Bugfix/api naming convention

docs/SUMMARY.md

@@ -8,32 +8,35 @@
 * [Quick Start Guide](getting-started/quickstart.md)
 
 ## API Reference
-* [Client Configuration](api-reference/client.md)
-* [Public Client](api-reference/public-client.md)
-* [Evaluations](api-reference/evaluations.md)
-* [Results](api-reference/results.md)
-* [Models & Benchmarks](api-reference/models-benchmarks.md)
-* [Judges](api-reference/judges.md)
-* [Traces](api-reference/traces.md)
-* [Trace Evaluations](api-reference/trace-evaluations.md)
-* [Judge Optimizations](api-reference/judge-optimizations.md)
-* [Error Handling](api-reference/errors.md)
+* [Overview](api-reference/README.md)
+  * [Client Configuration](api-reference/client.md)
+  * [Public Client](api-reference/public-client.md)
+  * [Evaluations](api-reference/evaluations.md)
+  * [Results](api-reference/results.md)
+  * [Models & Benchmarks](api-reference/models-benchmarks.md)
+  * [Judges](api-reference/judges.md)
+  * [Traces](api-reference/traces.md)
+  * [Trace Evaluations](api-reference/trace-evaluations.md)
+  * [Judge Optimizations](api-reference/judge-optimizations.md)
+  * [Error Handling](api-reference/errors.md)
 
 ## Code Examples
-* [Creating Evaluations](examples/creating-evaluations.md)
-* [Retrieving Results](examples/retrieving-results.md)
-* [Models and Benchmarks](examples/models-and-benchmarks.md)
-* [Judges and Traces](examples/judges-and-traces.md)
-* [Public API](examples/public-api.md)
+* [Overview](examples/README.md)
+  * [Creating Evaluations](examples/creating-evaluations.md)
+  * [Retrieving Results](examples/retrieving-results.md)
+  * [Models and Benchmarks](examples/models-and-benchmarks.md)
+  * [Judges and Traces](examples/judges-and-traces.md)
+  * [Public API](examples/public-api.md)
 
 ## Troubleshooting
-* [Common Issues](troubleshooting/common-issues.md)
-* [Authentication Problems](troubleshooting/authentication.md)
-* [Error Codes Reference](troubleshooting/error-codes.md)
+* [Overview](troubleshooting/README.md)
+  * [Common Issues](troubleshooting/common-issues.md)
+  * [Authentication Problems](troubleshooting/authentication.md)
+  * [Error Codes Reference](troubleshooting/error-codes.md)
 
 ## Security Best Practices
-* [API Key Management](security/api-key-management.md)
-* [Environment Variables](security/environment-variables.md)
-* [Rate Limiting](security/rate-limiting.md)
-* [Data Privacy](security/data-privacy.md)
-
+* [Overview](security/README.md)
+  * [API Key Management](security/api-key-management.md)
+  * [Environment Variables](security/environment-variables.md)
+  * [Rate Limiting](security/rate-limiting.md)
+  * [Data Privacy](security/data-privacy.md)

examples/evaluation_sorting.py

@@ -23,7 +23,7 @@ async def main():
 
     # --- Get evaluations sorted by submission date (newest first)
     response = await client.evaluations.get_many(
-        sort_by="submittedAt",
+        sort_by="submitted_at",
         order="desc",
         page_size=5,
     )
@@ -34,7 +34,7 @@ async def main():
 
     # --- Get evaluations sorted by average duration (fastest first)
     response = await client.evaluations.get_many(
-        sort_by="averageDuration",
+        sort_by="average_duration",
         order="asc",
         page_size=5,
     )
@@ -66,7 +66,7 @@ async def main():
     # Replace with actual benchmark IDs from your organization
     response = await client.evaluations.get_many(
         benchmark_ids=["your-benchmark-id"],
-        sort_by="submittedAt",
+        sort_by="submitted_at",
         order="desc",
     )
     if response:

examples/public_evaluations.py

@@ -34,7 +34,7 @@ def main():
     response = client.evaluations.get_many(
         page=1,
         page_size=5,
-        sort_by="submittedAt",
+        sort_by="submitted_at",
         order="desc",
     )
     if response:

examples/public_models.py

@@ -35,7 +35,7 @@ def main():
     print(f"\nFound {response.total_count} open-source models")
 
     # --- Sort by release date (newest first)
-    response = client.models.get(sort_by="releasedAt", order="desc", page_size=5)
+    response = client.models.get(sort_by="released_at", order="desc", page_size=5)
     print(f"\nNewest 5 models:")
     for model in response.models:
         print(f"  - {model.name} (released_at={model.released_at})")

src/layerlens/_version.py

@@ -1,4 +1,4 @@
-__version__ = "1.3.2"
+__version__ = "1.3.3"
 
