generativeai formatter is replaced by google-genai; any code referencing the old formatter will break on upgrade.
arize-phoenix-v19.21.0 Aug 10, 2026 · issue -009

Adds REST endpoints for experiment tag management and AI-powered natural-language session filtering.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.21.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.21.0
```
- ›Adds REST endpoints for setting tags on experiments, enabling programmatic experiment organization via the API.
- ›Adds AI-powered natural-language query support to the session filter in the UI, allowing practitioners to filter sessions using plain-language prompts.
arize-phoenix-v19.21.0 Aug 10, 2026 · issue 002

Phoenix v19.21.0 adds REST endpoints for experiment tag management and AI-powered session filtering.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.21.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.21.0
```
- ›Adds REST endpoints for setting tags on experiments, enabling programmatic tag management via the API.
- ›Adds AI-powered query filtering for the session filter in the UI, allowing natural-language session search.
arize-phoenix-v19.20.0 Aug 10, 2026 · issue -009

Phoenix v19.20.0 adds dataset split REST endpoints and copy actions for session turns.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.20.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.20.0
```
- ›Adds REST endpoints to create, update, and delete dataset splits.
- ›Adds copy actions to session turns in the UI.
arize-phoenix-v19.20.0 Aug 10, 2026 · issue 002

Phoenix v19.20.0 adds dataset split REST endpoints and copy actions for session turns.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.20.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.20.0
```
- ›Adds copy actions to session turns in the UI, letting practitioners quickly copy turn content.
arize-phoenix-otel-v0.17.0 Aug 8, 2026 · issue -011

arize-phoenix-otel v0.17.0 adds support for a Phoenix environment file for configuration.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-otel-v0.17.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-otel-v0.17.0
```
- ›Supports a Phoenix env file for configuring arize-phoenix-otel settings via a file-based environment variable approach.
arize-phoenix-evals-v3.4.0 Aug 8, 2026 · issue -011

Arize Phoenix Evals 3.4.0 adds a built-in hallucination evaluator.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v3.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v3.4.0
```
- ›Adds a hallucination evaluator to the evals library for detecting hallucinated content in LLM outputs.
arize-phoenix-evals-v3.4.0 Aug 8, 2026 · issue 002

Arize Phoenix Evals 3.4.0 adds a built-in hallucination evaluator.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v3.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v3.4.0
```
- ›Adds a hallucination evaluator to the arize-phoenix-evals library for detecting hallucinated content in LLM outputs.
arize-phoenix-v19.19.0 Aug 7, 2026 · issue -012

Phoenix v19.19.0 collapses older messages in LLM span views to reduce noise.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.19.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.19.0
```
- ›In the trace UI, all messages except the last are now collapsed by default in LLM spans, reducing visual clutter when inspecting long conversations.
arize-phoenix-v19.19.0 Aug 7, 2026 · issue 002

Phoenix v19.19.0 collapses all but the last message in LLM span views for cleaner trace inspection.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.19.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.19.0
```
- ›In the UI, LLM span detail views now collapse all messages except the last one by default, reducing noise when inspecting multi-turn conversation spans.
arize-phoenix-v19.18.0 Aug 5, 2026 · issue -014

Phoenix v19.18.0 adds a REST endpoint for prompt metadata updates and an expression filter DSL for sessions.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.18.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.18.0
```
- ›Adds a REST endpoint for updating prompt metadata.
- ›Adds an expression filter DSL for filtering sessions.
arize-phoenix-v19.18.0 Aug 5, 2026 · issue 002

Phoenix v19.18.0 adds a REST endpoint for prompt metadata updates and an expression filter DSL for sessions.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.18.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.18.0
```
- ›Adds a REST endpoint for prompt metadata updates, enabling programmatic management of prompt metadata via the Phoenix API.
- ›Adds an expression filter DSL for sessions, enabling structured query filtering over session data.
arize-phoenix-sqlean-v0.1.0 Aug 5, 2026 · issue -014

Arize Phoenix ships arize-phoenix-sqlean v0.1.0, vendoring nalgeon/sqlean.py as a first-party library.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-sqlean-v0.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-sqlean-v0.1.0
```
- ›Introduces the arize-phoenix-sqlean package, a vendored distribution of nalgeon/sqlean.py under the Arize Phoenix project.
arize-phoenix-sqlean-v0.1.0 Aug 5, 2026 · issue 002

Arize Phoenix adds arize-phoenix-sqlean, a vendored distribution of nalgeon/sqlean.py for SQLite extensions.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-sqlean-v0.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-sqlean-v0.1.0
```
- ›Introduces the arize-phoenix-sqlean package, a vendored copy of nalgeon/sqlean.py providing SQLite extension support within the Phoenix ecosystem.
arize-phoenix-v19.17.0 Aug 4, 2026 · issue -015

Arize Phoenix v19.17.0 adds AI-powered query assistance for filter fields in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.17.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.17.0
```
- ›Adds AI Query assistance for filter fields in the UI, enabling natural-language construction of trace/span filters.
arize-phoenix-v19.16.0 Aug 4, 2026 · issue -015

Phoenix v19.16.0 adds an OpenAI-compatible /v1/chat/completions proxy with server-side credentials and parallelized span export downloads.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.16.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.16.0
```
- ›Adds an OpenAI-compatible v1/chat/completions proxy endpoint to the Phoenix server, enabling server-side credential management for LLM requests.
- ›Parallelizes span export fetches and streams downloads to disk, unlocking faster large-scale trace exports from the UI.
- ›Adds preview card contents while collapsed in the UI, letting practitioners skim trace details without expanding each card.
arize-phoenix-v19.16.0 Aug 4, 2026 · issue 002

Phoenix 19.16.0 adds an OpenAI-compatible v1/chat/completions proxy with server-side credentials and a UI preview for collapsed cards.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.16.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.16.0
```
- ›Adds an OpenAI-compatible v1/chat/completions proxy endpoint on the Phoenix server, allowing clients to route LLM calls through Phoenix using server-side credentials instead of passing API keys client-side.
- ›Parallelizes span export fetches and streams downloads to disk, enabling faster and more scalable span exports from the UI.
- ›New UI feature: collapsed cards now show a preview of their contents, reducing the need to expand each card to identify relevant traces.
arize-phoenix-v19.15.0 Aug 3, 2026 · issue 002

Phoenix v19.15.0 defers and parallelizes annotation metric chart loading for faster project views.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.15.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.15.0
```
- ›Annotation metric charts in the project view now load independently and are deferred, improving perceived performance for projects with many annotations.
- ›Annotation metric charts are fetched in parallel rather than as part of the main project query, reducing initial page load time.
arize-phoenix-v19.14.0 Aug 3, 2026 · issue -016

Phoenix v19.14.0 adds a built-in hallucination evaluator to the evals library.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.14.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.14.0
```
- ›Adds a hallucination evaluator to the evals module for detecting hallucinated content in LLM outputs.
arize-phoenix-v19.14.0 Aug 3, 2026 · issue 002

Arize Phoenix 19.14.0 adds a new hallucination evaluator to its LLM evals library.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.14.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.14.0
```
- ›Adds a hallucination evaluator to the evals module for benchmarking LLM application outputs against hallucination.
arize-phoenix-v19.13.0 Aug 1, 2026 · issue -018

Phoenix v19.13.0 adds annotations to span exports and lifts the experiment metric chart selection limit.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.13.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.13.0
```
- ›Span and trace annotations are now included when exporting spans, enriching exported data with human and automated feedback signals.
- ›Removes the metric chart selection limit in the experiments view, allowing unlimited metrics to be charted simultaneously.
arize-phoenix-v19.13.0 Aug 1, 2026 · issue 002

Phoenix v19.13.0 adds span/trace annotations to span exports and removes the metric chart selection limit in experiments.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.13.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.13.0
```
- ›Span exports now include span and trace annotations, surfacing reviewer feedback and evaluation labels alongside raw span data.
- ›Lifts the metric chart selection limit in the Experiments UI, enabling comparison of an unrestricted number of metrics simultaneously.
arize-phoenix-v19.12.0 Jul 31, 2026 · issue -019

Arize Phoenix v19.12.0 adds a Harbor proof-of-concept integration for evals.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.12.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.12.0
```
- ›Adds Harbor proof-of-concept integration to the evals module.
arize-phoenix-v19.12.0 Jul 31, 2026 · issue 002

Adds Harbor integration proof-of-concept to Phoenix evals.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.12.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.12.0
```
- ›Introduces Harbor integration (proof-of-concept) for the evals subsystem.
arize-phoenix-v19.11.0 Jul 30, 2026 · issue -020

Phoenix v19.11.0 adds project evaluation metric charts, subagent tool call counting, and a pinned note-taking bar for span details.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.11.0
```
- ›Adds project evaluation metrics charts to visualize eval results at the project level.
- ›Counts subagent tool calls online during evaluations, enabling real-time tracking of tool usage in agentic workflows.
- ›Defers metric chart loading and removes the chart selection cap, allowing more charts to be displayed simultaneously without blocking.
- ›Displays tool and tool call counts in LLM span card headers for at-a-glance agentic span inspection.
- ›Adds a pinned note-taking bar to the span details view for persistent inline annotations.
+2 moreshow less
- ›Moves root-span scoping into the filter condition UI, integrating trace-root filtering with the standard filter builder.
- ›Updates the Monty provider icon to use the Pydantic logo in the sandboxes UI.
arize-phoenix-v19.11.0 Jul 30, 2026 · issue 002

Phoenix v19.11.0 adds project evaluation metric charts, online subagent tool-call counting, and a pinned note-taking bar in span details.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.11.0
```
- ›Adds project evaluation metrics charts to the project view for at-a-glance assessment of eval performance over time.
- ›Counts subagent tool calls online in evals, enabling live monitoring of tool-use behavior in agentic workflows.
- ›Defers metric chart loading and removes the chart selection cap, allowing more metric charts to be displayed simultaneously without blocking the UI.
- ›Shows tool and tool call counts in LLM span card headers for faster inspection of how many tools an LLM span invoked.
- ›Adds a pinned note-taking bar to the span details panel so annotations persist while scrolling through trace data.
+1 moreshow less
- ›Moves root-span scoping into the filter condition in the traces UI, giving finer-grained control over trace filtering.
arize-phoenix-v19.10.0 Jul 28, 2026 · issue -022

Phoenix v19.10.0 adds experiment evaluation metrics charts, token sub-type breakdowns, and drag-to-reorder chart menus.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.10.0
```
- ›Adds experiment evaluation metrics charts to the experiments UI for visualizing eval results over runs.
- ›Breaks down token charts by sub-type (e.g. prompt, completion) and surfaces cost and token breakdown bars inside chart tooltips.
- ›Enables drag-to-reorder selected charts via the chart menu for custom dashboard layouts.
- ›Collapses experiment table rows to a single line for a more compact experiments view.
- ›Adds Monty provider with shared runtime to the sandbox environment.
arize-phoenix-v19.10.0 Jul 28, 2026 · issue 002

Phoenix v19.10.0 adds experiment evaluation metrics charts, token sub-type breakdowns, and drag-to-reorder chart menus.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.10.0
```
- ›Adds evaluation metrics charts to the experiments view for visualizing experiment evaluation results over time.
- ›Breaks down token charts by sub-type, with cost and token breakdown bars now visible in chart tooltips.
- ›Enables drag-to-reorder selected charts via the chart menu for custom dashboard layouts.
- ›Adds collapsible experiment table rows to a single line for a more compact experiments view.
- ›Adds a Monty provider with shared runtime to the sandbox environment.
arize-phoenix-v19.9.0 Jul 28, 2026 · issue -022

Phoenix v19.9.0 adds bulk expand/collapse of span info sections and narrow-width chart readability improvements.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.9.0
```
- ›Adds expand or collapse all span info sections at once in the trace view, reducing manual clicking when inspecting complex traces.
- ›Chart panels remain readable at narrow widths, making dashboards usable in split-screen or constrained layouts.
arize-phoenix-v19.9.0 Jul 28, 2026 · issue 002

Phoenix v19.9.0 adds bulk expand/collapse of span info sections and improved chart readability at narrow widths.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.9.0
```
- ›Adds expand-or-collapse-all control for span info sections in the trace view, letting practitioners open or close every section at once instead of one at a time.
- ›Keeps chart panels readable at narrow widths, improving usability of dashboards in constrained layouts.
arize-phoenix-v19.8.0 Jul 27, 2026 · issue -023

Phoenix v19.8.0 adds Claude Opus 5 to the curated agent model list and the Playground.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.8.0
```
- ›Adds Claude Opus 5 to the curated model list for agent evaluations.
- ›Registers Claude Opus 5 in the Playground for interactive prompt testing.
arize-phoenix-v19.8.0 Jul 27, 2026 · issue 002

Arize Phoenix v19.8.0 adds Claude Opus 5 to the agent model list and the Playground.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.8.0
```
- ›Adds Claude Opus 5 to the curated model list for agent use cases.
- ›Registers Claude Opus 5 in the Playground for prompt comparison and model evaluation.
arize-phoenix-v19.7.0 Jul 27, 2026 · issue -023

Phoenix 19.7.0 adds span detail downloads, a root-span DSL predicate, and richer span inspection tables in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.7.0
```
- ›Adds parent_span is None root-span predicate to the span filter DSL, enabling queries scoped to only root spans.
- ›Adds span detail downloads from the span detail view.
- ›Adds evaluator trace isolation and experiment metadata support to the pytest plugin.
- ›Adds collapse/expand row controls in the tracing tables UI.
- ›Adds a searchable table view for span attributes in the UI.
+3 moreshow less
- ›Adds span annotations and notes rendered as tables in the span detail UI.
- ›Makes the retention policy project list manageable from the UI.
- ›Adds an expandable search button (expands from icon) in the UI.
arize-phoenix-v19.7.0 Jul 27, 2026 · issue 002

Phoenix 19.7.0 adds span detail downloads, a parent_span is None root-span DSL predicate, evaluator trace isolation in pytest, and richer span UI tables.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.7.0
```
- ›Adds parent_span is None predicate to the span filter DSL, enabling queries that scope results to root spans only.
- ›Adds span detail downloads directly from the span detail view.
- ›Adds evaluator trace isolation and experiment metadata support to the pytest plugin.
- ›Adds collapse/expand row controls to tracing tables in the UI.
- ›Adds a searchable table view for span attributes in the UI.
+2 moreshow less
- ›Displays a span's annotations and notes as tables in the UI.
- ›Makes the retention policy project list manageable from the UI, allowing per-project control.
arize-phoenix-v19.6.0 Jul 24, 2026 · issue -026

Phoenix 19.6.0 adds span_ids filter to get_spans in Python and TypeScript clients, plus OTLP JSON export for selected spans/traces in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.6.0
```
└──▷ USE IT
Fetch only the spans you care about by passing specific span IDs — useful when you already know which spans to investigate and want to skip a broader query.
python
```
spans = client.get_spans(span_ids=["abc123", "def456"])
```
- ›Adds span_ids filter parameter to get_spans in the Python and TypeScript clients, enabling targeted retrieval of specific spans by ID.
- ›New UI capability to download selected spans or traces as OTLP JSON directly from the spans/traces view.
arize-phoenix-v19.6.0 Jul 24, 2026 · issue 002

Phoenix v19.6.0 adds span_ids filter to get_spans in Python and TypeScript clients, plus OTLP JSON export for selected spans/traces in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.6.0
```
└──▷ USE IT
Fetch only a known set of spans by ID — useful when you have span IDs from an alert or upstream system and want to pull just those traces for analysis.
python
```
spans = client.get_spans(span_ids=["abc123", "def456"])
```
- ›Adds span_ids filter parameter to get_spans in the Python and TypeScript clients, enabling targeted retrieval of specific spans by ID.
- ›New UI capability to download selected spans or traces as OTLP JSON directly from the trace view.
arize-phoenix-v19.5.0 Jul 24, 2026 · issue -026

Phoenix 19.5.0 adds evaluation metrics aggregation APIs, online agent trace evals with tool_count_per_turn and user_friction, a toxicity eval template, and Gemini 3.6 Flash support.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.5.0
```
- ›Adds evaluation metrics aggregation APIs for programmatic rollup of eval results across traces.
- ›Adds online trace evals for agent workflows with two new built-in metrics: tool_count_per_turn and user_friction.
- ›Exposes dataset example source span via the API, linking dataset examples back to their originating trace span.
- ›Adds a toxicity gallery eval template designed to be input/output-agnostic for benchmarking.
- ›Adds Gemini 3.6 Flash and 3.5 Flash-lite model support in the Playground.
+1 moreshow less
- ›Adds semantic PXI tool icons to the UI for clearer agent tool visualization.
arize-phoenix-v19.5.0 Jul 24, 2026 · issue 002

Phoenix 19.5.0 adds evaluation metrics aggregation APIs, online agent trace evals with tool_count_per_turn and user_friction, a toxicity eval gallery template, and Gemini 3.6 Flash / 3.5 Flash-lite playground support.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.5.0
```
- ›Adds evaluation metrics aggregation APIs for programmatic roll-up of eval results across traces.
- ›Adds online trace evaluators tool_count_per_turn and user_friction for real-time agent quality monitoring.
- ›Exposes dataset example source span via the API, linking dataset examples back to their originating trace span.
- ›Adds a toxicity gallery template — an input/output-agnostic benchmark eval — to the evals library.
- ›Adds Gemini 3.6 Flash and Gemini 3.5 Flash-lite as selectable models in the Playground.
arize-phoenix-evals-v3.3.0 Jul 23, 2026 · issue -027

Arize Phoenix Evals 3.3.0 adds a toxicity gallery template with an input/output-agnostic benchmark.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v3.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v3.3.0
```
- ›Adds a toxicity gallery template with an input/output-agnostic benchmark for evaluating toxic content across varied prompt and response surfaces.
arize-phoenix-evals-v3.3.0 Jul 23, 2026 · issue 002

Arize Phoenix Evals 3.3.0 adds an input/output-agnostic toxicity gallery template for benchmarking.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v3.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v3.3.0
```
- ›Adds a toxicity gallery template with an input/output-agnostic benchmark for evaluating toxic content in LLM outputs.
arize-phoenix-v19.4.0 Jul 22, 2026 · issue -028

Phoenix v19.4.0 upgrades JS tracing to AI SDK v7 and redesigns the span header UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.4.0
```
- ›Upgrades phoenix-otel to openinference-vercel v3, adding support for AI SDK v7 spans in JavaScript tracing.
- ›Redesigns the span header into separate identity and meta rows in the tracing UI.
- ›Makes IDBadge the consolidated click-to-copy ID element across the UI.
- ›Aligns span kind icon and timeline bar colors with token treatment in the components UI.
arize-phoenix-v19.4.0 Jul 22, 2026 · issue 002

Phoenix v19.4.0 upgrades Vercel AI SDK v7 span support and refreshes the tracing UI
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.4.0
```
- ›Upgrades phoenix-otel to openinference-vercel v3, adding support for Vercel AI SDK v7 spans in the JavaScript integration.
- ›Redesigns the span header in the tracing UI into separate identity and meta rows for improved readability.
- ›Aligns span kind icon and timeline bar colors with token treatment in the component library.
- ›Makes IDBadge the consolidated click-to-copy ID element across the UI.
arize-phoenix-evals-v3.2.0 Jul 21, 2026 · issue -029

Arize Phoenix Evals 3.2.0 adds a user friction evaluator for detecting friction in AI interactions.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v3.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v3.2.0
```
- ›Adds a user friction evaluator to detect and score friction points in AI assistant conversations.
arize-phoenix-evals-v3.2.0 Jul 21, 2026 · issue 002

Arize Phoenix Evals 3.2.0 adds a user friction evaluator for assessing conversational pain points in LLM applications.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v3.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v3.2.0
```
- ›Adds a user friction evaluator to detect friction points in LLM application conversations.
arize-phoenix-v19.3.0 Jul 20, 2026 · issue -030

Phoenix v19.3.0 adds HTTP/2 for OAuth2/OIDC, provisioned-provider model filtering in Playground, and routed profile settings tabs.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.3.0
```
- ›Playground model picker now filters to provisioned providers only, reducing misconfiguration when selecting models.
- ›Auth layer negotiates HTTP/2 for OAuth2/OIDC provider requests, improving connection efficiency for federated identity flows.
- ›Settings page gains documentation onramps for faster in-app guidance access.
- ›UI adds routed profile settings tabs, enabling deep-linking directly to specific profile setting sections.
arize-phoenix-v19.2.0 Jul 19, 2026 · issue -031

Phoenix v19.2.0 adds Antigravity and OpenCode MCP client instructions in settings.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.2.0
```
- ›Adds Antigravity and OpenCode MCP client instructions to the Settings UI.
- ›Improves the server startup banner to show dev tooling info at boot.
arize-phoenix-v19.1.0 Jul 18, 2026 · issue -032

Phoenix v19.1.0 adds px setup mcp CLI command and a new MCP settings tab in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.1.0
```
└──▷ TRY IT
Register the Phoenix remote MCP server with your coding agent in one step.
```
$ px setup mcp
```
- ›Adds px setup mcp CLI subcommand to register the Phoenix remote MCP server with a coding agent.
- ›Adds a new MCP settings tab in the Phoenix UI with a setup guide for configuring MCP connections.
arize-phoenix-v19.0.0 Jul 17, 2026 · issue -033

Phoenix v19 adds OAuth2 authorization server with CLI login and tightens API key creation to session-authenticated callers only.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v19.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v19.0.0
```
- ›Adds OAuth2 authorization server and CLI login (pxi CLI) for browser-based and unattended authentication workflows.
- ›Improved pxi token display makes issued tokens easier to inspect after CLI login.
- ›Relocates the pxi button in the UI for improved discoverability.
└──▷ BREAKING ON UPGRADE
- !GraphQL createUserApiKey and createSystemApiKey mutations no longer accept API-key-authenticated callers; workflows that used an existing API key for unattended key creation must switch to a session-authenticated context or, for system keys, use PHOENIX_ADMIN_SECRET.
arize-phoenix-v18.1.0 Jul 17, 2026 · issue -033

Phoenix 18.1.0 adds REST CRUD for API keys, a px setup CLI wizard, a user-friction evaluator, and user.id span tracing.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v18.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v18.1.0
```
└──▷ TRY IT
Onboard a new app to Phoenix and confirm traces are flowing without manual config.
```
$ px setup
```
- ›Adds REST CRUD endpoints for user and system API keys under /v1/users/api_keys (page size capped at 1000), enforcing a unified authority model that requires a human session to issue keys.
- ›Adds px setup CLI command to connect an application to Phoenix and verify that traces arrive, with an option to include the Phoenix docs MCP server during setup.
- ›Surfaces the user.id span attribute on spans, traces, and sessions for end-to-end user-level traceability.
- ›Adds a user-friction evaluator to arize-phoenix-evals for assessing friction in user interactions.
- ›Splits Users and API Keys into dedicated tabs in the Settings UI for clearer key management.
+2 moreshow less
- ›Adds browser/server tabs in the AI provider credential storage UI to clarify where credentials are held.
- ›Settings tabs now display vertically on large screens with a responsive fallback.
arize-phoenix-v18.0.0 Jul 14, 2026 · issue -036

Phoenix v18 shifts session time-range filters to interval-overlap semantics.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v18.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v18.0.0
```
- ›Session time-range filters now use interval-overlap semantics, returning sessions where any part of the session overlaps the queried range rather than requiring full containment.
└──▷ BREAKING ON UPGRADE
- !Session time-range filters changed to interval-overlap semantics — queries that previously relied on containment-based filtering will now return a different (broader) set of sessions. See MIGRATION.md for details.
arize-phoenix-v17.30.0 Jul 14, 2026 · issue -036

Phoenix v17.30.0 adds force-tracing via debug env var, batch annotation config management, and playground error count display.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.30.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.30.0
```
- ›Adds a debug environment variable to force tracing for agents, enabling trace capture without modifying application code.
- ›Supports batch annotation config management in the app, allowing annotation configurations to be created and managed in bulk.
- ›Playground now shows output error counts, making it easier to spot failures across multiple LLM runs at a glance.
arize-phoenix-v17.29.0 Jul 13, 2026 · issue -037

Phoenix v17.29.0 moves PXI tracing server-side and adds a remote export setup command.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.29.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.29.0
```
- ›Adds remote export setup command to pxi for configuring remote export.
- ›Moves PXI tracing to server-side execution for agent workflows.
arize-phoenix-v17.28.0 Jul 13, 2026 · issue -037

Phoenix 17.28.0 adds session annotation editing and collapsible playground sections in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.28.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.28.0
```
- ›Enables editing of session annotations directly within the session details view.
- ›Adds collapsible playground sections via the TitledPanel component for a cleaner workspace layout.
- ›Modernizes core Tabs with an animated selection indicator and scroll snapping.
arize-phoenix-v17.27.0 Jul 12, 2026 · issue -038

Phoenix 17.27.0 adds drag-and-drop column reordering, full span I/O tooltips, and authorship columns across traces, sessions, experiments, and prompts tables.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.27.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.27.0
```
- ›Adds drag-and-drop column reordering with a redesigned column selector across the traces, sessions, and experiments tables in the UI.
- ›Enables column customization for the prompts table in the UI.
- ›Adds dataset and prompt authorship columns (renamed to updatedBy) to the UI.
- ›Previews full span input/output content in table row tooltips in the traces UI.
arize-phoenix-client-v2.13.0 Jul 12, 2026 · issue -038

Phoenix client gains name_contains project filtering, .env file support, and a second project-name env var.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v2.13.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v2.13.0
```
└──▷ USE IT
Filter projects by a partial name match instead of listing all and filtering manually.
python
```
matching = client.projects.list(name_contains="prod")
```
- ›Adds name_contains filter parameter to projects.list() in the Python client, enabling substring search across projects.
- ›Supports a Phoenix .env file for storing environment-based configuration.
- ›Accepts both PHOENIX_PROJECT_NAME and PHOENIX_PROJECT environment variables interchangeably everywhere in the SDK.
arize-phoenix-v17.26.0 Jul 11, 2026 · issue -039

Phoenix v17.26.0 clarifies forced tool choice menus in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.26.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.26.0
```
- ›Improves forced tool choice menus with clearer labeling to make tool selection options more distinguishable.
arize-phoenix-v17.25.0 Jul 11, 2026 · issue -039

Phoenix v17.25.0 adds approval-gated annotation config tools, a .env file, and a new Metrics tab with experiment charts.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.25.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.25.0
```
└──▷ USE IT
Configure Phoenix server settings persistently without passing environment variables on every launch.
ini
```
PHOENIX_HOST=0.0.0.0
PHOENIX_PORT=6006
PHOENIX_SQL_DATABASE_URL=sqlite:///phoenix.db
```
- ›Introduces a Phoenix environment file for configuring the server via .env.
- ›Adds approval-gated annotation config tools and span-coding support for PXI in the agents workflow.
- ›Adds a Metrics tab to the dataset page showing experiment charts in the UI.
- ›Refines experiment metric charts in the UI with improved visuals.
arize-phoenix-v17.24.0 Jul 10, 2026 · issue -040

Phoenix evals move to a pytest plugin, enabling PXI evals to run natively in standard test suites.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.24.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.24.0
```
- ›Moves PXI evals to a pytest plugin, allowing Phoenix evals to be executed directly within pytest test suites.
arize-phoenix-v17.23.0 Jul 9, 2026 · issue -041

Arize Phoenix v17.23.0 adds support for the GPT 5.6 model family.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.23.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.23.0
```
- ›Adds support for the GPT 5.6 model family.
arize-phoenix-v17.21.0 Jul 8, 2026 · issue -042

Phoenix v17.21.0 adds end-to-end agent turn tracing, a global search palette, and session lifecycle management.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.21.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.21.0
```
- ›Adds end-to-end PXI turn tracing from browser to backend for agents, linking frontend interactions to backend spans in a single trace.
- ›Adds a global search command palette (⌘K) for fast in-app navigation across projects and traces.
- ›Adds a session stats side panel to the sessions table, surfacing per-session metrics without leaving the list view.
- ›Adds session turn dividers with copy support for easier inspection and sharing of individual turns.
- ›Automatically sweeps orphaned sessions after a one-hour grace period to keep session data clean.
+2 moreshow less
- ›Shows total session count on project cards for at-a-glance visibility.
- ›Introduces read-only UI styles for surfaces that should not be editable.
arize-phoenix-v17.20.0 Jul 7, 2026 · issue -043

Phoenix v17.20.0 adds user-selected metric charts above project tables in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.20.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.20.0
```
- ›Adds user-selected metric charts displayed above project tables on the Projects page, letting practitioners pin and view key metrics at a glance.
arize-phoenix-v17.19.0 Jul 6, 2026 · issue -044

Phoenix v17.19.0 adds trace tree search and a consolidated account menu in the side nav.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.19.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.19.0
```
- ›Adds trace tree search in the app UI, enabling practitioners to search within the trace tree view.
- ›Adds a consolidated account menu in the side navigation bar.
arize-phoenix-v17.17.0 Jul 4, 2026 · issue -046

Phoenix v17.17.0 adds shift-click range selection in tables and recent searches in the span filter typeahead.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.17.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.17.0
```
- ›Adds recent search history to the span filter typeahead for faster reuse of previous filter queries.
- ›Enables shift-click range selection in tables for bulk-selecting multiple rows at once.
arize-phoenix-v17.16.0 Jul 4, 2026 · issue -046

Phoenix v17.16.0 adds REST endpoints for annotation configs and dataset labels, CLI annotation-config commands, and JS precision/recall/F-score evaluators.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.16.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.16.0
```
└──▷ TRY IT
Filter projects by name substring when listing all projects — useful when managing large numbers of tracing projects.
```
$ curl -X GET 'https://<phoenix-host>/v1/projects?name_contains=prod' -H 'Authorization: Bearer <token>'
```
- ›Adds name_contains filter parameter to GET /v1/projects for server-side project name filtering.
- ›Adds REST endpoints for assigning annotation configs to projects via the API.
- ›Adds dataset label REST endpoints to the server.
- ›Adds annotation-config get, annotation-config create, and annotation-config update subcommands to the CLI.
- ›Adds precision, recall, and F-score code evaluators to the JavaScript phoenix-evals package.
+5 moreshow less
- ›Adds auth.md support for agent authentication discovery.
- ›Adds baseline tagging for experiments.
- ›Adds an error column to the spans and traces tables in the UI.
- ›Adds version count, latest version, and version tags columns to the prompts table in the UI.
- ›Adds a dismissable version update notice to the side navigation in the UI.
arize-phoenix-client-v2.12.0 Jul 3, 2026 · issue -047

Phoenix client v2.12.0 adds REST endpoints for assigning annotation configs to projects and managing dataset labels.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v2.12.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v2.12.0
```
- ›Adds REST API support for assigning annotation configs to projects.
- ›Adds REST endpoints for dataset label management.
arize-phoenix-v17.15.0 Jul 1, 2026 · issue -049

