feat(api): api update

Author: stainless-app[bot]

.stats.yml

@@ -1,3 +1,3 @@
 configured_endpoints: 44
-openapi_spec_hash: 947c1396f52c4f78645b067ac0b708e5
+openapi_spec_hash: eeb8ebc5600523bdfad046381a929572
 config_hash: 659f65b6ccf5612986f920f7f9abbcb5

src/codex/resources/projects/projects.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 import typing_extensions
-from typing import Dict, List, Optional
+from typing import Dict, List, Iterable, Optional
 from typing_extensions import Literal
 
 import httpx
@@ -436,6 +436,7 @@ def validate(
         custom_eval_thresholds: Optional[Dict[str, float]] | NotGiven = NOT_GIVEN,
         custom_metadata: Optional[object] | NotGiven = NOT_GIVEN,
         eval_scores: Optional[Dict[str, float]] | NotGiven = NOT_GIVEN,
+        messages: Optional[Iterable[project_validate_params.Message]] | NotGiven = NOT_GIVEN,
         options: Optional[project_validate_params.Options] | NotGiven = NOT_GIVEN,
         quality_preset: Literal["best", "high", "medium", "low", "base"] | NotGiven = NOT_GIVEN,
         task: Optional[str] | NotGiven = NOT_GIVEN,
@@ -465,6 +466,10 @@ def validate(
           eval_scores: Scores assessing different aspects of the RAG system. If not provided, TLM will
               be used to generate scores.
 
+          messages: Optional message history to provide conversation context for the query. Used to
+              rewrite query into a self-contained version of itself. If not provided, the
+              query will be treated as self-contained.
+
           options: Typed dict of advanced configuration options for the Trustworthy Language Model.
               Many of these configurations are determined by the quality preset selected
               (learn about quality presets in the TLM [initialization method](./#class-tlm)).
@@ -490,27 +495,24 @@ def validate(
                 `use_self_reflection` = True.
               - **base:** `num_candidate_responses` = 1, `num_consistency_samples` = 0,
                 `use_self_reflection` = False. When using `get_trustworthiness_score()` on
-                "base" preset, a cheaper self-reflection will be used to compute the
-                trustworthiness score.
-
-              By default, the TLM uses the "medium" quality preset. The default base LLM
-              `model` used is "gpt-4o-mini", and `max_tokens` is 512 for all quality presets.
-              You can set custom values for these arguments regardless of the quality preset
-              specified.
-
-              Args: model ({"gpt-4o-mini", "gpt-4o", "gpt-4.1", "gpt-4.1-mini",
-              "gpt-4.1-nano", "o4-mini", "o3", "o3-mini", "o1", "o1-mini", "gpt-4",
-              "gpt-4.5-preview", "gpt-3.5-turbo-16k", "claude-3.7-sonnet",
-              "claude-3.5-sonnet-v2", "claude-3.5-sonnet", "claude-3.5-haiku",
-              "claude-3-haiku", "nova-micro", "nova-lite", "nova-pro"}, default =
-              "gpt-4o-mini"): Underlying base LLM to use (better models yield better results,
-              faster models yield faster/cheaper results). - Models still in beta: "o3", "o1",
-              "o4-mini", "o3-mini", "o1-mini", "gpt-4.1", "gpt-4.1-mini", "gpt-4.1-nano",
-              "gpt-4.5-preview", "claude-3.7-sonnet", "claude-3.5-sonnet-v2",
-              "claude-3.5-haiku", "nova-micro", "nova-lite", "nova-pro". - Recommended models
-              for accuracy: "gpt-4.1", "o4-mini", "o3", "claude-3.7-sonnet",
-              "claude-3.5-sonnet-v2". - Recommended models for low latency/costs:
-              "gpt-4.1-nano", "nova-micro".
+                "base" preset, a faster self-reflection is employed.
+
+              By default, TLM uses the: "medium" `quality_preset`, "gpt-4.1-mini" base
+              `model`, and `max_tokens` is set to 512. You can set custom values for these
+              arguments regardless of the quality preset specified.
+
+              Args: model ({"gpt-4.1", "gpt-4.1-mini", "gpt-4.1-nano", "o4-mini", "o3",
+              "gpt-4.5-preview", "gpt-4o-mini", "gpt-4o", "o3-mini", "o1", "o1-mini", "gpt-4",
+              "gpt-3.5-turbo-16k", "claude-opus-4-0", "claude-sonnet-4-0",
+              "claude-3.7-sonnet", "claude-3.5-sonnet-v2", "claude-3.5-sonnet",
+              "claude-3.5-haiku", "claude-3-haiku", "nova-micro", "nova-lite", "nova-pro"},
+              default = "gpt-4.1-mini"): Underlying base LLM to use (better models yield
+              better results, faster models yield faster results). - Models still in beta:
+              "o3", "o1", "o4-mini", "o3-mini", "o1-mini", "gpt-4.5-preview",
+              "claude-opus-4-0", "claude-sonnet-4-0", "claude-3.7-sonnet",
+              "claude-3.5-haiku". - Recommended models for accuracy: "gpt-4.1", "o4-mini",
+              "o3", "claude-opus-4-0", "claude-sonnet-4-0". - Recommended models for low
+              latency/costs: "gpt-4.1-nano", "nova-micro".
 
