diff --git a/docs/my-website/docs/pass_through/assembly_ai.md b/docs/my-website/docs/pass_through/assembly_ai.md
index 4606640c5c4..c7c70639e7e 100644
--- a/docs/my-website/docs/pass_through/assembly_ai.md
+++ b/docs/my-website/docs/pass_through/assembly_ai.md
@@ -1,31 +1,36 @@
-# Assembly AI
+# AssemblyAI
 
-Pass-through endpoints for Assembly AI - call Assembly AI endpoints, in native format (no translation).
+Pass-through endpoints for AssemblyAI - call AssemblyAI endpoints, in native format (no translation).
 
-| Feature | Supported | Notes | 
+| Feature | Supported | Notes |
 |-------|-------|-------|
 | Cost Tracking | ✅ | works across all integrations |
 | Logging | ✅ | works across all integrations |
 
 
-Supports **ALL** Assembly AI Endpoints
+Supports **ALL** AssemblyAI Endpoints
 
-[**See All Assembly AI Endpoints**](https://www.assemblyai.com/docs/api-reference)
+[**See All AssemblyAI Endpoints**](https://www.assemblyai.com/docs/api-reference)
 
 
-<iframe width="840" height="500" src="https://www.loom.com/embed/aac3f4d74592448992254bfa79b9f62d?sid=267cd0ab-d92b-42fa-b97a-9f385ef8930c" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>
+## Supported Routes
+
+| AssemblyAI Service | LiteLLM Route | AssemblyAI Base URL |
+|-------------------|---------------|---------------------|
+| Speech-to-Text (US) | `/assemblyai/*` | `api.assemblyai.com` |
+| Speech-to-Text (EU) | `/eu.assemblyai/*` | `eu.api.assemblyai.com` |
 
 ## Quick Start
 
-Let's call the Assembly AI [`/v2/transcripts` endpoint](https://www.assemblyai.com/docs/api-reference/transcripts)
+Let's call the AssemblyAI [`/v2/transcripts` endpoint](https://www.assemblyai.com/docs/api-reference/transcripts)
 
-1. Add Assembly AI API Key to your environment 
+1. Add AssemblyAI API Key to your environment
 
 ```bash
 export ASSEMBLYAI_API_KEY=""
 ```
 
-2. Start LiteLLM Proxy 
+2. Start LiteLLM Proxy
 
 ```bash
 litellm
@@ -33,53 +38,157 @@ litellm
 # RUNNING on http://0.0.0.0:4000
 ```
 
-3. Test it! 
+3. Test it!
 
-Let's call the Assembly AI `/v2/transcripts` endpoint
+Let's call the AssemblyAI [`/v2/transcripts` endpoint](https://www.assemblyai.com/docs/api-reference/transcripts). Includes commented-out [Speech Understanding](https://www.assemblyai.com/docs/speech-understanding) features you can toggle on.
 
 ```python
 import assemblyai as aai
 
-LITELLM_VIRTUAL_KEY = "sk-1234" # <your-virtual-key>
-LITELLM_PROXY_BASE_URL = "http://0.0.0.0:4000/assemblyai" # <your-proxy-base-url>/assemblyai
+aai.settings.base_url = "http://0.0.0.0:4000/assemblyai" # <your-proxy-base-url>/assemblyai
+aai.settings.api_key = "Bearer sk-1234" # Bearer <your-virtual-key>
 
-aai.settings.api_key = f"Bearer {LITELLM_VIRTUAL_KEY}"
-aai.settings.base_url = LITELLM_PROXY_BASE_URL
+# Use a publicly-accessible URL
+audio_file = "https://assembly.ai/wildfires.mp3"
 
-# URL of the file to transcribe
-FILE_URL = "https://assembly.ai/wildfires.mp3"
+# Or use a local file:
+# audio_file = "./example.mp3"
 
-# You can also transcribe a local file by passing in a file path
-# FILE_URL = './path/to/file.mp3'
+config = aai.TranscriptionConfig(
+    speech_models=["universal-3-pro", "universal-2"],
+    language_detection=True,
+    speaker_labels=True,
+    # Speech understanding features
+    # sentiment_analysis=True,
+    # entity_detection=True,
+    # auto_chapters=True,
+    # summarization=True,
+    # summary_type=aai.SummarizationType.bullets,
+    # redact_pii=True,
+    # content_safety=True,
+)
 
-transcriber = aai.Transcriber()
-transcript = transcriber.transcribe(FILE_URL)
-print(transcript)
-print(transcript.id)
-```
+transcript = aai.Transcriber().transcribe(audio_file, config=config)
 
-## Calling Assembly AI EU endpoints
+if transcript.status == aai.TranscriptStatus.error:
+    raise RuntimeError(f"Transcription failed: {transcript.error}")
 
-If you want to send your request to the Assembly AI EU endpoint, you can do so by setting the `LITELLM_PROXY_BASE_URL` to `<your-proxy-base-url>/eu.assemblyai`
+print(f"\nFull Transcript:\n\n{transcript.text}")
 
+# Optionally print speaker diarization results
+# for utterance in transcript.utterances:
+#     print(f"Speaker {utterance.speaker}: {utterance.text}")
+```
+
+4. [Prompting with Universal-3 Pro](https://www.assemblyai.com/docs/speech-to-text/prompting) (optional)
 
 ```python
 import assemblyai as aai
 
-LITELLM_VIRTUAL_KEY = "sk-1234" # <your-virtual-key>
-LITELLM_PROXY_BASE_URL = "http://0.0.0.0:4000/eu.assemblyai" # <your-proxy-base-url>/eu.assemblyai
+aai.settings.base_url = "http://0.0.0.0:4000/assemblyai" # <your-proxy-base-url>/assemblyai
+aai.settings.api_key = "Bearer sk-1234" # Bearer <your-virtual-key>
+
+audio_file = "https://assemblyaiassets.com/audios/verbatim.mp3"
+
+config = aai.TranscriptionConfig(
+    speech_models=["universal-3-pro", "universal-2"],
+    language_detection=True,
+    prompt="Produce a transcript suitable for conversational analysis. Every disfluency is meaningful data. Include: fillers (um, uh, er, ah, hmm, mhm, like, you know, I mean), repetitions (I I, the the), restarts (I was- I went), stutters (th-that, b-but, no-not), and informal speech (gonna, wanna, gotta)",
+)
+
+transcript = aai.Transcriber().transcribe(audio_file, config)
+
+print(transcript.text)
+```
+
+## Calling AssemblyAI EU endpoints
+
+If you want to send your request to the AssemblyAI EU endpoint, you can do so by setting the `LITELLM_PROXY_BASE_URL` to `<your-proxy-base-url>/eu.assemblyai`
 
-aai.settings.api_key = f"Bearer {LITELLM_VIRTUAL_KEY}"
-aai.settings.base_url = LITELLM_PROXY_BASE_URL
 
-# URL of the file to transcribe
-FILE_URL = "https://assembly.ai/wildfires.mp3"
+```python
+import assemblyai as aai
+
+aai.settings.base_url = "http://0.0.0.0:4000/eu.assemblyai" # <your-proxy-base-url>/eu.assemblyai
+aai.settings.api_key = "Bearer sk-1234" # Bearer <your-virtual-key>
 
-# You can also transcribe a local file by passing in a file path
-# FILE_URL = './path/to/file.mp3'
+# Use a publicly-accessible URL
+audio_file = "https://assembly.ai/wildfires.mp3"
+
+# Or use a local file:
+# audio_file = "./path/to/file.mp3"
 
 transcriber = aai.Transcriber()
-transcript = transcriber.transcribe(FILE_URL)
+transcript = transcriber.transcribe(audio_file)
 print(transcript)
 print(transcript.id)
 ```
+
+## LLM Gateway
+
+Use AssemblyAI's [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway) as an OpenAI-compatible provider — a unified API for Claude, GPT, and Gemini models with full LiteLLM logging, guardrails, and cost tracking support.
+
+[**See Available Models**](https://www.assemblyai.com/docs/llm-gateway#available-models)
+
+### Usage
+
+#### LiteLLM Python SDK
+
+```python
+import litellm
+import os
+
+os.environ["ASSEMBLYAI_API_KEY"] = "your-assemblyai-api-key"
+
+response = litellm.completion(
+    model="assemblyai/claude-sonnet-4-5-20250929",
+    messages=[{"role": "user", "content": "What is the capital of France?"}]
+)
+
+print(response.choices[0].message.content)
+```
+
+#### LiteLLM Proxy
+
+1. Config
+
+```yaml
+model_list:
+  - model_name: assemblyai/*
+    litellm_params:
+      model: assemblyai/*
+      api_key: os.environ/ASSEMBLYAI_API_KEY
+```
+
+2. Start proxy
+
+```bash
+litellm --config config.yaml
+
+# RUNNING on http://0.0.0.0:4000
+```
+
+3. Test it!
+
+```python
+import requests
+
+headers = {
+    "authorization": "Bearer sk-1234"  # Bearer <your-virtual-key>
+}
+
+response = requests.post(
+    "http://0.0.0.0:4000/v1/chat/completions",
+    headers=headers,
+    json={
+        "model": "assemblyai/claude-sonnet-4-5-20250929",
+        "messages": [
+            {"role": "user", "content": "What is the capital of France?"}
+        ],
+        "max_tokens": 1000
+    }
+)
+
+result = response.json()
+print(result["choices"][0]["message"]["content"])
+```
diff --git a/docs/my-website/docs/proxy/prometheus.md b/docs/my-website/docs/proxy/prometheus.md
index 18a139d1d29..d8f0d83b59d 100644
--- a/docs/my-website/docs/proxy/prometheus.md
+++ b/docs/my-website/docs/proxy/prometheus.md
@@ -113,6 +113,31 @@ litellm_settings:
 ```
 
 
+## Pod Health Metrics
+
+Use these to measure per-pod queue depth and diagnose latency that occurs **before** LiteLLM starts processing a request.
+
+| Metric Name | Type | Description |
+|---|---|---|
+| `litellm_in_flight_requests` | Gauge | Number of HTTP requests currently in-flight on this uvicorn worker. Tracks the pod's queue depth in real time. With multiple workers, values are summed across all live workers (`livesum`). |
+
+### When to use this
+
+LiteLLM measures latency from when its handler starts. If a request waits in uvicorn's event loop before the handler runs, that wait is invisible to LiteLLM's own logs. `litellm_in_flight_requests` shows how loaded the pod was at any point in time.
+
+```
+high in_flight_requests + high ALB TargetResponseTime → pod overloaded, scale out
+low  in_flight_requests + high ALB TargetResponseTime → delay is pre-ASGI (event loop blocking)
+```
+
+You can also check the current value directly without Prometheus:
+
+```bash
+curl http://localhost:4000/health/backlog \
+  -H "Authorization: Bearer sk-..."
+# {"in_flight_requests": 47}
+```
+
 ## Proxy Level Tracking Metrics
 
 Use this to track overall LiteLLM Proxy usage.
diff --git a/docs/my-website/docs/troubleshoot/latency_overhead.md b/docs/my-website/docs/troubleshoot/latency_overhead.md
index cfb2cb43a7e..dd7f012dcde 100644
--- a/docs/my-website/docs/troubleshoot/latency_overhead.md
+++ b/docs/my-website/docs/troubleshoot/latency_overhead.md
@@ -2,9 +2,41 @@
 
 Use this guide when you see unexpected latency overhead between LiteLLM proxy and the LLM provider.
 
+## The Invisible Latency Gap
+
+LiteLLM measures latency from when its handler starts. If a request waits in uvicorn's event loop **before** the handler runs, that wait is invisible to LiteLLM's own logs.
+
+```
+T=0   Request arrives at load balancer
+      [queue wait — LiteLLM never logs this]
+T=10  LiteLLM handler starts → timer begins
+T=20  Response sent
+
+LiteLLM logs: 10s    User experiences: 20s
+```
+
+To measure the pre-handler wait, poll `/health/backlog` on each pod:
+
+```bash
+curl http://localhost:4000/health/backlog \
+  -H "Authorization: Bearer sk-..."
+# {"in_flight_requests": 47}
+```
+
+Or scrape the `litellm_in_flight_requests` Prometheus gauge at `/metrics`.
+
+| `in_flight_requests` | ALB `TargetResponseTime` | Diagnosis |
+|---|---|---|
+| High | High | Pod overloaded → scale out |
+| Low | High | Delay is pre-ASGI — check for sync blocking code or event loop saturation |
+| High | Normal | Pod is busy but healthy, no queue buildup |
+
+If you're on **AWS ALB**, correlate `litellm_in_flight_requests` spikes with ALB's `TargetResponseTime` CloudWatch metric. The gap between what ALB reports and what LiteLLM logs is the invisible wait.
+
 ## Quick Checklist
 