Phoenix v17.15.0 adds Claude Sonnet 5 to the Anthropic and AWS Bedrock playground providers.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.15.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.15.0
```
- ›Adds Claude Sonnet 5 as a selectable model in the Playground for both the Anthropic and AWS (Bedrock) providers.
arize-phoenix-client-v2.11.0 Jun 30, 2026 · issue -050

Arize Phoenix client 2.11.0 adds an annotation summary view to project settings.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v2.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v2.11.0
```
- ›Adds an annotation summary panel to project settings in the UI.
arize-phoenix-v17.14.0 Jun 30, 2026 · issue -050

Phoenix v17.14.0 adds an annotation summary view to project settings in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.14.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.14.0
```
- ›Adds an annotation summary panel to the project settings page in the UI.
arize-phoenix-v17.13.0 Jun 30, 2026 · issue -050

Phoenix 17.13.0 adds a TUI for the pxi CLI, a pytest plugin for eval CI, and simplified pydantic-ai turn output instrumentation.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.13.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.13.0
```
- ›Adds pxi tui subcommand — an interactive terminal UI for the Phoenix CLI (pxi).
- ›Adds a pytest plugin in phoenix-client for running LLM evals inside CI pipelines.
- ›Simplifies turn output instrumentation for pydantic-ai integrations.
arize-phoenix-client-v2.10.0 Jun 26, 2026 · issue -054

Phoenix client v2.10.0 adds a pytest plugin for eval CI, a direct server agent endpoint, session context for agents, and prompt route contexts.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v2.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v2.10.0
```
- ›Adds a pytest plugin for running eval CI directly from the phoenix-client library.
- ›Adds a direct server agent endpoint for communicating with agents.
- ›Adds session context support for agents, enabling stateful agent interactions.
- ›Adds prompt route contexts (pxi) for managing prompt routing.
- ›Adds experiment editing and eval skills for agents.
arize-phoenix-v17.12.0 Jun 25, 2026 · issue -055

Phoenix v17.12.0 adds a direct server agent endpoint, opt-in user ID on traces, CI eval testing API for JS, and sub-agent progress streaming.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.12.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.12.0
```
- ›Adds CI eval testing API to the JavaScript phoenix-client library for automated evaluation testing in CI pipelines.
- ›Adds a direct server agent endpoint for agent interactions.
- ›Attaches opt-in user.id to Phoenix Intelligence (pxi) traces to correlate agent activity with individual users.
- ›Streams call_subagent progress in real time so agent task status is visible as it executes.
- ›Adds a copyable trace ID in the trace details dialog header within the Experiments UI.
arize-phoenix-v17.11.0 Jun 24, 2026 · issue -056

Phoenix v17.11.0 adds agent-readable eval failure reports, trace annotation summaries, and Swagger UI exposure of agent endpoints in dev mode.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.11.0
```
└──▷ TRY IT
Explore agent endpoints interactively via Swagger UI during local development without needing external API documentation.
```
$ python -m phoenix.server.main --dev
```
- ›Exposes agent endpoints in Swagger UI when running the server with --dev, making it easier to explore and test agent APIs interactively.
- ›Adds agent-readable failure reports for the PXI eval harness, surfacing structured evaluation failures directly to agents.
- ›Shows trace annotation summaries in the project stats panel, giving a at-a-glance view of annotation coverage across traces.
- ›Enables submitting a highlighted command on Enter in the agent skill prompt UI.
arize-phoenix-v17.10.0 Jun 22, 2026 · issue -058

Phoenix v17.10.0 surfaces trace-level annotations directly in the trace header UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.10.0
```
- ›Trace-level annotations are now displayed in the trace header, making annotation context visible without navigating into individual spans.
arize-phoenix-v17.9.0 Jun 19, 2026 · issue -061

Phoenix 17.9.0 adds a server-side bash tool for agents, OAuth2 role-resync control, and label filtering for prompts and datasets.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.9.0
```
└──▷ TRY IT
Disable the server-side bash tool in a hardened deployment where arbitrary shell execution is not permitted.
```
$ export PHOENIX_AGENTS_DISABLE_BASH=true
```
- ›Adds PHOENIX_AGENTS_DISABLE_BASH environment variable to disable the server-side bash tool for agents.
- ›Adds a server-side bash tool for agents, enabling server-executed shell commands within agent workflows.
- ›Adds ROLE_RESYNC configuration for OAuth2 identity providers to preserve manually assigned role overrides during resync.
- ›Adds prompt route contexts to the Phoenix Inference (pxi) interface.
- ›Adds label filtering for prompts and datasets, with label management directly from the list view and a prompt model column.
+2 moreshow less
- ›Renders every tool call individually with execution summaries in the pxi UI.
- ›Shows usage counts for dataset and prompt labels in the UI.
arize-phoenix-v17.8.0 Jun 17, 2026 · issue -063

Phoenix v17.8.0 adds an Agent GraphQL skill and theme-aware UI pre-loading.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.8.0
```
- ›Adds an Agent GraphQL skill, enabling agent-oriented queries through the GraphQL interface.
- ›UI background color pre-loading now respects saved theme preferences and OS-level dark/light mode settings.
arize-phoenix-v17.7.0 Jun 16, 2026 · issue -064

Phoenix 17.7.0 adds token detail metrics charts, agent session context, and shareable trace time range URLs.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.7.0
```
- ›Adds token detail metrics charts to visualize granular token usage breakdowns in the UI.
- ›Adds session context for agents, enabling richer tracking of agent sessions across traces.
- ›Makes trace time range URLs shareable so practitioners can link directly to a specific time window in a trace view.
arize-phoenix-v17.6.0 Jun 15, 2026 · issue -065

Phoenix v17.6.0 adds experiment editing, annotation score time series, and live-streaming pan/zoom controls.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.6.0
```
- ›Adds trace and session annotation score time series to the metrics view, enabling trend analysis of annotation scores over time.
- ›Adds pan and zoom time range controls to the UI with a live streaming toggle for real-time monitoring.
- ›Adds experiment editing and eval skills for agents, allowing in-place modification of experiments and evaluations.
arize-phoenix-v17.5.0 Jun 12, 2026 · issue -068

Phoenix 17.5.0 adds a subagents toggle in assistant settings and a calendar-based time range picker in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.5.0
```
- ›Adds a subagents toggle to assistant settings, enabling control over whether subagents are used during agent interactions.
- ›Adds a calendar-based date picker to the time range selector in the UI for more precise trace and data filtering.
arize-phoenix-client-v2.9.0 Jun 11, 2026 · issue -069

Phoenix client v2.9.0 adds playground repetitions, experiment recording, and a user-invokable skill menu for agents.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v2.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v2.9.0
```
- ›Adds a playground repetitions tool to the Phoenix client.
- ›Adds a playground experiment recording tool (pxi) for capturing experiment runs directly from the playground.
- ›Introduces a user-invokable skill menu for agents, enabling interactive skill selection during agent workflows.
arize-phoenix-v17.4.0 Jun 11, 2026 · issue -069

Phoenix v17.4.0 adds local slash commands in the chat menu, dataset evaluator management via pxi, and free-form duration search in the time range selector.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.4.0
```
- ›Adds select, read, and edit operations for dataset evaluators in the pxi CLI.
- ›Adds local slash commands to the agents chat menu for in-session actions.
- ›Adds search and free-form duration entry to the UI time range selector.
arize-phoenix-v17.3.0 Jun 10, 2026 · issue -070

Phoenix v17.3.0 adds subagents, playground run controls, claude-fable-5 support, and expanded PXI agent tooling.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.3.0
```
- ›Adds set_appended_messages_path PXI tool for configuring appended messages paths in the playground.
- ›Adds playground prompt instance tools via the pxi agent toolset, enabling agent-driven prompt management.
- ›Adds playground experiment recording tool for capturing experiment results from within the PXI agent.
- ›Adds dataset management tools for the PXI agent, enabling agent-driven dataset operations.
- ›Adds a template variables path tool in the playground for setting template variable sources.
+11 moreshow less
- ›Adds support for claude-fable-5 model in the playground.
- ›Introduces subagents support in the agents framework, enabling multi-agent orchestration.
- ›Adds a user-invokable skill menu in the agents UI for manually triggering agent skills.
- ›Adds evals for the trace-debug skill in the agents framework.
- ›Adds agent-driven validated evaluator submit in the PXI agent.
- ›Surfaces dataset-run experiment context within the PXI agent.
- ›Adds a playground repetitions tool for running multiple repetitions of a playground prompt.
- ›Adds a playground run cancellation tool to stop in-progress playground runs.
- ›Adds a 'copy trace ID' chat action in the chat UI.
- ›Introduces an inline, editable time range selector across the app UI.
- ›Auto-truncates large tools in the UI while preserving their position.
arize-phoenix-client-v2.8.0 Jun 9, 2026 · issue -071

Phoenix client 2.8.0 adds span annotation, code evaluators, sandboxing, and provider-native web search for agents.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v2.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v2.8.0
```
- ›Adds a span annotation tool for agents, enabling programmatic annotation of spans during agent execution.
- ›Adds sandboxing and code evaluator support, allowing safe execution of custom evaluation code.
- ›Adds a code-evaluator authoring interface in the PXI playground for building and editing code-based evaluators.
- ›Adds a playground model-switching tool in PXI, enabling dynamic model selection during prompt experimentation.
- ›Enables provider-native web search and fetch capabilities for agents when the underlying provider supports them.
+1 moreshow less
- ›Stamps tool execution environment onto tool-call provider metadata, making agent infrastructure context visible in traces.
arize-phoenix-v17.2.0 Jun 3, 2026 · issue -077

Arize Phoenix 17.2.0 adds a PXI route info tool.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.2.0
```
- ›Adds a PXI route info tool for surfacing routing information within the PXI interface.
arize-phoenix-v17.1.0 Jun 2, 2026 · issue -078

Phoenix 17.1.0 adds a load_dataset tool for the PXI agent and enables LLM-evaluator authoring directly in the PXI agent interface.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.1.0
```
- ›Adds load_dataset tool to the PXI agent in the Playground, enabling dataset loading directly from the agent interface.
- ›Enables LLM-evaluator authoring within the PXI agent, allowing practitioners to create and configure LLM-based evaluators without leaving the agent workflow.
- ›Adds skill loading display to surface skill status during PXI agent interactions.
- ›Adds warning colors and a search-off icon to the UI for clearer visual feedback.
arize-phoenix-v17.0.0 Jun 2, 2026 · issue -078

Phoenix v17.0.0 adds admin-managed system settings for assistant enablement and trace recording policy.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v17.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.0.0
```
- ›Adds server-side system settings for admin-managed assistant enablement and trace recording policy control.
└──▷ BREAKING ON UPGRADE
- !The addition of system settings with admin-managed assistant enablement and trace recording policy introduces breaking changes — see MIGRATION.md for upgrade steps.
arize-phoenix-v16.6.0 Jun 2, 2026 · issue -078

Phoenix v16.6.0 adds playground model switching, web search toggle in agent chat, and code-evaluator authoring.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v16.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v16.6.0
```
- ›Adds code-evaluator authoring in PXI, enabling practitioners to write and manage custom code-based evaluators directly in the UI.
- ›Adds a model switching tool to the PXI playground, allowing users to swap models mid-session without leaving the interface.
- ›Adds a web search globe toggle to the agent chat interface, letting users enable or disable live web search during agent conversations.
arize-phoenix-v16.5.0 Jun 1, 2026 · issue -079

Phoenix 16.5.0 adds playground prompt saving, PXI agent span annotation, and prompt read/write tools for agents.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v16.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v16.5.0
```
- ›Adds read_prompt_tools and write_prompt_tools capabilities to the PXI agent for programmatic prompt management.
- ›Adds annotate-spans skill to the PXI agent, enabling automated span annotation workflows.
- ›Adds summary argument to the PXI bash tool for UI preview of bash tool output.
- ›Adds save-prompt capability to the Playground UI, allowing prompts to be saved directly from the prompt editor.
- ›Adds rewind, fork, and copy controls for chat messages in the agent UI.
+1 moreshow less
- ›Seeds default sandbox configurations for local adapters.
arize-phoenix-v16.4.0 Jun 1, 2026 · issue -079

Phoenix v16.4.0 adds Claude Opus 4.8 support, a span annotation tool, trace debugging skill, and playground skill to the PXI agent.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v16.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v16.4.0
```
- ›Adds Claude Opus 4.8 as a supported model in the PXI agent interface.
- ›Adds a span annotation tool to the PXI agents capability, enabling annotation of spans directly from the agent.
- ›Adds a trace debugging skill to PXI agents for investigating traces from within the agent UI.
- ›Adds a playground skill to PXI agents, enabling prompt playground workflows from the agent interface.
- ›Makes span_kind filter comparisons case-insensitive when querying spans.
+7 moreshow less
- ›Surfaces PXI model credential setup, allowing users to configure model credentials within the PXI interface.
- ›Upgrades the PXI eval harness with message history support.
- ›Makes PXI quick actions dynamic per page context, adapting available actions based on the current view.
- ›Collapses agent context pills into a deck UI in the PXI agent panel.
- ›Adds no-data chart overlays to charts when data is absent.
- ›Adds draggable and resizable floating chat panel to the PXI agents UI.
- ›Lifts the trace UX feature flag, making the updated trace experience generally available.
arize-phoenix-v16.3.0 May 27, 2026 · issue -084

Phoenix v16.3.0 adds drag-to-zoom on metric charts, skills for the PXI agent, and an expanded model selector.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v16.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v16.3.0
```
- ›Adds drag-to-zoom interaction on project metric charts for faster time-range exploration.
- ›Adds skills capability to the PXI agent, expanding what the built-in AI agent can do.
- ›Expands the PXI settings model selector with additional model options.
arize-phoenix-v16.2.0 May 26, 2026 · issue -085

Phoenix AI assistant now accessible over modal overlays in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v16.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v16.2.0
```
- ›The agents assistant is now accessible while modal overlays are open, removing the need to dismiss modals to interact with it.
arize-phoenix-v16.1.0 May 26, 2026 · issue -085

Phoenix v16.1.0 adds a floating resizable PXI assistant panel, new eval-dataset agent skill, and a dashboards route.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v16.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v16.1.0
```
- ›Adds a new agent skill for creating eval datasets and new data objects from within the PXI assistant.
- ›Adds a floating assistant panel for the PXI assistant, detachable and resizable within the UI.
- ›Adds a dashboards route to the application navigation.
- ›Adds a hotkey tooltip to the PXI assistant for discoverability.
arize-phoenix-v16.0.0 May 21, 2026 · issue -090

Phoenix v16 adds sandboxed Code Evaluators and provider-native web search/fetch for agents.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v16.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v16.0.0
```
- ›Adds sandboxed Code Evaluators: write a Python or TypeScript evaluate() function directly in the Phoenix UI and Phoenix runs it server-side, recording labels and scores as annotations on every experiment run — no SDK, no local runtime, no deploy step required.
- ›Code Evaluators support composite scoring (blending LLM judgment with deterministic rules into a weighted metric), embedding-based evaluation (cosine similarity over embeddings), and LLM juries (polling multiple models into a weighted consensus verdict).
- ›Enables provider-native web search and fetch tools for agents when the underlying provider supports them.
└──▷ BREAKING ON UPGRADE
- !Sandboxing and Code Evaluators introduce a breaking change — see MIGRATION.md at https://github.com/Arize-ai/phoenix/blob/main/MIGRATION.md for upgrade steps.
arize-phoenix-v15.12.0 May 21, 2026 · issue -090

Phoenix v15.12.0 stamps tool execution environment on tool-call provider metadata and adds Enter-key submission for elicitation responses.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v15.12.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v15.12.0
```
- ›Stamps tool execution environment on tool-call provider metadata for agent spans, making runtime context visible in traces.
- ›Enables submitting elicitation responses with the Enter key in the UI, reducing friction during annotation workflows.
arize-phoenix-v15.11.0 May 19, 2026 · issue -092

Arize Phoenix v15.11.0 adds generative UI rendering inside agent chat sessions.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v15.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v15.11.0
```
- ›Adds generative UI rendering within agent chats, enabling dynamic visual components to be displayed inline during agent conversations.
arize-phoenix-v15.10.0 May 15, 2026 · issue -096

Phoenix v15.10.0 adds trace feedback on session turns, OTel GenAI semconv conversion, and agent session retention caps.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v15.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v15.10.0
```
- ›Converts OTel GenAI semantic convention attributes to OpenInference format automatically during trace ingestion.
- ›Adds a trace feedback toolbar to session turns, enabling annotation directly within multi-turn agent sessions.
- ›Introduces agent session retention capping to bound how many sessions are stored.
- ›Curates the agent model menu for a streamlined model selection experience in the agents UI.
arize-phoenix-client-v2.7.0 May 15, 2026 · issue -096

Phoenix client v2.7.0 adds agent session summaries, ATIF v1.7 trajectory upload, token counts in REST payloads, and TS trace annotations.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v2.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v2.7.0
```
└──▷ TRY IT
Retrieve a summary of a specific agent session to quickly assess what happened without reading the full trace.
```
$ curl -X GET 'https://<phoenix-host>/agents/<agent_id>/sessions/<session_id>/summary' -H 'Authorization: Bearer <token>'
```
- ›Adds GET /agents/{agent_id}/sessions/{session_id}/summary endpoint to retrieve summarized views of individual agent sessions.
- ›Includes token counts in span, trace, and session payloads returned by the REST API.
- ›Supports ATIF v1.7 trajectory upload via the client library.
- ›Adds TypeScript trace annotations to the phoenix-client, with clarified note semantics and a skills audit.
- ›Adds session-tagged identifiers to support open and axial coding workflows.
+3 moreshow less
- ›Supports vendor passthrough tools, enabling pass-through of provider-native tool definitions.
- ›Adds Playground manipulation tools with confirmation step for agent workflows.
- ›Types frontend REST calls against the OpenAPI schema for stronger client-side safety.
└──▷ BREAKING ON UPGRADE
- !The v1 /chat route and its associated code have been removed.
arize-phoenix-v15.9.0 May 14, 2026 · issue -097

Phoenix v15.9.0 backfills TOOL spans for external tool returns in the agent wrapper.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v15.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v15.9.0
```
- ›Backfills TOOL spans for external tool returns in the agent wrapper, improving trace completeness for agent workflows.
arize-phoenix-v15.8.0 May 13, 2026 · issue -098

Phoenix 15.8.0 adds session population for agent traces and thinking controls for Anthropic and Google in the playground.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v15.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v15.8.0
```
- ›Adds thinking controls for Anthropic and Google models in the playground UI.
- ›Populates project_sessions for /chat and /summary agent traces, enabling session-level grouping of agent interactions.
- ›Rebalances the pxi tool layout for improved workspace ergonomics.
arize-phoenix-v15.7.0 May 13, 2026 · issue -098

Phoenix v15.7.0 adds trace user feedback annotations and session-tagged identifiers for open/axial coding workflows.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v15.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v15.7.0
```
- ›Adds trace user feedback annotations, enabling practitioners to attach human feedback directly to individual traces.
- ›Adds session-tagged identifiers for open/axial coding workflows, supporting qualitative analysis patterns on session data.
- ›Makes session turn messages expandable in the UI for easier inspection of multi-turn conversation traces.
- ›Moves UI toast notifications to top-center with sonner-style stacking for improved visibility during active workflows.
└──▷ BREAKING ON UPGRADE
- !The v1 /chat route and its associated code have been removed.
arize-phoenix-v15.6.0 May 10, 2026 · issue -101

Phoenix v15.6.0 adds an agent session summary endpoint, playground manipulation tools, and per-user default provider/model preferences.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v15.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v15.6.0
```
└──▷ TRY IT
Fetch a summary of a specific agent session to quickly assess what happened without reviewing every span.
```
$ curl -X GET 'https://<phoenix-host>/agents/<agent_id>/sessions/<session_id>/summary' -H 'Authorization: Bearer <token>'
```
- ›Adds GET /agents/{agent_id}/sessions/{session_id}/summary endpoint to retrieve a summary for a specific agent session.
- ›Adds playground manipulation tools with confirmation support for agent workflows.
- ›Adds user preference for default provider and model in the Playground, persisted per user.
- ›Tracing view now always displays metrics alongside traces, replacing the legacy stats header.
arize-phoenix-v15.5.0 May 8, 2026 · issue -103

Phoenix 15.5.0 adds x-project-name HTTP header support for OTLP trace ingestion and wires agent tools into /chat-v2.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v15.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v15.5.0
```
└──▷ TRY IT
Route OTLP traces to a specific Phoenix project without changing the endpoint — useful in multi-project CI pipelines.
```
$ curl -X POST http://localhost:6006/v1/traces \
  -H 'Content-Type: application/x-protobuf' \
  -H 'x-project-name: my-agent-project' \
  --data-binary @traces.pb
```
- ›Supports x-project-name HTTP header for OTLP trace ingestion, allowing callers to route traces to a named project at the transport layer.
- ›Wires /chat-v2 with tool-calling support for agents, available behind an experimental toggle.
- ›Updates session details turns layout in the UI.
arize-phoenix-v15.4.0 May 5, 2026 · issue -106

Phoenix 15.4.0 adds filter-based DELETE annotation endpoints, token counts in REST payloads, and vendor passthrough tool support.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v15.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v15.4.0
```
- ›Adds filter-based DELETE endpoints for span, trace, and session annotations via the REST API, enabling bulk deletion without enumerating individual IDs.
- ›REST API span/trace/session payloads now include token counts, surfacing LLM usage data directly in API responses.
- ›Adds set_time_range tool for agents with hardened context injection, enabling time-scoped agent queries.
- ›Adds vendor passthrough tools support, allowing tool definitions to be forwarded as-is to underlying model providers.
- ›Adds ToolPart styles and subcomponents for richer agent tool rendering in the UI.
+1 moreshow less
- ›Simplifies trace/span status icons and introduces a status badge in panel views.
arize-phoenix-v15.2.0 May 3, 2026 · issue -108

Phoenix v15.2.0 adds TanStack AI tracing integration and enhanced filter conditions.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v15.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v15.2.0
```
- ›Adds TanStack AI tracing integration for tracing AI workloads built with TanStack.
- ›Enhances filter condition filtering in the UI for more precise trace and span queries.
- ›Moves PXI prompt assembly server-side and adds prompt caching for agents.
arize-phoenix-v15.1.0 Apr 30, 2026 · issue -111

Phoenix 15.1.0 adds named CLI auth profiles, session annotations, REST annotation filtering by identifier, and TypeScript trace annotations.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v15.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v15.1.0
```
- ›Adds named auth profile management to the phoenix CLI, enabling teams to store and switch between multiple authentication configurations.
- ›Adds session annotations and notes via the phoenix CLI for tagging and commenting on trace sessions from the command line.
- ›Enables querying annotations by identifier on REST GET endpoints, allowing more targeted annotation retrieval via the API.
- ›Adds TypeScript trace annotations to the phoenix-client library with clarified note semantics.
arize-phoenix-client-v2.6.0 Apr 29, 2026 · issue -112

Phoenix client v2.6.0 adds a session notes API endpoint, dataset upsert support, and extended prompt invocation parameter types.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v2.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v2.6.0
```
- ›Adds a session notes API endpoint (add session notes endpoint) for annotating sessions via the API.
- ›Introduces dataset upsert support, enabling create-or-update semantics when uploading datasets.
- ›Gates v15 dataset upload parameters by server version, ensuring compatibility across Phoenix server versions.
- ›Extends database prompt types to support additional invocation parameters.
└──▷ BREAKING ON UPGRADE
- !Dataset upsert changes the behavior of dataset uploads; existing workflows relying on the prior insert-only semantics may be affected on upgrade.
arize-phoenix-v15.0.0 Apr 29, 2026 · issue -112

Phoenix v15.0.0 adds dataset upsert support and extended DB prompt types for invocation parameters.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v15.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v15.0.0
```
- ›Adds dataset upsert capability, enabling insert-or-update semantics when pushing records to a dataset.
- ›Extends database prompt types to support invocation parameters, broadening the range of prompt configurations that can be stored.
arize-phoenix-v14.17.0 Apr 29, 2026 · issue -112

Phoenix v14.17.0 adds custom provider support for agents, a session notes API endpoint, and a JSON schema for settings config.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v14.17.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v14.17.0
```
- ›Adds a session notes API endpoint for programmatic annotation of sessions.
- ›Adds JSON schema for the settings config, enabling editor validation of Phoenix configuration files.
- ›Agents now support custom providers and secret store values for extended LLM integrations.
arize-phoenix-v14.16.0 Apr 28, 2026 · issue -113

Phoenix 14.16.0 adds page-context-aware agent chat, consolidated assistant config, and GraphQL field redaction.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v14.16.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v14.16.0
```
- ›Introduces RedactedString scalar to automatically redact sensitive fields returned by the GraphQL API.
- ›Agent assistant now advertises the current Phoenix page context to the chat, enabling context-aware responses.
- ›Moves advanced PXI toggles into the Assistant config panel, consolidating agent configuration in one place.
arize-phoenix-v14.15.0 Apr 26, 2026 · issue -115

Phoenix v14.15.0 adds a sessions UX flag with a Turns/Traces toggle for session views.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v14.15.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v14.15.0
```
- ›Adds sessions_ux flag with a Turns/Traces toggle to the sessions UI, letting users switch between turn-level and trace-level views of session data.
arize-phoenix-client-v2.5.0 Apr 25, 2026 · issue -116

Phoenix client v2.5.0 adds a trace note REST endpoint for the Phoenix CLI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v2.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v2.5.0
```
- ›Adds a trace note REST endpoint accessible via the Phoenix CLI, enabling programmatic annotation of traces.
arize-phoenix-v14.14.0 Apr 24, 2026 · issue -117

Phoenix CLI gains trace note support via the px command.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v14.14.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v14.14.0
```
- ›Adds trace note support to the px CLI command.
arize-phoenix-v14.13.0 Apr 24, 2026 · issue -117

Phoenix v14.13.0 adds trace note REST endpoint, span notes UI column, and re-exports OpenInference helpers from phoenix-otel.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v14.13.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v14.13.0
```
- ›Adds a trace note REST endpoint for the Phoenix CLI, enabling programmatic annotation of traces via the API.
- ›Re-exports OpenInference helpers, decorators, and semconv from phoenix-otel, so instrumentation code can import them from a single package.
- ›Adds a dedicated span notes column to the spans table in the UI, with cleaned-up annotation selection.
arize-phoenix-otel-v0.16.0 Apr 24, 2026 · issue -117

arize-phoenix-otel v0.16.0 re-exports OpenInference helpers, decorators, and semconv directly from the package.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-otel-v0.16.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-otel-v0.16.0
```
- ›Re-exports OpenInference helpers, decorators, and semantic conventions (semconv) from arize-phoenix-otel, so practitioners can import them directly without depending on a separate openinference package.
arize-phoenix-v14.12.0 Apr 24, 2026 · issue -117

Phoenix v14.12.0 adds trace annotations in the spans table, aggregated span info on traces, and page controls in the top nav.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v14.12.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v14.12.0
```
- ›Adds a trace annotations column to the spans table, surfacing annotation data without leaving the spans view.
- ›Aggregates span-level information on the traces view, giving a rolled-up summary of span data per trace.
- ›Moves page controls into the top navigation bar for faster access across the UI.
arize-phoenix-v14.11.0 Apr 22, 2026 · issue -119

Phoenix v14.11.0 adds session summary evals, a secrets settings page, and a root span name in session turn lists.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v14.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v14.11.0
```
- ›Adds a session summary eval and sidebar-title prompt rewrite capability for agent sessions.
- ›Adds a Secrets settings page for managing secrets directly in the Phoenix UI.
- ›Shows root span name in the session turn list for easier agent session navigation.
- ›Adds a 'Show Table Aside' toggle to the project filter configuration (feature-flagged).
arize-phoenix-client-v2.4.0 Apr 22, 2026 · issue -119

Phoenix client passes trace_id to experiment evaluators and adds type-aware attribute filtering to GET /v1/spans.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v2.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v2.4.0
```
- ›Adds type-aware attribute filter to GET /v1/spans REST endpoint, enabling more precise span queries that match on attribute type as well as value.
- ›Passes trace_id through to experiment evaluators in the client, making trace correlation available inside evaluator logic.
arize-phoenix-v14.10.0 Apr 21, 2026 · issue -120

Arize Phoenix v14.10.0 adds token count display for agent chat sessions.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v14.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v14.10.0
```
- ›Displays token count for agent chat sessions in the UI.
arize-phoenix-v14.9.0 Apr 20, 2026 · issue -121

Phoenix 14.9.0 adds type-aware span filtering to GET /v1/spans, Claude Opus 4.7 in Playground, and consent/trace-sharing controls.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v14.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v14.9.0
```
- ›Adds type-aware attribute filter to GET /v1/spans REST API endpoint, enabling precise span queries by attribute type.
- ›Exposes agentsConfig via GraphQL and surfaces it on the settings page.
- ›Adds consent and trace-sharing controls via PXI consent settings.
- ›Adds Claude Opus 4.7 as a model option in the Playground.
- ›Splits out span note support in the CLI.
+2 moreshow less
- ›Introduces a resizable Drawer component in the UI with Modal simplification.
- ›Adds an empty-state screen for PXI chat in the agent UI.
arize-phoenix-v14.8.0 Apr 16, 2026 · issue -125

Arize Phoenix v14.8.0 adds Azure managed identity authentication for PostgreSQL connections.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v14.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v14.8.0
```
- ›Adds Azure managed identity authentication support for PostgreSQL database connections.
arize-phoenix-v14.7.0 Apr 16, 2026 · issue -125

Phoenix 14.7.0 adds session pagination, a trace annotation dataloader, and auto-refreshing projects page.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v14.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v14.7.0
```
- ›Adds a trace annotation dataloader for more efficient bulk loading of trace annotations.
- ›Adds session pagination support for navigating large sets of sessions.
- ›The projects page now auto-refreshes on mount and every 60 seconds, keeping project status current without manual reloads.
arize-phoenix-v14.6.0 Apr 15, 2026 · issue -126

Phoenix 14.6.0 adds an eval harness for the agent system and a list-detail layout for session turns.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v14.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v14.6.0
```
- ›Adds an eval harness to the PXI agent system prompt for structured evaluation workflows.
- ›Introduces a list-detail layout for session turns in the app UI, improving navigation of multi-turn conversations.
arize-phoenix-v14.5.0 Apr 14, 2026 · issue -127