 # Will be templated during the build
 __git_commit__ = "__GIT_COMMIT__"

src/layerlens/models/benchmark.py

@@ -2,10 +2,12 @@
 
 from typing import List, Optional
 
-from pydantic import Field, BaseModel
+from pydantic import Field, BaseModel, ConfigDict
 
 
 class Benchmark(BaseModel):
+    model_config = ConfigDict(extra="allow")
+
     id: str
     key: str
     name: str
@@ -32,6 +34,7 @@ def type(self) -> str:
 class PublicBenchmark(Benchmark):
     description: Optional[str] = Field(None, alias="full_description")
     language: Optional[str] = None
+    categories: Optional[List[str]] = None
     prompt_count: Optional[int] = None
     deprecated: Optional[bool] = None
 

src/layerlens/models/model.py

@@ -2,10 +2,12 @@
 
 from typing import Optional
 
-from pydantic import BaseModel
+from pydantic import BaseModel, ConfigDict
 
 
 class Model(BaseModel):
+    model_config = ConfigDict(extra="allow")
+
     id: str
     key: str
     name: str

src/layerlens/resources/benchmarks/benchmarks.py

@@ -40,6 +40,8 @@ def get(
         type: Literal["custom", "public"] | None = None,
         name: Optional[str] = None,
         key: Optional[str] = None,
+        categories: Optional[List[str]] = None,
+        languages: Optional[List[str]] = None,
     ) -> Optional[List[Benchmark]]:
         base_url = f"/organizations/{self._client.organization_id}/projects/{self._client.project_id}/benchmarks"
 
@@ -49,6 +51,10 @@ def fetch(bench_type: str) -> BenchmarksResponse | None:
                 params["name"] = name
             if key:
                 params["key"] = key
+            if categories:
+                params["categories"] = ",".join(categories)
+            if languages:
+                params["languages"] = ",".join(languages)
 
             resp = self._get(
                 base_url,
@@ -77,6 +83,9 @@ def cast_benchmark(b: Benchmark, bench_type: str) -> Benchmark:
             if resp:
                 benchmarks.extend([cast_benchmark(b, type) for b in resp.data.benchmarks])
 
+        if name:
+            benchmarks = [b for b in benchmarks if name.lower() in b.name.lower()]
+
         return benchmarks
 
     def get_by_id(self, id: str, *, timeout: float | httpx.Timeout | None = DEFAULT_TIMEOUT) -> Optional[Benchmark]:
@@ -304,6 +313,8 @@ async def get(
         type: Literal["custom", "public"] | None = None,
         name: Optional[str] = None,
         key: Optional[str] = None,
+        categories: Optional[List[str]] = None,
+        languages: Optional[List[str]] = None,
     ) -> Optional[List[Benchmark]]:
         base_url = f"/organizations/{self._client.organization_id}/projects/{self._client.project_id}/benchmarks"
 
@@ -313,6 +324,10 @@ async def fetch(bench_type: str) -> Optional[BenchmarksResponse]:
                 params["name"] = name
             if key:
                 params["key"] = key
+            if categories:
+                params["categories"] = ",".join(categories)
+            if languages:
+                params["languages"] = ",".join(languages)
 
             resp = await self._get(
                 base_url,
@@ -341,6 +356,9 @@ def cast_benchmark(b: Benchmark, bench_type: str) -> Benchmark:
             if resp:
                 benchmarks.extend([cast_benchmark(b, type) for b in resp.data.benchmarks])
 
+        if name:
+            benchmarks = [b for b in benchmarks if name.lower() in b.name.lower()]
+
         return benchmarks
 
     async def get_by_id(

src/layerlens/resources/comparisons/comparisons.py

@@ -37,9 +37,9 @@ def compare(
         if page is not None:
             params["page"] = str(page)
         if page_size is not None:
-            params["pageSize"] = str(page_size)
+            params["page_size"] = str(page_size)
         if outcome_filter:
-            params["outcomeFilter"] = outcome_filter
+            params["outcome_filter"] = outcome_filter
         if search:
             params["search"] = search
 
@@ -79,7 +79,7 @@ def compare_models(
             model_ids=[model_id_1],
             benchmark_ids=[benchmark_id],
             status=EvaluationStatus.SUCCESS,
-            sort_by="submittedAt",
+            sort_by="submitted_at",
             order="desc",
             page_size=1,
             timeout=timeout,
@@ -90,7 +90,7 @@ def compare_models(
             model_ids=[model_id_2],
             benchmark_ids=[benchmark_id],
             status=EvaluationStatus.SUCCESS,
-            sort_by="submittedAt",
+            sort_by="submitted_at",
             order="desc",
             page_size=1,
             timeout=timeout,
@@ -127,9 +127,9 @@ async def compare(
         if page is not None:
             params["page"] = str(page)
         if page_size is not None:
-            params["pageSize"] = str(page_size)
+            params["page_size"] = str(page_size)
         if outcome_filter:
-            params["outcomeFilter"] = outcome_filter
+            params["outcome_filter"] = outcome_filter
         if search:
             params["search"] = search
 