-1. **Collect the `x-litellm-overhead-duration-ms` response header** — this tells you LiteLLM's total overhead on every request. Start here.
+1. **Check `in_flight_requests` on each pod** via `/health/backlog` or the `litellm_in_flight_requests` Prometheus gauge — this tells you if requests are queuing before LiteLLM starts processing. Start here for unexplained latency.
+2. **Collect the `x-litellm-overhead-duration-ms` response header** — this tells you LiteLLM's total overhead on every request.
 2. **Is DEBUG logging enabled?** This is the #1 cause of latency with large payloads.
 3. **Are you sending large base64 payloads?** (images, PDFs) — see [Large Payload Overhead](#large-payload-overhead).
 4. **Enable detailed timing headers** to pinpoint where time is spent.
diff --git a/litellm-proxy-extras/litellm_proxy_extras/migrations/20260228000000_add_claude_code_plugin_table/migration.sql b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260228000000_add_claude_code_plugin_table/migration.sql
new file mode 100644
index 00000000000..e2a3694e8ef
--- /dev/null
+++ b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260228000000_add_claude_code_plugin_table/migration.sql
@@ -0,0 +1,18 @@
+-- CreateTable
+CREATE TABLE "LiteLLM_ClaudeCodePluginTable" (
+    "id" TEXT NOT NULL,
+    "name" TEXT NOT NULL,
+    "version" TEXT,
+    "description" TEXT,
+    "manifest_json" TEXT,
+    "files_json" TEXT DEFAULT '{}',
+    "enabled" BOOLEAN NOT NULL DEFAULT true,
+    "created_at" TIMESTAMP(3) DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP(3) DEFAULT CURRENT_TIMESTAMP,
+    "created_by" TEXT,
+
+    CONSTRAINT "LiteLLM_ClaudeCodePluginTable_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateIndex
+CREATE UNIQUE INDEX "LiteLLM_ClaudeCodePluginTable_name_key" ON "LiteLLM_ClaudeCodePluginTable"("name");
diff --git a/litellm/llms/bedrock/chat/converse_transformation.py b/litellm/llms/bedrock/chat/converse_transformation.py
index 306d63b77d0..a0f2f65fb7f 100644
--- a/litellm/llms/bedrock/chat/converse_transformation.py
+++ b/litellm/llms/bedrock/chat/converse_transformation.py
@@ -511,6 +511,7 @@ def get_supported_openai_params(self, model: str) -> List[str]:
             "response_format",
             "requestMetadata",
             "service_tier",
+            "parallel_tool_calls",
         ]
 
         if (
@@ -913,6 +914,13 @@ def map_openai_params(
                 )
                 if _tool_choice_value is not None:
                     optional_params["tool_choice"] = _tool_choice_value
+            if param == "parallel_tool_calls":
+                disable_parallel = not value
+                optional_params["_parallel_tool_use_config"] = {
+                    "tool_choice": {
+                        "disable_parallel_tool_use": disable_parallel
+                    }
+                }
             if param == "thinking":
                 optional_params["thinking"] = value
             elif param == "reasoning_effort" and isinstance(value, str):
diff --git a/litellm/llms/openai/chat/gpt_5_transformation.py b/litellm/llms/openai/chat/gpt_5_transformation.py
index 05c003c8b7a..e491770a24d 100644
--- a/litellm/llms/openai/chat/gpt_5_transformation.py
+++ b/litellm/llms/openai/chat/gpt_5_transformation.py
@@ -40,11 +40,16 @@ def is_model_gpt_5_1_model(cls, model: str) -> bool:
         
         gpt-5.1/5.2 support temperature when reasoning_effort="none",
         unlike base gpt-5 which only supports temperature=1. Excludes
-        pro variants which keep stricter knobs.
+        pro variants which keep stricter knobs and gpt-5.2-chat variants
+        which only support temperature=1.
         """
         model_name = model.split("/")[-1]
         is_gpt_5_1 = model_name.startswith("gpt-5.1")
-        is_gpt_5_2 = model_name.startswith("gpt-5.2") and "pro" not in model_name
+        is_gpt_5_2 = (
+            model_name.startswith("gpt-5.2")
+            and "pro" not in model_name
+            and not model_name.startswith("gpt-5.2-chat")
+        )
         return is_gpt_5_1 or is_gpt_5_2
 
     @classmethod
diff --git a/litellm/llms/openai_like/providers.json b/litellm/llms/openai_like/providers.json
index 1b1b1c2f8cc..b3125d4ad38 100644
--- a/litellm/llms/openai_like/providers.json
+++ b/litellm/llms/openai_like/providers.json
@@ -90,5 +90,9 @@
     "headers": {
       "api-subscription-key": "{api_key}"
     }
+  },
+  "assemblyai": {
+    "base_url": "https://llm-gateway.assemblyai.com/v1",
+    "api_key_env": "ASSEMBLYAI_API_KEY"
   }
 }
diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index b21f23ac022..1ac8a347775 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -19210,6 +19210,39 @@
         "supports_tool_choice": true,
         "supports_vision": false
     },
+    "gpt-audio-1.5": {
+        "input_cost_per_audio_token": 3.2e-05,
+        "input_cost_per_token": 2.5e-06,
+        "litellm_provider": "openai",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_audio_token": 6.4e-05,
+        "output_cost_per_token": 1e-05,
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true,
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": false,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
     "gpt-audio-2025-08-28": {
         "input_cost_per_audio_token": 3.2e-05,
         "input_cost_per_token": 2.5e-06,
@@ -20927,6 +20960,38 @@
         "supports_system_messages": true,
         "supports_tool_choice": true
     },
+    "gpt-realtime-1.5": {
+        "cache_creation_input_audio_token_cost": 4e-07,
+        "cache_read_input_token_cost": 4e-07,
+        "input_cost_per_audio_token": 3.2e-05,
+        "input_cost_per_image": 5e-06,
+        "input_cost_per_token": 4e-06,
+        "litellm_provider": "openai",
+        "max_input_tokens": 32000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
+        "mode": "chat",
+        "output_cost_per_audio_token": 6.4e-05,
+        "output_cost_per_token": 1.6e-05,
+        "supported_endpoints": [
+            "/v1/realtime"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true
+    },
     "gpt-realtime-mini": {
         "cache_creation_input_audio_token_cost": 3e-07,
         "cache_read_input_audio_token_cost": 3e-07,
@@ -26650,8 +26715,8 @@
         "mode": "chat",
         "output_cost_per_token": 0.0,
         "source": "https://platform.publicai.co/docs",
-        "supports_function_calling": true,
-        "supports_tool_choice": true
+        "supports_function_calling": false,
+        "supports_tool_choice": false
     },
     "publicai/swiss-ai/apertus-70b-instruct": {
         "input_cost_per_token": 0.0,
@@ -26662,8 +26727,8 @@
         "mode": "chat",
         "output_cost_per_token": 0.0,
         "source": "https://platform.publicai.co/docs",
-        "supports_function_calling": true,
-        "supports_tool_choice": true
+        "supports_function_calling": false,
+        "supports_tool_choice": false
     },
     "publicai/aisingapore/Gemma-SEA-LION-v4-27B-IT": {
         "input_cost_per_token": 0.0,
@@ -32991,6 +33056,7 @@
         "supports_web_search": true
     },
     "xai/grok-2-vision-1212": {
+        "deprecation_date": "2026-02-28",
         "input_cost_per_image": 2e-06,
         "input_cost_per_token": 2e-06,
         "litellm_provider": "xai",
@@ -33095,6 +33161,7 @@
     },
     "xai/grok-3-mini": {
         "cache_read_input_token_cost": 7.5e-08,
+        "deprecation_date": "2026-02-28",
         "input_cost_per_token": 3e-07,
         "litellm_provider": "xai",
         "max_input_tokens": 131072,
@@ -33111,6 +33178,7 @@
     },
     "xai/grok-3-mini-beta": {
         "cache_read_input_token_cost": 7.5e-08,
+        "deprecation_date": "2026-02-28",
         "input_cost_per_token": 3e-07,
         "litellm_provider": "xai",
         "max_input_tokens": 131072,
diff --git a/litellm/proxy/_types.py b/litellm/proxy/_types.py
index dfc2ba59d96..3af878f49d3 100644
--- a/litellm/proxy/_types.py
+++ b/litellm/proxy/_types.py
@@ -431,6 +431,7 @@ class LiteLLMRoutes(enum.Enum):
 
     agent_routes = [
         "/v1/agents",
+        "/v1/agents/{agent_id}",
         "/agents",
         "/a2a/{agent_id}",
         "/a2a/{agent_id}/message/send",
diff --git a/litellm/proxy/agent_endpoints/endpoints.py b/litellm/proxy/agent_endpoints/endpoints.py
index b411b81b434..65674d01be7 100644
--- a/litellm/proxy/agent_endpoints/endpoints.py
+++ b/litellm/proxy/agent_endpoints/endpoints.py
@@ -31,6 +31,23 @@
 router = APIRouter()
 
 
+def _check_agent_management_permission(user_api_key_dict: UserAPIKeyAuth) -> None:
+    """
+    Raises HTTP 403 if the caller does not have permission to create, update,
+    or delete agents.  Only PROXY_ADMIN users are allowed to perform these
+    write operations.
+    """
+    if user_api_key_dict.user_role != LitellmUserRoles.PROXY_ADMIN:
+        raise HTTPException(
+            status_code=403,
+            detail={
+                "error": "Only proxy admins can create, update, or delete agents. Your role={}".format(
+                    user_api_key_dict.user_role
+                )
+            },
+        )
+
+
 @router.get(
     "/v1/agents",
     tags=["[beta] A2A Agents"],
@@ -164,6 +181,8 @@ async def create_agent(
     """
     from litellm.proxy.proxy_server import prisma_client
 
+    _check_agent_management_permission(user_api_key_dict)
+
     if prisma_client is None:
         raise HTTPException(status_code=500, detail="Prisma client not initialized")
 
@@ -302,6 +321,8 @@ async def update_agent(
     """
     from litellm.proxy.proxy_server import prisma_client
 
+    _check_agent_management_permission(user_api_key_dict)
+
     if prisma_client is None:
         raise HTTPException(
             status_code=500, detail=CommonProxyErrors.db_not_connected_error.value
@@ -391,6 +412,8 @@ async def patch_agent(
     """
     from litellm.proxy.proxy_server import prisma_client
 
+    _check_agent_management_permission(user_api_key_dict)
+
     if prisma_client is None:
         raise HTTPException(
             status_code=500, detail=CommonProxyErrors.db_not_connected_error.value
@@ -441,7 +464,10 @@ async def patch_agent(
     tags=["Agents"],
     dependencies=[Depends(user_api_key_auth)],
 )
-async def delete_agent(agent_id: str):
+async def delete_agent(
+    agent_id: str,
+    user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
+):
     """
     Delete an agent
 
@@ -460,6 +486,8 @@ async def delete_agent(agent_id: str):
     """
     from litellm.proxy.proxy_server import prisma_client
 
+    _check_agent_management_permission(user_api_key_dict)
+
     if prisma_client is None:
         raise HTTPException(status_code=500, detail="Prisma client not initialized")
 
diff --git a/litellm/proxy/health_endpoints/_health_endpoints.py b/litellm/proxy/health_endpoints/_health_endpoints.py
index 4496ad92631..95b1836d8a9 100644
--- a/litellm/proxy/health_endpoints/_health_endpoints.py
+++ b/litellm/proxy/health_endpoints/_health_endpoints.py
@@ -33,6 +33,9 @@
     perform_health_check,
     run_with_timeout,
 )
+from litellm.proxy.middleware.in_flight_requests_middleware import (
+    get_in_flight_requests,
+)
 from litellm.secret_managers.main import get_secret
 
 #### Health ENDPOINTS ####
@@ -1297,6 +1300,23 @@ async def health_readiness():
         raise HTTPException(status_code=503, detail=f"Service Unhealthy ({str(e)})")
 
