arize-phoenix 11.20.0__py3-none-any.whl → 11.21.1__py3-none-any.whl

{arize_phoenix-11.20.0.dist-info → arize_phoenix-11.21.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: arize-phoenix
-Version: 11.20.0
+Version: 11.21.1
 Summary: AI Observability and Evaluation
 Project-URL: Documentation, https://arize.com/docs/phoenix/
 Project-URL: Issues, https://github.com/Arize-ai/phoenix/issues
@@ -167,7 +167,7 @@ Description-Content-Type: text/markdown
     <a target="_blank" href="https://github.com/Arize-ai/phoenix/tree/main/js/packages/phoenix-mcp">
         <img src="https://badge.mcpx.dev?status=on" title="MCP Enabled"/>
     </a>
-    <a href="https://cursor.com/install-mcp?name=phoenix&config=eyJjb21tYW5kIjoibnB4IC15IEBhcml6ZWFpL3Bob2VuaXgtbWNwQGxhdGVzdCAtLWJhc2VVcmwgaHR0cDovL2xvY2FsaG9zdDo2MDA2IC0tYXBpS2V5IHlvdXItYXBpLWtleSJ9"><img src="https://cursor.com/deeplink/mcp-install-dark.svg" alt="Add Arize Phoenix MCP server to Cursor" height=20 /></a>
+    <a href="cursor://anysphere.cursor-deeplink/mcp/install?name=phoenix&config=eyJjb21tYW5kIjoibnB4IC15IEBhcml6ZWFpL3Bob2VuaXgtbWNwQGxhdGVzdCAtLWJhc2VVcmwgaHR0cHM6Ly9teS1waG9lbml4LmNvbSAtLWFwaUtleSB5b3VyLWFwaS1rZXkifQ%3D%3D"><img src="https://cursor.com/deeplink/mcp-install-dark.svg" alt="Add Arize Phoenix MCP server to Cursor" height=20 /></a>
 </p>
 
 Phoenix is an open-source AI observability platform designed for experimentation, evaluation, and troubleshooting. It provides:
@@ -254,14 +254,16 @@ Phoenix is built on top of OpenTelemetry and is vendor, language, and framework
 | Integration                                                                                                                       | Package                                     | Version Badge                                                                                                                                                                                                 |
 | --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | [LangChain4j](https://github.com/Arize-ai/openinference/tree/main/java/instrumentation/openinference-instrumentation-langchain4j) | `openinference-instrumentation-langchain4j` | [![Maven Central](https://img.shields.io/maven-central/v/com.arize/openinference-instrumentation-langchain4j.svg)](https://central.sonatype.com/artifact/com.arize/openinference-instrumentation-langchain4j) |
+| [SpringAI](https://central.sonatype.com/artifact/com.arize/openinference-instrumentation-springAI) | `openinference-instrumentation-springAI` | [![Maven Central](https://img.shields.io/maven-central/v/com.arize/openinference-instrumentation-springAI.svg)](https://central.sonatype.com/artifact/com.arize/openinference-instrumentation-springAI) |
 
 ### Platforms
 
 | Platform                                                                                                 | Description                                                    | Docs                                                                                                          |
 | -------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------- |
+| [BeeAI](https://docs.beeai.dev/observability/agents-traceability)                                        | AI agent framework with built-in observability                 | [Integration Guide](https://docs.beeai.dev/observability/agents-traceability)                                 |
 | [Dify](https://docs.dify.ai/en/guides/monitoring/integrate-external-ops-tools/integrate-phoenix)         | Open-source LLM app development platform                       | [Integration Guide](https://docs.dify.ai/en/guides/monitoring/integrate-external-ops-tools/integrate-phoenix) |
+| [Envoy AI Gateway](https://github.com/envoyproxy/ai-gateway)                                              | AI Gateway built on Envoy Proxy for AI workloads              | [Integration Guide](https://github.com/envoyproxy/ai-gateway/tree/main/cmd/aigw#opentelemetry-setup-with-phoenix) |
 | [LangFlow](https://arize.com/docs/phoenix/tracing/integrations-tracing/langflow)                         | Visual framework for building multi-agent and RAG applications | [Integration Guide](https://arize.com/docs/phoenix/tracing/integrations-tracing/langflow)                     |
-| [BeeAI](https://docs.beeai.dev/observability/agents-traceability)                                        | AI agent framework with built-in observability                 | [Integration Guide](https://docs.beeai.dev/observability/agents-traceability)                                 |
 | [LiteLLM Proxy](https://docs.litellm.ai/docs/observability/phoenix_integration#using-with-litellm-proxy) | Proxy server for LLMs                                          | [Integration Guide](https://docs.litellm.ai/docs/observability/phoenix_integration#using-with-litellm-proxy)  |
 
