Merge branch 'main' into ragtool-migration

benchmarking/k8s-benchmark/README.md

@@ -34,13 +34,12 @@ This data enables data-driven architectural decisions and performance optimizati
 
 **1. Deploy base k8s infrastructure:**
 ```bash
-cd ../k8s
+cd ../../docs/source/distributions/k8s
 ./apply.sh
 ```
 
 **2. Deploy benchmark components:**
 ```bash
-cd ../k8s-benchmark
 ./apply.sh
 ```
 
@@ -56,7 +55,6 @@ kubectl get pods
 
 **Benchmark Llama Stack (default):**
 ```bash
-cd docs/source/distributions/k8s-benchmark/
 ./run-benchmark.sh
 ```
 

benchmarking/k8s-benchmark/benchmark.py

@@ -14,7 +14,7 @@ import os
 import random
 import statistics
 import time
-from typing import Tuple
+
 import aiohttp
 
 
@@ -55,50 +55,50 @@ class BenchmarkStats:
 
         total_time = self.end_time - self.start_time
         success_rate = (self.success_count / self.total_requests) * 100
-        
-        print(f"\n{'='*60}")
-        print(f"BENCHMARK RESULTS")
-        
-        print(f"\nResponse Time Statistics:")
+
+        print(f"\n{'=' * 60}")
+        print("BENCHMARK RESULTS")
+
+        print("\nResponse Time Statistics:")
         print(f"  Mean: {statistics.mean(self.response_times):.3f}s")
         print(f"  Median: {statistics.median(self.response_times):.3f}s")
         print(f"  Min: {min(self.response_times):.3f}s")
         print(f"  Max: {max(self.response_times):.3f}s")
-        
+
         if len(self.response_times) > 1:
             print(f"  Std Dev: {statistics.stdev(self.response_times):.3f}s")
-            
+
         percentiles = [50, 90, 95, 99]
         sorted_times = sorted(self.response_times)
-        print(f"\nPercentiles:")
+        print("\nPercentiles:")
         for p in percentiles:
             idx = int(len(sorted_times) * p / 100) - 1
             idx = max(0, min(idx, len(sorted_times) - 1))
             print(f"  P{p}: {sorted_times[idx]:.3f}s")
-            
+
         if self.ttft_times:
-            print(f"\nTime to First Token (TTFT) Statistics:")
+            print("\nTime to First Token (TTFT) Statistics:")
             print(f"  Mean: {statistics.mean(self.ttft_times):.3f}s")
             print(f"  Median: {statistics.median(self.ttft_times):.3f}s")
             print(f"  Min: {min(self.ttft_times):.3f}s")
             print(f"  Max: {max(self.ttft_times):.3f}s")
-            
+
             if len(self.ttft_times) > 1:
                 print(f"  Std Dev: {statistics.stdev(self.ttft_times):.3f}s")
-                
+
             sorted_ttft = sorted(self.ttft_times)
-            print(f"\nTTFT Percentiles:")
+            print("\nTTFT Percentiles:")
             for p in percentiles:
                 idx = int(len(sorted_ttft) * p / 100) - 1
                 idx = max(0, min(idx, len(sorted_ttft) - 1))
                 print(f"  P{p}: {sorted_ttft[idx]:.3f}s")
-            
+
         if self.chunks_received:
-            print(f"\nStreaming Statistics:")
+            print("\nStreaming Statistics:")
             print(f"  Mean chunks per response: {statistics.mean(self.chunks_received):.1f}")
             print(f"  Total chunks received: {sum(self.chunks_received)}")
-        
-        print(f"{'='*60}")
+
+        print(f"{'=' * 60}")
         print(f"Total time: {total_time:.2f}s")
         print(f"Concurrent users: {self.concurrent_users}")
         print(f"Total requests: {self.total_requests}")
@@ -106,16 +106,16 @@ class BenchmarkStats:
         print(f"Failed requests: {len(self.errors)}")
         print(f"Success rate: {success_rate:.1f}%")
         print(f"Requests per second: {self.success_count / total_time:.2f}")
-        
+
         if self.errors:
-            print(f"\nErrors (showing first 5):")
+            print("\nErrors (showing first 5):")
             for error in self.errors[:5]:
                 print(f"  {error}")
 
 
 class LlamaStackBenchmark:
     def __init__(self, base_url: str, model_id: str):
-        self.base_url = base_url.rstrip('/')
+        self.base_url = base_url.rstrip("/")
         self.model_id = model_id
         self.headers = {"Content-Type": "application/json"}
         self.test_messages = [
@@ -126,74 +126,67 @@ class LlamaStackBenchmark:
             [
                 {"role": "user", "content": "What is machine learning?"},
                 {"role": "assistant", "content": "Machine learning is a subset of AI..."},
-                {"role": "user", "content": "Can you give me a practical example?"}
-            ]
+                {"role": "user", "content": "Can you give me a practical example?"},
+            ],
         ]
 