Phoenix 14.5.0 adds span/trace annotation CLI commands, chat metadata on assistant messages, and agent feedback actions.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v14.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v14.5.0
```
- ›Adds span and trace annotation commands to the Phoenix CLI.
- ›Attaches chat metadata to assistant messages in the agent interface.
- ›Adds feedback actions to assistant messages in the agent interface.
- ›Enables toggling the assistant agent on or off from Settings.
arize-phoenix-v14.4.0 Apr 14, 2026 · issue -127

Phoenix v14.4.0 adds a capability menu and capability registry for the PXI frontend agent tooling.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v14.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v14.4.0
```
- ›Adds a capability menu and refactors PXI frontend tool wiring around a capability registry for the agent interface.
arize-phoenix-v14.3.0 Apr 14, 2026 · issue -127

Phoenix v14.3.0 adds an assistant agent settings page and re-exports openinference-core from phoenix-otel.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v14.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v14.3.0
```
- ›Re-exports openinference-core directly from phoenix-otel, reducing the need for a separate import.
- ›Adds an assistant agent settings page in the UI for configuring agent behavior.
arize-phoenix-v14.2.0 Apr 10, 2026 · issue -131

Phoenix v14.2.0 adds name-based project URL routing via /redirects/projects/:project_name.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v14.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v14.2.0
```
└──▷ TRY IT
Navigate directly to a project by name instead of looking up its internal ID — useful for bookmarks, dashboards, or sharing links with teammates.
```
$ curl -L http://localhost:6006/redirects/projects/my-llm-project
```
- ›Adds /redirects/projects/:project_name endpoint for resolving projects by name rather than by internal ID, enabling stable, human-readable project URLs.
arize-phoenix-v14.0.0 Apr 7, 2026 · issue -134

Phoenix v14 adds PostgreSQL read replicas, ephemeral experiments with ExperimentSweeper, a subcommand-first CLI, and Strands Agents integration.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v14.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v14.0.0
```
└──▷ TRY IT
Start the Phoenix server in dev mode using the new subcommand-first CLI syntax.
```
$ phoenix serve --dev
```
- ›Restructures CLI into a subcommand-first architecture: flags now follow the subcommand (e.g. phoenix serve --dev, phoenix db ...) instead of preceding it.
- ›Adds PostgreSQL read replica routing support for load-distributing query traffic.
- ›Introduces ephemeral experiments and the ExperimentSweeper daemon for automated experiment lifecycle management.
- ›Adds a background experiment runner to execute experiment jobs asynchronously.
- ›Adds experiment record toggle with ephemeral tracking in the Playground UI.
+12 moreshow less
- ›Adds a structured error table with sanitized messages in the experiments view.
- ›Includes span and experiment run data in error subscription payloads.
- ›Polls the experiments table automatically while jobs are running.
- ›Adds Strands Agents integration with onboarding snippet.
- ›Adds new provider integrations and environment variable support to the onboarding flow.
- ›Adds ask_user elicitation tool with a carousel UI to the agent panel.
- ›Adds a backend MCP docs tool via Mintlify integration to the agent.
- ›Traces Phoenix agent chat requests both locally and remotely.
- ›Adds @defer support to Relay and ProjectPageHeader for progressive UI loading.
- ›Requires explicit first argument for forward pagination in the GraphQL API.
- ›Uses non-streaming mode for LLM evaluator calls.
- ›Uses raw vendor response as output.value for non-streaming Playground sessions.
└──▷ BREAKING ON UPGRADE
- !The /v1/evaluations REST endpoint and its supporting plumbing have been removed.
- !The legacy experiments module has been removed and evals 1.0 is deprecated.
- !CLI flags must now follow the subcommand: phoenix serve --dev instead of phoenix --dev serve.
- !The legacy client has been removed.
arize-phoenix-client-v2.3.0 Apr 3, 2026 · issue -138

Phoenix client 2.3.0 adds a utility to convert ATIF data into trace trajectories.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v2.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v2.3.0
```
- ›Adds an ATIF-to-trace-trajectory conversion utility for transforming ATIF data into trace trajectories.
arize-phoenix-v13.23.0 Apr 2, 2026 · issue -139

Arize Phoenix v13.23.0 bundles TypeScript SDK docs directly into npm packages.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.23.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.23.0
```
- ›Bundles TypeScript SDK documentation into npm packages for offline/local access.
arize-phoenix-client-v2.2.0 Apr 1, 2026 · issue -140

Phoenix client v2.2.0 adds get_traces, a GET /v1/user endpoint, secrets management REST API, and Python 3.14 support.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v2.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v2.2.0
```
└──▷ TRY IT
Look up the currently authenticated user via the new REST endpoint.
```
$ curl -X GET https://<phoenix-host>/v1/user \
  -H 'Authorization: Bearer <api-key>'
```
- ›Adds get_traces method to both the Python and TypeScript Phoenix clients for programmatic trace retrieval.
- ›Adds GET /v1/user REST endpoint to retrieve user information via the phoenix-rest-api.
- ›Adds a REST endpoint for secrets management on the Phoenix server.
- ›Adds Python 3.14 support (excluding Windows).
arize-phoenix-evals-v2.13.0 Apr 1, 2026 · issue -140

Arize Phoenix Evals 2.13.0 adds Python 3.14 support (except Windows).
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v2.13.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v2.13.0
```
- ›Supports Python 3.14 on Linux and macOS (Windows excluded).
arize-phoenix-v13.22.0 Apr 1, 2026 · issue -140

Phoenix v13.22.0 refreshes the UI with updated provider and integration icons plus a new agent skill logo icon.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.22.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.22.0
```
- ›Updates provider and integration icons and adds a new agent skill logo icon in the UI.
arize-phoenix-v13.21.0 Apr 1, 2026 · issue -140

Phoenix v13.21.0 adds Python 3.14 support, a secrets-management REST endpoint, and improved agent session summaries.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.21.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.21.0
```
- ›New REST endpoint for secrets management on the Phoenix server.
- ›Adds Python 3.14 support (excluding Windows).
- ›Improves agent session summaries.
arize-phoenix-v13.20.0 Mar 30, 2026 · issue -142

Phoenix 13.20.0 adds REST endpoints to delete prompts and prompt version tags, plus a new copy field in the settings UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.20.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.20.0
```
└──▷ TRY IT
Remove a tag (e.g. 'production') from a prompt version to unpin it from that lifecycle stage.
```
$ curl -X DELETE https://<phoenix-host>/prompt_versions/<version-id>/tags/production
```
Delete a prompt and all its versions when retiring an unused prompt from the registry.
```
$ curl -X DELETE https://<phoenix-host>/prompts/<prompt_identifier>
```
- ›New DELETE /prompt_versions/{id}/tags/{tag_name} REST endpoint to remove a specific tag from a prompt version.
- ›New DELETE /prompts/{prompt_identifier} REST endpoint to delete a prompt entirely.
- ›New CopyField component in the settings UI for one-click copying of configuration values.
arize-phoenix-v13.19.0 Mar 26, 2026 · issue -146

Phoenix v13.19.0 adds a PromptInput compound component, collapsible agent tool calls, session management controls, and an improved project creation flow.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.19.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.19.0
```
- ›Adds PromptInput compound component for building AI interaction UIs.
- ›Agent chat now collapses tool calls into an expandable pool with streaming performance improvements.
- ›Agent sessions gain a switcher with delete controls and async summary generation.
- ›Project creation flow updated with a color picker and description field.
arize-phoenix-evals-v2.12.0 Mar 24, 2026 · issue -148

Phoenix Evals v2.12.0 adds support for structured data as eval inputs.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v2.12.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v2.12.0
```
- ›Accepts structured data (not just plain text) as inputs to evaluators, enabling richer eval pipelines.
arize-phoenix-v13.18.0 Mar 24, 2026 · issue -148

Phoenix 13.18.0 adds a prompt version diff view and replaces markdown rendering with streamdown.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.18.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.18.0
```
- ›Adds a prompt version diff view in the UI, enabling side-by-side comparison of prompt versions.
- ›Replaces all markdown rendering with the streamdown renderer across the application.
arize-phoenix-v13.17.0 Mar 23, 2026 · issue -149

Phoenix v13.17.0 adds an experimental GQL simulated bash tool for agents and one-click span ID copying in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.17.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.17.0
```
- ›Adds experimental px-gql simulated bash tool for agent workflows.
- ›Adds one-click copy of span IDs to clipboard in the trace UI.
arize-phoenix-v13.16.0 Mar 22, 2026 · issue -150

Phoenix v13.16.0 adds a spans CLI command, GET /v1/user endpoint, expectedRunCount experiment field, and Bedrock/Mastra tracing onboarding.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.16.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.16.0
```
└──▷ TRY IT
Retrieve the current authenticated user's information from the Phoenix REST API.
```
$ curl -s -H 'Authorization: Bearer <token>' https://<phoenix-host>/v1/user
```
- ›Adds spans subcommand to the Phoenix CLI for fetching and filtering spans.
- ›Adds GET /v1/user REST endpoint for retrieving user information.
- ›Adds expectedRunCount field to experiments and a completion-fraction display in the experiments table.
- ›Adds configurable package manager preference per language for code snippet generation.
- ›Adds tracing onboarding integration snippets for TypeScript (LangChain, OpenAI, Anthropic, Mastra) and Python, plus AWS Bedrock integration with language tab icons.
+7 moreshow less
- ›Expands the tracing onboarding integration list with a search filter.
- ›Adds copy-to-clipboard for session, span, and trace ID cells in the UI.
- ›Adds copy name/ID action menu to navigation breadcrumbs.
- ›Adds collapse top-level keys toggle for dataset upload in the UI.
- ›Adds canonical hub-and-spoke tool choice and response format controls to the Playground.
- ›Adds trace-level and annotation APIs to the evals skill.
- ›Adds browser bash tool execution capability to the agent.
arize-phoenix-client-v2.1.0 Mar 18, 2026 · issue -154

Phoenix client v2.1.0 adds span filter parameters to the getSpans method.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v2.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v2.1.0
```
- ›Adds span filter params to getSpans, enabling callers to narrow span queries server-side.
arize-phoenix-v13.15.0 Mar 13, 2026 · issue -158

Phoenix 13.15.0 adds phoenix db migrate, a traces REST endpoint, and new span filters.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.15.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.15.0
```
└──▷ TRY IT
Run database migrations independently of the Phoenix server, useful in CI or containerised deploy pipelines.
```
$ phoenix db migrate
```
- ›Adds phoenix db migrate subcommand for running database migrations standalone, decoupled from server startup.
- ›Adds GET /v1/projects/{project_identifier}/traces REST endpoint for retrieving traces per project.
- ›Adds name, span_kind, and status_code filter parameters to the REST spans API.
arize-phoenix-client-v2.0.0 Mar 11, 2026 · issue -160

Phoenix client v2.0.0 adds session conversation APIs, trace_ids filtering, parent_id filtering, and six new first-class LLM providers.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v2.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v2.0.0
```
└──▷ USE IT
Retrieve only the spans belonging to a specific set of traces — useful when you already know the trace IDs from a CI run or incident and want to pull just those spans for analysis.
python
```
spans = client.spans.get_spans(trace_ids=["abc123", "def456"])
```
Fetch only the child spans of a known parent span to inspect a specific sub-tree of a trace without loading the entire trace.
python
```
spans = client.spans.get_spans(parent_id="span-789")
```
- ›Adds trace_ids parameter to client.spans getSpans methods to filter spans by one or more trace IDs.
- ›Adds parent_id filter propagation to both the Python and JavaScript/TypeScript client.spans interfaces.
- ›Adds session conversation API to both the Python and TypeScript clients via client session methods.
- ›Adds DELETE session API on the server side for removing sessions programmatically.
- ›Adds Cerebras, Fireworks, Groq, and Moonshot as first-class providers in the playground.
+1 moreshow less
- ›Adds Perplexity and Together AI as built-in providers in the playground.
└──▷ BREAKING ON UPGRADE
- !client.annotations has been removed; replace all usages with client.spans.
arize-phoenix-v13.14.0 Mar 11, 2026 · issue -160

Phoenix v13.14.0 adds a session conversation API to Python and TypeScript clients and a new tracing onboarding layout.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.14.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.14.0
```
- ›Adds session conversation API to both the Python and TypeScript Phoenix clients.
- ›New tracing onboarding page layout to guide users through trace setup.
arize-phoenix-v13.13.0 Mar 10, 2026 · issue -161

Phoenix 13.13.0 adds provider filtering env vars, a DELETE session API, and dataset column drag-and-drop
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.13.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.13.0
```
└──▷ TRY IT
Restrict the playground and UI to only show specific model providers, e.g. to enforce org-approved vendors.
```
$ export PHOENIX_ALLOWED_PROVIDERS=openai,anthropic
```
Hide one or more model providers from the UI without a strict allowlist, e.g. to suppress internal or deprecated providers.
```
$ export PHOENIX_HIDDEN_PROVIDERS=azure,cohere
```
- ›Adds PHOENIX_ALLOWED_PROVIDERS environment variable to restrict which model providers appear in the UI.
- ›Adds PHOENIX_HIDDEN_PROVIDERS environment variable to hide specific model providers from the UI.
- ›Adds a DELETE session API endpoint on the server.
- ›Splits the side-nav API reference into separate REST API and GraphQL sections in the UI.
- ›Adds drag-and-drop column reordering for datasets in the UI.
└──▷ BREAKING ON UPGRADE
- !The client.annotations module has been removed from the Python client (was previously deprecated).
arize-phoenix-v13.12.0 Mar 9, 2026 · issue -162

Adds parent_id filter to GET spans endpoints for targeted span tree queries.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.12.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.12.0
```
└──▷ TRY IT
Retrieve only the child spans of a specific parent span to investigate a single trace subtree.
```
$ GET /v1/spans?parent_id=<span_id>
```
- ›Adds parent_id filter to GET spans endpoints, enabling queries scoped to child spans of a specific parent span.
- ›Adds a feature-flagged tracing onboarding empty state to guide new users through tracing setup.
- ›Adds PackageManagerCommandBlock UI component for displaying package manager commands.
arize-phoenix-v13.11.0 Mar 8, 2026 · issue -163

Phoenix playground gains Perplexity AI and Together AI as built-in providers with cost tracking included.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.11.0
```
- ›Adds Perplexity AI as a built-in playground provider, configured via the PERPLEXITY_API_KEY environment variable and https://api.perplexity.ai base URL, including Perplexity's Sonar search-augmented model family with 9 model cost-manifest entries.
- ›Adds Together AI as a built-in playground provider, configured via the TOGETHER_API_KEY environment variable and https://api.together.xyz/v1 base URL, with 26 model cost-manifest entries covering models including moonshotai/Kimi-K2.5, deepseek-ai/DeepSeek-V3.1, deepseek-ai/DeepSeek-R1, Qwen/Qwen3-235B-A22B-Thinking-2507, openai/gpt-oss-120b, openai/gpt-oss-20b, zai-org/GLM-5, and zai-org/GLM-4.5-Air-FP8.
arize-phoenix-v13.10.0 Mar 8, 2026 · issue -163

Phoenix adds Cerebras, Fireworks AI, Groq, and Moonshot as first-class playground providers with automatic cost tracking.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.10.0
```
- ›Adds CEREBRAS_API_KEY, FIREWORKS_API_KEY, GROQ_API_KEY, and MOONSHOT_API_KEY environment variables to enable Cerebras, Fireworks AI, Groq, and Moonshot (Kimi) as first-class providers in the playground — all use OpenAI-compatible APIs with no new dependencies.
- ›Adds automatic token cost tracking for all four new providers via 298 new model pricing entries.
- ›Adds a patchProject GraphQL mutation enabling edits to a project's description and gradient colors from the Project Settings tab.
- ›Expands the playground model list with latest OpenAI reasoning models including the gpt-5.4 family, gpt-5.3-chat-latest, gpt-5.2-pro variants, gpt-5 date-stamped and pro variants, and o3-pro-2025-06-10.
- ›Replaces the loading spinner during playground experiments with a pulsing red recording icon and elapsed timer to clearly signal an in-progress experiment.
arize-phoenix-v13.9.0 Mar 7, 2026 · issue -164

Phoenix 13.9.0 adds a trace_id filter to GET spans REST endpoints and filetype-agnostic dataset uploads.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.9.0
```
└──▷ TRY IT
Retrieve all spans belonging to a specific trace by filtering directly in the REST API call.
```
$ curl -X GET 'https://<phoenix-host>/v1/spans?trace_id=<trace_id>' \
  -H 'Authorization: Bearer <api-key>'
```
- ›Adds trace_id filter parameter to GET spans REST endpoints, enabling callers to retrieve spans scoped to a specific trace.
- ›New filetype-agnostic dataset upload in the UI allows uploading dataset files regardless of file extension.
- ›Adds a record icon to the UI.
arize-phoenix-client-v1.31.0 Mar 6, 2026 · issue -165

Arize Phoenix client v1.31.0 adds session retrieval methods and a list_sessions alias with timeout support to the Python SDK.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.31.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.31.0
```
- ›Adds list_sessions alias and timeout parameter to the sessions API in the Python client SDK.
- ›Adds session retrieval methods to the Python client SDK, enabling programmatic lookup of tracing sessions.
arize-phoenix-v13.8.0 Mar 4, 2026 · issue -167

Phoenix 13.8.0 adds brute-force login protection, Vercel AI SDK streaming support, and live playground evaluation metrics.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.8.0
```
- ›Adds brute-force login protection to the authentication layer, limiting repeated failed login attempts.
- ›Supports the Pydantic Vercel data stream protocol for agent tracing, enabling observability over Vercel AI SDK streaming responses.
- ›Playground evaluation metrics now update incrementally as results arrive, rather than waiting for full completion.
- ›Adds integration icons for Claude and LangGraph in the UI.
- ›Introduces a file dropzone component in the UI for file uploads.
arize-phoenix-v13.7.0 Mar 2, 2026 · issue -169

Arize Phoenix 13.7.0 updates the container image base to Debian 13.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.7.0
```
- ›Updates the official container image base to Debian 13.
arize-phoenix-otel-v0.15.0 Mar 2, 2026 · issue -169

arize-phoenix-otel now supports Python 3.10 through 3.14
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-otel-v0.15.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-otel-v0.15.0
```
- ›Extends arize-phoenix-otel compatibility to Python 3.10, 3.11, 3.12, 3.13, and 3.14.
arize-phoenix-client-v1.30.0 Mar 2, 2026 · issue -169

Phoenix client v1.30.0 adds GET endpoints for the sessions REST API.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.30.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.30.0
```
- ›Adds GET endpoints for the sessions REST API, enabling programmatic retrieval of session data.
arize-phoenix-v13.6.0 Mar 2, 2026 · issue -169

Phoenix v13.6.0 adds inline document annotation for retriever spans and CLI sessions commands for multi-turn conversations.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.6.0
```
- ›Adds sessions and session subcommands to the CLI for multi-turn conversation support.
- ›Adds inline document annotation UI for retriever spans in the app.
arize-phoenix-v13.5.0 Feb 27, 2026 · issue -171

Phoenix v13.5.0 adds configurable password policy and GET endpoints for the sessions REST API.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.5.0
```
- ›Adds GET endpoints to the sessions REST API, enabling programmatic retrieval of session data.
- ›Adds configurable password policy support for tighter authentication control.
arize-phoenix-evals-v2.11.0 Feb 27, 2026 · issue -171

Phoenix Evals v2.11.0 adds conciseness and refusal evaluators plus a utility to convert Phoenix prompts to eval templates.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v2.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v2.11.0
```
- ›Adds a conciseness classification evaluator to assess whether LLM responses are appropriately brief.
- ›Adds a refusal evaluator to detect when an LLM declines to answer a query.
- ›Adds a utility to convert Phoenix prompts into evals templates, enabling reuse of existing prompt assets in evaluation pipelines.
arize-phoenix-v13.4.0 Feb 26, 2026 · issue -172

Phoenix 13.4.0 adds a refusal evaluator, a GraphQL CLI command, PHOENIX_MIGRATE_INDEX_CONCURRENTLY flag, and SQL stdout visibility.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.4.0
```
└──▷ TRY IT
Run a rolling DB migration without locking tables — set before starting Phoenix in a multi-replica deployment.
```
$ export PHOENIX_MIGRATE_INDEX_CONCURRENTLY=true
```
Query the Phoenix GraphQL API from the CLI without opening a browser or constructing a raw curl request.
```
$ px api graphql
```
- ›Adds PHOENIX_MIGRATE_INDEX_CONCURRENTLY environment variable to enable concurrent index migrations for rolling deployments without downtime.
- ›Adds px api graphql subcommand to the Phoenix CLI for issuing GraphQL queries directly from the command line.
- ›Adds ability to print SQL to stdout for observability into database query activity.
- ›Adds a refusal evaluator to the evals module for detecting LLM refusal responses.
- ›Adds navigation counters in the UI for projects, datasets, evaluators, and prompts to surface item counts at a glance.
+2 moreshow less
- ›Upgrades the AI SDK dependency to v6.
- ›Adds integration icons to the UI.
arize-phoenix-v13.3.0 Feb 20, 2026 · issue -178

Phoenix 13.3.0 adds a conciseness classification evaluator and removes the model inferences/embeddings UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.3.0
```
- ›Adds a conciseness classification evaluator to the evals library for scoring response brevity.
- ›Removes model inferences, dimensions, embeddings, and point-cloud UI surfaces from the Phoenix interface.
└──▷ BREAKING ON UPGRADE
- !The model inferences, dimensions, embeddings, and point-cloud UI has been removed — any workflows that relied on those screens will no longer find them in the interface.
arize-phoenix-v13.2.0 Feb 19, 2026 · issue -179

Arize Phoenix 13.2.0 adds AWS Bedrock cross-region inference model prefix preference.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.2.0
```
- ›Adds AWS Bedrock cross-region inference model prefix preference, enabling selection of cross-region routing when calling Bedrock models.
arize-phoenix-v13.1.0 Feb 18, 2026 · issue -180

Phoenix 13.1.0 adds session skills, dynamic markdown chat rendering, model display in evaluator details, and column resizing in evaluator tables.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.1.0
```
- ›Merges the phoenix-sdk-python skill into phoenix-evals, consolidating skill capabilities into the evals package.
- ›Adds session skills support via the new skills system, enabling skill-based session workflows.
- ›Adds model information display to evaluator details in the UI.
- ›Adds column resizing support to EvaluatorsTable and DatasetEvaluatorsTable for improved data exploration.
- ›Renders session chat using dynamic markdown content, enabling richer chat display in the session view.
+1 moreshow less
- ›Updates the CLI starter kit to use clack for an improved interactive CLI experience.
arize-phoenix-evals-v2.10.0 Feb 13, 2026 · issue -185

Phoenix Evals 2.10.0 adds dataset evaluators, a tool-response evaluator template, label filtering for classifiers, and full Mustache prompt support.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v2.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v2.10.0
```
- ›Adds dataset evaluators, enabling evaluation runs directly against datasets.
- ›Adds a tool response handling evaluator template for assessing LLM tool-call outputs.
- ›Adds label-based filtering for built-in classification evaluators, letting practitioners scope results to specific labels.
- ›Enables full Mustache prompt templates on the server side for more expressive eval prompt authoring.
arize-phoenix-client-v1.29.0 Feb 13, 2026 · issue -185

Arize Phoenix client v1.29.0 adds dataset evaluators for running evaluations over datasets.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.29.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.29.0
```
- ›Adds dataset evaluators, enabling evaluation runs to be applied across datasets in the Phoenix client.
arize-phoenix-v13.0.0 Feb 13, 2026 · issue -185

Phoenix v13 ships dataset evaluators, built-in LLM eval configs in GraphQL, OpenAI Responses API support, and async Bedrock client.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v13.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v13.0.0
```
- ›Adds built-in LLM evaluator configs to the GraphQL API, exposing pre-built evaluator templates directly via the graph.
- ›Adds support for OpenAI API type selection between Chat Completions and Responses API in the playground.
- ›Converts the Bedrock client from boto3 to aioboto3 for fully async operation, unlocking non-blocking LLM calls.
- ›Adds a session ID index for spans across SQLite and Postgres backends, improving span query performance at scale.
- ›Introduces dataset evaluators — a new first-class object that attaches evaluators directly to datasets.
+16 moreshow less
- ›Adds pre-built LLM evaluators (built-ins) to the evaluator creation menu, with input mapping, output config display, config overrides, and a dedicated built-in evaluator table.
- ›Adds a tool response handling evaluator template for evaluating LLM tool call outputs.
- ›Adds a JSON parse toggle to the JSON distance built-in evaluator.
- ›Adds custom LLM provider support: create, edit, delete custom providers from the model menu, with secrets management.
- ›Adds model search to the model menu for faster provider/model selection.
- ›Adds an evaluator preview mutation to the GraphQL API for testing evaluators before saving.
- ›Adds an explanation toggle to the evaluator form to control whether evaluations include reasoning.
- ›Adds an append messages parameter in the playground for controlling message chaining.
- ›Adds available tools display to experiment output so tool-calling behavior is visible alongside results.
- ›Adds a dataset deep link after dataset selection from the playground.
- ›Adds an examples route with an examples table for browsing dataset examples directly.
- ›Enables creating dataset examples in a chain (sequential example creation flow).
- ›Deserializes JSON in message function/tool call arguments via dataset_helpers.
- ›Adds user ID tracking on evaluators for attribution.
- ›Adds eval outputs panel to the playground for inline evaluation results.
- ›Adds autocomplete to the LLM eval prompt editor.
arize-phoenix-v12.35.0 Feb 9, 2026 · issue -189

Arize Phoenix 12.35.0 adds Claude Opus 4.6 to the playground.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.35.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.35.0
```
- ›Adds Claude Opus 4.6 model as a selectable option in the Phoenix playground.
arize-phoenix-v12.34.0 Feb 6, 2026 · issue -192

Arize Phoenix 12.34.0 adds a tool_selection evaluator to the evals library.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.34.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.34.0
```
- ›Adds tool_selection evaluator to the evals library for assessing whether an LLM chose the correct tool during a tool-use span.
arize-phoenix-evals-v2.9.0 Feb 3, 2026 · issue -195

Phoenix Evals 2.9.0 adds FaithfulnessEvaluator, tool invocation accuracy metric, tool_selection evaluator, and neutral optimization direction.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v2.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v2.9.0
```
└──▷ USE IT
Evaluate whether an LLM response is faithful to the retrieved context, replacing the deprecated HallucinationEvaluator.
python
```
from phoenix.evals import FaithfulnessEvaluator

evaluator = FaithfulnessEvaluator(model=model)
results = evaluator.evaluate(input=query, response=answer, context=retrieved_docs)
```
- ›Adds FaithfulnessEvaluator class to replace HallucinationEvaluator for grounded response evaluation.
- ›Adds tool_selection evaluator to assess whether an agent selected the correct tool.
- ›Adds tool invocation accuracy metric for measuring correctness of tool calls made by agents.
- ›Adds neutral optimization direction option for Scores, enabling evaluation metrics where neither higher nor lower values are inherently better.
- ›Returns trace_id in Scores objects, enabling direct correlation of evaluation results to traces.
arize-phoenix-v12.33.0 Jan 28, 2026 · issue -201

Arize Phoenix 12.33.0 adds EMAIL_ATTRIBUTE_PATH for configurable email extraction in OAuth2 flows.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.33.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.33.0
```
└──▷ TRY IT
Map a non-standard email claim path from your IdP's token payload so Phoenix can identify users during OAuth2 login.
```
$ EMAIL_ATTRIBUTE_PATH=user.contact.email
```
- ›Adds EMAIL_ATTRIBUTE_PATH environment variable to OAuth2 configuration, enabling customizable extraction of the email field from identity provider token responses.
arize-phoenix-v12.32.0 Jan 27, 2026 · issue -202

Arize Phoenix v12.32.0 adds a tool invocation accuracy metric for evaluating agent tool-calling behavior.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.32.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.32.0
```
- ›Adds a tool invocation accuracy metric to measure how accurately agents invoke tools.
arize-phoenix-client-v1.28.0 Jan 21, 2026 · issue -208

Phoenix client 1.28.0 adds FaithfulnessEvaluator and a span_id_key for linking dataset examples to traces.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.28.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.28.0
```
- ›Adds span_id_key parameter to link dataset examples to traces.
- ›Adds FaithfulnessEvaluator class for faithfulness evaluation of LLM outputs.
arize-phoenix-v12.31.0 Jan 21, 2026 · issue -208

Phoenix v12.31.0 adds a CLI, FaithfulnessEvaluator, span-to-trace linking, and dataset/experiment CLI commands.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.31.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.31.0
```
└──▷ USE IT
Score LLM responses for faithfulness directly from the Phoenix evaluator library instead of the deprecated HallucinationEvaluator.
python
```
from phoenix.evals import FaithfulnessEvaluator

evaluator = FaithfulnessEvaluator(model=model)
results = evaluator.evaluate(dataframe=df)
```
- ›Adds span_id_key parameter to link dataset examples to traces, enabling traceability between datasets and recorded spans.
- ›Introduces a phoenix CLI with dataset and experiment subcommands for managing datasets and experiments from the command line.
- ›Adds FaithfulnessEvaluator, a new built-in LLM classification evaluator for assessing response faithfulness.
arize-phoenix-v12.30.0 Jan 15, 2026 · issue -214

Phoenix v12.30.0 adds enhanced JSON attribute display with new UI components for span inspection.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.30.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.30.0
```
- ›Adds AttributesJSONBlock component for enhanced JSON attribute display in the span detail view.
- ›Adds text block and JSON block icons for expanding attribute strings in the UI.
arize-phoenix-v12.29.0 Jan 12, 2026 · issue -217

Phoenix v12.29.0 adds a correctness evaluator, span event attributes in the UI, and connection timeout error handling.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.29.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.29.0
```
- ›Adds a correctness evaluator for assessing LLM output accuracy in evaluation workflows.
- ›Displays span event attributes in the Phoenix UI, making trace event data visible during span inspection.
- ›Adds connection timeout error handling to improve resilience when the Phoenix server is unreachable.
arize-phoenix-evals-v2.8.0 Jan 8, 2026 · issue -221