                   max_tokens (int, default = 512): the maximum number of tokens that can be generated in the TLM response (and in internal trustworthiness scoring).
                   Higher values here may produce better (more reliable) TLM responses and trustworthiness scores, but at higher runtimes/costs.
@@ -536,7 +538,7 @@ def validate(
 
                   similarity_measure ({"semantic", "string", "embedding", "embedding_large", "code", "discrepancy"}, default = "semantic"): how the
                   trustworthiness scoring's consistency algorithm measures similarity between alternative responses considered plausible by the model.
-                  Supported similarity measures include: "semantic" (based on natural language inference),
+                  Supported similarity measures include - "semantic" (based on natural language inference),
                   "embedding" (based on vector embedding similarity), "embedding_large" (based on a larger embedding model),
                   "code" (based on model-based analysis designed to compare code), "discrepancy" (based on model-based analysis of possible discrepancies),
                   and "string" (based on character/word overlap). Set this to "string" for minimal runtimes/costs.
@@ -588,6 +590,7 @@ def validate(
                     "custom_eval_thresholds": custom_eval_thresholds,
                     "custom_metadata": custom_metadata,
                     "eval_scores": eval_scores,
+                    "messages": messages,
                     "options": options,
                     "quality_preset": quality_preset,
                     "task": task,
@@ -985,6 +988,7 @@ async def validate(
         custom_eval_thresholds: Optional[Dict[str, float]] | NotGiven = NOT_GIVEN,
         custom_metadata: Optional[object] | NotGiven = NOT_GIVEN,
         eval_scores: Optional[Dict[str, float]] | NotGiven = NOT_GIVEN,
+        messages: Optional[Iterable[project_validate_params.Message]] | NotGiven = NOT_GIVEN,
         options: Optional[project_validate_params.Options] | NotGiven = NOT_GIVEN,
         quality_preset: Literal["best", "high", "medium", "low", "base"] | NotGiven = NOT_GIVEN,
         task: Optional[str] | NotGiven = NOT_GIVEN,
@@ -1014,6 +1018,10 @@ async def validate(
           eval_scores: Scores assessing different aspects of the RAG system. If not provided, TLM will
               be used to generate scores.
 