 ## Community

{arize_phoenix-11.20.0.dist-info → arize_phoenix-11.21.1.dist-info}/RECORD

@@ -6,7 +6,7 @@ phoenix/exceptions.py,sha256=n2L2KKuecrdflB9MsCdAYCiSEvGJptIsfRkXMoJle7A,169
 phoenix/py.typed,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
 phoenix/services.py,sha256=ngkyKGVatX3cO2WJdo2hKdaVKP-xJCMvqthvga6kJss,5196
 phoenix/settings.py,sha256=2kHfT3BNOVd4dAO1bq-syEQbHSG8oX2-7NhOwK2QREk,896
-phoenix/version.py,sha256=PWj_8RsVSxALf302x1wXXyxFVSuiHNYoMU_ppot504s,24
+phoenix/version.py,sha256=MKnna2l-ytcQjtXJcRSl2t1LDUmcw25A2XUiuU4Tln0,24
 phoenix/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 phoenix/core/embedding_dimension.py,sha256=zKGbcvwOXgLf-yrJBpQyKtd-LEOPRKHnUToyAU8Owis,87
 phoenix/core/model.py,sha256=qBFraOtmwCCnWJltKNP18DDG0mULXigytlFsa6YOz6k,4837
@@ -112,7 +112,7 @@ phoenix/server/api/auth.py,sha256=AyYhnZIbY9ALVjg2K6aC2UXSa3Pva5GVDBXyaZ3nD3o,27
 phoenix/server/api/context.py,sha256=mqsq_8Ru50e-PxKWNTzh9zptb1PFjYFUf58uW59UYL0,8996
 phoenix/server/api/exceptions.py,sha256=E2W0x63CBzc0CoQPptrLr9nZxPF9zIP8MCJ3RuJMddw,1322
 phoenix/server/api/interceptor.py,sha256=ykDnoC_apUd-llVli3m1CW18kNSIgjz2qZ6m5JmPDu8,1294
-phoenix/server/api/queries.py,sha256=RC-MS6x1gNqYhNQ6TnWA6zqDDnpiW4puKLBTrbtS8os,67102
+phoenix/server/api/queries.py,sha256=rHV8gBqCwNjuDCtfKTfBcJB-eWxbJFivZzFV3mId1HY,67524
 phoenix/server/api/schema.py,sha256=fcs36xQwFF_Qe41_5cWR8wYpDvOrnbcyTeo5WNMbDsA,1702
 phoenix/server/api/subscriptions.py,sha256=U7JZl-FGfsaIhRkIFdeSQLqR7xCS7CY1h-21BOAcaqY,25439
 phoenix/server/api/utils.py,sha256=quCBRcusc6PUq9tJq7M8PgwFZp7nXgVAxtbw8feribY,833
@@ -176,11 +176,11 @@ phoenix/server/api/helpers/__init__.py,sha256=m2-xaSPqUiSs91k62JaRDjFNfl-1byxBfY
 phoenix/server/api/helpers/annotations.py,sha256=9gMXKpMTfWEChoSCnvdWYuyB0hlSnNOp-qUdar9Vono,262
 phoenix/server/api/helpers/dataset_helpers.py,sha256=3bdGBoUzqrtg-sr5p2wpQLOU6dhg_3TKFHNeJj8p0TU,9155
 phoenix/server/api/helpers/experiment_run_filters.py,sha256=DOnVwrmn39eAkk2mwuZP8kIcAnR5jrOgllEwWSjsw94,29893
-phoenix/server/api/helpers/playground_clients.py,sha256=3EoJx4bYgCl0LXQnL8lbYdTklk4TxGKbNYcRZFDYxrY,73652
+phoenix/server/api/helpers/playground_clients.py,sha256=R_lXbm58ejnsdHMvlbHbrasC7XsaLfqh5pZoHaL3DSg,72129
 phoenix/server/api/helpers/playground_registry.py,sha256=n0v4-KnvZJxeaEwOla5qBbnOQjSWznKmMhZnh9ziJt0,2584
 phoenix/server/api/helpers/playground_spans.py,sha256=QpXwPl_fFNwm_iA1A77XApUyXMl1aDmonw8aXuNZ_4k,17132
 phoenix/server/api/helpers/prompts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-phoenix/server/api/helpers/prompts/models.py,sha256=nlPtLZaGcHfWNRR0iNRaBUv8eoKOnoGqRm6zadrTt0I,23547
