Merge branch 'main' into feat/bedrock-native-structured-outputs

Resolve conflict in test_converse_transformation.py by keeping both the structured outputs tests (from this branch) and the TestBedrockMinThinkingBudgetTokens tests (from main).
2026-09-11 22:51:28 +00:00 · 2026-02-16 15:34:22 -05:00 · 2026-02-16 15:34:22 -05:00 · 8f647cad2b
commit 8f647cad2b
parent da8c1bd111 a5e8eb6848
860 changed files with 26397 additions and 7234 deletions
--- a/.circleci/config.yml
+++ b/.circleci/config.yml
@ -1656,7 +1656,7 @@ jobs:
            - search_coverage.xml
            - search_coverage
  # Split litellm_mapped_tests into 3 parallel jobs for 3x faster execution
-  litellm_mapped_tests_proxy:
+  litellm_mapped_tests_proxy_part1:
    docker:
      - image: cimg/python:3.11
        auth:
@ -1667,23 +1667,53 @@ jobs:
    steps:
      - setup_litellm_test_deps
      - run:
-          name: Run proxy tests
+          name: Run proxy tests part 1 (high-volume directories)
          command: |
            prisma generate
-            python -m pytest tests/test_litellm/proxy --cov=litellm --cov-report=xml --junitxml=test-results/junit-proxy.xml --durations=10 -n 16 --maxfail=5 --timeout=300 -vv --log-cli-level=WARNING
-          no_output_timeout: 120m
+            export PYTHONUNBUFFERED=1
+            python -m pytest tests/test_litellm/proxy/guardrails tests/test_litellm/proxy/management_endpoints tests/test_litellm/proxy/_experimental tests/test_litellm/proxy/client tests/test_litellm/proxy/auth --cov=litellm --cov-report=xml --junitxml=test-results/junit-proxy-part1.xml --durations=10 -n 8 --maxfail=5 --timeout=60 -vv --log-cli-level=WARNING -r A
+          no_output_timeout: 60m
      - run:
          name: Rename the coverage files
          command: |
-            mv coverage.xml litellm_proxy_tests_coverage.xml
-            mv .coverage litellm_proxy_tests_coverage
+            mv coverage.xml litellm_proxy_tests_part1_coverage.xml
+            mv .coverage litellm_proxy_tests_part1_coverage
      - store_test_results:
          path: test-results
      - persist_to_workspace:
          root: .
          paths:
-            - litellm_proxy_tests_coverage.xml
-            - litellm_proxy_tests_coverage
+            - litellm_proxy_tests_part1_coverage.xml
+            - litellm_proxy_tests_part1_coverage
+  litellm_mapped_tests_proxy_part2:
+    docker:
+      - image: cimg/python:3.11
+        auth:
+          username: ${DOCKERHUB_USERNAME}
+          password: ${DOCKERHUB_PASSWORD}
+    working_directory: ~/project
+    resource_class: xlarge
+    steps:
+      - setup_litellm_test_deps
+      - run:
+          name: Run proxy tests part 2 (all other tests)
+          command: |
+            prisma generate
+            export PYTHONUNBUFFERED=1
+            python -m pytest tests/test_litellm/proxy --ignore=tests/test_litellm/proxy/guardrails --ignore=tests/test_litellm/proxy/management_endpoints --ignore=tests/test_litellm/proxy/_experimental --ignore=tests/test_litellm/proxy/client --ignore=tests/test_litellm/proxy/auth --cov=litellm --cov-report=xml --junitxml=test-results/junit-proxy-part2.xml --durations=10 -n 8 --maxfail=5 --timeout=60 -vv --log-cli-level=WARNING -r A
+          no_output_timeout: 60m
+      - run:
+          name: Rename the coverage files
+          command: |
+            mv coverage.xml litellm_proxy_tests_part2_coverage.xml
+            mv .coverage litellm_proxy_tests_part2_coverage
+      - store_test_results:
+          path: test-results
+      - persist_to_workspace:
+          root: .
+          paths:
+            - litellm_proxy_tests_part2_coverage.xml
+            - litellm_proxy_tests_part2_coverage
  litellm_mapped_tests_llms:
    docker:
      - image: cimg/python:3.11
@ -1724,7 +1754,7 @@ jobs:
      - run:
          name: Run core tests
          command: |
-            python -m pytest tests/test_litellm --ignore=tests/test_litellm/proxy --ignore=tests/test_litellm/llms --ignore=tests/test_litellm/integrations --ignore=tests/test_litellm/litellm_core_utils --cov=litellm --cov-report=xml --junitxml=test-results/junit-core.xml --durations=10 -n 16 --maxfail=5 --timeout=300 -vv --log-cli-level=WARNING
+            python -m pytest tests/test_litellm --ignore=tests/test_litellm/proxy --ignore=tests/test_litellm/llms --ignore=tests/test_litellm/integrations --ignore=tests/test_litellm/litellm_core_utils --ignore=tests/test_litellm/experimental_mcp_client --cov=litellm --cov-report=xml --junitxml=test-results/junit-core.xml --durations=10 -n 16 --maxfail=5 --timeout=300 -vv --log-cli-level=WARNING
          no_output_timeout: 120m
      - run:
          name: Rename the coverage files
@ -1765,6 +1795,33 @@ jobs:
          paths:
            - litellm_core_utils_tests_coverage.xml
            - litellm_core_utils_tests_coverage
+  litellm_mapped_tests_mcps:
+    docker:
+      - image: cimg/python:3.11
+        auth:
+          username: ${DOCKERHUB_USERNAME}
+          password: ${DOCKERHUB_PASSWORD}
+    working_directory: ~/project
+    resource_class: xlarge
+    steps:
+      - setup_litellm_test_deps
+      - run:
+          name: Run MCP client tests
+          command: |
+            python -m pytest tests/test_litellm/experimental_mcp_client --cov=litellm --cov-report=xml --junitxml=test-results/junit-mcps.xml --durations=10 -n 4 --maxfail=5 --timeout=300 -vv --log-cli-level=WARNING
+          no_output_timeout: 120m
+      - run:
+          name: Rename the coverage files
+          command: |
+            mv coverage.xml litellm_mcps_tests_coverage.xml
+            mv .coverage litellm_mcps_tests_coverage
+      - store_test_results:
+          path: test-results
+      - persist_to_workspace:
+          root: .
+          paths:
+            - litellm_mcps_tests_coverage.xml
+            - litellm_mcps_tests_coverage
  litellm_mapped_tests_integrations:
    docker:
      - image: cimg/python:3.11
@ -3597,6 +3654,7 @@ jobs:
              -p 4000:4000 \
              -e DATABASE_URL=postgresql://postgres:postgres@host.docker.internal:5432/circle_test \
              -e LITELLM_MASTER_KEY="sk-1234" \
+              -e ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY \
              -e AWS_ACCESS_KEY_ID=$AWS_ACCESS_KEY_ID \
              -e AWS_SECRET_ACCESS_KEY=$AWS_SECRET_ACCESS_KEY \
              -e AWS_REGION_NAME="us-east-1" \
@ -3653,7 +3711,7 @@ jobs:
            python -m venv venv
            . venv/bin/activate
            pip install coverage
-            coverage combine llm_translation_coverage realtime_translation_coverage llm_responses_api_coverage ocr_coverage search_coverage mcp_coverage logging_coverage audio_coverage litellm_router_coverage litellm_router_unit_coverage local_testing_part1_coverage local_testing_part2_coverage litellm_assistants_api_coverage auth_ui_unit_tests_coverage langfuse_coverage caching_coverage litellm_proxy_unit_tests_part1_coverage litellm_proxy_unit_tests_part2_coverage image_gen_coverage pass_through_unit_tests_coverage batches_coverage litellm_security_tests_coverage guardrails_coverage litellm_mapped_tests_coverage
+            coverage combine llm_translation_coverage realtime_translation_coverage llm_responses_api_coverage ocr_coverage search_coverage mcp_coverage litellm_mcps_tests_coverage logging_coverage audio_coverage litellm_router_coverage litellm_router_unit_coverage local_testing_part1_coverage local_testing_part2_coverage litellm_assistants_api_coverage auth_ui_unit_tests_coverage langfuse_coverage caching_coverage litellm_proxy_unit_tests_part1_coverage litellm_proxy_unit_tests_part2_coverage image_gen_coverage pass_through_unit_tests_coverage batches_coverage litellm_security_tests_coverage guardrails_coverage litellm_mapped_tests_coverage
            coverage xml
      - codecov/upload:
          file: ./coverage.xml
@ -4393,7 +4451,13 @@ workflows:
              only:
                - main
                - /litellm_.*/
-      - litellm_mapped_tests_proxy:
+      - litellm_mapped_tests_proxy_part1:
+          filters:
+            branches:
+              only:
+                - main
+                - /litellm_.*/
+      - litellm_mapped_tests_proxy_part2:
          filters:
            branches:
              only:
@ -4411,6 +4475,12 @@ workflows:
              only:
                - main
                - /litellm_.*/
+      - litellm_mapped_tests_mcps:
+          filters:
+            branches:
+              only:
+                - main
+                - /litellm_.*/
      - litellm_mapped_tests_integrations:
          filters:
            branches:
@ -4470,9 +4540,11 @@ workflows:
            - llm_responses_api_testing
            - ocr_testing
            - search_testing
-            - litellm_mapped_tests_proxy
+            - litellm_mapped_tests_proxy_part1
+            - litellm_mapped_tests_proxy_part2
            - litellm_mapped_tests_llms
            - litellm_mapped_tests_core
+            - litellm_mapped_tests_mcps
            - litellm_mapped_tests_integrations
            - litellm_mapped_tests_litellm_core_utils
            - litellm_mapped_enterprise_tests
@ -4549,9 +4621,11 @@ workflows:
            - llm_responses_api_testing
            - ocr_testing
            - search_testing
-            - litellm_mapped_tests_proxy
+            - litellm_mapped_tests_proxy_part1
+            - litellm_mapped_tests_proxy_part2
            - litellm_mapped_tests_llms
            - litellm_mapped_tests_core
+            - litellm_mapped_tests_mcps
            - litellm_mapped_tests_integrations
            - litellm_mapped_tests_litellm_core_utils
            - litellm_mapped_enterprise_tests
--- a/.github/workflows/test-litellm-ui-build.yml
+++ b/.github/workflows/test-litellm-ui-build.yml
@ -0,0 +1,32 @@
+name: UI Build Check
+permissions:
+  contents: read
+
+on:
+  pull_request:
+    branches: [main]
+
+jobs:
+  build-ui:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    defaults:
+      run:
+        working-directory: ui/litellm-dashboard
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: "20"
+          cache: "npm"
+          cache-dependency-path: ui/litellm-dashboard/package-lock.json
+
+      - name: Install dependencies
+        run: npm install
+
+      - name: Build
+        run: npm run build
--- a/.gitignore
+++ b/.gitignore
@ -2,6 +2,7 @@
 .venv
 .venv_policy_test
 .env
+.claude
 .newenv
 newenv/*
 litellm/proxy/myenv/*
--- a/docs/my-website/blog/claude_code_beta_headers/index.md
+++ b/docs/my-website/blog/claude_code_beta_headers/index.md
@ -0,0 +1,274 @@
+---
+slug: claude_code_beta_headers
+title: "Claude Code - Managing Anthropic Beta Headers"
+date: 2026-02-16T10:00:00
+authors:
+  - name: Sameer Kankute
+    title: SWE @ LiteLLM (LLM Translation)
+    url: https://www.linkedin.com/in/sameer-kankute/
+    image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
+  - name: Ishaan Jaff
+    title: "CTO, LiteLLM"
+    url: https://www.linkedin.com/in/reffajnaahsi/
+    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+  - name: Krrish Dholakia
+    title: "CEO, LiteLLM"
+    url: https://www.linkedin.com/in/krish-d/
+    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
+description: "How to manage and configure Anthropic beta headers with Claude Code in LiteLLM: filtering, mapping, and dynamic updates across providers."
+tags: [anthropic, claude, beta headers, configuration, liteLLM]
+hide_table_of_contents: false
+
+---
+import Image from '@theme/IdealImage';
+
+When using Claude Code with LiteLLM and non-Anthropic providers (Bedrock, Azure AI, Vertex AI), you need to ensure that only supported beta headers are sent to each provider. This guide explains how to add support for new beta headers or fix invalid beta header errors.
+
+## What Are Beta Headers?
+
+Anthropic uses beta headers to enable experimental features in Claude. When you use Claude Code, it may send beta headers like:
+
+```
+anthropic-beta: prompt-caching-scope-2026-01-05,advanced-tool-use-2025-11-20
+```
+
+However, not all providers support all Anthropic beta features. LiteLLM uses `anthropic_beta_headers_config.json` to manage which beta headers are supported by each provider.
+
+## Common Error Message
+
+```bash
+Error: The model returned the following errors: invalid beta flag
+```
+
+## How LiteLLM Handles Beta Headers
+
+LiteLLM uses a strict validation approach with a configuration file:
+
+```
+litellm/litellm/anthropic_beta_headers_config.json
+```
+
+This JSON file contains a **mapping** of beta headers for each provider:
+- **Keys**: Input beta header names (from Anthropic)
+- **Values**: Provider-specific header names (or `null` if unsupported)
+- **Validation**: Only headers present in the mapping with non-null values are forwarded
+
+This enforces stricter validation than just filtering unsupported headers - headers must be explicitly defined to be allowed.
+
+## Adding Support for a New Beta Header
+
+When Anthropic releases a new beta feature, you need to add it to the configuration file for each provider.
+
+### Step 1: Add the New Beta Header
+
+Open `anthropic_beta_headers_config.json` and add the new header to each provider's mapping:
+
+```json title="anthropic_beta_headers_config.json"
+{
+  "description": "Mapping of Anthropic beta headers for each provider. Keys are input header names, values are provider-specific header names (or null if unsupported). Only headers present in mapping keys with non-null values can be forwarded.",
+  "anthropic": {
+    "advanced-tool-use-2025-11-20": "advanced-tool-use-2025-11-20",
+    "new-feature-2026-03-01": "new-feature-2026-03-01",
+    ...
+  },
+  "azure_ai": {
+    "advanced-tool-use-2025-11-20": "advanced-tool-use-2025-11-20",
+    "new-feature-2026-03-01": "new-feature-2026-03-01",
+    ...
+  },
+  "bedrock_converse": {
+    "advanced-tool-use-2025-11-20": "tool-search-tool-2025-10-19",
+    "new-feature-2026-03-01": null,
+    ...
+  },
+  "bedrock": {
+    "advanced-tool-use-2025-11-20": "tool-search-tool-2025-10-19",
+    "new-feature-2026-03-01": null,
+    ...
+  },
+  "vertex_ai": {
+    "advanced-tool-use-2025-11-20": "tool-search-tool-2025-10-19",
+    "new-feature-2026-03-01": null,
+    ...
+  }
+}
+```
+
+**Key Points:**
+- **Supported headers**: Set the value to the provider-specific header name (often the same as the key)
+- **Unsupported headers**: Set the value to `null`
+- **Header transformations**: Some providers use different header names (e.g., Bedrock maps `advanced-tool-use-2025-11-20` to `tool-search-tool-2025-10-19`)
+- **Alphabetical order**: Keep headers sorted alphabetically for maintainability
+
+### Step 2: Reload Configuration (No Restart Required!)
+
+**Option 1: Dynamic Reload Without Restart** 
+
+Instead of restarting your application, you can dynamically reload the beta headers configuration using environment variables and API endpoints:
+
+```bash
+# Set environment variable to fetch from remote URL (Do this if you want to point it to some other URL)
+export LITELLM_ANTHROPIC_BETA_HEADERS_URL="https://raw.githubusercontent.com/BerriAI/litellm/main/litellm/anthropic_beta_headers_config.json"
+
+# Manually trigger reload via API (no restart needed!)
+curl -X POST "https://your-proxy-url/reload/anthropic_beta_headers" \
+  -H "Authorization: Bearer YOUR_ADMIN_TOKEN"
+```
+
+**Option 2: Schedule Automatic Reloads** 
+
+Set up automatic reloading to always stay up-to-date with the latest beta headers:
+
+```bash
+# Reload configuration every 24 hours
+curl -X POST "https://your-proxy-url/schedule/anthropic_beta_headers_reload?hours=24" \
+  -H "Authorization: Bearer YOUR_ADMIN_TOKEN"
+```
+
+**Option 3: Traditional Restart**
+
+If you prefer the traditional approach, restart your LiteLLM proxy or application:
+
+```bash
+# If using LiteLLM proxy
+litellm --config config.yaml
+
+# If using Python SDK
+# Just restart your Python application
+```
+
+:::tip Zero-Downtime Updates
+With dynamic reloading, you can fix invalid beta header errors **without restarting your service**! This is especially useful in production environments where downtime is costly.
+
+See [Auto Sync Anthropic Beta Headers](../proxy/sync_anthropic_beta_headers.md) for complete documentation.
+:::
+
+## Fixing Invalid Beta Header Errors
+
+If you encounter an "invalid beta flag" error, it means a beta header is being sent that the provider doesn't support.
+
+### Step 1: Identify the Problematic Header
+
+Check your logs to see which header is causing the issue:
+
+```bash
+Error: The model returned the following errors: invalid beta flag: new-feature-2026-03-01
+```
+
+### Step 2: Update the Config
+
+Set the header value to `null` for that provider:
+
+```json title="anthropic_beta_headers_config.json"
+{
+  "bedrock_converse": {
+    "new-feature-2026-03-01": null
+  }
+}
+```
+
+### Step 3: Restart and Test
+
+Restart your application and verify the header is now filtered out.
+
+## Contributing a Fix to LiteLLM
+
+Help the community by contributing your fix!
+
+### What to Include in Your PR
+
+1. **Update the config file**: Add the new beta header to `litellm/anthropic_beta_headers_config.json`
+2. **Test your changes**: Verify the header is correctly filtered/mapped for each provider
+3. **Documentation**: Include provider documentation links showing which headers are supported
+
+### Example PR Description
+
+```markdown
+## Add support for new-feature-2026-03-01 beta header
+
+### Changes
+- Added `new-feature-2026-03-01` to anthropic_beta_headers_config.json
+- Set to `null` for bedrock_converse (unsupported)
+- Set to header name for anthropic, azure_ai (supported)
+
+### Testing
+Tested with:
+- ✅ Anthropic: Header passed through correctly
+- ✅ Azure AI: Header passed through correctly  
+- ✅ Bedrock Converse: Header filtered out (returns error without fix)
+
+### References
+- Anthropic docs: [link]
+- AWS Bedrock docs: [link]
+```
+
+
+## How Beta Header Filtering Works
+
+When you make a request through LiteLLM:
+
+```mermaid
+sequenceDiagram
+    participant CC as Claude Code
+    participant LP as LiteLLM
+    participant Config as Beta Headers Config
+    participant Provider as Provider (Bedrock/Azure/etc)
+
+    CC->>LP: Request with beta headers
+    Note over CC,LP: anthropic-beta: header1,header2,header3
+    
+    LP->>Config: Load header mapping for provider
+    Config-->>LP: Returns mapping (header→value or null)
+    
+    Note over LP: Validate & Transform:<br/>1. Check if header exists in mapping<br/>2. Filter out null values<br/>3. Map to provider-specific names
+    
+    LP->>Provider: Request with filtered & mapped headers
+    Note over LP,Provider: anthropic-beta: mapped-header2<br/>(header1, header3 filtered out)
+    
+    Provider-->>LP: Success response
+    LP-->>CC: Response
+```
+
+### Filtering Rules
+
+1. **Header must exist in mapping**: Unknown headers are filtered out
+2. **Header must have non-null value**: Headers with `null` values are filtered out
+3. **Header transformation**: Headers are mapped to provider-specific names (e.g., `advanced-tool-use-2025-11-20` → `tool-search-tool-2025-10-19` for Bedrock)
+
+### Example
+
+Request with headers:
+```
+anthropic-beta: advanced-tool-use-2025-11-20,computer-use-2025-01-24,unknown-header
+```
+
+For Bedrock Converse:
+- ✅ `computer-use-2025-01-24` → `computer-use-2025-01-24` (supported, passed through)
+- ❌ `advanced-tool-use-2025-11-20` → filtered out (null value in config)
+- ❌ `unknown-header` → filtered out (not in config)
+
+Result sent to Bedrock:
+```
+anthropic-beta: computer-use-2025-01-24
+```
+
+## Dynamic Configuration Management (No Restart Required!)
+
+### Environment Variables
+
+Control how LiteLLM loads the beta headers configuration:
+
+| Variable | Description | Default |
+|----------|-------------|---------|
+| `LITELLM_ANTHROPIC_BETA_HEADERS_URL` | URL to fetch config from | GitHub main branch |
+| `LITELLM_LOCAL_ANTHROPIC_BETA_HEADERS` | Set to `True` to use local config only | `False` |
+
+**Example: Use Custom Config URL**
+```bash
+export LITELLM_ANTHROPIC_BETA_HEADERS_URL="https://your-company.com/custom-beta-headers.json"
+```
+
+**Example: Use Local Config Only (No Remote Fetching)**
+```bash
+export LITELLM_LOCAL_ANTHROPIC_BETA_HEADERS=True
+```
--- a/docs/my-website/blog/claude_opus_4_6/index.md
+++ b/docs/my-website/blog/claude_opus_4_6/index.md
@ -185,7 +185,7 @@ curl --location 'http://0.0.0.0:4000/chat/completions' \
 model_list:
  - model_name: claude-opus-4-6
    litellm_params:
-      model: bedrock/anthropic.claude-opus-4-6-v1:0
+      model: bedrock/anthropic.claude-opus-4-6-v1
      aws_access_key_id: os.environ/AWS_ACCESS_KEY_ID
      aws_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY
      aws_region_name: us-east-1
--- a/docs/my-website/docs/projects/openai-agents.md
+++ b/docs/my-website/docs/projects/openai-agents.md
@ -1,22 +1,121 @@
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';

 # OpenAI Agents SDK

-The [OpenAI Agents SDK](https://github.com/openai/openai-agents-python) is a lightweight framework for building multi-agent workflows.
-It includes an official LiteLLM extension that lets you use any of the 100+ supported providers (Anthropic, Gemini, Mistral, Bedrock, etc.) 
+Use OpenAI Agents SDK with any LLM provider through LiteLLM Proxy.
+
+The [OpenAI Agents SDK](https://github.com/openai/openai-agents-python) is a lightweight framework for building multi-agent workflows. It includes an official LiteLLM extension that lets you use any of the 100+ supported providers.
+
+## Quick Start
+
+### 1. Install Dependencies
+
+```bash
+pip install "openai-agents[litellm]"
+```
+
+### 2. Add Model to Config
+
+```yaml title="config.yaml"
+model_list:
+  - model_name: gpt-4o
+    litellm_params:
+      model: "openai/gpt-4o"
+      api_key: "os.environ/OPENAI_API_KEY"
+
+  - model_name: claude-sonnet
+    litellm_params:
+      model: "anthropic/claude-3-5-sonnet-20241022"
+      api_key: "os.environ/ANTHROPIC_API_KEY"
+
+  - model_name: gemini-pro
+    litellm_params:
+      model: "gemini/gemini-2.0-flash-exp"
+      api_key: "os.environ/GEMINI_API_KEY"
+```
+
+### 3. Start LiteLLM Proxy
+
+```bash
+litellm --config config.yaml
+```
+
+### 4. Use with Proxy
+
+<Tabs>
+<TabItem value="proxy" label="Via Proxy">

 ```python
 from agents import Agent, Runner
 from agents.extensions.models.litellm_model import LitellmModel

+# Point to LiteLLM proxy
 agent = Agent(
    name="Assistant",
    instructions="You are a helpful assistant.",
-    model=LitellmModel(model="provider/model-name")
+    model=LitellmModel(
+        model="claude-sonnet",  # Model from config.yaml
+        api_key="sk-1234",      # LiteLLM API key
+        base_url="http://localhost:4000"
+    )
 )

-result = Runner.run_sync(agent, "your_prompt_here")
-print("Result:", result.final_output)
+result = await Runner.run(agent, "What is LiteLLM?")
+print(result.final_output)
 ```