-
-    async def make_async_streaming_request(self) -> Tuple[float, int, float | None, str | None]:
+    async def make_async_streaming_request(self) -> tuple[float, int, float | None, str | None]:
         """Make a single async streaming chat completion request."""
         messages = random.choice(self.test_messages)
-        payload = {
-            "model": self.model_id,
-            "messages": messages,
-            "stream": True,
-            "max_tokens": 100
-        }
-        
+        payload = {"model": self.model_id, "messages": messages, "stream": True, "max_tokens": 100}
+
         start_time = time.time()
         chunks_received = 0
         ttft = None
         error = None
-        
+
         session = aiohttp.ClientSession()
-        
+
         try:
             async with session.post(
                 f"{self.base_url}/chat/completions",
                 headers=self.headers,
                 json=payload,
-                timeout=aiohttp.ClientTimeout(total=30)
+                timeout=aiohttp.ClientTimeout(total=30),
             ) as response:
                 if response.status == 200:
                     async for line in response.content:
                         if line:
-                            line_str = line.decode('utf-8').strip()
-                            if line_str.startswith('data: '):
+                            line_str = line.decode("utf-8").strip()
+                            if line_str.startswith("data: "):
                                 chunks_received += 1
                                 if ttft is None:
                                     ttft = time.time() - start_time
-                                if line_str == 'data: [DONE]':
+                                if line_str == "data: [DONE]":
                                     break
-                    
+
                     if chunks_received == 0:
                         error = "No streaming chunks received"
                 else:
                     text = await response.text()
                     error = f"HTTP {response.status}: {text[:100]}"
-                    
+
         except Exception as e:
             error = f"Request error: {str(e)}"
         finally:
             await session.close()
-            
+
         response_time = time.time() - start_time
         return response_time, chunks_received, ttft, error
 
-
     async def run_benchmark(self, duration: int, concurrent_users: int) -> BenchmarkStats:
         """Run benchmark using async requests for specified duration."""
         stats = BenchmarkStats()
         stats.concurrent_users = concurrent_users
         stats.start_time = time.time()
-        
+
         print(f"Starting benchmark: {duration}s duration, {concurrent_users} concurrent users")
         print(f"Target URL: {self.base_url}/chat/completions")
         print(f"Model: {self.model_id}")
-        
+
         connector = aiohttp.TCPConnector(limit=concurrent_users)
-        async with aiohttp.ClientSession(connector=connector) as session:
-            
+        async with aiohttp.ClientSession(connector=connector):
+
             async def worker(worker_id: int):
                 """Worker that sends requests sequentially until canceled."""
                 request_count = 0
@@ -202,12 +195,12 @@ class LlamaStackBenchmark:
                         response_time, chunks, ttft, error = await self.make_async_streaming_request()
                         await stats.add_result(response_time, chunks, ttft, error)
                         request_count += 1
-                        
+
                     except asyncio.CancelledError:
                         break
                     except Exception as e:
                         await stats.add_result(0, 0, None, f"Worker {worker_id} error: {str(e)}")
-            
+
             # Progress reporting task
             async def progress_reporter():
                 last_report_time = time.time()
@@ -216,48 +209,52 @@ class LlamaStackBenchmark:
                         await asyncio.sleep(1)  # Report every second
                         if time.time() >= last_report_time + 10:  # Report every 10 seconds
                             elapsed = time.time() - stats.start_time
-                            print(f"Completed: {stats.total_requests} requests in {elapsed:.1f}s, RPS: {stats.total_requests / elapsed:.1f}")
+                            print(
+                                f"Completed: {stats.total_requests} requests in {elapsed:.1f}s, RPS: {stats.total_requests / elapsed:.1f}"
+                            )
                             last_report_time = time.time()
                     except asyncio.CancelledError:
                         break
-            
+
             # Spawn concurrent workers
             tasks = [asyncio.create_task(worker(i)) for i in range(concurrent_users)]
             progress_task = asyncio.create_task(progress_reporter())
             tasks.append(progress_task)
-            
+
             # Wait for duration then cancel all tasks
             await asyncio.sleep(duration)
-            
+
             for task in tasks:
                 task.cancel()
-            
+
             # Wait for all tasks to complete
             await asyncio.gather(*tasks, return_exceptions=True)
-        
+
         stats.end_time = time.time()
         return stats
 
