Merge branch 'main' into litellm_dev_03_04_2026_p1

2026-09-11 22:51:28 +00:00 · 2026-03-07 19:12:02 -08:00 · 2026-03-07 19:12:02 -08:00 · 058b7fb66c
commit 058b7fb66c
parent 1bd6c24c06 03ca98123f
888 changed files with 24051 additions and 7781 deletions
--- a/AGENTS.md
+++ b/AGENTS.md
@ -251,9 +251,11 @@ The proxy takes ~15-20 seconds to fully start (it runs Prisma migrations on boot
 See `CLAUDE.md` and the `Makefile` for standard commands. Key notes:

 - `psycopg-binary` must be installed (`poetry run pip install psycopg-binary`) because the pytest-postgresql plugin requires it and the lock file only includes `psycopg` (no binary).
+- `openapi-core` must be installed (`poetry run pip install openapi-core`) for the OpenAPI compliance tests in `tests/test_litellm/interactions/`.
 - The `--timeout` pytest flag is NOT available; don't pass it.
 - Unit tests: `poetry run pytest tests/test_litellm/ -x -vv -n 4`
 - Black `--check` may report pre-existing formatting issues; this does not block test runs.
+- If `poetry install` fails with "pyproject.toml changed significantly since poetry.lock was last generated", run `poetry lock` first to regenerate the lock file.

 ### Lint

--- a/13
+++ b/13
@ -49,7 +49,7 @@ USER root

 # Install runtime dependencies (libsndfile needed for audio processing on ARM64)
 RUN apk add --no-cache bash openssl tzdata nodejs npm python3 py3-pip libsndfile && \
-    npm install -g npm@latest tar@7.5.8 glob@11.1.0 @isaacs/brace-expansion@5.0.1 minimatch@10.2.4 diff@8.0.3 && \
+    npm install -g npm@latest tar@7.5.10 glob@11.1.0 @isaacs/brace-expansion@5.0.1 minimatch@10.2.4 diff@8.0.3 && \
    # SECURITY FIX: npm bundles tar, glob, and brace-expansion at multiple nested
    # levels inside its dependency tree. `npm install -g <pkg>` only creates a
    # SEPARATE global package, it does NOT replace npm's internal copies.
@ -70,7 +70,15 @@ RUN apk add --no-cache bash openssl tzdata nodejs npm python3 py3-pip libsndfile
    find "$GLOBAL/npm" -type d -name "diff" -path "*/node_modules/diff" | while read d; do \
        rm -rf "$d" && cp -rL "$GLOBAL/diff" "$d"; \
    done && \
-    npm cache clean --force
+    # SECURITY FIX: patch npm's own package.json metadata so scanners see the
+    # actual installed versions instead of the stale declared dependencies.
+    find /usr/local/lib /usr/lib -path "*/node_modules/npm/package.json" -exec \
+        sed -i 's/"tar": "\^7\.5\.[0-9]*"/"tar": "^7.5.10"/g; s/"minimatch": "\^10\.[0-9.]*"/"minimatch": "^10.2.4"/g' {} + 2>/dev/null && \
+    npm cache clean --force && \
+    # Remove the apk-tracked npm so its stale SBOM metadata (tar 7.5.9) is
+    # no longer visible to image scanners.  The globally installed npm@latest
+    # at /usr/local/lib/node_modules/npm/ remains fully functional.
+    { apk del --no-cache npm 2>/dev/null || true; }

 WORKDIR /app
 # Copy the current directory contents into the container at /app
@ -96,6 +104,7 @@ RUN find /usr/lib -type f -path "*/tornado/test/*" -delete && \
 # npm with old vulnerable deps at /usr/lib/python3.*/site-packages/nodejs_wheel/.
 # Patch every copy of tar, glob, and brace-expansion inside that tree.
 RUN GLOBAL="$(npm root -g)" && \
+    [ -n "$GLOBAL" ] || { echo "ERROR: npm root -g returned empty; aborting"; exit 1; } && \
    find /usr/lib -type d -name "tar" -path "*/node_modules/tar" | while read d; do \
        rm -rf "$d" && cp -rL "$GLOBAL/tar" "$d"; \
    done && \
--- a/ci_cd/security_scans.sh
+++ b/ci_cd/security_scans.sh
@ -161,6 +161,8 @@ run_grype_scans() {
        "GHSA-3ppc-4f35-3m26" # minimatch ReDoS via repeated wildcards - from nodejs_wheel bundled npm, not used in application runtime code
        "GHSA-83g3-92jg-28cx" # tar arbitrary file read/write via hardlink - from nodejs_wheel bundled npm, not used in application runtime code
        "CVE-2026-25639" # axios - full fix requires 1.x major version bump; pinned to >=0.30.2 to clear other axios CVEs, upgrade to 1.x in follow-up
+        "CVE-2026-2297" # Python 3.13 SourcelessFileLoader audit hook bypass - no fix available in base image
+        "GHSA-qffp-2rhf-9h96" # tar hardlink path traversal - from nodejs_wheel bundled npm, not used in application runtime code
    )

    # Build JSON array of allowlisted CVE IDs for jq
--- a/docker/Dockerfile.custom_ui
+++ b/docker/Dockerfile.custom_ui
@ -19,7 +19,7 @@ RUN apt-get update && apt-get upgrade -y \
        libgnutls30 \
        libc6 && \
    apt-get install -y nodejs npm && \
-    npm install -g npm@latest tar@7.5.8 glob@11.1.0 @isaacs/brace-expansion@5.0.1 minimatch@10.2.1 diff@8.0.3 && \
+    npm install -g npm@latest tar@7.5.10 glob@11.1.0 @isaacs/brace-expansion@5.0.1 minimatch@10.2.4 diff@8.0.3 && \
    GLOBAL="$(npm root -g)" && \
    find "$GLOBAL/npm" -type d -name "tar" -path "*/node_modules/tar" | while read d; do \
        rm -rf "$d" && cp -rL "$GLOBAL/tar" "$d"; \
@ -36,7 +36,10 @@ RUN apt-get update && apt-get upgrade -y \
    find "$GLOBAL/npm" -type d -name "diff" -path "*/node_modules/diff" | while read d; do \
        rm -rf "$d" && cp -rL "$GLOBAL/diff" "$d"; \
    done && \
-    npm cache clean --force
+    find /usr/local/lib /usr/lib -path "*/node_modules/npm/package.json" -exec \
+        sed -i 's/"tar": "\^7\.5\.[0-9]*"/"tar": "^7.5.10"/g; s/"minimatch": "\^10\.[0-9.]*"/"minimatch": "^10.2.4"/g' {} + 2>/dev/null && \
+    npm cache clean --force && \
+    apt-get purge -y npm

 # Copy the UI source into the container
 COPY ./ui/litellm-dashboard /app/ui/litellm-dashboard
--- a/docker/Dockerfile.database
+++ b/docker/Dockerfile.database
@ -50,7 +50,7 @@ USER root

 # Install runtime dependencies
 RUN apk add --no-cache bash openssl tzdata nodejs npm python3 py3-pip libsndfile && \
-    npm install -g npm@latest tar@7.5.8 glob@11.1.0 @isaacs/brace-expansion@5.0.1 minimatch@10.2.1 diff@8.0.3 && \
+    npm install -g npm@latest tar@7.5.10 glob@11.1.0 @isaacs/brace-expansion@5.0.1 minimatch@10.2.4 diff@8.0.3 && \
    GLOBAL="$(npm root -g)" && \
    find "$GLOBAL/npm" -type d -name "tar" -path "*/node_modules/tar" | while read d; do \
        rm -rf "$d" && cp -rL "$GLOBAL/tar" "$d"; \
@ -67,7 +67,10 @@ RUN apk add --no-cache bash openssl tzdata nodejs npm python3 py3-pip libsndfile
    find "$GLOBAL/npm" -type d -name "diff" -path "*/node_modules/diff" | while read d; do \
        rm -rf "$d" && cp -rL "$GLOBAL/diff" "$d"; \
    done && \
-    npm cache clean --force
+    find /usr/local/lib /usr/lib -path "*/node_modules/npm/package.json" -exec \
+        sed -i 's/"tar": "\^7\.5\.[0-9]*"/"tar": "^7.5.10"/g; s/"minimatch": "\^10\.[0-9.]*"/"minimatch": "^10.2.4"/g' {} + 2>/dev/null && \
+    npm cache clean --force && \
+    { apk del --no-cache npm 2>/dev/null || true; }

 WORKDIR /app
 # Copy the current directory contents into the container at /app
@ -85,6 +88,7 @@ RUN pip install *.whl /wheels/* --no-index --find-links=/wheels/ && rm -f *.whl
 # npm with old vulnerable deps at /usr/lib/python3.*/site-packages/nodejs_wheel/.
 # Patch every copy of tar, glob, and brace-expansion inside that tree.
 RUN GLOBAL="$(npm root -g)" && \
+    [ -n "$GLOBAL" ] || { echo "ERROR: npm root -g returned empty; aborting"; exit 1; } && \
    find /usr/lib -type d -name "tar" -path "*/node_modules/tar" | while read d; do \
        rm -rf "$d" && cp -rL "$GLOBAL/tar" "$d"; \
    done && \
--- a/docker/Dockerfile.dev
+++ b/docker/Dockerfile.dev
@ -75,7 +75,7 @@ RUN apt-get update && apt-get upgrade -y \
    nodejs \
    npm \
    && rm -rf /var/lib/apt/lists/* \
-    && npm install -g npm@latest tar@7.5.8 glob@11.1.0 @isaacs/brace-expansion@5.0.1 minimatch@10.2.1 diff@8.0.3 \
+    && npm install -g npm@latest tar@7.5.10 glob@11.1.0 @isaacs/brace-expansion@5.0.1 minimatch@10.2.4 diff@8.0.3 \
    && GLOBAL="$(npm root -g)" \
    && find "$GLOBAL/npm" -type d -name "tar" -path "*/node_modules/tar" | while read d; do \
          rm -rf "$d" && cp -rL "$GLOBAL/tar" "$d"; \
@ -92,7 +92,10 @@ RUN apt-get update && apt-get upgrade -y \
    && find "$GLOBAL/npm" -type d -name "diff" -path "*/node_modules/diff" | while read d; do \
          rm -rf "$d" && cp -rL "$GLOBAL/diff" "$d"; \
       done \
-    && npm cache clean --force
+    && find /usr/local/lib /usr/lib -path "*/node_modules/npm/package.json" -exec \
+        sed -i 's/"tar": "\^7\.5\.[0-9]*"/"tar": "^7.5.10"/g; s/"minimatch": "\^10\.[0-9.]*"/"minimatch": "^10.2.4"/g' {} + 2>/dev/null \
+    && npm cache clean --force \
+    && apt-get purge -y npm

 WORKDIR /app

@ -114,6 +117,7 @@ RUN pip install --no-cache-dir *.whl /wheels/* --no-index --find-links=/wheels/
 # npm with old vulnerable deps at /usr/lib/python3.*/site-packages/nodejs_wheel/.
 # Patch every copy of tar, glob, and brace-expansion inside that tree.
 RUN GLOBAL="$(npm root -g)" && \
+    [ -n "$GLOBAL" ] || { echo "ERROR: npm root -g returned empty; aborting"; exit 1; } && \
    find /usr/lib -type d -name "tar" -path "*/node_modules/tar" | while read d; do \
        rm -rf "$d" && cp -rL "$GLOBAL/tar" "$d"; \
    done && \
--- a/docker/Dockerfile.non_root
+++ b/docker/Dockerfile.non_root
@ -106,7 +106,7 @@ RUN for i in 1 2 3; do \
    apk add --no-cache python3 py3-pip bash openssl tzdata nodejs npm supervisor && break || sleep 5; \
    done \
  && apk upgrade --no-cache nodejs \
-  && npm install -g npm@latest tar@7.5.8 glob@11.1.0 @isaacs/brace-expansion@5.0.1 minimatch@10.2.1 diff@8.0.3 \
+  && npm install -g npm@latest tar@7.5.10 glob@11.1.0 @isaacs/brace-expansion@5.0.1 minimatch@10.2.4 diff@8.0.3 \
  && GLOBAL="$(npm root -g)" \
  && find "$GLOBAL/npm" -type d -name "tar" -path "*/node_modules/tar" | while read d; do \
        rm -rf "$d" && cp -rL "$GLOBAL/tar" "$d"; \
@ -123,7 +123,10 @@ RUN for i in 1 2 3; do \
  && find "$GLOBAL/npm" -type d -name "diff" -path "*/node_modules/diff" | while read d; do \
        rm -rf "$d" && cp -rL "$GLOBAL/diff" "$d"; \
     done \
-  && npm cache clean --force
+  && find /usr/local/lib /usr/lib -path "*/node_modules/npm/package.json" -exec \
+        sed -i 's/"tar": "\^7\.5\.[0-9]*"/"tar": "^7.5.10"/g; s/"minimatch": "\^10\.[0-9.]*"/"minimatch": "^10.2.4"/g' {} + 2>/dev/null \
+  && npm cache clean --force \
+  && { apk del --no-cache npm 2>/dev/null || true; }