- [GitHub](https://github.com/openai/openai-agents-python)
- [LiteLLM Extension Docs](https://openai.github.io/openai-agents-python/ref/extensions/litellm/)
+</TabItem>
+<TabItem value="direct" label="Direct (No Proxy)">
+
+```python
+from agents import Agent, Runner
+from agents.extensions.models.litellm_model import LitellmModel
+
+# Use any provider directly
+agent = Agent(
+    name="Assistant",
+    instructions="You are a helpful assistant.",
+    model=LitellmModel(
+        model="anthropic/claude-3-5-sonnet-20241022",
+        api_key="your-anthropic-key"
+    )
+)
+
+result = await Runner.run(agent, "What is LiteLLM?")
+print(result.final_output)
+```
+
+</TabItem>
+</Tabs>
+
+## Track Usage
+
+Enable usage tracking to monitor token consumption:
+
+```python
+from agents import Agent, ModelSettings
+from agents.extensions.models.litellm_model import LitellmModel
+
+agent = Agent(
+    name="Assistant",
+    model=LitellmModel(model="claude-sonnet", api_key="sk-1234"),
+    model_settings=ModelSettings(include_usage=True)
+)
+
+result = await Runner.run(agent, "Hello")
+print(result.context_wrapper.usage)  # Token counts
+```
+
+## Environment Variables
+
+| Variable | Value | Description |
+|----------|-------|-------------|
+| `LITELLM_BASE_URL` | `http://localhost:4000` | LiteLLM proxy URL |
+| `LITELLM_API_KEY` | `sk-1234` | Your LiteLLM API key |
+
+## Related Resources
+
+- [OpenAI Agents SDK Documentation](https://openai.github.io/openai-agents-python/)
+- [LiteLLM Extension Docs](https://openai.github.io/openai-agents-python/models/litellm/)
+- [LiteLLM Proxy Quick Start](../proxy/quick_start)
--- a/docs/my-website/docs/proxy/access_groups.md
+++ b/docs/my-website/docs/proxy/access_groups.md
@ -0,0 +1,122 @@
+import Image from '@theme/IdealImage';
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# Access Groups
+
+Access Groups simplify how you define and manage resource access across your organization. Instead of configuring models, MCP servers, and agents separately on each key or team, you create one group that bundles the resources you want to grant, then attach that group to your keys or teams.
+
+## Overview
+
+**Access Groups** let you define a reusable set of allowed resources—models, MCP servers, and agents—in a single place. One group can grant access to all three resource types. Simply attach the group to a key or team, and they get access to everything defined in that group.
+
+- **Unified resource control** – One group controls access to models, MCP servers, and agents together
+- **Reusable** – Define once, attach to many keys or teams
+- **Easy to maintain** – Update the group (add or remove resources) and all attached keys and teams automatically reflect the change
+- **Clear visibility** – See exactly which resources each group grants and which keys/teams use it
+
+<Image img={require('../../img/ui_access_groups.png')} />
+
+### How It Works
+
+**Key concept:** Define resources in a group → Attach group to key or team → Key/team gets access to all resources in the group
+
+| Resource Type   | What the group controls                                              |
+| --------------- | -------------------------------------------------------------------- |
+| **Models**      | Which LLM models keys/teams can use (e.g., `gpt-4`, `claude-3-opus`) |
+| **MCP Servers** | Which MCP servers are available for tool calling                     |
+| **Agents**      | Which agents can be invoked                                          |
+
+## How to Create and Use Access Groups in the UI
+
+### 1. Navigate to Access Groups
+
+Go to the Admin UI (e.g. `http://localhost:4000/ui` or your `PROXY_BASE_URL/ui`) and click **Access Groups** in the sidebar.
+
+![](https://colony-recorder.s3.amazonaws.com/files/2026-02-15/d117fdb2-18c8-49e0-91e6-1f830d2d4b85/ascreenshot_f5822a0ddac64e3383124419d0c66298_text_export.jpeg)
+
+### 2. Create an Access Group
+
+Click **Create Access Group** and give your group a name.
+
+![](https://colony-recorder.s3.amazonaws.com/files/2026-02-15/aefb900d-d106-4436-806c-3608ad19659f/ascreenshot_3f6fed1256604fe3b7038a0778ce3342_text_export.jpeg)
+
+![](https://colony-recorder.s3.amazonaws.com/files/2026-02-15/0951bb93-61bd-477e-beaf-f58810f8980b/ascreenshot_f0fb5d552fd74ff8a1080e82758fcdc2_text_export.jpeg)
+
+### 3. Define Resources in the Group
+
+Use the tabs to select which models, MCP servers, and agents this group grants access to:
+
+- **Models tab** – Select the LLM models
+- **MCP Servers tab** – Select MCP servers (for tool calling)
+- **Agents tab** – Select agents
+
+![](https://colony-recorder.s3.amazonaws.com/files/2026-02-15/37398e8f-cd50-48c9-85e2-c77b2eeb994b/ascreenshot_440ec7906c8f4199b30ef91c903960b9_text_export.jpeg)
+
+![](https://colony-recorder.s3.amazonaws.com/files/2026-02-15/99d36543-8582-4bb7-a34d-3d5fe0fcf12f/ascreenshot_d9983240955c496892e1f7c38c074045_text_export.jpeg)
+
+![](https://colony-recorder.s3.amazonaws.com/files/2026-02-15/06fc5919-5c71-4fc3-999b-da7a4800af3f/ascreenshot_db93fdf742b249dc90a4b9d5991d6097_text_export.jpeg)
+
+### 4. Attach the Access Group to a Key
+
+When creating or editing a virtual key, expand **Optional Settings** and select your Access Group. The key will inherit access to all models, MCP servers, and agents defined in that group.
+
+1. Go to **Virtual Keys** and click **+ Create New Key**
+2. Expand **Optional Settings**
+3. In the Access Group field, select the group you created
+4. Save the key
+
+![](https://colony-recorder.s3.amazonaws.com/files/2026-02-15/cdfa76ab-bf38-4ca4-a97d-2cb50fafe50b/ascreenshot_046daecb57554c28ba553cf6c01f5450_text_export.jpeg)
+
+![](https://colony-recorder.s3.amazonaws.com/files/2026-02-15/84f08e9c-e9d0-42aa-8317-f385190b6d7d/ascreenshot_2d239716d30f431d9ad494baf7933d6a_text_export.jpeg)
+
+![](https://colony-recorder.s3.amazonaws.com/files/2026-02-15/41d7b7f9-ac58-4602-b887-c35c9b419dce/ascreenshot_8abd4fef48014dd1b88848411e6d7912_text_export.jpeg)
+
+![](https://colony-recorder.s3.amazonaws.com/files/2026-02-15/e37b01c0-f2d7-4133-8b2f-ccc51f6769e1/ascreenshot_f495df428ad54cac9ec43b46c3dfc1b1_text_export.jpeg)
+
+![](https://colony-recorder.s3.amazonaws.com/files/2026-02-15/3fe33cad-6b64-46c3-a66e-6e6e073c3d7a/ascreenshot_f2dcc79ae8af47dd86ade2f85165d3c1_text_export.jpeg)
+
+### 5. Attach the Access Group to a Team
+
+You can also attach an Access Group to a team when creating or editing the team. All keys associated with that team will then have access to the resources defined in the group.
+
+## Use Cases
+
+### Team-based Access
+
+Create groups like "Engineering", "Data Science", or "Product" with the models, MCP servers, and agents each team needs. Attach the group to the team—no need to configure each resource on every key.
+
+### Environment Separation
+
+- **Production group** – Production models, approved MCP servers, and production agents
+- **Development group** – Cost-efficient models, experimental MCP tools, and dev agents
+
+Attach the appropriate group to keys or teams based on environment.
+
+### Simplified Onboarding
+
+New developers get a key with an Access Group instead of manually configuring models, MCP servers, and agents. Add them to the right team or give them a key with the correct group.
+
+### Centralized Updates
+
+When you add a new model or MCP server to a group, every key and team attached to that group automatically gains access. Remove a resource from the group and it’s revoked everywhere at once.
+
+## Access Group vs. Model Access Groups
+
+LiteLLM has two related concepts:
+
+| Feature    | **Access Groups** (this page)                                           | **Model Access Groups**                                 |
+| ---------- | ----------------------------------------------------------------------- | ------------------------------------------------------- |
+| Definition | Define in the UI; one group can include models, MCP servers, and agents | Defined in config or via API; groups are model-centric  |
+| Scope      | Models + MCP servers + agents                                           | Models only                                             |
+| Attach to  | Keys, teams                                                             | Keys, teams                                             |
+| Use when   | You want unified control over models, MCP, and agents from the UI       | You need config-based or API-based model access control |
+
+For config-based model access with `access_groups` in `model_info`, see [Model Access Groups](./model_access_groups.md).
+
+## Related Documentation
+
+- [Virtual Keys](./virtual_keys.md) – Creating and managing API keys
+- [Role-based Access Controls](./access_control.md) – Organizations, teams, and user roles
+- [Model Access Groups](./model_access_groups.md) – Config-based model access groups
+- [MCP Control](../mcp_control.md) – MCP server setup and access control
--- a/docs/my-website/docs/proxy/config_settings.md
+++ b/docs/my-website/docs/proxy/config_settings.md
@ -520,6 +520,7 @@ router_settings:
 | DEBUG_OTEL | Enable debug mode for OpenTelemetry
 | DEFAULT_ALLOWED_FAILS | Maximum failures allowed before cooling down a model. Default is 3
 | DEFAULT_A2A_AGENT_TIMEOUT | Default timeout in seconds for A2A (Agent-to-Agent) protocol requests. Default is 6000
+| DEFAULT_ACCESS_GROUP_CACHE_TTL | Time-to-live in seconds for cached access group information. Default is 600 (10 minutes)
 | DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS | Default maximum tokens for Anthropic chat completions. Default is 4096
 | DEFAULT_BATCH_SIZE | Default batch size for operations. Default is 512
 | DEFAULT_CHUNK_OVERLAP | Default chunk overlap for RAG text splitters. Default is 200
@ -548,6 +549,7 @@ router_settings:
 | DEFAULT_MCP_SEMANTIC_FILTER_EMBEDDING_MODEL | Default embedding model for MCP semantic tool filtering. Default is "text-embedding-3-small"
 | DEFAULT_MCP_SEMANTIC_FILTER_SIMILARITY_THRESHOLD | Default similarity threshold for MCP semantic tool filtering. Default is 0.3
 | DEFAULT_MCP_SEMANTIC_FILTER_TOP_K | Default number of top results to return for MCP semantic tool filtering. Default is 10
+| MCP_NPM_CACHE_DIR | Directory for npm cache used by STDIO MCP servers. In containers the default (~/.npm) may not exist or be read-only. Default is `/tmp/.npm_mcp_cache`
 | MCP_OAUTH2_TOKEN_CACHE_DEFAULT_TTL | Default TTL in seconds for MCP OAuth2 token cache. Default is 3600
 | MCP_OAUTH2_TOKEN_CACHE_MAX_SIZE | Maximum number of entries in MCP OAuth2 token cache. Default is 200
 | MCP_OAUTH2_TOKEN_CACHE_MIN_TTL | Minimum TTL in seconds for MCP OAuth2 token cache. Default is 10
@ -745,10 +747,12 @@ router_settings:
 | LITERAL_API_KEY | API key for Literal integration
 | LITERAL_API_URL | API URL for Literal service
 | LITERAL_BATCH_SIZE | Batch size for Literal operations
+| LITELLM_ANTHROPIC_BETA_HEADERS_URL | Custom URL for fetching Anthropic beta headers configuration. Default is the GitHub main branch URL
 | LITELLM_ANTHROPIC_DISABLE_URL_SUFFIX | Disable automatic URL suffix appending for Anthropic API base URLs. When set to `true`, prevents LiteLLM from automatically adding `/v1/messages` or `/v1/complete` to custom Anthropic API endpoints
 | LITELLM_ASSETS_PATH | Path to directory for UI assets and logos. Used when running with read-only filesystem (e.g., Kubernetes). Default is `/var/lib/litellm/assets` in Docker.
 | LITELLM_CLI_JWT_EXPIRATION_HOURS | Expiration time in hours for CLI-generated JWT tokens. Default is 24 hours
 | LITELLM_DD_AGENT_HOST | Hostname or IP of DataDog agent for LiteLLM-specific logging. When set, logs are sent to agent instead of direct API
+| LITELLM_DEPLOYMENT_ENVIRONMENT | Environment name for the deployment (e.g., "production", "staging"). Used as a fallback when OTEL_ENVIRONMENT_NAME is not set. Sets the `environment` tag in telemetry data
 | LITELLM_DD_AGENT_PORT | Port of DataDog agent for LiteLLM-specific log intake. Default is 10518
 | LITELLM_DD_LLM_OBS_PORT | Port for Datadog LLM Observability agent. Default is 8126
 | LITELLM_DONT_SHOW_FEEDBACK_BOX | Flag to hide feedback box in LiteLLM UI
@ -765,7 +769,9 @@ router_settings:
 | LITELM_ENVIRONMENT | Environment of LiteLLM Instance, used by logging services. Currently only used by DeepEval.
 | LITELLM_KEY_ROTATION_ENABLED | Enable auto-key rotation for LiteLLM (boolean). Default is false.
 | LITELLM_KEY_ROTATION_CHECK_INTERVAL_SECONDS | Interval in seconds for how often to run job that auto-rotates keys. Default is 86400 (24 hours).
+| LITELLM_KEY_ROTATION_GRACE_PERIOD | Duration to keep old key valid after rotation (e.g. "24h", "2d"). Default is empty (immediate revoke). Used for scheduled rotations and as fallback when not specified in regenerate request.
 | LITELLM_LICENSE | License key for LiteLLM usage
+| LITELLM_LOCAL_ANTHROPIC_BETA_HEADERS | Set to `True` to use the local bundled Anthropic beta headers config only, disabling remote fetching. Default is `False`
 | LITELLM_LOCAL_MODEL_COST_MAP | Local configuration for model cost mapping in LiteLLM
 | LITELLM_LOCAL_POLICY_TEMPLATES | When set to "true", uses local backup policy templates instead of fetching from GitHub. Policy templates are fetched from https://raw.githubusercontent.com/BerriAI/litellm/main/policy_templates.json by default, with automatic fallback to local backup on failure
 | LITELLM_LOG | Enable detailed logging for LiteLLM
--- a/docs/my-website/docs/proxy/guardrails/policy_templates.md
+++ b/docs/my-website/docs/proxy/guardrails/policy_templates.md
@ -16,8 +16,6 @@ Policy templates provide pre-configured guardrail policies that you can use as a
 6. Review and customize the pre-filled policy form
 7. Click **"Create Policy"** to save

-![Policy Templates UI](/img/policy_templates_ui.png)
-
 ### Workflow

 ```
--- a/docs/my-website/docs/proxy/logging.md
+++ b/docs/my-website/docs/proxy/logging.md
@ -1338,6 +1338,7 @@ litellm_settings:
    s3_aws_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY  # AWS Secret Access Key for S3
    s3_path: my-test-path # [OPTIONAL] set path in bucket you want to write logs to
    s3_endpoint_url: https://s3.amazonaws.com  # [OPTIONAL] S3 endpoint URL, if you want to use Backblaze/cloudflare s3 buckets
+    s3_use_virtual_hosted_style: false # [OPTIONAL] use virtual-hosted-style URLs (bucket.endpoint/key) instead of path-style (endpoint/bucket/key). Useful for S3-compatible services like MinIO
    s3_strip_base64_files: false # [OPTIONAL] remove base64 files before storing in s3
 ```

--- a/docs/my-website/docs/proxy/virtual_keys.md
+++ b/docs/my-website/docs/proxy/virtual_keys.md
@ -549,11 +549,14 @@ curl 'http://localhost:4000/key/sk-1234/regenerate' \
    "models": [
      "gpt-4",
      "gpt-3.5-turbo"
-    ]
+    ],
+    "grace_period": "48h"
  }'

 ```

+**Grace period (optional)**: Set `grace_period` (e.g. `"24h"`, `"2d"`, `"1w"`) to keep the old key valid for a transitional period. Both old and new keys work until the grace period elapses, enabling seamless cutover without production downtime. Omitted or empty = immediate revoke. Can also be set via `LITELLM_KEY_ROTATION_GRACE_PERIOD` env var for scheduled rotations.
+
 **Read More**

 - [Write rotated keys to secrets manager](https://docs.litellm.ai/docs/secret#aws-secret-manager)
@ -640,11 +643,13 @@ Set these environment variables when starting the proxy:
 |----------|-------------|---------|
 | `LITELLM_KEY_ROTATION_ENABLED` | Enable the rotation worker | `false` |
 | `LITELLM_KEY_ROTATION_CHECK_INTERVAL_SECONDS` | How often to scan for keys to rotate (in seconds) | `86400` (24 hours) |
+| `LITELLM_KEY_ROTATION_GRACE_PERIOD` | Duration to keep old key valid after rotation (e.g. `24h`, `2d`) | `""` (immediate revoke) |

 **Example:**
 ```bash
 export LITELLM_KEY_ROTATION_ENABLED=true
 export LITELLM_KEY_ROTATION_CHECK_INTERVAL_SECONDS=3600  # Check every hour
+export LITELLM_KEY_ROTATION_GRACE_PERIOD=48h  # Keep old key valid for 48h during cutover