 
 def main():
     parser = argparse.ArgumentParser(description="Llama Stack Benchmark Tool")
-    parser.add_argument("--base-url", default=os.getenv("BENCHMARK_BASE_URL", "http://localhost:8000/v1/openai/v1"),
-                       help="Base URL for the API (default: http://localhost:8000/v1/openai/v1)")
-    parser.add_argument("--model", default=os.getenv("INFERENCE_MODEL", "test-model"),
-                       help="Model ID to use for requests")
-    parser.add_argument("--duration", type=int, default=60,
-                       help="Duration in seconds to run benchmark (default: 60)")
-    parser.add_argument("--concurrent", type=int, default=10,
-                       help="Number of concurrent users (default: 10)")
-    
+    parser.add_argument(
+        "--base-url",
+        default=os.getenv("BENCHMARK_BASE_URL", "http://localhost:8000/v1/openai/v1"),
+        help="Base URL for the API (default: http://localhost:8000/v1/openai/v1)",
+    )
+    parser.add_argument(
+        "--model", default=os.getenv("INFERENCE_MODEL", "test-model"), help="Model ID to use for requests"
+    )
+    parser.add_argument("--duration", type=int, default=60, help="Duration in seconds to run benchmark (default: 60)")
+    parser.add_argument("--concurrent", type=int, default=10, help="Number of concurrent users (default: 10)")
+
     args = parser.parse_args()
-    
+
     benchmark = LlamaStackBenchmark(args.base_url, args.model)
-    
+
     try:
         stats = asyncio.run(benchmark.run_benchmark(args.duration, args.concurrent))
         stats.print_summary()
-        
+
     except KeyboardInterrupt:
         print("\nBenchmark interrupted by user")
     except Exception as e:

benchmarking/k8s-benchmark/openai-mock-server.py

@@ -11,180 +11,192 @@ OpenAI-compatible mock server that returns:
 - Valid OpenAI-formatted chat completion responses with dynamic content
 """
 
-from flask import Flask, request, jsonify, Response
-import time
-import random
-import uuid
-import json
 import argparse
+import json
 import os
+import random
+import time
+import uuid
+
+from flask import Flask, Response, jsonify, request
 
 app = Flask(__name__)
 
+
 # Models from environment variables
 def get_models():
     models_str = os.getenv("MOCK_MODELS", "meta-llama/Llama-3.2-3B-Instruct")
     model_ids = [m.strip() for m in models_str.split(",") if m.strip()]
-    
+
     return {
         "object": "list",
         "data": [
-            {
-                "id": model_id,
-                "object": "model",
-                "created": 1234567890,
-                "owned_by": "vllm"
-            }
-            for model_id in model_ids
-        ]
+            {"id": model_id, "object": "model", "created": 1234567890, "owned_by": "vllm"} for model_id in model_ids
+        ],
     }
 
+
 def generate_random_text(length=50):
     """Generate random but coherent text for responses."""
     words = [
-        "Hello", "there", "I'm", "an", "AI", "assistant", "ready", "to", "help", "you",
-        "with", "your", "questions", "and", "tasks", "today", "Let", "me","know", "what",
-        "you'd", "like", "to", "discuss", "or", "explore", "together", "I", "can", "assist",
-        "with", "various", "topics", "including", "coding", "writing", "analysis", "and", "more"
+        "Hello",
+        "there",
+        "I'm",
+        "an",
+        "AI",
+        "assistant",
+        "ready",
+        "to",
+        "help",
+        "you",
+        "with",
+        "your",
+        "questions",
+        "and",
+        "tasks",
+        "today",
+        "Let",
+        "me",
+        "know",
+        "what",
+        "you'd",
+        "like",
+        "to",
+        "discuss",
+        "or",
+        "explore",
+        "together",
+        "I",
+        "can",
+        "assist",
+        "with",
+        "various",
+        "topics",
+        "including",
+        "coding",
+        "writing",
+        "analysis",
+        "and",
+        "more",
     ]
     return " ".join(random.choices(words, k=length))
 