Phoenix Evals 2.8.0 adds a correctness evaluator, tool-selection correctness metric, and sync/async LLM client kwargs support.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v2.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v2.8.0
```
└──▷ USE IT
Pass transport-level options to sync and async LLM clients separately when constructing an evaluator LLM.
python
```
from phoenix.evals import OpenAIModel

model = OpenAIModel(
    model="gpt-4o",
    sync_client_kwargs={"timeout": 30},
    async_client_kwargs={"timeout": 60},
)
```
- ›Adds sync_client_kwargs and async_client_kwargs support to the LLM constructor, enabling per-client configuration for synchronous and asynchronous calls.
- ›Adds a built-in tool selection correctness metric to evaluate whether an LLM agent chose the right tool.
- ›Adds a new correctness evaluator for assessing the accuracy of LLM outputs.
arize-phoenix-v12.28.0 Jan 6, 2026 · issue -223

Phoenix v12.28.0 adds JSONL dataset uploads and a built-in tool selection correctness eval metric.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.28.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.28.0
```
- ›Adds support for JSONL format in dataset uploads.
- ›Adds a built-in tool selection correctness metric to the evals framework.
- ›Adds a skeleton loader for paragraphs in the playground UI while content loads.
arize-phoenix-v12.27.0 Dec 26, 2025 · issue -234

Phoenix v12.27.0 adds theme selection, language preference persistence, API key generation in onboarding, and trace links in experiment tables.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.27.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.27.0
```
- ›Adds 'Generate API Key' buttons directly to project onboarding modals, reducing setup friction for new projects.
- ›Adds a theme selector to viewer preferences, allowing users to switch UI themes.
- ›Persists a user's programming language preferences across sessions.
- ›Promotes trace links into the experiment table for direct navigation from experiment runs to traces.
- ›Moves the dataset selector into the input/experiment sections of the playground for a more consistent layout.
+1 moreshow less
- ›Adds usage analytics to the platform.
arize-phoenix-v12.26.0 Dec 22, 2025 · issue -238

Phoenix v12.26.0 moves 'Add Dataset Example' into the Examples tab for a more streamlined dataset workflow.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.26.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.26.0
```
- ›Moves the 'Add Dataset Example' action into the Examples tab, consolidating dataset example management within a single UI location.
arize-phoenix-v12.25.0 Dec 12, 2025 · issue -248

Phoenix v12.25.0 adds Gemini tool call support, lazy-loaded embeddings, and a null sentinel for LDAP email config.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.25.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.25.0
```
- ›Supports setting PHOENIX_LDAP_ATTR_EMAIL to null as a sentinel value to control LDAP email attribute mapping.
- ›Supports Gemini tool calls in tracing and observability workflows.
- ›Lazy-loads embeddings and dimension features, reducing startup overhead for large datasets.
arize-phoenix-client-v1.27.0 Dec 11, 2025 · issue -249

Phoenix client v1.27.0 adds span annotation notes via Python client and REST endpoint, plus LDAP authentication support.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.27.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.27.0
```
- ›Adds a span notes REST endpoint, enabling programmatic creation and retrieval of notes attached to individual spans.
- ›Adds a span note function to the Python client library for annotating spans with freeform notes.
- ›Adds Lightweight Directory Access Protocol (LDAP) support for authentication.
arize-phoenix-v12.23.0 Dec 10, 2025 · issue -250

Arize Phoenix 12.23.0 makes email optional for LDAP authentication.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.23.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.23.0
```
- ›Makes email optional when configuring LDAP authentication, allowing LDAP users without a mapped email attribute to authenticate successfully.
arize-phoenix-v12.22.0 Dec 9, 2025 · issue -251

Arize Phoenix v12.22.0 adds a span note function to the Python client.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.22.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.22.0
```
- ›Adds a span note function to the Python client, enabling programmatic annotation of spans.
arize-phoenix-v12.21.0 Dec 9, 2025 · issue -251

Phoenix v12.21.0 adds a span notes endpoint for annotating trace spans via API.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.21.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.21.0
```
- ›Adds a span notes endpoint, enabling programmatic creation and retrieval of notes on trace spans.
arize-phoenix-v12.20.0 Dec 6, 2025 · issue -254

Phoenix v12.20.0 adds LDAP authentication support and existing secret reuse for credential management.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.20.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.20.0
```
- ›Adds Lightweight Directory Access Protocol (LDAP) authentication support for enterprise directory-based login.
- ›Adds existing secret support, enabling credential reuse from pre-existing secrets rather than requiring new secret creation.
arize-phoenix-evals-v2.7.0 Dec 4, 2025 · issue -256

Arize Phoenix Evals 2.7.0 adds support for prompt/template messages in evaluations.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v2.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v2.7.0
```
- ›Supports prompt/template messages in evals, enabling structured message-based inputs to evaluation pipelines.
arize-phoenix-v12.19.0 Dec 1, 2025 · issue -259

Phoenix v12.19.0 adds split-based filtering to the experiments table UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.19.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.19.0
```
- ›Adds splits view to the experiments table, enabling comparison of experiment results broken down by splits.
arize-phoenix-v12.18.0 Nov 25, 2025 · issue -265

Phoenix v12.18.0 adds Claude Opus 4-5 support, dataset split assignment on upload, and server credential visibility in the Playground.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.18.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.18.0
```
- ›Supports split assignment directly from dataset upload, letting users label train/test/validation splits at ingest time.
- ›Adds support for Claude Opus 4-5 as a model option.
- ›Shows server credential setup inside the Playground API keys panel, surfacing pre-configured credentials alongside user-entered keys.
arize-phoenix-client-v1.26.0 Nov 25, 2025 · issue -265

Phoenix client v1.26.0 lets you assign dataset splits directly at upload time.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.26.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.26.0
```
- ›Supports split assignment when uploading a dataset, enabling train/test/validation partitioning in a single step.
arize-phoenix-client-v1.25.0 Nov 24, 2025 · issue -266

Phoenix client v1.25.0 adds evaluation helpers for pulling RAG spans.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.25.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.25.0
```
- ›Adds evaluation helper utilities to simplify pulling RAG spans for downstream evaluation workflows.
arize-phoenix-v12.17.0 Nov 24, 2025 · issue -266

Phoenix 12.17.0 enables playground repetitions for manual invocations and relicenses the client to Apache 2.0.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.17.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.17.0
```
- ›Enables repetitions for manual playground invocations, allowing users to run the same prompt multiple times in a single session.
- ›Switches the Phoenix client license to Apache 2.0.
- ›Improves the UX of the retention policy form.
arize-phoenix-v12.16.0 Nov 19, 2025 · issue -271

Phoenix v12.16.0 adds OpenAI 5.1 model support, reasoning for OpenAI and Gemini, and connection pagination on trace spans.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.16.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.16.0
```
- ›Implements connection pagination on trace spans, enabling traversal of large trace datasets.
- ›Adds support for the OpenAI 5.1 model family.
- ›Adds reasoning support for OpenAI and Gemini models, and adds gemini-3 to the supported model list.
└──▷ BREAKING ON UPGRADE
- !Python 3.9 is no longer supported; upgrade to Python 3.10 or later before upgrading Phoenix.
arize-phoenix-v12.15.0 Nov 14, 2025 · issue -276

Phoenix v12.15.0 updates the Anthropic model list with latest models.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.15.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.15.0
```
- ›Updates the supported Anthropic model list to include the latest available models.
arize-phoenix-evals-v2.6.0 Nov 12, 2025 · issue -278

Phoenix Evals 2.6.0 adds Anthropic and Google GenAI adapters, GPT-5 on Azure, and invocation params for ClassificationEvaluators.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v2.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v2.6.0
```
- ›Adds support for invocation params in ClassificationEvaluators, enabling per-evaluation model parameter control.
- ›Adds Anthropic and Google GenAI adapters for use with Phoenix evals.
- ›Adds GPT-5 support to Azure OpenAI model integrations.
arize-phoenix-client-v1.23.0 Nov 12, 2025 · issue -278

Arize Phoenix client v1.23.0 adds retry support for experiments.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.23.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.23.0
```
- ›Adds retry support for experiments, allowing failed experiment runs to be automatically retried.
arize-phoenix-v12.12.0 Nov 7, 2025 · issue -283

Phoenix v12.12.0 adds page titles derived from navigation context.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.12.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.12.0
```
- ›Page titles are now derived from navigation context, improving browser tab and history usability.
arize-phoenix-v12.11.0 Nov 7, 2025 · issue -283

Arize Phoenix v12.11.0 adds a user display timezone preference to the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.11.0
```
- ›Adds a user display timezone preference so practitioners can view timestamps in their local timezone.
arize-phoenix-client-v1.22.0 Nov 5, 2025 · issue -285

Arize Phoenix client v1.22.0 adds example binding to evaluators, prompt metadata, dataset split querying, and experiment resumption.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.22.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.22.0
```
- ›Adds ability to query dataset examples by splits, enabling filtered retrieval of training/test/validation subsets.
- ›Adds metadata support for prompts, allowing structured metadata to be attached to prompt objects.
- ›Enables binding examples directly to evaluators for more tightly coupled evaluation workflows.
- ›Adds resume capability for experiments and evaluations, allowing interrupted runs to continue from where they left off.
arize-phoenix-v12.10.0 Nov 5, 2025 · issue -285

Phoenix 12.10.0 adds OIDC role mapping, experiment resume, prompt metadata, extra body params, and Prometheus metrics for trace retention.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.10.0
```
└──▷ USE IT
Reference a Kubernetes secret for the Phoenix auth secret without embedding the value directly in Helm values.
yaml
```
auth:
  secret:
    valueFrom:
      secretKeyRef:
        name: phoenix-auth-secret
        key: secret-key
```
Inject custom environment variables into the Phoenix deployment via Helm for things like custom LLM provider keys.
yaml
```
additionalEnv:
  - name: OPENAI_API_KEY
    valueFrom:
      secretKeyRef:
        name: openai-secret
        key: api-key
```
- ›Adds valueFrom option to auth.secret in Helm config for referencing Kubernetes secrets by reference rather than inline value.
- ›Adds additionalEnv support to Helm chart for injecting arbitrary environment variables into the Phoenix deployment.
- ›Adds fullnameOverride support to Helm chart for controlling the full resource name prefix.
- ›Adds extra body param support for API playground requests.
- ›Adds OIDC role mapping to automatically assign Phoenix roles based on claims from an OIDC provider.
+5 moreshow less
- ›Adds Prometheus metrics for the trace retention sweeper, enabling observability into trace cleanup operations.
- ›Adds metadata support for prompts, allowing structured key-value data to be attached to prompt versions.
- ›Adds ability to resume interrupted experiments and evaluations from where they left off.
- ›Adds system theme option to the UI, following the OS-level light/dark preference.
- ›Restricts prominent write actions in the UI for users with the viewer role.
arize-phoenix-v12.9.0 Oct 29, 2025 · issue -292

Phoenix 12.9.0 adds AWS IAM auth for database configuration and metadata display for experiment run annotations.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.9.0
```
- ›Enables AWS IAM authentication for database configuration.
- ›Displays metadata for experiment run annotations in the UI.
- ›Merges dataset label application with new label creation into a unified workflow.
- ›Moves reference output to the bottom pane of the experiment compare slideover.
arize-phoenix-v12.8.0 Oct 27, 2025 · issue -294

Phoenix 12.8.0 adds a split edit menu for dataset examples, dataset label GraphQL mutations, and real-time split name validation.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.8.0
```
- ›Adds GraphQL dataset label set operation, enabling programmatic labeling of datasets via the GraphQL API.
- ›Adds a split edit menu to single dataset examples in the UI, enabling per-example split management.
- ›Adds real-time validation of split names while typing in the UI.
- ›Settings pages now preload GraphQL queries during navigation for faster load times.
arize-phoenix-v12.7.0 Oct 24, 2025 · issue -297

Phoenix 12.7.0 adds dataset splits support across experiments and datasets, plus label filtering for datasets and prompts.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.7.0
```
- ›Enables label filtering on the datasets table, allowing practitioners to narrow the dataset list by label in the UI.
- ›Enables label filtering on the prompts page, so prompt versions can be browsed by label.
- ›Supports querying dataset examples by splits, surfacing split-aware data in the playground and experiment workflows.
- ›Makes the Experiment Compare page split-aware, so experiment runs can be compared across dataset splits.
- ›Adds ExperimentRuns scoped over dataset splits, enabling per-split evaluation tracking.
+6 moreshow less
- ›Adds annotation values and sorting to the experiment compare slideover for richer side-by-side review.
- ›Adds annotation filtering in the experiment compare slideover to focus on specific evaluator results.
- ›Supports individual dataset label editing directly from the dataset page.
- ›Removes the dataset-label feature flag, making label management generally available.
- ›Removes the splits feature flag and simplifies the split menu selection, making dataset splits generally available.
- ›Updates the playground dataset examples table slideover with an improved UI.
arize-phoenix-v12.5.0 Oct 10, 2025 · issue -311

Phoenix v12.5.0 adds a viewer role, dataset split selection, example table filtering, and annotation sorting in sessions.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.5.0
```
- ›Adds a viewer role for read-only access control in Phoenix.
- ›Enables selection of dataset splits alongside datasets in the UI.
- ›Adds filtering to the examples table and a split management filter menu.
- ›Enables sorting on annotations in the sessions table.
- ›Adds editable labels on datasets.
+2 moreshow less
- ›Adds trace links to the experiment compare slideover.
- ›Shows missing experiment runs in the experiment compare slideover.
arize-phoenix-v12.4.0 Oct 8, 2025 · issue -313

Phoenix 12.4.0 adds PKCE support for OAuth 2.0 OIDC authentication flows.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.4.0
```
- ›Adds PKCE (Proof Key for Code Exchange) support for OAuth 2.0 OIDC authentication, hardening authorization code flows against interception attacks.
arize-phoenix-evals-v2.5.0 Oct 7, 2025 · issue -314

Phoenix Evals 2.5.0 adds a regex evaluator and broader LLM provider support.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v2.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v2.5.0
```
- ›Adds a regex evaluator for pattern-based output validation without requiring an LLM judge.
- ›Supports more LLM providers through the LLM integration layer.
- ›Improves binding ergonomics for constructing evaluator inputs.
arize-phoenix-v12.3.0 Oct 6, 2025 · issue -315

Phoenix 12.3.0 adds dataset label management in the UI with a new settings tab and a label column in the datasets table.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.3.0
```
- ›Adds a dataset label tab in the Settings page for managing dataset labels.
- ›Adds a label column to the datasets table for at-a-glance label visibility.
- ›Updates the experiment comparison slideover UI and adds pagination to the experiment comparison slideover on the list page.
arize-phoenix-v12.2.0 Oct 3, 2025 · issue -317

Phoenix 12.2.0 adds root_path to launch_app, prompt version editing and tag loading in playground, and dataset label bulk management.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.2.0
```
└──▷ USE IT
Serve Phoenix behind a reverse proxy or subpath by setting a root path at launch time.
python
```
import phoenix as px
px.launch_app(root_path="/phoenix")
```
- ›Adds root_path parameter to launch_app to control the URL prefix when serving Phoenix behind a reverse proxy or subpath.
- ›Enables bulk add/remove of labels on dataset examples via the UI.
- ›Adds dataset label color validation to enforce valid label colors.
- ›Supports editing prompt versions directly in the playground.
- ›Supports loading a prompt into the playground by tag.
arize-phoenix-evals-v2.4.0 Oct 2, 2025 · issue -318

Arize Phoenix Evals 2.4.0 adds coroutine (async) function support to create_evaluator.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v2.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v2.4.0
```
└──▷ USE IT
Wrap an async LLM-calling function as a Phoenix evaluator to run evaluations concurrently.
python
```
import asyncio
import phoenix.evals as evals

async def my_async_eval_fn(input):
    # async call to an LLM or scoring service
    return {"score": 1.0, "label": "correct"}

evaluator = evals.create_evaluator(my_async_eval_fn)
```
- ›Adds coroutine (async) function support to phoenix.evals.create_evaluator, enabling async callables to be used directly as custom evaluators.
arize-phoenix-evals-v2.3.0 Oct 1, 2025 · issue -319

Phoenix Evals v2.3.0 adds dot-delimited f-string key support in eval Templates.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v2.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v2.3.0
```
- ›Allows dot-delimited f-string keys in eval Templates, enabling nested attribute references inside template strings.
arize-phoenix-v12.1.0 Sep 30, 2025 · issue -320

Arize Phoenix v12.1.0 adds dataset label GraphQL mutations, Claude Sonnet 4.5 support, and a Helm chart migration.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.1.0
```
- ›Adds dataset label GraphQL operations (create, delete, read) for managing labels on datasets via the API.
- ›Supports Claude Sonnet 4.5 as a model option in the playground.
- ›Migrates the Helm chart from the Bitnami chart to the groundhog2k chart.
arize-phoenix-client-v1.21.0 Sep 29, 2025 · issue -321

Arize Phoenix client v1.21.0 adds methods for annotating traces and sessions programmatically.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.21.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.21.0
```
- ›Adds client methods for adding annotations to traces and sessions, enabling programmatic labeling of LLM trace data and session-level feedback.
arize-phoenix-v12.0.0 Sep 29, 2025 · issue -321

Phoenix v12 adds session/trace annotation APIs, dataset splits, experiment repetitions view, and Google GenAI SDK support.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v12.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v12.0.0
```
- ›Adds client methods for adding trace and session annotations via the Phoenix client library.
- ›Adds GraphQL mutations and a database table for session annotations, surfacing annotation columns in the sessions table UI.
- ›Adds user_id column to the datasets and dataset_versions tables, enabling per-user dataset attribution.
- ›Introduces dataset splits: backend support, 'Add Split' dialog UI, and split labels displayed in the examples table.
- ›Snapshots examples into a junction table when an experiment is inserted, preserving the exact dataset state used.
+5 moreshow less
- ›Adds experiment tags on experiments and datasets.
- ›Adds a 'viewer' role row to the database, expanding role-based access control.
- ›Experiment repetitions are now shown as a column in the experiments table UI.
- ›Upgrades the Playground to use the Google GenAI SDK.
- ›Enforces a minimum client version requirement, ensuring server/client compatibility.
└──▷ BREAKING ON UPGRADE
- !Version 12 is a major release with breaking changes (see PR #9695); existing databases require migration before upgrading.
arize-phoenix-evals-v2.2.0 Sep 27, 2025 · issue -323

Phoenix Evals 2.2.0 adds a document relevance evaluator and a utility to convert eval DataFrames into Phoenix annotations.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v2.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v2.2.0
```
- ›Adds a document relevance evaluator to assess whether retrieved documents are relevant to a query.
- ›Adds a utility to format dataframe evaluation results as annotations suitable for logging back to Phoenix.
arize-phoenix-client-v1.20.0 Sep 26, 2025 · issue -324

Arize Phoenix client v1.20.0 adds support for repetitions in experiments.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.20.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.20.0
```
- ›Adds repetitions support for experiment runs.
arize-phoenix-v11.38.0 Sep 26, 2025 · issue -324

Arize Phoenix v11.38.0 adds repetitions support to the playground for multi-run prompt testing.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.38.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.38.0
```
- ›Adds repetitions to the playground, enabling multiple runs of the same prompt configuration in a single session.
arize-phoenix-v11.37.0 Sep 24, 2025 · issue -326

Phoenix playground gains custom HTTP header support for LLM proxy and gateway scenarios.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.37.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.37.0
```
- ›Adds custom HTTP headers for playground requests, enabling auth tokens and routing headers to be sent when calling LLM endpoints through proxies or gateways.
- ›Adds a new checkbox UI control (details unspecified in release notes).
arize-phoenix-evals-v2.1.0 Sep 24, 2025 · issue -326

arize-phoenix-evals 2.1.0 adds Azure provider support for LLM-based evaluations.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v2.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v2.1.0
```
- ›Adds Azure provider support, enabling evals to run against Azure-hosted LLM endpoints.
arize-phoenix-v11.36.0 Sep 23, 2025 · issue -327

Phoenix v11.36.0 adds per-repetition breakdown in the experiments compare slideover.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.36.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.36.0
```
- ›Breaks out individual repetitions in the experiments compare slideover, making it easier to inspect variance across repeated experiment runs.
- ›Ports notifications to react-aria toasts for improved accessibility in the Phoenix UI.
arize-phoenix-v11.35.0 Sep 22, 2025 · issue -328

Arize Phoenix Helm chart gains IPv6 support and configurable image registry.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.35.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.35.0
```
- ›Adds IPv6 support to the Helm chart deployment.
- ›Allows image registry configuration in the Helm chart.
arize-phoenix-client-v1.19.0 Sep 18, 2025 · issue -332

Arize Phoenix client v1.19.0 adds Experiments↔Evals 2.0 compatibility.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.19.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.19.0
```
- ›Adds Experiments↔Evals 2.0 compatibility, enabling experiments to work with the Evals 2.0 evaluation format.
arize-phoenix-evals-v2.0.0 Sep 17, 2025 · issue -333

Arize Phoenix Evals 2.0 graduates from preview, adding async dataframe evaluation, rate limiting, and Experiments compatibility.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v2.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v2.0.0
```
- ›Adds an async version of evaluate_dataframe for non-blocking LLM-based evaluations.
- ›Adds rate limiting to LLM methods to avoid exceeding provider API limits.
- ›Adds Experiments ↔ Evals 2.0 compatibility, enabling experiment workflows to use the stable Evals 2.0 API.
- ›Promotes Evals 2.0 out of preview into the stable, production-ready release.
└──▷ BREAKING ON UPGRADE
- !Evals 2.0 is moved out of preview and is now the stable API; any code depending on preview-only behavior or the previous 0.x API surface may require updates.
arize-phoenix-v11.34.0 Sep 16, 2025 · issue -334

Phoenix v11.34.0 adds an experiment compare details slideover in the list view and caps span queue capacity.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.34.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.34.0
```
- ›Adds an experiment compare details slideover to the experiments list view, letting practitioners inspect side-by-side experiment results without leaving the list.
- ›Puts a capacity limit on the internal span queue to bound memory usage under high ingestion load.
arize-phoenix-v11.33.0 Sep 15, 2025 · issue -335

Phoenix v11.33.0 adds prompt labels, an experiment compare list page, repetitions carousel, and annotation popovers in experiment details.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.33.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.33.0
```
- ›Adds prompt labels to prompt versions, now visible in prompt details view.
- ›Releases a new experiment compare list page for side-by-side experiment comparison.
- ›Adds a repetitions carousel on the experiment compare grid page to browse repeated runs.
- ›Adds an annotation popover on the experiment details view for inline annotation inspection.
- ›Enables paging on the experiment compare details view to navigate large result sets.
arize-phoenix-v11.32.0 Sep 4, 2025 · issue -346

Phoenix 11.32.0 paginates experiment runs and improves the experiment list UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.32.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.32.0
```
- ›Paginates experiment runs inside run_experiment to support large experiment datasets without memory pressure.
- ›Improves the experiments list page UI with frontend enhancements for browsing experiments.
arize-phoenix-client-v1.18.0 Sep 4, 2025 · issue -346

Phoenix client v1.18.0 adds pagination to run_experiment when fetching experiment runs.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.18.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.18.0
```
- ›Adds pagination support to run_experiment when retrieving experiment runs, enabling use with large experiment datasets.
arize-phoenix-client-v1.17.0 Sep 3, 2025 · issue -347

Arize Phoenix client v1.17.0 adds methods to log document annotations.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.17.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.17.0
```
- ›Adds new methods to the Phoenix client for logging document annotations.
arize-phoenix-v11.31.0 Sep 3, 2025 · issue -347

Phoenix v11.31.0 adds methods to log document annotations for retrieval tracing.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.31.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.31.0
```
- ›Adds new methods to log document annotations, enabling practitioners to attach structured annotations to retrieved documents within traces.
arize-phoenix-client-v1.16.0 Aug 30, 2025 · issue -351

Phoenix client gains sorted span retrieval and new OpenAI tool type support in v1.16.0
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.16.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.16.0
```
- ›Adds sort-by-newest/oldest ordering to get_spans_dataframe, enabling time-ordered span analysis without manual post-processing.
- ›Supports new OpenAI tool types in span handling, extending coverage for the latest OpenAI API tool definitions.
- ›Re-exports client types for improved developer experience when importing from the phoenix.Client package.
arize-phoenix-v11.30.0 Aug 28, 2025 · issue -353

Phoenix 11.30.0 adds a span document annotations API and missing-percentage visibility for experiment evaluations.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.30.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.30.0
```
- ›Adds a span document annotations API endpoint for annotating documents associated with spans.
- ›Experiments UI now shows the missing percentage for experiment evaluations, making gaps in eval coverage visible at a glance.
arize-phoenix-v11.29.0 Aug 27, 2025 · issue -354

Phoenix v11.29.0 improves the experiments compare list page styling.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.29.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.29.0
```
- ›Improves styling of the experiments compare list page UI.
arize-phoenix-v11.28.0 Aug 26, 2025 · issue -355

Phoenix v11.28.0 adds a new experiment list page to the frontend UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.28.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.28.0
```
- ›Adds an experiment list page to the frontend UI for browsing and managing experiments.
arize-phoenix-evals-v0.29.0 Aug 26, 2025 · issue -355

Phoenix Evals 0.29.0 adds evaluate_dataframe function and evals 2.0 tracing support.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.29.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.29.0
```
└──▷ USE IT
Run LLM evaluations over a pandas DataFrame of traces or records in a single call.
python
```
from phoenix.evals import evaluate_dataframe

results = evaluate_dataframe(df, evaluators=[my_evaluator])
```
- ›Adds evaluate_dataframe function for running evaluations directly against a pandas DataFrame.
- ›Adds evals 2.0 tracing to instrument and observe evaluation runs.
arize-phoenix-v11.27.0 Aug 25, 2025 · issue -356

Arize Phoenix v11.27.0 adds support for extra volumes and volume mounts in the Helm chart.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.27.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.27.0
```
- ›Adds support for extra volumes and volume mounts in the Helm chart, enabling custom storage configurations for Phoenix deployments.
arize-phoenix-v11.26.0 Aug 22, 2025 · issue -359

Arize Phoenix 11.26.0 adds a timeline view for tracing.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.26.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.26.0
```
- ›Adds a timeline view for inspecting traces in the tracing UI.
arize-phoenix-v11.25.0 Aug 22, 2025 · issue -359

Phoenix v11.25.0 adds get_spans_dataframe time-ordering, experiment quick filters, and Helm in-memory SQLite support.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.25.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.25.0
```
- ›get_spans_dataframe now sorts results by newest/oldest spans, enabling time-ordered span retrieval from the API.
- ›Adds eval and annotation quick filters to the experiments UI for faster result exploration.
- ›Helm chart now special-cases sqlite:///:memory: so in-memory SQLite deployments are handled correctly.
- ›Experiment compare list page now hydrates data for richer side-by-side comparisons.
- ›Disk usage notification emails now CC a support email address.
arize-phoenix-evals-v0.28.0 Aug 19, 2025 · issue -362

Arize Phoenix Evals v0.28.0 adds dynamic concurrency control for LLM evaluations.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.28.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.28.0
```
- ›Adds dynamic concurrency to LLM evaluation runs, allowing throughput to adjust automatically during execution.
└──▷ BREAKING ON UPGRADE
- !Batch evaluation methods have been removed from the evals library.
arize-phoenix-v11.24.0 Aug 15, 2025 · issue -363

Phoenix v11.24.0 enhances the experiment compare page for side-by-side experiment analysis.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.24.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.24.0
```
- ›Enhances the experiment compare page UI for improved side-by-side experiment comparison.
arize-phoenix-v11.23.0 Aug 14, 2025 · issue -363

Arize Phoenix v11.23.0 adds the ability to transfer traces between projects.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.23.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.23.0
```
- ›Adds trace transfer between projects, enabling traces to be moved from one project to another.
arize-phoenix-evals-v0.27.0 Aug 13, 2025 · issue -363

Phoenix Evals v0.27.0 adds precision/recall/F-score metrics and new evaluator and score abstractions.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.27.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.27.0
```
- ›New evaluator and score abstractions provide a structured foundation for building and composing custom evaluators.
- ›Adds precision, recall, and F-score metrics for evaluating LLM output quality.
arize-phoenix-v11.22.0 Aug 12, 2025 · issue -363

Phoenix v11.22.0 adds Geist Mono font for value display in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.22.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.22.0
```
- ›Introduces the Geist Mono typeface for rendering values in the Phoenix UI, improving readability of trace and span data.
arize-phoenix-client-v1.15.0 Aug 7, 2025 · issue -363

Phoenix client gains span deletion, re-exported experiment utilities, and GPT-5 playground support.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.15.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.15.0
```
└──▷ USE IT
Delete a specific span by ID to clean up unwanted trace data programmatically.
python
```
import phoenix as px

client = px.Client()
client.delete_span(span_id="<span_id>")
```
- ›Adds delete_span method to the Python phoenix-client for programmatic span removal.
- ›Re-exports experiment utilities at the top-level client module, so they are importable directly from phoenix without deep sub-module paths.
- ›Adds GPT-5 support in the playground.
arize-phoenix-v11.21.0 Aug 7, 2025 · issue -363

Phoenix Playground now supports GPT-5 for prompt testing and evaluation.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.21.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.21.0
```
- ›Adds GPT-5 as a supported model in the Playground for prompt experimentation and evaluation.
arize-phoenix-v11.19.0 Aug 5, 2025 · issue -363

Phoenix v11.19.0 adds Anthropic Claude 4.1 support, span subtree deletion, and Helm-configurable data retention policies.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.19.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.19.0
```
- ›Adds Helm-configurable default data retention policy for Phoenix deployments.
- ›Supports Anthropic Claude 4.1 models in the playground and evaluations.
- ›Deleting a span now also deletes its entire span subtree.
- ›Experiment comparison view now shows example counts across experiments.
arize-phoenix-v11.18.0 Aug 1, 2025 · issue -363

Phoenix v11.18.0 adds experiment compare metrics, improved evals templating, and a trace delete route by relay ID.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.18.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.18.0
```
- ›Adds trace delete route by relay ID, enabling targeted trace removal via relay ID lookup.
- ›Wires up metrics on the experiment compare metrics page, making cross-experiment metric comparisons visible in the UI.
- ›Improves evals templating for more flexible evaluation prompt construction.
arize-phoenix-evals-v0.26.0 Aug 1, 2025 · issue -363

Phoenix Evals 0.26.0 adds token usage returns from llm_classify, object generation method control, and improved templating.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.26.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.26.0
```
- ›llm_classify now returns token usage data alongside classification results, enabling cost and quota tracking per eval run.
- ›Adds support for specifying the object generation method, giving callers control over how structured outputs are produced by the LLM.
- ›Improved evals templating for more flexible prompt construction.
arize-phoenix-v11.17.0 Jul 30, 2025 · issue -364

Arize Phoenix v11.17.0 adds an environment variable to configure the default data retention policy.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.17.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.17.0
```
- ›Adds an environment variable setting to configure the default retention policy, enabling ops teams to control data lifecycle at startup without manual UI intervention.
arize-phoenix-evals-v0.25.0 Jul 30, 2025 · issue -364

Arize Phoenix Evals 0.25.0 adds a new classification generation primitive.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.25.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.25.0
```
- ›Adds a new classification generation primitive to support structured classification workflows in LLM evals.
arize-phoenix-v11.16.0 Jul 30, 2025 · issue -364