 litellm --config config.yaml
 ```
--- a/docs/my-website/img/release_notes/guard_actions.png
+++ b/docs/my-website/img/release_notes/guard_actions.png
--- a/docs/my-website/img/ui_access_groups.png
+++ b/docs/my-website/img/ui_access_groups.png
--- a/docs/my-website/package-lock.json
+++ b/docs/my-website/package-lock.json
@ -20455,6 +20455,13 @@
        "url": "https://opencollective.com/webpack"
      }
    },
+    "node_modules/search-insights": {
+      "version": "2.17.3",
+      "resolved": "https://registry.npmjs.org/search-insights/-/search-insights-2.17.3.tgz",
+      "integrity": "sha512-RQPdCYTa8A68uM2jwxoY842xDhvx3E5LFL1LxvxCNMev4o5mLuokczhzjAgGwUZBAmOKZknArSxLKmXtIi2AxQ==",
+      "license": "MIT",
+      "peer": true
+    },
    "node_modules/section-matter": {
      "version": "1.0.0",
      "resolved": "https://registry.npmjs.org/section-matter/-/section-matter-1.0.0.tgz",
--- a/docs/my-website/release_notes/v1.81.12.md
+++ b/docs/my-website/release_notes/v1.81.12.md
@ -0,0 +1,433 @@
+---
+title: "[Preview] v1.81.12 - Guardrail Policy Templates & Action Builder"
+slug: "v1-81-12"
+date: 2026-02-14T00:00:00
+authors:
+  - name: Krrish Dholakia
+    title: CEO, LiteLLM
+    url: https://www.linkedin.com/in/krish-d/
+    image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
+  - name: Ishaan Jaff
+    title: CTO, LiteLLM
+    url: https://www.linkedin.com/in/reffajnaahsi/
+    image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
+hide_table_of_contents: false
+---
+
+## Deploy this version
+
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+import Image from '@theme/IdealImage';
+
+<Tabs>
+<TabItem value="docker" label="Docker">
+
+``` showLineNumbers title="docker run litellm"
+docker run \
+-e STORE_MODEL_IN_DB=True \
+-p 4000:4000 \
+ghcr.io/berriai/litellm:main-v1.81.12.rc.1
+```
+
+</TabItem>
+<TabItem value="pip" label="Pip">
+
+``` showLineNumbers title="pip install litellm"
+pip install litellm==1.81.12.rc1
+```
+
+</TabItem>
+</Tabs>
+
+## Key Highlights
+
+- **Policy Templates** - [Pre-configured guardrail policy templates for common safety and compliance use-cases (including NSFW, toxic content, and child safety)](../../docs/proxy/guardrails/policy_templates)
+- **Guardrail Action Builder** - [Build and customize guardrail policy flows with the new action-builder UI and conditional execution support](../../docs/proxy/guardrails/policy_templates)
+- **MCP OAuth2 M2M + Tracing** - [Add machine-to-machine OAuth2 support for MCP servers and OpenTelemetry tracing for MCP calls through AI Gateway](../../docs/mcp)
+- **Responses API `shell` Tool & `context_management` support** - [Server-side context management (compaction) and Shell tool support for the OpenAI Responses API](../../docs/response_api)
+- **Access Groups** - [Create access groups to manage model, MCP server, and agent access across teams and keys](../../docs/proxy/access_groups)
+- **50+ New Bedrock Regional Model Entries** - DeepSeek V3.2, MiniMax M2.1, Kimi K2.5, Qwen3 Coder Next, and NVIDIA Nemotron Nano across multiple regions
+- **Add Semgrep & fix OOMs** - [Static analysis rules and out-of-memory fixes](#add-semgrep--fix-ooms) - [PR #20912](https://github.com/BerriAI/litellm/pull/20912)
+
+---
+
+## Add Semgrep & fix OOMs
+
+This release fixes out-of-memory (OOM) risks from unbounded `asyncio.Queue()` usage. Log queues (e.g. GCS bucket) and DB spend-update queues were previously unbounded and could grow without limit under load. They now use a configurable max size (`LITELLM_ASYNCIO_QUEUE_MAXSIZE`, default 1000); when full, queues flush immediately to make room instead of growing memory. A Semgrep rule (`.semgrep/rules/python/unbounded-memory.yml`) was added to flag similar unbounded-memory patterns in future code. [PR #20912](https://github.com/BerriAI/litellm/pull/20912)
+
+---
+
+## Guardrail Action Builder
+
+This release adds a visual action builder for guardrail policies with conditional execution support. You can now chain guardrails into multi-step pipelines — if a simple guardrail fails, route to an advanced one instead of immediately blocking. Each step has configurable ON PASS and ON FAIL actions (Next Step, Block, or Allow), and you can test the full pipeline with a sample message before saving.
+
+![Guardrail Action Builder](../img/release_notes/guard_actions.png)
+
+### Access Groups
+
+Access Groups simplify defining resource access across your organization. One group can grant access to models, MCP servers, and agents—simply attach it to a key or team. Create groups in the Admin UI, define which resources each group includes, then assign the group when creating keys or teams. Updates to a group apply automatically to all attached keys and teams.
+
+<Image img={require('../img/ui_access_groups.png')} />
+
+## New Providers and Endpoints
+
+### New Providers (2 new providers)
+
+| Provider | Supported LiteLLM Endpoints | Description |
+| -------- | --------------------------- | ----------- |
+| [Scaleway](../../docs/providers/scaleway) | `/chat/completions` | Scaleway Generative APIs for chat completions |
+| [Sarvam AI](../../docs/providers/sarvam) | `/chat/completions`, `/audio/transcriptions`, `/audio/speech` | Sarvam AI STT and TTS support for Indian languages |
+
+---
+
+## New Models / Updated Models
+
+#### New Model Support (19 highlighted models)
+
+| Provider | Model | Context Window | Input ($/1M tokens) | Output ($/1M tokens) |
+| -------- | ----- | -------------- | ------------------- | -------------------- |
+| AWS Bedrock | `deepseek.v3.2` | 164K | $0.62 | $1.85 |
+| AWS Bedrock | `minimax.minimax-m2.1` | 196K | $0.30 | $1.20 |
+| AWS Bedrock | `moonshotai.kimi-k2.5` | 262K | $0.60 | $3.00 |
+| AWS Bedrock | `moonshotai.kimi-k2-thinking` | 262K | $0.73 | $3.03 |
+| AWS Bedrock | `qwen.qwen3-coder-next` | 262K | $0.50 | $1.20 |
+| AWS Bedrock | `nvidia.nemotron-nano-3-30b` | 262K | $0.06 | $0.24 |
+| Azure AI | `azure_ai/kimi-k2.5` | 262K | $0.60 | $3.00 |
+| Vertex AI | `vertex_ai/zai-org/glm-5-maas` | 200K | $1.00 | $3.20 |
+| MiniMax | `minimax/MiniMax-M2.5` | 1M | $0.30 | $1.20 |
+| MiniMax | `minimax/MiniMax-M2.5-lightning` | 1M | $0.30 | $2.40 |
+| Dashscope | `dashscope/qwen3-max` | 258K | Tiered pricing | Tiered pricing |
+| Perplexity | `perplexity/preset/pro-search` | - | Per-request | Per-request |
+| Perplexity | `perplexity/openai/gpt-4o` | - | Per-request | Per-request |
+| Perplexity | `perplexity/openai/gpt-5.2` | - | Per-request | Per-request |
+| Vercel AI Gateway | `vercel_ai_gateway/anthropic/claude-opus-4.6` | 200K | $5.00 | $25.00 |
+| Vercel AI Gateway | `vercel_ai_gateway/anthropic/claude-sonnet-4` | 200K | $3.00 | $15.00 |
+| Vercel AI Gateway | `vercel_ai_gateway/anthropic/claude-haiku-4.5` | 200K | $1.00 | $5.00 |
+| Sarvam AI | `sarvam/sarvam-m` | 8K | Free tier | Free tier |
+| Anthropic | `fast/claude-opus-4-6` | 1M | $30.00 | $150.00 |
+
+*Note: AWS Bedrock models are available across multiple regions (us-east-1, us-east-2, us-west-2, eu-central-1, eu-north-1, ap-northeast-1, ap-south-1, ap-southeast-3, sa-east-1). 54 regional model entries were added in total.*
+
+#### Features
+
+- **[Anthropic](../../docs/providers/anthropic)**
+    - Enable non-tool structured outputs on Claude Opus 4.5 and 4.6 using `output_format` param - [PR #20548](https://github.com/BerriAI/litellm/pull/20548)
+    - Add support for `anthropic_messages` call type in prompt caching - [PR #19233](https://github.com/BerriAI/litellm/pull/19233)
+    - Managing Anthropic Beta Headers with remote URL fetching - [PR #20935](https://github.com/BerriAI/litellm/pull/20935), [PR #21110](https://github.com/BerriAI/litellm/pull/21110)
+    - Remove `x-anthropic-billing` block - [PR #20951](https://github.com/BerriAI/litellm/pull/20951)
+    - Use Authorization Bearer for OAuth tokens instead of x-api-key - [PR #21039](https://github.com/BerriAI/litellm/pull/21039)
+    - Filter unsupported JSON schema constraints for structured outputs - [PR #20813](https://github.com/BerriAI/litellm/pull/20813)
+    - New Claude Opus 4.6 features for `/v1/messages` - [PR #20733](https://github.com/BerriAI/litellm/pull/20733)
+    - Fix `reasoning_effort=None` and `"none"` should return None for Opus 4.6 - [PR #20800](https://github.com/BerriAI/litellm/pull/20800)
+
+- **[AWS Bedrock](../../docs/providers/bedrock)**
+    - Extend model support with 4 new beta models - [PR #21035](https://github.com/BerriAI/litellm/pull/21035)
+    - Add Claude Opus 4.6 to `_supports_tool_search_on_bedrock` - [PR #21017](https://github.com/BerriAI/litellm/pull/21017)
+    - Correct Bedrock Claude Opus 4.6 model IDs (remove `:0` suffix) - [PR #20564](https://github.com/BerriAI/litellm/pull/20564), [PR #20671](https://github.com/BerriAI/litellm/pull/20671)
+    - Add `output_config` as supported param - [PR #20748](https://github.com/BerriAI/litellm/pull/20748)
+
+- **[Vertex AI](../../docs/providers/vertex)**
+    - Add Vertex GLM-5 model support - [PR #21053](https://github.com/BerriAI/litellm/pull/21053)
+    - Propagate `extra_headers` anthropic-beta to request body - [PR #20666](https://github.com/BerriAI/litellm/pull/20666)
+    - Preserve `usageMetadata` in `_hidden_params` - [PR #20559](https://github.com/BerriAI/litellm/pull/20559)
+    - Map `IMAGE_PROHIBITED_CONTENT` to `content_filter` - [PR #20524](https://github.com/BerriAI/litellm/pull/20524)
+    - Add RAG ingest for Vertex AI - [PR #21120](https://github.com/BerriAI/litellm/pull/21120)
+
+- **[OCI / Cohere](../../docs/providers/cohere)**
+    - OCI Cohere responseFormat/Pydantic support - [PR #20663](https://github.com/BerriAI/litellm/pull/20663)
+    - Fix OCI Cohere system messages by populating `preambleOverride` - [PR #20958](https://github.com/BerriAI/litellm/pull/20958)
+
+- **[Perplexity](../../docs/providers/perplexity)**
+    - Perplexity Research API support with preset search - [PR #20860](https://github.com/BerriAI/litellm/pull/20860)
+
+- **[MiniMax](../../docs/providers/minimax)**
+    - Add MiniMax-M2.5 and MiniMax-M2.5-lightning models - [PR #21054](https://github.com/BerriAI/litellm/pull/21054)
+
+- **[Kimi / Moonshot](../../docs/providers/moonshot)**
+    - Add Kimi model pricing by region - [PR #20855](https://github.com/BerriAI/litellm/pull/20855)
+    - Add `moonshotai.kimi-k2.5` - [PR #20863](https://github.com/BerriAI/litellm/pull/20863)
+
+- **[Dashscope](../../docs/providers/dashscope)**
+    - Add `dashscope/qwen3-max` model with tiered pricing - [PR #20919](https://github.com/BerriAI/litellm/pull/20919)
+
+- **[Vercel AI Gateway](../../docs/providers/vercel_ai_gateway)**
+    - Add new Vercel AI Anthropic models - [PR #20745](https://github.com/BerriAI/litellm/pull/20745)
+
+- **[Azure AI](../../docs/providers/azure_ai)**
+    - Add `azure_ai/kimi-k2.5` to Azure model DB - [PR #20896](https://github.com/BerriAI/litellm/pull/20896)
+    - Support Azure AD token auth for non-Claude azure_ai models - [PR #20981](https://github.com/BerriAI/litellm/pull/20981)
+    - Fix Azure batches issues - [PR #21092](https://github.com/BerriAI/litellm/pull/21092)
+
+- **[DeepSeek](../../docs/providers/deepseek)**
+    - Sync DeepSeek model metadata and add bare-name fallback - [PR #20938](https://github.com/BerriAI/litellm/pull/20938)
+
+- **[Gemini](../../docs/providers/gemini)**
+    - Handle image in assistant message for Gemini - [PR #20845](https://github.com/BerriAI/litellm/pull/20845)
+    - Add missing tpm/rpm for Gemini models - [PR #21175](https://github.com/BerriAI/litellm/pull/21175)
+
+- **General**
+    - Add 30 missing models to pricing JSON - [PR #20797](https://github.com/BerriAI/litellm/pull/20797)
+    - Cleanup 39 deprecated OpenRouter models - [PR #20786](https://github.com/BerriAI/litellm/pull/20786)
+    - Standardize endpoint `display_name` naming convention - [PR #20791](https://github.com/BerriAI/litellm/pull/20791)
+    - Fix and stabilize model cost map formatting - [PR #20895](https://github.com/BerriAI/litellm/pull/20895)
+    - Export `PermissionDeniedError` from `litellm.__init__` - [PR #20960](https://github.com/BerriAI/litellm/pull/20960)
+
+### Bug Fixes
+
+- **[Anthropic](../../docs/providers/anthropic)**
+    - Fix `get_supported_anthropic_messages_params` - [PR #20752](https://github.com/BerriAI/litellm/pull/20752)
+    - Fix `base_model` name for body and deployment name in URL - [PR #20747](https://github.com/BerriAI/litellm/pull/20747)
+
+- **[Azure](../../docs/providers/azure/azure)**
+    - Preserve `content_policy_violation` error details from Azure OpenAI - [PR #20883](https://github.com/BerriAI/litellm/pull/20883)
+
+- **[Vertex AI](../../docs/providers/vertex)**
+    - Fix Gemini multi-turn tool calling message formatting (added and reverted) - [PR #20569](https://github.com/BerriAI/litellm/pull/20569), [PR #21051](https://github.com/BerriAI/litellm/pull/21051)
+
+---
+
+## LLM API Endpoints
+
+#### Features
+
+- **[Responses API](../../docs/response_api)**
+    - Add server-side context management (compaction) support - [PR #21058](https://github.com/BerriAI/litellm/pull/21058)
+    - Add Shell tool support for OpenAI Responses API - [PR #21063](https://github.com/BerriAI/litellm/pull/21063)
+    - Preserve tool call argument deltas when streaming id is omitted - [PR #20712](https://github.com/BerriAI/litellm/pull/20712)
+    - Preserve interleaved thinking/redacted_thinking blocks during streaming - [PR #20702](https://github.com/BerriAI/litellm/pull/20702)
+
+- **[Chat Completions](../../docs/completion/input)**
+    - Add Web Search support using LiteLLM `/search` (web search interception hook) - [PR #20483](https://github.com/BerriAI/litellm/pull/20483)
+    - Preserved nullable object fields by carrying schema properties - [PR #19132](https://github.com/BerriAI/litellm/pull/19132)
+    - Support `prompt_cache_key` for OpenAI and Azure chat completions - [PR #20989](https://github.com/BerriAI/litellm/pull/20989)
+
+- **[Pass-Through Endpoints](../../docs/pass_through/bedrock)**
+    - Add support for `langchain_aws` via LiteLLM passthrough - [PR #20843](https://github.com/BerriAI/litellm/pull/20843)
+    - Add `custom_body` parameter to `endpoint_func` in `create_pass_through_route` - [PR #20849](https://github.com/BerriAI/litellm/pull/20849)
+
+- **[Vector Stores](../../docs/providers/openai)**
+    - Add `target_model_names` for vector store endpoints - [PR #21089](https://github.com/BerriAI/litellm/pull/21089)
+
+- **General**
+    - Add `output_config` as supported param - [PR #20748](https://github.com/BerriAI/litellm/pull/20748)
+    - Add managed error file support - [PR #20838](https://github.com/BerriAI/litellm/pull/20838)
+
+#### Bugs
+
+- **General**
+    - Stop leaking Python tracebacks in streaming SSE error responses - [PR #20850](https://github.com/BerriAI/litellm/pull/20850)
+    - Fix video list pagination cursors not encoded with provider metadata - [PR #20710](https://github.com/BerriAI/litellm/pull/20710)
+    - Handle `metadata=None` in SDK path retry/error logic - [PR #20873](https://github.com/BerriAI/litellm/pull/20873)
+    - Fix Spend logs pickle error with Pydantic models and redaction - [PR #20685](https://github.com/BerriAI/litellm/pull/20685)
+    - Remove duplicate `PerplexityResponsesConfig` from `LLM_CONFIG_NAMES` - [PR #21105](https://github.com/BerriAI/litellm/pull/21105)
+
+---
+
+## Management Endpoints / UI
+
+#### Features
+
+- **Access Groups**
+    - New Access Groups feature for managing model, MCP server, and agent access - [PR #21022](https://github.com/BerriAI/litellm/pull/21022)
+    - Access Groups table and details page UI - [PR #21165](https://github.com/BerriAI/litellm/pull/21165)
+    - Refactor `model_ids` to `model_names` for backwards compatibility - [PR #21166](https://github.com/BerriAI/litellm/pull/21166)
+
+- **Policies**
+    - Allow connecting Policies to Tags, simulating Policies, viewing key/team counts - [PR #20904](https://github.com/BerriAI/litellm/pull/20904)
+    - Guardrail pipeline support for conditional sequential execution - [PR #21177](https://github.com/BerriAI/litellm/pull/21177)
+    - Pipeline flow builder UI for guardrail policies - [PR #21188](https://github.com/BerriAI/litellm/pull/21188)
+
+- **SSO / Auth**
+    - New Login With SSO Button - [PR #20908](https://github.com/BerriAI/litellm/pull/20908)
+    - M2M OAuth2 UI Flow - [PR #20794](https://github.com/BerriAI/litellm/pull/20794)
+    - Allow Organization and Team Admins to call `/invitation/new` - [PR #20987](https://github.com/BerriAI/litellm/pull/20987)
+    - Invite User: Email Integration Alert - [PR #20790](https://github.com/BerriAI/litellm/pull/20790)
+    - Populate identity fields in proxy admin JWT early-return path - [PR #21169](https://github.com/BerriAI/litellm/pull/21169)
+
+- **Spend Logs**
+    - Show predefined error codes in filter with user definable fallback - [PR #20773](https://github.com/BerriAI/litellm/pull/20773)
+    - Paginated searchable model select - [PR #20892](https://github.com/BerriAI/litellm/pull/20892)
+    - Sorting columns support - [PR #21143](https://github.com/BerriAI/litellm/pull/21143)
+    - Allow sorting on `/spend/logs/ui` - [PR #20991](https://github.com/BerriAI/litellm/pull/20991)
+
+- **UI Improvements**
+    - Navbar: Option to hide Usage Popup - [PR #20910](https://github.com/BerriAI/litellm/pull/20910)
+    - Model Page: Improve Credentials Messaging - [PR #21076](https://github.com/BerriAI/litellm/pull/21076)
+    - Fallbacks: Default configurable to 10 models - [PR #21144](https://github.com/BerriAI/litellm/pull/21144)
+    - Fallback display with arrows and card structure - [PR #20922](https://github.com/BerriAI/litellm/pull/20922)
+    - Team Info: Migrate to AntD Tabs + Table - [PR #20785](https://github.com/BerriAI/litellm/pull/20785)
+    - AntD refactoring and 0 cost models fix - [PR #20687](https://github.com/BerriAI/litellm/pull/20687)
+    - Zscaler AI Guard UI - [PR #21077](https://github.com/BerriAI/litellm/pull/21077)
+    - Include Config Defined Pass Through Endpoints - [PR #20898](https://github.com/BerriAI/litellm/pull/20898)
+    - Rename "HTTP" to "Streamable HTTP (Recommended)" in MCP server page - [PR #21000](https://github.com/BerriAI/litellm/pull/21000)
+    - MCP server discovery UI - [PR #21079](https://github.com/BerriAI/litellm/pull/21079)
+
+- **Virtual Keys**
+    - Allow Management keys to access `user/daily/activity` and team - [PR #20124](https://github.com/BerriAI/litellm/pull/20124)
+    - Skip premium check for empty metadata fields on team/key update - [PR #20598](https://github.com/BerriAI/litellm/pull/20598)
+
+#### Bugs
+
+- Logs: Fix Input and Output Copying - [PR #20657](https://github.com/BerriAI/litellm/pull/20657)
+- Teams: Fix Available Teams - [PR #20682](https://github.com/BerriAI/litellm/pull/20682)
+- Spend Logs: Reset Filters Resets Custom Date Range - [PR #21149](https://github.com/BerriAI/litellm/pull/21149)
+- Usage: Request Chart stack variant fix - [PR #20894](https://github.com/BerriAI/litellm/pull/20894)
+- Add Auto Router: Description Text Input Focus - [PR #21004](https://github.com/BerriAI/litellm/pull/21004)
+- Guardrail Edit: LiteLLM Content Filter Categories - [PR #21002](https://github.com/BerriAI/litellm/pull/21002)
+- Add null guard for models in API keys table - [PR #20655](https://github.com/BerriAI/litellm/pull/20655)
+- Show error details instead of 'Data Not Available' for failed requests - [PR #20656](https://github.com/BerriAI/litellm/pull/20656)
+- Fix Spend Management Tests - [PR #21088](https://github.com/BerriAI/litellm/pull/21088)
+- Fix JWT email domain validation error message - [PR #21212](https://github.com/BerriAI/litellm/pull/21212)
+
+---
+
+## AI Integrations
+
+### Logging
+
+- **[PostHog](../../docs/observability/posthog_integration)**
+    - Fix JSON serialization error for non-serializable objects - [PR #20668](https://github.com/BerriAI/litellm/pull/20668)
+
+- **[Prometheus](../../docs/proxy/logging#prometheus)**
+    - Sanitize label values to prevent metric scrape failures - [PR #20600](https://github.com/BerriAI/litellm/pull/20600)
+
+- **[Langfuse](../../docs/proxy/logging#langfuse)**
+    - Prevent empty proxy request spans from being sent to Langfuse - [PR #19935](https://github.com/BerriAI/litellm/pull/19935)
+
+- **[OpenTelemetry](../../docs/proxy/logging#otel)**
+    - Auto-infer `otlp_http` exporter when endpoint is configured - [PR #20438](https://github.com/BerriAI/litellm/pull/20438)
+
+- **[CloudZero](../../docs/proxy/logging)**
+    - Update CBF field mappings per LIT-1907 - [PR #20906](https://github.com/BerriAI/litellm/pull/20906)
+
+- **General**
+    - Allow `MAX_CALLBACKS` override via env var - [PR #20781](https://github.com/BerriAI/litellm/pull/20781)
+    - Add `standard_logging_payload_excluded_fields` config option - [PR #20831](https://github.com/BerriAI/litellm/pull/20831)
+    - Enable `verbose_logger` when `LITELLM_LOG=DEBUG` - [PR #20496](https://github.com/BerriAI/litellm/pull/20496)
+    - Guard against None `litellm_metadata` in batch logging path - [PR #20832](https://github.com/BerriAI/litellm/pull/20832)
+    - Propagate model-level tags from config to SpendLogs - [PR #20769](https://github.com/BerriAI/litellm/pull/20769)
+
+### Guardrails
+
+- **Policy Templates**
+    - New Policy Templates: pre-configured guardrail combinations for specific use-cases - [PR #21025](https://github.com/BerriAI/litellm/pull/21025)
+    - Add NSFW policy template, toxic keywords in multiple languages, child safety content filter, JSON content viewer - [PR #21205](https://github.com/BerriAI/litellm/pull/21205)
+    - Add toxic/abusive content filter guardrails - [PR #20934](https://github.com/BerriAI/litellm/pull/20934)
+
+- **Pipeline Execution**
+    - Add guardrail pipeline support for conditional sequential execution - [PR #21177](https://github.com/BerriAI/litellm/pull/21177)
+    - Agent Guardrails on streaming output - [PR #21206](https://github.com/BerriAI/litellm/pull/21206)
+    - Pipeline flow builder UI - [PR #21188](https://github.com/BerriAI/litellm/pull/21188)
+
+- **[Zscaler AI Guard](../../docs/apply_guardrail)**
+    - Zscaler AI Guard bug fixes and support during post-call - [PR #20801](https://github.com/BerriAI/litellm/pull/20801)
+    - Zscaler AI Guard UI - [PR #21077](https://github.com/BerriAI/litellm/pull/21077)
+
+- **[ZGuard](../../docs/apply_guardrail)**
+    - Add team policy mapping for ZGuard - [PR #20608](https://github.com/BerriAI/litellm/pull/20608)
+
+- **General**
+    - Add logging to all unified guardrails + link to custom code guardrail templates - [PR #20900](https://github.com/BerriAI/litellm/pull/20900)
+    - Forward request headers + `litellm_version` to generic guardrails - [PR #20729](https://github.com/BerriAI/litellm/pull/20729)
+    - Empty `guardrails`/`policies` arrays should not trigger enterprise license check - [PR #20567](https://github.com/BerriAI/litellm/pull/20567)
+    - Fix OpenAI moderation guardrails - [PR #20718](https://github.com/BerriAI/litellm/pull/20718)
+    - Fix `/v2/guardrails/list` returning sensitive values - [PR #20796](https://github.com/BerriAI/litellm/pull/20796)
+    - Fix guardrail status error - [PR #20972](https://github.com/BerriAI/litellm/pull/20972)
+    - Reuse `get_instance_fn` in `initialize_custom_guardrail` - [PR #20917](https://github.com/BerriAI/litellm/pull/20917)
+
+---
+
+## Spend Tracking, Budgets and Rate Limiting
+
+- **Prevent shared backend model key from being polluted** by per-deployment custom pricing - [PR #20679](https://github.com/BerriAI/litellm/pull/20679)
+- **Avoid in-place mutation** in SpendUpdateQueue aggregation - [PR #20876](https://github.com/BerriAI/litellm/pull/20876)
+
+---
+
+## MCP Gateway (12 updates)
+
+- **MCP M2M OAuth2 Support** - Add support for machine-to-machine OAuth2 for MCP servers - [PR #20788](https://github.com/BerriAI/litellm/pull/20788)
+- **MCP Server Discovery UI** - Browse and discover available MCP servers from the UI - [PR #21079](https://github.com/BerriAI/litellm/pull/21079)
+- **MCP Tracing** - Add OpenTelemetry tracing for MCP calls running through AI Gateway - [PR #21018](https://github.com/BerriAI/litellm/pull/21018)
+- **MCP OAuth2 Debug Headers** - Client-side debug headers for OAuth2 troubleshooting - [PR #21151](https://github.com/BerriAI/litellm/pull/21151)
+- **Fix MCP "Session not found" errors** - Resolve session persistence issues - [PR #21040](https://github.com/BerriAI/litellm/pull/21040)
+- **Fix MCP OAuth2 root endpoints** returning "MCP server not found" - [PR #20784](https://github.com/BerriAI/litellm/pull/20784)
+- **Fix MCP OAuth2 query param merging** when `authorization_url` already contains params - [PR #20968](https://github.com/BerriAI/litellm/pull/20968)
+- **Fix MCP SCOPES on Atlassian** issue - [PR #21150](https://github.com/BerriAI/litellm/pull/21150)
+- **Fix MCP StreamableHTTP backend** - Use `anyio.fail_after` instead of `asyncio.wait_for` - [PR #20891](https://github.com/BerriAI/litellm/pull/20891)
+- **Inject `NPM_CONFIG_CACHE`** into STDIO MCP subprocess env - [PR #21069](https://github.com/BerriAI/litellm/pull/21069)
+- **Block spaces and hyphens** in MCP server names and aliases - [PR #21074](https://github.com/BerriAI/litellm/pull/21074)
+
+---
+
+## Performance / Loadbalancing / Reliability improvements (8 improvements)
+
+- **Remove orphan entries from queue** - Fix memory leak in scheduler queue - [PR #20866](https://github.com/BerriAI/litellm/pull/20866)
+- **Remove repeated provider parsing** in budget limiter hot path - [PR #21043](https://github.com/BerriAI/litellm/pull/21043)
+- **Use current retry exception** for retry backoff instead of stale exception - [PR #20725](https://github.com/BerriAI/litellm/pull/20725)
+- **Add Semgrep & fix OOMs** - Static analysis rules and out-of-memory fixes - [PR #20912](https://github.com/BerriAI/litellm/pull/20912)
+- **Add Pyroscope** for continuous profiling and observability - [PR #21167](https://github.com/BerriAI/litellm/pull/21167)
+- **Respect `ssl_verify`** with shared aiohttp sessions - [PR #20349](https://github.com/BerriAI/litellm/pull/20349)
+- **Fix shared health check serialization** - [PR #21119](https://github.com/BerriAI/litellm/pull/21119)
+- **Change model mismatch logs** from WARNING to DEBUG - [PR #20994](https://github.com/BerriAI/litellm/pull/20994)
+
+---
+
+## Database Changes
+
+### Schema Updates
+
+| Table | Change Type | Description | PR | Migration |
+| ----- | ----------- | ----------- | -- | --------- |
+| `LiteLLM_VerificationToken` | New Indexes | Added indexes on `user_id`+`team_id`, `team_id`, and `budget_reset_at`+`expires` | [PR #20736](https://github.com/BerriAI/litellm/pull/20736) | [Migration](https://github.com/BerriAI/litellm/blob/main/litellm-proxy-extras/litellm_proxy_extras/migrations/20260209085821_add_verificationtoken_indexes/migration.sql) |
+| `LiteLLM_PolicyAttachmentTable` | New Column | Added `tags` text array for policy-to-tag connections | [PR #21061](https://github.com/BerriAI/litellm/pull/21061) | [Migration](https://github.com/BerriAI/litellm/blob/main/litellm-proxy-extras/litellm_proxy_extras/migrations/20260212103349_adjust_tags_policy_table/migration.sql) |
+| `LiteLLM_AccessGroupTable` | New Table | Access groups for managing model, MCP server, and agent access | [PR #21022](https://github.com/BerriAI/litellm/pull/21022) | [Migration](https://github.com/BerriAI/litellm/blob/main/litellm-proxy-extras/litellm_proxy_extras/migrations/20260212143306_add_access_group_table/migration.sql) |
+| `LiteLLM_AccessGroupTable` | Column Change | Renamed `access_model_ids` to `access_model_names` | [PR #21166](https://github.com/BerriAI/litellm/pull/21166) | [Migration](https://github.com/BerriAI/litellm/blob/main/litellm-proxy-extras/litellm_proxy_extras/migrations/20260213170952_access_group_change_to_model_name/migration.sql) |
+| `LiteLLM_ManagedVectorStoreTable` | New Table | Managed vector store tracking with model mappings | - | [Migration](https://github.com/BerriAI/litellm/blob/main/litellm-proxy-extras/litellm_proxy_extras/migrations/20260213105436_add_managed_vector_store_table/migration.sql) |
+| `LiteLLM_TeamTable`, `LiteLLM_VerificationToken` | New Column | Added `access_group_ids` text array | [PR #21022](https://github.com/BerriAI/litellm/pull/21022) | [Migration](https://github.com/BerriAI/litellm/blob/main/litellm-proxy-extras/litellm_proxy_extras/migrations/20260212143306_add_access_group_table/migration.sql) |
+| `LiteLLM_GuardrailsTable` | New Column | Added `team_id` text column | - | [Migration](https://github.com/BerriAI/litellm/blob/main/litellm-proxy-extras/litellm_proxy_extras/migrations/20260214094754_schema_sync/migration.sql) |
+
+---
+
+## Documentation Updates (14 updates)
+
+- LiteLLM Observatory section added to v1.81.9 release notes - [PR #20675](https://github.com/BerriAI/litellm/pull/20675)
+- Callback registration optimization added to release notes - [PR #20681](https://github.com/BerriAI/litellm/pull/20681)
+- Middleware performance blog post - [PR #20677](https://github.com/BerriAI/litellm/pull/20677)
+- UI Team Soft Budget documentation - [PR #20669](https://github.com/BerriAI/litellm/pull/20669)
+- UI Contributing and Troubleshooting guide - [PR #20674](https://github.com/BerriAI/litellm/pull/20674)
+- Reorganize Admin UI subsection - [PR #20676](https://github.com/BerriAI/litellm/pull/20676)
+- SDK proxy authentication (OAuth2/JWT auto-refresh) - [PR #20680](https://github.com/BerriAI/litellm/pull/20680)
+- Forward client headers to LLM API documentation fix - [PR #20768](https://github.com/BerriAI/litellm/pull/20768)
+- Add docs guide for using policies - [PR #20914](https://github.com/BerriAI/litellm/pull/20914)
+- Add native thinking param examples for Claude Opus 4.6 - [PR #20799](https://github.com/BerriAI/litellm/pull/20799)
+- Fix Claude Code MCP tutorial - [PR #21145](https://github.com/BerriAI/litellm/pull/21145)
+- Add API base URLs for Dashscope (International and China/Beijing) - [PR #21083](https://github.com/BerriAI/litellm/pull/21083)
+- Fix `DEFAULT_NUM_WORKERS_LITELLM_PROXY` default (1, not 4) - [PR #21127](https://github.com/BerriAI/litellm/pull/21127)
+- Correct ElevenLabs support status in README - [PR #20643](https://github.com/BerriAI/litellm/pull/20643)
+
+---
+
+## New Contributors
+* @iver56 made their first contribution in [PR #20643](https://github.com/BerriAI/litellm/pull/20643)
+* @eliasaronson made their first contribution in [PR #20666](https://github.com/BerriAI/litellm/pull/20666)
+* @NirantK made their first contribution in [PR #19656](https://github.com/BerriAI/litellm/pull/19656)
+* @looksgood made their first contribution in [PR #20919](https://github.com/BerriAI/litellm/pull/20919)
+* @kelvin-tran made their first contribution in [PR #20548](https://github.com/BerriAI/litellm/pull/20548)
+* @bluet made their first contribution in [PR #20873](https://github.com/BerriAI/litellm/pull/20873)
+* @itayov made their first contribution in [PR #20729](https://github.com/BerriAI/litellm/pull/20729)
+* @CSteigstra made their first contribution in [PR #20960](https://github.com/BerriAI/litellm/pull/20960)
+* @rahulrd25 made their first contribution in [PR #20569](https://github.com/BerriAI/litellm/pull/20569)
+* @muraliavarma made their first contribution in [PR #20598](https://github.com/BerriAI/litellm/pull/20598)
+* @joaokopernico made their first contribution in [PR #21039](https://github.com/BerriAI/litellm/pull/21039)
+* @datzscaler made their first contribution in [PR #21077](https://github.com/BerriAI/litellm/pull/21077)
+* @atapia27 made their first contribution in [PR #20922](https://github.com/BerriAI/litellm/pull/20922)
+* @fpagny made their first contribution in [PR #21121](https://github.com/BerriAI/litellm/pull/21121)
+* @aidankovacic-8451 made their first contribution in [PR #21119](https://github.com/BerriAI/litellm/pull/21119)
+* @luisgallego-aily made their first contribution in [PR #19935](https://github.com/BerriAI/litellm/pull/19935)
+
+---
+
+## Full Changelog
+[v1.81.9.rc.1...v1.81.12.rc.1](https://github.com/BerriAI/litellm/compare/v1.81.9.rc.1...v1.81.12.rc.1)
--- a/docs/my-website/release_notes/v1.81.6.md
+++ b/docs/my-website/release_notes/v1.81.6.md
@ -14,6 +14,14 @@ authors:
 hide_table_of_contents: false
 ---

+:::danger Known Issue - CPU Usage
+
+This release had known issues with CPU usage. This has been fixed in [v1.81.9-stable](./v1-81-9).
+
+**We recommend using v1.81.9-stable instead.**
+
+:::
+
 ## Deploy this version

 import Tabs from '@theme/Tabs';
--- a/docs/my-website/release_notes/v1.81.9.md
+++ b/docs/my-website/release_notes/v1.81.9.md
@ -1,5 +1,5 @@
 ---
-title: "[Preview] v1.81.9 - Control which MCP Servers are exposed on the Internet"
+title: "v1.81.9 - Control which MCP Servers are exposed on the Internet"
 slug: "v1-81-9"
 date: 2026-02-07T00:00:00
 authors:
@ -14,6 +14,16 @@ authors:
 hide_table_of_contents: false
 ---

+:::info Stable Release Branch
+
+For each stable release, we now maintain a dedicated branch with the format `litellm_stable_release_branch_x_xx_xx` for the version.
+
+This allows easier patching for day 0 model launches.
+
+**Branch for v1.81.9:** [litellm_stable_release_branch_1_81_9](https://github.com/BerriAI/litellm/tree/litellm_stable_release_branch_1_81_9)
+
+:::
+
 ## Deploy this version

 import Tabs from '@theme/Tabs';
@ -27,7 +37,7 @@ import Image from '@theme/IdealImage';
 docker run \
 -e STORE_MODEL_IN_DB=True \
 -p 4000:4000 \
-ghcr.io/berriai/litellm:main-v1.81.9.rc.1
+ghcr.io/berriai/litellm:main-v1.81.9-stable
 ```