 # Copy artifacts from builder
 COPY --from=builder /app/requirements.txt /app/requirements.txt
@ -169,6 +172,7 @@ RUN pip install --no-index --find-links=/wheels/ -r requirements.txt && \
 # npm with old vulnerable deps at /usr/lib/python3.*/site-packages/nodejs_wheel/.
 # Patch every copy of tar, glob, and brace-expansion inside that tree.
 RUN GLOBAL="$(npm root -g)" && \
+    [ -n "$GLOBAL" ] || { echo "ERROR: npm root -g returned empty; aborting"; exit 1; } && \
    find /usr/lib -type d -name "tar" -path "*/node_modules/tar" | while read d; do \
        rm -rf "$d" && cp -rL "$GLOBAL/tar" "$d"; \
    done && \
--- a/docs/my-website/docs/a2a_agent_headers.md
+++ b/docs/my-website/docs/a2a_agent_headers.md
@ -0,0 +1,252 @@
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# A2A Agent Authentication Headers
+
+Forward authentication credentials (Bearer tokens, API keys, etc.) from clients to backend A2A agents.
+
+## Overview
+
+When LiteLLM proxies a request to a backend A2A agent, the agent may require its own authentication headers. There are three ways to supply them:
+
+| Method | Who configures | How it works |
+|---|---|---|
+| **Static headers** | Admin (UI / API) | Always sent, regardless of client request |
+| **Forward client headers** | Admin (UI / API) | Header names to extract from client request and forward |
+| **Convention-based** | Client (no admin config) | Client sends `x-a2a-{agent_name}-{header}` — automatically routed |
+
+All three methods can be combined. **Static headers always win** on key conflicts.
+
+---
+
+## Method 1 — Static Headers
+
+Admin-configured headers that are always sent to the backend agent. Use this for server-to-server tokens or internal credentials that clients should never see or override.
+
+<Tabs>
+<TabItem value="ui" label="UI">
+
+1. Go to **Agents** in the LiteLLM dashboard.
+2. Create or edit an agent.
+3. Open the **Authentication Headers** panel.
+4. Under **Static Headers**, click **Add Static Header** and fill in the header name and value.
+
+</TabItem>
+<TabItem value="api" label="REST API">
+
+```bash
+curl -X POST http://localhost:4000/v1/agents \
+  -H "Authorization: Bearer sk-admin" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "agent_name": "my-agent",
+    "agent_card_params": { ... },
+    "static_headers": {
+      "Authorization": "Bearer internal-server-token",
+      "X-Internal-Service": "litellm-proxy"
+    }
+  }'
+```
+
+To update an existing agent:
+
+```bash
+curl -X PATCH http://localhost:4000/v1/agents/{agent_id} \
+  -H "Authorization: Bearer sk-admin" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "static_headers": {
+      "Authorization": "Bearer new-token"
+    }
+  }'
+```
+
+</TabItem>
+</Tabs>
+
+**Client call — no special headers needed:**
+
+```bash
+curl -X POST http://localhost:4000/a2a/my-agent \
+  -H "Authorization: Bearer sk-client-key" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "jsonrpc": "2.0", "id": "1", "method": "message/send",
+    "params": { "message": { "role": "user", "parts": [{"kind": "text", "text": "Hello"}], "messageId": "msg-1" } }
+  }'
+```
+
+The backend agent receives `Authorization: Bearer internal-server-token` without the client ever knowing the value.
+
+---
+
+## Method 2 — Forward Client Headers
+
+Admin specifies a list of header **names**. When the client sends a request that includes those headers, LiteLLM extracts their values and forwards them to the backend agent. The client controls the values; the admin controls which headers are eligible to be forwarded.
+
+<Tabs>
+<TabItem value="ui" label="UI">
+
+1. Go to **Agents** in the LiteLLM dashboard.
+2. Create or edit an agent.
+3. Open the **Authentication Headers** panel.
+4. Under **Forward Client Headers**, type header names and press **Enter** (e.g. `x-api-key`, `Authorization`).
+
+</TabItem>
+<TabItem value="api" label="REST API">
+
+```bash
+curl -X POST http://localhost:4000/v1/agents \
+  -H "Authorization: Bearer sk-admin" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "agent_name": "my-agent",
+    "agent_card_params": { ... },
+    "extra_headers": ["x-api-key", "x-user-token"]
+  }'
+```
+
+</TabItem>
+</Tabs>
+
+**Client call — include the forwarded headers:**
+
+```bash
+curl -X POST http://localhost:4000/a2a/my-agent \
+  -H "Authorization: Bearer sk-client-key" \
+  -H "x-api-key: user-secret-value" \
+  -H "Content-Type: application/json" \
+  -d '{ ... }'
+```
+
+The backend agent receives `x-api-key: user-secret-value`.
+
+:::note
+Header name matching is **case-insensitive**. If the client sends `X-API-Key` and `extra_headers` lists `x-api-key`, they match.
+:::
+
+---
+
+## Method 3 — Convention-Based Forwarding
+
+Clients can forward headers to a specific agent without any admin pre-configuration by using the naming convention:
+
+```
+x-a2a-{agent_name_or_id}-{header_name}: value
+```
+
+LiteLLM parses these headers automatically and routes them to the matching agent only.
+
+**Examples:**
+
+| Client header sent | Agent name/ID | Forwarded as |
+|---|---|---|
+| `x-a2a-my-agent-authorization: Bearer tok` | `my-agent` | `authorization: Bearer tok` |
+| `x-a2a-my-agent-x-api-key: secret` | `my-agent` | `x-api-key: secret` |
+| `x-a2a-abc123-authorization: Bearer tok` | agent ID `abc123` | `authorization: Bearer tok` |
+
+```bash
+curl -X POST http://localhost:4000/a2a/my-agent \
+  -H "Authorization: Bearer sk-client-key" \
+  -H "x-a2a-my-agent-authorization: Bearer agent-specific-token" \
+  -H "Content-Type: application/json" \
+  -d '{ ... }'
+```
+
+The `x-a2a-other-agent-authorization` header sent in the same request is **not** forwarded to `my-agent` — it is silently ignored.
+
+:::tip Matches both agent name and agent ID
+Both the human-readable name (e.g. `my-agent`) and the UUID (e.g. `abc123-...`) are valid. Use whichever is convenient for the client.
+:::
+
+---
+
+## Merge Precedence
+
+When multiple methods supply the same header name, **static headers win**:
+
+```
+dynamic (forwarded/convention)  →  merged  ←  static (overlays, wins)
+```
+
+Example:
+
+| Source | `Authorization` value |
+|---|---|
+| Client sends (via `extra_headers` or convention) | `Bearer client-token` |
+| Admin-configured `static_headers` | `Bearer server-token` |
+| **What the backend agent receives** | **`Bearer server-token`** |
+
+This ensures admin-controlled credentials cannot be overridden by client requests.
+
+---
+
+## Combining All Three Methods
+
+```bash
+# Register agent with static + forwarded headers
+curl -X POST http://localhost:4000/v1/agents \
+  -H "Authorization: Bearer sk-admin" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "agent_name": "my-agent",
+    "agent_card_params": { ... },
+    "static_headers": {
+      "X-Internal-Token": "secret123"
+    },
+    "extra_headers": ["x-user-id"]
+  }'
+
+# Client call using all three mechanisms
+curl -X POST http://localhost:4000/a2a/my-agent \
+  -H "Authorization: Bearer sk-client-key" \
+  -H "x-user-id: user-42" \
+  -H "x-a2a-my-agent-x-request-id: req-abc" \
+  -H "Content-Type: application/json" \
+  -d '{ ... }'
+```
+
+The backend agent receives:
+
+```
+X-Internal-Token: secret123          ← static header (always)
+x-user-id: user-42                   ← forwarded (in extra_headers)
+x-request-id: req-abc                ← convention-based (x-a2a-my-agent-*)
+X-LiteLLM-Trace-Id: <uuid>           ← LiteLLM internal
+X-LiteLLM-Agent-Id: <agent-id>       ← LiteLLM internal
+```
+
+---
+
+## Header Isolation
+
+Each agent invocation uses an isolated HTTP connection. Headers configured for agent A are **never** sent to agent B, even if both agents are running and receiving requests simultaneously.
+
+---
+
+## API Reference
+
+### `POST /v1/agents` / `PATCH /v1/agents/{agent_id}`
+
+| Field | Type | Description |
+|---|---|---|
+| `static_headers` | `object` | `{"Header-Name": "value"}` — always forwarded |
+| `extra_headers` | `string[]` | Header names to extract from client request and forward |
+
+### Agent Response
+
+Both fields are returned in `GET /v1/agents` and `GET /v1/agents/{agent_id}`:
+
+```json
+{
+  "agent_id": "...",
+  "agent_name": "my-agent",
+  "static_headers": { "X-Internal-Token": "secret123" },
+  "extra_headers": ["x-user-id"],
+  ...
+}
+```
+
+:::caution
+`static_headers` values are stored in the database and returned by the API. Treat them as you would any credential — do not store sensitive long-lived tokens here if your API is publicly accessible. Consider using short-lived tokens or environment-injected secrets instead.
+:::
--- a/docs/my-website/docs/mcp.md
+++ b/docs/my-website/docs/mcp.md
@ -704,6 +704,63 @@ asyncio.run(main())

 [Learn more about customer management →](./proxy/customers)

+## Calling the Proxy's /v1/responses Endpoint
+
+When calling your LiteLLM Proxy's `/v1/responses` endpoint to use MCP tools, **always use `server_url: "litellm_proxy"`** in the tools array. This tells the proxy to use its configured MCP servers.
+
+:::important Do not use the full proxy URL
+Using `server_url: "https://your-proxy.com/mcp"` is incorrect when the request is already going to the proxy. The proxy needs the literal value `litellm_proxy` to route to its configured MCP servers.
+:::
+
+```bash title="Correct: Using litellm_proxy" showLineNumbers
+curl --location 'https://your-proxy.com/v1/responses' \
+--header 'Content-Type: application/json' \
+--header "Authorization: Bearer $LITELLM_API_KEY" \
+--data '{
+    "model": "gpt-4",
+    "tools": [
+        {
+            "type": "mcp",
+            "server_label": "litellm",
+            "server_url": "litellm_proxy",
+            "require_approval": "never"
+        }
+    ],
+    "input": "Run available tools",
+    "tool_choice": "required"
+}'
+```
+
+### Sending Custom Headers to MCP Servers
+
+To pass custom headers (e.g., API keys, auth tokens) to specific MCP servers, use either:
+
+**Option 1: Request headers** – Add `x-mcp-{server_alias}-{header_name}` to your request headers. The proxy forwards these to the matching MCP server.
+
+```bash
+# Send Authorization header to the "weather2" MCP server
+--header 'x-mcp-weather2-authorization: Bearer your-token'
+
+# Send custom header to the "github" MCP server  
+--header 'x-mcp-github-x-api-key: your-api-key'
+```
+
+**Option 2: Headers in tool config** – Include a `headers` object in the tool definition. These are merged with request headers.
+
+```json
+{
+    "type": "mcp",
+    "server_label": "litellm",
+    "server_url": "litellm_proxy",
+    "require_approval": "never",
+    "headers": {
+        "x-litellm-api-key": "Bearer YOUR_LITELLM_API_KEY",
+        "x-mcp-servers": "Zapier_MCP,dev-group",
+        "x-mcp-weather2-authorization": "Bearer your-weather-api-token"
+    }
+}
+```
+
 ## Using your MCP with client side credentials

 Use this if you want to pass a client side authentication token to LiteLLM to then pass to your MCP to auth to your MCP.
--- a/docs/my-website/docs/mcp_control.md
+++ b/docs/my-website/docs/mcp_control.md
@ -323,7 +323,7 @@ curl --location '<your-litellm-proxy-base-url>/v1/responses' \
        {
            "type": "mcp",
            "server_label": "litellm",
-            "server_url": "<your-litellm-proxy-base-url>/dev_group/mcp",
+            "server_url": "litellm_proxy",
            "require_approval": "never",
            "headers": {
                "x-litellm-api-key": "Bearer YOUR_LITELLM_API_KEY"
@ -335,7 +335,7 @@ curl --location '<your-litellm-proxy-base-url>/v1/responses' \
 }'
 ```

-This example uses URL namespacing to access all servers in the "dev_group" access group.
+This example uses the `x-mcp-servers` header to access all servers in the "dev_group" access group. Use `server_url: "litellm_proxy"` when calling the proxy's `/v1/responses` endpoint—do not use the full proxy URL.

 </TabItem>

@ -423,7 +423,7 @@ curl --location '<your-litellm-proxy-base-url>/v1/responses' \
        {
            "type": "mcp",
            "server_label": "litellm",
-            "server_url": "<your-litellm-proxy-base-url>/mcp/",
+            "server_url": "litellm_proxy",
            "require_approval": "never",
            "headers": {
                "x-litellm-api-key": "Bearer YOUR_LITELLM_API_KEY",
@ -436,7 +436,7 @@ curl --location '<your-litellm-proxy-base-url>/v1/responses' \
 }'
 ```

-This configuration restricts the request to only use tools from the specified MCP servers.
+This configuration restricts the request to only use tools from the specified MCP servers. Use `server_url: "litellm_proxy"` when calling the proxy's `/v1/responses` endpoint.

 </TabItem>

--- a/docs/my-website/docs/providers/azure_ai/azure_model_router.md
+++ b/docs/my-website/docs/providers/azure_ai/azure_model_router.md
@ -2,6 +2,32 @@

 Azure Model Router is a feature in Azure AI Foundry that automatically routes your requests to the best available model based on your requirements. This allows you to use a single endpoint that intelligently selects the optimal model for each request.

+## Quick Start
+
+**Model pattern**: `azure_ai/model_router/<deployment-name>`
+
+```python
+import litellm
+
+response = litellm.completion(
+    model="azure_ai/model_router/model-router",  # Replace with your deployment name
+    messages=[{"role": "user", "content": "Hello!"}],
+    api_base="https://your-endpoint.cognitiveservices.azure.com/openai/v1/",
+    api_key="your-api-key",
+)
+```
+
+**Proxy config** (`config.yaml`):
+
+```yaml
+model_list:
+  - model_name: model-router
+    litellm_params:
+      model: azure_ai/model_router/model-router
+      api_base: https://your-endpoint.cognitiveservices.azure.com/openai/deployments/model-router/chat/completions?api-version=2025-01-01-preview
+      api_key: your-api-key
+```
+
 ## Key Features

 - **Automatic Model Selection**: Azure Model Router dynamically selects the best model for your request
@ -229,19 +255,51 @@ Cost is tracked based on the actual model used (e.g., `gpt-4.1-nano`), plus a fl

 ## Cost Tracking

-LiteLLM automatically handles cost tracking for Azure Model Router by:
+LiteLLM automatically handles cost tracking for Azure Model Router. Understanding how this works helps you interpret spend and debug billing.

-1. **Detecting the actual model**: When Azure Model Router routes your request to a specific model (e.g., `gpt-4.1-nano-2025-04-14`), LiteLLM extracts this from the response
-2. **Calculating accurate costs**: Costs are calculated based on:
-   - The actual model used (e.g., `gpt-4.1-nano` token costs)
-   - Plus a flat infrastructure cost of **$0.14 per million input tokens** for using the Model Router
-3. **Streaming support**: Cost tracking works correctly for both streaming and non-streaming requests
+### How LiteLLM Calculates Cost
+
+When you use Azure Model Router, LiteLLM computes **two cost components**:
+
+| Component | Description | When Applied |
+|-----------|-------------|--------------|
+| **Model Cost** | Token-based cost for the actual model that handled the request (e.g., `gpt-5-nano`, `gpt-4.1-nano`) | Always, when Azure returns the model in the response |
+| **Router Flat Cost** | $0.14 per million input tokens (Azure AI Foundry infrastructure fee) | When the **request** was made via a model router endpoint |
+
+### Cost Calculation Flow
+
+1. **Request model detection**: LiteLLM records the model you requested (e.g., `azure_ai/model_router/model-router`). If it contains `model_router` or `model-router`, the request is treated as a router request.
+
+2. **Response model extraction**: Azure returns the actual model used in the response (e.g., `gpt-5-nano-2025-08-07`). LiteLLM uses this for the model cost lookup.
+
+3. **Model cost**: LiteLLM looks up the response model in its pricing table and computes cost from prompt tokens and completion tokens.
+
+4. **Router flat cost**: Because the original request was to a model router, LiteLLM adds the flat cost ($0.14 per M input tokens) on top of the model cost.
+
+5. **Total cost**: `Total = Model Cost + Router Flat Cost`
+
+### Configuration Requirements
+
+For cost tracking to work correctly:
+
+- **Use the full pattern**: `azure_ai/model_router/<deployment-name>` (e.g., `azure_ai/model_router/model-router`)
+- **Proxy config**: When using the LiteLLM proxy, set `model` in `litellm_params` to the full pattern so the request model is correctly identified as a router
+
+```yaml
+# proxy_server_config.yaml
+model_list:
+  - model_name: model-router
+    litellm_params:
+      model: azure_ai/model_router/model-router  # Required for router cost detection
+      api_base: https://your-endpoint.cognitiveservices.azure.com/openai/deployments/model-router/chat/completions?api-version=2025-01-01-preview
+      api_key: your-api-key
+```

 ### Cost Breakdown

 When you use Azure Model Router, the total cost includes:

- **Model Cost**: Based on the actual model that handled your request (e.g., `gpt-4.1-nano`)
+- **Model Cost**: Based on the actual model that handled your request (e.g., `gpt-5-nano`, `gpt-4.1-nano`)
 - **Router Flat Cost**: $0.14 per million input tokens (Azure AI Foundry infrastructure fee)

 ### Example Response with Cost
--- a/docs/my-website/docs/providers/chatgpt.md
+++ b/docs/my-website/docs/providers/chatgpt.md
@ -4,12 +4,12 @@ Use ChatGPT Pro/Max subscription models through LiteLLM with OAuth device flow a

 | Property | Details |
 |-------|-------|
-| Description | ChatGPT subscription access (Codex + GPT-5.2 family) via ChatGPT backend API |
+| Description | ChatGPT subscription access (Codex + GPT-5.3/5.4 family) via ChatGPT backend API |
 | Provider Route on LiteLLM | `chatgpt/` |
 | Supported Endpoints | `/responses`, `/chat/completions` (bridged to Responses for supported models) |
 | API Reference | https://chatgpt.com |

-ChatGPT subscription access is native to the Responses API. Chat Completions requests are bridged to Responses for supported models (for example `chatgpt/gpt-5.2`).
+ChatGPT subscription access is native to the Responses API. Chat Completions requests are bridged to Responses for supported models (for example `chatgpt/gpt-5.4`).