+          messages: Optional message history to provide conversation context for the query. Used to
+              rewrite query into a self-contained version of itself. If not provided, the
+              query will be treated as self-contained.
+
           options: Typed dict of advanced configuration options for the Trustworthy Language Model.
               Many of these configurations are determined by the quality preset selected
               (learn about quality presets in the TLM [initialization method](./#class-tlm)).
@@ -1039,27 +1047,24 @@ async def validate(
                 `use_self_reflection` = True.
               - **base:** `num_candidate_responses` = 1, `num_consistency_samples` = 0,
                 `use_self_reflection` = False. When using `get_trustworthiness_score()` on
-                "base" preset, a cheaper self-reflection will be used to compute the
-                trustworthiness score.
-
-              By default, the TLM uses the "medium" quality preset. The default base LLM
-              `model` used is "gpt-4o-mini", and `max_tokens` is 512 for all quality presets.
-              You can set custom values for these arguments regardless of the quality preset
-              specified.
-
-              Args: model ({"gpt-4o-mini", "gpt-4o", "gpt-4.1", "gpt-4.1-mini",
-              "gpt-4.1-nano", "o4-mini", "o3", "o3-mini", "o1", "o1-mini", "gpt-4",
-              "gpt-4.5-preview", "gpt-3.5-turbo-16k", "claude-3.7-sonnet",
-              "claude-3.5-sonnet-v2", "claude-3.5-sonnet", "claude-3.5-haiku",
-              "claude-3-haiku", "nova-micro", "nova-lite", "nova-pro"}, default =
-              "gpt-4o-mini"): Underlying base LLM to use (better models yield better results,
-              faster models yield faster/cheaper results). - Models still in beta: "o3", "o1",
-              "o4-mini", "o3-mini", "o1-mini", "gpt-4.1", "gpt-4.1-mini", "gpt-4.1-nano",
-              "gpt-4.5-preview", "claude-3.7-sonnet", "claude-3.5-sonnet-v2",
-              "claude-3.5-haiku", "nova-micro", "nova-lite", "nova-pro". - Recommended models
-              for accuracy: "gpt-4.1", "o4-mini", "o3", "claude-3.7-sonnet",
-              "claude-3.5-sonnet-v2". - Recommended models for low latency/costs:
-              "gpt-4.1-nano", "nova-micro".
+                "base" preset, a faster self-reflection is employed.
+
+              By default, TLM uses the: "medium" `quality_preset`, "gpt-4.1-mini" base
+              `model`, and `max_tokens` is set to 512. You can set custom values for these
+              arguments regardless of the quality preset specified.
+
+              Args: model ({"gpt-4.1", "gpt-4.1-mini", "gpt-4.1-nano", "o4-mini", "o3",
+              "gpt-4.5-preview", "gpt-4o-mini", "gpt-4o", "o3-mini", "o1", "o1-mini", "gpt-4",
+              "gpt-3.5-turbo-16k", "claude-opus-4-0", "claude-sonnet-4-0",
+              "claude-3.7-sonnet", "claude-3.5-sonnet-v2", "claude-3.5-sonnet",
+              "claude-3.5-haiku", "claude-3-haiku", "nova-micro", "nova-lite", "nova-pro"},
+              default = "gpt-4.1-mini"): Underlying base LLM to use (better models yield
+              better results, faster models yield faster results). - Models still in beta:
+              "o3", "o1", "o4-mini", "o3-mini", "o1-mini", "gpt-4.5-preview",
+              "claude-opus-4-0", "claude-sonnet-4-0", "claude-3.7-sonnet",
+              "claude-3.5-haiku". - Recommended models for accuracy: "gpt-4.1", "o4-mini",
+              "o3", "claude-opus-4-0", "claude-sonnet-4-0". - Recommended models for low
+              latency/costs: "gpt-4.1-nano", "nova-micro".
 
                   max_tokens (int, default = 512): the maximum number of tokens that can be generated in the TLM response (and in internal trustworthiness scoring).
                   Higher values here may produce better (more reliable) TLM responses and trustworthiness scores, but at higher runtimes/costs.
@@ -1085,7 +1090,7 @@ async def validate(
 
                   similarity_measure ({"semantic", "string", "embedding", "embedding_large", "code", "discrepancy"}, default = "semantic"): how the
                   trustworthiness scoring's consistency algorithm measures similarity between alternative responses considered plausible by the model.
-                  Supported similarity measures include: "semantic" (based on natural language inference),
+                  Supported similarity measures include - "semantic" (based on natural language inference),
                   "embedding" (based on vector embedding similarity), "embedding_large" (based on a larger embedding model),
                   "code" (based on model-based analysis designed to compare code), "discrepancy" (based on model-based analysis of possible discrepancies),
                   and "string" (based on character/word overlap). Set this to "string" for minimal runtimes/costs.
@@ -1137,6 +1142,7 @@ async def validate(
                     "custom_eval_thresholds": custom_eval_thresholds,
                     "custom_metadata": custom_metadata,
                     "eval_scores": eval_scores,
+                    "messages": messages,
                     "options": options,
                     "quality_preset": quality_preset,
                     "task": task,