 </TabItem>
--- a/docs/my-website/sidebars.js
+++ b/docs/my-website/sidebars.js
@ -176,6 +176,7 @@ const sidebars = {
        "tutorials/copilotkit_sdk",
        "tutorials/google_adk",
        "tutorials/livekit_xai_realtime",
+        "projects/openai-agents"
      ]
    },

@ -467,6 +468,7 @@ const sidebars = {
            "proxy/model_access_guide",
            "proxy/model_access",
            "proxy/model_access_groups",
+            "proxy/access_groups",
            "proxy/team_model_add"
          ]
        },
--- a/enterprise/dist/litellm_enterprise-0.1.32-py3-none-any.whl
+++ b/enterprise/dist/litellm_enterprise-0.1.32-py3-none-any.whl
--- a/enterprise/dist/litellm_enterprise-0.1.32.tar.gz
+++ b/enterprise/dist/litellm_enterprise-0.1.32.tar.gz
--- a/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py
+++ b/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py
@ -4,7 +4,7 @@ Polls LiteLLM_ManagedObjectTable to check if the batch job is complete, and if t

 from litellm._uuid import uuid
 from datetime import datetime
-from typing import TYPE_CHECKING, Optional, cast
+from typing import TYPE_CHECKING, Optional

 from litellm._logging import verbose_proxy_logger

@ -35,14 +35,11 @@ class CheckBatchCost:
        - if not, return False
        - if so, return True
        """
-        from litellm_enterprise.proxy.hooks.managed_files import (
-            _PROXY_LiteLLMManagedFiles,
-        )
-
        from litellm.batches.batch_utils import (
            _get_file_content_as_dictionary,
            calculate_batch_cost_and_usage,
        )
+        from litellm.files.main import afile_content
        from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
        from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLogging
        from litellm.proxy.openai_files_endpoints.common_utils import (
@ -102,27 +99,29 @@ class CheckBatchCost:
                continue

            ## RETRIEVE THE BATCH JOB OUTPUT FILE
-            managed_files_obj = cast(
-                Optional[_PROXY_LiteLLMManagedFiles],
-                self.proxy_logging_obj.get_proxy_hook("managed_files"),
-            )
            if (
                response.status == "completed"
                and response.output_file_id is not None
-                and managed_files_obj is not None
            ):
                verbose_proxy_logger.info(
                    f"Batch ID: {batch_id} is complete, tracking cost and usage"
                )
-                # track cost
-                model_file_id_mapping = {
-                    response.output_file_id: {model_id: response.output_file_id}
-                }
-                _file_content = await managed_files_obj.afile_content(
-                    file_id=response.output_file_id,
-                    litellm_parent_otel_span=None,
-                    llm_router=self.llm_router,
-                    model_file_id_mapping=model_file_id_mapping,
+
+                # This background job runs as default_user_id, so going through the HTTP endpoint
+                # would trigger check_managed_file_id_access and get 403. Instead, extract the raw
+                # provider file ID and call afile_content directly with deployment credentials.
+                raw_output_file_id = response.output_file_id
+                decoded = _is_base64_encoded_unified_file_id(raw_output_file_id)
+                if decoded:
+                    try:
+                        raw_output_file_id = decoded.split("llm_output_file_id,")[1].split(";")[0]
+                    except (IndexError, AttributeError):
+                        pass
+
+                credentials = self.llm_router.get_deployment_credentials_with_provider(model_id) or {}
+                _file_content = await afile_content(
+                    file_id=raw_output_file_id,
+                    **credentials,
                )

                file_content_as_dict = _get_file_content_as_dictionary(
@ -143,11 +142,15 @@ class CheckBatchCost:
                    custom_llm_provider=custom_llm_provider,
                )

+                # Pass deployment model_info so custom batch pricing
+                # (input_cost_per_token_batches etc.) is used for cost calc
+                deployment_model_info = deployment_info.model_info.model_dump() if deployment_info.model_info else {}
                batch_cost, batch_usage, batch_models = (
                    await calculate_batch_cost_and_usage(
                        file_content_dictionary=file_content_as_dict,
                        custom_llm_provider=llm_provider,  # type: ignore
                        model_name=model_name,
+                        model_info=deployment_model_info,
                    )
                )
                logging_obj = LiteLLMLogging(
--- a/enterprise/litellm_enterprise/proxy/hooks/managed_files.py
+++ b/enterprise/litellm_enterprise/proxy/hooks/managed_files.py
@ -230,12 +230,14 @@ class _PROXY_LiteLLMManagedFiles(CustomLogger, BaseFileEndpoints):

        if managed_file:
            return managed_file.created_by == user_id
-        return False
+        raise HTTPException(
+            status_code=404,
+            detail=f"File not found: {unified_file_id}",
+        )

    async def can_user_call_unified_object_id(
        self, unified_object_id: str, user_api_key_dict: UserAPIKeyAuth
    ) -> bool:
-        ## check if the user has access to the unified object id
        ## check if the user has access to the unified object id
        user_id = user_api_key_dict.user_id
        managed_object = (
@ -246,7 +248,10 @@ class _PROXY_LiteLLMManagedFiles(CustomLogger, BaseFileEndpoints):

        if managed_object:
            return managed_object.created_by == user_id
-        return True  # don't raise error if managed object is not found
+        raise HTTPException(
+            status_code=404,
+            detail=f"Object not found: {unified_object_id}",
+        )

    async def list_user_batches(
        self,
@ -911,15 +916,22 @@ class _PROXY_LiteLLMManagedFiles(CustomLogger, BaseFileEndpoints):
                        )
                        setattr(response, file_attr, unified_file_id)
                        
-                        # Fetch the actual file object from the provider
+                        # Use llm_router credentials when available. Without credentials,
+                        # Azure and other auth-required providers return 500/401.
                        file_object = None
                        try:
-                            # Use litellm to retrieve the file object from the provider
-                            from litellm import afile_retrieve
-                            file_object = await afile_retrieve(
-                                custom_llm_provider=model_name.split("/")[0] if model_name and "/" in model_name else "openai",
-                                file_id=original_file_id
-                            )
+                            from litellm.proxy.proxy_server import llm_router as _llm_router
+                            if _llm_router is not None and model_id:
+                                _creds = _llm_router.get_deployment_credentials_with_provider(model_id) or {}
+                                file_object = await litellm.afile_retrieve(
+                                    file_id=original_file_id,
+                                    **_creds,
+                                )
+                            else:
+                                file_object = await litellm.afile_retrieve(
+                                    custom_llm_provider=model_name.split("/")[0] if model_name and "/" in model_name else "openai",
+                                    file_id=original_file_id,
+                                )
                            verbose_logger.debug(
                                f"Successfully retrieved file object for {file_attr}={original_file_id}"
                            )
@ -1004,7 +1016,10 @@ class _PROXY_LiteLLMManagedFiles(CustomLogger, BaseFileEndpoints):
            raise Exception(f"LiteLLM Managed File object with id={file_id} not found")
        
        # Case 2: Managed file and the file object exists in the database
+        # The stored file_object has the raw provider ID. Replace with the unified ID
+        # so callers see a consistent ID (matching Case 3 which does response.id = file_id).
        if stored_file_object and stored_file_object.file_object:
+            stored_file_object.file_object.id = file_id
            return stored_file_object.file_object

        # Case 3: Managed file exists in the database but not the file object (for. e.g the batch task might not have run)
--- a/enterprise/pyproject.toml
+++ b/enterprise/pyproject.toml
@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm-enterprise"
-version = "0.1.31"
+version = "0.1.32"
 description = "Package for LiteLLM Enterprise features"
 authors = ["BerriAI"]
 readme = "README.md"
@ -22,7 +22,7 @@ requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"

 [tool.commitizen]
-version = "0.1.31"
+version = "0.1.32"
 version_files = [
    "pyproject.toml:version",
    "../requirements.txt:litellm-enterprise==",
--- a/litellm-proxy-extras/build_and_publish.md
+++ b/litellm-proxy-extras/build_and_publish.md
@ -0,0 +1,127 @@
+# Build & Publish `litellm-proxy-extras`
+
+This runbook covers building and publishing a new version of the `litellm-proxy-extras` PyPI package. For use by litellm engineers only.
+
+## Prerequisites
+
+- All `schema.prisma` files are in sync (see [migration_runbook.md](./migration_runbook.md) Step 0)
+- Migration has been generated and committed
+- You are in the `litellm-proxy-extras/` directory
+
+## Step 1: Bump the Version
+
+### Option A: Automatic Version Bump (Recommended)
+
+Use commitizen to automatically bump the version across all files:
+
+```bash
+cd litellm-proxy-extras
+cz bump --increment patch
+```
+
+This will automatically:
+- Bump the version in `pyproject.toml` (both `[tool.poetry].version` and `[tool.commitizen].version`)
+- Update the version in `../requirements.txt`
+- Update the version in `../pyproject.toml` (root)
+- Create a git commit with the version bump
+
+Then skip to Step 3 (Install Build Dependencies).
+
+### Option B: Manual Version Bump
+
+Update the version in `pyproject.toml`:
+
+```bash
+cd litellm-proxy-extras
+
+# Check current version
+grep 'version' pyproject.toml
+```
+
+Edit `pyproject.toml` and bump the version (both `[tool.poetry].version` and `[tool.commitizen].version`).
+
+#### Step 2: Update Version in Root Package Files (Manual Only)
+
+After bumping the version in `litellm-proxy-extras/pyproject.toml`, you **must** also update the version reference in the root-level files:
+
+| File | Line to update |
+|------|---------------|
+| `requirements.txt` | `litellm-proxy-extras==X.Y.Z` |
+| `pyproject.toml` (root) | `litellm-proxy-extras = {version = "X.Y.Z", optional = true}` |
+
+```bash
+# From the repo root — replace OLD with NEW version
+sed -i '' 's/litellm-proxy-extras==OLD/litellm-proxy-extras==NEW/' requirements.txt
+sed -i '' 's/litellm-proxy-extras = {version = "OLD"/litellm-proxy-extras = {version = "NEW"/' pyproject.toml
+```
+
+> **Do NOT skip this step.** The main `litellm` package pins the extras version — if you don't update these, users will install the old version.
+
+## Step 3: Install Build Dependencies
+
+```bash
+pip install build twine
+```
+
+## Step 4: Clean Old Artifacts
+
+```bash
+rm -rf dist/ build/ *.egg-info
+```
+
+## Step 5: Build the Package
+
+```bash
+python3 -m build
+```
+
+This creates `.tar.gz` and `.whl` files in the `dist/` directory.
+
+Verify the build output:
+
+```bash
+ls -la dist/
+```
+
+## Step 6: Upload to PyPI
+
+```bash
+twine upload dist/*
+```
+
+You will be prompted for your PyPI API token:
+
+```
+Enter your API token: pypi-...
+```
+
+> Use `__token__` as the username and your PyPI API token as the password.
+
+## Quick Reference (Copy-Paste)
+
+```bash
+cd litellm-proxy-extras
+rm -rf dist/ build/ *.egg-info
+python3 -m build
+twine upload dist/*
+```
+
+---
+
+## Do you want to build and publish a new `litellm-proxy-extras` package? (y/n)
+
+If **yes**, run the following commands in order:
+
+```bash
+cd litellm-proxy-extras
+pip install build twine
+rm -rf dist/ build/ *.egg-info
+python3 -m build
+twine upload dist/*
+```
+
+When `twine upload` runs, enter your PyPI credentials:
+- **Username:** `__token__`
+- **Password:** *(paste your PyPI API key)*
+
+If **no**, you're done — no package publish needed.
--- a/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.40-py3-none-any.whl
+++ b/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.40-py3-none-any.whl
--- a/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.40.tar.gz
+++ b/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.40.tar.gz
--- a/litellm-proxy-extras/litellm_proxy_extras/migrations/20260203120000_add_deprecated_verification_token_table/migration.sql
+++ b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260203120000_add_deprecated_verification_token_table/migration.sql
@ -0,0 +1,19 @@
+-- CreateTable
+CREATE TABLE "LiteLLM_DeprecatedVerificationToken" (
+    "id" TEXT NOT NULL,
+    "token" TEXT NOT NULL,
+    "active_token_id" TEXT NOT NULL,
+    "revoke_at" TIMESTAMP(3) NOT NULL,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+
+    CONSTRAINT "LiteLLM_DeprecatedVerificationToken_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateIndex
+CREATE UNIQUE INDEX "LiteLLM_DeprecatedVerificationToken_token_key" ON "LiteLLM_DeprecatedVerificationToken"("token");
+
+-- CreateIndex
+CREATE INDEX "LiteLLM_DeprecatedVerificationToken_token_revoke_at_idx" ON "LiteLLM_DeprecatedVerificationToken"("token", "revoke_at");
+
+-- CreateIndex
+CREATE INDEX "LiteLLM_DeprecatedVerificationToken_revoke_at_idx" ON "LiteLLM_DeprecatedVerificationToken"("revoke_at");
--- a/litellm-proxy-extras/litellm_proxy_extras/migrations/20260214094754_schema_sync/migration.sql
+++ b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260214094754_schema_sync/migration.sql
@ -0,0 +1,3 @@
+-- AlterTable
+ALTER TABLE "LiteLLM_GuardrailsTable" ADD COLUMN     "team_id" TEXT;
+
--- a/litellm-proxy-extras/litellm_proxy_extras/migrations/20260214124140_baseline_diff/migration.sql
+++ b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260214124140_baseline_diff/migration.sql
@ -0,0 +1,2 @@
+-- This is an empty migration.
+
--- a/litellm-proxy-extras/litellm_proxy_extras/migrations/20260214163027_add_pipeline_to_policy_table/migration.sql
+++ b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260214163027_add_pipeline_to_policy_table/migration.sql
@ -0,0 +1,3 @@
+-- AlterTable
+ALTER TABLE "LiteLLM_PolicyTable" ADD COLUMN     "pipeline" JSONB;
+
--- a/litellm-proxy-extras/litellm_proxy_extras/schema.prisma
+++ b/litellm-proxy-extras/litellm_proxy_extras/schema.prisma
@ -325,6 +325,19 @@ model LiteLLM_VerificationToken {
    @@index([budget_reset_at, expires])
 }

+// Deprecated keys during grace period - allows old key to work until revoke_at
+model LiteLLM_DeprecatedVerificationToken {
+    id               String   @id @default(uuid())
+    token            String   // Hashed old key
+    active_token_id  String   // Current token hash in LiteLLM_VerificationToken
+    revoke_at        DateTime // When the old key stops working
+    created_at       DateTime @default(now()) @map("created_at")
+
+    @@unique([token])
+    @@index([token, revoke_at])
+    @@index([revoke_at])
+}
+
 // Audit table for deleted keys - preserves spend and key information for historical tracking
 model LiteLLM_DeletedVerificationToken {
    id                      String   @id @default(uuid())
@ -920,6 +933,7 @@ model LiteLLM_PolicyTable {
  guardrails_add   String[]  @default([])
  guardrails_remove String[] @default([])
  condition        Json?     @default("{}")  // Policy conditions (e.g., model matching)
+  pipeline         Json?     // Optional guardrail pipeline (mode + steps[])
  created_at       DateTime  @default(now())
  created_by       String?
  updated_at       DateTime  @default(now()) @updatedAt
--- a/litellm-proxy-extras/migration_runbook.md
+++ b/litellm-proxy-extras/migration_runbook.md
@ -2,7 +2,35 @@

 This is a runbook for creating and running database migrations for the LiteLLM proxy. For use for litellm engineers only.