-@app.route('/v1/models', methods=['GET'])
+
+@app.route("/v1/models", methods=["GET"])
 def list_models():
     models = get_models()
     print(f"[MOCK] Returning models: {[m['id'] for m in models['data']]}")
     return jsonify(models)
 
-@app.route('/v1/chat/completions', methods=['POST'])
+
+@app.route("/v1/chat/completions", methods=["POST"])
 def chat_completions():
     """Return OpenAI-formatted chat completion responses."""
     data = request.get_json()
-    default_model = get_models()['data'][0]['id']
-    model = data.get('model', default_model)
-    messages = data.get('messages', [])
-    stream = data.get('stream', False)
-     
+    default_model = get_models()["data"][0]["id"]
+    model = data.get("model", default_model)
+    messages = data.get("messages", [])
+    stream = data.get("stream", False)
+
     print(f"[MOCK] Chat completion request - model: {model}, stream: {stream}")
-    
+
     if stream:
         return handle_streaming_completion(model, messages)
     else:
         return handle_non_streaming_completion(model, messages)
 
+
 def handle_non_streaming_completion(model, messages):
     response_text = generate_random_text(random.randint(20, 80))
-    
+
     # Calculate realistic token counts
-    prompt_tokens = sum(len(str(msg.get('content', '')).split()) for msg in messages)
+    prompt_tokens = sum(len(str(msg.get("content", "")).split()) for msg in messages)
     completion_tokens = len(response_text.split())
-    
+
     response = {
         "id": f"chatcmpl-{uuid.uuid4().hex[:8]}",
         "object": "chat.completion",
         "created": int(time.time()),
         "model": model,
-        "choices": [
-            {
-                "index": 0,
-                "message": {
-                    "role": "assistant",
-                    "content": response_text
-                },
-                "finish_reason": "stop"
-            }
-        ],
+        "choices": [{"index": 0, "message": {"role": "assistant", "content": response_text}, "finish_reason": "stop"}],
         "usage": {
             "prompt_tokens": prompt_tokens,
             "completion_tokens": completion_tokens,
-            "total_tokens": prompt_tokens + completion_tokens
-        }
+            "total_tokens": prompt_tokens + completion_tokens,
+        },
     }
-    
+
     return jsonify(response)
 
+
 def handle_streaming_completion(model, messages):
     def generate_stream():
         # Generate response text
         full_response = generate_random_text(random.randint(30, 100))
         words = full_response.split()
-        
+
         # Send initial chunk
         initial_chunk = {
             "id": f"chatcmpl-{uuid.uuid4().hex[:8]}",
             "object": "chat.completion.chunk",
             "created": int(time.time()),
             "model": model,
-            "choices": [
-                {
-                    "index": 0,
-                    "delta": {"role": "assistant", "content": ""}
-                }
-            ]
+            "choices": [{"index": 0, "delta": {"role": "assistant", "content": ""}}],
         }
         yield f"data: {json.dumps(initial_chunk)}\n\n"
-        
+
         # Send word by word
         for i, word in enumerate(words):
             chunk = {
                 "id": f"chatcmpl-{uuid.uuid4().hex[:8]}",
-                "object": "chat.completion.chunk", 
+                "object": "chat.completion.chunk",
                 "created": int(time.time()),
                 "model": model,
-                "choices": [
-                    {
-                        "index": 0,
-                        "delta": {"content": f"{word} " if i < len(words) - 1 else word}
-                    }
-                ]
+                "choices": [{"index": 0, "delta": {"content": f"{word} " if i < len(words) - 1 else word}}],
             }
             yield f"data: {json.dumps(chunk)}\n\n"
             # Configurable delay to simulate realistic streaming
             stream_delay = float(os.getenv("STREAM_DELAY_SECONDS", "0.005"))
             time.sleep(stream_delay)
-        
+
         # Send final chunk
         final_chunk = {
             "id": f"chatcmpl-{uuid.uuid4().hex[:8]}",
             "object": "chat.completion.chunk",
             "created": int(time.time()),
             "model": model,
-            "choices": [
-                {
-                    "index": 0,
-                    "delta": {"content": ""},
-                    "finish_reason": "stop"
-                }
-            ]
+            "choices": [{"index": 0, "delta": {"content": ""}, "finish_reason": "stop"}],
         }
         yield f"data: {json.dumps(final_chunk)}\n\n"
         yield "data: [DONE]\n\n"
-    
+
     return Response(
         generate_stream(),
-        mimetype='text/event-stream',
+        mimetype="text/event-stream",
         headers={
-            'Cache-Control': 'no-cache',
-            'Connection': 'keep-alive',
-            'Access-Control-Allow-Origin': '*',
-        }
+            "Cache-Control": "no-cache",
+            "Connection": "keep-alive",
+            "Access-Control-Allow-Origin": "*",
+        },
     )
 