 Notes:
 - The ChatGPT subscription backend rejects token limit fields (`max_tokens`, `max_output_tokens`, `max_completion_tokens`) and `metadata`. LiteLLM strips these fields for this provider.
@ -31,7 +31,7 @@ ChatGPT subscription access uses an OAuth device code flow:
 import litellm

 response = litellm.responses(
-    model="chatgpt/gpt-5.2-codex",
+    model="chatgpt/gpt-5.3-codex",
    input="Write a Python hello world"
 )

@ -44,7 +44,7 @@ print(response)
 import litellm

 response = litellm.completion(
-    model="chatgpt/gpt-5.2",
+    model="chatgpt/gpt-5.4",
    messages=[{"role": "user", "content": "Write a Python hello world"}]
 )

@ -55,16 +55,36 @@ print(response)

 ```yaml showLineNumbers title="config.yaml"
 model_list:
-  - model_name: chatgpt/gpt-5.2
+  - model_name: chatgpt/gpt-5.4
    model_info:
      mode: responses
    litellm_params:
-      model: chatgpt/gpt-5.2
-  - model_name: chatgpt/gpt-5.2-codex
+      model: chatgpt/gpt-5.4
+  - model_name: chatgpt/gpt-5.4-pro
    model_info:
      mode: responses
    litellm_params:
-      model: chatgpt/gpt-5.2-codex
+      model: chatgpt/gpt-5.4-pro
+  - model_name: chatgpt/gpt-5.3-codex
+    model_info:
+      mode: responses
+    litellm_params:
+      model: chatgpt/gpt-5.3-codex
+  - model_name: chatgpt/gpt-5.3-codex-spark
+    model_info:
+      mode: responses
+    litellm_params:
+      model: chatgpt/gpt-5.3-codex-spark
+  - model_name: chatgpt/gpt-5.3-instant
+    model_info:
+      mode: responses
+    litellm_params:
+      model: chatgpt/gpt-5.3-instant
+  - model_name: chatgpt/gpt-5.3-chat-latest
+    model_info:
+      mode: responses
+    litellm_params:
+      model: chatgpt/gpt-5.3-chat-latest
 ```

 ```bash showLineNumbers title="Start LiteLLM Proxy"
--- a/docs/my-website/docs/providers/openai.md
+++ b/docs/my-website/docs/providers/openai.md
@ -192,8 +192,12 @@ os.environ["OPENAI_BASE_URL"] = "https://your_host/v1"     # OPTIONAL
 | gpt-5.2-2025-12-11 | `response = completion(model="gpt-5.2-2025-12-11", messages=messages)` |
 | gpt-5.2-chat-latest | `response = completion(model="gpt-5.2-chat-latest", messages=messages)` |
 | gpt-5.3-chat-latest | `response = completion(model="gpt-5.3-chat-latest", messages=messages)` |
+| gpt-5.4 | `response = completion(model="gpt-5.4", messages=messages)` |
+| gpt-5.4-2026-03-05 | `response = completion(model="gpt-5.4-2026-03-05", messages=messages)` |
 | gpt-5.2-pro | `response = completion(model="gpt-5.2-pro", messages=messages)` |
 | gpt-5.2-pro-2025-12-11 | `response = completion(model="gpt-5.2-pro-2025-12-11", messages=messages)` |
+| gpt-5.4-pro | `response = completion(model="gpt-5.4-pro", messages=messages)` |
+| gpt-5.4-pro-2026-03-05 | `response = completion(model="gpt-5.4-pro-2026-03-05", messages=messages)` |
 | gpt-5.1 | `response = completion(model="gpt-5.1", messages=messages)` |
 | gpt-5.1-codex | `response = completion(model="gpt-5.1-codex", messages=messages)` |
 | gpt-5.1-codex-mini | `response = completion(model="gpt-5.1-codex-mini", messages=messages)` |
--- a/docs/my-website/docs/providers/vertex.md
+++ b/docs/my-website/docs/providers/vertex.md
@ -1472,6 +1472,82 @@ Your WIF credentials JSON file typically looks like this (for AWS federation):

 For more details on setting up Workload Identity Federation, see [Google Cloud WIF documentation](https://cloud.google.com/iam/docs/workload-identity-federation).

+#### Explicit AWS Credentials for WIF
+
+By default, AWS-based WIF relies on the EC2 instance metadata service to obtain AWS credentials. This works when LiteLLM runs on an EC2 instance or ECS task with an IAM role attached.
+
+If your environment **does not have access to the EC2 metadata service** (e.g., running on-premises, in a container without host networking, or in a different cloud with security restrictions), you can provide explicit AWS credentials directly in the WIF credential JSON file. LiteLLM will use these to authenticate to AWS before performing the GCP token exchange.
+
+Add the `aws_*` keys at the **top level** of your WIF credential JSON (alongside `type`, `audience`, etc.):
+
+```json
+{
+  "type": "external_account",
+  "audience": "//iam.googleapis.com/projects/PROJECT_NUMBER/locations/global/workloadIdentityPools/POOL_ID/providers/PROVIDER_ID",
+  "subject_token_type": "urn:ietf:params:aws:token-type:aws4_request",
+  "service_account_impersonation_url": "https://iamcredentials.googleapis.com/v1/projects/-/serviceAccounts/SERVICE_ACCOUNT_EMAIL:generateAccessToken",
+  "token_url": "https://sts.googleapis.com/v1/token",
+  "credential_source": {
+    "environment_id": "aws1",
+    "region_url": "http://169.254.169.254/latest/meta-data/placement/availability-zone",
+    "url": "http://169.254.169.254/latest/meta-data/iam/security-credentials",
+    "regional_cred_verification_url": "https://sts.{region}.amazonaws.com?Action=GetCallerIdentity&Version=2011-06-15"
+  },
+  "aws_role_name": "arn:aws:iam::123456789012:role/MyWifRole",
+  "aws_region_name": "us-east-1"
+}
+```
+
+**Supported `aws_*` parameters:**
+
+| Parameter | Required | Description |
+|---|---|---|
+| `aws_region_name` | Yes | AWS region for credential verification (e.g. `us-east-1`) |
+| `aws_role_name` | No | IAM role ARN for STS AssumeRole |
+| `aws_access_key_id` | No | Static AWS access key ID |
+| `aws_secret_access_key` | No | Static AWS secret access key |
+| `aws_session_token` | No | Temporary session token |
+| `aws_profile_name` | No | AWS CLI profile name |
+| `aws_session_name` | No | Session name for AssumeRole |
+| `aws_web_identity_token` | No | Web identity token for STS |
+| `aws_sts_endpoint` | No | Custom STS endpoint URL |
+| `aws_external_id` | No | External ID for cross-account AssumeRole |
+
+`aws_region_name` is always required when using explicit AWS credentials. The other parameters follow the same authentication flows as [Bedrock AWS auth](/docs/providers/bedrock#authentication) -- you can use role assumption, static keys, profiles, or web identity tokens.
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+from litellm import completion
+
+response = completion(
+    model="vertex_ai/gemini-1.5-pro",
+    messages=[{"role": "user", "content": "Hello!"}],
+    vertex_credentials="/path/to/wif-credentials-with-aws.json",  # WIF JSON with aws_* keys
+    vertex_project="your-gcp-project-id",
+    vertex_location="us-central1"
+)
+```
+
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+```yaml
+model_list:
+  - model_name: gemini-model
+    litellm_params:
+      model: vertex_ai/gemini-1.5-pro
+      vertex_project: your-gcp-project-id
+      vertex_location: us-central1
+      vertex_credentials: /path/to/wif-credentials-with-aws.json  # WIF JSON with aws_* keys
+```
+
+</TabItem>
+</Tabs>
+
+When `aws_*` keys are present in the JSON, LiteLLM automatically uses explicit AWS authentication instead of the EC2 metadata service. When they are absent, the standard metadata-based flow is used unchanged.
+
 ### **Environment Variables**

 You can set:
@ -1687,6 +1763,20 @@ litellm.vertex_location = "us-central1 # Your Location
 | gemini-2.5-flash-lite-preview-09-2025   | `completion('gemini-2.5-flash-lite-preview-09-2025', messages)`, `completion('vertex_ai/gemini-2.5-flash-lite-preview-09-2025', messages)` |
 | gemini-3.1-flash-lite-preview   | `completion('gemini-3.1-flash-lite-preview', messages)`, `completion('vertex_ai/gemini-3.1-flash-lite-preview', messages)` |

+## PayGo / Priority Cost Tracking
+
+LiteLLM automatically tracks spend for Vertex AI Gemini models using the correct pricing tier based on the response's `usageMetadata.trafficType`:
+
+| Vertex AI `trafficType` | LiteLLM `service_tier` | Pricing applied |
+|-------------------------|-------------------------|-----------------|
+| `ON_DEMAND_PRIORITY` | `priority` | PayGo / priority pricing (`input_cost_per_token_priority`, `output_cost_per_token_priority`) |
+| `ON_DEMAND` | standard | Default on-demand pricing |
+| `FLEX` / `BATCH` | `flex` | Batch/flex pricing |
+
+When you use [Vertex AI PayGo](https://cloud.google.com/vertex-ai/generative-ai/pricing) (on-demand priority) or batch workloads, LiteLLM reads `trafficType` from the response and applies the matching cost per token from the [model cost map](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json). No configuration is required — spend tracking works out of the box for both standard and PayGo requests.
+
+See [Spend Tracking](../proxy/cost_tracking.md) for general cost tracking setup.
+
 ## Private Service Connect (PSC) Endpoints

 LiteLLM supports Vertex AI models deployed to Private Service Connect (PSC) endpoints, allowing you to use custom `api_base` URLs for private deployments.
--- a/docs/my-website/docs/proxy/admin_ui_sso.md
+++ b/docs/my-website/docs/proxy/admin_ui_sso.md
@ -41,12 +41,38 @@ After creating the app, copy your **Client ID** and **Client Secret** from the a

 Ensure users are assigned to the app in the **Assignments** tab. If Federation Broker Mode is enabled, you may need to disable it to assign users manually.

-#### Step 3: Configure Authorization Server Access Policy
+#### Step 3: Set Environment Variables

-:::warning Important
-This step is required. Without an Access Policy for your app, users will get a `no_matching_policy` error when attempting to log in.
+Set the following environment variables. The only difference between the two Okta authorization servers is the endpoint URLs:
+
+**Org Authorization Server** (available on all Okta plans, no additional SKU required):
+```bash
+GENERIC_CLIENT_ID="<your-client-id>"
+GENERIC_CLIENT_SECRET="<your-client-secret>"
+GENERIC_AUTHORIZATION_ENDPOINT="https://<your-okta-domain>/oauth2/v1/authorize"
+GENERIC_TOKEN_ENDPOINT="https://<your-okta-domain>/oauth2/v1/token"
+GENERIC_USERINFO_ENDPOINT="https://<your-okta-domain>/oauth2/v1/userinfo"
+PROXY_BASE_URL="https://<your-proxy-base-url>"
+```
+
+**Custom Authorization Server** (requires the Okta API Access Management SKU):
+```bash
+GENERIC_CLIENT_ID="<your-client-id>"
+GENERIC_CLIENT_SECRET="<your-client-secret>"
+GENERIC_AUTHORIZATION_ENDPOINT="https://<your-okta-domain>/oauth2/default/v1/authorize"
+GENERIC_TOKEN_ENDPOINT="https://<your-okta-domain>/oauth2/default/v1/token"
+GENERIC_USERINFO_ENDPOINT="https://<your-okta-domain>/oauth2/default/v1/userinfo"
+PROXY_BASE_URL="https://<your-proxy-base-url>"
+```
+
+:::tip
+You can find all OAuth endpoints at `https://<your-okta-domain>/.well-known/openid-configuration`
 :::

+#### Step 3a: Configure Access Policy (Custom Authorization Server only)
+
+If you are using the Custom Authorization Server, you must configure an Access Policy. Without it, users will get a `no_matching_policy` error. Skip this step if you are using the Org Authorization Server.
+
 1. Go to **Security** → **API**

 <Image img={require('../../img/okta_security_api.png')} />
@ -62,21 +88,21 @@ This step is required. Without an Access Policy for your app, users will get a `

 See [Okta's Access Policy documentation](https://help.okta.com/en-us/content/topics/security/api-access-management/access-policies.htm) for more details.

-#### Step 4: Configure LiteLLM Environment Variables
+#### Step 4: Configure Okta Security Settings
+
+**GENERIC_CLIENT_STATE** is recommended for Okta to prevent CSRF attacks:

 ```bash
-GENERIC_CLIENT_ID="<your-client-id>"
-GENERIC_CLIENT_SECRET="<your-client-secret>"
-GENERIC_AUTHORIZATION_ENDPOINT="https://<your-okta-domain>/oauth2/default/v1/authorize"
-GENERIC_TOKEN_ENDPOINT="https://<your-okta-domain>/oauth2/default/v1/token"
-GENERIC_USERINFO_ENDPOINT="https://<your-okta-domain>/oauth2/default/v1/userinfo"
 GENERIC_CLIENT_STATE="random-string"
-PROXY_BASE_URL="https://<your-proxy-base-url>"
 ```

-:::tip
-You can find all OAuth endpoints at `https://<your-okta-domain>/.well-known/openid-configuration`
-:::
+**PKCE (Proof Key for Code Exchange)** — If your Okta application is configured to require PKCE, enable it by setting:
+
+```bash
+GENERIC_CLIENT_USE_PKCE="true"
+```
+
+LiteLLM will automatically handle PKCE parameter generation and verification during the OAuth flow.

 #### Step 5: Test the SSO Flow

@ -91,7 +117,7 @@ You can find all OAuth endpoints at `https://<your-okta-domain>/.well-known/open
 |-------|-------|----------|
 | `redirect_uri` error | Redirect URI not configured | Add `<proxy_base_url>/sso/callback` to Sign-in redirect URIs in Okta |
 | `access_denied` | User not assigned to app | Assign the user in the Assignments tab |
-| `no_matching_policy` | Missing Access Policy | Create an Access Policy in the Authorization Server (see Step 3) |
+| `no_matching_policy` | Missing Access Policy (Custom Authorization Server only) | Create an Access Policy in the Authorization Server (see Step 3a) |

 </TabItem>
 <TabItem value="google" label="Google SSO">
@ -456,23 +482,9 @@ PROXY_BASE_URL=http://litellm.platform.com
 PROXY_BASE_URL=litellm.platform.com
 ```

-**2. For Okta specifically, ensure GENERIC_CLIENT_STATE is set**
+**2. For Okta specifically, ensure `GENERIC_CLIENT_STATE` is set and PKCE is configured if required**

-Okta requires the `GENERIC_CLIENT_STATE` parameter:
-
-```bash
-GENERIC_CLIENT_STATE="random-string" # Required for Okta
-```
-
-### Okta PKCE
-
-If your Okta application is configured to require PKCE (Proof Key for Code Exchange), enable it by setting:
-
-```bash
-GENERIC_CLIENT_USE_PKCE="true"
-```
-
-This is required when your Okta app settings enforce PKCE for enhanced security. LiteLLM will automatically handle PKCE parameter generation and verification during the OAuth flow.
+See [Okta SSO — Step 4: Configure Okta Security Settings](#step-4-configure-okta-security-settings) for details on `GENERIC_CLIENT_STATE` and PKCE configuration.

 ### Common Configuration Issues

--- a/docs/my-website/docs/proxy/config_settings.md
+++ b/docs/my-website/docs/proxy/config_settings.md
@ -199,6 +199,7 @@ router_settings:
 | use_chat_completions_url_for_anthropic_messages | boolean | If true, routes OpenAI `/v1/messages` requests through chat/completions instead of the Responses API. Can also be set via env var `LITELLM_USE_CHAT_COMPLETIONS_URL_FOR_ANTHROPIC_MESSAGES=true`. |
 | disable_hf_tokenizer_download | boolean | If true, it defaults to using the openai tokenizer for all models (including huggingface models). |
 | enable_json_schema_validation | boolean | If true, enables json schema validation for all requests. |
+| enable_key_alias_format_validation | boolean | If true, validates `key_alias` format on `/key/generate` and `/key/update`. Must be 2-255 chars, start/end with alphanumeric, only allow `a-zA-Z0-9_-/.@`. Default `false`. |
 | disable_copilot_system_to_assistant | boolean | **DEPRECATED** - GitHub Copilot API supports system prompts. |

 ### general_settings - Reference
@ -815,6 +816,7 @@ router_settings:
 | LITELLM_TOKEN | Access token for LiteLLM integration
 | LITELLM_USE_CHAT_COMPLETIONS_URL_FOR_ANTHROPIC_MESSAGES | When set to "true", routes OpenAI /v1/messages requests through chat/completions instead of the Responses API for Anthropic models. Can also be set via `litellm_settings.use_chat_completions_url_for_anthropic_messages`
 | LITELLM_USER_AGENT | Custom user agent string for LiteLLM API requests. Used for partner telemetry attribution
+| LITELLM_WORKER_STARTUP_HOOKS | Comma-separated list of `module.path:function_name` callables to run in each worker process during startup. Runs early in the worker lifecycle (before config/DB loading). Useful for re-initializing per-process state like [gflags](https://github.com/google/python-gflags). See [Worker Startup Hooks](/proxy/worker_startup_hooks) for details
 | LITELLM_PRINT_STANDARD_LOGGING_PAYLOAD | If true, prints the standard logging payload to the console - useful for debugging
 | LITELM_ENVIRONMENT | Environment for LiteLLM Instance. This is currently only logged to DeepEval to determine the environment for DeepEval integration.
 | LITELLM_ASYNCIO_QUEUE_MAXSIZE | Maximum size for asyncio queues (e.g. log queues, spend update queues, and cookbook examples such as realtime audio in `nova_sonic_realtime.py`). Bounds in-memory growth to prevent OOM. Default is 1000.
@ -918,6 +920,7 @@ router_settings:
 | PRISMA_HEALTH_WATCHDOG_INTERVAL_SECONDS | Interval in seconds for Prisma health watchdog probes. Default is 30
 | PRISMA_HEALTH_WATCHDOG_PROBE_TIMEOUT_SECONDS | Timeout in seconds for each Prisma health probe. Default is 5.0
 | PRISMA_RECONNECT_COOLDOWN_SECONDS | Cooldown in seconds between Prisma reconnection attempts. Default is 15
+| PRISMA_RECONNECT_ESCALATION_THRESHOLD | Number of consecutive reconnect failures before escalating the reconnection strategy. Default is 3
 | PRISMA_WATCHDOG_RECONNECT_TIMEOUT_SECONDS | Timeout in seconds for Prisma watchdog-initiated reconnection. Default is 30.0
 | PREDIBASE_API_BASE | Base URL for Predibase API
 | PRESIDIO_ANALYZER_API_BASE | Base URL for Presidio Analyzer service
@ -940,6 +943,7 @@ router_settings:
 | QDRANT_URL | Connection URL for Qdrant database
 | QDRANT_VECTOR_SIZE | Vector size for Qdrant operations. Default is 1536
 | REDIS_CONNECTION_POOL_TIMEOUT | Timeout in seconds for Redis connection pool. Default is 5
+| REDIS_CLUSTER_NODES | JSON-formatted list of Redis cluster startup nodes for Redis Cluster mode. Example: '[{"host": "node1", "port": 6379}]'
 | REDIS_HOST | Hostname for Redis server
 | REDIS_PASSWORD | Password for Redis service
 | REDIS_PORT | Port number for Redis server
--- a/docs/my-website/docs/proxy/cost_tracking.md
+++ b/docs/my-website/docs/proxy/cost_tracking.md
@ -8,6 +8,8 @@ Track spend for keys, users, and teams across 100+ LLMs.