-## Quick Start
+## Step 0: Sync All `schema.prisma` Files
+
+Before doing anything else, make sure all `schema.prisma` files in the repo are in sync. There are multiple copies that must match:
+
+| File | Purpose |
+|------|---------|
+| `schema.prisma` (repo root) | Source of truth |
+| `litellm/proxy/schema.prisma` | Used by the proxy server |
+| `litellm-proxy-extras/litellm_proxy_extras/schema.prisma` | Used for migration generation |
+
+**Sync process:**
+
+```bash
+# 1. Diff all schema files against the root source of truth
+diff schema.prisma litellm/proxy/schema.prisma
+diff schema.prisma litellm-proxy-extras/litellm_proxy_extras/schema.prisma
+
+# 2. If there are differences, copy the root schema to all locations
+cp schema.prisma litellm/proxy/schema.prisma
+cp schema.prisma litellm-proxy-extras/litellm_proxy_extras/schema.prisma
+
+# 3. Verify all files are now identical
+diff schema.prisma litellm/proxy/schema.prisma && echo "proxy schema in sync" || echo "MISMATCH"
+diff schema.prisma litellm-proxy-extras/litellm_proxy_extras/schema.prisma && echo "extras schema in sync" || echo "MISMATCH"
+```
+
+> **Do NOT proceed to migration generation until all schema files are identical.**
+
+## Step 1: Quick Start — Generate Migration

 ```bash
 # Install deps (one time)
@ -43,8 +71,13 @@ rm -rf litellm-proxy-extras/litellm_proxy_extras/migrations/[empty_dir]

 ## Rules

- Update `schema.prisma` first
+- Sync all `schema.prisma` files first (Step 0)
+- Update `schema.prisma` at the repo root first, then sync copies
 - Review generated SQL before committing
 - Use descriptive migration names
 - Never edit existing migration files
 - Commit schema + migration together
+
+---
+
+**Done with migration?** See [build_and_publish.md](./build_and_publish.md) to publish a new `litellm-proxy-extras` package.
--- a/litellm-proxy-extras/pyproject.toml
+++ b/litellm-proxy-extras/pyproject.toml
@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm-proxy-extras"
-version = "0.4.37"
+version = "0.4.40"
 description = "Additional files for the LiteLLM Proxy. Reduces the size of the main litellm package."
 authors = ["BerriAI"]
 readme = "README.md"
@ -22,7 +22,7 @@ requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"

 [tool.commitizen]
-version = "0.4.37"
+version = "0.4.40"
 version_files = [
    "pyproject.toml:version",
    "../requirements.txt:litellm-proxy-extras==",
--- a/litellm/_service_logger.py
+++ b/litellm/_service_logger.py
@ -312,10 +312,12 @@ class ServiceLogging(CustomLogger):
                        _duration, type(_duration)
                    )
                )  # invalid _duration value
+            # Batch polling callbacks (check_batch_cost) don't include call_type in kwargs.
+            # Use .get() to avoid KeyError.
            await self.async_service_success_hook(
                service=ServiceTypes.LITELLM,
                duration=_duration,
-                call_type=kwargs["call_type"],
+                call_type=kwargs.get("call_type", "unknown")
            )
        except Exception as e:
            raise e
--- a/litellm/batches/batch_utils.py
+++ b/litellm/batches/batch_utils.py
@ -8,7 +8,7 @@ import litellm
 from litellm._logging import verbose_logger
 from litellm._uuid import uuid
 from litellm.types.llms.openai import Batch
-from litellm.types.utils import CallTypes, ModelResponse, Usage
+from litellm.types.utils import CallTypes, ModelInfo, ModelResponse, Usage
 from litellm.utils import token_counter


@ -16,14 +16,22 @@ async def calculate_batch_cost_and_usage(
    file_content_dictionary: List[dict],
    custom_llm_provider: Literal["openai", "azure", "vertex_ai", "hosted_vllm", "anthropic"],
    model_name: Optional[str] = None,
+    model_info: Optional[ModelInfo] = None,
 ) -> Tuple[float, Usage, List[str]]:
    """
-    Calculate the cost and usage of a batch
+    Calculate the cost and usage of a batch.
+
+    Args:
+        model_info: Optional deployment-level model info with custom batch
+            pricing. Threaded through to batch_cost_calculator so that
+            deployment-specific pricing (e.g. input_cost_per_token_batches)
+            is used instead of the global cost map.
    """
    batch_cost = _batch_cost_calculator(
        custom_llm_provider=custom_llm_provider,
        file_content_dictionary=file_content_dictionary,
        model_name=model_name,
+        model_info=model_info,
    )
    batch_usage = _get_batch_job_total_usage_from_file_content(
        file_content_dictionary=file_content_dictionary,
@ -94,6 +102,7 @@ def _batch_cost_calculator(
    file_content_dictionary: List[dict],
    custom_llm_provider: Literal["openai", "azure", "vertex_ai", "hosted_vllm", "anthropic"] = "openai",
    model_name: Optional[str] = None,
+    model_info: Optional[ModelInfo] = None,
 ) -> float:
    """
    Calculate the cost of a batch based on the output file id
@ -108,6 +117,7 @@ def _batch_cost_calculator(
    total_cost = _get_batch_job_cost_from_file_content(
        file_content_dictionary=file_content_dictionary,
        custom_llm_provider=custom_llm_provider,
+        model_info=model_info,
    )
    verbose_logger.debug("total_cost=%s", total_cost)
    return total_cost
@ -290,10 +300,13 @@ def _get_file_content_as_dictionary(file_content: bytes) -> List[dict]:
 def _get_batch_job_cost_from_file_content(
    file_content_dictionary: List[dict],
    custom_llm_provider: Literal["openai", "azure", "vertex_ai", "hosted_vllm", "anthropic"] = "openai",
+    model_info: Optional[ModelInfo] = None,
 ) -> float:
    """
    Get the cost of a batch job from the file content
    """
+    from litellm.cost_calculator import batch_cost_calculator
+
    try:
        total_cost: float = 0.0
        # parse the file content as json
@ -303,11 +316,22 @@ def _get_batch_job_cost_from_file_content(
        for _item in file_content_dictionary:
            if _batch_response_was_successful(_item):
                _response_body = _get_response_from_batch_job_output_file(_item)
-                total_cost += litellm.completion_cost(
-                    completion_response=_response_body,
-                    custom_llm_provider=custom_llm_provider,
-                    call_type=CallTypes.aretrieve_batch.value,
-                )
+                if model_info is not None:
+                    usage = _get_batch_job_usage_from_response_body(_response_body)
+                    model = _response_body.get("model", "")
+                    prompt_cost, completion_cost = batch_cost_calculator(
+                        usage=usage,
+                        model=model,
+                        custom_llm_provider=custom_llm_provider,
+                        model_info=model_info,
+                    )
+                    total_cost += prompt_cost + completion_cost
+                else:
+                    total_cost += litellm.completion_cost(
+                        completion_response=_response_body,
+                        custom_llm_provider=custom_llm_provider,
+                        call_type=CallTypes.aretrieve_batch.value,
+                    )
                verbose_logger.debug("total_cost=%s", total_cost)
        return total_cost
    except Exception as e:
--- a/litellm/constants.py
+++ b/litellm/constants.py
@ -106,9 +106,7 @@ MCP_OAUTH2_TOKEN_CACHE_DEFAULT_TTL = int(
 # npm/npx needs a writable cache dir; in containers the default (~/.npm)
 # may not exist or be read-only. /tmp is always writable.
 MCP_NPM_CACHE_DIR = os.getenv("MCP_NPM_CACHE_DIR", "/tmp/.npm_mcp_cache")
-MCP_OAUTH2_TOKEN_CACHE_MIN_TTL = int(
-    os.getenv("MCP_OAUTH2_TOKEN_CACHE_MIN_TTL", "10")
-)
+MCP_OAUTH2_TOKEN_CACHE_MIN_TTL = int(os.getenv("MCP_OAUTH2_TOKEN_CACHE_MIN_TTL", "10"))

 LITELLM_UI_ALLOW_HEADERS = [
    "x-litellm-semantic-filter",
@ -131,7 +129,7 @@ DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET_GEMINI_2_5_FLASH_LITE = int(
 # Maximum number of callbacks that can be registered
 # This prevents callbacks from exponentially growing and consuming CPU resources
 # Override with LITELLM_MAX_CALLBACKS env var for large deployments (e.g., many teams with guardrails)
-MAX_CALLBACKS = get_env_int("LITELLM_MAX_CALLBACKS", 30)
+MAX_CALLBACKS = get_env_int("LITELLM_MAX_CALLBACKS", 100)

 # Generic fallback for unknown models
 DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET = int(
@ -167,15 +165,19 @@ _DEFAULT_TTL_FOR_HTTPX_CLIENTS = 3600  # 1 hour, re-use the same httpx client fo
 # Aiohttp connection pooling - prevents memory leaks from unbounded connection growth
 # Set to 0 for unlimited (not recommended for production)
 AIOHTTP_CONNECTOR_LIMIT = int(os.getenv("AIOHTTP_CONNECTOR_LIMIT", 300))
-AIOHTTP_CONNECTOR_LIMIT_PER_HOST = int(os.getenv("AIOHTTP_CONNECTOR_LIMIT_PER_HOST", 50))
+AIOHTTP_CONNECTOR_LIMIT_PER_HOST = int(
+    os.getenv("AIOHTTP_CONNECTOR_LIMIT_PER_HOST", 50)
+)
 AIOHTTP_KEEPALIVE_TIMEOUT = int(os.getenv("AIOHTTP_KEEPALIVE_TIMEOUT", 120))
 AIOHTTP_TTL_DNS_CACHE = int(os.getenv("AIOHTTP_TTL_DNS_CACHE", 300))
 # enable_cleanup_closed is only needed for Python versions with the SSL leak bug
 # Fixed in Python 3.12.7+ and 3.13.1+ (see https://github.com/python/cpython/pull/118960)
 # Reference: https://github.com/aio-libs/aiohttp/blob/master/aiohttp/connector.py#L74-L78
-AIOHTTP_NEEDS_CLEANUP_CLOSED = (
-    (3, 13, 0) <= sys.version_info < (3, 13, 1) or sys.version_info < (3, 12, 7)
-)
+AIOHTTP_NEEDS_CLEANUP_CLOSED = (3, 13, 0) <= sys.version_info < (
+    3,
+    13,
+    1,
+) or sys.version_info < (3, 12, 7)

 # WebSocket constants
 # Default to None (unlimited) to match OpenAI's official agents SDK behavior
@ -213,15 +215,15 @@ REDIS_UPDATE_BUFFER_KEY = "litellm_spend_update_buffer"
 REDIS_DAILY_SPEND_UPDATE_BUFFER_KEY = "litellm_daily_spend_update_buffer"
 REDIS_DAILY_TEAM_SPEND_UPDATE_BUFFER_KEY = "litellm_daily_team_spend_update_buffer"
 REDIS_DAILY_ORG_SPEND_UPDATE_BUFFER_KEY = "litellm_daily_org_spend_update_buffer"
-REDIS_DAILY_END_USER_SPEND_UPDATE_BUFFER_KEY = "litellm_daily_end_user_spend_update_buffer"
+REDIS_DAILY_END_USER_SPEND_UPDATE_BUFFER_KEY = (
+    "litellm_daily_end_user_spend_update_buffer"
+)
 REDIS_DAILY_AGENT_SPEND_UPDATE_BUFFER_KEY = "litellm_daily_agent_spend_update_buffer"
 REDIS_DAILY_TAG_SPEND_UPDATE_BUFFER_KEY = "litellm_daily_tag_spend_update_buffer"
 MAX_REDIS_BUFFER_DEQUEUE_COUNT = int(os.getenv("MAX_REDIS_BUFFER_DEQUEUE_COUNT", 100))
 MAX_SIZE_IN_MEMORY_QUEUE = int(os.getenv("MAX_SIZE_IN_MEMORY_QUEUE", 2000))
 # Bounds asyncio.Queue() instances (log queues, spend update queues, etc.) to prevent unbounded memory growth
-LITELLM_ASYNCIO_QUEUE_MAXSIZE = int(
-    os.getenv("LITELLM_ASYNCIO_QUEUE_MAXSIZE", 1000)
-)
+LITELLM_ASYNCIO_QUEUE_MAXSIZE = int(os.getenv("LITELLM_ASYNCIO_QUEUE_MAXSIZE", 1000))
 MAX_IN_MEMORY_QUEUE_FLUSH_COUNT = int(
    os.getenv("MAX_IN_MEMORY_QUEUE_FLUSH_COUNT", 1000)
 )
@ -317,6 +319,9 @@ NON_LLM_CONNECTION_TIMEOUT = int(
 MAX_EXCEPTION_MESSAGE_LENGTH = int(os.getenv("MAX_EXCEPTION_MESSAGE_LENGTH", 2000))
 MAX_STRING_LENGTH_PROMPT_IN_DB = int(os.getenv("MAX_STRING_LENGTH_PROMPT_IN_DB", 2048))
 BEDROCK_MAX_POLICY_SIZE = int(os.getenv("BEDROCK_MAX_POLICY_SIZE", 75))
+BEDROCK_MIN_THINKING_BUDGET_TOKENS = int(
+    os.getenv("BEDROCK_MIN_THINKING_BUDGET_TOKENS", 1024)
+)
 REPLICATE_POLLING_DELAY_SECONDS = float(
    os.getenv("REPLICATE_POLLING_DELAY_SECONDS", 0.5)
 )
@ -343,7 +348,9 @@ MAX_SIZE_PER_ITEM_IN_MEMORY_CACHE_IN_KB = int(
 DEFAULT_MAX_TOKENS_FOR_TRITON = int(os.getenv("DEFAULT_MAX_TOKENS_FOR_TRITON", 2000))
 #### Networking settings ####
 request_timeout: float = float(os.getenv("REQUEST_TIMEOUT", 6000))  # time in seconds
-DEFAULT_A2A_AGENT_TIMEOUT: float = float(os.getenv("DEFAULT_A2A_AGENT_TIMEOUT", 6000))  # 10 minutes
+DEFAULT_A2A_AGENT_TIMEOUT: float = float(
+    os.getenv("DEFAULT_A2A_AGENT_TIMEOUT", 6000)
+)  # 10 minutes
 # Patterns that indicate a localhost/internal URL in A2A agent cards that should be
 # replaced with the original base_url. This is a common misconfiguration where
 # developers deploy agents with development URLs in their agent cards.
@ -395,8 +402,12 @@ DD_TRACER_STREAMING_CHUNK_YIELD_RESOURCE = os.getenv(
    "DD_TRACER_STREAMING_CHUNK_YIELD_RESOURCE", "streaming.chunk.yield"
 )

-EMAIL_BUDGET_ALERT_TTL = int(os.getenv("EMAIL_BUDGET_ALERT_TTL", 24 * 60 * 60))  # 24 hours in seconds
-EMAIL_BUDGET_ALERT_MAX_SPEND_ALERT_PERCENTAGE = float(os.getenv("EMAIL_BUDGET_ALERT_MAX_SPEND_ALERT_PERCENTAGE", 0.8))  # 80% of max budget
+EMAIL_BUDGET_ALERT_TTL = int(
+    os.getenv("EMAIL_BUDGET_ALERT_TTL", 24 * 60 * 60)
+)  # 24 hours in seconds
+EMAIL_BUDGET_ALERT_MAX_SPEND_ALERT_PERCENTAGE = float(
+    os.getenv("EMAIL_BUDGET_ALERT_MAX_SPEND_ALERT_PERCENTAGE", 0.8)
+)  # 80% of max budget
 ############### LLM Provider Constants ###############
 ### ANTHROPIC CONSTANTS ###
 ANTHROPIC_TOKEN_COUNTING_BETA_VERSION = os.getenv(
@ -1150,7 +1161,17 @@ known_tokenizer_config = {
 }


-OPENAI_FINISH_REASONS = ["stop", "length", "function_call", "content_filter", "null", "finish_reason_unspecified", "malformed_function_call", "guardrail_intervened", "eos"]
+OPENAI_FINISH_REASONS = [
+    "stop",
+    "length",
+    "function_call",
+    "content_filter",
+    "null",
+    "finish_reason_unspecified",
+    "malformed_function_call",
+    "guardrail_intervened",
+    "eos",
+]
 HUMANLOOP_PROMPT_CACHE_TTL_SECONDS = int(
    os.getenv("HUMANLOOP_PROMPT_CACHE_TTL_SECONDS", 60)
 )  # 1 minute
@ -1240,6 +1261,9 @@ LITELLM_KEY_ROTATION_ENABLED = os.getenv("LITELLM_KEY_ROTATION_ENABLED", "false"
 LITELLM_KEY_ROTATION_CHECK_INTERVAL_SECONDS = int(
    os.getenv("LITELLM_KEY_ROTATION_CHECK_INTERVAL_SECONDS", 86400)
 )  # 24 hours default
+LITELLM_KEY_ROTATION_GRACE_PERIOD: str = os.getenv(
+    "LITELLM_KEY_ROTATION_GRACE_PERIOD", ""
+)  # Duration to keep old key valid after rotation (e.g. "24h", "2d"); empty = immediate revoke (default)
 UI_SESSION_TOKEN_TEAM_ID = "litellm-dashboard"
 LITELLM_PROXY_ADMIN_NAME = "default_user_id"

@ -1250,8 +1274,8 @@ CLI_SSO_SESSION_CACHE_KEY_PREFIX = "cli_sso_session"
 CLI_JWT_TOKEN_NAME = "cli-jwt-token"
 # Support both CLI_JWT_EXPIRATION_HOURS and LITELLM_CLI_JWT_EXPIRATION_HOURS for backwards compatibility
 CLI_JWT_EXPIRATION_HOURS = int(
-    os.getenv("CLI_JWT_EXPIRATION_HOURS") 
-    or os.getenv("LITELLM_CLI_JWT_EXPIRATION_HOURS") 
+    os.getenv("CLI_JWT_EXPIRATION_HOURS")
+    or os.getenv("LITELLM_CLI_JWT_EXPIRATION_HOURS")
    or 24
 )

@ -1342,6 +1366,9 @@ SPECIAL_LITELLM_AUTH_TOKEN = ["ui-token"]
 DEFAULT_MANAGEMENT_OBJECT_IN_MEMORY_CACHE_TTL = int(
    os.getenv("DEFAULT_MANAGEMENT_OBJECT_IN_MEMORY_CACHE_TTL", 60)
 )
+DEFAULT_ACCESS_GROUP_CACHE_TTL = int(
+    os.getenv("DEFAULT_ACCESS_GROUP_CACHE_TTL", 600)
+)

 # Sentry Scrubbing Configuration
 SENTRY_DENYLIST = [
@ -1432,9 +1459,7 @@ MICROSOFT_USER_EMAIL_ATTRIBUTE = str(
 MICROSOFT_USER_DISPLAY_NAME_ATTRIBUTE = str(
    os.getenv("MICROSOFT_USER_DISPLAY_NAME_ATTRIBUTE", "displayName")
 )
-MICROSOFT_USER_ID_ATTRIBUTE = str(
-    os.getenv("MICROSOFT_USER_ID_ATTRIBUTE", "id")
-)
+MICROSOFT_USER_ID_ATTRIBUTE = str(os.getenv("MICROSOFT_USER_ID_ATTRIBUTE", "id"))
 MICROSOFT_USER_FIRST_NAME_ATTRIBUTE = str(
    os.getenv("MICROSOFT_USER_FIRST_NAME_ATTRIBUTE", "givenName")
 )
--- a/litellm/cost_calculator.py
+++ b/litellm/cost_calculator.py
@ -74,6 +74,7 @@ from litellm.llms.vertex_ai.cost_calculator import (
 from litellm.llms.vertex_ai.cost_calculator import cost_router as google_cost_router
 from litellm.llms.xai.cost_calculator import cost_per_token as xai_cost_per_token
 from litellm.responses.utils import ResponseAPILoggingUtils
+from litellm.types.agents import LiteLLMSendMessageResponse
 from litellm.types.llms.openai import (
    HttpxBinaryResponseContent,
    ImageGenerationRequestQuality,
@ -150,32 +151,33 @@ def _get_additional_costs(
 ) -> Optional[dict]:
    """
    Calculate additional costs beyond standard token costs.
-    
+
    This function delegates to provider-specific config classes to calculate
    any additional costs like routing fees, infrastructure costs, etc.
-    
+
    Args:
        model: The model name
        custom_llm_provider: The provider name (optional)
        prompt_tokens: Number of prompt tokens
        completion_tokens: Number of completion tokens
-        
+
    Returns:
        Optional dictionary with cost names and amounts, or None if no additional costs
    """
    if not custom_llm_provider:
        return None
-        
+
    try:
        config_class = None
        if custom_llm_provider == "azure_ai":
            from litellm.llms.azure_ai.common_utils import AzureFoundryModelInfo
+
            config_class = AzureFoundryModelInfo.get_azure_ai_config_for_model(model)
        # Add more providers here as needed
        # elif custom_llm_provider == "other_provider":
        #     config_class = get_other_provider_config(model)
-        
-        if config_class and hasattr(config_class, 'calculate_additional_costs'):
+
+        if config_class and hasattr(config_class, "calculate_additional_costs"):
            return config_class.calculate_additional_costs(
                model=model,
                prompt_tokens=prompt_tokens,
@ -183,7 +185,7 @@ def _get_additional_costs(
            )
    except Exception as e:
        verbose_logger.debug(f"Error calculating additional costs: {e}")
-    
+
    return None


@ -748,6 +750,8 @@ def _infer_call_type(
        return "image_generation"
    elif isinstance(completion_response, TextCompletionResponse):
        return "text_completion"
+    elif isinstance(completion_response, LiteLLMSendMessageResponse):
+        return "send_message"

    return call_type

@ -1037,9 +1041,9 @@ def completion_cost(  # noqa: PLR0915
                    or isinstance(completion_response, dict)
                ):  # tts returns a custom class
                    if isinstance(completion_response, dict):
-                        usage_obj: Optional[
-                            Union[dict, Usage]
-                        ] = completion_response.get("usage", {})
+                        usage_obj: Optional[Union[dict, Usage]] = (
+                            completion_response.get("usage", {})
+                        )
                    else:
                        usage_obj = getattr(completion_response, "usage", {})
                    if isinstance(usage_obj, BaseModel) and not _is_known_usage_objects(
@ -1393,7 +1397,7 @@ def completion_cost(  # noqa: PLR0915
                    service_tier=service_tier,
                    response=completion_response,
                )
-                
+
                # Get additional costs from provider (e.g., routing fees, infrastructure costs)
                additional_costs = _get_additional_costs(
                    model=model,
@ -1401,7 +1405,7 @@ def completion_cost(  # noqa: PLR0915
                    prompt_tokens=prompt_tokens,
                    completion_tokens=completion_tokens,
                )
-                
+
                _final_cost = (
                    prompt_tokens_cost_usd_dollar + completion_tokens_cost_usd_dollar
                )
@ -1892,9 +1896,16 @@ def batch_cost_calculator(
    usage: Usage,
    model: str,
    custom_llm_provider: Optional[str] = None,
+    model_info: Optional[ModelInfo] = None,
 ) -> Tuple[float, float]:
    """
-    Calculate the cost of a batch job
+    Calculate the cost of a batch job.
+
+    Args:
+        model_info: Optional deployment-level model info containing custom
+            batch pricing (e.g. input_cost_per_token_batches). When provided,
+            skips the global litellm.get_model_info() lookup so that
+            deployment-specific pricing is used.
    """

    _, custom_llm_provider, _, _ = litellm.get_llm_provider(
@ -1907,12 +1918,13 @@ def batch_cost_calculator(
        custom_llm_provider,
    )

-    try:
-        model_info: Optional[ModelInfo] = litellm.get_model_info(
-            model=model, custom_llm_provider=custom_llm_provider
-        )
-    except Exception:
-        model_info = None
+    if model_info is None:
+        try:
+            model_info = litellm.get_model_info(
+                model=model, custom_llm_provider=custom_llm_provider
+            )
+        except Exception:
+            model_info = None

    if not model_info:
        return 0.0, 0.0
--- a/litellm/integrations/langfuse/langfuse_otel.py
+++ b/litellm/integrations/langfuse/langfuse_otel.py
@ -1,6 +1,7 @@
 import base64
 import json  # <--- NEW
 import os
+from datetime import datetime
 from typing import TYPE_CHECKING, Any, Optional, Union

 from litellm._logging import verbose_logger
@ -392,6 +393,22 @@ class LangfuseOtelLogger(OpenTelemetry):

        return dynamic_headers

+    def create_litellm_proxy_request_started_span(
+        self,
+        start_time: datetime,
+        headers: dict,
+    ) -> Optional[Span]:
+        """
+        Override to prevent creating empty proxy request spans.
+
+        Langfuse should only receive spans for actual LLM calls, not for
+        internal proxy operations (auth, postgres, proxy_pre_call, etc.).
+
+        By returning None, we prevent the parent span from being created,
+        which in turn prevents empty traces from being sent to Langfuse.
+        """
+        return None
+
    async def async_service_success_hook(self, *args, **kwargs):
        """
        Langfuse should not receive service success logs.
--- a/litellm/integrations/opentelemetry.py
+++ b/litellm/integrations/opentelemetry.py
@ -1051,23 +1051,15 @@ class OpenTelemetry(CustomLogger):
        # See: https://github.com/open-telemetry/opentelemetry-python/pull/4676
        # TODO: Refactor to use the proper OTEL Logs API instead of directly creating SDK LogRecords

-        from opentelemetry._logs import (
-            SeverityNumber,
-            get_logger,
-        )
-
-        # MyPy evaluates both branches of try/except imports and can fail when
-        # newer OTEL stubs remove/relocate symbols. Gate the typing import so
-        # only the canonical location is type-checked.
-        if TYPE_CHECKING:
-            from opentelemetry.sdk._logs._internal import LogRecord as SdkLogRecord
-        else:
-            try:
-                from opentelemetry.sdk._logs import (
-                    LogRecord as SdkLogRecord,  # type: ignore[attr-defined]
-                )
-            except ImportError:
-                from opentelemetry.sdk._logs._internal import LogRecord as SdkLogRecord
+        from opentelemetry._logs import SeverityNumber, get_logger
+        try:
+            from opentelemetry.sdk._logs import (  # type: ignore[attr-defined]  # OTEL < 1.39.0
+                LogRecord as SdkLogRecord,
+            )
+        except ImportError:
+            from opentelemetry.sdk._logs._internal import (
+                LogRecord as SdkLogRecord,  # type: ignore[attr-defined]  # OTEL >= 1.39.0
+            )

        otel_logger = get_logger(LITELLM_LOGGER_NAME)

--- a/litellm/integrations/s3_v2.py
+++ b/litellm/integrations/s3_v2.py
@ -51,6 +51,7 @@ class S3Logger(CustomBatchLogger, BaseAWSLLM):
        s3_use_team_prefix: bool = False,
        s3_strip_base64_files: bool = False,
        s3_use_key_prefix: bool = False,
+        s3_use_virtual_hosted_style: bool = False,
        **kwargs,
    ):
        try:
@ -78,7 +79,8 @@ class S3Logger(CustomBatchLogger, BaseAWSLLM):
                s3_path=s3_path,
                s3_use_team_prefix=s3_use_team_prefix,
                s3_strip_base64_files=s3_strip_base64_files,
-                s3_use_key_prefix=s3_use_key_prefix
+                s3_use_key_prefix=s3_use_key_prefix,
+                s3_use_virtual_hosted_style=s3_use_virtual_hosted_style
            )
            verbose_logger.debug(f"s3 logger using endpoint url {s3_endpoint_url}")

@ -135,6 +137,7 @@ class S3Logger(CustomBatchLogger, BaseAWSLLM):
        s3_use_team_prefix: bool = False,
        s3_strip_base64_files: bool = False,
        s3_use_key_prefix: bool = False,
+        s3_use_virtual_hosted_style: bool = False,
    ):
        """
        Initialize the s3 params for this logging callback
@ -217,6 +220,11 @@ class S3Logger(CustomBatchLogger, BaseAWSLLM):
            or s3_strip_base64_files
        )

+        self.s3_use_virtual_hosted_style = (
+            bool(litellm.s3_callback_params.get("s3_use_virtual_hosted_style", False))
+            or s3_use_virtual_hosted_style
+        )
+
        return

    async def async_log_success_event(self, kwargs, response_obj, start_time, end_time):
@ -247,8 +255,14 @@ class S3Logger(CustomBatchLogger, BaseAWSLLM):
                standard_logging_payload=kwargs.get("standard_logging_object", None),
            )

+            # afile_delete and other non-model call types never produce a standard_logging_object,
+            # so s3_batch_logging_element is None. Skip gracefully instead of raising ValueError.
            if s3_batch_logging_element is None:
-                raise ValueError("s3_batch_logging_element is None")
+                verbose_logger.debug(
+                    "s3 Logging - skipping event, no standard_logging_object for call_type=%s",
+                    kwargs.get("call_type", "unknown"),
+                )
+                return

            verbose_logger.debug(
                "\ns3 Logger - Logging payload = %s", s3_batch_logging_element
@ -302,13 +316,20 @@ class S3Logger(CustomBatchLogger, BaseAWSLLM):
            url = f"https://{self.s3_bucket_name}.s3.{self.s3_region_name}.amazonaws.com/{batch_logging_element.s3_object_key}"

            if self.s3_endpoint_url and self.s3_bucket_name:
-                url = (
-                    self.s3_endpoint_url
-                    + "/"
-                    + self.s3_bucket_name
-                    + "/"
-                    + batch_logging_element.s3_object_key
-                )