 
+@router.get(
+    "/health/backlog",
+    tags=["health"],
+    dependencies=[Depends(user_api_key_auth)],
+)
+async def health_backlog():
+    """
+    Returns the number of HTTP requests currently in-flight on this uvicorn worker.
+
+    Use this to measure per-pod queue depth. A high value means the worker is
+    processing many concurrent requests — requests arriving now will have to wait
+    for the event loop to get to them, adding latency before LiteLLM even starts
+    its own timer.
+    """
+    return {"in_flight_requests": get_in_flight_requests()}
+
+
 @router.get(
     "/health/liveliness",  # Historical LiteLLM name; doesn't match k8s terminology but kept for backwards compatibility
     tags=["health"],
diff --git a/litellm/proxy/middleware/in_flight_requests_middleware.py b/litellm/proxy/middleware/in_flight_requests_middleware.py
new file mode 100644
index 00000000000..d615640d870
--- /dev/null
+++ b/litellm/proxy/middleware/in_flight_requests_middleware.py
@@ -0,0 +1,81 @@
+"""
+Tracks the number of HTTP requests currently in-flight on this uvicorn worker.
+
+Used by /health/backlog to expose per-pod queue depth, and emitted as the
+Prometheus gauge `litellm_in_flight_requests`.
+"""
+
+import os
+from typing import Optional
+
+from starlette.types import ASGIApp, Receive, Scope, Send
+
+
+class InFlightRequestsMiddleware:
+    """
+    ASGI middleware that increments a counter when a request arrives and
+    decrements it when the response is sent (or an error occurs).
+
+    The counter is class-level and therefore scoped to a single uvicorn worker
+    process — exactly the per-pod granularity we want.
+
+    Also updates the `litellm_in_flight_requests` Prometheus gauge if
+    prometheus_client is installed. The gauge is lazily initialised on the
+    first request so that PROMETHEUS_MULTIPROC_DIR is already set by the time
+    we register the metric. Initialisation is attempted only once — if
+    prometheus_client is absent the class remembers and never retries.
+    """
+
+    _in_flight: int = 0
+    _gauge: Optional[object] = None
+    _gauge_init_attempted: bool = False
+
+    def __init__(self, app: ASGIApp) -> None:
+        self.app = app
+
+    async def __call__(self, scope: Scope, receive: Receive, send: Send) -> None:
+        if scope["type"] != "http":
+            await self.app(scope, receive, send)
+            return
+
+        InFlightRequestsMiddleware._in_flight += 1
+        gauge = InFlightRequestsMiddleware._get_gauge()
+        if gauge is not None:
+            gauge.inc()  # type: ignore[union-attr]
+        try:
+            await self.app(scope, receive, send)
+        finally:
+            InFlightRequestsMiddleware._in_flight -= 1
+            if gauge is not None:
+                gauge.dec()  # type: ignore[union-attr]
+
+    @staticmethod
+    def get_count() -> int:
+        """Return the number of HTTP requests currently in-flight."""
+        return InFlightRequestsMiddleware._in_flight
+
+    @staticmethod
+    def _get_gauge() -> Optional[object]:
+        if InFlightRequestsMiddleware._gauge_init_attempted:
+            return InFlightRequestsMiddleware._gauge
+        InFlightRequestsMiddleware._gauge_init_attempted = True
+        try:
+            from prometheus_client import Gauge
+
+            kwargs = {}
+            if "PROMETHEUS_MULTIPROC_DIR" in os.environ:
+                # livesum aggregates across all worker processes in the scrape response
+                kwargs["multiprocess_mode"] = "livesum"
+            InFlightRequestsMiddleware._gauge = Gauge(
+                "litellm_in_flight_requests",
+                "Number of HTTP requests currently in-flight on this uvicorn worker",
+                **kwargs,
+            )
+        except Exception:
+            InFlightRequestsMiddleware._gauge = None
+        return InFlightRequestsMiddleware._gauge
+
+
+def get_in_flight_requests() -> int:
+    """Module-level convenience wrapper used by the /health/backlog endpoint."""
+    return InFlightRequestsMiddleware.get_count()
diff --git a/litellm/proxy/prometheus_cleanup.py b/litellm/proxy/prometheus_cleanup.py
index 6d935a8dd90..6353588532a 100644
--- a/litellm/proxy/prometheus_cleanup.py
+++ b/litellm/proxy/prometheus_cleanup.py
@@ -28,3 +28,20 @@ def wipe_directory(directory: str) -> None:
         verbose_proxy_logger.info(
             f"Prometheus cleanup: wiped {deleted} stale .db files from {directory}"
         )
+
+
+def mark_worker_exit(worker_pid: int) -> None:
+    """Remove prometheus .db files for a dead worker. Called by gunicorn child_exit hook."""
+    if not os.environ.get("PROMETHEUS_MULTIPROC_DIR"):
+        return
+    try:
+        from prometheus_client import multiprocess
+
+        multiprocess.mark_process_dead(worker_pid)
+        verbose_proxy_logger.info(
+            f"Prometheus cleanup: marked worker {worker_pid} as dead"
+        )
+    except Exception as e:
+        verbose_proxy_logger.warning(
+            f"Failed to mark prometheus worker {worker_pid} as dead: {e}"
+        )
diff --git a/litellm/proxy/proxy_cli.py b/litellm/proxy/proxy_cli.py
index f5163114983..921d86c35c1 100644
--- a/litellm/proxy/proxy_cli.py
+++ b/litellm/proxy/proxy_cli.py
@@ -277,6 +277,15 @@ def load(self):
         if max_requests_before_restart is not None:
             gunicorn_options["max_requests"] = max_requests_before_restart
 
+        # Clean up prometheus .db files when a worker exits (prevents ghost gauge values)
+        if os.environ.get("PROMETHEUS_MULTIPROC_DIR"):
+            from litellm.proxy.prometheus_cleanup import mark_worker_exit
+
+            def child_exit(server, worker):
+                mark_worker_exit(worker.pid)
+
+            gunicorn_options["child_exit"] = child_exit
+
         if ssl_certfile_path is not None and ssl_keyfile_path is not None:
             print(  # noqa
                 f"\033[1;32mLiteLLM Proxy: Using SSL with certfile: {ssl_certfile_path} and keyfile: {ssl_keyfile_path}\033[0m\n"  # noqa
diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py
index be76c2ac5fb..48025863641 100644
--- a/litellm/proxy/proxy_server.py
+++ b/litellm/proxy/proxy_server.py
@@ -424,6 +424,9 @@ def generate_feedback_box():
     router as user_agent_analytics_router,
 )
 from litellm.proxy.management_helpers.audit_logs import create_audit_log_for_update
+from litellm.proxy.middleware.in_flight_requests_middleware import (
+    InFlightRequestsMiddleware,
+)
 from litellm.proxy.middleware.prometheus_auth_middleware import PrometheusAuthMiddleware
 from litellm.proxy.ocr_endpoints.endpoints import router as ocr_router
 from litellm.proxy.openai_evals_endpoints.endpoints import router as evals_router
@@ -1404,6 +1407,7 @@ def _restructure_ui_html_files(ui_root: str) -> None:
 )
 
 app.add_middleware(PrometheusAuthMiddleware)
+app.add_middleware(InFlightRequestsMiddleware)
 
 
 def mount_swagger_ui():
diff --git a/litellm/types/integrations/prometheus.py b/litellm/types/integrations/prometheus.py
index 2c75276d9ca..0856d8a6f9b 100644
--- a/litellm/types/integrations/prometheus.py
+++ b/litellm/types/integrations/prometheus.py
@@ -237,6 +237,7 @@ class UserAPIKeyLabelNames(Enum):
     "litellm_remaining_api_key_tokens_for_model",
     "litellm_llm_api_failed_requests_metric",
     "litellm_callback_logging_failures_metric",
+    "litellm_in_flight_requests",
 ]
 
 
diff --git a/tests/litellm/llms/openai_like/test_assemblyai_provider.py b/tests/litellm/llms/openai_like/test_assemblyai_provider.py
new file mode 100644
index 00000000000..7eee810b271
--- /dev/null
+++ b/tests/litellm/llms/openai_like/test_assemblyai_provider.py
@@ -0,0 +1,77 @@
+"""
+Unit tests for the AssemblyAI LLM Gateway OpenAI-like provider.
+"""
+
+import os
+import sys
+
+sys.path.insert(
+    0, os.path.abspath(os.path.join(os.path.dirname(__file__), "../../../.."))
+)
+
+from litellm.llms.openai_like.dynamic_config import create_config_class
+from litellm.llms.openai_like.json_loader import JSONProviderRegistry
+
+ASSEMBLYAI_BASE_URL = "https://llm-gateway.assemblyai.com/v1"
+
+
+def _get_config():
+    provider = JSONProviderRegistry.get("assemblyai")
+    assert provider is not None
+    config_class = create_config_class(provider)
+    return config_class()
+
+
+def test_assemblyai_provider_registered():
+    provider = JSONProviderRegistry.get("assemblyai")
+    assert provider is not None
+    assert provider.base_url == ASSEMBLYAI_BASE_URL
+    assert provider.api_key_env == "ASSEMBLYAI_API_KEY"
+
+
+def test_assemblyai_resolves_env_api_key(monkeypatch):
+    config = _get_config()
+    monkeypatch.setenv("ASSEMBLYAI_API_KEY", "test-key")
+    api_base, api_key = config._get_openai_compatible_provider_info(None, None)
+    assert api_base == ASSEMBLYAI_BASE_URL
+    assert api_key == "test-key"
+
+
+def test_assemblyai_complete_url_appends_endpoint():
+    config = _get_config()
+    url = config.get_complete_url(
+        api_base=ASSEMBLYAI_BASE_URL,
+        api_key="test-key",
+        model="assemblyai/claude-sonnet-4-5-20250929",
+        optional_params={},
+        litellm_params={},
+        stream=False,
+    )
+    assert url == f"{ASSEMBLYAI_BASE_URL}/chat/completions"
+
+
+def test_assemblyai_provider_resolution():
+    from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
+
+    model, provider, api_key, api_base = get_llm_provider(
+        model="assemblyai/claude-sonnet-4-5-20250929",
+        custom_llm_provider=None,
+        api_base=None,
+        api_key=None,
+    )
+
+    assert model == "claude-sonnet-4-5-20250929"
+    assert provider == "assemblyai"
+    assert api_base == ASSEMBLYAI_BASE_URL
+
+
+def test_assemblyai_provider_config_manager():
+    from litellm import LlmProviders
+    from litellm.utils import ProviderConfigManager
+
+    config = ProviderConfigManager.get_provider_chat_config(
+        model="claude-sonnet-4-5-20250929", provider=LlmProviders.ASSEMBLYAI
+    )
+
+    assert config is not None
+    assert config.custom_llm_provider == "assemblyai"
diff --git a/tests/mcp_tests/test_mcp_server.py b/tests/mcp_tests/test_mcp_server.py
index dc1e2068365..a81702d0db3 100644
--- a/tests/mcp_tests/test_mcp_server.py
+++ b/tests/mcp_tests/test_mcp_server.py
@@ -659,9 +659,9 @@ async def test_list_tools_rest_api_server_not_found():
         mock_manager.get_allowed_mcp_servers = AsyncMock(
             return_value=["non_existent_server_id"]
         )
-        # Mock filter_server_ids_by_ip to return input unchanged (no IP filtering in test)
-        mock_manager.filter_server_ids_by_ip = MagicMock(
-            side_effect=lambda server_ids, client_ip: server_ids
+        # Mock filter_server_ids_by_ip_with_info to return input unchanged (no IP filtering in test)
+        mock_manager.filter_server_ids_by_ip_with_info = MagicMock(
+            side_effect=lambda server_ids, client_ip: (server_ids, 0)
         )
         # Return None when trying to get the server (server doesn't exist)
         mock_manager.get_mcp_server_by_id = MagicMock(return_value=None)
@@ -732,9 +732,9 @@ async def test_list_tools_rest_api_success():
             return_value=["test-server-123"]
         )
         mock_manager.get_mcp_server_by_id = MagicMock(return_value=mock_server)
-        # Mock filter_server_ids_by_ip to return input unchanged (no IP filtering in test)
-        mock_manager.filter_server_ids_by_ip = MagicMock(
-            side_effect=lambda server_ids, client_ip: server_ids
+        # Mock filter_server_ids_by_ip_with_info to return input unchanged (no IP filtering in test)
+        mock_manager.filter_server_ids_by_ip_with_info = MagicMock(
+            side_effect=lambda server_ids, client_ip: (server_ids, 0)
         )
 
         # Mock the _get_tools_for_single_server function
@@ -814,9 +814,9 @@ def mock_get_server_by_id(server_id):
         )
         mock_manager.get_mcp_server_by_id = lambda server_id: mock_server_1 if server_id == "server1_id" else mock_server_2
         mock_manager._get_tools_from_server = AsyncMock(return_value=[mock_tool_1])
-        # Mock filter_server_ids_by_ip to return input unchanged (no IP filtering in test)
-        mock_manager.filter_server_ids_by_ip = MagicMock(
-            side_effect=lambda server_ids, client_ip: server_ids
+        # Mock filter_server_ids_by_ip_with_info to return input unchanged (no IP filtering in test)
+        mock_manager.filter_server_ids_by_ip_with_info = MagicMock(
+            side_effect=lambda server_ids, client_ip: (server_ids, 0)
         )
 
         with patch(
@@ -853,9 +853,9 @@ async def mock_get_tools_side_effect(
             mock_manager_2._get_tools_from_server = AsyncMock(
                 side_effect=mock_get_tools_side_effect
             )
-            # Mock filter_server_ids_by_ip to return input unchanged (no IP filtering in test)
-            mock_manager_2.filter_server_ids_by_ip = MagicMock(
-                side_effect=lambda server_ids, client_ip: server_ids
+            # Mock filter_server_ids_by_ip_with_info to return input unchanged (no IP filtering in test)
+            mock_manager_2.filter_server_ids_by_ip_with_info = MagicMock(
+                side_effect=lambda server_ids, client_ip: (server_ids, 0)
             )
 
         with patch(
@@ -881,9 +881,9 @@ async def mock_get_tools_side_effect(
         )
         mock_manager.get_mcp_server_by_id = lambda server_id: mock_server_1 if server_id == "server1_id" else (mock_server_2 if server_id == "server2_id" else mock_server_3)
         mock_manager._get_tools_from_server = AsyncMock(return_value=[mock_tool_1])
-        # Mock filter_server_ids_by_ip to return input unchanged (no IP filtering in test)
-        mock_manager.filter_server_ids_by_ip = MagicMock(
-            side_effect=lambda server_ids, client_ip: server_ids
+        # Mock filter_server_ids_by_ip_with_info to return input unchanged (no IP filtering in test)
+        mock_manager.filter_server_ids_by_ip_with_info = MagicMock(
+            side_effect=lambda server_ids, client_ip: (server_ids, 0)
         )
 
         with patch(
@@ -1817,9 +1817,9 @@ async def test_list_tool_rest_api_with_server_specific_auth():
                 mock_server.mcp_info = {"server_name": "zapier"}
 
                 mock_manager.get_mcp_server_by_id.return_value = mock_server
-                # Mock filter_server_ids_by_ip to return input unchanged (no IP filtering in test)
-                mock_manager.filter_server_ids_by_ip = MagicMock(
-                    side_effect=lambda server_ids, client_ip: server_ids
+                # Mock filter_server_ids_by_ip_with_info to return input unchanged (no IP filtering in test)
+                mock_manager.filter_server_ids_by_ip_with_info = MagicMock(
+                    side_effect=lambda server_ids, client_ip: (server_ids, 0)
                 )
 