 LiteLLM automatically tracks spend for all known models. See our [model cost map](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json)

+Provider-specific cost tracking (e.g., [Vertex AI PayGo / priority pricing](../providers/vertex.md#paygo--priority-cost-tracking), [Bedrock service tiers](../providers/bedrock.md#usage---service-tier), [Azure base model mapping](./custom_pricing.md#set-base_model-for-cost-tracking-eg-azure-deployments)) is applied automatically when the response includes tier metadata.
+
 :::tip Keep Pricing Data Updated
 [Sync model pricing data from GitHub](./sync_models_github.md) to ensure accurate cost tracking.
 :::
--- a/docs/my-website/docs/proxy/custom_pricing.md
+++ b/docs/my-website/docs/proxy/custom_pricing.md
@ -104,9 +104,18 @@ There are other keys you can use to specify costs for different scenarios and mo
 - `input_cost_per_video_per_second` - Cost per second of video input
 - `input_cost_per_video_per_second_above_128k_tokens` - Video cost for large contexts
 - `input_cost_per_character` - Character-based pricing for some providers
+- `input_cost_per_token_priority` / `output_cost_per_token_priority` - Priority/PayGo pricing (Vertex AI Gemini, Bedrock)
+- `input_cost_per_token_flex` / `output_cost_per_token_flex` - Batch/flex pricing

 These keys evolve based on how new models handle multimodality. The latest version can be found at [https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json).

+### Service Tier / PayGo Pricing (Vertex AI, Bedrock)
+
+For providers that support multiple pricing tiers (e.g., Vertex AI PayGo, Bedrock service tiers), LiteLLM automatically applies the correct cost based on the response:
+
+- **Vertex AI Gemini**: Uses `usageMetadata.trafficType` (`ON_DEMAND_PRIORITY` → priority, `FLEX`/`BATCH` → flex). See [Vertex AI - PayGo / Priority Cost Tracking](../providers/vertex.md#paygo--priority-cost-tracking).
+- **Bedrock**: Uses `serviceTier` from the response. See [Bedrock - Usage - Service Tier](../providers/bedrock.md#usage---service-tier).
+
 ## Zero-Cost Models (Bypass Budget Checks)

 **Use Case**: You have on-premises or free models that should be accessible even when users exceed their budget limits.
--- a/docs/my-website/docs/proxy/custom_sso.md
+++ b/docs/my-website/docs/proxy/custom_sso.md
@ -121,15 +121,14 @@ Use this if you want to run your own code **after** a user signs on to the LiteL
 Make sure the response type follows the `SSOUserDefinedValues` pydantic object. This is used for logging the user into the Admin UI:

 ```python
-from fastapi import Request
 from fastapi_sso.sso.base import OpenID

 from litellm.proxy._types import LitellmUserRoles, SSOUserDefinedValues
-from litellm.proxy.management_endpoints.internal_user_endpoints import (
-    new_user,
-    user_info,
-)
-from litellm.proxy.management_endpoints.team_endpoints import add_new_member
+from litellm.proxy import proxy_server
+
+# These imports are available if you need to create users or manage team membership:
+# from litellm.proxy.management_endpoints.internal_user_endpoints import new_user
+# from litellm.proxy.management_endpoints.team_endpoints import add_new_member


 async def custom_sso_handler(userIDPInfo: OpenID) -> SSOUserDefinedValues:
@ -158,8 +157,9 @@ async def custom_sso_handler(userIDPInfo: OpenID) -> SSOUserDefinedValues:
        #################################################
        # Run your custom code / logic here
        # check if user exists in litellm proxy DB
-        _user_info = await user_info(user_id=userIDPInfo.id)
-        print("_user_info from litellm DB ", _user_info)  # noqa
+        if proxy_server.prisma_client is not None:
+            _user_info = await proxy_server.prisma_client.get_data(user_id=userIDPInfo.id)
+            print("_user_info from litellm DB ", _user_info)  # noqa
        #################################################

        return SSOUserDefinedValues(
--- a/docs/my-website/docs/proxy/forward_client_headers.md
+++ b/docs/my-website/docs/proxy/forward_client_headers.md
@ -112,6 +112,8 @@ general_settings:
  forward_llm_provider_auth_headers: true  # Enable BYOK
 ```

+For **Claude Code** with `/login` and your own Anthropic key, see [Claude Code BYOK](../tutorials/claude_code_byok.md). Use `ANTHROPIC_CUSTOM_HEADERS="x-litellm-api-key: sk-12345"` to pass your LiteLLM key while your Anthropic key (from `/login`) is forwarded as `x-api-key`.
+
 Client request:
 ```bash
 curl -X POST "http://localhost:4000/v1/messages" \
--- a/docs/my-website/docs/proxy/guardrails/quick_start.md
+++ b/docs/my-website/docs/proxy/guardrails/quick_start.md
@ -497,7 +497,7 @@ curl --location 'http://0.0.0.0:4000/chat/completions' \

 Run guardrails based on the user-agent header. This is useful for running pre-call checks on OpenWebUI but only masking in logs for Claude CLI.

-`default` can be a single mode string or a list of modes.
+Both `default` and tag values can be a single mode string or a list of modes.

 <Tabs>
 <TabItem value="single" label="Single Default Mode">
@ -545,6 +545,29 @@ guardrails:
      default_on: true
 ```

+</TabItem>
+<TabItem value="tag-list" label="Multiple Tag Modes">
+
+```yaml
+model_list:
+  - model_name: gpt-3.5-turbo
+    litellm_params:
+      model: gpt-3.5-turbo
+      api_key: os.environ/OPENAI_API_KEY
+
+guardrails:
+  - guardrail_name: "guardrails_ai-guard"
+    litellm_params:
+      guardrail: guardrails_ai
+      guard_name: "pii_detect"
+      mode:
+        tags:
+            "User-Agent: claude-cli": ["pre_call", "post_call"]  # Run both pre and post call for claude-cli
+        default: "logging_only"  # Default to logging only when no tags match
+      api_base: os.environ/GUARDRAILS_AI_API_BASE
+      default_on: true
+```
+
 </TabItem>
 </Tabs>

@ -669,7 +692,7 @@ guardrails:

 Mode Specification

-`default` accepts either a single string or a list of strings.
+Both `default` and tag values accept either a single string or a list of strings.

 ```python
 from litellm.types.guardrails import Mode
@ -685,6 +708,12 @@ mode = Mode(
    tags={"User-Agent: claude-cli": "logging_only"},
    default=["pre_call", "post_call"]
 )
+
+# Multiple modes on a tag value
+mode = Mode(
+    tags={"User-Agent: claude-cli": ["pre_call", "post_call"]},
+    default="logging_only"
+)
 ```

 ### `guardrails` Request Parameter
--- a/docs/my-website/docs/proxy/worker_startup_hooks.md
+++ b/docs/my-website/docs/proxy/worker_startup_hooks.md
@ -0,0 +1,155 @@
+# Worker Startup Hooks
+
+Use `LITELLM_WORKER_STARTUP_HOOKS` to run custom initialization functions in **each worker process** during proxy startup. This is essential when using multi-worker deployments (`--num_workers > 1`) with libraries that require per-process initialization, such as [gflags](https://github.com/google/python-gflags).
+
+## The Problem
+
+When running the LiteLLM proxy with multiple workers:
+
+```bash
+litellm --config config.yaml --num_workers 4
+```
+
+Each worker is a **separate process** spawned by uvicorn or gunicorn. Any in-process state initialized in the master process (before `run_server()`) is **not available** in worker processes. This includes:
+
+- [python-gflags](https://github.com/google/python-gflags) (`gflags.FLAGS`)
+- [absl-py flags](https://abseil.io/docs/python/guides/flags) (`absl.flags.FLAGS`)
+- Custom singleton registries or connection pools
+- Any module-level state that requires explicit initialization
+
+## Usage
+
+Set the `LITELLM_WORKER_STARTUP_HOOKS` environment variable to a comma-separated list of `module.path:function_name` callables:
+
+```bash
+export LITELLM_WORKER_STARTUP_HOOKS="my_module:my_init_function"
+```
+
+Each hook is called **early** in the worker startup lifecycle — before config loading, database setup, or any request handling. Both sync and async functions are supported.
+
+## Example: gflags Initialization
+
+### 1. Define your wrapper module
+
+```python title="my_litellm_wrapper.py"
+import gflags
+import json
+import os
+import sys
+from typing import Optional, List, Any
+
+
+def init_gflags(
+    usage: Optional[Any] = None,
+    raw_args: Optional[List[str]] = None,
+    known_only: bool = False,
+) -> List[str]:
+    """Initialize gflags from command-line arguments."""
+    try:
+        gflags.FLAGS.set_gnu_getopt(True)
+        if raw_args is None:
+            raw_args = sys.argv
+        argv = gflags.FLAGS(raw_args, known_only=known_only)
+    except gflags.Error as e:
+        if usage is None:
+            print("%s\nUsage: %s ARGS\n%s" % (e, sys.argv[0], gflags.FLAGS))
+        else:
+            print(usage % dict(cmd=sys.argv[0], flags=gflags.FLAGS))
+        sys.exit(1)
+    return argv
+
+
+def init_gflags_for_worker():
+    """Re-initialize gflags in each worker process.
+
+    Reads the original sys.argv from the GFLAGS_ARGV env var
+    (set by the master process before starting the proxy).
+    """
+    raw_args = json.loads(os.environ.get("GFLAGS_ARGV", "[]")) or sys.argv
+    init_gflags(raw_args=raw_args, known_only=True)
+```
+
+### 2. Start the proxy
+
+```python title="start_proxy.py"
+import json
+import os
+import sys
+
+from my_litellm_wrapper import init_gflags
+
+# Store sys.argv so workers can re-parse the same flags
+os.environ["GFLAGS_ARGV"] = json.dumps(sys.argv)
+
+# Tell LiteLLM to call our hook in each worker
+os.environ["LITELLM_WORKER_STARTUP_HOOKS"] = "my_litellm_wrapper:init_gflags_for_worker"
+
+# Initialize gflags in the master process
+init_gflags()
+
+# Start the proxy (programmatic invocation)
+from litellm.proxy.proxy_cli import run_server
+
+run_server(
+    ["--config", "config.yaml", "--num_workers", "4"],
+    standalone_mode=False,
+)
+```
+
+Or via shell:
+
+```bash
+export GFLAGS_ARGV='["my_app", "--my_flag=value", "--batch_size=32"]'
+export LITELLM_WORKER_STARTUP_HOOKS="my_litellm_wrapper:init_gflags_for_worker"
+
+litellm --config config.yaml --num_workers 4
+```
+
+## How It Works
+
+```
+Master Process                          Worker Process (×N)
+─────────────────                       ──────────────────────
+1. init_gflags()                        3. proxy_startup_event():
+2. run_server()                            → Read LITELLM_WORKER_STARTUP_HOOKS
+   → sets env vars                         → Import & call each hook
+   → uvicorn.run(workers=N)                  (gflags.FLAGS re-initialized ✓)
+   → spawns workers ──────────────────►    → Continue with config/DB setup
+                                           → Ready to serve requests
+```
+
+- Hooks run at the **very beginning** of `proxy_startup_event` (the FastAPI lifespan), before config loading, database connections, or any other initialization.
+- Environment variables set in the master process are **inherited** by worker processes (standard Unix fork/spawn behavior).
+- If a hook **raises an exception**, the worker fails to start — this is intentional, since missing initialization (e.g., uninitialized gflags) would cause downstream errors.
+
+## Multiple Hooks
+
+Separate multiple hooks with commas:
+
+```bash
+export LITELLM_WORKER_STARTUP_HOOKS="my_module:init_gflags,my_module:init_metrics,my_module:init_connections"
+```
+
+Hooks are executed **in order**, left to right.
+
+## Async Hooks
+
+Async functions are also supported — they are automatically awaited:
+
+```python
+async def init_async_connections():
+    """Example async hook for initializing async resources."""
+    await setup_async_connection_pool()
+```
+
+```bash
+export LITELLM_WORKER_STARTUP_HOOKS="my_module:init_async_connections"
+```
+
+## Reference
+
+| Environment Variable | Description |
+|---|---|
+| `LITELLM_WORKER_STARTUP_HOOKS` | Comma-separated `module.path:function_name` callables to run in each worker on startup |
+
+The hook format follows the standard Python entry point syntax: `module.path:function_name`, where `module.path` is a dotted Python import path and `function_name` is the name of the callable within that module.
--- a/docs/my-website/docs/tutorials/claude_code_byok.md
+++ b/docs/my-website/docs/tutorials/claude_code_byok.md
@ -0,0 +1,123 @@
+# Claude Code with Bring Your Own Key (BYOK)
+
+Use Claude Code with your own Anthropic API key through the LiteLLM proxy. When you use Claude's `/login` with your Anthropic account, your API key is sent as `x-api-key`. With BYOK enabled, LiteLLM forwards your key to Anthropic instead of using proxy-configured keys — so you pay Anthropic directly while still benefiting from LiteLLM's routing, logging, and guardrails.
+
+## How It Works
+
+1. **Claude Code `/login`** — You sign in with your Anthropic account; Claude Code sends your Anthropic API key as `x-api-key`.
+2. **LiteLLM authentication** — You pass your LiteLLM proxy key via `ANTHROPIC_CUSTOM_HEADERS` so the proxy can authenticate and track your usage.
+3. **Key forwarding** — With `forward_llm_provider_auth_headers: true`, LiteLLM forwards your `x-api-key` to Anthropic, giving it precedence over any proxy-configured keys.
+
+## Prerequisites
+
+- [Claude Code](https://docs.anthropic.com/en/docs/claude-code/overview) installed
+- Anthropic API key (from [console.anthropic.com](https://console.anthropic.com))
+- LiteLLM proxy with a virtual key for authentication
+
+## Step 1: Configure LiteLLM Proxy
+
+Enable forwarding of LLM provider auth headers so your Anthropic key takes precedence:
+
+```yaml title="config.yaml"
+model_list:
+  - model_name: claude-sonnet-4-5
+    litellm_params:
+      model: anthropic/claude-sonnet-4-5
+      # No api_key needed — client's key will be used
+
+litellm_settings:
+  forward_llm_provider_auth_headers: true  # Required for BYOK
+```
+
+:::info Why `forward_llm_provider_auth_headers`?
+
+By default, LiteLLM strips `x-api-key` from client requests for security. Setting this to `true` allows client-provided provider keys (like your Anthropic key from `/login`) to be forwarded to Anthropic, overriding any proxy-configured keys.
+
+:::
+
+## Step 2: Create a LiteLLM Virtual Key
+
+Create a virtual key in the LiteLLM UI or via API. 
+```bash
+# Example: Create key via API
+curl -X POST "http://localhost:4000/key/generate" \
+  -H "Authorization: Bearer sk-your-master-key" \
+  -H "Content-Type: application/json" \
+  -d '{"key_alias": "claude-code-byok", "models": ["claude-sonnet-4-5"]}'
+```
+
+## Step 3: Configure Claude Code
+
+Set environment variables so Claude Code uses LiteLLM and sends your LiteLLM key for proxy auth:
+
+```bash
+# Point Claude Code to your LiteLLM proxy
+export ANTHROPIC_BASE_URL="http://localhost:4000"
+
+# Model name from your config
+export ANTHROPIC_MODEL="claude-sonnet-4-5"
+
+# LiteLLM proxy auth — this is added to every request
+# Use x-litellm-api-key so the proxy authenticates you; your Anthropic key goes via x-api-key from /login
+export ANTHROPIC_CUSTOM_HEADERS="x-litellm-api-key: sk-12345"
+```
+
+Replace `sk-12345` with your actual LiteLLM virtual key.
+
+:::tip Multiple headers
+
+For multiple headers, use newline-separated values:
+
+```bash
+export ANTHROPIC_CUSTOM_HEADERS="x-litellm-api-key: sk-12345
+x-litellm-user-id: my-user-id"
+```
+
+:::
+
+## Step 4: Sign In with Claude Code
+
+1. Launch Claude Code:
+
+   ```bash
+   claude
+   ```
+
+2. Use **`/login`** and sign in with your Anthropic account (or use your API key directly).
+
+3. Claude Code will send:
+   - `x-api-key`: Your Anthropic API key (from `/login`)
+   - `x-litellm-api-key`: Your LiteLLM key (from `ANTHROPIC_CUSTOM_HEADERS`)
+
+4. LiteLLM authenticates you via `x-litellm-api-key`, then forwards `x-api-key` to Anthropic. Your Anthropic key takes precedence over any proxy-configured key.
+
+## Summary
+
+| Header | Source | Purpose |
+|--------|--------|---------|
+| `x-api-key` | Claude Code `/login` (Anthropic key) | Sent to Anthropic for API calls |
+| `x-litellm-api-key` | `ANTHROPIC_CUSTOM_HEADERS` | Proxy authentication, tracking, rate limits |
+
+## Troubleshooting
+
+### Requests fail with "invalid x-api-key"
+
+- Ensure `forward_llm_provider_auth_headers: true` is set in `litellm_settings` (or `general_settings`).
+- Restart the LiteLLM proxy after changing the config.
+- Verify you completed `/login` in Claude Code so your Anthropic key is being sent.
+
+### Proxy returns 401
+
+- Check that `ANTHROPIC_CUSTOM_HEADERS` includes `x-litellm-api-key: <your-key>`.
+- Ensure the LiteLLM key is valid and has access to the model.
+
+### Proxy key is used instead of my Anthropic key
+
+- Confirm `forward_llm_provider_auth_headers: true` is in your config.
+- The setting can be in `litellm_settings` or `general_settings` depending on your config structure.
+- Enable debug logging: `LITELLM_LOG=DEBUG` to see which key is being forwarded.
+
+## Related
+
+- [Forward Client Headers](./../proxy/forward_client_headers.md) — Full BYOK and header forwarding docs
+- [Claude Code Max Subscription](./claude_code_max_subscription.md) — Using Claude Code with OAuth/Max subscription through LiteLLM
--- a/docs/my-website/img/claude_code_byok_screenshot.png
+++ b/docs/my-website/img/claude_code_byok_screenshot.png
--- a/docs/my-website/package-lock.json
+++ b/docs/my-website/package-lock.json
@ -7449,15 +7449,6 @@
        "tslib": "^2.6.2"
      }
    },
-    "node_modules/@trysound/sax": {
-      "version": "0.2.0",
-      "resolved": "https://registry.npmjs.org/@trysound/sax/-/sax-0.2.0.tgz",
-      "integrity": "sha512-L7z9BgrNEcYyUYtF+HaEfiS5ebkh9jXqbszz7pC0hRBPaatV0XjSD3+eHrpqFemQfgwiFF0QPIarnIihIDn7OA==",
-      "license": "ISC",
-      "engines": {
-        "node": ">=10.13.0"
-      }
-    },
    "node_modules/@types/body-parser": {
      "version": "1.19.6",
      "resolved": "https://registry.npmjs.org/@types/body-parser/-/body-parser-1.19.6.tgz",
@ -10340,13 +10331,13 @@
      }
    },
    "node_modules/css-tree": {
-      "version": "2.3.1",
-      "resolved": "https://registry.npmjs.org/css-tree/-/css-tree-2.3.1.tgz",
-      "integrity": "sha512-6Fv1DV/TYw//QF5IzQdqsNDjx/wc8TrMBZsqjL9eW01tWb7R7k/mq+/VXfJCl7SoD5emsJop9cOByJZfs8hYIw==",
+      "version": "3.2.1",
+      "resolved": "https://registry.npmjs.org/css-tree/-/css-tree-3.2.1.tgz",
+      "integrity": "sha512-X7sjQzceUhu1u7Y/ylrRZFU2FS6LRiFVp6rKLPg23y3x3c3DOKAwuXGDp+PAGjh6CSnCjYeAul8pcT8bAl+lSA==",
      "license": "MIT",
      "dependencies": {
-        "mdn-data": "2.0.30",
-        "source-map-js": "^1.0.1"
+        "mdn-data": "2.27.1",
+        "source-map-js": "^1.2.1"
      },
      "engines": {
        "node": "^10 || ^12.20.0 || ^14.13.0 || >=15.0.0"
@ -11363,10 +11354,13 @@
      }
    },
    "node_modules/dompurify": {
-      "version": "3.3.0",
-      "resolved": "https://registry.npmjs.org/dompurify/-/dompurify-3.3.0.tgz",
-      "integrity": "sha512-r+f6MYR1gGN1eJv0TVQbhA7if/U7P87cdPl3HN5rikqaBSBxLiCb/b9O+2eG0cxz0ghyU+mU1QkbsOwERMYlWQ==",
+      "version": "3.3.2",
+      "resolved": "https://registry.npmjs.org/dompurify/-/dompurify-3.3.2.tgz",
+      "integrity": "sha512-6obghkliLdmKa56xdbLOpUZ43pAR6xFy1uOrxBaIDjT+yaRuuybLjGS9eVBoSR/UPU5fq3OXClEHLJNGvbxKpQ==",
      "license": "(MPL-2.0 OR Apache-2.0)",
+      "engines": {
+        "node": ">=20"
+      },
      "optionalDependencies": {
        "@types/trusted-types": "^2.0.7"
      }
@ -14704,9 +14698,9 @@
      }
    },
    "node_modules/mdn-data": {
-      "version": "2.0.30",
-      "resolved": "https://registry.npmjs.org/mdn-data/-/mdn-data-2.0.30.tgz",
-      "integrity": "sha512-GaqWWShW4kv/G9IEucWScBx9G1/vsFZZJUO+tD26M8J8z3Kw5RDQjaoZe03YAClgeS/SWPOcb4nkFBTEi5DUEA==",
+      "version": "2.27.1",
+      "resolved": "https://registry.npmjs.org/mdn-data/-/mdn-data-2.27.1.tgz",
+      "integrity": "sha512-9Yubnt3e8A0OKwxYSXyhLymGW4sCufcLG6VdiDdUGVkPhpqLxlvP5vl1983gQjJl3tqbrM731mjaZaP68AgosQ==",
      "license": "CC0-1.0"
    },
    "node_modules/media-typer": {
@ -20409,6 +20403,13 @@
        "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",
@ -21381,24 +21382,24 @@
      "license": "MIT"
    },
    "node_modules/svgo": {
-      "version": "3.3.2",
-      "resolved": "https://registry.npmjs.org/svgo/-/svgo-3.3.2.tgz",
-      "integrity": "sha512-OoohrmuUlBs8B8o6MB2Aevn+pRIH9zDALSR+6hhqVfa6fRwG/Qw9VUMSMW9VNg2CFc/MTIfabtdOVl9ODIJjpw==",
+      "version": "4.0.1",
+      "resolved": "https://registry.npmjs.org/svgo/-/svgo-4.0.1.tgz",
+      "integrity": "sha512-XDpWUOPC6FEibaLzjfe0ucaV0YrOjYotGJO1WpF0Zd+n6ZGEQUsSugaoLq9QkEZtAfQIxT42UChcssDVPP3+/w==",
      "license": "MIT",
      "dependencies": {
-        "@trysound/sax": "0.2.0",
-        "commander": "^7.2.0",
+        "commander": "^11.1.0",
        "css-select": "^5.1.0",
-        "css-tree": "^2.3.1",
+        "css-tree": "^3.0.1",
        "css-what": "^6.1.0",
        "csso": "^5.0.5",
-        "picocolors": "^1.0.0"
+        "picocolors": "^1.1.1",
+        "sax": "^1.5.0"
      },
      "bin": {
-        "svgo": "bin/svgo"
+        "svgo": "bin/svgo.js"
      },
      "engines": {
-        "node": ">=14.0.0"
+        "node": ">=16"
      },
      "funding": {
        "type": "opencollective",
@ -21406,12 +21407,12 @@
      }
    },
    "node_modules/svgo/node_modules/commander": {
-      "version": "7.2.0",
-      "resolved": "https://registry.npmjs.org/commander/-/commander-7.2.0.tgz",
-      "integrity": "sha512-QrWXB+ZQSVPmIWIhtEO9H+gwHaMGYiF5ChvoJ+K9ZGHG/sVsa6yiesAD1GC/x46sET00Xlwo1u49RVVVzvcSkw==",
+      "version": "11.1.0",
+      "resolved": "https://registry.npmjs.org/commander/-/commander-11.1.0.tgz",
+      "integrity": "sha512-yPVavfyCcRhmorC7rWlkHn15b4wDVgVmBA7kV4QVBsF7kv/9TKJAbAXVTxvTnwP8HHKjRCJDClKbciiYS7p0DQ==",
      "license": "MIT",
      "engines": {
-        "node": ">= 10"
+        "node": ">=16"
      }
    },
    "node_modules/tailwind-merge": {
--- a/docs/my-website/package.json
+++ b/docs/my-website/package.json
@ -61,7 +61,7 @@
    "mermaid": ">=11.10.0",
    "gray-matter": "4.0.3",
    "glob": ">=11.1.0",
-    "tar": ">=7.5.8",
+    "tar": ">=7.5.10",
    "minimatch": ">=10.2.4",
    "diff": ">=8.0.3",
    "@isaacs/brace-expansion": ">=5.0.1",
@ -93,6 +93,8 @@
    "axios": ">=0.30.2",
    "webpack": ">=5.94.0",
    "serve-static": ">=1.16.0",
-    "path-to-regexp": ">=0.1.12"
+    "path-to-regexp": ">=0.1.12",
+    "dompurify": ">=3.3.2",
+    "svgo": ">=3.3.3"
  }
 }
--- a/docs/my-website/sidebars.js
+++ b/docs/my-website/sidebars.js
@ -154,6 +154,7 @@ const sidebars = {
          items: [
            "tutorials/claude_responses_api",
            "tutorials/claude_code_max_subscription",
+            "tutorials/claude_code_byok",
            "tutorials/claude_code_customer_tracking",
            "tutorials/claude_code_prompt_cache_routing",
            "tutorials/claude_code_websearch",
@ -310,6 +311,7 @@ const sidebars = {
            "proxy/master_key_rotations",
            "proxy/model_management",
            "proxy/prod",
+            "proxy/worker_startup_hooks",
            "proxy/release_cycle",
          ],
        },
@ -538,6 +540,7 @@ const sidebars = {
          items: [
            "a2a",
            "a2a_invoking_agents",
+            "a2a_agent_headers",
            "a2a_cost_tracking",
            "a2a_agent_permissions",
            "a2a_iteration_budgets"
--- a/enterprise/litellm_enterprise/integrations/custom_guardrail.py
+++ b/enterprise/litellm_enterprise/integrations/custom_guardrail.py
@ -50,8 +50,10 @@ class EnterpriseCustomGuardrailHelper:
                    break