+phoenix/server/api/helpers/prompts/models.py,sha256=pEPmloU27j5c4dM0dbDSAeIAzxpfsjPtjNRdF99mlhM,23558
 phoenix/server/api/helpers/prompts/conversions/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 phoenix/server/api/helpers/prompts/conversions/anthropic.py,sha256=ZT--UqBwoGf7QMusajB6aeB7zyWGttaZigb113kgiY8,3571
 phoenix/server/api/helpers/prompts/conversions/aws.py,sha256=6vaT8K13r0bMXB9XHA8qY1MCjVsmR9TO0VIwyBMjQoY,2941
@@ -220,7 +220,7 @@ phoenix/server/api/input_types/ProjectSessionSort.py,sha256=KZzEtOMpcxtP11brL4fX
 phoenix/server/api/input_types/ProjectSort.py,sha256=ZTT-InFB6NvInDwLuivyHe9PxR5nsmQ8aXCHAPjZm9k,329
 phoenix/server/api/input_types/PromptFilter.py,sha256=f2F7fDlYRsNJp_rKkmvpgUt9rfgr_e-dyZxuHX8YfkU,256
 phoenix/server/api/input_types/PromptTemplateOptions.py,sha256=8ZJdH1F9fExcdH9dF8SJ29WycCvtEpK-Z6dZwFO7KgQ,232
-phoenix/server/api/input_types/PromptVersionInput.py,sha256=n6zBeSkK8ZFRHTjtVx4BK--azZIxXeYETa6Cufcet2I,3743
+phoenix/server/api/input_types/PromptVersionInput.py,sha256=6iFWf2Ye9K1dwL1810L-wUTLkMtOIHemJTxar4xF4kw,3911
 phoenix/server/api/input_types/SpanAnnotationFilter.py,sha256=-djfIXYCxV6sV3GPOZQUV0SPfiWDhRlTORfeQ7tCBgQ,2671
 phoenix/server/api/input_types/SpanAnnotationSort.py,sha256=T5pAGzmh4MiJp9JMAzNDByFVTczfw02FH4WFWwFezyI,361
 phoenix/server/api/input_types/SpanSort.py,sha256=GReQx9yOo0Kehi2y4AtY69aZhRtcqvcg-9bSIFru69U,7540
@@ -362,7 +362,7 @@ phoenix/server/cost_tracking/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NM
 phoenix/server/cost_tracking/cost_details_calculator.py,sha256=Tt0YcuLhgPuXKWJemWVmYQfG0xQUvH4VziIj6KcDnoA,8945
 phoenix/server/cost_tracking/cost_model_lookup.py,sha256=jhtVdnQBzrTUHeOGPWgOebk-Io5hpJ1vAgWOu8ojeJ4,6801
 phoenix/server/cost_tracking/helpers.py,sha256=Pk6ECjnYreTxrldtRwxnwFcxIPVsvDq_yAwDA_spkOc,2122
-phoenix/server/cost_tracking/model_cost_manifest.json,sha256=XKOgaRE9bq109MnopfyC6jFY7F4ZZbLFPRB2juLqfBU,57556
+phoenix/server/cost_tracking/model_cost_manifest.json,sha256=kE8VrBbvdqDy1ijk8KWWs_76U-L_vcRUT5hVT418evY,63488
 phoenix/server/cost_tracking/regex_specificity.py,sha256=9kqWuQ68C-hlwW25hr7BhFlRt5y2Nnpy0Ax3n9UN6Xk,11622
 phoenix/server/cost_tracking/token_cost_calculator.py,sha256=2JEZnvusx2-xbhp8krp9EarjWuyGH2KO4e-ZwJX-K0s,1598
 phoenix/server/daemons/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -391,10 +391,10 @@ phoenix/server/static/apple-touch-icon-76x76.png,sha256=CT_xT12I0u2i0WU8JzBZBuOQ
 phoenix/server/static/apple-touch-icon.png,sha256=fOfpjqGpWYbJ0eAurKsyoZP1EAs6ZVooBJ_SGk2ZkDs,3801
 phoenix/server/static/favicon.ico,sha256=bY0vvCKRftemZfPShwZtE93DiiQdaYaozkPGwNFr6H8,34494