                 mock_user_api_key_dict = UserAPIKeyAuth(
@@ -1911,9 +1911,9 @@ async def test_list_tool_rest_api_with_default_auth():
                 mock_server.mcp_info = {"server_name": "unknown_server"}
 
                 mock_manager.get_mcp_server_by_id.return_value = mock_server
-                # Mock filter_server_ids_by_ip to return input unchanged (no IP filtering in test)
-                mock_manager.filter_server_ids_by_ip = MagicMock(
-                    side_effect=lambda server_ids, client_ip: server_ids
+                # Mock filter_server_ids_by_ip_with_info to return input unchanged (no IP filtering in test)
+                mock_manager.filter_server_ids_by_ip_with_info = MagicMock(
+                    side_effect=lambda server_ids, client_ip: (server_ids, 0)
                 )
 
                 mock_user_api_key_dict = UserAPIKeyAuth(
@@ -2021,9 +2021,9 @@ async def test_list_tool_rest_api_all_servers_with_auth():
                         server_id
                     )
                 )
-                # Mock filter_server_ids_by_ip to return input unchanged (no IP filtering in test)
-                mock_manager.filter_server_ids_by_ip = MagicMock(
-                    side_effect=lambda server_ids, client_ip: server_ids
+                # Mock filter_server_ids_by_ip_with_info to return input unchanged (no IP filtering in test)
+                mock_manager.filter_server_ids_by_ip_with_info = MagicMock(
+                    side_effect=lambda server_ids, client_ip: (server_ids, 0)
                 )
 
                 mock_user_api_key_dict = UserAPIKeyAuth(
@@ -2154,9 +2154,9 @@ def mock_client_constructor(*args, **kwargs):
             return_value=["test-server-123"]
         )
         mock_manager.get_mcp_server_by_id = MagicMock(return_value=mock_server)
-        # Mock filter_server_ids_by_ip to return input unchanged (no IP filtering in test)
-        mock_manager.filter_server_ids_by_ip = MagicMock(
-            side_effect=lambda server_ids, client_ip: server_ids
+        # Mock filter_server_ids_by_ip_with_info to return input unchanged (no IP filtering in test)
+        mock_manager.filter_server_ids_by_ip_with_info = MagicMock(
+            side_effect=lambda server_ids, client_ip: (server_ids, 0)
         )
 
         # Mock the _get_tools_from_server method to return all tools
@@ -2268,9 +2268,9 @@ def mock_client_constructor(*args, **kwargs):
             return_value=["test-server-456"]
         )
         mock_manager.get_mcp_server_by_id = MagicMock(return_value=mock_server)
-        # Mock filter_server_ids_by_ip to return input unchanged (no IP filtering in test)
-        mock_manager.filter_server_ids_by_ip = MagicMock(
-            side_effect=lambda server_ids, client_ip: server_ids
+        # Mock filter_server_ids_by_ip_with_info to return input unchanged (no IP filtering in test)
+        mock_manager.filter_server_ids_by_ip_with_info = MagicMock(
+            side_effect=lambda server_ids, client_ip: (server_ids, 0)
         )
         # Mock the _get_tools_from_server method to return all tools
         mock_manager._get_tools_from_server = AsyncMock(return_value=mock_tools)
@@ -2368,9 +2368,9 @@ def mock_client_constructor(*args, **kwargs):
             return_value=["test-server-000"]
         )
         mock_manager.get_mcp_server_by_id = MagicMock(return_value=mock_server)
-        # Mock filter_server_ids_by_ip to return input unchanged (no IP filtering in test)
-        mock_manager.filter_server_ids_by_ip = MagicMock(
-            side_effect=lambda server_ids, client_ip: server_ids
+        # Mock filter_server_ids_by_ip_with_info to return input unchanged (no IP filtering in test)
+        mock_manager.filter_server_ids_by_ip_with_info = MagicMock(
+            side_effect=lambda server_ids, client_ip: (server_ids, 0)
         )
 
         # Mock the _get_tools_from_server method to return all tools
diff --git a/tests/test_litellm/litellm_core_utils/test_realtime_streaming.py b/tests/test_litellm/litellm_core_utils/test_realtime_streaming.py
index 11d6bb028d8..7d38a5cc80a 100644
--- a/tests/test_litellm/litellm_core_utils/test_realtime_streaming.py
+++ b/tests/test_litellm/litellm_core_utils/test_realtime_streaming.py
@@ -379,7 +379,8 @@ async def test_realtime_guardrail_blocks_prompt_injection():
     """
     Test that when a transcription event containing prompt injection arrives from the
     backend, a registered guardrail blocks it — sending a warning to the client
-    and NOT sending response.create to the backend.
+    and voicing the guardrail violation message via response.cancel +
+    conversation.item.create + response.create.
     """
     import litellm
     from litellm.integrations.custom_guardrail import CustomGuardrail
@@ -430,19 +431,36 @@ async def apply_guardrail(self, inputs, request_data, input_type, logging_obj=No
     streaming = RealTimeStreaming(client_ws, backend_ws, logging_obj)
     await streaming.backend_to_client_send_messages()
 
-    # ASSERT 1: no response.create was sent to backend (injection blocked).
+    # ASSERT 1: the guardrail blocked the normal auto-response and instead
+    # injected a conversation.item.create + response.create to voice the
+    # violation message.  There should be exactly ONE response.create (the
+    # guardrail-triggered one), preceded by a response.cancel and a
+    # conversation.item.create carrying the violation text.
     sent_to_backend = [
         json.loads(c.args[0])
         for c in backend_ws.send.call_args_list
         if c.args
     ]
-    response_creates = [
+    response_cancels = [
+        e for e in sent_to_backend if e.get("type") == "response.cancel"
+    ]
+    assert len(response_cancels) == 1, (
+        f"Guardrail should send response.cancel, got: {response_cancels}"
+    )
+    guardrail_items = [
         e for e in sent_to_backend
-        if e.get("type") == "response.create"
+        if e.get("type") == "conversation.item.create"
     ]
-    assert len(response_creates) == 0, (
-        f"Guardrail should prevent response.create for injected content, "
-        f"but got: {response_creates}"
+    assert len(guardrail_items) == 1, (
+        f"Guardrail should inject a conversation.item.create with violation message, "
+        f"got: {guardrail_items}"
+    )
+    response_creates = [
+        e for e in sent_to_backend if e.get("type") == "response.create"
+    ]
+    assert len(response_creates) == 1, (
+        f"Guardrail should send exactly one response.create to voice the violation, "
+        f"got: {response_creates}"
     )
 
     # ASSERT 2: error event was sent directly to the client WebSocket
@@ -595,14 +613,26 @@ async def apply_guardrail(self, inputs, request_data, input_type, logging_obj=No
     assert len(error_events) == 1, f"Expected one error event, got: {sent_texts}"
     assert error_events[0]["error"]["type"] == "guardrail_violation"
 
-    # ASSERT: blocked item was NOT forwarded to the backend
+    # ASSERT: the original blocked item was NOT forwarded to the backend.
+    # The guardrail handler injects its own conversation.item.create with
+    # the violation message — only that one should be present, not the
+    # original user message.
     sent_to_backend = [c.args[0] for c in backend_ws.send.call_args_list if c.args]
     forwarded_items = [
         json.loads(m) for m in sent_to_backend
         if isinstance(m, str) and json.loads(m).get("type") == "conversation.item.create"
     ]
-    assert len(forwarded_items) == 0, (
-        f"Blocked item should not be forwarded to backend, got: {forwarded_items}"
+    # Filter out guardrail-injected items (contain "Say exactly the following message")
+    original_items = [
+        item for item in forwarded_items
+        if not any(
+            "Say exactly the following message" in c.get("text", "")
+            for c in item.get("item", {}).get("content", [])
+            if isinstance(c, dict)
+        )
+    ]
+    assert len(original_items) == 0, (
+        f"Blocked item should not be forwarded to backend, got: {original_items}"
     )
 
     litellm.callbacks = []  # cleanup
diff --git a/tests/test_litellm/llms/anthropic/experimental_pass_through/messages/test_anthropic_experimental_pass_through_messages_handler.py b/tests/test_litellm/llms/anthropic/experimental_pass_through/messages/test_anthropic_experimental_pass_through_messages_handler.py
index c671d9b37b8..636e84fe796 100644
--- a/tests/test_litellm/llms/anthropic/experimental_pass_through/messages/test_anthropic_experimental_pass_through_messages_handler.py
+++ b/tests/test_litellm/llms/anthropic/experimental_pass_through/messages/test_anthropic_experimental_pass_through_messages_handler.py
@@ -39,14 +39,14 @@ def test_anthropic_experimental_pass_through_messages_handler():
 
 def test_anthropic_experimental_pass_through_messages_handler_dynamic_api_key_and_api_base_and_custom_values():
     """
-    Test that api key, api base, and extra kwargs are forwarded to litellm.responses for Azure models.
-    Azure models are routed directly to the Responses API.
+    Test that api key, api base, and extra kwargs are forwarded to litellm.completion for Azure models.
+    Azure models are routed through chat/completions (not the Responses API).
     """
     from litellm.llms.anthropic.experimental_pass_through.messages.handler import (
         anthropic_messages_handler,
     )
 
-    with patch("litellm.responses", return_value="test-response") as mock_responses:
+    with patch("litellm.completion", return_value=MagicMock()) as mock_completion:
         try:
             anthropic_messages_handler(
                 max_tokens=100,
@@ -58,10 +58,10 @@ def test_anthropic_experimental_pass_through_messages_handler_dynamic_api_key_an
             )
         except Exception as e:
             print(f"Error: {e}")
-        mock_responses.assert_called_once()
-        assert mock_responses.call_args.kwargs["api_key"] == "test-api-key"
-        assert mock_responses.call_args.kwargs["api_base"] == "test-api-base"
-        assert mock_responses.call_args.kwargs["custom_key"] == "custom_value"
+        mock_completion.assert_called_once()
+        assert mock_completion.call_args.kwargs["api_key"] == "test-api-key"
+        assert mock_completion.call_args.kwargs["api_base"] == "test-api-base"
+        assert mock_completion.call_args.kwargs["custom_key"] == "custom_value"
 
 
 def test_anthropic_experimental_pass_through_messages_handler_custom_llm_provider():
diff --git a/tests/test_litellm/llms/openai/test_gpt5_transformation.py b/tests/test_litellm/llms/openai/test_gpt5_transformation.py
index 386f264a4dd..4ccde674098 100644
--- a/tests/test_litellm/llms/openai/test_gpt5_transformation.py
+++ b/tests/test_litellm/llms/openai/test_gpt5_transformation.py
@@ -267,7 +267,8 @@ def test_gpt5_1_model_detection(gpt5_config: OpenAIGPT5Config):
     assert gpt5_config.is_model_gpt_5_1_model("gpt-5.1-chat")
     assert gpt5_config.is_model_gpt_5_1_model("gpt-5.2")
     assert gpt5_config.is_model_gpt_5_1_model("gpt-5.2-2025-12-11")
-    assert gpt5_config.is_model_gpt_5_1_model("gpt-5.2-chat-latest")
+    assert not gpt5_config.is_model_gpt_5_1_model("gpt-5.2-chat")
+    assert not gpt5_config.is_model_gpt_5_1_model("gpt-5.2-chat-latest")
     assert not gpt5_config.is_model_gpt_5_1_model("gpt-5.2-pro")
     assert not gpt5_config.is_model_gpt_5_1_model("gpt-5")
     assert not gpt5_config.is_model_gpt_5_1_model("gpt-5-mini")
@@ -395,7 +396,38 @@ def test_gpt5_temperature_still_restricted(config: OpenAIConfig):
     assert params["temperature"] == 1.0
 
 
-def test_gpt5_2_pro_allows_reasoning_effort_xhigh(config: OpenAIConfig):
+def test_gpt5_2_chat_temperature_restricted(config: OpenAIConfig):
+    """Test that gpt-5.2-chat only supports temperature=1, like base gpt-5.
+
+    Regression test for https://github.com/BerriAI/litellm/issues/21911
+    """
+    # gpt-5.2-chat should reject non-1 temperature when drop_params=False
+    for model in ["gpt-5.2-chat", "gpt-5.2-chat-latest"]:
+        with pytest.raises(litellm.utils.UnsupportedParamsError):
+            config.map_openai_params(
+                non_default_params={"temperature": 0.7},
+                optional_params={},
+                model=model,
+                drop_params=False,
+            )
+
+        # temperature=1 should still work
+        params = config.map_openai_params(
+            non_default_params={"temperature": 1.0},
+            optional_params={},
+            model=model,
+            drop_params=False,
+        )
+        assert params["temperature"] == 1.0
+
+        # drop_params=True should silently drop non-1 temperature
+        params = config.map_openai_params(
+            non_default_params={"temperature": 0.5},
+            optional_params={},
+            model=model,
+            drop_params=True,
+        )
+        assert "temperature" not in params
     params = config.map_openai_params(
         non_default_params={"reasoning_effort": "xhigh"},
         optional_params={},
diff --git a/tests/test_litellm/proxy/agent_endpoints/test_endpoints.py b/tests/test_litellm/proxy/agent_endpoints/test_endpoints.py
index 8cec3538077..fcf8f048190 100644
--- a/tests/test_litellm/proxy/agent_endpoints/test_endpoints.py
+++ b/tests/test_litellm/proxy/agent_endpoints/test_endpoints.py
@@ -7,6 +7,7 @@
 from litellm.proxy._types import LitellmUserRoles, UserAPIKeyAuth
 from litellm.proxy.agent_endpoints import endpoints as agent_endpoints
 from litellm.proxy.agent_endpoints.endpoints import (
+    _check_agent_management_permission,
     get_agent_daily_activity,
     router,
     user_api_key_auth,
@@ -47,6 +48,16 @@ def _sample_agent_response(
     )
 
