feat(api): api update

Author: stainless-app[bot]

.stats.yml

@@ -1,3 +1,3 @@
 configured_endpoints: 54
-openapi_spec_hash: 04e1b7aefbeff10daab249b153de147f
+openapi_spec_hash: ad0180a0926e2b6434601e6adf9c322a
 config_hash: 930284cfa37f835d949c8a1b124f4807

src/codex/resources/projects/projects.py

@@ -527,12 +527,11 @@ def validate(
               "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: "gpt-5", "gpt-5-mini", "gpt-5-nano", "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-5", "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".
+              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-5", "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".
 
                   log (list[str], default = []): optionally specify additional logs or metadata that TLM should return.
                   For instance, include "explanation" here to get explanations of why a response is scored with low trustworthiness.
@@ -1106,12 +1105,11 @@ async def validate(
               "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: "gpt-5", "gpt-5-mini", "gpt-5-nano", "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-5", "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".
+              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-5", "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".
 
                   log (list[str], default = []): optionally specify additional logs or metadata that TLM should return.
                   For instance, include "explanation" here to get explanations of why a response is scored with low trustworthiness.

src/codex/resources/tlm.py

@@ -101,12 +101,11 @@ def prompt(
               "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: "gpt-5", "gpt-5-mini", "gpt-5-nano", "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-5", "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".
+              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-5", "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".
 
                   log (list[str], default = []): optionally specify additional logs or metadata that TLM should return.
                   For instance, include "explanation" here to get explanations of why a response is scored with low trustworthiness.
@@ -245,12 +244,11 @@ def score(
               "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: "gpt-5", "gpt-5-mini", "gpt-5-nano", "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-5", "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".
+              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-5", "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".
 
                   log (list[str], default = []): optionally specify additional logs or metadata that TLM should return.
                   For instance, include "explanation" here to get explanations of why a response is scored with low trustworthiness.
@@ -405,12 +403,11 @@ async def prompt(
               "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: "gpt-5", "gpt-5-mini", "gpt-5-nano", "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-5", "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".
+              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-5", "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".
 
                   log (list[str], default = []): optionally specify additional logs or metadata that TLM should return.
                   For instance, include "explanation" here to get explanations of why a response is scored with low trustworthiness.
@@ -549,12 +546,11 @@ async def score(
               "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: "gpt-5", "gpt-5-mini", "gpt-5-nano", "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-5", "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".
+              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-5", "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".
 
                   log (list[str], default = []): optionally specify additional logs or metadata that TLM should return.
                   For instance, include "explanation" here to get explanations of why a response is scored with low trustworthiness.

src/codex/types/project_validate_params.py

@@ -130,12 +130,11 @@ class ProjectValidateParams(TypedDict, total=False):
     "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: "gpt-5", "gpt-5-mini", "gpt-5-nano", "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-5", "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".
+    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-5", "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".
 
         log (list[str], default = []): optionally specify additional logs or metadata that TLM should return.
         For instance, include "explanation" here to get explanations of why a response is scored with low trustworthiness.
@@ -653,6 +652,8 @@ class MessageChatCompletionDeveloperMessageParam(TypedDict, total=False):
 class Options(TypedDict, total=False):
     custom_eval_criteria: Iterable[object]
 
+    disable_persistence: bool
+
     disable_trustworthiness: bool
 
     log: List[str]

src/codex/types/tlm_prompt_params.py

@@ -52,12 +52,11 @@ class TlmPromptParams(TypedDict, total=False):
     "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: "gpt-5", "gpt-5-mini", "gpt-5-nano", "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-5", "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".
+    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-5", "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".
 
         log (list[str], default = []): optionally specify additional logs or metadata that TLM should return.
         For instance, include "explanation" here to get explanations of why a response is scored with low trustworthiness.
@@ -116,6 +115,8 @@ class TlmPromptParams(TypedDict, total=False):
 class Options(TypedDict, total=False):
     custom_eval_criteria: Iterable[object]
 
+    disable_persistence: bool
+
     disable_trustworthiness: bool
 
     log: List[str]

src/codex/types/tlm_score_params.py

@@ -54,12 +54,11 @@ class TlmScoreParams(TypedDict, total=False):
     "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: "gpt-5", "gpt-5-mini", "gpt-5-nano", "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-5", "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".
+    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-5", "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".
 
         log (list[str], default = []): optionally specify additional logs or metadata that TLM should return.
         For instance, include "explanation" here to get explanations of why a response is scored with low trustworthiness.
@@ -118,6 +117,8 @@ class TlmScoreParams(TypedDict, total=False):
 class Options(TypedDict, total=False):
     custom_eval_criteria: Iterable[object]
 
+    disable_persistence: bool
+
     disable_trustworthiness: bool
 
     log: List[str]

tests/api_resources/test_projects.py

@@ -617,6 +617,7 @@ def test_method_validate_with_all_params(self, client: Codex) -> None:
             ],
             options={
                 "custom_eval_criteria": [{}],
+                "disable_persistence": True,
                 "disable_trustworthiness": True,
                 "log": ["string"],
                 "max_tokens": 0,
@@ -1292,6 +1293,7 @@ async def test_method_validate_with_all_params(self, async_client: AsyncCodex) -
             ],
             options={
                 "custom_eval_criteria": [{}],
+                "disable_persistence": True,
                 "disable_trustworthiness": True,
                 "log": ["string"],
                 "max_tokens": 0,

tests/api_resources/test_tlm.py

@@ -33,6 +33,7 @@ def test_method_prompt_with_all_params(self, client: Codex) -> None:
             constrain_outputs=["string"],
             options={
                 "custom_eval_criteria": [{}],
+                "disable_persistence": True,
                 "disable_trustworthiness": True,
                 "log": ["string"],
                 "max_tokens": 0,
@@ -93,6 +94,7 @@ def test_method_score_with_all_params(self, client: Codex) -> None:
             constrain_outputs=["string"],
             options={
                 "custom_eval_criteria": [{}],
+                "disable_persistence": True,
                 "disable_trustworthiness": True,
                 "log": ["string"],
                 "max_tokens": 0,
@@ -159,6 +161,7 @@ async def test_method_prompt_with_all_params(self, async_client: AsyncCodex) ->
             constrain_outputs=["string"],
             options={
                 "custom_eval_criteria": [{}],
+                "disable_persistence": True,
                 "disable_trustworthiness": True,
                 "log": ["string"],
                 "max_tokens": 0,
@@ -219,6 +222,7 @@ async def test_method_score_with_all_params(self, async_client: AsyncCodex) -> N
             constrain_outputs=["string"],
             options={
                 "custom_eval_criteria": [{}],
+                "disable_persistence": True,
                 "disable_trustworthiness": True,
                 "log": ["string"],
                 "max_tokens": 0,