        if matched_mode is not None:
-            # Tag matched: only run if event_type matches the tag's mode value
+            # Tag matched: only run if event_type matches the tag's mode value(s)
            if event_type is not None:
+                if isinstance(matched_mode, list):
+                    return event_type.value in matched_mode
                return event_type.value == matched_mode
            return True

--- a/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py
+++ b/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py
@ -78,8 +78,6 @@ class CheckBatchCost:
                "status": {"not_in": ["failed", "expired", "cancelled"]}
            }
        )
-        completed_jobs = []
-
        for job in jobs:
            # get the model from the job
            unified_object_id = job.unified_object_id
@ -237,10 +235,16 @@ class CheckBatchCost:
                )

                # mark the job as complete
-                completed_jobs.append(job)
-
-            if len(completed_jobs) > 0:
-                await self.prisma_client.db.litellm_managedobjecttable.update_many(
-                    where={"id": {"in": [job.id for job in completed_jobs]}},
-                    data={"batch_processed": True, "status": "complete"},
-                )
+                try:
+                    await self.prisma_client.db.litellm_managedobjecttable.update(
+                        where={"id": job.id},
+                        data={
+                            "batch_processed": True,
+                            "status": "complete",
+                            "file_object": response.model_dump_json(),
+                        },
+                    )
+                except Exception as db_err:
+                    verbose_proxy_logger.error(
+                        f"CheckBatchCost: failed to mark job {job.id} complete in DB: {db_err}"
+                    )
--- a/litellm-js/spend-logs/package.json
+++ b/litellm-js/spend-logs/package.json
@ -12,8 +12,8 @@
  },
  "overrides": {
    "glob": ">=11.1.0",
-    "tar": ">=7.5.8",
-    "minimatch": ">=10.2.1",
+    "tar": ">=7.5.10",
+    "minimatch": ">=10.2.4",
    "diff": ">=8.0.3",
    "@isaacs/brace-expansion": ">=5.0.1",
    "@babel/traverse": ">=7.23.2",
--- a/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.51-py3-none-any.whl
+++ b/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.51-py3-none-any.whl
--- a/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.51.tar.gz
+++ b/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.51.tar.gz
--- a/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.52-py3-none-any.whl
+++ b/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.52-py3-none-any.whl
--- a/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.52.tar.gz
+++ b/litellm-proxy-extras/dist/litellm_proxy_extras-0.4.52.tar.gz
--- a/litellm-proxy-extras/litellm_proxy_extras/migrations/20260305000000_add_agent_headers/migration.sql
+++ b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260305000000_add_agent_headers/migration.sql
@ -0,0 +1,5 @@
+-- Add static_headers and extra_headers to LiteLLM_AgentsTable
+
+ALTER TABLE "LiteLLM_AgentsTable"
+  ADD COLUMN IF NOT EXISTS "static_headers" JSONB DEFAULT '{}',
+  ADD COLUMN IF NOT EXISTS "extra_headers"  TEXT[] DEFAULT ARRAY[]::TEXT[];
--- a/litellm-proxy-extras/litellm_proxy_extras/migrations/20260306175056_add_configs_override_table/migration.sql
+++ b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260306175056_add_configs_override_table/migration.sql
@ -0,0 +1,3 @@
+-- AlterTable
+ALTER TABLE "LiteLLM_MCPServerTable" ADD COLUMN     "spec_path" TEXT;
+
--- a/litellm-proxy-extras/litellm_proxy_extras/migrations/20260306233848_schema_sync/migration.sql
+++ b/litellm-proxy-extras/litellm_proxy_extras/migrations/20260306233848_schema_sync/migration.sql
@ -0,0 +1,57 @@
+-- AlterTable
+ALTER TABLE "LiteLLM_MCPServerTable" ADD COLUMN     "byok_api_key_help_url" TEXT,
+ADD COLUMN     "byok_description" TEXT[] DEFAULT ARRAY[]::TEXT[],
+ADD COLUMN     "is_byok" BOOLEAN NOT NULL DEFAULT false,
+ADD COLUMN     "tool_name_to_description" JSONB DEFAULT '{}',
+ADD COLUMN     "tool_name_to_display_name" JSONB DEFAULT '{}';
+
+-- CreateTable
+CREATE TABLE "LiteLLM_MCPUserCredentials" (
+    "id" TEXT NOT NULL,
+    "user_id" TEXT NOT NULL,
+    "server_id" TEXT NOT NULL,
+    "credential_b64" TEXT NOT NULL,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+
+    CONSTRAINT "LiteLLM_MCPUserCredentials_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateTable
+CREATE TABLE "LiteLLM_JWTKeyMapping" (
+    "id" TEXT NOT NULL,
+    "jwt_claim_name" TEXT NOT NULL,
+    "jwt_claim_value" TEXT NOT NULL,
+    "token" TEXT NOT NULL,
+    "description" TEXT,
+    "is_active" BOOLEAN NOT NULL DEFAULT true,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "created_by" TEXT,
+    "updated_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_by" TEXT,
+
+    CONSTRAINT "LiteLLM_JWTKeyMapping_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateTable
+CREATE TABLE "LiteLLM_ConfigOverrides" (
+    "config_type" TEXT NOT NULL,
+    "config_value" JSONB NOT NULL,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP(3) NOT NULL,
+
+    CONSTRAINT "LiteLLM_ConfigOverrides_pkey" PRIMARY KEY ("config_type")
+);
+
+-- CreateIndex
+CREATE UNIQUE INDEX "LiteLLM_MCPUserCredentials_user_id_server_id_key" ON "LiteLLM_MCPUserCredentials"("user_id", "server_id");
+
+-- CreateIndex
+CREATE INDEX "LiteLLM_JWTKeyMapping_jwt_claim_name_jwt_claim_value_is_act_idx" ON "LiteLLM_JWTKeyMapping"("jwt_claim_name", "jwt_claim_value", "is_active");
+
+-- CreateIndex
+CREATE UNIQUE INDEX "LiteLLM_JWTKeyMapping_jwt_claim_name_jwt_claim_value_key" ON "LiteLLM_JWTKeyMapping"("jwt_claim_name", "jwt_claim_value");
+
+-- AddForeignKey
+ALTER TABLE "LiteLLM_JWTKeyMapping" ADD CONSTRAINT "LiteLLM_JWTKeyMapping_token_fkey" FOREIGN KEY ("token") REFERENCES "LiteLLM_VerificationToken"("token") ON DELETE RESTRICT ON UPDATE CASCADE;
+
--- a/litellm-proxy-extras/litellm_proxy_extras/schema.prisma
+++ b/litellm-proxy-extras/litellm_proxy_extras/schema.prisma
@ -63,6 +63,8 @@ model LiteLLM_AgentsTable {
  agent_name String @unique
  litellm_params Json?
  agent_card_params Json
+  static_headers       Json?          @default("{}")
+  extra_headers        String[]       @default([])
  agent_access_groups String[]       @default([])
  object_permission_id String?
  object_permission LiteLLM_ObjectPermissionTable? @relation(fields: [object_permission_id], references: [object_permission_id])
@ -293,6 +295,8 @@ model LiteLLM_MCPServerTable {
  mcp_info     Json?          @default("{}")
  mcp_access_groups String[]
  allowed_tools String[]      @default([])
+  tool_name_to_display_name Json? @default("{}")
+  tool_name_to_description   Json? @default("{}")
  extra_headers String[]    @default([])
  static_headers Json?        @default("{}")
  // Health check status
@ -308,6 +312,21 @@ model LiteLLM_MCPServerTable {
  registration_url   String?
  allow_all_keys Boolean @default(false)
  available_on_public_internet Boolean @default(true)
+  is_byok               Boolean  @default(false)
+  byok_description      String[] @default([])
+  byok_api_key_help_url String?
+}
+
+// Per-user BYOK credentials for MCP servers
+model LiteLLM_MCPUserCredentials {
+  id             String   @id @default(uuid())
+  user_id        String
+  server_id      String
+  credential_b64 String
+  created_at     DateTime @default(now()) @map("created_at")
+  updated_at     DateTime @default(now()) @updatedAt @map("updated_at")
+
+  @@unique([user_id, server_id])
 }