 
+def _make_app_with_role(role: LitellmUserRoles) -> TestClient:
+    """Create a TestClient where the auth dependency returns the given role."""
+    test_app = FastAPI()
+    test_app.include_router(router)
+    test_app.dependency_overrides[user_api_key_auth] = lambda: UserAPIKeyAuth(
+        user_id="test-user", user_role=role
+    )
+    return TestClient(test_app)
+
+
 app = FastAPI()
 app.include_router(router)
 app.dependency_overrides[user_api_key_auth] = lambda: UserAPIKeyAuth(
@@ -258,3 +269,173 @@ async def test_get_agent_daily_activity_with_agent_names(monkeypatch):
         "agent-1": {"agent_name": "First Agent"},
         "agent-2": {"agent_name": "Second Agent"},
     }
+
+
+# ---------- RBAC enforcement tests ----------
+
+
+class TestAgentRBACInternalUser:
+    """Internal users should be able to read agents but not create/update/delete."""
+
+    @pytest.fixture(autouse=True)
+    def _setup(self, monkeypatch):
+        self.internal_client = _make_app_with_role(LitellmUserRoles.INTERNAL_USER)
+        self.mock_registry = MagicMock()
+        monkeypatch.setattr(agent_endpoints, "AGENT_REGISTRY", self.mock_registry)
+
+    def test_should_allow_internal_user_to_list_agents(self, monkeypatch):
+        self.mock_registry.get_agent_list = MagicMock(return_value=[])
+        resp = self.internal_client.get(
+            "/v1/agents", headers={"Authorization": "Bearer k"}
+        )
+        assert resp.status_code == 200
+
+    def test_should_allow_internal_user_to_get_agent_by_id(self, monkeypatch):
+        self.mock_registry.get_agent_by_id = MagicMock(
+            return_value=_sample_agent_response()
+        )
+        with patch("litellm.proxy.proxy_server.prisma_client") as mock_prisma:
+            resp = self.internal_client.get(
+                "/v1/agents/agent-123", headers={"Authorization": "Bearer k"}
+            )
+        assert resp.status_code == 200
+
+    def test_should_block_internal_user_from_creating_agent(self):
+        resp = self.internal_client.post(
+            "/v1/agents",
+            json=_sample_agent_config(),
+            headers={"Authorization": "Bearer k"},
+        )
+        assert resp.status_code == 403
+        assert "Only proxy admins" in resp.json()["detail"]["error"]
+
+    def test_should_block_internal_user_from_updating_agent(self):
+        resp = self.internal_client.put(
+            "/v1/agents/agent-123",
+            json=_sample_agent_config(),
+            headers={"Authorization": "Bearer k"},
+        )
+        assert resp.status_code == 403
+
+    def test_should_block_internal_user_from_patching_agent(self):
+        resp = self.internal_client.patch(
+            "/v1/agents/agent-123",
+            json={"agent_name": "new-name"},
+            headers={"Authorization": "Bearer k"},
+        )
+        assert resp.status_code == 403
+
+    def test_should_block_internal_user_from_deleting_agent(self):
+        resp = self.internal_client.delete(
+            "/v1/agents/agent-123", headers={"Authorization": "Bearer k"}
+        )
+        assert resp.status_code == 403
+
+
+class TestAgentRBACInternalUserViewOnly:
+    """View-only internal users should only be able to read agents."""
+
+    @pytest.fixture(autouse=True)
+    def _setup(self, monkeypatch):
+        self.viewer_client = _make_app_with_role(
+            LitellmUserRoles.INTERNAL_USER_VIEW_ONLY
+        )
+        self.mock_registry = MagicMock()
+        monkeypatch.setattr(agent_endpoints, "AGENT_REGISTRY", self.mock_registry)
+
+    def test_should_allow_view_only_user_to_list_agents(self):
+        self.mock_registry.get_agent_list = MagicMock(return_value=[])
+        resp = self.viewer_client.get(
+            "/v1/agents", headers={"Authorization": "Bearer k"}
+        )
+        assert resp.status_code == 200
+
+    def test_should_block_view_only_user_from_creating_agent(self):
+        resp = self.viewer_client.post(
+            "/v1/agents",
+            json=_sample_agent_config(),
+            headers={"Authorization": "Bearer k"},
+        )
+        assert resp.status_code == 403
+
+    def test_should_block_view_only_user_from_deleting_agent(self):
+        resp = self.viewer_client.delete(
+            "/v1/agents/agent-123", headers={"Authorization": "Bearer k"}
+        )
+        assert resp.status_code == 403
+
+
+class TestAgentRBACProxyAdmin:
+    """Proxy admins should have full CRUD access to agents."""
+
+    @pytest.fixture(autouse=True)
+    def _setup(self, monkeypatch):
+        self.admin_client = _make_app_with_role(LitellmUserRoles.PROXY_ADMIN)
+        self.mock_registry = MagicMock()
+        monkeypatch.setattr(agent_endpoints, "AGENT_REGISTRY", self.mock_registry)
+
+    def test_should_allow_admin_to_create_agent(self, monkeypatch):
+        with patch("litellm.proxy.proxy_server.prisma_client") as mock_prisma:
+            self.mock_registry.get_agent_by_name = MagicMock(return_value=None)
+            self.mock_registry.add_agent_to_db = AsyncMock(
+                return_value=_sample_agent_response()
+            )
+            self.mock_registry.register_agent = MagicMock()
+            resp = self.admin_client.post(
+                "/v1/agents",
+                json=_sample_agent_config(),
+                headers={"Authorization": "Bearer k"},
+            )
+            assert resp.status_code == 200
+
+    def test_should_allow_admin_to_delete_agent(self):
+        existing = {
+            "agent_id": "agent-123",
+            "agent_name": "Existing Agent",
+            "agent_card_params": _sample_agent_card_params(),
+        }
+        with patch("litellm.proxy.proxy_server.prisma_client") as mock_prisma:
+            mock_prisma.db.litellm_agentstable.find_unique = AsyncMock(
+                return_value=existing
+            )
+            self.mock_registry.delete_agent_from_db = AsyncMock()
+            self.mock_registry.deregister_agent = MagicMock()
+            resp = self.admin_client.delete(
+                "/v1/agents/agent-123", headers={"Authorization": "Bearer k"}
+            )
+            assert resp.status_code == 200
+
+
+class TestCheckAgentManagementPermission:
+    """Unit tests for the _check_agent_management_permission helper."""
+
+    def test_should_allow_proxy_admin(self):
+        auth = UserAPIKeyAuth(
+            user_id="admin", user_role=LitellmUserRoles.PROXY_ADMIN
+        )
+        _check_agent_management_permission(auth)
+
+    @pytest.mark.parametrize(
+        "role",
+        [
+            LitellmUserRoles.INTERNAL_USER,
+            LitellmUserRoles.INTERNAL_USER_VIEW_ONLY,
+            LitellmUserRoles.PROXY_ADMIN_VIEW_ONLY,
+        ],
+    )
+    def test_should_block_non_admin_roles(self, role):
+        from fastapi import HTTPException
+
+        auth = UserAPIKeyAuth(user_id="user", user_role=role)
+        with pytest.raises(HTTPException) as exc_info:
+            _check_agent_management_permission(auth)
+        assert exc_info.value.status_code == 403
+
+
+class TestAgentRoutesIncludesAgentIdPattern:
+    """Verify that agent_routes includes the {agent_id} pattern for route access."""
+
+    def test_should_include_agent_id_pattern(self):
+        from litellm.proxy._types import LiteLLMRoutes
+
+        assert "/v1/agents/{agent_id}" in LiteLLMRoutes.agent_routes.value
diff --git a/tests/test_litellm/proxy/middleware/test_in_flight_requests_middleware.py b/tests/test_litellm/proxy/middleware/test_in_flight_requests_middleware.py
new file mode 100644
index 00000000000..830bca49936
--- /dev/null
+++ b/tests/test_litellm/proxy/middleware/test_in_flight_requests_middleware.py
@@ -0,0 +1,98 @@
+"""
+Tests for InFlightRequestsMiddleware.
+
+Verifies that in_flight_requests is incremented during a request and
+decremented after it completes, including on errors.
+"""
+import asyncio
+
+import pytest
+from starlette.middleware.base import BaseHTTPMiddleware
+from starlette.requests import Request
+from starlette.responses import JSONResponse, Response
+from starlette.routing import Route
+from starlette.testclient import TestClient
+
+from litellm.proxy.middleware.in_flight_requests_middleware import (
+    InFlightRequestsMiddleware,
+    get_in_flight_requests,
+)
+
+
+@pytest.fixture(autouse=True)
+def reset_state():
+    """Reset class-level state between tests."""
+    InFlightRequestsMiddleware._in_flight = 0
+    yield
+    InFlightRequestsMiddleware._in_flight = 0
+
+
+def _make_app(handler):
+    from starlette.applications import Starlette
+
+    app = Starlette(routes=[Route("/", handler)])
+    app.add_middleware(InFlightRequestsMiddleware)
+    return app
+
+
+# ── Structure ─────────────────────────────────────────────────────────────────
+
+
+def test_is_not_base_http_middleware():
+    """Must be pure ASGI — BaseHTTPMiddleware causes streaming degradation."""
+    assert not issubclass(InFlightRequestsMiddleware, BaseHTTPMiddleware)
+
+
+def test_has_asgi_call_protocol():
+    assert "__call__" in InFlightRequestsMiddleware.__dict__
+
+
+# ── Counter behaviour ─────────────────────────────────────────────────────────
+
+
+def test_counter_zero_at_start():
+    assert get_in_flight_requests() == 0
+
+
+def test_counter_increments_inside_handler():
+    captured = []
+
+    async def handler(request: Request) -> Response:
+        captured.append(InFlightRequestsMiddleware.get_count())
+        return JSONResponse({})
+
+    TestClient(_make_app(handler)).get("/")
+    assert captured == [1]
+
+
+def test_counter_returns_to_zero_after_request():
+    async def handler(request: Request) -> Response:
+        return JSONResponse({})
+
+    TestClient(_make_app(handler)).get("/")
+    assert get_in_flight_requests() == 0
+
+
+def test_counter_decrements_after_error():
+    """Counter must reach 0 even when the handler raises."""
+
+    async def handler(request: Request) -> Response:
+        return Response("boom", status_code=500)
+
+    TestClient(_make_app(handler)).get("/")
+    assert get_in_flight_requests() == 0
+
+
+def test_non_http_scopes_not_counted():
+    """Lifespan / websocket scopes must not touch the counter."""
+
+    class _InnerApp:
+        async def __call__(self, scope, receive, send):
+            pass
+
+    mw = InFlightRequestsMiddleware(_InnerApp())
+
+    asyncio.get_event_loop().run_until_complete(
+        mw({"type": "lifespan"}, None, None)  # type: ignore[arg-type]
+    )
+    assert get_in_flight_requests() == 0
diff --git a/tests/test_litellm/proxy/test_prometheus_cleanup.py b/tests/test_litellm/proxy/test_prometheus_cleanup.py
index 276f2b592db..b3d785f1133 100644
--- a/tests/test_litellm/proxy/test_prometheus_cleanup.py
+++ b/tests/test_litellm/proxy/test_prometheus_cleanup.py
@@ -10,7 +10,7 @@
 
 import pytest
 
-from litellm.proxy.prometheus_cleanup import wipe_directory
+from litellm.proxy.prometheus_cleanup import mark_worker_exit, wipe_directory
 from litellm.proxy.proxy_cli import ProxyInitializationHelpers
 
 
@@ -23,6 +23,35 @@ def test_deletes_all_db_files(self, tmp_path):
         assert not list(tmp_path.glob("*.db"))
 