+                if self.s3_use_virtual_hosted_style:
+                    # Virtual-hosted-style: bucket.endpoint/key
+                    endpoint_host = self.s3_endpoint_url.replace("https://", "").replace("http://", "")
+                    protocol = "https://" if self.s3_endpoint_url.startswith("https://") else "http://"
+                    url = f"{protocol}{self.s3_bucket_name}.{endpoint_host}/{batch_logging_element.s3_object_key}"
+                else:
+                    # Path-style: endpoint/bucket/key
+                    url = (
+                        self.s3_endpoint_url
+                        + "/"
+                        + self.s3_bucket_name
+                        + "/"
+                        + batch_logging_element.s3_object_key
+                    )

            # Convert JSON to string
            json_string = safe_dumps(batch_logging_element.payload)
@ -456,13 +477,20 @@ class S3Logger(CustomBatchLogger, BaseAWSLLM):
            url = f"https://{self.s3_bucket_name}.s3.{self.s3_region_name}.amazonaws.com/{batch_logging_element.s3_object_key}"

            if self.s3_endpoint_url and self.s3_bucket_name:
-                url = (
-                    self.s3_endpoint_url
-                    + "/"
-                    + self.s3_bucket_name
-                    + "/"
-                    + batch_logging_element.s3_object_key
-                )
+                if self.s3_use_virtual_hosted_style:
+                    # Virtual-hosted-style: bucket.endpoint/key
+                    endpoint_host = self.s3_endpoint_url.replace("https://", "").replace("http://", "")
+                    protocol = "https://" if self.s3_endpoint_url.startswith("https://") else "http://"
+                    url = f"{protocol}{self.s3_bucket_name}.{endpoint_host}/{batch_logging_element.s3_object_key}"
+                else:
+                    # Path-style: endpoint/bucket/key
+                    url = (
+                        self.s3_endpoint_url
+                        + "/"
+                        + self.s3_bucket_name
+                        + "/"
+                        + batch_logging_element.s3_object_key
+                    )

            # Convert JSON to string
            json_string = safe_dumps(batch_logging_element.payload)
@ -550,13 +578,20 @@ class S3Logger(CustomBatchLogger, BaseAWSLLM):
            url = f"https://{self.s3_bucket_name}.s3.{self.s3_region_name}.amazonaws.com/{s3_object_key}"

            if self.s3_endpoint_url and self.s3_bucket_name:
-                url = (
-                    self.s3_endpoint_url
-                    + "/"
-                    + self.s3_bucket_name
-                    + "/"
-                    + s3_object_key
-                )
+                if self.s3_use_virtual_hosted_style:
+                    # Virtual-hosted-style: bucket.endpoint/key
+                    endpoint_host = self.s3_endpoint_url.replace("https://", "").replace("http://", "")
+                    protocol = "https://" if self.s3_endpoint_url.startswith("https://") else "http://"
+                    url = f"{protocol}{self.s3_bucket_name}.{endpoint_host}/{s3_object_key}"
+                else:
+                    # Path-style: endpoint/bucket/key
+                    url = (
+                        self.s3_endpoint_url
+                        + "/"
+                        + self.s3_bucket_name
+                        + "/"
+                        + s3_object_key
+                    )

            # Prepare the request for GET operation
            # For GET requests, we need x-amz-content-sha256 with hash of empty string
@ -618,4 +653,4 @@ class S3Logger(CustomBatchLogger, BaseAWSLLM):
            verbose_logger.exception(
                f"Error retrieving object {object_key} from cold storage: {str(e)}"
            )
-            return None
+            return None
--- a/litellm/litellm_core_utils/api_route_to_call_types.py
+++ b/litellm/litellm_core_utils/api_route_to_call_types.py
@ -3,6 +3,9 @@ Dictionary mapping API routes to their corresponding CallTypes in LiteLLM.

 This dictionary maps each API endpoint to the CallTypes that can be used for that route.
 Each route can have both async (prefixed with 'a') and sync call types.
+
+Route patterns may contain placeholders like {agent_id}, {model}, {batch_id}; these
+match a single path segment when resolving call types for a concrete path.
 """

 from typing import List, Optional
@ -10,17 +13,43 @@ from typing import List, Optional
 from litellm.types.utils import API_ROUTE_TO_CALL_TYPES, CallTypes


+def _route_matches_pattern(route: str, pattern: str) -> bool:
+    """
+    Return True if the concrete route matches the pattern.
+    Pattern segments like {param} match any single path segment.
+    """
+    route_parts = route.strip("/").split("/")
+    pattern_parts = pattern.strip("/").split("/")
+    if len(route_parts) != len(pattern_parts):
+        return False
+    for r, p in zip(route_parts, pattern_parts):
+        if p.startswith("{") and p.endswith("}"):
+            continue
+        if r != p:
+            return False
+    return True
+
+
 def get_call_types_for_route(route: str) -> Optional[List[CallTypes]]:
    """
    Get the list of CallTypes for a given API route.

+    Supports both exact keys and dynamic patterns (e.g. /a2a/my-agent/message/send
+    matches /a2a/{agent_id}/message/send).
+
    Args:
-        route: API route path (e.g., "/chat/completions")
+        route: API route path (e.g., "/chat/completions" or "/a2a/my-pydantic-agent/message/send")

    Returns:
        List of CallTypes for that route, or None if route not found
    """
-    return API_ROUTE_TO_CALL_TYPES.get(route, None)
+    exact = API_ROUTE_TO_CALL_TYPES.get(route, None)
+    if exact is not None:
+        return exact
+    for pattern, call_types in API_ROUTE_TO_CALL_TYPES.items():
+        if _route_matches_pattern(route, pattern):
+            return call_types
+    return None


 def get_routes_for_call_type(call_type: CallTypes) -> list:
--- a/litellm/llms/a2a/chat/guardrail_translation/handler.py
+++ b/litellm/llms/a2a/chat/guardrail_translation/handler.py
@ -10,6 +10,7 @@ A2A Protocol Format:
 - Output: JSON-RPC 2.0 with result containing message/artifact parts
 """

+import json
 from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union

 from litellm._logging import verbose_proxy_logger
@ -206,6 +207,118 @@ class A2AGuardrailHandler(BaseTranslation):
            response["result"] = result
            return response

+    async def process_output_streaming_response(
+        self,
+        responses_so_far: List[Any],
+        guardrail_to_apply: "CustomGuardrail",
+        litellm_logging_obj: Optional["LiteLLMLoggingObj"] = None,
+        user_api_key_dict: Optional["UserAPIKeyAuth"] = None,
+    ) -> List[Any]:
+        """
+        Process A2A streaming output by applying guardrails to accumulated text.
+
+        responses_so_far can be a list of JSON-RPC 2.0 objects (dict or NDJSON str), e.g.:
+        - task with history, status-update, artifact-update (with result.artifact.parts),
+        - then status-update (final). Text is extracted from result.artifact.parts,
+        result.message.parts, result.parts, etc., concatenated in order, guardrailed once,
+        then the combined guardrailed text is written into the first chunk that had text
+        and all other text parts in other chunks are cleared (in-place).
+        """
+        from litellm.llms.a2a.common_utils import extract_text_from_a2a_response
+
+        # Parse each item; keep alignment with responses_so_far (None where unparseable)
+        parsed: List[Optional[Dict[str, Any]]] = [None] * len(responses_so_far)
+        for i, item in enumerate(responses_so_far):
+            if isinstance(item, dict):
+                obj = item
+            elif isinstance(item, str):
+                try:
+                    obj = json.loads(item.strip())
+                except (json.JSONDecodeError, TypeError):
+                    continue
+            else:
+                continue
+            if isinstance(obj.get("result"), dict):
+                parsed[i] = obj
+
+        valid_parsed = [(i, obj) for i, obj in enumerate(parsed) if obj is not None]
+        if not valid_parsed:
+            return responses_so_far
+
+        # Collect text from each chunk in order (by original index in responses_so_far)
+        text_parts: List[str] = []
+        chunk_indices_with_text: List[int] = []  # indices into valid_parsed
+        for idx, (orig_i, obj) in enumerate(valid_parsed):
+            t = extract_text_from_a2a_response(obj)
+            if t:
+                text_parts.append(t)
+                chunk_indices_with_text.append(orig_i)
+
+        combined_text = "".join(text_parts)
+        if not combined_text:
+            return responses_so_far
+
+        request_data: dict = {"responses_so_far": responses_so_far}
+        user_metadata = self.transform_user_api_key_dict_to_metadata(user_api_key_dict)
+        if user_metadata:
+            request_data["litellm_metadata"] = user_metadata
+
+        inputs = GenericGuardrailAPIInputs(texts=[combined_text])
+        guardrailed_inputs = await guardrail_to_apply.apply_guardrail(
+            inputs=inputs,
+            request_data=request_data,
+            input_type="response",
+            logging_obj=litellm_logging_obj,
+        )
+        guardrailed_texts = guardrailed_inputs.get("texts", [])
+        if not guardrailed_texts:
+            return responses_so_far
+        guardrailed_text = guardrailed_texts[0]
+
+        # Find first chunk (by original index) that has text; put full guardrailed text there and clear rest
+        first_chunk_with_text: Optional[int] = (
+            chunk_indices_with_text[0] if chunk_indices_with_text else None
+        )
+
+        for orig_i, obj in valid_parsed:
+            result = obj.get("result", {})
+            if not isinstance(result, dict):
+                continue
+            texts_in_chunk: List[str] = []
+            mappings: List[Tuple[Tuple[str, ...], int]] = []
+            self._extract_texts_from_result(
+                result=result,
+                texts_to_check=texts_in_chunk,
+                task_mappings=mappings,
+            )
+            if not mappings:
+                continue
+            if orig_i == first_chunk_with_text:
+                # Put full guardrailed text in first text part; clear others
+                for task_idx, (path, part_idx) in enumerate(mappings):
+                    text = guardrailed_text if task_idx == 0 else ""
+                    self._apply_text_to_path(
+                        result=result,
+                        path=path,
+                        part_idx=part_idx,
+                        text=text,
+                    )
+            else:
+                for path, part_idx in mappings:
+                    self._apply_text_to_path(
+                        result=result,
+                        path=path,
+                        part_idx=part_idx,
+                        text="",
+                    )
+
+        # Write back to responses_so_far where we had NDJSON strings
+        for i, item in enumerate(responses_so_far):
+            if isinstance(item, str) and parsed[i] is not None:
+                responses_so_far[i] = json.dumps(parsed[i]) + "\n"
+
+        return responses_so_far
+
    def _extract_texts_from_result(
        self,
        result: Dict[str, Any],
--- a/litellm/llms/anthropic/chat/transformation.py
+++ b/litellm/llms/anthropic/chat/transformation.py
@ -1282,9 +1282,13 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
            output_config = optional_params.get("output_config")
            if output_config and isinstance(output_config, dict):
                effort = output_config.get("effort")
-                if effort and effort not in ["high", "medium", "low"]:
+                if effort and effort not in ["high", "medium", "low", "max"]:
                    raise ValueError(
-                        f"Invalid effort value: {effort}. Must be one of: 'high', 'medium', 'low'"
+                        f"Invalid effort value: {effort}. Must be one of: 'high', 'medium', 'low', 'max'"
+                    )
+                if effort == "max" and not self._is_claude_opus_4_6(model):
+                    raise ValueError(
+                        f"effort='max' is only supported by Claude Opus 4.6. Got model: {model}"
                    )
                data["output_config"] = output_config

--- a/litellm/llms/anthropic/experimental_pass_through/adapters/handler.py
+++ b/litellm/llms/anthropic/experimental_pass_through/adapters/handler.py
@ -19,6 +19,7 @@ from litellm.types.llms.anthropic_messages.anthropic_response import (
    AnthropicMessagesResponse,
 )
 from litellm.types.utils import ModelResponse
+from litellm.utils import get_model_info

 if TYPE_CHECKING:
    pass
@ -63,6 +64,14 @@ class LiteLLMMessagesToCompletionTransformationHandler:
            return

        model = completion_kwargs.get("model")
+        try:
+            model_info = get_model_info(model=cast(str, model), custom_llm_provider=custom_llm_provider)
+            if model_info and model_info.get("supports_reasoning") is False:
+                # Model doesn't support reasoning/responses API, don't route
+                return
+        except Exception:
+            pass
+
        if isinstance(model, str) and model and not model.startswith("responses/"):
            # Prefix model with "responses/" to route to OpenAI Responses API
            completion_kwargs["model"] = f"responses/{model}"
--- a/litellm/llms/anthropic/experimental_pass_through/adapters/streaming_iterator.py
+++ b/litellm/llms/anthropic/experimental_pass_through/adapters/streaming_iterator.py
@ -239,8 +239,13 @@ class AnthropicStreamWrapper(AdapterCompletionStreamWrapper):
                        merged_chunk["delta"] = {}

                    # Add usage to the held chunk
+                    uncached_input_tokens = chunk.usage.prompt_tokens or 0
+                    if hasattr(chunk.usage, "prompt_tokens_details") and chunk.usage.prompt_tokens_details:
+                        cached_tokens = getattr(chunk.usage.prompt_tokens_details, "cached_tokens", 0) or 0
+                        uncached_input_tokens -= cached_tokens
+                    
                    usage_dict: UsageDelta = {
-                        "input_tokens": chunk.usage.prompt_tokens or 0,
+                        "input_tokens": uncached_input_tokens,
                        "output_tokens": chunk.usage.completion_tokens or 0,
                    }
                    # Add cache tokens if available (for prompt caching support)
@ -412,6 +417,7 @@ class AnthropicStreamWrapper(AdapterCompletionStreamWrapper):
        if block_type == "tool_use":
            # Type narrowing: content_block_start is ToolUseBlock when block_type is "tool_use"
            from typing import cast
+
            from litellm.types.llms.anthropic import ToolUseBlock
            
            tool_block = cast(ToolUseBlock, content_block_start)
@ -430,6 +436,7 @@ class AnthropicStreamWrapper(AdapterCompletionStreamWrapper):
        # if we get a function name since it signals a new tool call
        if block_type == "tool_use":
            from typing import cast
+
            from litellm.types.llms.anthropic import ToolUseBlock
            
            tool_block = cast(ToolUseBlock, content_block_start)
--- a/litellm/llms/anthropic/experimental_pass_through/adapters/transformation.py
+++ b/litellm/llms/anthropic/experimental_pass_through/adapters/transformation.py
@ -1070,8 +1070,13 @@ class LiteLLMAnthropicMessagesAdapter:
        )
        # extract usage
        usage: Usage = getattr(response, "usage")
+        uncached_input_tokens = usage.prompt_tokens or 0
+        if hasattr(usage, "prompt_tokens_details") and usage.prompt_tokens_details:
+            cached_tokens = getattr(usage.prompt_tokens_details, "cached_tokens", 0) or 0
+            uncached_input_tokens -= cached_tokens
+        
        anthropic_usage = AnthropicUsage(
-            input_tokens=usage.prompt_tokens or 0,
+            input_tokens=uncached_input_tokens,
            output_tokens=usage.completion_tokens or 0,
        )
        # Add cache tokens if available (for prompt caching support)
@ -1230,8 +1235,13 @@ class LiteLLMAnthropicMessagesAdapter:
            else:
                litellm_usage_chunk = None
            if litellm_usage_chunk is not None:
+                uncached_input_tokens = litellm_usage_chunk.prompt_tokens or 0
+                if hasattr(litellm_usage_chunk, "prompt_tokens_details") and litellm_usage_chunk.prompt_tokens_details:
+                    cached_tokens = getattr(litellm_usage_chunk.prompt_tokens_details, "cached_tokens", 0) or 0
+                    uncached_input_tokens -= cached_tokens
+                
                usage_delta = UsageDelta(
-                    input_tokens=litellm_usage_chunk.prompt_tokens or 0,
+                    input_tokens=uncached_input_tokens,
                    output_tokens=litellm_usage_chunk.completion_tokens or 0,
                )
                # Add cache tokens if available (for prompt caching support)
--- a/litellm/llms/azure/responses/transformation.py
+++ b/litellm/llms/azure/responses/transformation.py
@ -1,5 +1,5 @@
-from typing import TYPE_CHECKING, Any, Dict, List, Literal, Optional, Tuple, Union
 from copy import deepcopy
+from typing import TYPE_CHECKING, Any, Dict, List, Literal, Optional, Tuple, Union

 import httpx
 from openai.types.responses import ResponseReasoningItem
@ -21,10 +21,25 @@ else:


 class AzureOpenAIResponsesAPIConfig(OpenAIResponsesAPIConfig):
+
+    # Parameters not supported by Azure Responses API
+    AZURE_UNSUPPORTED_PARAMS = ["context_management"]
+
    @property
    def custom_llm_provider(self) -> LlmProviders:
        return LlmProviders.AZURE

+    def get_supported_openai_params(self, model: str) -> list:
+        """
+        Azure Responses API does not support context_management (compaction).
+        """
+        base_supported_params = super().get_supported_openai_params(model)
+        return [
+            param
+            for param in base_supported_params
+            if param not in self.AZURE_UNSUPPORTED_PARAMS
+        ]
+
    def validate_environment(
        self, headers: dict, model: str, litellm_params: Optional[GenericLiteLLMParams]
    ) -> dict:
--- a/litellm/llms/bedrock/chat/converse_transformation.py
+++ b/litellm/llms/bedrock/chat/converse_transformation.py
@ -12,7 +12,10 @@ import httpx

 import litellm
 from litellm._logging import verbose_logger
-from litellm.constants import RESPONSE_FORMAT_TOOL_NAME
+from litellm.constants import (
+    BEDROCK_MIN_THINKING_BUDGET_TOKENS,
+    RESPONSE_FORMAT_TOOL_NAME,
+)
 from litellm.litellm_core_utils.core_helpers import (
    filter_exceptions_from_params,
    filter_internal_params,
@ -463,6 +466,25 @@ class AmazonConverseConfig(BaseConfig):
                reasoning_effort=reasoning_effort, model=model
            )

+    @staticmethod
+    def _clamp_thinking_budget_tokens(optional_params: dict) -> None:
+        """
+        Clamp thinking.budget_tokens to the Bedrock minimum (1024).
+
+        Bedrock returns a 400 error if budget_tokens < 1024.
+        """
+        thinking = optional_params.get("thinking")
+        if isinstance(thinking, dict):
+            budget = thinking.get("budget_tokens")
+            if isinstance(budget, int) and budget < BEDROCK_MIN_THINKING_BUDGET_TOKENS:
+                verbose_logger.debug(
+                    "Bedrock requires thinking.budget_tokens >= %d, got %d. "
+                    "Clamping to minimum.",
+                    BEDROCK_MIN_THINKING_BUDGET_TOKENS,
+                    budget,
+                )
+                thinking["budget_tokens"] = BEDROCK_MIN_THINKING_BUDGET_TOKENS
+
    def get_supported_openai_params(self, model: str) -> List[str]:
        from litellm.utils import supports_function_calling

@ -1002,9 +1024,14 @@ class AmazonConverseConfig(BaseConfig):
        Checks 'non_default_params' for 'thinking' and 'max_tokens'

        if 'thinking' is enabled and 'max_tokens' is not specified, set 'max_tokens' to the thinking token budget + DEFAULT_MAX_TOKENS
+
+        Also clamps thinking.budget_tokens to the Bedrock minimum (1024) to
+        prevent 400 errors from the Bedrock API.
        """
        from litellm.constants import DEFAULT_MAX_TOKENS

+        self._clamp_thinking_budget_tokens(optional_params)
+
        is_thinking_enabled = self.is_thinking_enabled(optional_params)
        is_max_tokens_in_request = self.is_max_tokens_in_request(non_default_params)
        if is_thinking_enabled and not is_max_tokens_in_request:
--- a/litellm/llms/chatgpt/responses/transformation.py
+++ b/litellm/llms/chatgpt/responses/transformation.py
@ -73,10 +73,6 @@ class ChatGPTResponsesAPIConfig(OpenAIResponsesAPIConfig):
            litellm_params,
            headers,
        )
-        request.pop("max_output_tokens", None)
-        request.pop("max_tokens", None)
-        request.pop("max_completion_tokens", None)
-        request.pop("metadata", None)
        base_instructions = get_chatgpt_default_instructions()
        existing_instructions = request.get("instructions")
        if existing_instructions:
@ -92,7 +88,22 @@ class ChatGPTResponsesAPIConfig(OpenAIResponsesAPIConfig):
        if "reasoning.encrypted_content" not in include:
            include.append("reasoning.encrypted_content")
        request["include"] = include
-        return request
+
+        allowed_keys = {
+            "model",
+            "input",
+            "instructions",
+            "stream",
+            "store",
+            "include",
+            "tools",
+            "tool_choice",
+            "reasoning",
+            "previous_response_id",
+            "truncation",
+        }
+
+        return {k: v for k, v in request.items() if k in allowed_keys}

    def transform_response_api_response(
        self,
--- a/litellm/llms/custom_httpx/aiohttp_transport.py
+++ b/litellm/llms/custom_httpx/aiohttp_transport.py
@ -119,8 +119,13 @@ class AiohttpResponseStream(httpx.AsyncByteStream):


 class AiohttpTransport(httpx.AsyncBaseTransport):
-    def __init__(self, client: Union[ClientSession, Callable[[], ClientSession]]) -> None:
+    def __init__(
+        self,
+        client: Union[ClientSession, Callable[[], ClientSession]],
+        owns_session: bool = True,
+    ) -> None:
        self.client = client
+        self._owns_session = owns_session

        #########################################################
        # Class variables for proxy settings
@ -128,7 +133,7 @@ class AiohttpTransport(httpx.AsyncBaseTransport):
        self.proxy_cache: Dict[str, Optional[str]] = {}

    async def aclose(self) -> None:
-        if isinstance(self.client, ClientSession):
+        if self._owns_session and isinstance(self.client, ClientSession):
            await self.client.close()


@ -144,10 +149,11 @@ class LiteLLMAiohttpTransport(AiohttpTransport):
        self,
        client: Union[ClientSession, Callable[[], ClientSession]],
        ssl_verify: Optional[Union[bool, ssl.SSLContext]] = None,
+        owns_session: bool = True,
    ):
        self.client = client
        self._ssl_verify = ssl_verify  # Store for per-request SSL override
-        super().__init__(client=client)
+        super().__init__(client=client, owns_session=owns_session)
        # Store the client factory for recreating sessions when needed
        if callable(client):
            self._client_factory = client
--- a/litellm/llms/custom_httpx/http_handler.py
+++ b/litellm/llms/custom_httpx/http_handler.py
@ -866,6 +866,7 @@ class AsyncHTTPHandler:
            return LiteLLMAiohttpTransport(
                client=shared_session,
                ssl_verify=ssl_for_transport,
+                owns_session=False,
            )

        # Create new session only if none provided or existing one is invalid
--- a/litellm/llms/openai_like/dynamic_config.py
+++ b/litellm/llms/openai_like/dynamic_config.py
@ -4,6 +4,7 @@ Dynamic configuration class generator for JSON-based providers.

 from typing import Any, Coroutine, List, Literal, Optional, Tuple, Union, overload

+from litellm._logging import verbose_logger
 from litellm.litellm_core_utils.prompt_templates.common_utils import (
    handle_messages_with_content_list_to_str_conversion,
 )
@ -96,8 +97,27 @@ def create_config_class(provider: SimpleProviderConfig):
            return api_base

        def get_supported_openai_params(self, model: str) -> list:
-            """Get supported OpenAI params from base class"""
-            return super().get_supported_openai_params(model=model)
+            """Get supported OpenAI params, excluding tool-related params for models
+            that don't support function calling."""
+            from litellm.utils import supports_function_calling
+
+            supported_params = super().get_supported_openai_params(model=model)
+
+            _supports_fc = supports_function_calling(
+                model=model, custom_llm_provider=provider.slug
+            )
+
+            if not _supports_fc:
+                tool_params = ["tools", "tool_choice", "function_call", "functions", "parallel_tool_calls"]
+                for param in tool_params:
+                    if param in supported_params:
+                        supported_params.remove(param)
+                verbose_logger.debug(
+                    f"Model {model} on provider {provider.slug} does not support "
+                    f"function calling — removed tool-related params from supported params."
+                )
+
+            return supported_params

        def map_openai_params(
            self,