-@app.route('/health', methods=['GET'])
+
+@app.route("/health", methods=["GET"])
 def health():
     return jsonify({"status": "healthy", "type": "openai-mock"})
 
-if __name__ == '__main__':
-    parser = argparse.ArgumentParser(description='OpenAI-compatible mock server')
-    parser.add_argument('--port', type=int, default=8081, 
-                       help='Port to run the server on (default: 8081)')
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="OpenAI-compatible mock server")
+    parser.add_argument("--port", type=int, default=8081, help="Port to run the server on (default: 8081)")
     args = parser.parse_args()
-    
+
     port = args.port
-    
+
     models = get_models()
     print("Starting OpenAI-compatible mock server...")
     print(f"- /models endpoint with: {[m['id'] for m in models['data']]}")
     print("- OpenAI-formatted chat/completion responses with dynamic content")
     print("- Streaming support with valid SSE format")
     print(f"- Listening on: http://0.0.0.0:{port}")
-    app.run(host='0.0.0.0', port=port, debug=False)
+    app.run(host="0.0.0.0", port=port, debug=False)

docs/source/contributing/index.md

@@ -35,5 +35,5 @@ testing/record-replay
 
 ### Benchmarking
 
-```{include} ../../../docs/source/distributions/k8s-benchmark/README.md
+```{include} ../../../benchmarking/k8s-benchmark/README.md
 ```

llama_stack/ui/package-lock.json

@@ -3578,6 +3578,13 @@
         "tailwindcss": "4.1.6"
       }
     },
+    "node_modules/@tailwindcss/node/node_modules/tailwindcss": {
+      "version": "4.1.6",
+      "resolved": "https://registry.npmjs.org/tailwindcss/-/tailwindcss-4.1.6.tgz",
+      "integrity": "sha512-j0cGLTreM6u4OWzBeLBpycK0WIh8w7kSwcUsQZoGLHZ7xDTdM69lN64AgoIEEwFi0tnhs4wSykUa5YWxAzgFYg==",
+      "dev": true,
+      "license": "MIT"
+    },
     "node_modules/@tailwindcss/oxide": {
       "version": "4.1.6",
       "resolved": "https://registry.npmjs.org/@tailwindcss/oxide/-/oxide-4.1.6.tgz",
@@ -3838,6 +3845,13 @@
         "tailwindcss": "4.1.6"
       }
     },
+    "node_modules/@tailwindcss/postcss/node_modules/tailwindcss": {
+      "version": "4.1.6",
+      "resolved": "https://registry.npmjs.org/tailwindcss/-/tailwindcss-4.1.6.tgz",
+      "integrity": "sha512-j0cGLTreM6u4OWzBeLBpycK0WIh8w7kSwcUsQZoGLHZ7xDTdM69lN64AgoIEEwFi0tnhs4wSykUa5YWxAzgFYg==",
+      "dev": true,
+      "license": "MIT"
+    },
     "node_modules/@testing-library/dom": {
       "version": "10.4.1",
       "resolved": "https://registry.npmjs.org/@testing-library/dom/-/dom-10.4.1.tgz",
@@ -13843,9 +13857,9 @@
       }
     },
     "node_modules/tailwindcss": {
-      "version": "4.1.6",
-      "resolved": "https://registry.npmjs.org/tailwindcss/-/tailwindcss-4.1.6.tgz",
-      "integrity": "sha512-j0cGLTreM6u4OWzBeLBpycK0WIh8w7kSwcUsQZoGLHZ7xDTdM69lN64AgoIEEwFi0tnhs4wSykUa5YWxAzgFYg==",
+      "version": "4.1.13",
+      "resolved": "https://registry.npmjs.org/tailwindcss/-/tailwindcss-4.1.13.tgz",
+      "integrity": "sha512-i+zidfmTqtwquj4hMEwdjshYYgMbOrPzb9a0M3ZgNa0JMoZeFC6bxZvO8yr8ozS6ix2SDz0+mvryPeBs2TFE+w==",
       "dev": true,
       "license": "MIT"
     },

tests/integration/telemetry/test_openai_telemetry.py

@@ -49,16 +49,13 @@ def setup_openai_telemetry_data(llama_stack_client, text_model_id):
         traces = llama_stack_client.telemetry.query_traces(limit=10)
         if len(traces) >= 5:  # 5 OpenAI completion traces