 phoenix/server/static/modernizr.js,sha256=mvK-XtkNqjOral-QvzoqsyOMECXIMu5BQwSVN_wcU9c,2564
-phoenix/server/static/.vite/manifest.json,sha256=VfeGEGEeidc2iRZCqPQ8Ae-XTEOyLCy0MQw8DsvFEc0,2328
-phoenix/server/static/assets/components-BNcxEjYs.js,sha256=1_lobSTCfokeUlK4ClEylCmZ4gMIpa_zCsgZYZDGF9w,658582
-phoenix/server/static/assets/index-CKIBKnVD.js,sha256=ig-C5VgtSHWxhrkqhMwj6k1WKTjCYXdYvqI30ajC3v0,63064
-phoenix/server/static/assets/pages-3RoC-adr.js,sha256=Y5BgOTRvJRpBKJJ4rBMi7iTM3TNRDFe_v0nlxUEpV-0,1224388
+phoenix/server/static/.vite/manifest.json,sha256=42hM44kTkxtzKywj80vA_-KqJ9LJO9p6Xvi52T8UnGU,2328
+phoenix/server/static/assets/components-BHdwFK1u.js,sha256=aWWK46DXOMuDUTYquIY07idjdtqJqdF_H8Kc7vcE0ZU,658573
+phoenix/server/static/assets/index-BuFamj8g.js,sha256=ijIj6Frv0WbowI5EYmfJQibFOsFD102TOQ7o6q4QkFk,63122
+phoenix/server/static/assets/pages-wNrdUuht.js,sha256=OCYvFNXL1V7CiMFoeszBhHtQJ7CZnfmXkwRl8vj-A3A,1225254
 phoenix/server/static/assets/vendor-BbqekBfb.js,sha256=8xINQdH4ikfrf8nr8mlO0B9YrKJ2FPecrA9qu5kPILo,2588857
 phoenix/server/static/assets/vendor-CqDb5u4o.css,sha256=zIyFiNJKxMaQk8AvtLgt1rR01oO10d1MFndSDKH9Clw,5517
 phoenix/server/static/assets/vendor-arizeai-CEwHhYfL.js,sha256=EIl1d9G6uPn7_Fc8YyAdxWmyV1Y7k1nN7VeJmI4MxtA,121514
@@ -441,9 +441,9 @@ phoenix/utilities/project.py,sha256=auVpARXkDb-JgeX5f2aStyFIkeKvGwN9l7qrFeJMVxI,
 phoenix/utilities/re.py,sha256=6YyUWIkv0zc2SigsxfOWIHzdpjKA_TZo2iqKq7zJKvw,2081
 phoenix/utilities/span_store.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 phoenix/utilities/template_formatters.py,sha256=gh9PJD6WEGw7TEYXfSst1UR4pWWwmjxMLrDVQ_CkpkQ,2779
-arize_phoenix-11.20.0.dist-info/METADATA,sha256=_ihQiuoj-PL_R0L83OBu6UdGvzM6wkRmjFQKJbPaU2M,30950
-arize_phoenix-11.20.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-arize_phoenix-11.20.0.dist-info/entry_points.txt,sha256=Pgpn8Upxx9P8z8joPXZWl2LlnAlGc3gcQoVchb06X1Q,94
-arize_phoenix-11.20.0.dist-info/licenses/IP_NOTICE,sha256=JBqyyCYYxGDfzQ0TtsQgjts41IJoa-hiwDrBjCb9gHM,469
-arize_phoenix-11.20.0.dist-info/licenses/LICENSE,sha256=HFkW9REuMOkvKRACuwLPT0hRydHb3zNg-fdFt94td18,3794
-arize_phoenix-11.20.0.dist-info/RECORD,,
+arize_phoenix-11.21.1.dist-info/METADATA,sha256=XaEthhkljvctwAGuXZs1mQwD6AXTMF8Jzx_ngrsjTQg,31612
+arize_phoenix-11.21.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+arize_phoenix-11.21.1.dist-info/entry_points.txt,sha256=Pgpn8Upxx9P8z8joPXZWl2LlnAlGc3gcQoVchb06X1Q,94
+arize_phoenix-11.21.1.dist-info/licenses/IP_NOTICE,sha256=JBqyyCYYxGDfzQ0TtsQgjts41IJoa-hiwDrBjCb9gHM,469
+arize_phoenix-11.21.1.dist-info/licenses/LICENSE,sha256=HFkW9REuMOkvKRACuwLPT0hRydHb3zNg-fdFt94td18,3794
+arize_phoenix-11.21.1.dist-info/RECORD,,