--- a/litellm/llms/vertex_ai/vertex_ai_partner_models/llama3/transformation.py
+++ b/litellm/llms/vertex_ai/vertex_ai_partner_models/llama3/transformation.py
@ -9,7 +9,13 @@ from litellm.llms.openai.chat.gpt_transformation import (
    OpenAIGPTConfig,
 )
 from litellm.types.llms.openai import AllMessageValues, OpenAIChatCompletionResponse
-from litellm.types.utils import ModelResponse, ModelResponseStream, Usage
+from litellm.types.utils import (
+    Delta,
+    ModelResponse,
+    ModelResponseStream,
+    StreamingChoices,
+    Usage,
+)

 from ...common_utils import VertexAIError

@ -145,17 +151,74 @@ class VertexAILlama3StreamingHandler(OpenAIChatCompletionStreamingHandler):
    """
    Vertex AI Llama models may not include role in streaming chunk deltas.
    This handler ensures the first chunk always has role="assistant".
+    
+    When Vertex AI returns a single chunk with both role and finish_reason (empty response),
+    this handler splits it into two chunks:
+    1. First chunk: role="assistant", content="", finish_reason=None
+    2. Second chunk: role=None, content=None, finish_reason="stop"
+    
+    This matches OpenAI's streaming format where the first chunk has role and
+    the final chunk has finish_reason but no role.
    """

    def __init__(self, **kwargs):
        super().__init__(**kwargs)
        self.sent_role = False
+        self._pending_chunk: Optional[ModelResponseStream] = None

    def chunk_parser(self, chunk: dict) -> ModelResponseStream:
        result = super().chunk_parser(chunk)
        if not self.sent_role and result.choices:
            delta = result.choices[0].delta
-            if delta.role is None:
+            finish_reason = result.choices[0].finish_reason
+            
+            # If this is both the first chunk AND the final chunk (has finish_reason),
+            # we need to split it into two chunks to match OpenAI format
+            if finish_reason is not None:
+                # Create a pending final chunk with finish_reason but no role
+                self._pending_chunk = ModelResponseStream(
+                    id=result.id,
+                    object="chat.completion.chunk",
+                    created=result.created,
+                    model=result.model,
+                    choices=[
+                        StreamingChoices(
+                            index=0,
+                            delta=Delta(content=None, role=None),
+                            finish_reason=finish_reason,
+                        )
+                    ],
+                )
+                # Modify current chunk to be the first chunk with role but no finish_reason
+                result.choices[0].finish_reason = None
                delta.role = "assistant"
+                # Ensure content is empty string for first chunk, not None
+                if delta.content is None:
+                    delta.content = ""
+                # Prevent downstream stream wrapper from dropping this chunk
+                # (it drops empty-content chunks unless special fields are present)
+                if delta.provider_specific_fields is None:
+                    delta.provider_specific_fields = {}
+            elif delta.role is None:
+                delta.role = "assistant"
+            # If the first chunk has empty content, ensure it's still emitted
+            if (delta.content == "" or delta.content is None) and delta.provider_specific_fields is None:
+                delta.provider_specific_fields = {}
            self.sent_role = True
        return result
+
+    def __next__(self):
+        # First return any pending chunk from a previous split
+        if self._pending_chunk is not None:
+            chunk = self._pending_chunk
+            self._pending_chunk = None
+            return chunk
+        return super().__next__()
+
+    async def __anext__(self):
+        # First return any pending chunk from a previous split
+        if self._pending_chunk is not None:
+            chunk = self._pending_chunk
+            self._pending_chunk = None
+            return chunk
+        return await super().__anext__()
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@ -12456,6 +12456,19 @@
        "supports_tool_choice": true,
        "supports_web_search": true
    },
+    "fireworks_ai/accounts/fireworks/models/kimi-k2p5": {
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "fireworks_ai",
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 3e-06,
+        "source": "https://fireworks.ai/pricing",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
    "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": {
        "input_cost_per_token": 3e-06,
        "litellm_provider": "fireworks_ai",
@ -23204,7 +23217,7 @@
        "mode": "chat",
        "output_cost_per_token": 6e-05,
        "supports_function_calling": true,
-        "supports_parallel_function_calling": true,
+        "supports_parallel_function_calling": false,
        "supports_pdf_input": true,
        "supports_prompt_caching": true,
        "supports_reasoning": true,
@ -23759,7 +23772,7 @@
        "max_output_tokens": 131072,
        "max_tokens": 131072,
        "mode": "chat",
-        "output_cost_per_token": 1.5e-07,
+        "output_cost_per_token": 1.5e-05,
        "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
        "supports_function_calling": true,
        "supports_response_schema": false
@ -23807,7 +23820,7 @@
        "max_output_tokens": 128000,
        "max_tokens": 128000,
        "mode": "chat",
-        "output_cost_per_token": 1.5e-07,
+        "output_cost_per_token": 1.5e-05,
        "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
        "supports_function_calling": true,
        "supports_response_schema": false
--- a/litellm/policy_templates_backup.json
+++ b/litellm/policy_templates_backup.json
@ -2,7 +2,7 @@
  {
    "id": "advanced-au-pii-protection",
    "title": "Advanced PII Protection (Australia)",
-    "description": "Comprehensive PII detection and masking for Australia. Protects Australian-specific identifiers, international employee data, financial information, credentials, protected class information, and industry-specific sensitive data.",
+    "description": "Protects Australian-specific identifiers, international employee data, financial information, credentials, protected class information, and industry-specific sensitive data.",
    "icon": "ShieldCheckIcon",
    "iconColor": "text-purple-500",
    "iconBg": "bg-purple-50",
@ -274,5 +274,405 @@
      ],
      "guardrails_remove": []
    }
+  },
+  {
+    "id": "nsfw-content-filter-australia",
+    "title": "NSFW Content Filter (Australia)",
+    "description": "Blocks profanity, sexual content, NSFW requests, self-harm content, and child safety violations using English and Australian-specific slang. Protects against inappropriate content including sexual solicitation, explicit content, Australian profanity, self-harm, and content involving minors.",
+    "icon": "ShieldExclamationIcon",
+    "iconColor": "text-red-500",
+    "iconBg": "bg-red-50",
+    "guardrails": [
+      "nsfw-content-filter-english",
+      "nsfw-content-filter-australian",
+      "nsfw-self-harm-filter",
+      "nsfw-child-safety-filter",
+      "nsfw-racial-bias-filter"
+    ],
+    "complexity": "Medium",
+    "guardrailDefinitions": [
+      {
+        "guardrail_name": "nsfw-content-filter-english",
+        "litellm_params": {
+          "guardrail": "litellm_content_filter",
+          "mode": "pre_call",
+          "categories": [
+            {
+              "category": "harm_toxic_abuse",
+              "enabled": true,
+              "action": "BLOCK",
+              "severity_threshold": "medium"
+            }
+          ]
+        },
+        "guardrail_info": {
+          "description": "Blocks profanity, sexual content, slurs, and NSFW terms in English"
+        }
+      },
+      {
+        "guardrail_name": "nsfw-content-filter-australian",
+        "litellm_params": {
+          "guardrail": "litellm_content_filter",
+          "mode": "pre_call",
+          "categories": [
+            {
+              "category": "harm_toxic_abuse_au",
+              "enabled": true,
+              "action": "BLOCK",
+              "severity_threshold": "medium"
+            }
+          ]
+        },
+        "guardrail_info": {
+          "description": "Blocks Australian-specific slang and profanity (root, perv, bogan, wanker, etc.)"
+        }
+      },
+      {
+        "guardrail_name": "nsfw-self-harm-filter",
+        "litellm_params": {
+          "guardrail": "litellm_content_filter",
+          "mode": "pre_call",
+          "categories": [
+            {
+              "category": "harmful_self_harm",
+              "enabled": true,
+              "action": "BLOCK",
+              "severity_threshold": "medium"
+            }
+          ]
+        },
+        "guardrail_info": {
+          "description": "Blocks content related to self-harm, suicide, and eating disorders"
+        }
+      },
+      {
+        "guardrail_name": "nsfw-child-safety-filter",
+        "litellm_params": {
+          "guardrail": "litellm_content_filter",
+          "mode": "pre_call",
+          "categories": [
+            {
+              "category": "harmful_child_safety",
+              "enabled": true,
+              "action": "BLOCK",
+              "severity_threshold": "medium"
+            }
+          ]
+        },
+        "guardrail_info": {
+          "description": "Blocks inappropriate content involving minors using identifier + block word combinations"
+        }
+      },
+      {
+        "guardrail_name": "nsfw-racial-bias-filter",
+        "litellm_params": {
+          "guardrail": "litellm_content_filter",
+          "mode": "pre_call",
+          "categories": [
+            {
+              "category": "bias_racial",
+              "enabled": true,
+              "action": "BLOCK",
+              "severity_threshold": "medium"
+            }
+          ]
+        },
+        "guardrail_info": {
+          "description": "Blocks racial and ethnic discrimination, hate speech, and supremacist content"
+        }
+      }
+    ],
+    "templateData": {
+      "policy_name": "nsfw-content-filter-australia",
+      "description": "NSFW content filter for Australia. Blocks profanity, sexual content, inappropriate requests, self-harm content, child safety violations, and racial bias in English and Australian slang.",
+      "guardrails_add": [
+        "nsfw-content-filter-english",
+        "nsfw-content-filter-australian",
+        "nsfw-self-harm-filter",
+        "nsfw-child-safety-filter",
+        "nsfw-racial-bias-filter"
+      ],
+      "guardrails_remove": []
+    }
+  },
+  {
+    "id": "nsfw-content-filter-basic",
+    "title": "NSFW Content Filter (Basic)",
+    "description": "Basic NSFW content filtering for English only. Blocks profanity, sexual content, slurs, solicitation, explicit requests, self-harm content, and child safety violations. Suitable for most applications requiring content moderation.",
+    "icon": "ShieldExclamationIcon",
+    "iconColor": "text-orange-500",
+    "iconBg": "bg-orange-50",
+    "guardrails": [
+      "nsfw-content-filter-english-only",
+      "nsfw-self-harm-filter-basic",
+      "nsfw-child-safety-filter-basic",
+      "nsfw-racial-bias-filter-basic"
+    ],
+    "complexity": "Low",
+    "guardrailDefinitions": [
+      {
+        "guardrail_name": "nsfw-content-filter-english-only",
+        "litellm_params": {
+          "guardrail": "litellm_content_filter",
+          "mode": "pre_call",
+          "categories": [
+            {
+              "category": "harm_toxic_abuse",
+              "enabled": true,
+              "action": "BLOCK",
+              "severity_threshold": "medium"
+            }
+          ]
+        },
+        "guardrail_info": {
+          "description": "Blocks profanity, sexual content, slurs, and NSFW terms. Includes 485+ keywords covering explicit content, solicitation, sexual behavior, and exploitation."
+        }
+      },
+      {
+        "guardrail_name": "nsfw-self-harm-filter-basic",
+        "litellm_params": {
+          "guardrail": "litellm_content_filter",
+          "mode": "pre_call",
+          "categories": [
+            {
+              "category": "harmful_self_harm",
+              "enabled": true,
+              "action": "BLOCK",
+              "severity_threshold": "medium"
+            }
+          ]
+        },
+        "guardrail_info": {
+          "description": "Blocks content related to self-harm, suicide, and eating disorders"
+        }
+      },
+      {
+        "guardrail_name": "nsfw-child-safety-filter-basic",
+        "litellm_params": {
+          "guardrail": "litellm_content_filter",
+          "mode": "pre_call",
+          "categories": [
+            {
+              "category": "harmful_child_safety",
+              "enabled": true,
+              "action": "BLOCK",
+              "severity_threshold": "medium"
+            }
+          ]
+        },
+        "guardrail_info": {
+          "description": "Blocks inappropriate content involving minors using identifier + block word combinations"
+        }
+      },
+      {
+        "guardrail_name": "nsfw-racial-bias-filter-basic",
+        "litellm_params": {
+          "guardrail": "litellm_content_filter",
+          "mode": "pre_call",
+          "categories": [
+            {
+              "category": "bias_racial",
+              "enabled": true,
+              "action": "BLOCK",
+              "severity_threshold": "medium"
+            }
+          ]
+        },
+        "guardrail_info": {
+          "description": "Blocks racial and ethnic discrimination, hate speech, and supremacist content"
+        }
+      }
+    ],
+    "templateData": {
+      "policy_name": "nsfw-content-filter-basic",
+      "description": "Basic NSFW content filter. Blocks profanity, sexual content, inappropriate requests, self-harm content, child safety violations, and racial bias in English.",
+      "guardrails_add": [
+        "nsfw-content-filter-english-only",
+        "nsfw-self-harm-filter-basic",
+        "nsfw-child-safety-filter-basic",
+        "nsfw-racial-bias-filter-basic"
+      ],
+      "guardrails_remove": []
+    }
+  },
+  {
+    "id": "nsfw-content-filter-all-regions",
+    "title": "NSFW Content Filter (All Regions)",
+    "description": "Comprehensive multi-language NSFW content filtering. Blocks profanity, sexual content, inappropriate requests, self-harm content, and child safety violations in English, Spanish, French, German, and Australian. Best for global applications.",
+    "icon": "ShieldExclamationIcon",
+    "iconColor": "text-purple-500",
+    "iconBg": "bg-purple-50",
+    "guardrails": [
+      "nsfw-filter-english",
+      "nsfw-filter-spanish",
+      "nsfw-filter-french",
+      "nsfw-filter-german",
+      "nsfw-filter-australian",
+      "nsfw-self-harm-filter-global",
+      "nsfw-child-safety-filter-global",
+      "nsfw-racial-bias-filter-global"
+    ],
+    "complexity": "High",
+    "guardrailDefinitions": [
+      {
+        "guardrail_name": "nsfw-filter-english",
+        "litellm_params": {
+          "guardrail": "litellm_content_filter",
+          "mode": "pre_call",
+          "categories": [
+            {
+              "category": "harm_toxic_abuse",
+              "enabled": true,
+              "action": "BLOCK",
+              "severity_threshold": "medium"
+            }
+          ]
+        },
+        "guardrail_info": {
+          "description": "English profanity, sexual content, slurs, and NSFW terms (485+ keywords)"
+        }
+      },
+      {
+        "guardrail_name": "nsfw-filter-spanish",
+        "litellm_params": {
+          "guardrail": "litellm_content_filter",
+          "mode": "pre_call",
+          "categories": [
+            {
+              "category": "harm_toxic_abuse_es",
+              "enabled": true,
+              "action": "BLOCK",
+              "severity_threshold": "medium"
+            }
+          ]
+        },
+        "guardrail_info": {
+          "description": "Spanish profanity and offensive terms (68 keywords)"
+        }
+      },
+      {
+        "guardrail_name": "nsfw-filter-french",
+        "litellm_params": {
+          "guardrail": "litellm_content_filter",
+          "mode": "pre_call",
+          "categories": [
+            {
+              "category": "harm_toxic_abuse_fr",
+              "enabled": true,
+              "action": "BLOCK",
+              "severity_threshold": "medium"
+            }
+          ]
+        },
+        "guardrail_info": {
+          "description": "French profanity and offensive terms (91 keywords)"
+        }
+      },
+      {
+        "guardrail_name": "nsfw-filter-german",
+        "litellm_params": {
+          "guardrail": "litellm_content_filter",
+          "mode": "pre_call",
+          "categories": [
+            {
+              "category": "harm_toxic_abuse_de",
+              "enabled": true,
+              "action": "BLOCK",
+              "severity_threshold": "medium"
+            }
+          ]
+        },
+        "guardrail_info": {
+          "description": "German profanity and offensive terms (65 keywords)"
+        }
+      },
+      {
+        "guardrail_name": "nsfw-filter-australian",
+        "litellm_params": {
+          "guardrail": "litellm_content_filter",
+          "mode": "pre_call",
+          "categories": [
+            {
+              "category": "harm_toxic_abuse_au",
+              "enabled": true,
+              "action": "BLOCK",
+              "severity_threshold": "medium"
+            }
+          ]
+        },
+        "guardrail_info": {
+          "description": "Australian slang and profanity (32 keywords: root, perv, bogan, wanker, etc.)"
+        }
+      },
+      {
+        "guardrail_name": "nsfw-self-harm-filter-global",
+        "litellm_params": {
+          "guardrail": "litellm_content_filter",
+          "mode": "pre_call",
+          "categories": [
+            {
+              "category": "harmful_self_harm",
+              "enabled": true,
+              "action": "BLOCK",
+              "severity_threshold": "medium"
+            }
+          ]
+        },
+        "guardrail_info": {
+          "description": "Blocks content related to self-harm, suicide, and eating disorders"
+        }
+      },
+      {
+        "guardrail_name": "nsfw-child-safety-filter-global",
+        "litellm_params": {
+          "guardrail": "litellm_content_filter",
+          "mode": "pre_call",
+          "categories": [
+            {
+              "category": "harmful_child_safety",
+              "enabled": true,
+              "action": "BLOCK",
+              "severity_threshold": "medium"
+            }
+          ]
+        },
+        "guardrail_info": {
+          "description": "Blocks inappropriate content involving minors using identifier + block word combinations"
+        }
+      },
+      {
+        "guardrail_name": "nsfw-racial-bias-filter-global",
+        "litellm_params": {
+          "guardrail": "litellm_content_filter",
+          "mode": "pre_call",
+          "categories": [
+            {
+              "category": "bias_racial",
+              "enabled": true,
+              "action": "BLOCK",
+              "severity_threshold": "medium"
+            }
+          ]
+        },
+        "guardrail_info": {
+          "description": "Blocks racial and ethnic discrimination, hate speech, and supremacist content"
+        }
+      }
+    ],
+    "templateData": {
+      "policy_name": "nsfw-content-filter-all-regions",
+      "description": "Comprehensive multi-language NSFW content filter. Blocks profanity, inappropriate content, self-harm, child safety violations, and racial bias in English, Spanish, French, German, and Australian. Total coverage: 741+ keywords across all languages plus self-harm, child safety, and racial bias protection.",
+      "guardrails_add": [
+        "nsfw-filter-english",
+        "nsfw-filter-spanish",
+        "nsfw-filter-french",
+        "nsfw-filter-german",
+        "nsfw-filter-australian",
+        "nsfw-self-harm-filter-global",
+        "nsfw-child-safety-filter-global",
+        "nsfw-racial-bias-filter-global"
+      ],
+      "guardrails_remove": []
+    }
  }
 ]
--- a/litellm/proxy/_experimental/mcp_server/server.py
+++ b/litellm/proxy/_experimental/mcp_server/server.py
@ -149,7 +149,7 @@ if MCP_AVAILABLE:
        app=server,
        event_store=None,
        json_response=False, # enables SSE streaming
-        stateless=False, # enables session state
+        stateless=True,
    )

    # Create SSE session manager
--- a/litellm/proxy/_experimental/out/404.html
+++ b/litellm/proxy/_experimental/out/404.html
--- a/litellm/proxy/_experimental/out/next.PAGE__.txt
+++ b/litellm/proxy/_experimental/out/next.PAGE__.txt
@ -0,0 +1,31 @@
+1:"$Sreact.fragment"
+2:I[347257,["/litellm-asset-prefix/_next/static/chunks/d96012bcfc98706a.js","/litellm-asset-prefix/_next/static/chunks/dbca964212122d58.js"],"ClientPageRoot"]
+3:I[952683,["/litellm-asset-prefix/_next/static/chunks/26adfa4e8ffc85c7.js","/litellm-asset-prefix/_next/static/chunks/e8ed72789c2b42ff.js","/litellm-asset-prefix/_next/static/chunks/9f5ccd929375c1d6.js","/litellm-asset-prefix/_next/static/chunks/e3bc795c751bb99a.js","/litellm-asset-prefix/_next/static/chunks/1fe0596a309ad6cf.js","/litellm-asset-prefix/_next/static/chunks/c93c5c533dba84d1.js","/litellm-asset-prefix/_next/static/chunks/47ed25bb99ff8a39.js","/litellm-asset-prefix/_next/static/chunks/5f9c3b92a016f382.js","/litellm-asset-prefix/_next/static/chunks/58b9eb1766fba8e0.js","/litellm-asset-prefix/_next/static/chunks/5eb6648cefff2d8a.js","/litellm-asset-prefix/_next/static/chunks/4188d520ca4e5f2b.js","/litellm-asset-prefix/_next/static/chunks/403c4d96324c23a6.js","/litellm-asset-prefix/_next/static/chunks/88c74f8b4b20d25a.js","/litellm-asset-prefix/_next/static/chunks/0a671fedee641c02.js","/litellm-asset-prefix/_next/static/chunks/134f728fa7099e3e.js","/litellm-asset-prefix/_next/static/chunks/fe750aa0bf04912c.js","/litellm-asset-prefix/_next/static/chunks/7b788dd93ad868b3.js","/litellm-asset-prefix/_next/static/chunks/81bf20526995284e.js","/litellm-asset-prefix/_next/static/chunks/d64d74932cb225a3.js","/litellm-asset-prefix/_next/static/chunks/c91982ee39ef0f77.js","/litellm-asset-prefix/_next/static/chunks/64f1a2ef9113d86f.js","/litellm-asset-prefix/_next/static/chunks/457923c551f21385.js","/litellm-asset-prefix/_next/static/chunks/82a6c2af12705c46.js","/litellm-asset-prefix/_next/static/chunks/2f04fe05bcb1c150.js","/litellm-asset-prefix/_next/static/chunks/72250192fd3153b7.js","/litellm-asset-prefix/_next/static/chunks/a9ebedc318fa36dc.js","/litellm-asset-prefix/_next/static/chunks/3f369c603677cd7a.js","/litellm-asset-prefix/_next/static/chunks/66a190706fc6c35a.js","/litellm-asset-prefix/_next/static/chunks/3b30ab8eaa03bc21.js","/litellm-asset-prefix/_next/static/chunks/99cf9cf99df5ccfc.js","/litellm-asset-prefix/_next/static/chunks/a7aecb91c09b0e9a.js","/litellm-asset-prefix/_next/static/chunks/e007904603a33bc5.js","/litellm-asset-prefix/_next/static/chunks/c7b74067c01ee971.js","/litellm-asset-prefix/_next/static/chunks/8e12212d7a0aeaee.js","/litellm-asset-prefix/_next/static/chunks/4980372eaa37b78b.js","/litellm-asset-prefix/_next/static/chunks/bf880fd979d4a2e6.js","/litellm-asset-prefix/_next/static/chunks/7ad0165018dc89ce.js","/litellm-asset-prefix/_next/static/chunks/8354d717e34ebd6f.js","/litellm-asset-prefix/_next/static/chunks/00ff280cdb7d7ee5.js","/litellm-asset-prefix/_next/static/chunks/0a65da2cd24e2ab6.js","/litellm-asset-prefix/_next/static/chunks/3d2a01213eb1cc87.js","/litellm-asset-prefix/_next/static/chunks/7e417dd24c8becd0.js","/litellm-asset-prefix/_next/static/chunks/a382857dbbcea5d1.js","/litellm-asset-prefix/_next/static/chunks/bdf355b41816a002.js","/litellm-asset-prefix/_next/static/chunks/1ab4ccc7c0ba9eff.js","/litellm-asset-prefix/_next/static/chunks/8992001a9a91bc67.js","/litellm-asset-prefix/_next/static/chunks/2971c4658f1bcd7d.js","/litellm-asset-prefix/_next/static/chunks/6c4c97f1ea6e7d77.js","/litellm-asset-prefix/_next/static/chunks/a21582fe1f52b973.js","/litellm-asset-prefix/_next/static/chunks/5d3e07ae5afa6fa6.js","/litellm-asset-prefix/_next/static/chunks/c4452a79c69324a6.js","/litellm-asset-prefix/_next/static/chunks/496b84010c33cf69.js","/litellm-asset-prefix/_next/static/chunks/511809a345b510d8.js","/litellm-asset-prefix/_next/static/chunks/450ebd094f4fa24d.js","/litellm-asset-prefix/_next/static/chunks/6367dd1d1cf7eeef.js","/litellm-asset-prefix/_next/static/chunks/69aeba649b0dc90f.js"],"default"]
+1b:I[897367,["/litellm-asset-prefix/_next/static/chunks/d96012bcfc98706a.js","/litellm-asset-prefix/_next/static/chunks/dbca964212122d58.js"],"OutletBoundary"]
+1c:"$Sreact.suspense"
+:HL["/litellm-asset-prefix/_next/static/chunks/3f3fa56b5786d58c.css","style"]