 
+class TestMarkWorkerExit:
+    def test_calls_mark_process_dead_when_env_set(self, tmp_path):
+        with patch.dict(os.environ, {"PROMETHEUS_MULTIPROC_DIR": str(tmp_path)}):
+            with patch(
+                "prometheus_client.multiprocess.mark_process_dead"
+            ) as mock_mark:
+                mark_worker_exit(12345)
+                mock_mark.assert_called_once_with(12345)
+
+    def test_noop_when_env_not_set(self):
+        with patch.dict(os.environ, {}, clear=False):
+            os.environ.pop("PROMETHEUS_MULTIPROC_DIR", None)
+            with patch(
+                "prometheus_client.multiprocess.mark_process_dead"
+            ) as mock_mark:
+                mark_worker_exit(12345)
+                mock_mark.assert_not_called()
+
+    def test_exception_is_caught_and_logged(self, tmp_path):
+        with patch.dict(os.environ, {"PROMETHEUS_MULTIPROC_DIR": str(tmp_path)}):
+            with patch(
+                "prometheus_client.multiprocess.mark_process_dead",
+                side_effect=FileNotFoundError("gone"),
+            ) as mock_mark:
+                # Should not raise
+                mark_worker_exit(99)
+                mock_mark.assert_called_once_with(99)
+
+
 class TestMaybeSetupPrometheusMultiprocDir:
     def test_respects_existing_env_var(self, tmp_path):
         """When PROMETHEUS_MULTIPROC_DIR is already set, don't override it."""
diff --git a/ui/litellm-dashboard/package-lock.json b/ui/litellm-dashboard/package-lock.json
index fc2aa1599d3..503ed4a62a8 100644
--- a/ui/litellm-dashboard/package-lock.json
+++ b/ui/litellm-dashboard/package-lock.json
@@ -90,7 +90,6 @@
       "version": "5.2.0",
       "resolved": "https://registry.npmjs.org/@alloc/quick-lru/-/quick-lru-5.2.0.tgz",
       "integrity": "sha512-UrcABB+4bUrFABwbluTIBErXwvbsU/V7TZWfmbgJfbkwiBuziS9gxdODUyuiecfdGQ85jglMW6juS3+z5TsKLw==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=10"
@@ -1772,7 +1771,6 @@
       "version": "0.3.13",
       "resolved": "https://registry.npmjs.org/@jridgewell/gen-mapping/-/gen-mapping-0.3.13.tgz",
       "integrity": "sha512-2kkt/7niJ6MgEPxF0bYdQ6etZaA+fQvDcLKckhy1yIQOzaoKjBBjSj63/aLVjYE3qhRt5dvM+uUyfCg6UKCBbA==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "@jridgewell/sourcemap-codec": "^1.5.0",
@@ -1783,7 +1781,6 @@
       "version": "3.1.2",
       "resolved": "https://registry.npmjs.org/@jridgewell/resolve-uri/-/resolve-uri-3.1.2.tgz",
       "integrity": "sha512-bRISgCIjP20/tbWSPWMEi54QVPRZExkuD9lJL+UIxUKtwVJA8wW1Trb1jMs1RFXo1CBTNZ/5hpC9QvmKWdopKw==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=6.0.0"
@@ -1793,14 +1790,12 @@
       "version": "1.5.5",
       "resolved": "https://registry.npmjs.org/@jridgewell/sourcemap-codec/-/sourcemap-codec-1.5.5.tgz",
       "integrity": "sha512-cYQ9310grqxueWbl+WuIUIaiUaDcj7WOq5fVhEljNVgRfOUhY9fy2zTvfoqWsnebh8Sl70VScFbICvJnLKB0Og==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/@jridgewell/trace-mapping": {
       "version": "0.3.31",
       "resolved": "https://registry.npmjs.org/@jridgewell/trace-mapping/-/trace-mapping-0.3.31.tgz",
       "integrity": "sha512-zzNR+SdQSDJzc8joaeP8QQoCQr8NuYx2dIIytl1QeBEZHJ9uW6hebsrYgbz8hJwUQao3TWCMtmfV8Nu1twOLAw==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "@jridgewell/resolve-uri": "^3.1.0",
@@ -1978,7 +1973,6 @@
       "version": "2.1.5",
       "resolved": "https://registry.npmjs.org/@nodelib/fs.scandir/-/fs.scandir-2.1.5.tgz",
       "integrity": "sha512-vq24Bq3ym5HEQm2NKCr3yXDwjc7vTsEThRDnkp2DK9p1uqLR+DHurm/NOTo0KG7HYHU7eppKZj3MyqYuMBf62g==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "@nodelib/fs.stat": "2.0.5",
@@ -1992,7 +1986,6 @@
       "version": "2.0.5",
       "resolved": "https://registry.npmjs.org/@nodelib/fs.stat/-/fs.stat-2.0.5.tgz",
       "integrity": "sha512-RkhPPp2zrqDAQA/2jNhnztcPAlv64XdhIp7a7454A5ovI7Bukxgt7MX7udwAu3zg1DcpPU0rz3VV1SeaqvY4+A==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">= 8"
@@ -2002,7 +1995,6 @@
       "version": "1.2.8",
       "resolved": "https://registry.npmjs.org/@nodelib/fs.walk/-/fs.walk-1.2.8.tgz",
       "integrity": "sha512-oGB+UxlgWcgQkgwo8GcEGwemoTFt3FIO9ababBmaGwXIoBKZ+GTy0pP185beGg7Llih/NSHSV2XAs1lnznocSg==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "@nodelib/fs.scandir": "2.1.5",
@@ -2326,7 +2318,7 @@
       "version": "1.58.1",
       "resolved": "https://registry.npmjs.org/@playwright/test/-/test-1.58.1.tgz",
       "integrity": "sha512-6LdVIUERWxQMmUSSQi0I53GgCBYgM2RpGngCPY7hSeju+VrKjq3lvs7HpJoPbDiY5QM5EYRtRX5fvrinnMAz3w==",
-      "dev": true,
+      "devOptional": true,
       "license": "Apache-2.0",
       "dependencies": {
         "playwright": "1.58.1"
@@ -3431,14 +3423,12 @@
       "version": "15.7.15",
       "resolved": "https://registry.npmjs.org/@types/prop-types/-/prop-types-15.7.15.tgz",
       "integrity": "sha512-F6bEyamV9jKGAFBEmlQnesRPGOQqS2+Uwi0Em15xenOxHaf2hv6L8YCVn3rPdPJOiJfPiCnLIRyvwVaqMY3MIw==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/@types/react": {
       "version": "18.2.48",
       "resolved": "https://registry.npmjs.org/@types/react/-/react-18.2.48.tgz",
       "integrity": "sha512-qboRCl6Ie70DQQG9hhNREz81jqC1cs9EVNcjQ1AU+jH6NFfSAhVVbrrY/+nSF+Bsk4AOwm9Qa61InvMCyV+H3w==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "@types/prop-types": "*",
@@ -3480,7 +3470,6 @@
       "version": "0.26.0",
       "resolved": "https://registry.npmjs.org/@types/scheduler/-/scheduler-0.26.0.tgz",
       "integrity": "sha512-WFHp9YUJQ6CKshqoC37iOlHnQSmxNc795UhB26CyBBttrN9svdIrUjl/NjnNmfcwtncN0h/0PPAFWv9ovP8mLA==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/@types/unist": {
@@ -4341,14 +4330,12 @@
       "version": "1.3.0",
       "resolved": "https://registry.npmjs.org/any-promise/-/any-promise-1.3.0.tgz",
       "integrity": "sha512-7UvmKalWRt1wgjL1RrGxoSJW/0QZFIegpeGvZG9kjp8vrRu55XTHbwnqq2GpXm9uLbcuhxm3IqX9OB4MZR1b2A==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/anymatch": {
       "version": "3.1.3",
       "resolved": "https://registry.npmjs.org/anymatch/-/anymatch-3.1.3.tgz",
       "integrity": "sha512-KMReFUr0B4t+D+OBkjR3KYqvocp2XaSzO55UcB6mgQMd3KbcE+mWTyvVV7D/zsdEbNnV6acZUutkiHQXvTr1Rw==",
-      "dev": true,
       "license": "ISC",
       "dependencies": {
         "normalize-path": "^3.0.0",
@@ -4362,7 +4349,6 @@
       "version": "2.3.1",
       "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-2.3.1.tgz",
       "integrity": "sha512-JU3teHTNjmE2VCGFzuY8EXzCDVwEqB2a8fsIvwaStHhAWJEeVd1o1QD80CU6+ZdEXXSLbSsuLwJjkCBWqRQUVA==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=8.6"
@@ -4375,7 +4361,6 @@
       "version": "5.0.2",
       "resolved": "https://registry.npmjs.org/arg/-/arg-5.0.2.tgz",
       "integrity": "sha512-PYjyFOLKQ9y57JvQ6QLo8dAgNqswh8M1RMJYdQduT6xbWSgK36P/Z/v+p888pM69jMMfS8Xd8F6I1kQ/I9HUGg==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/argparse": {
@@ -4747,7 +4732,6 @@
       "version": "2.3.0",
       "resolved": "https://registry.npmjs.org/binary-extensions/-/binary-extensions-2.3.0.tgz",
       "integrity": "sha512-Ceh+7ox5qe7LJuLHoY0feh3pHuUDHAcRUeyL2VYghZwfpkNIy/+8Ocg0a3UuSoYzavmylwuLWQOf3hl0jjMMIw==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=8"
@@ -4773,7 +4757,6 @@
       "version": "3.0.3",
       "resolved": "https://registry.npmjs.org/braces/-/braces-3.0.3.tgz",
       "integrity": "sha512-yQbXgO/OSZVD2IsiLlro+7Hf6Q18EJrKSEsdoMzKePKXct3gvD8oLcOQdIzGupr5Fj+EDe8gO/lxc1BzfMpxvA==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "fill-range": "^7.1.1"
@@ -4889,7 +4872,6 @@
       "version": "2.0.1",
       "resolved": "https://registry.npmjs.org/camelcase-css/-/camelcase-css-2.0.1.tgz",
       "integrity": "sha512-QOSvevhslijgYwRx6Rv7zKdMF8lbRmx+uQGx2+vDc+KI/eBnsy9kit5aj23AgGu3pa4t9AgwbnXWqS+iOY+2aA==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">= 6"
@@ -5013,7 +4995,6 @@
       "version": "3.6.0",
       "resolved": "https://registry.npmjs.org/chokidar/-/chokidar-3.6.0.tgz",
       "integrity": "sha512-7VT13fmjotKpGipCW9JEQAusEPE+Ei8nl6/g4FBAmIm0GOOLMua9NDDo/DWp0ZAxCr3cPq5ZpBqmPAQgDda2Pw==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "anymatch": "~3.1.2",
@@ -5038,7 +5019,6 @@
       "version": "5.1.2",
       "resolved": "https://registry.npmjs.org/glob-parent/-/glob-parent-5.1.2.tgz",
       "integrity": "sha512-AOIgSQCepiJYwP3ARnGx+5VnTu2HBYdzbGP45eLw1vr3zB3vZLeyed1sC9hnbcOc9/SrMyM5RPQrkGz4aS9Zow==",
-      "dev": true,
       "license": "ISC",
       "dependencies": {
         "is-glob": "^4.0.1"
@@ -5114,7 +5094,6 @@
       "version": "4.1.1",
       "resolved": "https://registry.npmjs.org/commander/-/commander-4.1.1.tgz",
       "integrity": "sha512-NOKm8xhkzAjzFx8B2v5OAHT+u5pRQc2UCa2Vq9jYL/31o2wi9mxBA7LIFs3sV5VSC49z6pEhfbMULvShKj26WA==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">= 6"
@@ -5175,7 +5154,6 @@
       "version": "3.0.0",
       "resolved": "https://registry.npmjs.org/cssesc/-/cssesc-3.0.0.tgz",
       "integrity": "sha512-/Tb/JcjK111nNScGob5MNtsntNM1aCNUDipB/TkwZFhyDrrE47SOx/18wF2bbjgc3ZzCSKW1T5nt5EbFoAz/Vg==",
-      "dev": true,
       "license": "MIT",
       "bin": {
         "cssesc": "bin/cssesc"
@@ -5589,14 +5567,12 @@
       "version": "1.2.2",
       "resolved": "https://registry.npmjs.org/didyoumean/-/didyoumean-1.2.2.tgz",
       "integrity": "sha512-gxtyfqMg7GKyhQmb056K7M3xszy/myH8w+B4RT+QXBQsvAOdc3XymqDDPHx1BgPgsdAA5SIifona89YtRATDzw==",
-      "dev": true,
       "license": "Apache-2.0"
     },
     "node_modules/dlv": {
       "version": "1.1.3",
       "resolved": "https://registry.npmjs.org/dlv/-/dlv-1.1.3.tgz",
       "integrity": "sha512-+HlytyjlPKnIG8XuRG8WvmBP8xs8P71y+SKKS6ZXWoEgLuePxtDoUEiH7WkdePWrQ5JBpE6aoVqfZfJUQkjXwA==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/doctrine": {
@@ -6510,7 +6486,6 @@
       "version": "1.20.1",
       "resolved": "https://registry.npmjs.org/fastq/-/fastq-1.20.1.tgz",
       "integrity": "sha512-GGToxJ/w1x32s/D2EKND7kTil4n8OVk/9mycTc4VDza13lOvpUZTGX3mFSCtV9ksdGBVzvsyAVLM6mHFThxXxw==",
-      "dev": true,
       "license": "ISC",
       "dependencies": {
         "reusify": "^1.0.4"
@@ -6543,7 +6518,6 @@
       "version": "6.5.0",
       "resolved": "https://registry.npmjs.org/fdir/-/fdir-6.5.0.tgz",
       "integrity": "sha512-tIbYtZbucOs0BRGqPJkshJUYdL+SDH7dVM8gjy+ERp3WAUjLEFJE+02kanyHtwjWOnwrKYBiwAmM0p4kLJAnXg==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=12.0.0"
@@ -6581,7 +6555,6 @@
       "version": "7.1.1",
       "resolved": "https://registry.npmjs.org/fill-range/-/fill-range-7.1.1.tgz",