phoenix/server/api/helpers/playground_clients.py

@@ -1141,6 +1141,10 @@ class OpenAIStreamingClient(OpenAIBaseStreamingClient):
 
 
 _OPENAI_REASONING_MODELS = [
+    "gpt-5",
+    "gpt-5-mini",
+    "gpt-5-nano",
+    "gpt-5-chat-latest",
     "o1",
     "o1-pro",
     "o1-2024-12-17",
@@ -1201,50 +1205,6 @@ class OpenAIReasoningNonStreamingClient(
     OpenAIReasoningReasoningModelsMixin,
     OpenAIStreamingClient,
 ):
-    @override
-    async def chat_completion_create(
-        self,
-        messages: list[
-            tuple[ChatCompletionMessageRole, str, Optional[str], Optional[list[JSONScalarType]]]
-        ],
-        tools: list[JSONScalarType],
-        **invocation_parameters: Any,
-    ) -> AsyncIterator[ChatCompletionChunk]:
-        from openai import NOT_GIVEN
-
-        # Convert standard messages to OpenAI messages
-        openai_messages = []
-        for message in messages:
-            openai_message = self.to_openai_chat_completion_param(*message)
-            if openai_message is not None:
-                openai_messages.append(openai_message)
-
-        throttled_create = self.rate_limiter._alimit(self.client.chat.completions.create)
-        response = await throttled_create(
-            messages=openai_messages,
-            model=self.model_name,
-            stream=False,
-            tools=tools or NOT_GIVEN,
-            **invocation_parameters,
-        )
-
-        if response.usage is not None:
-            self._attributes.update(dict(self._llm_token_counts(response.usage)))
-
-        choice = response.choices[0]
-        if choice.message.content:
-            yield TextChunk(content=choice.message.content)
-
-        if choice.message.tool_calls:
-            for tool_call in choice.message.tool_calls:
-                yield ToolCallChunk(
-                    id=tool_call.id,
-                    function=FunctionCallChunk(
-                        name=tool_call.function.name,
-                        arguments=tool_call.function.arguments,
-                    ),
-                )
-
     def to_openai_chat_completion_param(
         self,
         role: ChatCompletionMessageRole,

phoenix/server/api/helpers/prompts/models.py

@@ -329,7 +329,7 @@ class PromptOpenAIInvocationParametersContent(DBBaseModel):
     presence_penalty: float = UNDEFINED
     top_p: float = UNDEFINED
     seed: int = UNDEFINED
-    reasoning_effort: Literal["low", "medium", "high"] = UNDEFINED
+    reasoning_effort: Literal["minimal", "low", "medium", "high"] = UNDEFINED
 
 
 class PromptOpenAIInvocationParameters(DBBaseModel):

phoenix/server/api/input_types/PromptVersionInput.py

@@ -83,6 +83,11 @@ class ChatPromptVersionInput:
     model_provider: ModelProvider
     model_name: str
 