Phoenix v11.16.0 adds span deletion, Google GenAI SDK eval support, and OIDC env vars for Helm.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.16.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.16.0
```
- ›Adds a delete route for spans via the new DELETE /span endpoint.
- ›Adds OIDC environment variable support to the Helm chart, enabling OIDC configuration through env vars.
- ›Adds support for the google-genai SDK in the evals framework, expanding LLM provider coverage.
- ›Adds case-insensitive substring search for sessions in the UI.
arize-phoenix-evals-v0.24.0 Jul 30, 2025 · issue -364

Phoenix Evals v0.24.0 adds google-genai SDK support and a new LLM wrapper prototype.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.24.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.24.0
```
- ›Adds support for the google-genai SDK as a model backend for running evals.
- ›Introduces an LLM wrapper prototype to simplify integrating custom LLM clients into the evals framework.
arize-phoenix-v11.15.0 Jul 29, 2025 · issue -364

Phoenix v11.15.0 adds external resource configuration via environment variable.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.15.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.15.0
```
- ›Supports configuring external resources via an environment variable.
arize-phoenix-v11.14.0 Jul 29, 2025 · issue -364

Phoenix v11.14.0 adds a list method for datasets to the Python client and a collapsible nav UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.14.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.14.0
```
└──▷ USE IT
Enumerate all datasets in a Phoenix project without opening the UI.
python
```
import phoenix as px

client = px.Client()
datasets = client.list_datasets()
```
- ›Adds list method for datasets to the Python client, enabling programmatic enumeration of datasets.
- ›Adds collapsible navigation panel to the UI for improved workspace management.
arize-phoenix-client-v1.14.0 Jul 29, 2025 · issue -364

Arize Phoenix Python client gains a list method for datasets in v1.14.0.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.14.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.14.0
```
- ›Adds a list method to the Python client for enumerating datasets.
arize-phoenix-v11.13.0 Jul 25, 2025 · issue -364

Phoenix 11.13.0 adds experiment filtering by name/description and releases project metrics.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.13.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.13.0
```
- ›Releases project metrics dashboard, surfacing per-project observability metrics.
- ›Adds backend filtering of experiments by name and description.
arize-phoenix-v11.12.0 Jul 25, 2025 · issue -364

Phoenix v11.12.0 adds storage alerts, experiment compare averages, and synced metric chart tooltips.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.12.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.12.0
```
- ›Adds a banner alert in the UI when storage is insufficient, giving operators early warning before data loss.
- ›Displays average experiment run data in the headers of the experiment compare table, making cross-run comparisons faster to interpret.
- ›Syncs tooltips across metrics charts so hovering over one chart highlights the same timestamp on all visible charts simultaneously.
arize-phoenix-v11.11.0 Jul 24, 2025 · issue -364

Phoenix v11.11.0 adds top-N bar charts, prompts page search, and a floating toolbar to the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.11.0
```
- ›Adds basic 'tops' bar charts for visualizing top-N metrics distributions in the UI.
- ›Adds a search bar to the prompts page for filtering prompts.
- ›Adds a floating toolbar to the UI for quicker access to common actions.
- ›Adds consistent time-range formatting based on binning across metrics charts.
arize-phoenix-v11.10.0 Jul 22, 2025 · issue -364

Phoenix v11.10.0 adds LLM and tool span count metrics and displays allocated DB storage capacity in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.10.0
```
- ›Adds LLM and tool span count metrics to the metrics surface.
- ›Displays allocated database storage capacity in the UI when a storage limit is specified.
arize-phoenix-v11.9.0 Jul 21, 2025 · issue -364

Phoenix v11.9.0 adds a trace errors chart, createProject GraphQL mutation, project metrics dashboards, and a trace project transfer API.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.9.0
```
- ›Adds createProject GraphQL mutation for programmatically creating projects.
- ›Implements a trace project transfer API, enabling traces to be moved between projects.
- ›Adds a trace errors chart and generic bar chart component to the UI for visualizing error trends.
- ›Wires up resolvers for a project metrics dashboard page, surfacing per-project performance metrics.
arize-phoenix-v11.8.0 Jul 17, 2025 · issue -364

Arize Phoenix 11.8.0 adds a support-email env var for error messages and TimeBinConfig for span/trace count time series.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.8.0
```
- ›Adds an environment variable to embed a support email address in Phoenix error messages, making operator-customized error UX possible.
- ›Adds TimeBinConfig for span and trace count time series, enabling configurable time-bin granularity in usage charts.
arize-phoenix-evals-v0.23.0 Jul 16, 2025 · issue -364

Phoenix Evals 0.23.0 adds the ability to skip variable parsing in prompt templates.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.23.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.23.0
```
- ›Adds support for skipping prompt variable parsing in eval prompt templates, allowing raw template strings to pass through without substitution errors.
arize-phoenix-client-v1.13.0 Jul 16, 2025 · issue -364

Phoenix client v1.13.0 adds an experiments module and serialization support for client Datasets.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.13.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.13.0
```
- ›Adds an experiments module to the phoenix-client library, enabling experiment workflows directly from the client.
- ›Adds serialization and deserialization methods to client Datasets, allowing Dataset objects to be exported and restored programmatically.
- ›Delivers enhancements to the experiments functionality introduced in this release.
arize-phoenix-v11.7.0 Jul 14, 2025 · issue -364

Phoenix 11.7.0 adds an experiments module to the phoenix-client library and a new timeseries bar chart for metrics.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.7.0
```
- ›Adds an experiments module to the phoenix-client package, enabling experiment workflows directly from the client library.
- ›New timeseries bar chart visualization added to the metrics UI.
arize-phoenix-v11.6.0 Jul 9, 2025 · issue -364

Phoenix v11.6.0 adds a baseline comparison view to the experiments page.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.6.0
```
- ›Adds a baseline reference to the compare-experiments page, enabling side-by-side evaluation of experiment runs against a fixed baseline.
- ›Adds an experiment table story to the design system for consistent UI component development.
arize-phoenix-v11.5.0 Jul 8, 2025 · issue -364

Phoenix v11.5.0 adds a database disk usage monitor.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.5.0
```
- ›Adds a database disk usage monitor to track storage consumption.
arize-phoenix-v11.4.0 Jul 3, 2025 · issue -364

Phoenix v11.4.0 adds a cost summary to the trace header UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.4.0
```
- ›Adds a cost summary display to the trace header, surfacing token cost totals directly in the trace view.
arize-phoenix-client-v1.12.0 Jul 3, 2025 · issue -364

Arize Phoenix client v1.12.0 adds Bedrock playground support.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.12.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.12.0
```
- ›Adds Bedrock playground client integration, enabling use of Amazon Bedrock models within the Phoenix playground.
arize-phoenix-v11.3.0 Jul 2, 2025 · issue -364

Phoenix v11.3.0 adds a customizable Management URL link and a Cursor MCP button to the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.3.0
```
- ›Adds a 'add Cursor MCP' button to the UI for one-click MCP integration with the Cursor editor.
- ›Adds a link back to a customizable Management URL in the UI.
arize-phoenix-evals-v0.22.0 Jul 2, 2025 · issue -364

Arize Phoenix Evals v0.22.0 lets you pass extra keyword arguments when instantiating a Vertex AI GenerativeModel.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.22.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.22.0
```
- ›Supports passing additional keyword arguments to the Vertex AI GenerativeModel instantiation, enabling finer-grained model configuration (e.g. system instructions, safety settings) when using the Vertex AI evaluator backend.
arize-phoenix-v11.2.0 Jun 30, 2025 · issue -365

Phoenix v11.2.0 adds cost sorting on the traces table, paginated session details, and OpenTelemetry ID redirects.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.2.0
```
- ›Enables sorting by cost on the traces table.
- ›Adds pagination to the session details view for large session histories.
- ›Supports redirect navigation from OpenTelemetry IDs to the corresponding trace or span view.
arize-phoenix-v11.1.0 Jun 27, 2025 · issue -365

Arize Phoenix v11.1.0 adds imagePullSecrets support to the Helm chart.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.1.0
```
- ›Adds imagePullSecrets support to the Helm chart, enabling deployments that pull images from private registries.
arize-phoenix-v11.0.0 Jun 25, 2025 · issue -365

Phoenix v11 ships cost tracking for LLM spans, including model cost calculations and updated OpenAI reasoning model support.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v11.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v11.0.0
```
- ›Adds model cost tracking to LLM spans, calculating token-level costs across supported models.
- ›Adds updated cost definitions for OpenAI reasoning models.
└──▷ BREAKING ON UPGRADE
- !The cost feature release introduces breaking changes — see the published migration guide for required changes when upgrading from v10.
arize-phoenix-otel-v0.12.0 Jun 24, 2025 · issue -365

arize-phoenix-otel 0.12.0 adds support for passing tracer provider arguments.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-otel-v0.12.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-otel-v0.12.0
```
- ›Supports passing tracer provider arguments when initializing the OpenTelemetry integration in arize-phoenix-otel.
arize-phoenix-v10.15.0 Jun 22, 2025 · issue -365

Arize Phoenix 10.15.0 adds a Bedrock playground client for interactive model testing.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v10.15.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v10.15.0
```
- ›Adds a Bedrock playground client, enabling interactive testing of Amazon Bedrock models directly within the Phoenix UI.
arize-phoenix-v10.14.0 Jun 20, 2025 · issue -365

Phoenix now falls back to OTEL_EXPORTER_OTLP_ENDPOINT when PHOENIX_COLLECTOR_ENDPOINT is not set.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v10.14.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v10.14.0
```
└──▷ TRY IT
Use a standard OTel collector endpoint without setting a Phoenix-specific env var — useful in shared OTel environments where OTEL_EXPORTER_OTLP_ENDPOINT is already configured.
```
$ export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317
# PHOENIX_COLLECTOR_ENDPOINT is not set; Phoenix now picks up the OTel standard var automatically
```
- ›Reads OTEL_EXPORTER_OTLP_ENDPOINT as a fallback endpoint when PHOENIX_COLLECTOR_ENDPOINT is not defined, enabling standard OpenTelemetry environment variable conventions to work without Phoenix-specific configuration.
arize-phoenix-client-v1.11.0 Jun 19, 2025 · issue -365

Arize Phoenix client v1.11.0 adds log_spans, dataset methods, logout, and OTEL endpoint fallback.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.11.0
```
- ›Adds log_spans to the Phoenix client and REST API, enabling programmatic span ingestion.
- ›Adds dataset methods to the Phoenix client for managing datasets directly via the library.
- ›Adds logout support to the auth layer of the Phoenix client.
- ›Falls back to reading OTEL_EXPORTER_OTLP_ENDPOINT when PHOENIX_COLLECTOR_ENDPOINT is not set, easing OTEL-standard deployments.
arize-phoenix-otel-v0.11.0 Jun 18, 2025 · issue -365

arize-phoenix-otel v0.11.0 adds logout support, Phoenix Cloud spaces, and fallback to OTEL_EXPORTER_OTLP_ENDPOINT.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-otel-v0.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-otel-v0.11.0
```
└──▷ TRY IT
Point traces at a standard OTLP endpoint without setting a Phoenix-specific variable — useful when reusing an existing OpenTelemetry environment.
```
$ export OTEL_EXPORTER_OTLP_ENDPOINT=https://your-otel-collector:4318
python your_instrumented_app.py
```
- ›Falls back to the standard OTEL_EXPORTER_OTLP_ENDPOINT environment variable for the collector endpoint when PHOENIX_COLLECTOR_ENDPOINT is not set.
- ›Adds logout capability to the auth flow.
- ›Enables Phoenix Cloud spaces support.
arize-phoenix-v10.13.0 Jun 17, 2025 · issue -365

Phoenix v10.13.0 adds FullStory integration and enhanced Helm service configurability.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v10.13.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v10.13.0
```
- ›Adds FullStory session-replay integration to the Phoenix UI.
- ›Enhances Helm chart service configurability with improved configuration options and documentation.
arize-phoenix-v10.12.0 Jun 13, 2025 · issue -365

Phoenix v10.12.0 adds log_spans to the client and REST API, session filtering by ID, and zero-downtime Helm rollouts.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v10.12.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v10.12.0
```
- ›Adds log_spans to the Python client and REST API, enabling programmatic span ingestion directly via the client or HTTP.
- ›Adds filtering of sessions by session_id in the sessions API.
- ›Enables zero-downtime rollouts in the Helm chart deployment.
arize-phoenix-v10.11.0 Jun 12, 2025 · issue -365

Arize Phoenix v10.11.0 adds dataset filtering capability.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v10.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v10.11.0
```
- ›Adds dataset-filter support, enabling practitioners to filter datasets within Phoenix.
arize-phoenix-v10.9.0 Jun 7, 2025 · issue -365

Phoenix 10.9.0 adds an experiment progress chart and a composable ModalOverlay UI component.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v10.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v10.9.0
```
- ›Adds an experiment progress chart to the experiments view, giving practitioners a visual timeline of experiment run status.
- ›Introduces a composable ModalOverlay UI component for building layered dialog interfaces within Phoenix.
arize-phoenix-v10.8.0 Jun 6, 2025 · issue -365

Phoenix client gains dataset methods; experiments table is now resizable.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v10.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v10.8.0
```
- ›Adds dataset methods to the Phoenix client library, enabling programmatic dataset management.
- ›Experiments table columns are now resizable in the UI.
arize-phoenix-v10.7.0 Jun 4, 2025 · issue -365

Arize Phoenix 10.7.0 adds Ollama support and server-side playground credential management.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v10.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v10.7.0
```
- ›Adds server-side playground credentials, enabling credential key-value pairs to be stored and applied on the backend for playground LLM calls.
- ›Adds support for multiple credential key-value pairs in the playground UI frontend.
- ›Adds Ollama integration support.
arize-phoenix-client-v1.10.0 Jun 4, 2025 · issue -365

Phoenix client gains get_spans retrieval and Ollama model support in v1.10.0
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.10.0
```
└──▷ USE IT
Retrieve spans from a Phoenix project programmatically to analyze traces in code.
python
```
from phoenix.client import Client

client = Client()
spans = client.get_spans()
```
- ›Adds get_spans method to the Phoenix client library for programmatic span retrieval.
- ›Adds Ollama model support to the Phoenix client.
arize-phoenix-v10.6.0 Jun 3, 2025 · issue -365

Phoenix v10.6.0 adds get_spans to the client, new integrations, and a credentials field in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v10.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v10.6.0
```
└──▷ USE IT
Pull spans from a Phoenix project programmatically to inspect or export trace data outside the UI.
python
```
import phoenix as px

client = px.Client()
spans = client.get_spans(project_name="my-project")
print(spans)
```
- ›Adds get_spans method to the Phoenix client for programmatic span retrieval.
- ›Adds a credentials field to the UI for managing model/provider credentials.
- ›Expands the integrations catalog with additional provider integrations.
- ›Adds empty-state UI for the Prompts and Experiments sections.
arize-phoenix-client-v1.9.0 May 31, 2025 · issue -366

Phoenix client 1.9.0 adds a Users REST API and xAI model support in the Playground.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.9.0
```
- ›Adds a Users REST API under the admin surface for programmatic user management.
- ›Adds xAI as a supported model provider in the Playground for interactive LLM testing.
arize-phoenix-v10.5.0 May 31, 2025 · issue -366

Arize Phoenix v10.5.0 adds xAI as a supported provider in the Playground.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v10.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v10.5.0
```
- ›Adds xAI as a supported LLM provider in the Playground for interactive prompt testing.
arize-phoenix-v10.4.0 May 30, 2025 · issue -366

Phoenix 10.4.0 adds a Helm chart release and a tool-choice selector in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v10.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v10.4.0
```
- ›Adds a Helm chart release for deploying Arize Phoenix via Kubernetes.
- ›Adds a tool choice selector (toolChoiceSelect) to the UI for configuring tool-use behavior in the playground.
arize-phoenix-v10.3.0 May 30, 2025 · issue -366

Arize Phoenix 10.3.0 adds a users REST API for admin management.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v10.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v10.3.0
```
- ›Adds a users REST API under the admin surface for programmatic user management.
arize-phoenix-client-v1.8.0 May 29, 2025 · issue -366

Arize Phoenix client v1.8.0 adds DeepSeek model support to the Playground.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.8.0
```
- ›Adds DeepSeek as a supported model provider in the Playground for prompt testing and experimentation.
arize-phoenix-v10.2.0 May 29, 2025 · issue -366

Phoenix 10.2.0 adds a Helm chart, DeepSeek in Playground, tool-call query presets, and version ID from dataset upload.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v10.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v10.2.0
```
- ›The POST /v1/datasets/upload endpoint now returns a version ID in its response, enabling downstream workflows to reference the exact dataset version just uploaded.
- ›Adds an initial Helm chart for deploying Phoenix to Kubernetes clusters.
- ›Adds DeepSeek as a supported model provider in the Playground.
- ›Adds a predefined query for extracting tool calls from traces, reducing manual query construction.
arize-phoenix-v10.1.0 May 28, 2025 · issue -366

Phoenix 10.1.0 adds audio/cache token cost visibility, Annotation Summaries, and a new span search route.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v10.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v10.1.0
```
- ›Adds a span search route for querying spans directly.
- ›Displays audio, cache read, and cache write token counts on the span token tooltip for finer cost visibility.
- ›Replaces 'My Annotations' with Annotation Summaries, providing aggregated annotation views.
arize-phoenix-otel-v0.10.0 May 28, 2025 · issue -366

arize-phoenix-otel v0.10.0 adds an option to preserve the default span processor on initialization.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-otel-v0.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-otel-v0.10.0
```
- ›Adds an option to prevent Phoenix OTel setup from replacing the existing default span processor, allowing custom processors to coexist.
arize-phoenix-v10.0.0 May 21, 2025 · issue -366

Phoenix v10 adds OAuth2-only authentication mode, requiring a database migration on upgrade.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v10.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v10.0.0
```
- ›Adds OAuth2-only authentication mode, allowing deployments to enforce OAuth2 as the sole login mechanism.
└──▷ BREAKING ON UPGRADE
- !Enabling the OAuth2-only mode requires a database migration — run migrations before starting Phoenix v10.0.0.
arize-phoenix-client-v1.7.0 May 21, 2025 · issue -366

Phoenix client v1.7.0 adds a GraphQL query for hourly span count timeseries data.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.7.0
```
- ›Adds a GraphQL query for hourly span count timeseries, enabling time-bucketed span volume analysis.
arize-phoenix-v9.6.0 May 20, 2025 · issue -366

Phoenix 9.6.0 adds a model cost lookup table and token prompt details on span nodes.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v9.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v9.6.0
```
- ›Adds a model cost lookup table for resolving LLM token costs across models.
- ›Adds a token prompt details resolver on the span node, exposing cost-related prompt token breakdowns in tracing.
- ›Adds a TypeScript experiment example demonstrating how to run experiments from TypeScript.
arize-phoenix-v9.5.0 May 17, 2025 · issue -366

Phoenix 9.5.0 adds dashboard panels and a GraphQL hourly span count timeseries query.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v9.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v9.5.0
```
- ›Adds a GraphQL query for hourly span count timeseries, enabling time-bucketed volume analysis of spans directly via the API.
- ›Adds dashboard panel support, allowing observability metrics to be composed into panels within Phoenix dashboards.
arize-phoenix-v9.4.0 May 15, 2025 · issue -366

Arize Phoenix 9.4.0 adds rudimentary dashboard routing to the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v9.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v9.4.0
```
- ›Introduces initial dashboard routes, enabling navigation to dedicated dashboard views within the Phoenix UI.
arize-phoenix-client-v1.6.0 May 14, 2025 · issue -366

Arize Phoenix client v1.6.0 exposes experiment API routes in the client library.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.6.0
```
- ›Exposes experiment routes via the client API, enabling programmatic access to experiment functionality.
arize-phoenix-v9.3.0 May 13, 2025 · issue -366

Phoenix v9.3.0 adds Claude 3.7 support and exposes experiment routes via the API.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v9.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v9.3.0
```
- ›Exposes experiment routes via the API, making experiment data programmatically accessible.
- ›Adds Claude 3.7 model support.
arize-phoenix-v9.2.0 May 13, 2025 · issue -366

Phoenix 9.2.0 adds UI integrations for Agno, MCP, and Gemini.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v9.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v9.2.0
```
- ›Adds UI integrations for Agno, MCP, and Gemini, enabling trace visualization and observability for these frameworks and services.
arize-phoenix-v9.1.0 May 13, 2025 · issue -366

Arize Phoenix 9.1.0 adds project list/sort/filter in the UI and hotkey navigation for span details.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v9.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v9.1.0
```
- ›Adds hotkey support in the UI to open individual span details sections directly from the keyboard.
- ›Adds list, sort, and filter controls for projects in the UI.
arize-phoenix-client-v1.5.0 May 9, 2025 · issue -366

Phoenix client v1.5.0 adds span annotation read and write methods for programmatic trace review.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.5.0
```
└──▷ USE IT
Pull all annotations for a project's spans into a DataFrame for offline analysis or reporting.
python
```
import phoenix as px

client = px.Client()
df = client.get_span_annotations_dataframe(project_name="my-project")
```
- ›Adds get_span_annotations_dataframe method to the Phoenix client for retrieving span annotations as a DataFrame.
- ›Adds span annotation POST methods to the Phoenix client, enabling programmatic creation of span annotations.
arize-phoenix-v9.0.0 May 9, 2025 · issue -366

Phoenix v9.0.0 adds span annotation APIs, trace data retention policies, annotation configs, and JSON dataset uploads.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v9.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v9.0.0
```
└──▷ USE IT
Pull all span annotations for a project into a DataFrame for offline analysis or export.
python
```
import phoenix as px

client = px.Client()
df = client.get_span_annotations_dataframe(project_name="my-project")
print(df.head())
```
- ›Adds get_span_annotations_dataframe method to the Python client for retrieving span annotations as a DataFrame.
- ›Adds span annotation POST methods to the Python client for programmatically submitting span annotations.
- ›Adds GET /v1/span_annotations REST route for fetching span annotations.
- ›Associates the authenticated user with annotations submitted via /v1/span_annotations and /v1/trace_annotations.
- ›Adds GraphQL queries and mutations for trace retention policy CRUD operations, enabling programmatic management of data retention.
+16 moreshow less
- ›Supports multiple annotations per span sharing the same name, removing the previous uniqueness constraint.
- ›Adds upsert-on-conflict behavior keyed on annotation identifier, so re-submitted annotations update rather than error.
- ›Adds Annotation Configurations — project-level schemas that define valid annotation labels and scoring ranges, configurable per project.
- ›Adds timestamps to the annotation GraphQL type.
- ›Adds span annotation filters to the spans DSL, including filtering by annotation existence.
- ›Ensures all span annotations are included when exporting dataset examples.
- ›Adds a UI for creating, editing, and deleting trace data retention policies (global and per-project) in the Admin settings.
- ›Adds a system-level retention policies table in Admin for an overview of all configured policies.
- ›Adds capability-based access control to retention policy management.
- ›Adds a notes UI for free-text span annotations, with a reserved note annotation name.
- ›Adds a span comment mutation for attaching comments to spans.
- ›Adds an annotation summaries GraphQL query per span, and surfaces annotation summary columns in the spans and traces tables.
- ›Supports JSON dataset upload via the UI (in addition to existing CSV support).
- ›Adds Arize auth integration with auto-triggered login.
- ›Stabilizes categorical annotation summary pie chart colors across renders.
- ›Adds sorting to the span annotations table.
└──▷ BREAKING ON UPGRADE
- !The database table for trace data retention policies has changed schema — a migration is required on upgrade.
- !The database migrates from JSONB to JSON column storage — a migration is required on upgrade.
arize-phoenix-v8.32.0 May 6, 2025 · issue -366

Phoenix 8.32.0 adds a demo agent project with traces, datasets onboarding improvements, and message_contents support in the playground.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.32.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.32.0
```
- ›Adds support for message_contents span content in the playground, enabling richer message inspection.
- ›Adds a demo_agent project with pre-loaded traces for onboarding and exploration.
- ›Adds an empty-state onboarding experience for the datasets section.
arize-phoenix-client-v1.4.0 May 3, 2025 · issue -366

Arize Phoenix client v1.4.0 adds SpanQuery DSL and get_spans_dataframe for programmatic span retrieval.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.4.0
```
└──▷ USE IT
Pull filtered spans into a DataFrame for offline analysis or model evaluation pipelines.
python
```
from phoenix.client import Client
from phoenix.client.resources.spans import SpanQuery

client = Client()
query = SpanQuery().where("span_kind == 'LLM'")
df = client.get_spans_dataframe(query=query)
```
- ›Adds SpanQuery DSL to the Phoenix client for building structured span queries programmatically.
- ›Adds get_spans_dataframe method to the Phoenix client to retrieve spans as a DataFrame.
arize-phoenix-v8.31.0 May 1, 2025 · issue -366

Arize Phoenix 8.31.0 adds video tutorials to the UI components.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.31.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.31.0
```
- ›Adds video support to the tutorials UI component.
arize-phoenix-v8.30.0 Apr 30, 2025 · issue -367

Phoenix 8.30.0 adds SpanQuery DSL to the client, RBAC for REST, and separate TLS flags for HTTP and gRPC.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.30.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.30.0
```
└──▷ USE IT
Query spans from a Phoenix project into a pandas DataFrame for offline analysis.
python
```
from phoenix.client import Client
from phoenix.client.dsl import SpanQuery

client = Client()
query = SpanQuery()
df = client.get_spans_dataframe(query=query, project_name='my-project')
print(df.head())
```
- ›Adds SpanQuery DSL and get_spans_dataframe method to the Phoenix client for querying spans programmatically.
- ›Adds RBAC primitives for FastAPI / REST endpoints to enforce role-based access control.
- ›Adds separate TLS-enabled flags for HTTP and gRPC transports, allowing independent TLS configuration per protocol.
- ›Adds a 'copy name' button to the project menu in the UI.
arize-phoenix-v8.29.0 Apr 28, 2025 · issue -367

Arize Phoenix v8.29.0 adds environment variables for TLS configuration.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.29.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.29.0
```
- ›Adds environment variable support for TLS configuration, enabling certificate and key setup without code changes.
arize-phoenix-v8.28.0 Apr 28, 2025 · issue -367

Phoenix 8.28.0 gracefully handles Ctrl-C interrupts during execution.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.28.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.28.0
```
- ›Gracefully handles Ctrl-C (SIGINT) so the process shuts down cleanly instead of crashing or leaving state corrupted.
arize-phoenix-v8.27.0 Apr 24, 2025 · issue -367

Adds /readyz health endpoint for database connectivity checks and auto-scrolls selected spans in the trace view.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.27.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.27.0
```
└──▷ TRY IT
Poll the new readiness endpoint in a health-check script or Kubernetes readinessProbe to confirm Phoenix has a live database connection before routing traffic.
```
$ curl -f http://localhost:6006/readyz
```
- ›Adds GET /readyz endpoint to confirm database connectivity, enabling reliable liveness/readiness probes in orchestrated deployments.
- ›Scrolls the selected span into view automatically when navigating to a trace in the tracing UI.
arize-phoenix-v8.26.0 Apr 16, 2025 · issue -367

Arize Phoenix 8.26.0 adds PHOENIX_ADMIN_SECRET env var and infinite-scroll load-more in the tracing UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.26.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.26.0
```
└──▷ TRY IT
Restrict admin access to Phoenix by setting the admin secret before launching the server.
```
$ export PHOENIX_ADMIN_SECRET=my-secret-value
phoenix serve
```
- ›Adds PHOENIX_ADMIN_SECRET environment variable to control admin-level access.
- ›Adds 'load more' button and loading state to the infinite scroll in the tracing UI.
arize-phoenix-v8.25.0 Apr 15, 2025 · issue -367

Arize Phoenix 8.25.0 adds tool call and tool result IDs to span details in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.25.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.25.0
```
- ›Displays tool call and tool result IDs in the span details view, making it easier to correlate tool invocations with their results during trace inspection.
arize-phoenix-client-v1.3.0 Apr 9, 2025 · issue -367

Phoenix client v1.3.0 adds a full REST API for project CRUD and lets you address projects by name in REST paths.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.3.0
```
- ›Adds REST API endpoints for full CRUD operations on projects (create, read, update, delete).
- ›Allows project name as an identifier in the REST path for projects endpoints, in addition to project ID.
arize-phoenix-v8.24.0 Apr 9, 2025 · issue -367

Phoenix v8.24.0 lets you address projects by name in REST paths and sends welcome emails on user creation.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.24.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.24.0
```
- ›Allows project name as an identifier in the REST path for projects endpoints, so you can reference a project by name instead of only by ID.
- ›Sends a welcome email automatically after a new user is created.
arize-phoenix-v8.23.0 Apr 9, 2025 · issue -367

Phoenix 8.23.0 adds a PHOENIX_ALLOWED_ORIGINS env var and a REST API for full project CRUD operations.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.23.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.23.0
```
- ›Adds PHOENIX_ALLOWED_ORIGINS environment variable to the Phoenix server to control which origins are permitted (CORS allowlist).
- ›New REST API endpoints for full CRUD operations on projects.
- ›Enables deletion of annotations directly from the feedback column in the tracing UI.
- ›Makes the feedback table scrollable in the tracing UI.
arize-phoenix-client-v1.2.0 Apr 3, 2025 · issue -367

Arize Phoenix client adds REST endpoints to list and create prompt version tags.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.2.0
```
- ›Adds REST endpoints to list and create prompt version tags, enabling programmatic management of prompt versioning via the API.
arize-phoenix-v8.22.0 Apr 3, 2025 · issue -367

Phoenix v8.22.0 adds REST endpoints to list and create prompt version tags.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.22.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.22.0
```
- ›Adds REST endpoints to list or create prompt version tags, enabling programmatic tag management on prompt versions.
arize-phoenix-v8.21.0 Apr 2, 2025 · issue -367

Phoenix 8.21.0 moves span annotation editing into the Span Aside and adds chat/note-taking UI components.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.21.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.21.0
```
- ›Moves the Span Annotation Editor into the Span Aside panel, consolidating annotation workflows in one place.
- ›Adds chat and message UI components for note-taking within the interface.
- ›Allows PostgreSQL deployments to run without a working directory configured.
- ›Caches project table results when toggling the details slide-over, reducing redundant loads.
arize-phoenix-v8.19.0 Mar 25, 2025 · issue -368