             break
-        time.sleep(1)
+        time.sleep(0.1)
 
     if len(traces) < 5:
         pytest.fail(
             f"Failed to create sufficient OpenAI completion telemetry data after 30s. Got {len(traces)} traces."
         )
 
-    # Wait for 5 seconds to ensure traces has completed logging
-    time.sleep(5)
-
     yield
 
 
@@ -185,11 +182,13 @@ def test_openai_completion_creates_telemetry(llama_stack_client, text_model_id):
     assert len(response.choices) > 0, "Response should have at least one choice"
 
     # Wait for telemetry to be recorded
-    time.sleep(3)
-
-    # Check that we have more traces now
-    final_traces = llama_stack_client.telemetry.query_traces(limit=20)
-    final_count = len(final_traces)
+    start_time = time.time()
+    while time.time() - start_time < 30:
+        final_traces = llama_stack_client.telemetry.query_traces(limit=20)
+        final_count = len(final_traces)
+        if final_count > initial_count:
+            break
+        time.sleep(0.1)
 
     # Should have at least as many traces as before (might have more due to other activity)
     assert final_count >= initial_count, "Should have at least as many traces after OpenAI call"

tests/integration/telemetry/test_telemetry.py

@@ -42,14 +42,11 @@ def setup_telemetry_data(llama_stack_client, text_model_id):
         traces = llama_stack_client.telemetry.query_traces(limit=10)
         if len(traces) >= 4:
             break
-        time.sleep(1)
+        time.sleep(0.1)
 
     if len(traces) < 4:
         pytest.fail(f"Failed to create sufficient telemetry data after 30s. Got {len(traces)} traces.")
 
-    # Wait for 5 seconds to ensure traces has completed logging
-    time.sleep(5)
-
     yield
 
 

tests/integration/telemetry/test_telemetry_metrics.py

@@ -46,10 +46,7 @@ def setup_telemetry_metrics_data(openai_client, client_with_models, text_model_i
                 break
         except Exception:
             pass
-        time.sleep(1)
-
-    # Wait additional time to ensure all metrics are processed
-    time.sleep(5)
+        time.sleep(0.1)
 
     # Return the token lists for use in tests
     return {"prompt_tokens": prompt_tokens, "completion_tokens": completion_tokens, "total_tokens": total_tokens}

uv.lock

@@ -2023,7 +2023,7 @@ wheels = [
 
 [[package]]
 name = "locust"
-version = "2.39.1"
+version = "2.40.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "configargparse" },
@@ -2035,6 +2035,7 @@ dependencies = [
     { name = "locust-cloud" },
     { name = "msgpack" },
     { name = "psutil" },
+    { name = "pytest" },
     { name = "python-engineio" },
     { name = "python-socketio", extra = ["client"] },
     { name = "pywin32", marker = "sys_platform == 'win32'" },
@@ -2043,9 +2044,9 @@ dependencies = [
     { name = "setuptools" },
     { name = "werkzeug" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/95/c8/10aa5445c404eed389b56877e6714c1787190cc09dd70059ce3765979ec5/locust-2.39.1.tar.gz", hash = "sha256:6bdd19e27edf9a1c84391d6cf6e9a737dfb832be7dfbf39053191ae31b9cc498", size = 1409902, upload-time = "2025-08-29T17:41:01.544Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/01/22/82f40176473a98c9479bed667d3ad21bb859d2cb67f6880a6b0b6a725e45/locust-2.40.1.tar.gz", hash = "sha256:5bde76c1cf7e412071670f926f34844e119210c93f07a4cf9fc4cb93c60a578a", size = 1411606, upload-time = "2025-09-05T15:57:35.76Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ec/b3/b2f4b2ca88b1e72eba7be2b2982533b887f8b709d222db78eb9602aa5121/locust-2.39.1-py3-none-any.whl", hash = "sha256:fd5148f2f1a4ed34aee968abc4393674e69d1b5e1b54db50a397f6eb09ce0b04", size = 1428155, upload-time = "2025-08-29T17:41:00.245Z" },