+    def __post_init__(self) -> None:
+        self.invocation_parameters = {
+            k: v for k, v in self.invocation_parameters.items() if v is not None
+        }
+
 
 def to_pydantic_prompt_chat_template_v1(
     prompt_chat_template_input: PromptChatTemplateInput,

phoenix/server/api/queries.py

@@ -7,8 +7,8 @@ from typing import cast as type_cast
 import numpy as np
 import numpy.typing as npt
 import strawberry
-from sqlalchemy import ColumnElement, String, and_, case, cast, distinct, func, select, text
-from sqlalchemy.orm import aliased, joinedload
+from sqlalchemy import ColumnElement, String, and_, case, cast, func, select, text
+from sqlalchemy.orm import aliased, joinedload, load_only
 from starlette.authentication import UnauthenticatedUser
 from strawberry import ID, UNSET
 from strawberry.relay import Connection, GlobalID, Node
@@ -375,41 +375,52 @@ class Query:
             raise BadRequest("Compare experiment IDs cannot contain the base experiment ID")
         if len(set(compare_experiment_ids)) < len(compare_experiment_ids):
             raise BadRequest("Compare experiment IDs must be unique")
-        experiment_ids = [
-            from_global_id_with_expected_type(experiment_id, models.Experiment.__name__)
-            for experiment_id in (base_experiment_id, *compare_experiment_ids)
-        ]
+
+        try:
+            base_experiment_rowid = from_global_id_with_expected_type(
+                base_experiment_id, models.Experiment.__name__
+            )
+        except ValueError:
+            raise BadRequest(f"Invalid base experiment ID: {base_experiment_id}")
+
+        compare_experiment_rowids = []
+        for compare_experiment_id in compare_experiment_ids:
+            try:
+                compare_experiment_rowids.append(
+                    from_global_id_with_expected_type(
+                        compare_experiment_id, models.Experiment.__name__
+                    )
+                )
+            except ValueError:
+                raise BadRequest(f"Invalid compare experiment ID: {compare_experiment_id}")
+
+        experiment_rowids = [base_experiment_rowid, *compare_experiment_rowids]
+
         cursor = Cursor.from_string(after) if after else None
         page_size = first or 50
 
         async with info.context.db() as session:
-            validation_result = (
-                await session.execute(
+            experiments = (
+                await session.scalars(
                     select(
-                        func.count(distinct(models.DatasetVersion.dataset_id)),
-                        func.max(models.DatasetVersion.dataset_id),
-                        func.max(models.DatasetVersion.id),
-                        func.count(models.Experiment.id),
-                    )
-                    .select_from(models.DatasetVersion)
-                    .join(
                         models.Experiment,
-                        models.Experiment.dataset_version_id == models.DatasetVersion.id,
                     )
-                    .where(
-                        models.Experiment.id.in_(experiment_ids),
+                    .where(models.Experiment.id.in_(experiment_rowids))
+                    .options(
+                        load_only(
+                            models.Experiment.dataset_id, models.Experiment.dataset_version_id
+                        )
                     )
                 )
-            ).first()
-            if validation_result is None:
-                raise NotFound("No experiments could be found for input IDs.")
-
-            num_datasets, dataset_id, version_id, num_resolved_experiment_ids = validation_result
-            if num_datasets != 1:
-                raise BadRequest("Experiments must belong to the same dataset.")
-            if num_resolved_experiment_ids != len(experiment_ids):
+            ).all()
+            if not experiments or len(experiments) < len(experiment_rowids):
                 raise NotFound("Unable to resolve one or more experiment IDs.")
-
+            num_datasets = len(set(experiment.dataset_id for experiment in experiments))
+            if num_datasets > 1:
+                raise BadRequest("Experiments must belong to the same dataset.")
+            base_experiment = next(
+                experiment for experiment in experiments if experiment.id == base_experiment_rowid
+            )
             revision_ids = (
                 select(func.max(models.DatasetExampleRevision.id))
                 .join(
@@ -418,8 +429,9 @@ class Query:
                 )
                 .where(
                     and_(
-                        models.DatasetExampleRevision.dataset_version_id <= version_id,
-                        models.DatasetExample.dataset_id == dataset_id,
+                        models.DatasetExampleRevision.dataset_version_id
+                        <= base_experiment.dataset_version_id,
+                        models.DatasetExample.dataset_id == base_experiment.dataset_id,
                     )
                 )
                 .group_by(models.DatasetExampleRevision.dataset_example_id)
@@ -447,7 +459,7 @@ class Query:
                 examples_query = update_examples_query_with_filter_condition(
                     query=examples_query,
                     filter_condition=filter_condition,
-                    experiment_ids=experiment_ids,
+                    experiment_ids=experiment_rowids,
                 )
 