Arize Phoenix v8.19.0 adds a Config tab to the tracing UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.19.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.19.0
```
- ›Adds a Config tab to the tracing UI, giving practitioners a dedicated view for tracing configuration settings.
arize-phoenix-otel-v0.9.0 Mar 22, 2025 · issue -368

Arize Phoenix OTel v0.9.0 adds a warning when SimpleSpanProcessor is detected.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-otel-v0.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-otel-v0.9.0
```
- ›Adds a runtime warning when SimpleSpanProcessor is used, alerting practitioners to the performance implications of synchronous span export.
arize-phoenix-v8.17.0 Mar 21, 2025 · issue -368

Arize Phoenix 8.17.0 adds an environment variable to auto-provision admin users at startup.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.17.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.17.0
```
- ›Adds an environment variable to automatically insert admin users when the Phoenix server starts, enabling headless/automated deployment without manual user setup.
arize-phoenix-v8.16.0 Mar 20, 2025 · issue -368

Phoenix 8.16.0 adds experiment deletion from the action menu and date format explanations in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.16.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.16.0
```
- ›Adds a 'Delete Experiment' option to the experiment action menu in the UI.
- ›Shows the expected date format as an explanation in date input fields in the UI.
arize-phoenix-v8.14.0 Mar 18, 2025 · issue -368

Phoenix 8.14.0 adds resizable Span/Trace/Session tables and a tabbed Settings page.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.14.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.14.0
```
- ›Splits the Settings page into tabs for easier navigation.
- ›Adds column-resize capability to the Span, Trace, and Session tables in the UI.
arize-phoenix-v8.13.0 Mar 14, 2025 · issue -368

Phoenix v8.13.0 adds CSV export for experiment runs and annotations, and makes the spans table the default tab.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.13.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.13.0
```
- ›Download experiment runs and annotations as CSV from the UI.
- ›Makes the spans table the default tab for faster trace navigation.
arize-phoenix-v8.12.0 Mar 8, 2025 · issue -368

Arize Phoenix 8.12.0 adds a high-contrast UI mode.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.12.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.12.0
```
- ›Adds a high-contrast UI mode for improved accessibility and readability.
arize-phoenix-client-v1.1.0 Mar 7, 2025 · issue -368

Arize Phoenix client v1.1.0 adds Anthropic thinking config parameter support to the Python client.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-client-v1.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-client-v1.1.0
```
- ›Adds thinking config parameter for Anthropic models to the Python client, enabling extended thinking support in Phoenix-instrumented calls.
arize-phoenix-v8.11.0 Mar 7, 2025 · issue -368

Phoenix 8.11.0 adds a specialized UI for the thinking budget parameter and migrates the slider to react-aria.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.11.0
```
- ›Adds specialized UI for the thinking budget parameter, giving practitioners a dedicated control surface when configuring model reasoning limits.
- ›Ports the slider component to react-aria, improving accessibility and interaction consistency across parameter controls.
arize-phoenix-v8.10.0 Mar 6, 2025 · issue -368

Arize Phoenix 8.10.0 adds DB usage visibility in the admin panel and bulk trace deletion from the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.10.0
```
- ›Admin panel now shows percent of database storage used, giving operators visibility into DB capacity.
- ›Enables deletion of selected traces in bulk from the traces UI.
arize-phoenix-v8.9.0 Mar 6, 2025 · issue -368

Phoenix 8.9.0 adds Anthropic thinking config and budget params, a DB storage env var, and experiment JSON downloads.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.9.0
```
└──▷ TRY IT
Cap Phoenix database storage at a fixed size when running in a memory-constrained environment.
```
$ export PHOENIX_DB_ALLOCATED_STORAGE_CAPACITY_GIB=20
phoenix serve
```
- ›Adds PHOENIX_DB_ALLOCATED_STORAGE_CAPACITY_GIB environment variable to configure allocated database storage capacity in gibibytes.
- ›Adds Anthropic thinking config parameter support to the Python client for extended thinking mode.
- ›Adds thinking_budget as an invocation parameter for controlling Anthropic extended thinking token budget.
- ›Adds JSON download support for experiment results in the UI.
arize-phoenix-v8.8.0 Mar 1, 2025 · issue -368

Arize Phoenix 8.8.0 adds quick filtering from metadata cells in the trace table.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.8.0
```
- ›Adds quick filtering support for metadata cells in the trace table, letting users instantly filter traces by clicking metadata values.
arize-phoenix-v8.7.0 Feb 28, 2025 · issue -369

Phoenix 8.7.0 adds root-only trace filtering, GPT-4.5-preview in the playground, and a new Token UI component.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.7.0
```
- ›Adds a root-only filter to the traces view, letting practitioners scope trace lists to top-level spans only.
- ›Adds gpt-4.5-preview as a selectable model in the playground.
- ›Adds a new Token UI component to the component library.
arize-phoenix-v8.6.0 Feb 27, 2025 · issue -369

Phoenix 8.6.0 adds overflow span count display in the traces table UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.6.0
```
- ›Traces table now shows a '+ n more spans' indicator when a trace contains more spans than are visible, improving at-a-glance trace size awareness.
arize-phoenix-v8.5.0 Feb 27, 2025 · issue -369

Phoenix 8.5.0 adds a GraphQL query to retrieve per-trace span counts.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.5.0
```
- ›Adds a GraphQL query to retrieve the number of spans for each trace, enabling programmatic trace-depth inspection.
arize-phoenix-v8.4.0 Feb 26, 2025 · issue -369

Phoenix 8.4.0 adds DB usage introspection via GraphQL and persists project table column selections in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.4.0
```
- ›Adds GraphQL query to retrieve the byte size of each database table, enabling admins to monitor storage consumption per table.
- ›Adds GraphQL query to retrieve the number of child spans for a given span, supporting deeper trace analysis.
- ›Adds admin-level introspection into overall database usage.
- ›Persists project table column selections in the UI so column layouts survive page reloads.
arize-phoenix-v8.1.0 Feb 20, 2025 · issue -369

Arize Phoenix 8.1.0 adds support for standard PostgreSQL environment variables for database configuration.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.1.0
```
- ›Supports configuring the PostgreSQL connection via standard environment variables PGUSER, PGPASSWORD, PGDATABASE, and PGHOST (the exact standard Postgres env var names) in addition to any existing Phoenix-specific settings.
arize-phoenix-v8.0.0 Feb 19, 2025 · issue -369

Phoenix v8 ships a full Prompt Hub API — REST endpoints, GraphQL mutations, versioning, tagging, and OpenAI/Anthropic client helpers.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v8.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v8.0.0
```
└──▷ TRY IT
List all saved prompts from a CI script or external tool to audit what is registered in Phoenix.
```
$ curl -X GET 'http://localhost:6006/prompts' -H 'Accept: application/json'
```
Fetch all versions of a specific prompt to compare or roll back to a prior version.
```
$ curl -X GET 'http://localhost:6006/prompts/<id>/versions' -H 'Accept: application/json'
```
- ›Adds GET /prompts REST endpoint to list all prompts programmatically.
- ›Adds GET /prompts/{id}/versions REST endpoint to retrieve all versions of a specific prompt.
- ›Adds POST method to the prompts REST endpoint for creating prompts via REST.
- ›Adds previous_version resolver on the PromptVersion GraphQL type to traverse version history.
- ›Adds deletePrompt and deletePromptVersionTag GraphQL mutations for lifecycle management.
+23 moreshow less
- ›Adds patchPromptDescription GraphQL mutation to update prompt descriptions.
- ›Adds setPromptVersionTag GraphQL mutation (with Prompt input) for labeling prompt versions.
- ›Adds PromptTemplate GraphQL type and PromptLabel GraphQL interface for structured prompt data modeling.
- ›Adds GraphQL types for tools and output_schema on prompt versions.
- ›Adds tags-on-create support so version tags (including defaults prod, staging, dev) can be set when a new prompt version is created.
- ›Adds client helper methods for OpenAI and Anthropic prompt formats, including tool_choice in the Python client SDK helpers.
- ›Adds Anthropic code snippets to the prompt details UI alongside existing OpenAI snippets.
- ›Adds in-UI code snippets generated using the phoenix-clients library.
- ›Adds a 'Clone Prompt' flow to the prompts UI.
- ›Adds an 'Open in Playground' action button on the prompts table.
- ›Adds a prompt combobox to the Playground page with deep-linking to a prompt-specific playground URL.
- ›Adds label colors and version metadata display on prompt versions.
- ›Adds description and last-updated-at columns to the prompts table UI.
- ›Adds author, tags, and other metadata display to the version list UI.
- ›Supports loading a prompt into the playground via URL.
- ›Supports creating new prompts and prompt versions directly from the Playground.
- ›Supports editing prompt descriptions inline in the UI.
- ›Adds a hotkey to run the Playground without clicking the run button.
- ›Displays tool definitions on the prompt detail page.
- ›Displays basic LLM invocation parameters and model details on prompt detail pages.
- ›Shows a preview of the last 5 versions on the prompt detail view.
- ›Names experiments after the prompt they are derived from.
- ›Adds a prompthub database migration for the new prompt models.
arize-phoenix-otel-v0.8.0 Feb 18, 2025 · issue -369

Phoenix OTEL v0.8.0 enables one-line LLM instrumentation via phoenix.otel.register
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-otel-v0.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-otel-v0.8.0
```
- ›Adds phoenix.otel.register for one-line OpenTelemetry instrumentation setup in Python applications.
arize-phoenix-v7.12.0 Feb 5, 2025 · issue -369

Phoenix 7.12.0 records URL info in playground spans for better request traceability.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v7.12.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v7.12.0
```
- ›Playground spans now record URL information, enabling traceability of the exact endpoints called during playground LLM interactions.
arize-phoenix-evals-v0.20.0 Feb 5, 2025 · issue -369

Arize Phoenix Evals v0.20.0 adds per-model executor timeout overrides and OpenAI reasoning model support.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.20.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.20.0
```
- ›Enables overriding executor timeouts on a per-model basis, allowing fine-grained control over evaluation latency limits.
- ›Supports OpenAI reasoning models that do not use the system role, enabling evals against models like o1 and o3.
arize-phoenix-v7.11.0 Feb 5, 2025 · issue -369

Phoenix 7.11.0 adds centralized AI provider configuration in the Playground.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v7.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v7.11.0
```
- ›Adds centralized AI provider configuration in the Playground UI, consolidating provider settings in one place.
arize-phoenix-v7.10.0 Feb 4, 2025 · issue -369

Phoenix 7.10.0 adds experiment/dataset improvements and a base URL text field in the playground model config UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v7.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v7.10.0
```
- ›Adds a base URL text field in the playground model configuration UI, enabling custom endpoint targeting for LLM providers.
- ›Improves experiment and dataset workflows with unspecified enhancements to the experiments and datasets experience.
arize-phoenix-otel-v0.7.0 Jan 22, 2025 · issue -370

phoenix.otel gains automatic gRPC port inference from environment and an explicit OTEL protocol override.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-otel-v0.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-otel-v0.7.0
```
- ›Adds explicit OTEL protocol override support to phoenix.otel, letting callers force a specific transport protocol rather than relying on defaults.
- ›phoenix.otel now infers the gRPC port from the environment automatically, removing the need to hard-code port values when a relevant env var is set.
arize-phoenix-v7.9.0 Jan 21, 2025 · issue -370

Phoenix v7.9.0 adds support for OpenAI o1 developer messages and the reasoning parameter.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v7.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v7.9.0
```
- ›Adds support for o1 developer messages and the reasoning parameter in OpenAI o1 model integrations.
arize-phoenix-v7.8.0 Jan 17, 2025 · issue -370

Phoenix 7.8.0 improves error visibility with prettified user-facing mutation error messages.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v7.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v7.8.0
```
- ›Improves user-facing error display for GraphQL mutations, making error messages more readable in the UI.
arize-phoenix-evals-v0.19.0 Jan 16, 2025 · issue -370

Phoenix Evals 0.19.0 adds audio evaluation support to llm_classify().
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.19.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.19.0
```
- ›Adds audio evals and a data processor to llm_classify(), enabling evaluation of audio-based LLM inputs.
arize-phoenix-v7.7.0 Jan 14, 2025 · issue -370

Arize Phoenix 7.7.0 adds experiment run filtering on the compare experiments page.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v7.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v7.7.0
```
- ›Adds experiment run filter to the compare experiments page, enabling side-by-side comparison of specific runs across experiments.
arize-phoenix-v7.6.0 Jan 9, 2025 · issue -370

Phoenix playground now supports anyOf JSON schema for structured output definitions.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v7.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v7.6.0
```
- ›Adds anyOf JSON schema support in the playground for defining structured LLM outputs.
arize-phoenix-v7.4.0 Jan 3, 2025 · issue -370

Phoenix v7.4.0 adds a token breakdown view in the project header UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v7.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v7.4.0
```
- ›Shows a breakdown of tokens in the project header for at-a-glance token usage visibility.
arize-phoenix-v7.3.0 Dec 21, 2024 · issue -371

Phoenix 7.3.0 adds pretty-printed JSON for structured trace outputs and updated o1 model parameters in the playground.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v7.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v7.3.0
```
- ›Tracing UI now pretty-prints JSON strings for structured data outputs, making LLM response inspection easier.
- ›Playground updated with current o1 model listing and parameters.
arize-phoenix-evals-v0.18.0 Dec 20, 2024 · issue -371

phoenix.evals now supports multimodal message templates for richer LLM evaluation inputs.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.18.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.18.0
```
- ›Enables phoenix.evals to handle multimodal message templates, allowing evaluations over inputs that combine text and other media types.
arize-phoenix-v7.2.0 Dec 18, 2024 · issue -371

Phoenix 7.2.0 improves playground template editor ergonomics.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v7.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v7.2.0
```
- ›Enhances template editor ergonomics in the playground UI.
arize-phoenix-v7.1.0 Dec 11, 2024 · issue -371

Phoenix 7.1.0 adds arbitrary model name entry, Gemini 2.0 Flash support, and prettier JSON rendering in the playground.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v7.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v7.1.0
```
- ›Adds support for gemini-2.0-flash-exp as a selectable model in the Playground.
- ›Enables arbitrary string model names in the Playground, removing the restriction to a fixed model list.
- ›Prettifies JSON mimeType inputs and outputs rendered in the session details pane.
arize-phoenix-v7.0.0 Dec 9, 2024 · issue -371

Arize Phoenix v7.0.0 ships a full Sessions feature: grouped trace views, session details UI, and a new project_sessions database table.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v7.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v7.0.0
```
- ›Adds a project_sessions database table (via a new Alembic up migration 4ded9e43755f) to group traces into user sessions, with a back-population migration from existing spans data documented in MIGRATION.md.
- ›Adds a Sessions table on the project page showing per-session metrics including trace count, error count, trace latency percentiles (p50 and others), and last trace start time.
- ›Adds a session details page with per-session trace latency p50 and error counts.
- ›Adds navigation from an individual trace view to its parent session.
- ›Enables sorting on the sessions table.
+2 moreshow less
- ›Adds substring search filtering on sessions based on root span input/output values.
- ›Recognizes session_id and user_id attributes on root spans to associate traces with sessions.
└──▷ BREAKING ON UPGRADE
- !Upgrading requires running the new Alembic database migration (4ded9e43755f) and optionally back-populating the project_sessions table from existing spans data — see MIGRATION.md#v6x-to-v700.
arize-phoenix-v6.2.0 Dec 9, 2024 · issue -371

Arize Phoenix 6.2.0 adds timeout parameters to evaluation client calls and auto-pulls prompt template variables from spans into the playground.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v6.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v6.2.0
```
- ›Adds timeout parameters to log_evaluations and get_evaluations client methods, giving callers explicit control over request timeouts.
- ›Playground now automatically pulls prompt template variables from spans and captures them on playground spans, enabling faster replay and debugging of traced LLM calls.
arize-phoenix-v6.1.0 Dec 3, 2024 · issue -371

Phoenix 6.1.0 adds a cancel button for playground runs and inline invocation parameter error display.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v6.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v6.1.0
```
- ›Adds a cancel button to stop in-progress playground runs.
- ›Shows invocation parameter errors inline within the playground form instead of failing silently.
arize-phoenix-v6.0.0 Dec 2, 2024 · issue -371

Phoenix 6.0 ships a Playground UI for interactive LLM prompt testing and adds evaluations to its OpenAPI schema.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v6.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v6.0.0
```
- ›Adds evaluations to the OpenAPI schema, exposing evaluation data through the REST API.
- ›Releases the Playground feature — an interactive UI for running and comparing LLM prompts against live providers and datasets, with support for the AZURE_OPENAI_API_KEY environment variable for Azure OpenAI.
arize-phoenix-v5.12.0 Nov 25, 2024 · issue -372

Phoenix Playground gains a 'Move Output' button and a None template formatter option for messages.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v5.12.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v5.12.0
```
- ›Adds None as a selectable template formatter option for messages in the Playground, allowing messages to be sent without any template formatting applied.
- ›Adds a 'Move Output' button on the Playground Output panel to relocate output to other parts of the interface.
arize-phoenix-v5.11.0 Nov 22, 2024 · issue -372

Phoenix v5.11.0 adds an environment variable for setting the default admin password and blocks playground navigation during active runs.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v5.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v5.11.0
```
- ›Adds an environment variable to configure the default admin initial password at startup.
- ›Playground now blocks navigation when runs are in progress, preventing accidental loss of in-flight completions.
arize-phoenix-v5.10.0 Nov 20, 2024 · issue -372

Phoenix v5.10.0 adds Anthropic tool message support and playground chat completion error display.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v5.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v5.10.0
```
- ›Supports 'tool' message role for Anthropic in the playground, enabling tool-use conversation flows with Claude models.
- ›Displays chat completion errors inline within the playground output card for faster diagnosis of failed LLM calls.
arize-phoenix-v5.9.0 Nov 18, 2024 · issue -372

Phoenix 5.9.0 adds Google AI Studio/Gemini support and major Playground dataset-run capabilities.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v5.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v5.9.0
```
- ›Adds a GraphQL mutation for chat completion over a dataset, enabling batch prompt runs against dataset examples from the Playground.
- ›Adds Google AI Studio support for Gemini models (API-key-based) as a new LLM provider in the Playground.
- ›Adds a dataset example slideover in the Playground to inspect individual dataset examples and their template application.
- ›Adds streaming output display for Playground runs executed against datasets.
- ›Adds an example run slideover in the Playground for reviewing per-example run results.
+3 moreshow less
- ›Adds pre-emptive display of dataset example template application errors in the Playground dataset table before runs are submitted.
- ›Adds support for unknown tool and tool call formats in the Playground.
- ›Adds a rendered input field for JSON invocation parameters in the Playground.
arize-phoenix-v5.8.0 Nov 11, 2024 · issue -372

Phoenix Playground gains dataset integration, Anthropic tool calls, response format control, and env-var-driven gRPC interceptor extensions.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v5.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v5.8.0
```
- ›Adds env var configuration for gRPC interceptor extensions, enabling customization of the gRPC layer without code changes.
- ›Adds a non-streaming mode toggle to the Playground UI, letting users switch between streaming and non-streaming LLM calls.
- ›Adds a dataset selector and dataset examples table to the Playground, allowing prompt runs against existing datasets directly in the UI.
- ›Supports Anthropic tool calls in the Playground, expanding provider coverage for structured tool-use workflows.
- ›Supports Response Format configuration in the Playground, enabling structured output control (e.g. JSON mode) from the UI.
+3 moreshow less
- ›Adds rate limiters to Playground LLM clients to prevent API quota exhaustion during batch prompt runs.
- ›The default landing route now goes to the Projects page instead of a previous default, surfacing project-level observability immediately on load.
- ›Adds empty-state messaging and helper tooltips in the Playground when required provider client libraries are not installed.
arize-phoenix-v5.7.0 Nov 6, 2024 · issue -372

Phoenix 5.7.0 adds a chat completion mutation, cross-provider tool-call schema conversion, and streaming dataset runs in the Playground.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v5.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v5.7.0
```
- ›Adds response_format invocation parameter to the Playground, enabling structured-output control per LLM call.
- ›Adds a chatCompletion GraphQL mutation for programmatic chat completion requests.
- ›Supports converting tool call schemas between providers, enabling cross-provider prompt portability.
- ›Playground now streams chat completions over a full dataset, letting users batch-test prompts at scale.
- ›Playground persists model config (model name, parameters) per provider in user preferences.
+4 moreshow less
- ›Parses invocation parameters from a Span and populates them into the Playground page store when replaying a trace.
- ›Adds environment configuration support for FastAPI and GraphQL extensions.
- ›Detects WebSocket availability at runtime and passes the result to the client for adaptive transport.
- ›Playground UI surfaces only LLM providers whose SDK dependencies are installed.
arize-phoenix-v5.6.0 Oct 29, 2024 · issue -373

Phoenix 5.6.0 adds LLMRelationalEvaluator, Anthropic token counts in playground, and tool call support for span replay.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v5.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v5.6.0
```
- ›Adds LLMRelationalEvaluator to the Phoenix experiments library for relational LLM-based evaluation tasks.
- ›Playground now surfaces tool_calls from spans and plumbs span-defined tools into the playground UI, enabling full tool-call replay from production traces.
- ›Playground displays token counts for Anthropic models alongside existing providers.
- ›Playground adds tool role messages to the conversation UI, rounding out multi-turn message type support.
- ›Adds a model invocation parameters form scaffold to the playground for configuring model-specific parameters.
+2 moreshow less
- ›Adds a markdown toggle to playground output cards so LLM responses can be rendered as formatted markdown.
- ›Adds an Annotate button and slide-over panel to the run metadata footer for inline annotation of experiment runs.
arize-phoenix-v5.5.0 Oct 19, 2024 · issue -373

Arize Phoenix v5.5.0 adds Anthropic support to subscription streaming.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v5.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v5.5.0
```
- ›Adds Anthropic model support to subscription streaming.
arize-phoenix-v5.4.0 Oct 18, 2024 · issue -373

Phoenix 5.4.0 adds secure WSS connection support and playground span details on run completion.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v5.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v5.4.0
```
- ›Adds support for secure wss connections to Phoenix.
- ›Playground now returns the finalized span at the end of a subscription, making trace data available immediately after a run.
- ›Playground now displays span details when a run ends, surfacing trace information inline.
arize-phoenix-v5.3.0 Oct 17, 2024 · issue -373

Phoenix 5.3.0 ships a full Playground UI for LLM span replay, streaming completions, tool calling, Azure OpenAI support, and a TypeScript client scaffold.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v5.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v5.3.0
```
- ›Playground replays LLM spans by parsing the llm.input_messages span attribute and pre-populating the prompt editor, letting teams iterate on prompts directly from a captured trace.
- ›Playground supports streaming chat completions, letting practitioners see model output token-by-token during interactive prompt tuning.
- ›Playground adds a tools UI with full tool-calling backend support, including wiring up tool choice to the model invocation.
- ›Playground supports Azure OpenAI as a provider alongside existing providers, with model name and provider inferred automatically from the span.
- ›Playground allows up to 4 side-by-side instances, distinguished alphabetically, for parallel prompt comparison.
+6 moreshow less
- ›Playground includes a template language toggle and a CodeMirror-based template string editor that extracts and displays variables from all message templates as 'inputs'.
- ›Playground provides credential storage so API keys are persisted across sessions without re-entry.
- ›Playground creates an LLM span for each playground run, recording invocation parameters for traceability.
- ›Adds a LiteLLM integrations UI surface for configuring LiteLLM-backed models.
- ›Adds a generic model listing UI, enabling selection of models from configured providers.
- ›Scaffolds a TypeScript Phoenix client (ts package) for programmatic access to Phoenix from JavaScript/TypeScript environments.
arize-phoenix-evals-v0.17.0 Oct 9, 2024 · issue -373

Phoenix Evals now always sends prompts as system messages for OpenAI models.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.17.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.17.0
```
- ›OpenAI model evaluations now always send prompts as system-role messages instead of user-role messages.
arize-phoenix-v5.2.0 Oct 5, 2024 · issue -373

Arize Phoenix v5.2.0 introduces a new Phoenix CLI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v5.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v5.2.0
```
- ›Adds a Phoenix command-line interface (phoenix CLI) for interacting with Phoenix from the terminal.
arize-phoenix-v5.0.0 Sep 26, 2024 · issue -374

Phoenix 5.0 adds authentication, RBAC, API keys, OAuth2 (Google/Cognito/Auth0), and SMTP support across UI, REST, GraphQL, and gRPC.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v5.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v5.0.0
```
- ›Adds environment variables for token expiry configuration, letting operators tune access- and refresh-token lifetimes.
- ›Adds environment variable for the Secure attribute on cookies, enabling secure-cookie enforcement.
- ›Adds CreateUserApiKey GraphQL mutation and deleteUsers mutation for programmatic API key and user lifecycle management.
- ›Adds support for OAuth2 with OpenID Connect discovery, covering Google, AWS Cognito, and Auth0 as identity providers.
- ›Adds SMTP integration for password-reset emails.
+10 moreshow less
- ›Adds server-side rate limiting on authentication endpoints.
- ›Introduces token-based authentication (session tokens) gating the UI and all APIs (REST, GraphQL, gRPC) when auth is enabled.
- ›Introduces basic RBAC with two roles — admin (create/edit/delete users) and member (edit own profile only) — enforced on GraphQL queries.
- ›Adds GraphQL resolvers to patch (update) users and a GQL field indicating whether a user password requires a reset.
- ›Secures the /exports endpoint and the GraphQL API when authentication is enabled.
- ›Adds API key management to the user profile page in the UI, including creation and deletion.
- ›Adds admin user management UI for creating, editing, and deleting users.
- ›Adds a playground page (skeleton) to the UI.
- ›Adds Prometheus metrics for authentication events.
- ›Wires up API keys via environment variable for Phoenix clients and experiments.
└──▷ BREAKING ON UPGRADE
- !Python 3.8 is no longer supported; upgrade to Python 3.9 or later.
- !Legacy instrumentation modules have been removed; callers must migrate to the current instrumentation API.
arize-phoenix-v4.36.0 Sep 20, 2024 · issue -374

Phoenix v4.36.0 adds an environment variable to control structured logging output.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.36.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.36.0
```
- ›Adds an environment variable setting to enable structured (JSON) logging for Phoenix server output.
arize-phoenix-v4.34.0 Sep 17, 2024 · issue -374

Phoenix v4.34.0 adds finer-grain 'last N' time range selection to the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.34.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.34.0
```
- ›Adds finer-grain 'last N' time range controls for more precise time-window selection when exploring traces and inferences.
arize-phoenix-evals-v0.16.0 Sep 17, 2024 · issue -374

Phoenix Evals v0.16.0 adds support for OpenAI o1 preview models.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.16.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.16.0
```
- ›Adds OpenAI o1 preview model support to the Phoenix Evals library.
arize-phoenix-v4.33.0 Sep 4, 2024 · issue -374

Phoenix v4.33.0 adds user API keys table, PostgreSQL schema support, Bedrock onboarding, and improved DeleteSystemApiKey mutation.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.33.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.33.0
```
- ›The DeleteSystemApiKey mutation now returns a Query object, enabling callers to refetch dependent data in a single round-trip.
- ›Adds a user API keys management table in the auth UI.
- ›Adds PostgreSQL schema support with a dedicated integration test for production database deployments.
- ›Adds Amazon Bedrock to the onboarding flow.
- ›Renders the database schema in the welcome message when a supported database is configured.
arize-phoenix-v4.32.0 Aug 29, 2024 · issue -375

Phoenix 4.32.0 adds auth login/logout, system key deletion, tool schema display, and toggleable project auto-refresh.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.32.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.32.0
```
- ›Adds UI toggle to turn off auto-refresh of projects, reducing noise when reviewing stable traces.
- ›Adds login/logout flow wired up through the auth system.
- ›Enables deletion of system API keys via the auth interface.
- ›Displays tool schema definitions inline in the UI for inspecting LLM tool call structures.
arize-phoenix-v4.31.0 Aug 27, 2024 · issue -375

Arize Phoenix v4.31.0 adds a gallery view with expandable images for vision trace data.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.31.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.31.0
```
- ›Adds an image gallery view in the UI for vision traces, with support for expanding individual images.
arize-phoenix-v4.30.0 Aug 26, 2024 · issue -375

Arize Phoenix v4.30.0 adds a new project onboarding experience.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.30.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.30.0
```
- ›Introduces a new project onboarding flow to guide users through initial project setup.
arize-phoenix-v4.29.0 Aug 26, 2024 · issue -375

Phoenix v4.29.0 adds Experiments API to OpenAPI schema and a delete mutation for system API keys.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.29.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.29.0
```
- ›Adds Experiments API endpoints to the OpenAPI schema, making experiment operations formally documented and client-generatable.
- ›Adds a deleteSystemApiKey GraphQL mutation for removing system API keys.
arize-phoenix-v4.28.0 Aug 23, 2024 · issue -375

Phoenix 4.28.0 adds a UI modal for creating users and a refreshed login screen.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.28.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.28.0
```
- ›Adds a 'Create User' modal to the UI for managing user accounts directly from the interface.
- ›Refreshed login screen with improved visual design.
arize-phoenix-v4.27.0 Aug 22, 2024 · issue -375

Phoenix v4.27.0 adds list_experiments client method, clipboard copy for experiment IDs, and onboarding demo projects.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.27.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.27.0
```
└──▷ USE IT
Retrieve all experiments for a dataset to audit or compare runs programmatically.
python
```
import phoenix as px

client = px.Client()
experiments = client.list_experiments()
```
- ›Adds list_experiments client method to programmatically retrieve experiments from the Phoenix client.
- ›Adds a flag to force fixture ingestion on existing databases (in addition to limiting fixture loading to new DBs only).
- ›Adds a minimal login page for auth-enabled deployments.
- ›Enables copying experiment IDs to the clipboard directly from the experiments UI.
- ›Introduces onboarding demo projects to help new users get started quickly.
arize-phoenix-v4.26.0 Aug 21, 2024 · issue -375

Phoenix v4.26.0 adds login/logout routes and a createUser mutation for authentication support.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.26.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.26.0
```
- ›Adds login and logout routes and a createUser mutation to support user authentication workflows.
arize-phoenix-v4.25.0 Aug 21, 2024 · issue -375