+0:{"buildId":"C_XKHLw43nx5HaPfGD7XZ","rsc":["$","$1","c",{"children":[["$","$L2",null,{"Component":"$3","serverProvidedParams":{"searchParams":{},"params":{},"promises":["$@4","$@5"]}}],[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/chunks/3f3fa56b5786d58c.css","precedence":"next"}],["$","script","script-0",{"src":"/litellm-asset-prefix/_next/static/chunks/9f5ccd929375c1d6.js","async":true}],["$","script","script-1",{"src":"/litellm-asset-prefix/_next/static/chunks/e3bc795c751bb99a.js","async":true}],["$","script","script-2",{"src":"/litellm-asset-prefix/_next/static/chunks/1fe0596a309ad6cf.js","async":true}],["$","script","script-3",{"src":"/litellm-asset-prefix/_next/static/chunks/c93c5c533dba84d1.js","async":true}],["$","script","script-4",{"src":"/litellm-asset-prefix/_next/static/chunks/47ed25bb99ff8a39.js","async":true}],["$","script","script-5",{"src":"/litellm-asset-prefix/_next/static/chunks/5f9c3b92a016f382.js","async":true}],["$","script","script-6",{"src":"/litellm-asset-prefix/_next/static/chunks/58b9eb1766fba8e0.js","async":true}],["$","script","script-7",{"src":"/litellm-asset-prefix/_next/static/chunks/5eb6648cefff2d8a.js","async":true}],["$","script","script-8",{"src":"/litellm-asset-prefix/_next/static/chunks/4188d520ca4e5f2b.js","async":true}],["$","script","script-9",{"src":"/litellm-asset-prefix/_next/static/chunks/403c4d96324c23a6.js","async":true}],["$","script","script-10",{"src":"/litellm-asset-prefix/_next/static/chunks/88c74f8b4b20d25a.js","async":true}],["$","script","script-11",{"src":"/litellm-asset-prefix/_next/static/chunks/0a671fedee641c02.js","async":true}],["$","script","script-12",{"src":"/litellm-asset-prefix/_next/static/chunks/134f728fa7099e3e.js","async":true}],["$","script","script-13",{"src":"/litellm-asset-prefix/_next/static/chunks/fe750aa0bf04912c.js","async":true}],["$","script","script-14",{"src":"/litellm-asset-prefix/_next/static/chunks/7b788dd93ad868b3.js","async":true}],["$","script","script-15",{"src":"/litellm-asset-prefix/_next/static/chunks/81bf20526995284e.js","async":true}],["$","script","script-16",{"src":"/litellm-asset-prefix/_next/static/chunks/d64d74932cb225a3.js","async":true}],["$","script","script-17",{"src":"/litellm-asset-prefix/_next/static/chunks/c91982ee39ef0f77.js","async":true}],["$","script","script-18",{"src":"/litellm-asset-prefix/_next/static/chunks/64f1a2ef9113d86f.js","async":true}],["$","script","script-19",{"src":"/litellm-asset-prefix/_next/static/chunks/457923c551f21385.js","async":true}],["$","script","script-20",{"src":"/litellm-asset-prefix/_next/static/chunks/82a6c2af12705c46.js","async":true}],["$","script","script-21",{"src":"/litellm-asset-prefix/_next/static/chunks/2f04fe05bcb1c150.js","async":true}],["$","script","script-22",{"src":"/litellm-asset-prefix/_next/static/chunks/72250192fd3153b7.js","async":true}],["$","script","script-23",{"src":"/litellm-asset-prefix/_next/static/chunks/a9ebedc318fa36dc.js","async":true}],["$","script","script-24",{"src":"/litellm-asset-prefix/_next/static/chunks/3f369c603677cd7a.js","async":true}],["$","script","script-25",{"src":"/litellm-asset-prefix/_next/static/chunks/66a190706fc6c35a.js","async":true}],["$","script","script-26",{"src":"/litellm-asset-prefix/_next/static/chunks/3b30ab8eaa03bc21.js","async":true}],["$","script","script-27",{"src":"/litellm-asset-prefix/_next/static/chunks/99cf9cf99df5ccfc.js","async":true}],["$","script","script-28",{"src":"/litellm-asset-prefix/_next/static/chunks/a7aecb91c09b0e9a.js","async":true}],["$","script","script-29",{"src":"/litellm-asset-prefix/_next/static/chunks/e007904603a33bc5.js","async":true}],["$","script","script-30",{"src":"/litellm-asset-prefix/_next/static/chunks/c7b74067c01ee971.js","async":true}],["$","script","script-31",{"src":"/litellm-asset-prefix/_next/static/chunks/8e12212d7a0aeaee.js","async":true}],["$","script","script-32",{"src":"/litellm-asset-prefix/_next/static/chunks/4980372eaa37b78b.js","async":true}],["$","script","script-33",{"src":"/litellm-asset-prefix/_next/static/chunks/bf880fd979d4a2e6.js","async":true}],"$L6","$L7","$L8","$L9","$La","$Lb","$Lc","$Ld","$Le","$Lf","$L10","$L11","$L12","$L13","$L14","$L15","$L16","$L17","$L18","$L19"],"$L1a"]}],"loading":null,"isPartial":false}
+4:{}
+5:"$0:rsc:props:children:0:props:serverProvidedParams:params"
+6:["$","script","script-34",{"src":"/litellm-asset-prefix/_next/static/chunks/7ad0165018dc89ce.js","async":true}]
+7:["$","script","script-35",{"src":"/litellm-asset-prefix/_next/static/chunks/8354d717e34ebd6f.js","async":true}]
+8:["$","script","script-36",{"src":"/litellm-asset-prefix/_next/static/chunks/00ff280cdb7d7ee5.js","async":true}]
+9:["$","script","script-37",{"src":"/litellm-asset-prefix/_next/static/chunks/0a65da2cd24e2ab6.js","async":true}]
+a:["$","script","script-38",{"src":"/litellm-asset-prefix/_next/static/chunks/3d2a01213eb1cc87.js","async":true}]
+b:["$","script","script-39",{"src":"/litellm-asset-prefix/_next/static/chunks/7e417dd24c8becd0.js","async":true}]
+c:["$","script","script-40",{"src":"/litellm-asset-prefix/_next/static/chunks/a382857dbbcea5d1.js","async":true}]
+d:["$","script","script-41",{"src":"/litellm-asset-prefix/_next/static/chunks/bdf355b41816a002.js","async":true}]
+e:["$","script","script-42",{"src":"/litellm-asset-prefix/_next/static/chunks/1ab4ccc7c0ba9eff.js","async":true}]
+f:["$","script","script-43",{"src":"/litellm-asset-prefix/_next/static/chunks/8992001a9a91bc67.js","async":true}]
+10:["$","script","script-44",{"src":"/litellm-asset-prefix/_next/static/chunks/2971c4658f1bcd7d.js","async":true}]
+11:["$","script","script-45",{"src":"/litellm-asset-prefix/_next/static/chunks/6c4c97f1ea6e7d77.js","async":true}]
+12:["$","script","script-46",{"src":"/litellm-asset-prefix/_next/static/chunks/a21582fe1f52b973.js","async":true}]
+13:["$","script","script-47",{"src":"/litellm-asset-prefix/_next/static/chunks/5d3e07ae5afa6fa6.js","async":true}]
+14:["$","script","script-48",{"src":"/litellm-asset-prefix/_next/static/chunks/c4452a79c69324a6.js","async":true}]
+15:["$","script","script-49",{"src":"/litellm-asset-prefix/_next/static/chunks/496b84010c33cf69.js","async":true}]
+16:["$","script","script-50",{"src":"/litellm-asset-prefix/_next/static/chunks/511809a345b510d8.js","async":true}]
+17:["$","script","script-51",{"src":"/litellm-asset-prefix/_next/static/chunks/450ebd094f4fa24d.js","async":true}]
+18:["$","script","script-52",{"src":"/litellm-asset-prefix/_next/static/chunks/6367dd1d1cf7eeef.js","async":true}]
+19:["$","script","script-53",{"src":"/litellm-asset-prefix/_next/static/chunks/69aeba649b0dc90f.js","async":true}]
+1a:["$","$L1b",null,{"children":["$","$1c",null,{"name":"Next.MetadataOutlet","children":"$@1d"}]}]
+1d:null
--- a/litellm/proxy/_experimental/out/__next._full.txt
+++ b/litellm/proxy/_experimental/out/__next._full.txt
--- a/litellm/proxy/_experimental/out/__next._head.txt
+++ b/litellm/proxy/_experimental/out/__next._head.txt
@ -0,0 +1,6 @@
+1:"$Sreact.fragment"
+2:I[897367,["/litellm-asset-prefix/_next/static/chunks/d96012bcfc98706a.js","/litellm-asset-prefix/_next/static/chunks/dbca964212122d58.js"],"ViewportBoundary"]
+3:I[897367,["/litellm-asset-prefix/_next/static/chunks/d96012bcfc98706a.js","/litellm-asset-prefix/_next/static/chunks/dbca964212122d58.js"],"MetadataBoundary"]
+4:"$Sreact.suspense"
+5:I[27201,["/litellm-asset-prefix/_next/static/chunks/d96012bcfc98706a.js","/litellm-asset-prefix/_next/static/chunks/dbca964212122d58.js"],"IconMark"]
+0:{"buildId":"C_XKHLw43nx5HaPfGD7XZ","rsc":["$","$1","h",{"children":[null,["$","$L2",null,{"children":[["$","meta","0",{"charSet":"utf-8"}],["$","meta","1",{"name":"viewport","content":"width=device-width, initial-scale=1"}]]}],["$","div",null,{"hidden":true,"children":["$","$L3",null,{"children":["$","$4",null,{"name":"Next.Metadata","children":[["$","title","0",{"children":"LiteLLM Dashboard"}],["$","meta","1",{"name":"description","content":"LiteLLM Proxy Admin UI"}],["$","link","2",{"rel":"icon","href":"/favicon.ico?favicon.1d32c690.ico","sizes":"48x48","type":"image/x-icon"}],["$","link","3",{"rel":"icon","href":"./favicon.ico"}],["$","$L5","4",{}]]}]}]}],["$","meta",null,{"name":"next-size-adjust","content":""}]]}],"loading":null,"isPartial":false}
--- a/litellm/proxy/_experimental/out/__next._index.txt
+++ b/litellm/proxy/_experimental/out/__next._index.txt
@ -0,0 +1,7 @@
+1:"$Sreact.fragment"
+2:I[71195,["/litellm-asset-prefix/_next/static/chunks/26adfa4e8ffc85c7.js","/litellm-asset-prefix/_next/static/chunks/e8ed72789c2b42ff.js"],"default"]
+3:I[339756,["/litellm-asset-prefix/_next/static/chunks/d96012bcfc98706a.js","/litellm-asset-prefix/_next/static/chunks/dbca964212122d58.js"],"default"]
+4:I[837457,["/litellm-asset-prefix/_next/static/chunks/d96012bcfc98706a.js","/litellm-asset-prefix/_next/static/chunks/dbca964212122d58.js"],"default"]
+:HL["/litellm-asset-prefix/_next/static/chunks/4e20891f2fd03463.css","style"]
+:HL["/litellm-asset-prefix/_next/static/chunks/d682c064a60ae3d6.css","style"]
+0:{"buildId":"C_XKHLw43nx5HaPfGD7XZ","rsc":["$","$1","c",{"children":[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/chunks/4e20891f2fd03463.css","precedence":"next"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/chunks/d682c064a60ae3d6.css","precedence":"next"}],["$","script","script-0",{"src":"/litellm-asset-prefix/_next/static/chunks/26adfa4e8ffc85c7.js","async":true}],["$","script","script-1",{"src":"/litellm-asset-prefix/_next/static/chunks/e8ed72789c2b42ff.js","async":true}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"inter_5972bc34-module__OU16Qa__className","children":["$","$L2",null,{"children":["$","$L3",null,{"parallelRouterKey":"children","template":["$","$L4",null,{}],"notFound":[[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":404}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],[]]}]}]}]}]]}],"loading":null,"isPartial":false}
--- a/litellm/proxy/_experimental/out/__next._tree.txt
+++ b/litellm/proxy/_experimental/out/__next._tree.txt
@ -0,0 +1,5 @@
+:HL["/litellm-asset-prefix/_next/static/chunks/4e20891f2fd03463.css","style"]
+:HL["/litellm-asset-prefix/_next/static/chunks/d682c064a60ae3d6.css","style"]
+:HL["/litellm-asset-prefix/_next/static/media/83afe278b6a6bb3c-s.p.3a6ba036.woff2","font",{"crossOrigin":"","type":"font/woff2"}]
+:HL["/litellm-asset-prefix/_next/static/chunks/3f3fa56b5786d58c.css","style"]
+0:{"buildId":"C_XKHLw43nx5HaPfGD7XZ","tree":{"name":"","paramType":null,"paramKey":"","hasRuntimePrefetch":false,"slots":{"children":{"name":"__PAGE__","paramType":null,"paramKey":"__PAGE__","hasRuntimePrefetch":false,"slots":null,"isRootLayout":false}},"isRootLayout":true},"staleTime":300}
--- a/litellm/proxy/_experimental/out/_next/static/-YcCp5y5G0wpTwGaCJTwX/_buildManifest.js
+++ b/litellm/proxy/_experimental/out/_next/static/-YcCp5y5G0wpTwGaCJTwX/_buildManifest.js
@ -1 +0,0 @@
-self.__BUILD_MANIFEST={__rewrites:{afterFiles:[],beforeFiles:[],fallback:[]},"/_error":["static/chunks/pages/_error-cf5ca766ac8f493f.js"],sortedPages:["/_app","/_error"]},self.__BUILD_MANIFEST_CB&&self.__BUILD_MANIFEST_CB();
--- a/litellm/proxy/_experimental/out/_next/static/C_XKHLw43nx5HaPfGD7XZ/_buildManifest.js
+++ b/litellm/proxy/_experimental/out/_next/static/C_XKHLw43nx5HaPfGD7XZ/_buildManifest.js
@ -0,0 +1,16 @@
+self.__BUILD_MANIFEST = {
+  "__rewrites": {
+    "afterFiles": [],
+    "beforeFiles": [
+      {
+        "source": "/litellm-asset-prefix/_next/:path+",
+        "destination": "/_next/:path+"
+      }
+    ],
+    "fallback": []
+  },
+  "sortedPages": [
+    "/_app",
+    "/_error"
+  ]
+};self.__BUILD_MANIFEST_CB && self.__BUILD_MANIFEST_CB()
--- a/litellm/proxy/_experimental/out/_next/static/C_XKHLw43nx5HaPfGD7XZ/_clientMiddlewareManifest.json
+++ b/litellm/proxy/_experimental/out/_next/static/C_XKHLw43nx5HaPfGD7XZ/_clientMiddlewareManifest.json
@ -0,0 +1 @@
+[]
--- a/litellm/proxy/_experimental/out/_next/static/C_XKHLw43nx5HaPfGD7XZ/_ssgManifest.js
+++ b/litellm/proxy/_experimental/out/_next/static/C_XKHLw43nx5HaPfGD7XZ/_ssgManifest.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/00bcc8d30dd19793.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/00bcc8d30dd19793.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/00ff280cdb7d7ee5.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/00ff280cdb7d7ee5.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/04b9c7b5c33ea26c.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/04b9c7b5c33ea26c.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/06aaedbe7d27898c.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/06aaedbe7d27898c.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/088a4006aa78f150.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/088a4006aa78f150.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/0a65da2cd24e2ab6.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/0a65da2cd24e2ab6.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/0a671fedee641c02.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/0a671fedee641c02.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/0a6c418370a8c183.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/0a6c418370a8c183.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/0d1694151d7fdaec.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/0d1694151d7fdaec.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/1067d2c077cd73d6.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/1067d2c077cd73d6.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/1088-c02fed07efa8e3b8.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/1088-c02fed07efa8e3b8.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/1098-f78fb04eeb42c4e0.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/1098-f78fb04eeb42c4e0.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/1112-62aa5eef02a46309.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/1112-62aa5eef02a46309.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/1125-997dafd1c51527b8.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/1125-997dafd1c51527b8.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/11383a8b78399079.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/11383a8b78399079.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/115-9b3af056f550fde4.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/115-9b3af056f550fde4.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/1208-c73262bafe09e8d7.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/1208-c73262bafe09e8d7.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/120d96e5e05ab994.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/120d96e5e05ab994.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/1213-9a1179ea50cba754.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/1213-9a1179ea50cba754.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/121a51d3bbb6f362.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/121a51d3bbb6f362.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/1236-c4d9ccb0f99a3b51.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/1236-c4d9ccb0f99a3b51.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/1300460219810c10.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/1300460219810c10.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/134f728fa7099e3e.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/134f728fa7099e3e.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/1512-a2667f307ad7c115.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/1512-a2667f307ad7c115.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/1632-4f95f33a116ba3b2.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/1632-4f95f33a116ba3b2.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/1747-6538506d0a7865be.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/1747-6538506d0a7865be.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/179f4b987bc9083f.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/179f4b987bc9083f.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/193ac6435f936582.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/193ac6435f936582.js
@ -0,0 +1 @@
+(globalThis.TURBOPACK||(globalThis.TURBOPACK=[])).push(["object"==typeof document?document.currentScript:void 0,349356,e=>{e.v({AElig:"Æ",AMP:"&",Aacute:"Á",Acirc:"Â",Agrave:"À",Aring:"Å",Atilde:"Ã",Auml:"Ä",COPY:"©",Ccedil:"Ç",ETH:"Ð",Eacute:"É",Ecirc:"Ê",Egrave:"È",Euml:"Ë",GT:">",Iacute:"Í",Icirc:"Î",Igrave:"Ì",Iuml:"Ï",LT:"<",Ntilde:"Ñ",Oacute:"Ó",Ocirc:"Ô",Ograve:"Ò",Oslash:"Ø",Otilde:"Õ",Ouml:"Ö",QUOT:'"',REG:"®",THORN:"Þ",Uacute:"Ú",Ucirc:"Û",Ugrave:"Ù",Uuml:"Ü",Yacute:"Ý",aacute:"á",acirc:"â",acute:"´",aelig:"æ",agrave:"à",amp:"&",aring:"å",atilde:"ã",auml:"ä",brvbar:"¦",ccedil:"ç",cedil:"¸",cent:"¢",copy:"©",curren:"¤",deg:"°",divide:"÷",eacute:"é",ecirc:"ê",egrave:"è",eth:"ð",euml:"ë",frac12:"½",frac14:"¼",frac34:"¾",gt:">",iacute:"í",icirc:"î",iexcl:"¡",igrave:"ì",iquest:"¿",iuml:"ï",laquo:"«",lt:"<",macr:"¯",micro:"µ",middot:"·",nbsp:" ",not:"¬",ntilde:"ñ",oacute:"ó",ocirc:"ô",ograve:"ò",ordf:"ª",ordm:"º",oslash:"ø",otilde:"õ",ouml:"ö",para:"¶",plusmn:"±",pound:"£",quot:'"',raquo:"»",reg:"®",sect:"§",shy:"",sup1:"¹",sup2:"²",sup3:"³",szlig:"ß",thorn:"þ",times:"×",uacute:"ú",ucirc:"û",ugrave:"ù",uml:"¨",uuml:"ü",yacute:"ý",yen:"¥",yuml:"ÿ"})},137429,e=>{e.v({0:"<22>",128:"€",130:"‚",131:"ƒ",132:"„",133:"…",134:"†",135:"‡",136:"ˆ",137:"‰",138:"Š",139:"‹",140:"Œ",142:"Ž",145:"‘",146:"’",147:"“",148:"”",149:"•",150:"–",151:"—",152:"˜",153:"™",154:"š",155:"›",156:"œ",158:"ž",159:"Ÿ"})},921511,e=>{"use strict";var a=e.i(843476),l=e.i(271645),i=e.i(199133),t=e.i(764205);e.s(["default",0,({onChange:e,value:r,className:o,accessToken:c,disabled:s})=>{let[u,d]=(0,l.useState)([]),[n,g]=(0,l.useState)(!1);return(0,l.useEffect)(()=>{(async()=>{if(c){g(!0);try{let e=await (0,t.getPoliciesList)(c);console.log("Policies response:",e),e.policies&&(console.log("Policies data:",e.policies),d(e.policies))}catch(e){console.error("Error fetching policies:",e)}finally{g(!1)}}})()},[c]),(0,a.jsx)("div",{children:(0,a.jsx)(i.Select,{mode:"multiple",disabled:s,placeholder:s?"Setting policies is a premium feature.":"Select policies",onChange:a=>{console.log("Selected policies:",a),e(a)},value:r,loading:n,className:o,allowClear:!0,options:u.map(e=>(console.log("Mapping policy:",e),{label:`${e.policy_name}${e.description?` - ${e.description}`:""}`,value:e.policy_name})),optionFilterProp:"label",showSearch:!0,style:{width:"100%"}})})}])},916940,e=>{"use strict";var a=e.i(843476),l=e.i(271645),i=e.i(199133),t=e.i(764205);e.s(["default",0,({onChange:e,value:r,className:o,accessToken:c,placeholder:s="Select vector stores",disabled:u=!1})=>{let[d,n]=(0,l.useState)([]),[g,p]=(0,l.useState)(!1);return(0,l.useEffect)(()=>{(async()=>{if(c){p(!0);try{let e=await (0,t.vectorStoreListCall)(c);e.data&&n(e.data)}catch(e){console.error("Error fetching vector stores:",e)}finally{p(!1)}}})()},[c]),(0,a.jsx)("div",{children:(0,a.jsx)(i.Select,{mode:"multiple",placeholder:s,onChange:e,value:r,loading:g,className:o,allowClear:!0,options:d.map(e=>({label:`${e.vector_store_name||e.vector_store_id} (${e.vector_store_id})`,value:e.vector_store_id,title:e.vector_store_description||e.vector_store_id})),optionFilterProp:"label",showSearch:!0,style:{width:"100%"},disabled:u})})}])},737434,e=>{"use strict";var a=e.i(184163);e.s(["DownloadOutlined",()=>a.default])},891547,e=>{"use strict";var a=e.i(843476),l=e.i(271645),i=e.i(199133),t=e.i(764205);e.s(["default",0,({onChange:e,value:r,className:o,accessToken:c,disabled:s})=>{let[u,d]=(0,l.useState)([]),[n,g]=(0,l.useState)(!1);return(0,l.useEffect)(()=>{(async()=>{if(c){g(!0);try{let e=await (0,t.getGuardrailsList)(c);console.log("Guardrails response:",e),e.guardrails&&(console.log("Guardrails data:",e.guardrails),d(e.guardrails))}catch(e){console.error("Error fetching guardrails:",e)}finally{g(!1)}}})()},[c]),(0,a.jsx)("div",{children:(0,a.jsx)(i.Select,{mode:"multiple",disabled:s,placeholder:s?"Setting guardrails is a premium feature.":"Select guardrails",onChange:a=>{console.log("Selected guardrails:",a),e(a)},value:r,loading:n,className:o,allowClear:!0,options:u.map(e=>(console.log("Mapping guardrail:",e),{label:`${e.guardrail_name}`,value:e.guardrail_name})),optionFilterProp:"label",showSearch:!0,style:{width:"100%"}})})}])},133574,e=>{"use strict";var a=e.i(843476),l=e.i(220486),i=e.i(135214),t=e.i(271645),r=e.i(62478);e.s(["default",0,()=>{let{token:e,accessToken:o,userRole:c,userId:s,disabledPersonalKeyCreation:u}=(0,i.default)(),[d,n]=(0,t.useState)(void 0);return(0,t.useEffect)(()=>{(async()=>{if(o){let e=await (0,r.fetchProxySettings)(o);e&&n({PROXY_BASE_URL:e.PROXY_BASE_URL||void 0,LITELLM_UI_API_DOC_BASE_URL:e.LITELLM_UI_API_DOC_BASE_URL})}})()},[o]),(0,a.jsx)(l.default,{accessToken:o,token:e,userRole:c,userID:s,disabledPersonalKeyCreation:u,proxySettings:d})}])}]);
--- a/litellm/proxy/_experimental/out/_next/static/chunks/1953-4abaab16a291b91b.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/1953-4abaab16a291b91b.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/1994-39659d054539ed7e.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/1994-39659d054539ed7e.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/1a01cb4063a7b21e.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/1a01cb4063a7b21e.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/1ab4ccc7c0ba9eff.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/1ab4ccc7c0ba9eff.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/1b8186fdb9bf9067.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/1b8186fdb9bf9067.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/1d3826d625e92c33.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/1d3826d625e92c33.js
--- a/Show more
+++ b/Show more
				`@ -1 +0,0 @@`
				`self.__BUILD_MANIFEST={__rewrites:{afterFiles:[],beforeFiles:[],fallback:[]},"/_error":["static/chunks/pages/_error-cf5ca766ac8f493f.js"],sortedPages:["/_app","/_error"]},self.__BUILD_MANIFEST_CB&&self.__BUILD_MANIFEST_CB();`
				`@ -0,0 +1 @@`
				(globalThis.TURBOPACK\|\|(globalThis.TURBOPACK=[])).push(["object"==typeof document?document.currentScript:void 0,349356,e=>{e.v({AElig:"Æ",AMP:"&",Aacute:"Á",Acirc:"Â",Agrave:"À",Aring:"Å",Atilde:"Ã",Auml:"Ä",COPY:"©",Ccedil:"Ç",ETH:"Ð",Eacute:"É",Ecirc:"Ê",Egrave:"È",Euml:"Ë",GT:">",Iacute:"Í",Icirc:"Î",Igrave:"Ì",Iuml:"Ï",LT:"<",Ntilde:"Ñ",Oacute:"Ó",Ocirc:"Ô",Ograve:"Ò",Oslash:"Ø",Otilde:"Õ",Ouml:"Ö",QUOT:'"',REG:"®",THORN:"Þ",Uacute:"Ú",Ucirc:"Û",Ugrave:"Ù",Uuml:"Ü",Yacute:"Ý",aacute:"á",acirc:"â",acute:"´",aelig:"æ",agrave:"à",amp:"&",aring:"å",atilde:"ã",auml:"ä",brvbar:"¦",ccedil:"ç",cedil:"¸",cent:"¢",copy:"©",curren:"¤",deg:"°",divide:"÷",eacute:"é",ecirc:"ê",egrave:"è",eth:"ð",euml:"ë",frac12:"½",frac14:"¼",frac34:"¾",gt:">",iacute:"í",icirc:"î",iexcl:"¡",igrave:"ì",iquest:"¿",iuml:"ï",laquo:"«",lt:"<",macr:"¯",micro:"µ",middot:"·",nbsp:" ",not:"¬",ntilde:"ñ",oacute:"ó",ocirc:"ô",ograve:"ò",ordf:"ª",ordm:"º",oslash:"ø",otilde:"õ",ouml:"ö",para:"¶",plusmn:"±",pound:"£",quot:'"',raquo:"»",reg:"®",sect:"§",shy:"",sup1:"¹",sup2:"²",sup3:"³",szlig:"ß",thorn:"þ",times:"×",uacute:"ú",ucirc:"û",ugrave:"ù",uml:"¨",uuml:"ü",yacute:"ý",yen:"¥",yuml:"ÿ"})},137429,e=>{e.v({0:"<22>",128:"€",130:"‚",131:"ƒ",132:"„",133:"…",134:"†",135:"‡",136:"ˆ",137:"‰",138:"Š",139:"‹",140:"Œ",142:"Ž",145:"‘",146:"’",147:"“",148:"”",149:"•",150:"–",151:"—",152:"˜",153:"™",154:"š",155:"›",156:"œ",158:"ž",159:"Ÿ"})},921511,e=>{"use strict";var a=e.i(843476),l=e.i(271645),i=e.i(199133),t=e.i(764205);e.s(["default",0,({onChange:e,value:r,className:o,accessToken:c,disabled:s})=>{let[u,d]=(0,l.useState)([]),[n,g]=(0,l.useState)(!1);return(0,l.useEffect)(()=>{(async()=>{if(c){g(!0);try{let e=await (0,t.getPoliciesList)(c);console.log("Policies response:",e),e.policies&&(console.log("Policies data:",e.policies),d(e.policies))}catch(e){console.error("Error fetching policies:",e)}finally{g(!1)}}})()},[c]),(0,a.jsx)("div",{children:(0,a.jsx)(i.Select,{mode:"multiple",disabled:s,placeholder:s?"Setting policies is a premium feature.":"Select policies",onChange:a=>{console.log("Selected policies:",a),e(a)},value:r,loading:n,className:o,allowClear:!0,options:u.map(e=>(console.log("Mapping policy:",e),{label:`${e.policy_name}${e.description?` - ${e.description}`:""}`,value:e.policy_name})),optionFilterProp:"label",showSearch:!0,style:{width:"100%"}})})}])},916940,e=>{"use strict";var a=e.i(843476),l=e.i(271645),i=e.i(199133),t=e.i(764205);e.s(["default",0,({onChange:e,value:r,className:o,accessToken:c,placeholder:s="Select vector stores",disabled:u=!1})=>{let[d,n]=(0,l.useState)([]),[g,p]=(0,l.useState)(!1);return(0,l.useEffect)(()=>{(async()=>{if(c){p(!0);try{let e=await (0,t.vectorStoreListCall)(c);e.data&&n(e.data)}catch(e){console.error("Error fetching vector stores:",e)}finally{p(!1)}}})()},[c]),(0,a.jsx)("div",{children:(0,a.jsx)(i.Select,{mode:"multiple",placeholder:s,onChange:e,value:r,loading:g,className:o,allowClear:!0,options:d.map(e=>({label:`${e.vector_store_name\|\|e.vector_store_id} (${e.vector_store_id})`,value:e.vector_store_id,title:e.vector_store_description\|\|e.vector_store_id})),optionFilterProp:"label",showSearch:!0,style:{width:"100%"},disabled:u})})}])},737434,e=>{"use strict";var a=e.i(184163);e.s(["DownloadOutlined",()=>a.default])},891547,e=>{"use strict";var a=e.i(843476),l=e.i(271645),i=e.i(199133),t=e.i(764205);e.s(["default",0,({onChange:e,value:r,className:o,accessToken:c,disabled:s})=>{let[u,d]=(0,l.useState)([]),[n,g]=(0,l.useState)(!1);return(0,l.useEffect)(()=>{(async()=>{if(c){g(!0);try{let e=await (0,t.getGuardrailsList)(c);console.log("Guardrails response:",e),e.guardrails&&(console.log("Guardrails data:",e.guardrails),d(e.guardrails))}catch(e){console.error("Error fetching guardrails:",e)}finally{g(!1)}}})()},[c]),(0,a.jsx)("div",{children:(0,a.jsx)(i.Select,{mode:"multiple",disabled:s,placeholder:s?"Setting guardrails is a premium feature.":"Select guardrails",onChange:a=>{console.log("Selected guardrails:",a),e(a)},value:r,loading:n,className:o,allowClear:!0,options:u.map(e=>(console.log("Mapping guardrail:",e),{label:`${e.guardrail_name}`,value:e.guardrail_name})),optionFilterProp:"label",showSearch:!0,style:{width:"100%"}})})}])},133574,e=>{"use strict";var a=e.i(843476),l=e.i(220486),i=e.i(135214),t=e.i(271645),r=e.i(62478);e.s(["default",0,()=>{let{token:e,accessToken:o,userRole:c,userId:s,disabledPersonalKeyCreation:u}=(0,i.default)(),[d,n]=(0,t.useState)(void 0);return(0,t.useEffect)(()=>{(async()=>{if(o){let e=await (0,r.fetchProxySettings)(o);e&&n({PROXY_BASE_URL:e.PROXY_BASE_URL\|\|void 0,LITELLM_UI_API_DOC_BASE_URL:e.LITELLM_UI_API_DOC_BASE_URL})}})()},[o]),(0,a.jsx)(l.default,{accessToken:o,token:e,userRole:c,userID:s,disabledPersonalKeyCreation:u,proxySettings:d})}])}]);