             examples = (await session.scalars(examples_query)).all()
@@ -466,7 +478,7 @@ class Query:
                         models.ExperimentRun.dataset_example_id.in_(
                             example.id for example in examples
                         ),
-                        models.ExperimentRun.experiment_id.in_(experiment_ids),
+                        models.ExperimentRun.experiment_id.in_(experiment_rowids),
                     )
                 )
                 .options(joinedload(models.ExperimentRun.trace).load_only(models.Trace.trace_id))
@@ -479,7 +491,7 @@ class Query:
         cursors_and_nodes = []
         for example in examples:
             run_comparison_items = []
-            for experiment_id in experiment_ids:
+            for experiment_id in experiment_rowids:
                 run_comparison_items.append(
                     RunComparisonItem(
                         experiment_id=GlobalID(Experiment.__name__, str(experiment_id)),
@@ -496,7 +508,7 @@ class Query:
                 example=DatasetExample(
                     id_attr=example.id,
                     created_at=example.created_at,
-                    version_id=version_id,
+                    version_id=base_experiment.dataset_version_id,
                 ),
                 run_comparison_items=run_comparison_items,
             )
@@ -1491,7 +1503,7 @@ class Query:
         return None
 
     @strawberry.field
-    async def get_project_session_by_otel_id(
+    async def get_project_session_by_id(
         self,
         info: Info[Context, None],
         session_id: str,