       "integrity": "sha512-YsGpe3WHLK8ZYi4tWDg2Jy3ebRz2rXowDxnld4bkQB00cc/1Zw9AWnC0i9ztDJitivtQvaI9KaLyKrc+hBW0yg==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "to-regex-range": "^5.0.1"
@@ -6742,7 +6715,6 @@
       "version": "2.3.2",
       "resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.2.tgz",
       "integrity": "sha512-xiqMQR4xAeHTuB9uWm+fFRcIOgKBMiOBP+eXiyT7jsgVCq1bkVygt00oASowB7EdtpOHaaPgKt812P9ab+DDKA==",
-      "dev": true,
       "hasInstallScript": true,
       "license": "MIT",
       "optional": true,
@@ -6893,7 +6865,6 @@
       "version": "6.0.2",
       "resolved": "https://registry.npmjs.org/glob-parent/-/glob-parent-6.0.2.tgz",
       "integrity": "sha512-XxwI8EOhVQgWp6iDL+3b0r86f4d6AX6zSU55HfB4ydCEuXLXc5FcYeOu+nnGftS4TEju/11rt4KJPTMgbfmv4A==",
-      "dev": true,
       "license": "ISC",
       "dependencies": {
         "is-glob": "^4.0.3"
@@ -7391,7 +7362,6 @@
       "version": "2.1.0",
       "resolved": "https://registry.npmjs.org/is-binary-path/-/is-binary-path-2.1.0.tgz",
       "integrity": "sha512-ZMERYes6pDydyuGidse7OsHxtbI7WVeUEozgR/g7rd0xUimYNlvZRE/K2MgZTjWy725IfelLeVcEM97mmtRGXw==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "binary-extensions": "^2.0.0"
@@ -7444,7 +7414,6 @@
       "version": "2.16.1",
       "resolved": "https://registry.npmjs.org/is-core-module/-/is-core-module-2.16.1.tgz",
       "integrity": "sha512-UfoeMA6fIJ8wTYFEUjelnaGI67v6+N7qXJEvQuIGa99l4xsCruSYOVSQ0uPANn4dAzm8lkYPaKLrrijLq7x23w==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "hasown": "^2.0.2"
@@ -7505,7 +7474,6 @@
       "version": "2.1.1",
       "resolved": "https://registry.npmjs.org/is-extglob/-/is-extglob-2.1.1.tgz",
       "integrity": "sha512-SbKbANkN603Vi4jEZv49LeVJMn4yGwsbzZworEoyEiutsN3nJYdbO36zfhGJ6QEDpOZIFkDtnq5JRxmvl3jsoQ==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=0.10.0"
@@ -7551,7 +7519,6 @@
       "version": "4.0.3",
       "resolved": "https://registry.npmjs.org/is-glob/-/is-glob-4.0.3.tgz",
       "integrity": "sha512-xelSayHH36ZgE7ZWhli7pW34hNbNl8Ojv5KVmkJD4hBdD3th8Tfk9vYasLM+mXWOZhFkgZfxhLSnrwRr4elSSg==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "is-extglob": "^2.1.1"
@@ -7600,7 +7567,6 @@
       "version": "7.0.0",
       "resolved": "https://registry.npmjs.org/is-number/-/is-number-7.0.0.tgz",
       "integrity": "sha512-41Cifkg6e8TylSpdtTpeLVMqvSBEVzTttHvERD741+pnZ8ANv0004MRL43QKPDlK9cGvNp6NZWZUBlbGXYxxng==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=0.12.0"
@@ -7877,7 +7843,6 @@
       "version": "1.21.7",
       "resolved": "https://registry.npmjs.org/jiti/-/jiti-1.21.7.tgz",
       "integrity": "sha512-/imKNG4EbWNrVjoNC/1H5/9GFy+tqjGBHCaSsN+P2RnPqjsLmv6UD3Ej+Kj8nBWaRAwyk7kK5ZUc+OEatnTR3A==",
-      "dev": true,
       "license": "MIT",
       "bin": {
         "jiti": "bin/jiti.js"
@@ -8163,7 +8128,6 @@
       "version": "3.1.3",
       "resolved": "https://registry.npmjs.org/lilconfig/-/lilconfig-3.1.3.tgz",
       "integrity": "sha512-/vlFKAoH5Cgt3Ie+JLhRbwOsCQePABiU3tJ1egGvyQ+33R/vcwM2Zl2QR/LzjsBeItPt3oSVXapn+m4nQDvpzw==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=14"
@@ -8176,7 +8140,6 @@
       "version": "1.2.4",
       "resolved": "https://registry.npmjs.org/lines-and-columns/-/lines-and-columns-1.2.4.tgz",
       "integrity": "sha512-7ylylesZQ/PV29jhEDl3Ufjo6ZX7gCqJr5F7PKrqc93v7fzSymt1BpwEU8nAUXs8qzzvqhbjhK5QZg6Mt/HkBg==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/locate-path": {
@@ -8491,7 +8454,6 @@
       "version": "1.4.1",
       "resolved": "https://registry.npmjs.org/merge2/-/merge2-1.4.1.tgz",
       "integrity": "sha512-8q7VEgMJW4J8tcfVPy8g09NcQwZdbwFEqhe/WZkoIzjn/3TGDwtOCYtXGxA3O8tPzpczCCDgv+P2P5y00ZJOOg==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">= 8"
@@ -8943,7 +8905,6 @@
       "version": "4.0.8",
       "resolved": "https://registry.npmjs.org/micromatch/-/micromatch-4.0.8.tgz",
       "integrity": "sha512-PXwfBhYu0hBCPw8Dn0E+WDYb7af3dSLVWKi3HGv84IdF4TyFoC0ysxFd0Goxw7nSv4T/PzEJQxsYsEiFCKo2BA==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "braces": "^3.0.3",
@@ -8957,7 +8918,6 @@
       "version": "2.3.1",
       "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-2.3.1.tgz",
       "integrity": "sha512-JU3teHTNjmE2VCGFzuY8EXzCDVwEqB2a8fsIvwaStHhAWJEeVd1o1QD80CU6+ZdEXXSLbSsuLwJjkCBWqRQUVA==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=8.6"
@@ -9072,7 +9032,6 @@
       "version": "2.7.0",
       "resolved": "https://registry.npmjs.org/mz/-/mz-2.7.0.tgz",
       "integrity": "sha512-z81GNO7nnYMEhrGh9LeymoE4+Yr0Wn5McHIZMK5cfQCl+NDX08sCZgUc9/6MHni9IWuFLm1Z3HTCXu2z9fN62Q==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "any-promise": "^1.0.0",
@@ -9284,7 +9243,6 @@
       "version": "3.0.0",
       "resolved": "https://registry.npmjs.org/normalize-path/-/normalize-path-3.0.0.tgz",
       "integrity": "sha512-6eZs5Ls3WtCisHWp9S2GUy8dqkpGi4BVSz3GaqiE6ezub0512ESztXUwUB6C6IKbQkY2Pnb/mD4WYojCRwcwLA==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=0.10.0"
@@ -9303,7 +9261,6 @@
       "version": "3.0.0",
       "resolved": "https://registry.npmjs.org/object-hash/-/object-hash-3.0.0.tgz",
       "integrity": "sha512-RSn9F68PjH9HqtltsSnqYC1XXoWe9Bju5+213R98cNGttag9q9yAOTzdbsqvIa7aNm5WffBZFpWYr2aWrklWAw==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">= 6"
@@ -9648,7 +9605,6 @@
       "version": "1.0.7",
       "resolved": "https://registry.npmjs.org/path-parse/-/path-parse-1.0.7.tgz",
       "integrity": "sha512-LDJzPVEEEPR+y48z93A0Ed0yXb8pAByGWo/k5YYdYgpY2/2EsOsksJrq7lOHxryrVOn1ejG6oAp8ahvOIQD8sw==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/path-scurry": {
@@ -9695,7 +9651,6 @@
       "version": "4.0.3",
       "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.3.tgz",
       "integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=12"
@@ -9708,7 +9663,6 @@
       "version": "2.3.0",
       "resolved": "https://registry.npmjs.org/pify/-/pify-2.3.0.tgz",
       "integrity": "sha512-udgsAY+fTnvv7kI7aaxbqwWNb0AHiB0qBO89PZKPkoTmGOgdbrHDKD+0B2X4uTfJ/FT1R09r9gTsjUjNJotuog==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=0.10.0"
@@ -9718,7 +9672,6 @@
       "version": "4.0.7",
       "resolved": "https://registry.npmjs.org/pirates/-/pirates-4.0.7.tgz",
       "integrity": "sha512-TfySrs/5nm8fQJDcBDuUng3VOUKsd7S+zqvbOTiGXHfxX4wK31ard+hoNuvkicM/2YFzlpDgABOevKSsB4G/FA==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">= 6"
@@ -9728,7 +9681,7 @@
       "version": "1.58.1",
       "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.58.1.tgz",
       "integrity": "sha512-+2uTZHxSCcxjvGc5C891LrS1/NlxglGxzrC4seZiVjcYVQfUa87wBL6rTDqzGjuoWNjnBzRqKmF6zRYGMvQUaQ==",
-      "dev": true,
+      "devOptional": true,
       "license": "Apache-2.0",
       "dependencies": {
         "playwright-core": "1.58.1"
@@ -9747,7 +9700,7 @@
       "version": "1.58.1",
       "resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.58.1.tgz",
       "integrity": "sha512-bcWzOaTxcW+VOOGBCQgnaKToLJ65d6AqfLVKEWvexyS3AS6rbXl+xdpYRMGSRBClPvyj44njOWoxjNdL/H9UNg==",
-      "dev": true,
+      "devOptional": true,
       "license": "Apache-2.0",
       "bin": {
         "playwright-core": "cli.js"
@@ -9770,7 +9723,6 @@
       "version": "8.5.6",
       "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.6.tgz",
       "integrity": "sha512-3Ybi1tAuwAP9s0r1UQ2J4n5Y0G05bJkpUIO0/bI9MhwmD70S5aTWbXGBwxHrelT+XM1k6dM0pk+SwNkpTRN7Pg==",
-      "dev": true,
       "funding": [
         {
           "type": "opencollective",
@@ -9799,7 +9751,6 @@
       "version": "15.1.0",
       "resolved": "https://registry.npmjs.org/postcss-import/-/postcss-import-15.1.0.tgz",
       "integrity": "sha512-hpr+J05B2FVYUAXHeK1YyI267J/dDDhMU6B6civm8hSY1jYJnBXxzKDKDswzJmtLHryrjhnDjqqp/49t8FALew==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "postcss-value-parser": "^4.0.0",
@@ -9817,7 +9768,6 @@
       "version": "4.1.0",
       "resolved": "https://registry.npmjs.org/postcss-js/-/postcss-js-4.1.0.tgz",
       "integrity": "sha512-oIAOTqgIo7q2EOwbhb8UalYePMvYoIeRY2YKntdpFQXNosSu3vLrniGgmH9OKs/qAkfoj5oB3le/7mINW1LCfw==",
-      "dev": true,
       "funding": [
         {
           "type": "opencollective",
@@ -9843,7 +9793,6 @@
       "version": "6.0.1",
       "resolved": "https://registry.npmjs.org/postcss-load-config/-/postcss-load-config-6.0.1.tgz",
       "integrity": "sha512-oPtTM4oerL+UXmx+93ytZVN82RrlY/wPUV8IeDxFrzIjXOLF1pN+EmKPLbubvKHT2HC20xXsCAH2Z+CKV6Oz/g==",
-      "dev": true,
       "funding": [
         {
           "type": "opencollective",
@@ -9886,7 +9835,6 @@
       "version": "6.2.0",
       "resolved": "https://registry.npmjs.org/postcss-nested/-/postcss-nested-6.2.0.tgz",
       "integrity": "sha512-HQbt28KulC5AJzG+cZtj9kvKB93CFCdLvog1WFLf1D+xmMvPGlBstkpTEZfK5+AN9hfJocyBFCNiqyS48bpgzQ==",
-      "dev": true,
       "funding": [
         {
           "type": "opencollective",
@@ -9912,7 +9860,6 @@
       "version": "6.1.2",
       "resolved": "https://registry.npmjs.org/postcss-selector-parser/-/postcss-selector-parser-6.1.2.tgz",
       "integrity": "sha512-Q8qQfPiZ+THO/3ZrOrO0cJJKfpYCagtMUkXbnEfmgUjwXg6z/WBeOyS9APBBPCTSiDV+s4SwQGu8yFsiMRIudg==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "cssesc": "^3.0.0",
@@ -9926,7 +9873,6 @@
       "version": "4.2.0",
       "resolved": "https://registry.npmjs.org/postcss-value-parser/-/postcss-value-parser-4.2.0.tgz",
       "integrity": "sha512-1NNCs6uurfkVbeXG4S8JFT9t19m45ICnif8zWLd5oPSZ50QnwMfK+H3jv408d4jw/7Bttv5axS5IiHoLaVNHeQ==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/prelude-ls": {
@@ -10040,7 +9986,6 @@
       "version": "1.2.3",
       "resolved": "https://registry.npmjs.org/queue-microtask/-/queue-microtask-1.2.3.tgz",
       "integrity": "sha512-NuaNSa6flKT5JaSYQzJok04JzTL1CA6aGhv5rfLW3PgqA+M2ChpZQnAC8h8i4ZFkBS8X5RqkDBHA7r4hej3K9A==",
-      "dev": true,
       "funding": [
         {
           "type": "github",
@@ -10829,7 +10774,6 @@
       "version": "1.0.0",
       "resolved": "https://registry.npmjs.org/read-cache/-/read-cache-1.0.0.tgz",
       "integrity": "sha512-Owdv/Ft7IjOgm/i0xvNDZ1LrRANRfew4b2prF3OWMQLxLfu3bS8FVhCsrSCMK4lR56Y9ya+AThoTpDCTxCmpRA==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "pify": "^2.3.0"
@@ -10839,7 +10783,6 @@
       "version": "3.6.0",
       "resolved": "https://registry.npmjs.org/readdirp/-/readdirp-3.6.0.tgz",
       "integrity": "sha512-hOS089on8RduqdbhvQ5Z37A0ESjsqz6qnRcffsMU3495FuTdqSm+7bhJ29JvIOsBDEEnan5DPu9t3To9VRlMzA==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "picomatch": "^2.2.1"