Phoenix v4.25.0 adds system API keys with expiry support, a new phoenix.otel package, and a UI for managing system keys.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.25.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.25.0
```
- ›New phoenix.otel package provides a dedicated OpenTelemetry integration layer for Phoenix.
- ›Introduces system API key creation with optional expiry support, manageable via a new system API keys UI.
arize-phoenix-v4.24.0 Aug 15, 2024 · issue -375

Phoenix 4.24.0 adds concurrency control for experiments and separates user vs. system API key resolvers.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.24.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.24.0
```
└──▷ USE IT
Speed up a large experiment run by executing tasks in parallel instead of sequentially.
python
```
run_experiment(dataset, task=my_task, concurrency=10)
```
Run evaluations concurrently to reduce wall-clock time when scoring many experiment results.
python
```
evaluate_experiment(experiment, evaluators=[my_evaluator], concurrency=5)
```
- ›Adds concurrency parameter to run_experiment and evaluate_experiment to control parallel execution of experiments.
- ›Adds user/system API key resolvers, separating user-scoped and system-scoped key management.
- ›Adds user role support in auth, excluding system accounts from user-facing lists.
arize-phoenix-evals-v0.15.0 Aug 15, 2024 · issue -375

arize-phoenix-evals v0.15.0 exposes configuration for the initial rate limit on LLM eval calls.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.15.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.15.0
```
- ›Exposes configuration for the initial rate limit, allowing practitioners to tune request pacing from the start of an eval run.
arize-phoenix-v4.23.0 Aug 13, 2024 · issue -375

Phoenix v4.23.0 adds authentication controls with a settings page and users table in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.23.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.23.0
```
- ›Adds a Settings page to the UI exposing the auth_enabled flag for managing authentication configuration.
- ›Adds a user GraphQL query to retrieve user information via the Phoenix GQL API.
- ›Adds a Users table within the Settings page to view and manage user accounts.
arize-phoenix-v4.22.0 Aug 9, 2024 · issue -375

Phoenix v4.22.0 adds annotation filter actions to span and trace tables in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.22.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.22.0
```
- ›Adds annotation filter actions to span and trace tables, enabling users to filter table views by annotation values directly from the UI.
arize-phoenix-v4.21.0 Aug 8, 2024 · issue -375

Phoenix v4.21.0 adds a call-to-action prompt for span annotations in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.21.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.21.0
```
- ›Adds a call-to-action prompt in the UI to guide users toward creating span annotations.
arize-phoenix-v4.20.0 Aug 6, 2024 · issue -375

Phoenix v4.20.0 adds span annotations to dataset example metadata.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.20.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.20.0
```
- ›Adds span annotations to dataset example metadata, making annotation data available alongside examples in datasets.
arize-phoenix-v4.19.0 Aug 2, 2024 · issue -375

Phoenix v4.19.0 shows all annotations in the annotation summary on the project page header.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.19.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.19.0
```
- ›Displays all annotations in the annotation summary within the project page header for at-a-glance visibility across a project.
arize-phoenix-v4.18.0 Aug 2, 2024 · issue -375

Phoenix v4.18.0 adds annotation summaries, human span annotation editing, and slug support for session.view.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.18.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.18.0
```
- ›Supports a slug parameter in session.view for direct project navigation.
- ›Adds annotation summaries to projects, surfacing aggregate label and score data at the project level.
- ›Enables editing of existing human span annotations in the UI.
arize-phoenix-v4.17.0 Aug 2, 2024 · issue -375

Phoenix v4.17.0 adds a feedback column to spans/traces tables and a condensed trace tree view.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.17.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.17.0
```
- ›Adds a feedback column to the spans and traces tables that surfaces all annotations at a glance.
- ›Introduces a condensed trace tree layout in the UI for a denser view of trace hierarchies.
arize-phoenix-v4.16.0 Jul 30, 2024 · issue -376

Phoenix v4.16.0 adds a feedback tab to span details, a span aside with timing info, and sort ordering for annotation fields.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.16.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.16.0
```
- ›Adds sort order argument to SpanAnnotation and TraceAnnotation fields, enabling ordered retrieval of annotation data.
- ›Adds a feedback tab to span details in the UI, surfacing annotation feedback directly within span inspection.
- ›Adds a span aside panel with timing info and feedback in the trace view.
- ›Adds a trace stream toggle in the preferences context.
- ›Allows retries for annotation insertions when the corresponding span or trace does not yet exist, reducing dropped annotations during ingestion.
arize-phoenix-v4.15.0 Jul 26, 2024 · issue -376

Phoenix 4.15 adds containedInDataset GraphQL field, annotation macros, dataset edit UI, and lazy span loading.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.15.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.15.0
```
- ›Adds containedInDataset boolean field to GraphQL Spans type, enabling queries that filter spans by dataset membership.
- ›Adds annotation macro and filter condition snippets to the project page UI for faster annotation workflows.
- ›Adds dataset edit UI and support for supplying dataset metadata at creation time.
- ›Adds version mismatch checks to warn when client and server versions differ.
- ›Implements lazy loading of spans in the trace UI, enabling performant rendering of large traces.
+1 moreshow less
- ›Annotations now automatically refetch when annotation data changes, keeping the UI in sync without manual refresh.
arize-phoenix-v4.14.0 Jul 23, 2024 · issue -376

Phoenix v4.14.0 adds an annotations UI and extends the evals DSL with an annotations symbol.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.14.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.14.0
```
- ›Extends the evals DSL to accept the annotations symbol, enabling annotation data to be referenced directly in evaluation expressions.
- ›Adds a new annotations UI for viewing and managing span/trace annotations.
arize-phoenix-v4.13.0 Jul 22, 2024 · issue -376

Phoenix v4.13.0 adds a GraphQL resolver to query all annotation names on a project.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.13.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.13.0
```
- ›Adds a GraphQL resolver that returns all annotation names on a project, enabling programmatic discovery of annotation surfaces.
arize-phoenix-v4.12.0 Jul 18, 2024 · issue -376

Arize Phoenix 4.12.0 adds timeout arguments to client methods.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.12.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.12.0
```
- ›Adds timeout arguments to client methods, enabling callers to control request duration limits.
arize-phoenix-v4.11.0 Jul 18, 2024 · issue -376

Phoenix v4.11.0 adds a Guardrail span kind and a GraphQL resolver for span annotations.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.11.0
```
- ›Adds GraphQL resolver for querying annotations on a span, enabling programmatic retrieval of span-level annotation data.
- ›Adds GUARDRAIL span kind type, extending the span taxonomy to cover guardrail components in LLM pipelines.
arize-phoenix-v4.10.0 Jul 16, 2024 · issue -376

Phoenix v4.10.0 adds GraphQL mutations and REST routes for span and trace annotations, plus UI copy of IDs.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.10.0
```
- ›Adds REST routes for span and trace annotations, enabling programmatic annotation of spans and traces via HTTP.
- ›Adds GraphQL mutations for span and trace annotations, exposing annotation operations over the GQL API.
- ›Adds UI ability to copy span and trace IDs directly from the annotations interface.
arize-phoenix-v4.8.0 Jul 8, 2024 · issue -376

Phoenix 4.8.0 adds a REST endpoint to delete datasets from experiments.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.8.0
```
- ›Adds a REST endpoint to delete a dataset in the experiments API.
arize-phoenix-v4.7.0 Jul 4, 2024 · issue -376

Phoenix v4.7.0 adds image rendering for messages in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.7.0
```
- ›Renders images inline within messages in the trace/span UI.
arize-phoenix-v4.6.0 Jul 2, 2024 · issue -376

Phoenix v4.6.0 ships datasets, experiments, and LLM evaluators with new client methods, GraphQL resolvers, and environment-variable auth headers.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.6.0
```
└──▷ USE IT
Decorate a custom function to register it as an evaluator for experiment runs.
python
```
import phoenix as px
from phoenix.evals import create_evaluator

@create_evaluator
def my_evaluator(output, expected):
    return output.strip() == expected.strip()
```
Use reference as an alias for expected in an evaluator to match either naming convention from dataset examples.
python
```
import phoenix as px
from phoenix.evals import create_evaluator

@create_evaluator
def exact_match(output, reference):  # 'reference' is an alias for 'expected'
    return output.strip() == reference.strip()
```
- ›Adds reference as an alias for expected in evaluator argument bindings via **datasets** evaluator function signatures.
- ›Adds get_dataset_by_name client method to retrieve datasets by name.
- ›Adds a client method for appending to existing datasets.
- ›Adds create_evaluator decorator for defining custom evaluators.
- ›Adds built-in LLM evaluators and a relevance evaluator for experiment outputs.
+35 moreshow less
- ›Adds basic evaluators for string experiment outputs.
- ›Adds ability to set auth headers via environment variables.
- ›Adds ability to clear data older than a specified date.
- ›Adds patchDatasetExamples GraphQL mutation to update dataset examples.
- ›Adds compareExperiments GraphQL resolver for side-by-side experiment comparison.
- ›Adds annotations resolver on the DatasetRun GraphQL type.
- ›Adds experiments resolver on the DatasetExample GraphQL type.
- ›Adds runs resolver on the Experiment GraphQL type.
- ›Adds span resolver on the DatasetExample GraphQL type.
- ›Adds project resolver on Span GraphQL type.
- ›Adds GraphQL field linking a trace to its project.
- ›Adds deleteDataset GraphQL mutation and corresponding UI.
- ›Adds deleteExamples GraphQL mutation and corresponding UI.
- ›Adds GraphQL resolver for adding spans to datasets.
- ›Adds GraphQL dataset versions connection.
- ›Adds a JSON endpoint to retrieve dataset versions.
- ›Adds a dataset upload REST endpoint.
- ›Adds JSONL download option (including OpenAI-format JSONL) to the dataset download menu.
- ›Adds CSV download for datasets via the UI.
- ›Adds dataframe transformation support for datasets.
- ›Adds ability to create datasets dynamically from the client.
- ›Adds example and experiment counts to the datasets table.
- ›Adds pagination to the dataset examples table.
- ›Adds sequence numbers for experiments belonging to the same dataset.
- ›Captures traces from experiments and their evaluations.
- ›Posts each experiment/evaluation run result immediately upon completion.
- ›Prints experiment summaries after runs complete.
- ›Prints the URL to the dataset when it is uploaded.
- ›Allows evaluator functions with unrecognized parameters that have default values.
- ›Enforces read-only mode by denying v1 REST routes and GraphQL mutations when readonly.
- ›Adds multi-select on spans/traces tables for bulk dataset addition.
- ›Adds a dataset creation UI and example modal.
- ›Displays the latest dataset version in the UI.
- ›Adds a link to view the source span from a dataset example.
- ›Exposes API playgrounds from the datasets UI.
arize-phoenix-evals-v0.13.0 Jun 26, 2024 · issue -377

Arize Phoenix Evals v0.13.0 adds SQLEvaluator for evaluating SQL query outputs.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.13.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.13.0
```
- ›Adds SQLEvaluator class for evaluating SQL query correctness within the evals library.
arize-phoenix-v4.5.0 Jun 21, 2024 · issue -377

Arize Phoenix 4.5.0 adds SQLEvaluator for SQL-based LLM evaluation.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.5.0
```
- ›Adds SQLEvaluator for evaluating LLM outputs using SQL-based logic.
arize-phoenix-v4.4.0 Jun 10, 2024 · issue -377

Phoenix 4.4.0 adds UI filter snippets for metadata and substring search.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.4.0
```
- ›Adds UI filter snippets for metadata and substring search, making it faster to build trace/span filters without manual query entry.
arize-phoenix-v4.3.0 Jun 7, 2024 · issue -377

Phoenix v4.3.0 adds timing info to llm_classify, serializable execution details, and tool span I/O in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.3.0
```
- ›Adds timing information to llm_classify, enabling per-classification latency tracking.
- ›Execution details are now serializable, allowing results to be persisted or passed between processes.
- ›UI now displays input and output for tool spans when available.
arize-phoenix-evals-v0.12.0 Jun 6, 2024 · issue -377

Phoenix Evals 0.12.0 adds span-level hallucination/QA templates and timing info to llm_classify.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.12.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.12.0
```
- ›Adds timing information to llm_classify results, enabling latency tracking for LLM-based evaluations.
- ›Adds span-level prompt templates for evaluating hallucinations and QA correctness.
arize-phoenix-evals-v0.11.0 May 31, 2024 · issue -378

Phoenix Evals 0.11.0 adds graceful skipping on template mapping errors and serializable execution details.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.11.0
```
- ›Adds the ability to skip evaluations when template mapping errors occur, returning debug information instead of failing the run.
- ›Execution details are now serializable, enabling downstream persistence and inspection of eval run metadata.
arize-phoenix-evals-v0.10.0 May 29, 2024 · issue -378

Phoenix Evals 0.10.0 adds Mistral model support for LLM-based evaluations.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.10.0
```
- ›Supports Mistral as an LLM backend for running evaluations via the arize-phoenix-evals library.
- ›Docker image now runs as root by default, with additional tags available for nonroot and debug image variants.
arize-phoenix-v4.2.0 May 23, 2024 · issue -378

Phoenix Docker image now runs as root by default, with new nonroot and debug image tags available.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.2.0
```
- ›Docker image now runs as root by default, with dedicated image tags for nonroot and debug variants.
arize-phoenix-v4.1.0 May 17, 2024 · issue -378

Arize Phoenix 4.1.0 adds an ASGI root path parameter to the Phoenix server.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.1.0
```
- ›Adds ASGI root path parameter support to the Phoenix server, enabling deployment behind a reverse proxy or sub-path prefix.
arize-phoenix-evals-v0.9.0 May 17, 2024 · issue -378

Phoenix Evals 0.9.0 adds default_headers support for Azure OpenAI models.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.9.0
```
- ›Adds default_headers parameter support to the Azure OpenAI integration, enabling custom HTTP headers on all requests.
arize-phoenix-v4.0.0 May 9, 2024 · issue -378

Phoenix v4.0.0 adds gRPC ingestion, PostgreSQL support, basic auth, OpenAPI UI, new eval templates, and a log_traces method.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v4.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v4.0.0
```
└──▷ USE IT
Send a previously collected TraceDataset to Phoenix for analysis without re-running instrumented code.
python
```
import phoenix as px

px.log_traces(trace_dataset=trace_dataset)
```
- ›Adds log_traces method to send TraceDataset traces directly to Phoenix from Python.
- ›Adds gRPC endpoint for trace ingestion, with a Prometheus interceptor for gRPC metrics.
- ›Adds default limit to GET /v1/spans and corresponding client methods to prevent unbounded responses.
- ›Adds trace and document evaluations to GET /v1/evaluations, including span evaluations.
- ›Adds support for basic auth on the Phoenix server.
+13 moreshow less
- ›Adds support for pagination on the spans GraphQL resolver.
- ›Adds an OpenAPI UI for interactive API exploration.
- ›Adds experimental PostgreSQL support as an alternative to the default SQLite backend.
- ›Adds default_headers support for azure_openai model configurations.
- ›Adds SQL and Code Functionality eval templates for assessing generated code quality.
- ›Adds a user frustration eval template.
- ›Adds OpenTelemetry trace instrumentation for the Phoenix server itself.
- ›Adds a 'last N time range' selector on project and projects pages.
- ›Adds span filtering by span evaluation scores and labels in the UI.
- ›Adds sorting by eval scores and labels in the persistence layer.
- ›Adds a 'clear traces' action to the project UI.
- ›Switches the SQLite engine to sqlean v3.45.1 for improved SQL function coverage.
- ›Updates the API for OpenAPI compliance.
└──▷ BREAKING ON UPGRADE
- !The experimental module (px.experimental) has been removed; any code importing from it will break.
arize-phoenix-v3.24.0 Apr 22, 2024 · issue -379

Phoenix v3.24.0 adds a user frustration evaluator for LLM interaction quality assessment.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v3.24.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v3.24.0
```
- ›Adds a user frustration eval to detect when LLM interactions leave users frustrated.
arize-phoenix-evals-v0.8.0 Apr 22, 2024 · issue -379

Phoenix Evals 0.8.0 adds a user frustration evaluator for detecting negative user sentiment in LLM conversations.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.8.0
```
- ›Adds a user frustration eval to detect signs of user frustration in LLM application traces.
arize-phoenix-v3.23.0 Apr 19, 2024 · issue -379

Arize Phoenix v3.23.0 adds support for default_headers in Azure OpenAI integration.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v3.23.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v3.23.0
```
- ›Adds default_headers parameter support for the azure_openai integration, enabling custom HTTP headers to be sent with Azure OpenAI requests.
arize-phoenix-v3.22.0 Apr 16, 2024 · issue -379

Phoenix v3.22.0 adds log_traces method to send TraceDataset traces directly to Phoenix.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v3.22.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v3.22.0
```
└──▷ USE IT
Push a previously collected TraceDataset into Phoenix for analysis without re-running instrumented code.
python
```
import phoenix as px

dataset = px.TraceDataset(dataframe)
px.log_traces(trace_dataset=dataset)
```
- ›Adds log_traces method that sends a TraceDataset of traces to Phoenix programmatically.
arize-phoenix-evals-v0.7.0 Apr 13, 2024 · issue -379

Phoenix Evals v0.7.0 adds SQL and code functionality evaluation templates.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.7.0
```
- ›Adds SQL and Code Functionality Eval Templates for evaluating SQL queries and code outputs.
arize-phoenix-v3.21.0 Apr 12, 2024 · issue -379

Arize Phoenix v3.21.0 adds SQL and Code functionality eval templates for LLM evaluation.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v3.21.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v3.21.0
```
- ›Adds SQL and Code functionality eval templates for evaluating LLM outputs against structured query and code generation tasks.
arize-phoenix-v3.19.0 Mar 29, 2024 · issue -380

Phoenix v3.19.0 adds trace node and trace evaluations to the GraphQL API.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v3.19.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v3.19.0
```
- ›Adds trace node and trace evaluations to the GraphQL API, enabling querying and evaluation data at the trace level.
arize-phoenix-evals-v0.6.0 Mar 29, 2024 · issue -380

Phoenix Evals now uses the Messages API for Claude on Amazon Bedrock.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.6.0
```
- ›Updates the Bedrock integration to use the Messages API when calling Claude models, enabling compatibility with the newer Claude API surface.
arize-phoenix-v3.17.0 Mar 21, 2024 · issue -380

Arize Phoenix v3.17.0 adds Mistral AI as an eval model and a response_format argument to MistralAIModel.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v3.17.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v3.17.0
```
└──▷ USE IT
Run LLM evals using Mistral AI as the judge model with a structured response format.
python
```
from phoenix.evals import MistralAIModel

model = MistralAIModel(
    model="mistral-large-latest",
    response_format={"type": "json_object"}
)
```
- ›Adds response_format argument to MistralAIModel to control output formatting when using Mistral for evals.
- ›Adds Mistral AI as a supported eval model via MistralAIModel in the evals module.
arize-phoenix-evals-v0.5.0 Mar 20, 2024 · issue -380

Arize Phoenix Evals v0.5.0 adds response_format argument to MistralAIModel.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.5.0
```
└──▷ USE IT
Control the response format when using MistralAI as the backing model for evals.
python
```
from phoenix.evals import MistralAIModel

model = MistralAIModel(response_format={"type": "json_object"})
```
- ›Adds response_format argument to MistralAIModel to control the output format of Mistral AI responses.
arize-phoenix-evals-v0.4.0 Mar 20, 2024 · issue -380

Arize Phoenix Evals v0.4.0 adds Mistral as a supported evaluation model.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.4.0
```
- ›Adds Mistral as a supported model for running evals via the arize-phoenix-evals library.
arize-phoenix-v3.16.0 Mar 15, 2024 · issue -380

Arize Phoenix 3.16.0 adds a delete project UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v3.16.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v3.16.0
```
- ›Adds a UI action to delete projects directly from the interface.
arize-phoenix-v3.15.0 Mar 14, 2024 · issue -380

Phoenix 3.15.0 adds experimental persistent span storage to launch_app() and project archiving/deletion.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v3.15.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v3.15.0
```
- ›Extends launch_app() with experimental span storage configurable via environment variables for storage path and storage type enums.
- ›Adds project archiving and deletion capabilities.
arize-phoenix-v3.14.0 Mar 14, 2024 · issue -380

Phoenix v3.14.0 adds experimental append-only text file span storage.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v3.14.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v3.14.0
```
- ›Introduces experimental span storage backed by append-only text files.

arize-phoenix-v3.13.0 Mar 13, 2024 · issue -380

Arize Phoenix v3.13.0 adds Python 3.12 support.

└──▷ GET THIS VERSION

$ git clone --branch arize-phoenix-v3.13.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v3.13.0

›Adds support for Python 3.12.

arize-phoenix-evals-v0.3.0 Mar 13, 2024 · issue -380

Arize Phoenix Evals v0.3.0 adds Python 3.12 support.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.3.0
```
- ›Adds Python 3.12 support to the phoenix-evals library.
arize-phoenix-v3.12.0 Mar 13, 2024 · issue -380

Arize Phoenix 3.12.0 enables dynamic project switching in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v3.12.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v3.12.0
```
- ›Enables dynamic project switching, allowing users to change the active project without restarting.
arize-phoenix-v3.11.0 Mar 11, 2024 · issue -380

Phoenix v3.11.0 adds a context manager to pause tracing and embeds project inside GraphQL spans.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v3.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v3.11.0
```
- ›Adds a context manager to temporarily pause tracing, allowing selective suppression of trace collection within a code block.
- ›Embeds project as a private attribute inside GraphQL spans, making project context available at the span level.
arize-phoenix-v3.10.0 Mar 9, 2024 · issue -380

Arize Phoenix 3.10.0 adds PHOENIX_PROJECT_NAME env var and smarter default project display.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v3.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v3.10.0
```
└──▷ TRY IT
Route traces to a named project at startup without modifying instrumentation code.
```
$ PHOENIX_PROJECT_NAME=my-rag-pipeline python app.py
```
- ›Adds support for the PHOENIX_PROJECT_NAME environment variable to specify the active project without code changes.
- ›UI now displays the first non-empty project by default instead of a blank project view.
arize-phoenix-v3.9.0 Mar 8, 2024 · issue -380

Arize Phoenix 3.9.0 adds copy-to-clipboard for prompt templates in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v3.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v3.9.0
```
- ›Adds copy-to-clipboard functionality for prompt templates and related content in the UI.
arize-phoenix-v3.8.0 Mar 8, 2024 · issue -380

Phoenix evals graduates from experimental: install standalone via pip install arize-phoenix-evals or bundled with pip install arize-phoenix[evals].
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v3.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v3.8.0
```
- ›Promotes phoenix.evals out of phoenix.experimental.evals — now installable as a standalone package (pip install arize-phoenix-evals) or bundled (pip install arize-phoenix[evals]).
- ›Adds trace count to GraphQL project queries.
└──▷ BREAKING ON UPGRADE
- !Swapping to the new phoenix.evals module (from phoenix.experimental.evals) includes small breaking changes requiring migration work; see MIGRATION.md for details.
- !phoenix.experimental.evals is deprecated and will be removed from Phoenix in approximately one month.
arize-phoenix-evals-v0.2.0 Mar 7, 2024 · issue -380

Phoenix Evals v0.2.0 updates AnthropicModel to use the messages API.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-evals-v0.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-evals-v0.2.0
```
- ›Updates AnthropicModel to use the messages API, replacing the legacy completions interface.
arize-phoenix-v3.7.0 Mar 7, 2024 · issue -380

Arize Phoenix v3.7.0 adds project listing and project node interface capabilities.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v3.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v3.7.0
```
- ›Adds project listing support, enabling users to enumerate and navigate projects.
- ›Adds a project node interface for interacting with individual project nodes.
arize-phoenix-v3.6.0 Mar 6, 2024 · issue -380

Phoenix v3.6.0 adds project-name-scoped span storage and querying plus an auto-expanding side nav.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v3.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v3.6.0
```
- ›Enables storing and querying spans by project name, allowing traces to be scoped and retrieved per project.
- ›Side navigation panel now auto-expands on hover in the UI.
arize-phoenix-v3.5.0 Mar 5, 2024 · issue -380

Phoenix v3.5.0 adds metadata columns to spans/traces tables, a new project-aware side nav, and removes the token processing module from phoenix.evals.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v3.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v3.5.0
```
- ›Removes the token processing module from phoenix.evals, streamlining the evals package surface.
- ›Adds metadata columns to the spans and traces table in the UI for richer trace inspection.
- ›New side navigation with projects view, making multi-project workflows accessible from the main UI.
└──▷ BREAKING ON UPGRADE
- !The token processing module has been removed from phoenix.evals; any code importing it will break on upgrade.
arize-phoenix-v3.4.0 Feb 28, 2024 · issue -381

Arize Phoenix 3.4.0 bridges phoenix.evals into the core phoenix package with a new evals install extra.
└──▷ GET THIS VERSION
```
$ git clone --branch arize-phoenix-v3.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v3.4.0
```
└──▷ TRY IT
Install Phoenix with the new evals extra to get eval utilities bundled under the core phoenix namespace.
```
$ pip install arize-phoenix[evals]
```
- ›Adds phoenix.evals bridge to the phoenix package and introduces an evals extra install option (e.g. pip install arize-phoenix[evals]), making eval utilities directly accessible without a separate import path.
phoenix-v3.3.0 Feb 23, 2024 · issue -381

Phoenix v3.3.0 adds live span streaming and status descriptions in the trace inspector.
└──▷ GET THIS VERSION
```
$ git clone --branch phoenix-v3.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout phoenix-v3.3.0
```
- ›Spans now appear in the UI as soon as they arrive, enabling real-time trace visibility without waiting for a trace to complete.
- ›Displays status description text under trace info in the trace detail view, surfacing error and status context inline.
v3.2.0 Feb 16, 2024 · issue -381

Phoenix v3.2.0 adds log_evaluations to px.Client and displays trace metadata in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch v3.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v3.2.0
```
└──▷ USE IT
Upload evaluation results to a running Phoenix server after running evals on your trace dataset.
python
```
import phoenix as px

client = px.Client()
client.log_evaluations(evals_dataframe)
```
- ›Adds log_evaluations method to px.Client for programmatically uploading evaluation results to a Phoenix server.
- ›Displays span metadata fields in the trace page UI, making trace context visible without leaving the trace view.
v3.1.0 Feb 15, 2024 · issue -381

Arize Phoenix v3.1.0 adds metadata-value filtering for spans in the trace UI.
└──▷ GET THIS VERSION
```
$ git clone --branch v3.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v3.1.0
```
- ›Enables filtering spans by metadata values in the trace explorer.
v3.0.0 Feb 9, 2024 · issue -381

Phoenix v3.0.0 replaces its own tracers with OpenInference instrumentors for LLM observability.
└──▷ GET THIS VERSION
```
$ git clone --branch v3.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v3.0.0
```
- ›Replaces Phoenix-native tracers with OpenInference instrumentors for tracing LLM applications.
└──▷ BREAKING ON UPGRADE
- !Phoenix tracers are removed and replaced with OpenInference instrumentors — any code using Phoenix's built-in tracers will break on upgrade; see the 2.x-to-3.0.0 migration guide at https://github.com/Arize-ai/phoenix/blob/main/MIGRATION.md.
v2.11.0 Feb 9, 2024 · issue -381

Phoenix v2.11.0 adds an hour-level time range option to the UI for finer trace inspection.
└──▷ GET THIS VERSION
```
$ git clone --branch v2.11.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v2.11.0
```
- ›Adds an hour time range selector to the UI, enabling finer-grained filtering of traces and spans.
v2.10.0 Feb 7, 2024 · issue -381

Arize Phoenix v2.10.0 adds search by text and ID in the embeddings selection view.
└──▷ GET THIS VERSION
```
$ git clone --branch v2.10.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v2.10.0
```
- ›Adds search by text and ID on selection in the embeddings view.
v2.9.0 Feb 5, 2024 · issue -381

Phoenix client gains four new data-retrieval methods for spans, traces, and evaluations.
└──▷ GET THIS VERSION
```
$ git clone --branch v2.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v2.9.0
```
└──▷ USE IT
Pull all evaluations from a running Phoenix session into a script for offline analysis or reporting.
python
```
import phoenix as px

client = px.Client()
evaluations = client.get_evaluations()
print(evaluations)
```
Query spans matching specific criteria and load them as a pandas DataFrame for downstream ML or inspection workflows.
python
```
import phoenix as px

client = px.Client()
df = client.get_spans_dataframe()
print(df.head())
```
- ›Adds get_evaluations() and get_trace_dataset() methods to the Phoenix client for programmatic retrieval of evaluation results and trace datasets.
- ›Adds get_spans_dataframe() and query_spans() methods to the Phoenix client for querying and retrieving spans as a dataframe.
v2.7.0 Jan 24, 2024 · issue -382

Arize Phoenix v2.7.0 adds PHOENIX_WORKING_DIR env var to configure the persistence working directory.
└──▷ GET THIS VERSION
```
$ git clone --branch v2.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v2.7.0
```
└──▷ TRY IT
Set a custom working directory before launching Phoenix so traces and data persist across restarts.
```
$ export PHOENIX_WORKING_DIR=/data/phoenix
python -m phoenix.server.main serve
```
- ›Adds PHOENIX_WORKING_DIR environment variable to configure Phoenix's working directory for persistent storage.
v2.6.0 Jan 23, 2024 · issue -382

Phoenix v2.6.0 adds TraceDataset save/load, session eval exports, and GPT-4 Turbo context window support.
└──▷ GET THIS VERSION
```
$ git clone --branch v2.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v2.6.0
```
└──▷ USE IT
Launch Phoenix with existing evaluations already loaded so results are visible immediately on startup.
python
```
import phoenix as px

session = px.launch_app(evaluations=[my_eval_dataframe])
```
- ›Adds get_trace_dataset method to session objects to retrieve trace data programmatically.
- ›Adds ability to save and load TraceDataset objects for persistence and reuse across sessions.
- ›Adds eval export support for sessions, enabling evaluation results to be exported directly from a session.
- ›Supports launching Phoenix with pre-loaded evaluations at startup.
- ›Expands GPT-4 Turbo context window size support in the evals module.
v2.5.0 Jan 16, 2024 · issue -382

Arize Phoenix v2.5.0 adds Databricks notebook support.
└──▷ GET THIS VERSION
```
$ git clone --branch v2.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v2.5.0
```
- ›Adds support for running Phoenix inside Databricks notebooks.
v2.4.0 Jan 10, 2024 · issue -382

Phoenix v2.4.0 adds persistence for span evaluations and UI filter condition snippets.
└──▷ GET THIS VERSION
```
$ git clone --branch v2.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v2.4.0
```
- ›Adds persistence for span evaluations, allowing evaluation results to survive across sessions.
- ›Adds filter condition snippets in the UI to accelerate building trace/span filter queries.
v2.3.0 Jan 8, 2024 · issue -382

Arize Phoenix v2.3.0 ships evaluator enhancements for LLM trace assessment.
└──▷ GET THIS VERSION
```
$ git clone --branch v2.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v2.3.0
```
- ›Enhances evaluators for LLM trace assessment.
v2.2.0 Dec 22, 2023 · issue -383