+    { url = "https://files.pythonhosted.org/packages/3b/e6/9c6335ab16becf4f8ad3da6083ab78793c56ec1ca496d6f7c74660c21c3f/locust-2.40.1-py3-none-any.whl", hash = "sha256:ef0517f9bb5ed0afa7035014faaf944802917e07da8649461aaaf5e5f3ba8a65", size = 1430154, upload-time = "2025-09-05T15:57:33.233Z" },
 ]
 
 [[package]]
@@ -2619,7 +2620,7 @@ wheels = [
 
 [[package]]
 name = "openai"
-version = "1.102.0"
+version = "1.107.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "anyio" },
@@ -2631,9 +2632,9 @@ dependencies = [
     { name = "tqdm" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/07/55/da5598ed5c6bdd9939633854049cddc5cbac0da938dfcfcb3c6b119c16c0/openai-1.102.0.tar.gz", hash = "sha256:2e0153bcd64a6523071e90211cbfca1f2bbc5ceedd0993ba932a5869f93b7fc9", size = 519027, upload-time = "2025-08-26T20:50:29.397Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/88/67/d6498de300f83ff57a79cb7aa96ef3bef8d6f070c3ded0f1b5b45442a6bc/openai-1.107.0.tar.gz", hash = "sha256:43e04927584e57d0e9e640ee0077c78baf8150098be96ebd5c512539b6c4e9a4", size = 566056, upload-time = "2025-09-08T19:25:47.604Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/bd/0d/c9e7016d82c53c5b5e23e2bad36daebb8921ed44f69c0a985c6529a35106/openai-1.102.0-py3-none-any.whl", hash = "sha256:d751a7e95e222b5325306362ad02a7aa96e1fab3ed05b5888ce1c7ca63451345", size = 812015, upload-time = "2025-08-26T20:50:27.219Z" },
+    { url = "https://files.pythonhosted.org/packages/91/ed/e8a4fd20390f2858b95227c288df8fe0c835f7c77625f7583609161684ba/openai-1.107.0-py3-none-any.whl", hash = "sha256:3dcfa3cbb116bd6924b27913b8da28c4a787379ff60049588547a1013e6d6438", size = 950968, upload-time = "2025-09-08T19:25:45.552Z" },
 ]
 
 [[package]]
@@ -3540,7 +3541,7 @@ wheels = [
 
 [[package]]
 name = "pytest"
-version = "8.4.1"
+version = "8.4.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "colorama", marker = "sys_platform == 'win32'" },
@@ -3549,9 +3550,9 @@ dependencies = [
     { name = "pluggy" },
     { name = "pygments" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/08/ba/45911d754e8eba3d5a841a5ce61a65a685ff1798421ac054f85aa8747dfb/pytest-8.4.1.tar.gz", hash = "sha256:7c67fd69174877359ed9371ec3af8a3d2b04741818c51e5e99cc1742251fa93c", size = 1517714, upload-time = "2025-06-18T05:48:06.109Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/a3/5c/00a0e072241553e1a7496d638deababa67c5058571567b92a7eaa258397c/pytest-8.4.2.tar.gz", hash = "sha256:86c0d0b93306b961d58d62a4db4879f27fe25513d4b969df351abdddb3c30e01", size = 1519618, upload-time = "2025-09-04T14:34:22.711Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/29/16/c8a903f4c4dffe7a12843191437d7cd8e32751d5de349d45d3fe69544e87/pytest-8.4.1-py3-none-any.whl", hash = "sha256:539c70ba6fcead8e78eebbf1115e8b589e7565830d7d006a8723f19ac8a0afb7", size = 365474, upload-time = "2025-06-18T05:48:03.955Z" },
+    { url = "https://files.pythonhosted.org/packages/a8/a4/20da314d277121d6534b3a980b29035dcd51e6744bd79075a6ce8fa4eb8d/pytest-8.4.2-py3-none-any.whl", hash = "sha256:872f880de3fc3a5bdc88a11b39c9710c3497a547cfa9320bc3c5e62fbf272e79", size = 365750, upload-time = "2025-09-04T14:34:20.226Z" },
 ]
 
 [[package]]