@@ -169,7 +169,7 @@ async def compare_models(
             model_ids=[model_id_1],
             benchmark_ids=[benchmark_id],
             status=EvaluationStatus.SUCCESS,
-            sort_by="submittedAt",
+            sort_by="submitted_at",
             order="desc",
             page_size=1,
             timeout=timeout,
@@ -180,7 +180,7 @@ async def compare_models(
             model_ids=[model_id_2],
             benchmark_ids=[benchmark_id],
             status=EvaluationStatus.SUCCESS,
-            sort_by="submittedAt",
+            sort_by="submitted_at",
             order="desc",
             page_size=1,
             timeout=timeout,

src/layerlens/resources/evaluations/evaluations.py

@@ -81,7 +81,7 @@ def get_many(
         *,
         page: Optional[int] = None,
         page_size: Optional[int] = None,
-        sort_by: Optional[Literal["submittedAt", "accuracy", "averageDuration"]] = None,
+        sort_by: Optional[Literal["submitted_at", "accuracy", "average_duration"]] = None,
         order: Optional[Literal["asc", "desc"]] = None,
         model_ids: Optional[List[str]] = None,
         benchmark_ids: Optional[List[str]] = None,
@@ -94,7 +94,7 @@ def get_many(
         Args:
             page: Page number for pagination (1-based, defaults to 1 if not provided)
             page_size: Number of evaluations per page (default: 100, optional)
-            sort_by: Sort evaluations by field (submittedAt, accuracy, averageDuration)
+            sort_by: Sort evaluations by field (submitted_at, accuracy, average_duration)
             order: Sort order (asc or desc)
             model_ids: Filter by model IDs
             benchmark_ids: Filter by benchmark/dataset IDs
@@ -105,18 +105,18 @@ def get_many(
             EvaluationsResponse object or None
         """
         params = {
-            "organizationID": self._client.organization_id,
-            "projectID": self._client.project_id,
+            "organization_id": self._client.organization_id,
+            "project_id": self._client.project_id,
         }
 
         effective_page_size = min(max(page_size, 1), MAX_PAGE_SIZE) if page_size is not None else DEFAULT_PAGE_SIZE
         effective_page = page if page is not None else DEFAULT_PAGE
 
         params["page"] = str(effective_page)
-        params["pageSize"] = str(effective_page_size)
+        params["page_size"] = str(effective_page_size)
 
         if sort_by:
-            params["sortBy"] = sort_by
+            params["sort_by"] = sort_by
         if order:
             params["order"] = order
         if model_ids:
@@ -154,7 +154,7 @@ def get_many(
 
         try:
             return EvaluationsResponse.model_validate(resp_with_pagination)
-        except Exception:
+        except (ValueError, KeyError):
             return None
 
     def wait_for_completion(
@@ -236,7 +236,7 @@ async def get_many(
         *,
         page: Optional[int] = None,
         page_size: Optional[int] = None,
-        sort_by: Optional[Literal["submittedAt", "accuracy", "averageDuration"]] = None,
+        sort_by: Optional[Literal["submitted_at", "accuracy", "average_duration"]] = None,
         order: Optional[Literal["asc", "desc"]] = None,
         model_ids: Optional[List[str]] = None,
         benchmark_ids: Optional[List[str]] = None,
@@ -249,7 +249,7 @@ async def get_many(
         Args:
             page: Page number for pagination (1-based, defaults to 1 if not provided)
             page_size: Number of evaluations per page (default: 100, optional)
-            sort_by: Sort evaluations by field (submittedAt, accuracy, averageDuration)
+            sort_by: Sort evaluations by field (submitted_at, accuracy, average_duration)
             order: Sort order (asc or desc)
             model_ids: Filter by model IDs
             benchmark_ids: Filter by benchmark/dataset IDs
@@ -260,18 +260,18 @@ async def get_many(
             EvaluationsResponse object or None
         """
         params = {
-            "organizationID": self._client.organization_id,
-            "projectID": self._client.project_id,
+            "organization_id": self._client.organization_id,
+            "project_id": self._client.project_id,
         }
 
         effective_page_size = min(max(page_size, 1), MAX_PAGE_SIZE) if page_size is not None else DEFAULT_PAGE_SIZE
         effective_page = page if page is not None else DEFAULT_PAGE
 
         params["page"] = str(effective_page)
-        params["pageSize"] = str(effective_page_size)
+        params["page_size"] = str(effective_page_size)
 
         if sort_by:
-            params["sortBy"] = sort_by
+            params["sort_by"] = sort_by
         if order:
             params["order"] = order
         if model_ids:
@@ -309,7 +309,7 @@ async def get_many(
 
         try:
             return EvaluationsResponse.model_validate(resp_with_pagination)
-        except Exception:
+        except (ValueError, KeyError):
             return None
 
     async def wait_for_completion(

src/layerlens/resources/judges/judges.py

@@ -82,7 +82,7 @@ def get_many(
         effective_page = page if page is not None else DEFAULT_PAGE
 
         params["page"] = str(effective_page)
-        params["pageSize"] = str(effective_page_size)
+        params["page_size"] = str(effective_page_size)
 
         resp = self._get(
             self._base_url(),
@@ -221,7 +221,7 @@ async def get_many(
         effective_page = page if page is not None else DEFAULT_PAGE
 
         params["page"] = str(effective_page)
-        params["pageSize"] = str(effective_page_size)
+        params["page_size"] = str(effective_page_size)
 
         resp = await self._get(
             self._base_url(),