 // Generate Tokens for Proxy
@ -358,6 +377,7 @@ model LiteLLM_VerificationToken {
    litellm_organization_table LiteLLM_OrganizationTable?   @relation(fields: [organization_id], references: [organization_id])
    litellm_project_table LiteLLM_ProjectTable?   @relation(fields: [project_id], references: [project_id])
    object_permission LiteLLM_ObjectPermissionTable?   @relation(fields: [object_permission_id], references: [object_permission_id])
+    jwt_key_mappings LiteLLM_JWTKeyMapping[]

    // SELECT COUNT(*) FROM (SELECT "public"."LiteLLM_VerificationToken"."token" FROM "public"."LiteLLM_VerificationToken" WHERE ("public"."LiteLLM_VerificationToken"."user_id" = $1 AND ("public"."LiteLLM_VerificationToken"."team_id" IS NULL OR "public"."LiteLLM_VerificationToken"."team_id" <> $2)) OFFSET $3 ) AS "sub"
    // SELECT ... FROM "public"."LiteLLM_VerificationToken" WHERE "public"."LiteLLM_VerificationToken"."user_id" = $1 OFFSET $2
@ -370,6 +390,24 @@ model LiteLLM_VerificationToken {
    @@index([budget_reset_at, expires])
 }

+model LiteLLM_JWTKeyMapping {
+    id                String   @id @default(uuid())
+    jwt_claim_name    String   // e.g. "sub", "email"
+    jwt_claim_value   String   // The claim value to match
+    token             String   // Hashed virtual key (FK)
+    description       String?
+    is_active         Boolean  @default(true)
+    created_at        DateTime @default(now())
+    created_by        String?
+    updated_at        DateTime @default(now()) @updatedAt
+    updated_by        String?
+
+    litellm_verification_token LiteLLM_VerificationToken @relation(fields: [token], references: [token])
+
+    @@unique([jwt_claim_name, jwt_claim_value])
+    @@index([jwt_claim_name, jwt_claim_value, is_active])
+}
+
 // Deprecated keys during grace period - allows old key to work until revoke_at
 model LiteLLM_DeprecatedVerificationToken {
    id               String   @id @default(uuid())
@ -1024,6 +1062,14 @@ model LiteLLM_UISettings {
  updated_at DateTime @updatedAt
 }

+// Generic config overrides table - one row per config_type
+model LiteLLM_ConfigOverrides {
+  config_type  String   @id
+  config_value Json
+  created_at   DateTime @default(now())
+  updated_at   DateTime @updatedAt
+}
+
 // Skills table for storing LiteLLM-managed skills
 model LiteLLM_SkillsTable {
  skill_id       String   @id @default(uuid())
@ -1082,24 +1128,24 @@ model LiteLLM_PolicyAttachmentTable {
  updated_by       String?
 }

-// Global tool registry - auto-discovered from LLM responses; admins set input_policy/output_policy here
+// Global tool registry - auto-discovered from LLM responses; admins set input/output policies here
 model LiteLLM_ToolTable {
-  tool_id       String    @id @default(uuid())
-  tool_name     String    @unique   // e.g. "huggingface_remote-mcp__dynamic_space"
-  origin        String?             // MCP server name or "user_defined"
-  input_policy  String    @default("untrusted")  // "trusted" | "untrusted" | "blocked"
-  output_policy String    @default("untrusted")  // "trusted" | "untrusted"
-  call_count    Int       @default(0)             // cumulative number of times this tool was seen
-  assignments   Json?     @default("{}")
-  key_hash      String?             // hash of the virtual key that first called this tool
-  team_id       String?             // team that first called this tool
-  key_alias     String?             // human-readable alias of the virtual key
-  user_agent    String?             // user-agent of the first request that discovered this tool
-  last_used_at  DateTime?           // timestamp of the most recent call
-  created_at    DateTime  @default(now())
-  created_by    String?
-  updated_at    DateTime  @default(now()) @updatedAt
-  updated_by    String?
+  tool_id        String   @id @default(uuid())
+  tool_name      String   @unique   // e.g. "huggingface_remote-mcp__dynamic_space"
+  origin         String?            // MCP server name or "user_defined"
+  input_policy   String   @default("untrusted")  // "trusted" | "untrusted" | "blocked"
+  output_policy  String   @default("untrusted")  // "trusted" | "untrusted"
+  call_count     Int      @default(0)            // cumulative number of times this tool was seen
+  assignments    Json?    @default("{}")
+  key_hash       String?            // hash of the virtual key that first called this tool
+  team_id        String?            // team that first called this tool
+  key_alias      String?            // human-readable alias of the virtual key
+  user_agent     String?            // user-agent of the first request that discovered this tool
+  last_used_at   DateTime?          // timestamp of the most recent call
+  created_at     DateTime @default(now())
+  created_by     String?
+  updated_at     DateTime @default(now()) @updatedAt
+  updated_by     String?

  @@index([input_policy])
  @@index([output_policy])
--- a/litellm-proxy-extras/pyproject.toml
+++ b/litellm-proxy-extras/pyproject.toml
@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm-proxy-extras"
-version = "0.4.50"
+version = "0.4.52"
 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 = "0.4.50"
+version = "0.4.52"
 version_files = [
    "pyproject.toml:version",
    "../requirements.txt:litellm-proxy-extras==",
--- a/litellm/init.py
+++ b/litellm/init.py
@ -305,6 +305,9 @@ return_response_headers: bool = (
    False  # get response headers from LLM Api providers - example x-remaining-requests,
 )
 enable_json_schema_validation: bool = False
+enable_key_alias_format_validation: bool = (
+    False  # opt-in validation of key_alias format on /key/generate and /key/update
+)
 ####################
 logging: bool = True
 enable_loadbalancing_on_batch_endpoints: Optional[bool] = None
--- a/litellm/a2a_protocol/main.py
+++ b/litellm/a2a_protocol/main.py
@ -212,6 +212,7 @@ async def asend_message(
    api_base: Optional[str] = None,
    litellm_params: Optional[Dict[str, Any]] = None,
    agent_id: Optional[str] = None,
+    agent_extra_headers: Optional[Dict[str, str]] = None,
    **kwargs: Any,
 ) -> LiteLLMSendMessageResponse:
    """
@ -293,9 +294,12 @@ async def asend_message(
                "Either a2a_client or api_base is required for standard A2A flow"
            )
        trace_id = trace_id or str(uuid.uuid4())
-        extra_headers = {"X-LiteLLM-Trace-Id": trace_id}
+        extra_headers: Dict[str, str] = {"X-LiteLLM-Trace-Id": trace_id}
        if agent_id:
            extra_headers["X-LiteLLM-Agent-Id"] = agent_id
+        # Overlay agent-level headers (agent headers take precedence over LiteLLM internal ones)
+        if agent_extra_headers:
+            extra_headers.update(agent_extra_headers)
        a2a_client = await create_a2a_client(
            base_url=api_base, extra_headers=extra_headers
        )
@ -434,7 +438,7 @@ def _build_streaming_logging_obj(
    return logging_obj


-async def asend_message_streaming(
+async def asend_message_streaming(  # noqa: PLR0915
    a2a_client: Optional["A2AClientType"] = None,
    request: Optional["SendStreamingMessageRequest"] = None,
    api_base: Optional[str] = None,
@ -442,6 +446,7 @@ async def asend_message_streaming(
    agent_id: Optional[str] = None,
    metadata: Optional[Dict[str, Any]] = None,
    proxy_server_request: Optional[Dict[str, Any]] = None,
+    agent_extra_headers: Optional[Dict[str, str]] = None,
 ) -> AsyncIterator[Any]:
    """
    Async: Send a streaming message to an A2A agent.
@ -523,7 +528,17 @@ async def asend_message_streaming(
            raise ValueError(
                "Either a2a_client or api_base is required for standard A2A flow"
            )
-        a2a_client = await create_a2a_client(base_url=api_base)
+        # Mirror the non-streaming path: always include trace and agent-id headers
+        streaming_extra_headers: Dict[str, str] = {
+            "X-LiteLLM-Trace-Id": str(request.id),
+        }
+        if agent_id:
+            streaming_extra_headers["X-LiteLLM-Agent-Id"] = agent_id
+        if agent_extra_headers:
+            streaming_extra_headers.update(agent_extra_headers)
+        a2a_client = await create_a2a_client(
+            base_url=api_base, extra_headers=streaming_extra_headers
+        )

    # Type assertion: a2a_client is guaranteed to be non-None here
    assert a2a_client is not None
@ -637,17 +652,30 @@ async def create_a2a_client(

    verbose_logger.info(f"Creating A2A client for {base_url}")

-    # Use LiteLLM's cached httpx client
-    http_handler = get_async_httpx_client(
-        llm_provider=httpxSpecialProvider.A2A,
-        params={"timeout": timeout},
+    # Use get_async_httpx_client with per-agent params so that different agents
+    # (with different extra_headers) get separate cached clients.  The params
+    # dict is hashed into the cache key, keeping agent auth isolated while
+    # still reusing connections within the same agent.
+    #
+    # Only pass params that AsyncHTTPHandler.__init__ accepts (e.g. timeout).
+    # Use "disable_aiohttp_transport" key for cache-key-only data (it's
+    # filtered out before reaching the constructor).
+    _client_params: dict = {"timeout": timeout}
+    if extra_headers:
+        # Encode headers into a cache-key-only param so each unique header
+        # set produces a distinct cache key.
+        _client_params["disable_aiohttp_transport"] = str(
+            sorted(extra_headers.items())
+        )
+    _async_handler = get_async_httpx_client(
+        llm_provider=httpxSpecialProvider.A2AProvider,
+        params=_client_params,
    )
-    httpx_client = http_handler.client
-
+    httpx_client = _async_handler.client
    if extra_headers:
        httpx_client.headers.update(extra_headers)
        verbose_proxy_logger.debug(
-            f"A2A client created with extra_headers={extra_headers}"
+            f"A2A client created with extra_headers={list(extra_headers.keys())}"
        )

    # Resolve agent card
--- a/litellm/caching/caching.py
+++ b/litellm/caching/caching.py
@ -166,6 +166,14 @@ class Cache:
            None. Cache is set as a litellm param
        """
        if type == LiteLLMCacheType.REDIS:
+            # Check REDIS_CLUSTER_NODES env var if no explicit startup nodes
+            if not redis_startup_nodes:
+                _env_cluster_nodes = litellm.get_secret("REDIS_CLUSTER_NODES")
+                if _env_cluster_nodes is not None and isinstance(
+                    _env_cluster_nodes, str
+                ):
+                    redis_startup_nodes = json.loads(_env_cluster_nodes)
+
            if redis_startup_nodes:
                # Only pass GCP parameters if they are provided
                cluster_kwargs = {
--- a/litellm/constants.py
+++ b/litellm/constants.py
@ -1242,6 +1242,11 @@ X_LITELLM_DISABLE_CALLBACKS = "x-litellm-disable-callbacks"
 LITELLM_METADATA_FIELD = "litellm_metadata"
 OLD_LITELLM_METADATA_FIELD = "metadata"
 LITELLM_TRUNCATED_PAYLOAD_FIELD = "litellm_truncated"
+LITELLM_TRUNCATION_DB_SAFEGUARD_NOTE = (
+    "Truncation is a DB storage safeguard. "
+    "Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). "
+    "To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env."
+)

 ########################### LiteLLM Proxy Specific Constants ###########################
 ########################################################################################
--- a/litellm/cost_calculator.py
+++ b/litellm/cost_calculator.py
@ -272,6 +272,8 @@ def cost_per_token(  # noqa: PLR0915
    ### SERVICE TIER ###
    service_tier: Optional[str] = None,  # for OpenAI service tier pricing
    response: Optional[Any] = None,
+    ### REQUEST MODEL ###
+    request_model: Optional[str] = None,  # original request model for router detection
 ) -> Tuple[float, float]:  # type: ignore
    """
    Calculates the cost per token for a given model, prompt tokens, and completion tokens.
@ -520,7 +522,7 @@ def cost_per_token(  # noqa: PLR0915
        return dashscope_cost_per_token(model=model, usage=usage_block)
    elif custom_llm_provider == "azure_ai":
        return azure_ai_cost_per_token(
-            model=model, usage=usage_block, response_time_ms=response_time_ms
+            model=model, usage=usage_block, response_time_ms=response_time_ms, request_model=request_model
        )
    else:
        model_info = _cached_get_model_info_helper(
@ -1457,6 +1459,11 @@ def completion_cost(  # noqa: PLR0915
                            text=completion_string
                        )

+                # Get the original request model for router detection
+                request_model_for_cost = None
+                if litellm_logging_obj is not None:
+                    request_model_for_cost = litellm_logging_obj.model
+
                (
                    prompt_tokens_cost_usd_dollar,
                    completion_tokens_cost_usd_dollar,
@ -1479,6 +1486,7 @@ def completion_cost(  # noqa: PLR0915
                    rerank_billed_units=rerank_billed_units,
                    service_tier=service_tier,
                    response=completion_response,
+                    request_model=request_model_for_cost,
                )

                # Get additional costs from provider (e.g., routing fees, infrastructure costs)
--- a/litellm/integrations/custom_guardrail.py
+++ b/litellm/integrations/custom_guardrail.py
@ -231,8 +231,14 @@ class CustomGuardrail(CustomLogger):
                event_hook, supported_event_hooks
            )
        elif isinstance(event_hook, Mode):
+            tag_values_flat: list = []
+            for v in event_hook.tags.values():
+                if isinstance(v, list):
+                    tag_values_flat.extend(v)
+                else:
+                    tag_values_flat.append(v)
            _validate_event_hook_list_is_in_supported_event_hooks(
-                list(event_hook.tags.values()), supported_event_hooks
+                tag_values_flat, supported_event_hooks
            )
            if event_hook.default:
                default_list = (
@ -466,8 +472,12 @@ class CustomGuardrail(CustomLogger):
        if isinstance(self.event_hook, list):
            return event_type.value in self.event_hook
        if isinstance(self.event_hook, Mode):
-            if event_type.value in self.event_hook.tags.values():
-                return True
+            for tag_value in self.event_hook.tags.values():
+                if isinstance(tag_value, list):
+                    if event_type.value in tag_value:
+                        return True
+                elif event_type.value == tag_value:
+                    return True
            if self.event_hook.default:
                default_list = (
                    self.event_hook.default
--- a/litellm/integrations/opentelemetry.py
+++ b/litellm/integrations/opentelemetry.py
@ -735,13 +735,10 @@ class OpenTelemetry(CustomLogger):
            self._maybe_log_raw_request(
                kwargs, response_obj, start_time, end_time, span
            )
-            # Ensure proxy-request parent span is annotated with the actual operation kind
-            if (
-                parent_span is not None
-                and hasattr(parent_span, "name")
-                and parent_span.name == LITELLM_PROXY_REQUEST_SPAN_NAME
-            ):
-                self.set_attributes(parent_span, kwargs, response_obj)
+            # Do NOT duplicate attributes onto the parent proxy-request span.
+            # The child litellm_request span already carries all attributes;
+            # copying them to the parent doubles storage and complicates
+            # search (Issue #4).
        else:
            # Do not create primary span (keep hierarchy shallow when parent exists)
            from opentelemetry.trace import Status, StatusCode
@ -757,8 +754,12 @@ class OpenTelemetry(CustomLogger):
                kwargs, response_obj, start_time, end_time, parent_span
            )

-        # 3. Guardrail span
-        self._create_guardrail_span(kwargs=kwargs, context=ctx)
+        # 3. Guardrail span — ensure guardrails are always parented to an
+        #    existing span so they never become orphaned root spans (Issue #5).
+        guardrail_ctx = self._resolve_guardrail_context(
+            span=span, parent_span=parent_span, fallback_ctx=ctx
+        )
+        self._create_guardrail_span(kwargs=kwargs, context=guardrail_ctx)

        # 4. Metrics & cost recording
        self._record_metrics(kwargs, response_obj, start_time, end_time)
@ -1145,6 +1146,27 @@ class OpenTelemetry(CustomLogger):
            )
            otel_logger.emit(log_record)

