> ## Documentation Index
> Fetch the complete documentation index at: https://arizeai-433a7140.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# 11.18.2026: Python Decision-Model Evaluators and OpenTelemetry JS 3

> Python classification evaluators run on OpenAI and TypeSafe decision models, @arizeai/phoenix-otel moves to OpenTelemetry JS 3, and px lists prompt and dataset versions and tags prompts.

Python classification evaluators can now use a decision model as the judge, and `@arizeai/phoenix-otel` 3 moves TypeScript tracing to OpenTelemetry JS 3. The `px` CLI lists prompt and dataset versions and tags prompt versions.

# Breaking Change: OpenTelemetry JS 3 in @arizeai/phoenix-otel

November 11 to 16, 2026

**Breaking change in @arizeai/phoenix-otel 3.0.0 and @arizeai/phoenix-client 8.0.0; `sampler` and `spanLimits` in @arizeai/phoenix-otel 3.1.0+**

`@arizeai/phoenix-otel` now runs on OpenTelemetry JS 3, so spans from apps that use OpenTelemetry JS 3 are recorded after `register()`.

* **Node.js 22.15 or newer** and `@opentelemetry/api` 1.10 or newer are required.
* **Span processors take an options object.** Import `BatchSpanProcessor` and `SimpleSpanProcessor` from `@arizeai/phoenix-otel` and pass `{ exporter }`. These processors throw a `TypeError` for a positional exporter instead of silently dropping every span.
* **`register()` returns a provider without a `register()` method.** Call `attachGlobalTracerProvider(provider)` instead. A `tracerProvider` passed to `evaluateExperiment()` must also come from OpenTelemetry JS 3.
* **Set sampling and limits in code.** OpenTelemetry JS 3 ignores `OTEL_TRACES_SAMPLER`, `OTEL_SPAN_*`, `OTEL_ATTRIBUTE_*`, and `OTEL_BSP_*`, so `register()` accepts `sampler` and `spanLimits` and logs a warning for each ignored variable.

```typescript theme={"theme":{"light":"github-light-default","dark":"github-dark-default"}}
import {
  ParentBasedSampler,
  TraceIdRatioBasedSampler,
  register,
} from "@arizeai/phoenix-otel";

register({
  projectName: "my-app",
  sampler: new ParentBasedSampler({ root: new TraceIdRatioBasedSampler(0.1) }),
  spanLimits: { attributeValueLengthLimit: 4096 },
});
```

> [card] [Migration Guide](https://github.com/Arize-ai/phoenix/blob/main/js/packages/phoenix-otel/MIGRATION.md)
>
> Every step for upgrading from v2 to v3

> [card] [@arizeai/phoenix-otel](https://arizeai-433a7140.mintlify.site/docs/phoenix/sdk-api-reference/typescript/packages/phoenix-otel/overview.md)
>
> Registration options

# Decision-Model Evaluators in Python

November 10, 2026

**Available in arize-phoenix-evals 3.10.0+**

Python classification evaluators can now use a decision model as the judge. A decision model answers a typed choice question directly, so each score carries a label and per-label probabilities in its metadata, but no explanation.

* **`DecisionModel`** goes wherever an evaluator takes `llm`, including the built-in classification evaluators.
* **OpenAI Decisions API** with `provider="openai"`, which requires `openai` 3.26.0 or newer.
* **TypeSafe Jev** with `provider="typesafe"`, which requires `typesafe-sdk`.
* **Anthropic judges use native structured output** when you run language-model evaluators through the Anthropic adapter.

```python theme={"theme":{"light":"github-light-default","dark":"github-dark-default"}}
from phoenix.evals import ClassificationEvaluator, DecisionModel

evaluator = ClassificationEvaluator(
    name="sentiment",
    llm=DecisionModel(provider="openai", model="gpt-6-luna"),
    prompt_template="Classify the sentiment: {text}",
    choices={"positive": 1, "negative": 0},
)
scores = evaluator.evaluate({"text": "The refund arrived the same day."})
```

> [card] [Configuring the Decision Model](https://arizeai-433a7140.mintlify.site/docs/phoenix/evaluation/how-to-evals/configuring-the-decision-model.md)
>
> Providers, client options, and requirements

> [card] [Decision Models as a Judge](https://arizeai-433a7140.mintlify.site/docs/phoenix/evaluation/concepts-evals/decision-models-as-a-judge.md)
>
> When to use a decision model instead of an LLM

# Model Column and Prompt Version Timeline

November 12, 2026

**Available in arize-phoenix 21.1.0+**

* **See the model on the spans table.** A new model column shows each span's `llm.model_name`. Click a model to add an `llm.model_name == "..."` condition to the span filter.
* **Browse prompt versions as a timeline.** The prompt overview and the Versions tab show each version with its description, author, and tags, and link to it.
* **Open a new dataset right away.** Phoenix opens a dataset after you create it, and the annotation config table shows each config's optimization direction.

# px: Version Lists and Prompt Tags

November 5 to 17, 2026

**Available in @arizeai/phoenix-cli 1.20.0+ (`prompt-versions list`), 1.21.0+ (`dataset-versions list`), and 1.23.0+ (`prompt tag`)**

* **`px prompt-versions list`** and **`px dataset-versions list`** list versions newest first, with pretty, JSON, and raw output, so you can find IDs for `--version`.
* **`px prompt tag`** creates a tag on a prompt version or moves an existing tag to it. Omitting `--description` clears the tag's description.

```bash theme={"theme":{"light":"github-light-default","dark":"github-dark-default"}}
px prompt-versions list my-evaluator --limit 10
px dataset-versions list my-dataset --format json
px prompt tag UHJvbXB0VmVyc2lvbjox --tag production --description "Current release"
```

> [card] [Phoenix CLI](https://arizeai-433a7140.mintlify.site/docs/phoenix/integrations/developer-tools/cli.md)
>
> Commands and output formats

# Harbor: Model Parameters and Agent Settings

November 5, 2026

**Available in arize-phoenix-client 3.7.0+**

Each Harbor experiment's `harbor_agent` metadata now records the model parameters, such as `temperature` and `reasoning_effort`, and the agent settings, so you can tell apart experiments that differ only in one setting. Secret-named keys and URL credentials are removed before Phoenix stores them.

> [card] [Harbor](https://arizeai-433a7140.mintlify.site/docs/phoenix/integrations/evaluation-integrations/harbor.md)
>
> Experiment metadata fields

# Additional Improvements

November 4 to 18, 2026

**Available in arize-phoenix 21.1.0–21.2.0, @arizeai/phoenix-client 7.18.1–7.18.2, and arize-phoenix-otel 0.17.3**

* **LLM evaluators run on newer Claude models** that reject forced tool use, and on Anthropic prompts with extended thinking.
* **Retention sweeps delete traces in batches** that skip locked rows, so they no longer block ingestion.
* **The standalone `@arizeai/phoenix-mcp` stdio package is retired** in favor of the [MCP server](https://arizeai-433a7140.mintlify.site/docs/phoenix/integrations/mcp.md) built into Phoenix at `/mcp`.
* **GenAI spans keep reasoning and cache-write token counts**, and dataset uploads accept CSV and JSONL files with a byte order mark or blank lines.
* **The TypeScript client keeps literal `$` sequences** in prompt variables and keeps system instructions when converting prompts to Anthropic.
* **The Python OTel package keeps IPv6 brackets** in the inferred gRPC collector endpoint.