@@ -10852,7 +10795,6 @@
       "version": "2.3.1",
       "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-2.3.1.tgz",
       "integrity": "sha512-JU3teHTNjmE2VCGFzuY8EXzCDVwEqB2a8fsIvwaStHhAWJEeVd1o1QD80CU6+ZdEXXSLbSsuLwJjkCBWqRQUVA==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=8.6"
@@ -11117,7 +11059,6 @@
       "version": "1.22.11",
       "resolved": "https://registry.npmjs.org/resolve/-/resolve-1.22.11.tgz",
       "integrity": "sha512-RfqAvLnMl313r7c9oclB1HhUEAezcpLjz95wFH4LVuhk9JF/r22qmVP9AMmOU4vMX7Q8pN8jwNg/CSpdFnMjTQ==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "is-core-module": "^2.16.1",
@@ -11158,7 +11099,6 @@
       "version": "1.1.0",
       "resolved": "https://registry.npmjs.org/reusify/-/reusify-1.1.0.tgz",
       "integrity": "sha512-g6QUff04oZpHs0eG5p83rFLhHeV00ug/Yf9nZM6fLeUrPguBTkTQOdpAWWspMh55TZfVQDPaN3NQJfbVRAxdIw==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "iojs": ">=1.0.0",
@@ -11214,7 +11154,6 @@
       "version": "1.2.0",
       "resolved": "https://registry.npmjs.org/run-parallel/-/run-parallel-1.2.0.tgz",
       "integrity": "sha512-5l4VyZR86LZ/lDxZTR6jqL8AFE2S0IFLMP26AbjsLVADxHdhB/c0GUsH+y39UfCi3dzz8OlQuPmnaJOMoDHQBA==",
-      "dev": true,
       "funding": [
         {
           "type": "github",
@@ -11855,7 +11794,6 @@
       "version": "3.35.1",
       "resolved": "https://registry.npmjs.org/sucrase/-/sucrase-3.35.1.tgz",
       "integrity": "sha512-DhuTmvZWux4H1UOnWMB3sk0sbaCVOoQZjv8u1rDoTV0HTdGem9hkAZtl4JZy8P2z4Bg0nT+YMeOFyVr4zcG5Tw==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "@jridgewell/gen-mapping": "^0.3.2",
@@ -11891,7 +11829,6 @@
       "version": "1.0.0",
       "resolved": "https://registry.npmjs.org/supports-preserve-symlinks-flag/-/supports-preserve-symlinks-flag-1.0.0.tgz",
       "integrity": "sha512-ot0WnXS9fgdkgIcePe6RHNk1WA8+muPa6cSjeR3V8K27q9BB1rTE3R1p7Hv0z1ZyAc8s6Vvv8DIyWf681MAt0w==",
-      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">= 0.4"
@@ -11927,7 +11864,6 @@
       "version": "3.4.19",
       "resolved": "https://registry.npmjs.org/tailwindcss/-/tailwindcss-3.4.19.tgz",
       "integrity": "sha512-3ofp+LL8E+pK/JuPLPggVAIaEuhvIz4qNcf3nA1Xn2o/7fb7s/TYpHhwGDv1ZU3PkBluUVaF8PyCHcm48cKLWQ==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "@alloc/quick-lru": "^5.2.0",
@@ -11965,7 +11901,6 @@
       "version": "3.3.3",
       "resolved": "https://registry.npmjs.org/fast-glob/-/fast-glob-3.3.3.tgz",
       "integrity": "sha512-7MptL8U0cqcFdzIzwOTHoilX9x5BrNqye7Z/LuC7kCMRio1EMSyqRK3BEAUD7sXRq4iT4AzTVuZdhgQ2TCvYLg==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "@nodelib/fs.stat": "^2.0.2",
@@ -11982,7 +11917,6 @@
       "version": "5.1.2",
       "resolved": "https://registry.npmjs.org/glob-parent/-/glob-parent-5.1.2.tgz",
       "integrity": "sha512-AOIgSQCepiJYwP3ARnGx+5VnTu2HBYdzbGP45eLw1vr3zB3vZLeyed1sC9hnbcOc9/SrMyM5RPQrkGz4aS9Zow==",
-      "dev": true,
       "license": "ISC",
       "dependencies": {
         "is-glob": "^4.0.1"
@@ -12010,7 +11944,6 @@
       "version": "3.3.1",
       "resolved": "https://registry.npmjs.org/thenify/-/thenify-3.3.1.tgz",
       "integrity": "sha512-RVZSIV5IG10Hk3enotrhvz0T9em6cyHBLkH/YAZuKqd8hRkKhSfCGIcP2KUY0EPxndzANBmNllzWPwak+bheSw==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "any-promise": "^1.0.0"
@@ -12020,7 +11953,6 @@
       "version": "1.6.0",
       "resolved": "https://registry.npmjs.org/thenify-all/-/thenify-all-1.6.0.tgz",
       "integrity": "sha512-RNxQH/qI8/t3thXJDwcstUO4zeqo64+Uy/+sNVRBx4Xn2OX+OZ9oP+iJnNFqplFra2ZUVeKCSa2oVWi3T4uVmA==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "thenify": ">= 3.1.0 < 4"
@@ -12062,7 +11994,6 @@
       "version": "0.2.15",
       "resolved": "https://registry.npmjs.org/tinyglobby/-/tinyglobby-0.2.15.tgz",
       "integrity": "sha512-j2Zq4NyQYG5XMST4cbs02Ak8iJUdxRM0XI5QyxXuZOzKOINmWurp3smXu3y5wDcJrptwpSjgXHzIQxR0omXljQ==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "fdir": "^6.5.0",
@@ -12129,7 +12060,6 @@
       "version": "5.0.1",
       "resolved": "https://registry.npmjs.org/to-regex-range/-/to-regex-range-5.0.1.tgz",
       "integrity": "sha512-65P7iz6X5yEr1cwcgvQxbbIw7Uk3gOy5dIdtZ4rDveLqhrdJP+Li/Hx6tyK0NEb+2GCyneCMJiGqrADCSNk8sQ==",
-      "dev": true,
       "license": "MIT",
       "dependencies": {
         "is-number": "^7.0.0"
@@ -12217,7 +12147,6 @@
       "version": "0.1.13",
       "resolved": "https://registry.npmjs.org/ts-interface-checker/-/ts-interface-checker-0.1.13.tgz",
       "integrity": "sha512-Y/arvbn+rrz3JCKl9C4kVNfTfSm2/mEp5FSz5EsZSANGPSlQrpRI5M4PKF+mJnE52jOO90PnPSc3Ur3bTQw0gA==",
-      "dev": true,
       "license": "Apache-2.0"
     },
     "node_modules/tsconfig-paths": {
@@ -12334,7 +12263,7 @@
       "version": "5.3.3",
       "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.3.3.tgz",
       "integrity": "sha512-pXWcraxM0uxAS+tN0AG/BF2TyqmHO014Z070UsJ+pFvYuRSq8KH8DmWpnbXe0pEPDHXZV3FcAbJkijJ5oNEnWw==",
-      "dev": true,
+      "devOptional": true,
       "license": "Apache-2.0",
       "bin": {
         "tsc": "bin/tsc",
@@ -12536,7 +12465,6 @@
       "version": "1.0.2",
       "resolved": "https://registry.npmjs.org/util-deprecate/-/util-deprecate-1.0.2.tgz",
       "integrity": "sha512-EPD5q1uXyFxJpCrLnCc1nHnq3gOa6DZBocAIiI2TaSCA7VCJ1UJDMagCzIkXNsUYfD1daK//LTEQ8xiIbrHtcw==",
-      "dev": true,
       "license": "MIT"
     },
     "node_modules/uuid": {
@@ -12990,7 +12918,7 @@
       "version": "8.19.0",
       "resolved": "https://registry.npmjs.org/ws/-/ws-8.19.0.tgz",
       "integrity": "sha512-blAT2mjOEIi0ZzruJfIhb3nps74PRWTCz1IjglWEEpQl5XS/UNama6u2/rjFkDDouqr4L67ry+1aGIALViWjDg==",
-      "dev": true,
+      "devOptional": true,
       "license": "MIT",
       "engines": {
         "node": ">=10.0.0"
diff --git a/ui/litellm-dashboard/src/components/agents.test.tsx b/ui/litellm-dashboard/src/components/agents.test.tsx
new file mode 100644
index 00000000000..2d4c879dec0
--- /dev/null
+++ b/ui/litellm-dashboard/src/components/agents.test.tsx
@@ -0,0 +1,71 @@
+import React from "react";
+import { render, screen, waitFor } from "@testing-library/react";
+import { describe, it, expect, vi, beforeEach } from "vitest";
+import AgentsPanel from "./agents";
+
+vi.mock("./networking", () => ({
+  getAgentsList: vi.fn().mockResolvedValue({ agents: [] }),
+  deleteAgentCall: vi.fn(),
+  keyListCall: vi.fn().mockResolvedValue({ keys: [] }),
+}));
+
+vi.mock("./agents/add_agent_form", () => ({
+  default: () => <div data-testid="add-agent-form" />,
+}));
+
+vi.mock("./agents/agent_card_grid", () => ({
+  default: ({ isAdmin }: { isAdmin: boolean }) => (
+    <div data-testid="agent-card-grid" data-is-admin={String(isAdmin)} />
+  ),
+}));
+
+vi.mock("./agents/agent_info", () => ({
+  default: () => <div data-testid="agent-info" />,
+}));
+
+describe("AgentsPanel", () => {
+  beforeEach(() => {
+    vi.clearAllMocks();
+  });
+
+  it("should render the Agents panel title", async () => {
+    render(<AgentsPanel accessToken="test-token" userRole="Admin" />);
+    expect(screen.getByText("Agents")).toBeInTheDocument();
+  });
+
+  it("should show Add New Agent button for admin users", async () => {
+    render(<AgentsPanel accessToken="test-token" userRole="Admin" />);
+    expect(screen.getByText("+ Add New Agent")).toBeInTheDocument();
+  });
+
+  it("should show Add New Agent button for proxy_admin users", async () => {
+    render(<AgentsPanel accessToken="test-token" userRole="proxy_admin" />);
+    expect(screen.getByText("+ Add New Agent")).toBeInTheDocument();
+  });
+
+  it("should not show Add New Agent button for internal_user role", async () => {
+    render(<AgentsPanel accessToken="test-token" userRole="Internal User" />);
+    expect(screen.queryByText("+ Add New Agent")).not.toBeInTheDocument();
+  });
+
+  it("should not show Add New Agent button for internal_user_viewer role", async () => {
+    render(<AgentsPanel accessToken="test-token" userRole="Internal Viewer" />);
+    expect(screen.queryByText("+ Add New Agent")).not.toBeInTheDocument();
+  });
+
+  it("should pass isAdmin=true to AgentCardGrid for admin role", async () => {
+    render(<AgentsPanel accessToken="test-token" userRole="Admin" />);
+    await waitFor(() => {
+      const grid = screen.getByTestId("agent-card-grid");
+      expect(grid).toHaveAttribute("data-is-admin", "true");
+    });
+  });
+
+  it("should pass isAdmin=false to AgentCardGrid for internal user role", async () => {
+    render(<AgentsPanel accessToken="test-token" userRole="Internal User" />);
+    await waitFor(() => {
+      const grid = screen.getByTestId("agent-card-grid");
+      expect(grid).toHaveAttribute("data-is-admin", "false");
+    });
+  });
+});
diff --git a/ui/litellm-dashboard/src/components/agents.tsx b/ui/litellm-dashboard/src/components/agents.tsx
index 7ab6a5f0381..8dd9bc7d01c 100644
--- a/ui/litellm-dashboard/src/components/agents.tsx
+++ b/ui/litellm-dashboard/src/components/agents.tsx
@@ -141,11 +141,13 @@ const AgentsPanel: React.FC<AgentsPanelProps> = ({ accessToken, userRole }) => {
           showIcon
           className="mb-3"
         />
-        <div className="mt-2">
-          <Button onClick={handleAddAgent} disabled={!accessToken}>
-            + Add New Agent
-          </Button>
-        </div>
+        {isAdmin && (
+          <div className="mt-2">
+            <Button onClick={handleAddAgent} disabled={!accessToken}>
+              + Add New Agent
+            </Button>
+          </div>
+        )}
       </div>
 
       {selectedAgentId ? (
diff --git a/ui/litellm-dashboard/src/components/agents/agent_card_grid.tsx b/ui/litellm-dashboard/src/components/agents/agent_card_grid.tsx
index 0ba7902f8b2..5e984cf220d 100644
--- a/ui/litellm-dashboard/src/components/agents/agent_card_grid.tsx
+++ b/ui/litellm-dashboard/src/components/agents/agent_card_grid.tsx
@@ -37,7 +37,11 @@ const AgentCardGrid: React.FC<AgentCardGridProps> = ({
   if (!agentsList || agentsList.length === 0) {
     return (
       <div className="rounded-lg border border-gray-200 bg-gray-50/50 py-12 text-center">
-        <p className="text-gray-500">No agents found. Create one to get started.</p>
+        <p className="text-gray-500">
+          {isAdmin
+            ? "No agents found. Create one to get started."
+            : "No agents found. Contact an admin to create agents."}
+        </p>
       </div>
     );
   }