phoenix/server/cost_tracking/model_cost_manifest.json

@@ -341,6 +341,60 @@
         }
       ]
     },
+    {
+      "name": "claude-opus-4-1",
+      "name_pattern": "claude-opus-4-1",
+      "source": "litellm",
+      "token_prices": [
+        {
+          "base_rate": 0.000015,
+          "is_prompt": true,
+          "token_type": "input"
+        },
+        {
+          "base_rate": 0.000075,
+          "is_prompt": false,
+          "token_type": "output"
+        },
+        {
+          "base_rate": 1.5e-6,
+          "is_prompt": true,
+          "token_type": "cache_read"
+        },
+        {
+          "base_rate": 0.00001875,
+          "is_prompt": true,
+          "token_type": "cache_write"
+        }
+      ]
+    },
+    {
+      "name": "claude-opus-4-1-20250805",
+      "name_pattern": "claude-opus-4-1-20250805",
+      "source": "litellm",
+      "token_prices": [
+        {
+          "base_rate": 0.000015,
+          "is_prompt": true,
+          "token_type": "input"
+        },
+        {
+          "base_rate": 0.000075,
+          "is_prompt": false,
+          "token_type": "output"
+        },
+        {
+          "base_rate": 1.5e-6,
+          "is_prompt": true,
+          "token_type": "cache_read"
+        },
+        {
+          "base_rate": 0.00001875,
+          "is_prompt": true,
+          "token_type": "cache_write"
+        }
+      ]
+    },
     {
       "name": "claude-opus-4-20250514",
       "name_pattern": "claude-opus-4-20250514",
@@ -2078,6 +2132,182 @@
         }
       ]
     },
+    {
+      "name": "gpt-5",
+      "name_pattern": "gpt-5",
+      "source": "litellm",
+      "token_prices": [
+        {
+          "base_rate": 1.25e-6,
+          "is_prompt": true,
+          "token_type": "input"
+        },
+        {
+          "base_rate": 0.00001,
+          "is_prompt": false,
+          "token_type": "output"
+        },
+        {
+          "base_rate": 1.25e-7,
+          "is_prompt": true,
+          "token_type": "cache_read"
+        }
+      ]
+    },
+    {
+      "name": "gpt-5-2025-08-07",
+      "name_pattern": "gpt-5-2025-08-07",
+      "source": "litellm",
+      "token_prices": [
+        {
+          "base_rate": 1.25e-6,
+          "is_prompt": true,
+          "token_type": "input"
+        },
+        {
+          "base_rate": 0.00001,
+          "is_prompt": false,
+          "token_type": "output"
+        },
+        {
+          "base_rate": 1.25e-7,
+          "is_prompt": true,
+          "token_type": "cache_read"
+        }
+      ]
+    },
+    {
+      "name": "gpt-5-chat",
+      "name_pattern": "gpt-5-chat",
+      "source": "litellm",
+      "token_prices": [
+        {
+          "base_rate": 1.25e-6,
+          "is_prompt": true,
+          "token_type": "input"
+        },
+        {
+          "base_rate": 0.00001,
+          "is_prompt": false,
+          "token_type": "output"
+        },
+        {
+          "base_rate": 1.25e-7,
+          "is_prompt": true,
+          "token_type": "cache_read"
+        }
+      ]
+    },
+    {
+      "name": "gpt-5-chat-latest",
+      "name_pattern": "gpt-5-chat-latest",
+      "source": "litellm",
+      "token_prices": [
+        {
+          "base_rate": 1.25e-6,
+          "is_prompt": true,
+          "token_type": "input"
+        },
+        {
+          "base_rate": 0.00001,
+          "is_prompt": false,
+          "token_type": "output"
+        },
+        {
+          "base_rate": 1.25e-7,
+          "is_prompt": true,
+          "token_type": "cache_read"
+        }
+      ]
+    },
+    {
+      "name": "gpt-5-mini",
+      "name_pattern": "gpt-5-mini",
+      "source": "litellm",
+      "token_prices": [
+        {
+          "base_rate": 2.5e-7,
+          "is_prompt": true,
+          "token_type": "input"
+        },
+        {
+          "base_rate": 2e-6,
+          "is_prompt": false,
+          "token_type": "output"
+        },
+        {
+          "base_rate": 2.5e-8,
+          "is_prompt": true,
+          "token_type": "cache_read"
+        }
+      ]
+    },
+    {
+      "name": "gpt-5-mini-2025-08-07",
+      "name_pattern": "gpt-5-mini-2025-08-07",
+      "source": "litellm",
+      "token_prices": [
+        {
+          "base_rate": 2.5e-7,
+          "is_prompt": true,
+          "token_type": "input"
+        },
+        {
+          "base_rate": 2e-6,
+          "is_prompt": false,
+          "token_type": "output"
+        },
+        {
+          "base_rate": 2.5e-8,
+          "is_prompt": true,
+          "token_type": "cache_read"
+        }
+      ]
+    },
+    {
+      "name": "gpt-5-nano",
+      "name_pattern": "gpt-5-nano",
+      "source": "litellm",
+      "token_prices": [
+        {
+          "base_rate": 5e-8,
+          "is_prompt": true,
+          "token_type": "input"
+        },
+        {
+          "base_rate": 4e-7,
+          "is_prompt": false,
+          "token_type": "output"
+        },
+        {
+          "base_rate": 5e-9,
+          "is_prompt": true,
+          "token_type": "cache_read"
+        }
+      ]
+    },
+    {
+      "name": "gpt-5-nano-2025-08-07",
+      "name_pattern": "gpt-5-nano-2025-08-07",
+      "source": "litellm",
+      "token_prices": [
+        {
+          "base_rate": 5e-8,
+          "is_prompt": true,
+          "token_type": "input"
+        },
+        {
+          "base_rate": 4e-7,
+          "is_prompt": false,
+          "token_type": "output"
+        },
+        {
+          "base_rate": 5e-9,
+          "is_prompt": true,
+          "token_type": "cache_read"
+        }
+      ]
+    },
     {
       "name": "o1",
       "name_pattern": "o1",
@@ -2497,6 +2727,40 @@
           "token_type": "cache_read"
         }
       ]
+    },
+    {
+      "name": "openai.gpt-oss-120b-1:0",
+      "name_pattern": "openai\\.gpt-oss-120b-1:0",
+      "source": "litellm",
+      "token_prices": [
+        {
+          "base_rate": 1.5e-7,
+          "is_prompt": true,
+          "token_type": "input"
+        },
+        {
+          "base_rate": 6e-7,
+          "is_prompt": false,
+          "token_type": "output"
+        }
+      ]
+    },
+    {
+      "name": "openai.gpt-oss-20b-1:0",
+      "name_pattern": "openai\\.gpt-oss-20b-1:0",
+      "source": "litellm",
+      "token_prices": [
+        {
+          "base_rate": 7e-8,
+          "is_prompt": true,
+          "token_type": "input"
+        },
+        {
+          "base_rate": 3e-7,
+          "is_prompt": false,
+          "token_type": "output"
+        }
+      ]
     }
   ]
 }