+    @staticmethod
+    def _resolve_guardrail_context(
+        span: Optional[Any],
+        parent_span: Optional[Any],
+        fallback_ctx: Optional[Any],
+    ) -> Optional[Any]:
+        """
+        Return a valid OTEL context for guardrail child spans so they are
+        never orphaned (Issue #5).  Priority:
+          1. The litellm_request span that was just created
+          2. The parent proxy-request span
+          3. The original fallback context (may be None — last resort)
+        """
+        from opentelemetry import trace as _trace
+
+        if span is not None:
+            return _trace.set_span_in_context(span)
+        if parent_span is not None:
+            return _trace.set_span_in_context(parent_span)
+        return fallback_ctx
+
    def _create_guardrail_span(
        self, kwargs: Optional[dict], context: Optional[Context]
    ):
@ -1250,6 +1272,7 @@ class OpenTelemetry(CustomLogger):
            "USE_OTEL_LITELLM_REQUEST_SPAN"
        )

+        span = None
        if should_create_primary_span:
            # Span 1: Request sent to litellm SDK
            otel_tracer: Tracer = self.get_tracer_to_use_for_request(kwargs)
@ -1275,8 +1298,11 @@ class OpenTelemetry(CustomLogger):
                self.set_attributes(parent_otel_span, kwargs, response_obj)
                self._record_exception_on_span(span=parent_otel_span, kwargs=kwargs)

-        # Create span for guardrail information
-        self._create_guardrail_span(kwargs=kwargs, context=_parent_context)
+        # Create span for guardrail information — ensure proper parenting (Issue #5)
+        guardrail_ctx = self._resolve_guardrail_context(
+            span=span, parent_span=parent_otel_span, fallback_ctx=_parent_context
+        )
+        self._create_guardrail_span(kwargs=kwargs, context=guardrail_ctx)

        # Do NOT end parent span - it should be managed by its creator
        # External spans (from Langfuse, user code, HTTP headers, global context) must not be closed by LiteLLM
@ -1579,12 +1605,20 @@ class OpenTelemetry(CustomLogger):
                    value=optional_params.get("user"),
                )

-            # The unique identifier for the completion.
-            if response_obj and response_obj.get("id"):
+            # The unique identifier for the LLM call.
+            # Completions have a provider response ID (e.g. "chatcmpl-xxx"),
+            # but Embeddings and Image-gen responses do not.  Fall back to
+            # the litellm call ID so every call type can be correlated
+            # across LiteLLM UI, Phoenix traces, and provider logs (Issue #8).
+            response_id = (
+                (response_obj.get("id") if response_obj else None)
+                or standard_logging_payload.get("id")
+            )
+            if response_id:
                self.safe_set_attribute(
                    span=span,
                    key="gen_ai.response.id",
-                    value=response_obj.get("id"),
+                    value=response_id,
                )

            # The model used to generate the response.
@ -1808,8 +1842,10 @@ class OpenTelemetry(CustomLogger):

    def set_raw_request_attributes(self, span: Span, kwargs, response_obj):
        try:
-            self.set_attributes(span, kwargs, response_obj)
-            kwargs.get("optional_params", {})
+            # Only set provider-specific raw payload attributes on this span.
+            # The parent litellm_request span already carries the standard
+            # gen_ai.* / metadata.* attributes — duplicating them here doubles
+            # storage and adds noise (Issue #3).
            litellm_params = kwargs.get("litellm_params", {}) or {}
            custom_llm_provider = litellm_params.get("custom_llm_provider", "Unknown")

--- a/litellm/litellm_core_utils/streaming_chunk_builder_utils.py
+++ b/litellm/litellm_core_utils/streaming_chunk_builder_utils.py
@ -476,13 +476,15 @@ class ChunkProcessor:
            "prompt_tokens_details": prompt_tokens_details,
        }

-    def count_reasoning_tokens(self, response: ModelResponse) -> int:
-        reasoning_tokens = 0
+    def count_reasoning_tokens(self, response: ModelResponse) -> Optional[int]:
+        reasoning_tokens: Optional[int] = None
        for choice in response.choices:
            if (
                hasattr(cast(Choices, choice).message, "reasoning_content")
                and cast(Choices, choice).message.reasoning_content is not None
            ):
+                if reasoning_tokens is None:
+                    reasoning_tokens = 0
                reasoning_tokens += token_counter(
                    text=cast(Choices, choice).message.reasoning_content,
                    count_response_tokens=True,
--- a/litellm/llms/anthropic/chat/transformation.py
+++ b/litellm/llms/anthropic/chat/transformation.py
@ -317,6 +317,11 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
            else:
                result[key] = value

+        # Anthropic requires additionalProperties=false for object schemas
+        # See: https://docs.anthropic.com/en/docs/build-with-claude/structured-outputs
+        if result.get("type") == "object" and "additionalProperties" not in result:
+            result["additionalProperties"] = False
+
        return result

    def get_json_schema_from_pydantic_object(
@ -770,6 +775,19 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
        if json_schema is None:
            return None

+        # Resolve $ref/$defs before filtering — Anthropic doesn't support
+        # external schema references (e.g., /$defs/CalendarEvent).
+        import copy
+
+        from litellm.litellm_core_utils.prompt_templates.common_utils import (
+            unpack_defs,
+        )
+
+        json_schema = copy.deepcopy(json_schema)
+        defs = json_schema.pop("$defs", json_schema.pop("definitions", {}))
+        if defs:
+            unpack_defs(json_schema, defs)
+
        # Filter out unsupported fields for Anthropic's output_format API
        filtered_schema = self.filter_anthropic_output_schema(json_schema)

--- a/litellm/llms/anthropic/skills/transformation.py
+++ b/litellm/llms/anthropic/skills/transformation.py
@ -77,8 +77,8 @@ class AnthropicSkillsConfig(BaseSkillsAPIConfig):
            api_base = AnthropicModelInfo.get_api_base()

        if skill_id:
-            return f"{api_base}/v1/skills/{skill_id}?beta=true"
-        return f"{api_base}/v1/{endpoint}?beta=true"
+            return f"{api_base}/v1/skills/{skill_id}"
+        return f"{api_base}/v1/{endpoint}"

    def transform_create_skill_request(
        self,
--- a/litellm/llms/azure/chat/gpt_5_transformation.py
+++ b/litellm/llms/azure/chat/gpt_5_transformation.py
@ -15,6 +15,21 @@ class AzureOpenAIGPT5Config(AzureOpenAIConfig, OpenAIGPT5Config):

    GPT5_SERIES_ROUTE = "gpt5_series/"

+    @classmethod
+    def _supports_reasoning_effort_level(cls, model: str, level: str) -> bool:
+        """Override to handle gpt5_series/ prefix used for Azure routing.
+
+        The parent class calls ``_supports_factory(model, custom_llm_provider=None)``
+        which fails to resolve ``gpt5_series/gpt-5.1`` to the correct Azure model
+        entry. Strip the prefix and prepend ``azure/`` so the lookup finds
+        ``azure/gpt-5.1`` in model_prices_and_context_window.json.
+        """
+        if model.startswith(cls.GPT5_SERIES_ROUTE):
+            model = "azure/" + model[len(cls.GPT5_SERIES_ROUTE) :]
+        elif not model.startswith("azure/"):
+            model = "azure/" + model
+        return super()._supports_reasoning_effort_level(model, level)
+
    @classmethod
    def is_model_gpt_5_model(cls, model: str) -> bool:
        """Check if the Azure model string refers to a gpt-5 variant.
@ -46,7 +61,7 @@ class AzureOpenAIGPT5Config(AzureOpenAIConfig, OpenAIGPT5Config):
        # Only gpt-5.2+ has been verified to support logprobs on Azure.
        # The base OpenAI class includes logprobs for gpt-5.1+, but Azure
        # hasn't verified support for gpt-5.1, so remove them unless gpt-5.2/5.4+.
-        if self.is_model_gpt_5_1_model(model) and not self.is_model_gpt_5_2_model(model):
+        if self._supports_reasoning_effort_level(model, "none") and not self.is_model_gpt_5_2_model(model):
            params = [p for p in params if p not in ["logprobs", "top_logprobs"]]
        elif self.is_model_gpt_5_2_model(model):
            azure_supported_params = ["logprobs", "top_logprobs"]
@ -69,9 +84,9 @@ class AzureOpenAIGPT5Config(AzureOpenAIConfig, OpenAIGPT5Config):

        # gpt-5.1/5.2/5.4 support reasoning_effort='none', but other gpt-5 models don't
        # See: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/reasoning
-        is_gpt_5_1 = self.is_model_gpt_5_1_model(model)
+        supports_none = self._supports_reasoning_effort_level(model, "none")

-        if reasoning_effort_value == "none" and not is_gpt_5_1:
+        if reasoning_effort_value == "none" and not supports_none:
            if litellm.drop_params is True or (
                drop_params is not None and drop_params is True
            ):
@ -101,8 +116,8 @@ class AzureOpenAIGPT5Config(AzureOpenAIConfig, OpenAIGPT5Config):
            drop_params=drop_params,
        )

-        # Only drop reasoning_effort='none' for non-gpt-5.1/5.2/5.4 models
-        if result.get("reasoning_effort") == "none" and not is_gpt_5_1:
+        # Only drop reasoning_effort='none' for models that don't support it
+        if result.get("reasoning_effort") == "none" and not supports_none:
            result.pop("reasoning_effort")

        return result
--- a/litellm/llms/azure_ai/cost_calculator.py
+++ b/litellm/llms/azure_ai/cost_calculator.py
@ -61,7 +61,10 @@ def calculate_azure_model_router_flat_cost(model: str, prompt_tokens: int) -> fl


 def cost_per_token(
-    model: str, usage: Usage, response_time_ms: Optional[float] = 0.0
+    model: str, 
+    usage: Usage, 
+    response_time_ms: Optional[float] = 0.0,
+    request_model: Optional[str] = None,
 ) -> Tuple[float, float]:
    """
    Calculate the cost per token for Azure AI models.
@ -71,9 +74,10 @@ def cost_per_token(
    - Plus the cost of the actual model used (handled by generic_cost_per_token)
    
    Args:
-        model: str, the model name without provider prefix
+        model: str, the model name without provider prefix (from response)
        usage: LiteLLM Usage block
        response_time_ms: Optional response time in milliseconds
+        request_model: Optional[str], the original request model name (to detect router usage)
    
    Returns:
        Tuple[float, float] - prompt_cost_in_usd, completion_cost_in_usd
@ -84,7 +88,13 @@ def cost_per_token(
    """
    prompt_cost = 0.0
    completion_cost = 0.0
-    
+
+    # Determine if this was a model router request
+    # Check both the response model and the request model
+    is_router_request = _is_azure_model_router(model) or (
+        request_model is not None and _is_azure_model_router(request_model)
+    )
+
    # Calculate base cost using generic cost calculator
    # This may raise an exception if the model is not in the cost map
    try:
@ -103,19 +113,21 @@ def cost_per_token(
        verbose_logger.debug(
            f"Azure AI Model Router: model '{model}' not in cost map, calculating routing flat cost only. Error: {e}"
        )
-    
+
    # Add flat cost for Azure Model Router
    # The flat cost is defined in model_prices_and_context_window.json for azure_ai/model_router
-    if _is_azure_model_router(model):
-        router_flat_cost = calculate_azure_model_router_flat_cost(model, usage.prompt_tokens)
-        
+    if is_router_request:
+        # Use the request model for flat cost calculation if available, otherwise use response model
+        router_model_for_calc = request_model if request_model else model
+        router_flat_cost = calculate_azure_model_router_flat_cost(router_model_for_calc, usage.prompt_tokens)
+
        if router_flat_cost > 0:
            verbose_logger.debug(
                f"Azure AI Model Router flat cost: ${router_flat_cost:.6f} "
                f"({usage.prompt_tokens} tokens × ${router_flat_cost / usage.prompt_tokens:.9f}/token)"
            )
-            
+
            # Add flat cost to prompt cost
            prompt_cost += router_flat_cost
-    
+
    return prompt_cost, completion_cost
--- a/litellm/llms/bedrock/image_edit/stability_transformation.py
+++ b/litellm/llms/bedrock/image_edit/stability_transformation.py
@ -22,7 +22,6 @@ API Reference: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parame
 """

 import base64
-import json
 from typing import TYPE_CHECKING, Any, Dict, Optional, Tuple

 import httpx
@ -285,8 +284,6 @@ class BedrockStabilityImageEditConfig(BaseImageEditConfig):
        """
        try:
            response_data = raw_response.json()
-            with open("response_data.json", "w") as f:
-                json.dump(response_data, f)
        except Exception as e:
            raise self.get_error_class(
                error_message=f"Error parsing Bedrock Stability response: {e}",
@ -396,4 +393,3 @@ class BedrockStabilityImageEditConfig(BaseImageEditConfig):
            headers["Content-Type"] = "application/json"
        
        return headers
-
--- a/litellm/llms/openai/chat/gpt_5_transformation.py
+++ b/litellm/llms/openai/chat/gpt_5_transformation.py
@ -1,12 +1,30 @@
 """Support for OpenAI gpt-5 model family."""

-from typing import Optional
+from typing import Optional, Union

 import litellm
+from litellm.utils import _supports_factory

 from .gpt_transformation import OpenAIGPTConfig


+def _normalize_reasoning_effort_for_chat_completion(
+    value: Union[str, dict, None],
+) -> Optional[str]:
+    """Convert reasoning_effort to the string format expected by OpenAI chat completion API.
+
+    The chat completion API expects a simple string: 'none', 'low', 'medium', 'high', or 'xhigh'.
+    Config/deployments may pass the Responses API format: {'effort': 'high', 'summary': 'detailed'}.
+    """
+    if value is None:
+        return None
+    if isinstance(value, str):
+        return value
+    if isinstance(value, dict) and "effort" in value:
+        return value["effort"]
+    return None
+
+
 class OpenAIGPT5Config(OpenAIGPTConfig):
    """Configuration for gpt-5 models including GPT-5-Codex variants.

@ -40,47 +58,32 @@ class OpenAIGPT5Config(OpenAIGPTConfig):
        """Check if the model is specifically a GPT-5 Codex variant."""
        return "gpt-5-codex" in model

-    @classmethod
-    def is_model_gpt_5_1_codex_max_model(cls, model: str) -> bool:
-        """Check if the model is the gpt-5.1-codex-max variant."""
-        model_name = model.split("/")[-1]  # handle provider prefixes
-        return model_name == "gpt-5.1-codex-max"
-    
-    @classmethod
-    def is_model_gpt_5_1_model(cls, model: str) -> bool:
-        """Check if the model is a gpt-5.1, gpt-5.2, or gpt-5.4 chat variant.
-        
-        gpt-5.1/5.2/5.4 support temperature when reasoning_effort="none",
-        unlike base gpt-5 which only supports temperature=1. Excludes
-        pro variants which keep stricter knobs and chat-only variants
-        which only support temperature=1.
-        """
-        model_name = model.split("/")[-1]
-        is_gpt_5_1 = model_name.startswith("gpt-5.1")
-        is_gpt_5_2 = (
-            model_name.startswith("gpt-5.2")
-            and "pro" not in model_name
-            and not model_name.startswith("gpt-5.2-chat")
-        )
-        is_gpt_5_4 = (
-            model_name.startswith("gpt-5.4")
-            and "pro" not in model_name
-            and not model_name.startswith("gpt-5.4-chat")
-        )
-        return is_gpt_5_1 or is_gpt_5_2 or is_gpt_5_4
-
-    @classmethod
-    def is_model_gpt_5_2_pro_model(cls, model: str) -> bool:
-        """Check if the model is the gpt-5.2-pro snapshot/alias."""
-        model_name = model.split("/")[-1]
-        return model_name.startswith("gpt-5.2-pro")
-
    @classmethod
    def is_model_gpt_5_2_model(cls, model: str) -> bool:
        """Check if the model is a gpt-5.2 variant (including pro)."""
        model_name = model.split("/")[-1]
        return model_name.startswith("gpt-5.2") or model_name.startswith("gpt-5.4")

+    @classmethod
+    def is_model_gpt_5_4_model(cls, model: str) -> bool:
+        """Check if the model is a gpt-5.4 variant (including pro)."""
+        model_name = model.split("/")[-1]
+        return model_name.startswith("gpt-5.4")
+
+    @classmethod
+    def _supports_reasoning_effort_level(cls, model: str, level: str) -> bool:
+        """Check if the model supports a specific reasoning_effort level.
+
+        Looks up ``supports_{level}_reasoning_effort`` in the model map via
+        the shared ``_supports_factory`` helper.
+        Returns False for unknown models (safe fallback).
+        """
+        return _supports_factory(
+            model=model,
+            custom_llm_provider=None,
+            key=f"supports_{level}_reasoning_effort",
+        )
+
    def get_supported_openai_params(self, model: str) -> list:
        if self.is_model_gpt_5_search_model(model):
            return [
@ -118,8 +121,8 @@ class OpenAIGPT5Config(OpenAIGPTConfig):
            "web_search_options",
        ]