Phoenix v2.2.0 adds tracing support for Google Gemini via Vertex SDK and the first-party Anthropic Python SDK.
└──▷ GET THIS VERSION
```
$ git clone --branch v2.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v2.2.0
```
- ›Adds support for Google's Gemini models via the Vertex Python SDK.
- ›Adds support for the first-party Anthropic Python SDK.
v2.1.0 Dec 21, 2023 · issue -383

Phoenix v2.1.0 adds a v1/traces HTTP endpoint, function-calling evals, and criteria-based evaluator instantiation.
└──▷ GET THIS VERSION
```
$ git clone --branch v2.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v2.1.0
```
└──▷ USE IT
Run LLM-based evaluations with function calling enabled so the model returns structured verdicts instead of free-form text.
python
```
import phoenix.evals as evals

results = evals.run_evals(
    dataframe=df,
    evaluators=[evals.QAEvaluator(model=model)],
    provide_explanation=True,
    use_function_calling_if_available=True,
)
```
- ›Adds v1/traces HTTP endpoint to accept ExportTraceServiceRequest payloads, enabling OTLP-compatible trace ingestion over HTTP.
- ›Supports function calling for run_evals, allowing LLM evaluators to use structured function-call outputs during evaluation.
- ›Enables instantiating evaluators by criteria, letting practitioners define custom evaluation criteria directly rather than using only preset evaluators.
- ›Adds retrieval summary to the traces UI header for at-a-glance retrieval metrics.
- ›Adds evaluation summary to the traces UI header for at-a-glance eval metrics.
v2.0.0 Dec 20, 2023 · issue -383

Phoenix v2.0.0 adds async llm_generate, multi-eval parallelism, explanation support, and OpenAI streaming tool calls.
└──▷ GET THIS VERSION
```
$ git clone --branch v2.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v2.0.0
```
- ›Adds async submission to llm_generate, enabling non-blocking LLM generation calls.
- ›Adds explanation support to run_evals, allowing evaluations to return rationale alongside labels.
- ›Supports running multiple evals at once via run_evals, enabling parallel evaluation pipelines.
- ›Updates llm_classify and llm_generate interfaces with revised calling conventions.
- ›Adds evaluation column selectors for more granular control over which columns feed into evaluations.
+1 moreshow less
- ›Adds support for OpenAI streaming tool calls in tracing.
└──▷ BREAKING ON UPGRADE
- !The interfaces for llm_classify and llm_generate have changed; existing call sites must be updated to match the new signatures.
v1.9.0 Dec 11, 2023 · issue -383

Arize Phoenix v1.9.0 adds automatic retries for Amazon Bedrock calls.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.9.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v1.9.0
```
- ›Adds automatic retry support for Amazon Bedrock LLM calls, improving resilience against transient API failures.
v1.8.0 Dec 10, 2023 · issue -383

Phoenix v1.8.0 adds audio embedding support and OpenAI streaming function call message tracing.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v1.8.0
```
- ›Supports audio modality for embeddings, enabling audio data to be visualized and analyzed in the embeddings view.
- ›Supports OpenAI streaming function call messages, enabling tracing of streamed function-call interactions in LLM workflows.
v1.7.0 Dec 9, 2023 · issue -383

Phoenix v1.7.0 adds streaming instrumentation for LlamaIndex and OpenAI async, plus span-to-dataframe querying.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v1.7.0
```
- ›Adds px.Client().query_spans() (or equivalent trace query API) to pull spans directly into pandas DataFrames for offline analysis.
- ›Adds instrumentation for LlamaIndex streaming responses, capturing trace spans across streamed LLM calls.
- ›Adds instrumentation for OpenAI async streaming, enabling tracing of async streamed completions.
v1.6.0 Dec 8, 2023 · issue -383

Phoenix v1.6.0 adds OpenAI streaming instrumentation, document retrieval metrics, and filterable evaluation summaries in the trace UI.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v1.6.0
```
- ›Adds GraphQL query for document evaluation summary, enabling programmatic retrieval of per-document evaluation metrics.
- ›Adds instrumentation support for OpenAI synchronous streaming, capturing streaming spans in traces.
- ›OpenAI streaming spans now appear in the Phoenix UI alongside other trace data.
- ›Displays document retrieval metrics directly on the trace details panel.
- ›Adds filterable span and document evaluation summaries in the traces view.
v1.5.0 Dec 6, 2023 · issue -383

Phoenix v1.5.0 adds Human vs AI evals, span eval filtering, document retrieval metrics, and async OpenAI instrumentation.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.5.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v1.5.0
```
- ›Adds server-side span filtering by evaluation result values in the traces UI, enabling targeted review of spans that meet specific eval criteria.
- ›Adds evaluation annotations on traces to associate spans with eval metrics, surfacing eval scores and labels directly alongside trace data.
- ›Adds span evaluation summary with aggregation metrics (scores and labels) across spans in the trace and span tables.
- ›Adds document retrieval metrics derived from document evaluation scores, visible in trace and span tables.
- ›Adds semantic conventions for the tool_calls array in OpenAI ChatCompletion messages.
+2 moreshow less
- ›Supports asynchronous chat completions in the OpenAI instrumentation layer.
- ›Introduces Human vs AI Evals capability for comparing human-provided labels against model-generated evaluations.
v1.4.0 Nov 30, 2023 · issue -384

Phoenix v1.4.0 propagates error status codes to parent spans for better trace exception visibility.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.4.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v1.4.0
```
- ›Propagates error status codes to parent spans, making trace exceptions visible at higher levels of the span hierarchy.
v1.3.0 Nov 30, 2023 · issue -384

Phoenix v1.3.0 adds OpenAI rate limiting, async eval submission, configurable trace exporter endpoint, and richer evaluation UI across spans and documents.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v1.3.0
```
- ›Adds configurable endpoint for the trace exporter, letting users point spans at a custom collector address.
- ›Adds OpenAI rate limiting for eval calls, preventing API quota exhaustion during large evaluation runs.
- ›Implements asynchronous submission for OpenAI evals, enabling non-blocking evaluation workflows.
- ›Adds a reference link correctness evaluation prompt template for assessing retrieval quality.
- ›Shows span evaluations in the trace details slideout, surfacing eval scores and labels inline with trace data.
+4 moreshow less
- ›Displays document evaluations alongside their documents in the traces UI.
- ›Adds server-side sorting of spans by evaluation result (score or label) in the traces table.
- ›Shows all evaluations in the traces table view.
- ›Adds a trace page header displaying latency, status, and evaluations at a glance.
v1.2.0 Nov 17, 2023 · issue -384

Arize Phoenix v1.2.0 adds LiteLLM model support for evals, partial result recovery, a Dockerfile, and SageMaker notebook support.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.2.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v1.2.0
```
- ›Adds LiteLLM model support for evals, enabling any LiteLLM-supported model to be used as the evaluation LLM.
- ›Evals now return partial results when the LLM function is interrupted mid-run, preserving completed evaluation outputs.
- ›Adds a Dockerfile for containerized deployment of Phoenix.
- ›Adds SageMaker notebook support, enabling Phoenix to run in Amazon SageMaker environments.
v1.1.0 Nov 14, 2023 · issue -384

Phoenix v1.1.0 adds explanation output to evals and an output_parser argument to llm_generate.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v1.1.0
```
└──▷ USE IT
Parse structured results from llm_generate in a single step instead of post-processing raw LLM text.
python
```
llm_generate(dataframe=df, template=my_template, model=model, output_parser=my_parser)
```
- ›Adds output_parser argument to llm_generate for custom parsing of LLM responses during eval generation.
- ›Evals now support explanations, surfacing model reasoning alongside evaluation labels.
v1.0.0 Nov 10, 2023 · issue -384

Arize Phoenix v1.0.0 adds OpenAI 1.0 SDK support, with a breaking change for existing model integrations.
└──▷ GET THIS VERSION
```
$ git clone --branch v1.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v1.0.0
```
- ›Adds support for the OpenAI 1.0 SDK in the models integration layer.
└──▷ BREAKING ON UPGRADE
- !The models OpenAI integration now requires OpenAI SDK 1.0 — existing setups using an older OpenAI SDK version will break on upgrade.
v0.1.0 Nov 8, 2023 · issue -384

Arize Phoenix v0.1.0 adds long-context evaluators with map-reduce and refine patterns, plus span table column visibility controls.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.1.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.1.0
```
- ›Adds long-context evaluators supporting map-reduce and refine patterns for evaluating LLM outputs that exceed standard context windows.
- ›Adds column visibility controls to the span table in the traces UI, letting practitioners show or hide columns.
v0.0.51 Oct 31, 2023 · issue -385

Phoenix v0.0.51: llm_classify gains function-calling output constraints and now returns a dataframe.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.51 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.51
```
- ›In llm_classify, uses function calling to constrain LLM outputs when the model supports it, improving classification reliability.
- ›llm_classify now returns a dataframe instead of its previous return type, enabling direct pandas-style downstream analysis of eval results.
└──▷ BREAKING ON UPGRADE
- !llm_classify now returns a dataframe — code that expected the previous return type will break on upgrade.
v0.0.50 Oct 28, 2023 · issue -385

Phoenix v0.0.50 adds RAG eval relevancy conventions, protected LangChain callbacks, and a light UI theme.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.50 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.50
```
- ›Adds eval relevancy conventions for RAG pipelines.
- ›Adds protection for LangChain callbacks to prevent tracing errors from interrupting application flow.
- ›Introduces a light theme option for the Phoenix UI.
v0.0.49 Oct 16, 2023 · issue -385

Phoenix v0.0.49 adds multiclass classification support, video URL embeddings, and raises default eval retry count to 20.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.49 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.49
```
- ›Raises the default retry count for evals to 20 for more resilient evaluation runs.
- ›Supports video URLs for linkToData in embedding visualizations.
- ›Adds support for multiclass classification datasets.
v0.0.45 Oct 13, 2023 · issue -385

Phoenix v0.0.45 adds reranker span support, trace search/filtering, verbose eval mode, and gpt-3.5-turbo-instruct for evals.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.45 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.45
```
- ›Adds reranker span kind to LLM Traces, enabling visibility into document reranking steps in RAG pipelines.
- ›Adds gpt-3.5-turbo-instruct as a supported model in OpenAIModel for LLM evaluations.
- ›Adds search and filtering for traces and spans, including filtering on span IO content and computed values such as latency and token counts.
- ›Adds verbose mode for LLM evaluations to surface real-time progress and aid debugging of eval runs.
- ›Adds a general-purpose LlamaIndex debug callback handler for tracing LlamaIndex applications.
v0.0.44 Oct 6, 2023 · issue -385

Phoenix v0.0.44 adds live-updating trace UI, OpenAI and Bedrock instrumentors, Azure params, and exporter startup warnings.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.44 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.44
```
└──▷ USE IT
Trace OpenAI chat completion calls automatically by instrumenting the OpenAI client before running your app.
python
```
from phoenix.trace.openai import OpenAIInstrumentor

OpenAIInstrumentor().instrument()
```
- ›Adds Azure parameters to OpenAIModel for evals, enabling Azure OpenAI endpoints as an eval backend.
- ›Adds Amazon Bedrock model support to the evals framework via a new BedrockModel integration.
- ›Adds a new OpenAI instrumentor with chat completions support for tracing OpenAI calls.
- ›Adds gql validate_span_filter_condition to the tracing GraphQL API for validating span filter conditions.
- ›Adds default UMAP parameters in launch_app() so embeddings visualizations work out of the box without manual tuning.
+2 moreshow less
- ›Adds live-updating UI and a stream on/off switch to the trace view.
- ›Warns users at exporter initialization if Phoenix is not running, surfacing misconfiguration earlier.
v0.0.42 Sep 29, 2023 · issue -386

Phoenix v0.0.42 adds prompt template UI, latency percentiles, token methods, and broader eval input types.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.42 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.42
```
- ›Adds token methods to OpenAIModel via a new processing functions file.
- ›Displays latency P50 and P99 percentiles in the tracing page header.
- ›Enhances input types accepted by run_relevance_eval for greater flexibility.
- ›Shows the model name in the LLM span info within the trace UI.
- ›Adds a prompt template UI to the trace span details view.
v0.0.41 Sep 27, 2023 · issue -386

Phoenix v0.0.41 adds document metadata visibility in the trace view.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.41 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.41
```
- ›Displays document metadata in the trace UI, giving practitioners direct visibility into retrieval context during trace inspection.
v0.0.40 Sep 26, 2023 · issue -386

Phoenix v0.0.40 adds templating semantic conventions for LLM spans and a LangChainInstrumentor for nested chains.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.40 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.40
```
└──▷ USE IT
Instrument a nested LangChain pipeline to capture structured traces in Phoenix.
python
```
from phoenix.trace.langchain import LangChainInstrumentor

LangChainInstrumentor().instrument()
```
- ›Adds LangChainInstrumentor for tracing nested LangChain chains as structured spans.
- ›Adds templating semantic conventions to LLM spans, enabling structured capture of prompt template metadata.
v0.0.39 Sep 26, 2023 · issue -386

Phoenix v0.0.39 adds VertexAI model support, new LLM message attributes, and error handling for llama-index traces.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.39 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.39
```
- ›Adds LLM_OUTPUT_MESSAGES attribute and renames LLM_MESSAGES to LLM_INPUT_MESSAGES to distinguish input and output message spans.
- ›Adds VertexAI model implementation for use as an evaluation model.
- ›Adds error handling attributes for llama-index instrumentation.
- ›Displays total token count in the trace page header.
└──▷ BREAKING ON UPGRADE
- !The LLM_MESSAGES attribute is renamed to LLM_INPUT_MESSAGES; any code or downstream processing referencing LLM_MESSAGES will stop matching spans after this upgrade.
v0.0.38 Sep 24, 2023 · issue -386

Phoenix v0.0.38 adds LangChain LLM message attributes, agent span kind for LangChain, and slow-span highlighting in the tracing UI.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.38 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.38
```
- ›Adds agent span kind classification for LangChain traces, surfacing agent-type spans distinctly in the tracing view.
- ›Captures LangChain LLM message attributes in trace spans, giving practitioners visibility into the full message structure exchanged with LLMs.
- ›Highlights slow spans in the tracing UI to make latency outliers immediately visible during trace inspection.
- ›Makes trace rows clickable in the tracing UI for faster drill-down into individual span details.
v0.0.37 Sep 18, 2023 · issue -386

Phoenix v0.0.37 adds LangChain prompt semantic conventions, a tool details UI panel, and a prompts list view, plus moves tracing out of experimental.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.37 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.37
```
- ›Adds LangChain LLM prompts semantic convention support for richer span attribution in LangChain traces.
- ›New tool details UI panel surfaces tool call information directly in the tracing interface.
- ›New prompts list view in the UI lets practitioners browse and inspect captured prompts.
- ›Tracing is promoted out of experimental status, signaling production readiness.
v0.0.33 Sep 15, 2023 · issue -386

Phoenix v0.0.33 ships full LLM tracing with LangChain/LlamaIndex callbacks, binary evals, hallucination detection, and a rich spans/traces UI.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.33 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.33
```
└──▷ USE IT
Convert raw spans collected during an LLM run into a TraceDataset for analysis or export.
python
```
from phoenix.trace.trace_dataset import TraceDataset

dataset = TraceDataset.from_spans(spans)
```
- ›Adds host parameter to launch_app for controlling the bind address when starting the Phoenix server.
- ›Adds TraceDataset.from_spans class method to construct a dataset directly from collected spans.
- ›Adds run_eval function for running evaluations against a dataset.
- ›Adds llm_eval_binary function for binary (pass/fail) LLM evaluations using an OpenAI model.
- ›Adds hallucination eval capability via a new dedicated eval type.
+23 moreshow less
- ›Adds launch_app support for launching with traces pre-loaded.
- ›Adds experimental LangChain tracer callback for capturing LangChain chain/LLM/tool spans into Phoenix tracing.
- ›Adds LlamaIndex callback skeleton and agent function-call callback support for tracing LlamaIndex pipelines including agent spans.
- ›Adds semantic conventions for input/output span attributes, prompt templates, token counts, retrieval documents, tool attributes, and embedding attributes — covering both LangChain and LlamaIndex implementations.
- ›Adds agent span kind to the tracing span-kind enum.
- ›Adds span streaming, filtering, and exporting via the GraphQL API.
- ›Adds GraphQL query to filter spans by trace ID.
- ›Adds GraphQL fields for span attributes as JSON string, span input/output, token counts, cumulative token counts, descendant spans list, span count, and timestamp bookends.
- ›Adds tracing overview stats panel to the UI.
- ›Adds exception event capture and highlighting in span details.
- ›Adds attributes to span events in the tracing data model.
- ›Adds nested attributes support in the GraphQL tracing schema.
- ›Adds a spans table UI with sorting and pagination.
- ›Adds a traces table UI.
- ›Adds trace detail and tree-view UI for visualising parent/child span relationships.
- ›Adds span status display in the GraphQL API and spans table UI.
- ›Adds LLM messages view in span details UI.
- ›Adds LLM message attributes to the LangChain and LlamaIndex callbacks.
- ›Adds LLM invocation parameter and token-count attributes to the LangChain tracer.
- ›Adds token count tracking to the LlamaIndex callback.
- ›Adds latency column to the spans table UI.
- ›Adds a dataset download function for pulling evaluation datasets.
- ›Adds GraphQL time bookend and sorting for spans.
v0.0.31 Aug 4, 2023 · issue -387

Phoenix v0.0.31 adds an experimental sub-module, point-scale slider for embeddings, and early tracing foundations.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.31 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.31
```
- ›Adds experimental sub-module to the Phoenix library, refactoring related notebooks around it.
- ›Moves the single-model view to the /model route in the UI.
- ›Adds a point scale slider to the embeddings view for adjusting visualization density.
- ›Defines an initial span schema for tracing support.
- ›Introduces a strawman tracer implementation as a foundation for LLM call tracing.
0.0.30 Jul 26, 2023 · issue -388

Arize Phoenix 0.0.30 adds RAG retrieval troubleshooting with corpus datasets, distance metrics, and visual retrieval overlays in the point cloud.
└──▷ GET THIS VERSION
```
$ git clone --branch 0.0.30 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout 0.0.30
```
└──▷ USE IT
Construct a Phoenix dataset directly from an OpenInference-formatted dataframe, skipping manual schema wiring.
python
```
import phoenix as px

ds = px.Dataset.from_open_inference(open_inference_df)
px.launch_app(primary=ds)
```
- ›Adds phoenix.Dataset.from_open_inference class method to construct datasets directly from OpenInference-formatted data.
- ›Supports passing a knowledge base as a corpus dataset so Phoenix can inspect how a retrieval system queries for relevant documents in a vector store.
- ›Automatically computes Euclidean distance between query and document embeddings as a retrieval metric, surfaced as a time-series view.
- ›Renders retrieval connection lines in the UMAP point cloud, visually overlaying which vector store clusters the retriever pulls from.
- ›Displays corpus points as octahedrons in the 3D point cloud to distinguish them from primary dataset points.
+4 moreshow less
- ›Shows per-query corpus coverage percentage ('% query') in the embeddings panel.
- ›Surfaces retrieved documents and their distances in the slide-over detail panel.
- ›Accepts ISO 8601 timestamps as valid input across datasets.
- ›Allows string-only responses (without an accompanying embedding) to be ingested.
v0.0.28 Jul 11, 2023 · issue -388

Arize Phoenix v0.0.28 adds a relationships schema and parsing for retrieval data.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.28 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.28
```
- ›Adds relationships schema and parsing for retrieval data, enabling structured representation of retrieval relationships in Phoenix.
v0.0.27 Jun 30, 2023 · issue -389

Arize Phoenix v0.0.27 lets you export all embedding clusters to notebook or Parquet file directly from the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.27 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.27
```
- ›Adds UI export of all embedding clusters to notebook or Parquet file, enabling downstream exploration outside Phoenix.
v0.0.26 Jun 28, 2023 · issue -389

Arize Phoenix v0.0.26 adds interactive tooltips to the point-cloud embedding visualization.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.26 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.26
```
- ›Adds interactive tooltips to the point-cloud view, surfacing data point details on hover during embedding exploration.
v0.0.25 Jun 26, 2023 · issue -389

Arize Phoenix v0.0.25 adds multi-cluster export via GraphQL
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.25 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.25
```
- ›Enables exporting multiple clusters simultaneously via the GraphQL API.
v0.0.24 Jun 14, 2023 · issue -389

Phoenix v0.0.24 adds cluster-level performance and data quality metrics including accuracy_score and ad-hoc numeric averages via GraphQL.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.24 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.24
```
- ›Adds a standalone clusters endpoint to the GraphQL API, enabling programmatic retrieval of cluster data outside the embedding projection UI.
- ›Adds prediction_id to GraphQL event metadata and surfaces it in selection details, making it easier to trace individual predictions back to source records.
- ›Adds accuracy_score as a model performance metric on embedding clusters, letting practitioners sort clusters by worst accuracy to surface pockets of bad predictions.
- ›Adds cluster-level data quality / custom metrics: calculates the average of any numeric feature, tag, prediction, or actual value (e.g., precision@k, rouge score, LLM-assisted eval scores) per cluster.
- ›Adds a metric selector UI for embeddings, allowing users to switch between performance and data quality metrics on the cluster view.
+3 moreshow less
- ›Adds cluster sorting by metric value in the embeddings UI, so the worst-performing or lowest-quality clusters rise to the top.
- ›Adds accuracy timeseries tracking for clusters, extending the performance metric beyond point-in-time analysis.
- ›Adds data_type filter support on dimensions, enabling finer control over which features are included in analysis.
0.0.23 Jun 2, 2023 · issue -389

Phoenix 0.0.23 adds interactive HDBSCAN tuning, dimension filters on the GraphQL model endpoint, and dataset visibility in the embeddings table.
└──▷ GET THIS VERSION
```
$ git clone --branch 0.0.23 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout 0.0.23
```
- ›Adds dimension filters to the GraphQL model endpoint, enabling more targeted embedding and model data queries.
- ›Adds interactive HDBSCAN parameter tuning in the embeddings UI, letting practitioners dynamically adjust clustering without code changes.
- ›Shows the source dataset column in the embeddings point-selection table, making it easier to trace points back to their origin dataset.
v0.0.20 May 24, 2023 · issue -390

Phoenix v0.0.20 adds Dimension Details for tabular data with drift, histogram, and quantile charts via new GraphQL endpoints.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.20 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.20
```
- ›Adds GraphQL endpoint for histogram data to support dimension-level distribution analysis.
- ›Adds quantile metrics to GraphQL endpoints for data quality inspection of tabular features and tags.
- ›Adds GraphQL endpoint for HDBSCAN clustering results.
- ›New dimension segments bar chart in the UI for visualizing how data splits across categories within a dimension.
- ›New drift breakdown chart in the UI to isolate differences in dimension segment distributions between datasets.
+3 moreshow less
- ›New quantiles stream chart in the UI for tracking quantile metrics over time per dimension.
- ›Shows reference dataset data quality stats alongside primary dataset in dimension details view.
- ›Supports ISO 8601 formatted strings in the timestamp column, broadening accepted input formats.
v0.0.19 May 10, 2023 · issue -390

Phoenix v0.0.19 raises embedding dataset sample size to 10,000 and adds dataset role to GraphQL data quality metric endpoints.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.19 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.19
```
- ›Adds dataset role parameter to GraphQL endpoints for data quality metrics, enabling per-dataset filtering in queries.
- ›Raises the embedding dataset sample size maximum to 10,000 (up from the previous limit).
- ›Adds a dimension details route to the UI for inspecting individual dimension data.
- ›Distinguishes discrete vs. continuous data in GraphQL responses, enabling appropriate rendering of each data type.
- ›Introduces a basic segment interface in GraphQL for segmented data queries.
+1 moreshow less
- ›Adds time formatting on the x-axis of charts, with a move to a time-based axis for temporal data visualization.
v0.0.18 Apr 27, 2023 · issue -391

Phoenix v0.0.18 adds cluster counts in tab headers and human-friendly dataset names in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.18 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.18
```
- ›Displays cluster count directly in the tab header for quick at-a-glance visibility.
- ›Shows human-friendly names for datasets in the UI instead of raw identifiers.
v0.0.15 Apr 20, 2023 · issue -391

Arize Phoenix v0.0.15 adds generative LLM support with prompt and response embedding column configuration.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.15 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.15
```
└──▷ USE IT
Configure a generative LLM dataset schema to track prompt and response embeddings alongside a quality metric like ROUGE score.
python
```
Schema(
    tag_column_names=[
        "rouge_score",
    ],
    prompt_column_names=EmbeddingColumnNames(
        vector_column_name="document_vector", raw_data_column_name="document"
    ),
    response_column_names=EmbeddingColumnNames(
        vector_column_name="summary_vector", raw_data_column_name="summary"
    ),
)
```
- ›Adds prompt_column_names and response_column_names fields to Schema, each accepting EmbeddingColumnNames with vector_column_name and raw_data_column_name, enabling prompt/response pair ingestion for generative LLM workflows.
- ›Adds tag_column_names list field to Schema for attaching scalar metric columns (e.g. rouge scores) to LLM dataset entries.
v.0.0.14 Apr 20, 2023 · issue -391

Arize Phoenix v0.0.14 adds native LLM prompt/response pair support via prompt_column_names and response_column_names in Schema.
└──▷ GET THIS VERSION
```
$ git clone --branch v.0.0.14 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v.0.0.14
```
└──▷ USE IT
Define a schema for an LLM summarization dataset so Phoenix can surface prompt/response pairs in the embeddings explorer and event details.
python
```
Schema(
    tag_column_names=[
        "bleu_score",
        "rouge_score",
    ],
    prompt_column_names=EmbeddingColumnNames(
        vector_column_name="document_vector", raw_data_column_name="document"
    ),
    response_column_names=EmbeddingColumnNames(
        vector_column_name="summary_vector", raw_data_column_name="summary"
    ),
)
```
- ›Adds prompt_column_names and response_column_names parameters to Schema, each accepting an EmbeddingColumnNames with vector_column_name and raw_data_column_name, to natively represent LLM prompt/response pairs in datasets.
- ›Renders grid previews of LLM prompts and responses in the embeddings UI.
- ›Displays prompt and response content in the event details panel for LLM inference events.
- ›Shows prompt/response pairs in the selection table and on inference event views.
v0.0.12 Apr 12, 2023 · issue -391

Phoenix v0.0.12 improves the embeddings grid view with size controls and multi-modal output support.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.12 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.12
```
- ›Adds multi-modal output display and size improvements to the embeddings grid view.
v0.0.10 Apr 8, 2023 · issue -391

Phoenix v0.0.10 runs uvicorn in a thread by default, cutting boot time by an order of magnitude.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.10 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.10
```
- ›Runs uvicorn in a thread rather than a separate process by default, making boot time an order of magnitude faster.
v0.0.9 Apr 5, 2023 · issue -391

Phoenix v0.0.9 adds resizable selection table cells and contextual help for hyperparameters in the UI.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.9 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.9
```
- ›Adds contextual help tooltips for hyperparameters in the UI.
- ›Makes selection table cells resizable in the UI.
- ›Adds custom scrollbar styles via Modernizr for improved UI rendering.
v0.0.8 Mar 31, 2023 · issue -392

Phoenix v0.0.8 adds route-level error handling for more resilient UI navigation.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.8 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.8
```
- ›Adds route-level error handling to prevent full-app failures when individual UI routes encounter errors.
v0.0.7 Mar 29, 2023 · issue -392

Phoenix v0.0.7 adds Parquet-to-DataFrame export and a cluster export UI for embeddings.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.7 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.7
```
- ›Adds ability to read exported Parquet files directly into a pd.DataFrame.
- ›Adds a cluster export UI for embeddings visualizations.
v0.0.6 Mar 29, 2023 · issue -392

Phoenix v0.0.6 adds Parquet export with download, Arize schema support, timestamp normalization, and new embedding timeseries UI.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.6 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.6
```
- ›Supports Arize schema when provided, enabling datasets already described in Arize's schema format to be used directly with Phoenix.
- ›Adds export to Parquet format, with support for downloading the exported Parquet files from the session.
- ›Normalizes timestamps automatically across ingested datasets.
- ›New single-dataset timeseries graph and selection view for embeddings in the UI.
- ›Adds column formatting and time range selectors to the model view in the UI.
v0.0.2rc5 Mar 16, 2023 · issue -392

Phoenix v0.0.2rc5 adds app and docs links on launch and cleans up tooltip styles.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.2rc5 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.2rc5
```
- ›Adds links to the app and documentation on launch.
- ›Cleans up tooltip styles in the UI.
v0.0.2rc4 Mar 14, 2023 · issue -392

Phoenix v0.0.2rc4 adds cluster drift scoring, drift ratio display, granular drift timeseries, and selection details to the point cloud UI.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.2rc4 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.2rc4
```
- ›Adds cluster drift score computation to quantify embedding drift at the cluster level.
- ›Adds drift ratio display alongside cluster drift scores for contextual comparison.
- ›Adds granularity control for drift timeseries, enabling finer or coarser time bucketing in drift charts.
- ›Adds selection details panel showing metadata for points selected in the point cloud.
- ›Adds alternative point cloud coloring strategies for single-dataset (no reference) views.
v0.0.2rc3 Mar 8, 2023 · issue -392

Arize Phoenix v0.0.2rc3 adds dataset visibility toggles, color settings, DQ time series, and a selection gallery to the embedding UI.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.2rc3 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.2rc3
```
- ›Adds dataset visibility toggles to the UI, letting users show or hide individual datasets in the embedding view.
- ›Adds color visibility settings so users can control per-category or per-dataset coloring in visualizations.
- ›Adds min, max, and count metrics to data quality (DQ) reporting.
- ›Adds data quality time series charts to the embedding view.
- ›Adds a GraphQL resolver for unique values of string dimensions, enabling filtered and faceted analysis.
+2 moreshow less
- ›Adds a selection gallery for inspecting selected points from the embedding visualization.
- ›Adds top-level imports to the Python library for easier access to core Phoenix objects.
v0.0.2rc1 Feb 28, 2023 · issue -393

Arize Phoenix v0.0.2rc1 adds time-series graphs, timeslice selection, dataset time presets, record-level retrieval, and embedding validation.
└──▷ GET THIS VERSION
```
$ git clone --branch v0.0.2rc1 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout v0.0.2rc1
```
- ›Adds embedding validation to catch schema issues before data is ingested.
- ›Adds time-series graphing to visualize model metrics over time.
- ›Adds a timeslice selection UI to drill into a specific point on the time-series graph.
- ›Adds a dataset time preset selector for quickly scoping the active dataset to a time window.
- ›Adds record-level retrieval to inspect individual records in the UI.
+1 moreshow less
- ›Adds server startup polling so the library waits for the Phoenix server to be ready before proceeding.

Arize Phoenix

Summary

What Arize Phoenix answers

Examples

Command line

Release history