-        # gpt-5.1/5.2/5.4 support logprobs, top_p, top_logprobs when reasoning_effort="none"
-        if not self.is_model_gpt_5_1_model(model):
+        # gpt-5.1/5.2 support logprobs, top_p, top_logprobs when reasoning_effort="none"
+        if not self._supports_reasoning_effort_level(model, "none"):
            non_supported_params.extend(["logprobs", "top_p", "top_logprobs"])

        return [
@ -147,15 +150,22 @@ class OpenAIGPT5Config(OpenAIGPTConfig):
                drop_params=drop_params,
            )

-        reasoning_effort = (
+        # Normalize reasoning_effort: chat completion API expects a string, not a dict
+        # (e.g. {'effort': 'high', 'summary': 'detailed'} -> 'high')
+        raw_reasoning_effort = (
            non_default_params.get("reasoning_effort")
            or optional_params.get("reasoning_effort")
        )
+        normalized = _normalize_reasoning_effort_for_chat_completion(raw_reasoning_effort)
+        if raw_reasoning_effort is not None and normalized is not None:
+            if "reasoning_effort" in non_default_params:
+                non_default_params["reasoning_effort"] = normalized
+            if "reasoning_effort" in optional_params:
+                optional_params["reasoning_effort"] = normalized
+
+        reasoning_effort = normalized or raw_reasoning_effort
        if reasoning_effort is not None and reasoning_effort == "xhigh":
-            if not (
-                self.is_model_gpt_5_1_codex_max_model(model)
-                or self.is_model_gpt_5_2_model(model)
-            ):
+            if not self._supports_reasoning_effort_level(model, "xhigh"):
                if litellm.drop_params or drop_params:
                    non_default_params.pop("reasoning_effort", None)
                else:
@ -175,8 +185,20 @@ class OpenAIGPT5Config(OpenAIGPTConfig):
                "max_tokens"
            )

-        # gpt-5.1/5.2/5.4 support logprobs, top_p, top_logprobs only when reasoning_effort="none"
-        if self.is_model_gpt_5_1_model(model):
+        # gpt-5.4: function calls not supported when reasoning_effort != "none"
+        # Drop reasoning_effort when tools are present (small minority of volume)
+        if self.is_model_gpt_5_4_model(model):
+            has_tools = bool(
+                non_default_params.get("tools") or optional_params.get("tools")
+            )
+            if has_tools and reasoning_effort not in (None, "none"):
+                non_default_params.pop("reasoning_effort", None)
+                optional_params.pop("reasoning_effort", None)
+                reasoning_effort = None
+
+        # gpt-5.1/5.2 support logprobs, top_p, top_logprobs only when reasoning_effort="none"
+        supports_none = self._supports_reasoning_effort_level(model, "none")
+        if supports_none:
            sampling_params = ["logprobs", "top_logprobs", "top_p"]
            has_sampling = any(p in non_default_params for p in sampling_params)
            if has_sampling and reasoning_effort not in (None, "none"):
@ -196,10 +218,8 @@ class OpenAIGPT5Config(OpenAIGPTConfig):
        if "temperature" in non_default_params:
            temperature_value: Optional[float] = non_default_params.pop("temperature")
            if temperature_value is not None:
-                is_gpt_5_1 = self.is_model_gpt_5_1_model(model)
-                
-                # gpt-5.1 supports any temperature when reasoning_effort="none" (or not specified, as it defaults to "none")
-                if is_gpt_5_1 and (reasoning_effort == "none" or reasoning_effort is None):
+                # models supporting reasoning_effort="none" also support flexible temperature
+                if supports_none and (reasoning_effort == "none" or reasoning_effort is None):
                    optional_params["temperature"] = temperature_value
                elif temperature_value == 1:
                    optional_params["temperature"] = temperature_value
--- a/litellm/llms/openai/chat/o_series_transformation.py
+++ b/litellm/llms/openai/chat/o_series_transformation.py
@ -131,7 +131,10 @@ class OpenAIOSeriesConfig(OpenAIGPTConfig):

    def is_model_o_series_model(self, model: str) -> bool:
        model = model.split("/")[-1]  # could be "openai/o3" or "o3"
-        return model.startswith(("o1", "o3", "o4")) and model in litellm.open_ai_chat_completion_models
+        return (
+            len(model) > 1 and model[0] == "o" and model[1].isdigit()
+            and model in litellm.open_ai_chat_completion_models
+        )

    @overload
    def _transform_messages(
--- a/litellm/llms/searchapi/search/transformation.py
+++ b/litellm/llms/searchapi/search/transformation.py
@ -159,7 +159,7 @@ class SearchAPIConfig(BaseSearchConfig):
            domains = optional_params["search_domain_filter"]
            if isinstance(domains, list) and len(domains) > 0:
                result_data["q"] = self._append_domain_filters(
-                    result_data["q"], domains
+                    str(result_data["q"]), domains
                )

        if "country" in optional_params:
--- a/litellm/llms/vertex_ai/aws_credentials_supplier.py
+++ b/litellm/llms/vertex_ai/aws_credentials_supplier.py
@ -0,0 +1,52 @@
+"""
+Custom AWS Security Credentials Supplier for Vertex AI WIF.
+
+Wraps boto3/botocore credentials so that google-auth can use them
+for the AWS-to-GCP Workload Identity Federation token exchange
+without hitting the EC2 instance metadata service.
+
+Requires google-auth >= 2.29.0.
+"""
+
+from typing import Callable
+
+from google.auth import aws
+
+
+class AwsCredentialsSupplier(aws.AwsSecurityCredentialsSupplier):
+    """
+    Supplies AWS credentials to google-auth's aws.Credentials for WIF
+    token exchange.
+
+    This bypasses the default metadata-based credential retrieval,
+    allowing WIF to work in environments where EC2 metadata is blocked.
+
+    Accepts a credentials_provider callable that is invoked on every
+    get_aws_security_credentials() call, so that refreshed/rotated
+    credentials are picked up automatically (important for temporary
+    STS tokens).
+    """
+
+    def __init__(self, credentials_provider: Callable, aws_region: str):
+        """
+        Args:
+            credentials_provider: A zero-arg callable that returns a
+                botocore.credentials.Credentials object (with access_key,
+                secret_key, and token attributes).
+            aws_region: The AWS region string (e.g. "us-east-1").
+        """
+        self._credentials_provider = credentials_provider
+        self._region = aws_region
+
+    def get_aws_security_credentials(self, context, request):
+        """Return current AWS credentials for the GCP token exchange."""
+        current = self._credentials_provider()
+        return aws.AwsSecurityCredentials(
+            access_key_id=current.access_key,
+            secret_access_key=current.secret_key,
+            session_token=current.token,
+        )
+
+    def get_aws_region(self, context, request):
+        """Return the AWS region for credential verification."""
+        return self._region
--- a/litellm/llms/vertex_ai/common_utils.py
+++ b/litellm/llms/vertex_ai/common_utils.py
@ -571,38 +571,14 @@ def _filter_anyof_fields(schema_dict: Dict[str, Any]) -> Dict[str, Any]:
    return schema_dict


-def _is_any_type_schema(schema: dict) -> bool:
-    """
-    Detect schemas that represent "any JSON value" (no type constraints).
-
-    In JSON Schema, an empty schema {} means "any value is valid".
-    Schemas with only metadata keys (title, description, default, examples)
-    but no type-constraining keywords also represent "any type".
-
-    Gemini's Schema proto uses TYPE_UNSPECIFIED (0) as default,
-    so omitting the type field is valid and means "any type".
-    """
-    type_constraining_keys = {
-        "type",
-        "properties",
-        "items",
-        "anyOf",
-        "oneOf",
-        "allOf",
-        "enum",
-        "required",
-        "$ref",
-        "$schema",
-    }
-    return not any(key in type_constraining_keys for key in schema.keys())
-
-
 def process_items(schema, depth=0):
    if depth > DEFAULT_MAX_RECURSE_DEPTH:
        raise ValueError(
            f"Max depth of {DEFAULT_MAX_RECURSE_DEPTH} exceeded while processing schema. Please check the schema for excessive nesting."
        )
    if isinstance(schema, dict):
+        if "items" in schema and schema["items"] == {}:
+            schema["items"] = {"type": "object"}
        for key, value in schema.items():
            if isinstance(value, dict):
                process_items(value, depth + 1)
@ -701,8 +677,9 @@ def convert_anyof_null_to_nullable(schema, depth=0):
                # remove null type
                anyof.remove(atype)
                contains_null = True
-            elif isinstance(atype, dict) and _is_any_type_schema(atype):
-                pass  # preserve "any type" semantics — don't coerce to object
+            elif "type" not in atype and len(atype) == 0:
+                # Handle empty object case
+                atype["type"] = "object"

        if len(anyof) == 0:
            # Edge case: response schema with only null type present is invalid in Vertex AI
@ -737,8 +714,7 @@ def add_object_type(schema):
    # Gemini requires all function parameters to be type OBJECT
    # Handle case where schema has no properties and no type (e.g. tools with no arguments)
    if "type" not in schema and "anyOf" not in schema and "oneOf" not in schema and "allOf" not in schema:
-        if not _is_any_type_schema(schema):
-            schema["type"] = "object"
+        schema["type"] = "object"

    properties = schema.get("properties", None)
    if properties is not None:
--- a/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py
+++ b/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py
@ -800,9 +800,10 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
            GeminiThinkingConfig with thinkingLevel and includeThoughts
        """
        # Check if this is gemini-3-flash which supports MINIMAL thinking level
+        # Covers gemini-3-flash, gemini-3-flash-preview, gemini-3.1-flash, gemini-3.1-flash-lite-preview, etc.
        is_gemini3flash = model and (
-            "gemini-3-flash-preview" in model.lower()
-            or "gemini-3-flash" in model.lower()
+            "gemini-3-flash" in model.lower()
+            or "gemini-3.1-flash" in model.lower()
        )
        is_gemini31pro = model and (
            "gemini-3.1-pro-preview" in model.lower()
--- a/litellm/llms/vertex_ai/vertex_ai_aws_wif.py
+++ b/litellm/llms/vertex_ai/vertex_ai_aws_wif.py
@ -0,0 +1,125 @@
+"""
+AWS Workload Identity Federation (WIF) auth for Vertex AI.
+
+Handles explicit AWS credentials for GCP WIF token exchange,
+bypassing the EC2 instance metadata service.
+
+When aws_* keys are present in the WIF credential JSON, this module
+uses BaseAWSLLM to obtain AWS credentials and wraps them in a custom
+AwsSecurityCredentialsSupplier for google-auth.
+"""
+
+from typing import Dict
+
+GOOGLE_IMPORT_ERROR_MESSAGE = (
+    "Google Cloud SDK not found. Install it with: pip install 'litellm[google]' "
+    "or pip install google-cloud-aiplatform"
+)
+
+# AWS params recognized in WIF credential JSON for explicit auth.
+# These match the kwargs accepted by BaseAWSLLM.get_credentials().
+_AWS_CREDENTIAL_KEYS = frozenset({
+    "aws_access_key_id",
+    "aws_secret_access_key",
+    "aws_session_token",
+    "aws_region_name",
+    "aws_session_name",
+    "aws_profile_name",
+    "aws_role_name",
+    "aws_web_identity_token",
+    "aws_sts_endpoint",
+    "aws_external_id",
+})
+
+
+class VertexAIAwsWifAuth:
+    """
+    Handles AWS-to-GCP Workload Identity Federation credential creation
+    for Vertex AI, using explicit AWS credentials rather than EC2 metadata.
+    """
+
+    @staticmethod
+    def extract_aws_params(json_obj: dict) -> Dict[str, str]:
+        """
+        Extract LiteLLM-specific aws_* keys from a WIF credential JSON dict.
+
+        Returns a dict of {param_name: value} for any recognized aws_* keys
+        found in the JSON. Returns empty dict if none are present.
+        """
+        return {
+            key: json_obj[key]
+            for key in _AWS_CREDENTIAL_KEYS
+            if key in json_obj
+        }
+
+    @staticmethod
+    def credentials_from_explicit_aws(json_obj, aws_params, scopes):
+        """
+        Create GCP credentials using explicit AWS credentials for WIF.
+
+        Uses BaseAWSLLM to obtain AWS credentials (via STS AssumeRole, profile,
+        static keys, etc.), then wraps them in a custom AwsSecurityCredentialsSupplier
+        so that google-auth bypasses the EC2 metadata service.
+
+        Args:
+            json_obj: The WIF credential JSON dict (contains audience, token_url, etc.)
+            aws_params: Dict of aws_* params extracted from json_obj
+            scopes: OAuth scopes for the GCP credentials
+        """
+        try:
+            from google.auth import aws
+        except ImportError:
+            raise ImportError(GOOGLE_IMPORT_ERROR_MESSAGE)
+
+        from litellm.llms.bedrock.base_aws_llm import BaseAWSLLM
+        from litellm.llms.vertex_ai.aws_credentials_supplier import (
+            AwsCredentialsSupplier,
+        )
+
+        # Validate region first — required for the GCP token exchange.
+        # Check before get_credentials() to avoid unnecessary AWS API calls
+        # (e.g. STS AssumeRole) on misconfiguration.
+        aws_region = aws_params.get("aws_region_name")
+        if not aws_region:
+            raise ValueError(
+                "aws_region_name is required in the WIF credential JSON "
+                "when using explicit AWS authentication. Add "
+                '"aws_region_name": "<your-region>" to your credential file.'
+            )
+
+        # Build a credentials provider that re-resolves AWS creds on each call.
+        # This ensures rotated/refreshed STS tokens are picked up during
+        # long-running processes when google-auth refreshes the GCP token.
+        base_aws = BaseAWSLLM()
+        aws_params_copy = dict(aws_params)  # avoid mutating caller's dict
+
+        def _get_aws_credentials():
+            return base_aws.get_credentials(**aws_params_copy)
+
+        # Create the custom supplier with a lazy credentials provider
+        supplier = AwsCredentialsSupplier(
+            credentials_provider=_get_aws_credentials,
+            aws_region=aws_region,
+        )
+
+        # Build kwargs for aws.Credentials — forward optional fields from JSON
+        creds_kwargs = dict(
+            audience=json_obj.get("audience"),
+            subject_token_type=json_obj.get("subject_token_type"),
+            token_url=json_obj.get("token_url"),
+            credential_source=None,  # Not using metadata endpoints
+            aws_security_credentials_supplier=supplier,
+            service_account_impersonation_url=json_obj.get(
+                "service_account_impersonation_url"
+            ),
+        )
+        # Forward universe_domain if present (defaults to googleapis.com)
+        if "universe_domain" in json_obj:
+            creds_kwargs["universe_domain"] = json_obj["universe_domain"]
+
+        creds = aws.Credentials(**creds_kwargs)
+
+        if scopes and hasattr(creds, "requires_scopes") and creds.requires_scopes:
+            creds = creds.with_scopes(scopes)
+
+        return creds
--- a/litellm/llms/vertex_ai/vertex_llm_base.py
+++ b/litellm/llms/vertex_ai/vertex_llm_base.py
@ -96,10 +96,23 @@ class VertexBase:
                    else ""
                )
                if isinstance(environment_id, str) and "aws" in environment_id:
-                    creds = self._credentials_from_identity_pool_with_aws(
-                        json_obj,
-                        scopes=["https://www.googleapis.com/auth/cloud-platform"],
+                    # Check if explicit AWS params are in the JSON (bypasses metadata)
+                    from litellm.llms.vertex_ai.vertex_ai_aws_wif import (
+                        VertexAIAwsWifAuth,
                    )
+
+                    aws_params = VertexAIAwsWifAuth.extract_aws_params(json_obj)
+                    if aws_params:
+                        creds = VertexAIAwsWifAuth.credentials_from_explicit_aws(
+                            json_obj,
+                            aws_params=aws_params,
+                            scopes=["https://www.googleapis.com/auth/cloud-platform"],
+                        )
+                    else:
+                        creds = self._credentials_from_identity_pool_with_aws(
+                            json_obj,
+                            scopes=["https://www.googleapis.com/auth/cloud-platform"],
+                        )
                else:
                    creds = self._credentials_from_identity_pool(
                        json_obj,
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@ -1239,7 +1239,7 @@
        "supports_vision": true,
        "tool_use_system_prompt_tokens": 346
    },
-    "apac.anthropic.claude-sonnet-4-6": {
+    "au.anthropic.claude-sonnet-4-6": {
        "cache_creation_input_token_cost": 4.125e-06,
        "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06,
        "cache_read_input_token_cost": 3.3e-07,
@ -2110,7 +2110,8 @@
        "supports_response_schema": true,
        "supports_system_messages": true,
        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": true
    },
    "azure/eu/gpt-5.1-chat": {
        "cache_read_input_token_cost": 1.4e-07,
@ -2143,7 +2144,8 @@
        "supports_response_schema": true,
        "supports_system_messages": true,
        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": true
    },
    "azure/eu/gpt-5.1-codex": {
        "cache_read_input_token_cost": 1.4e-07,
@ -2410,7 +2412,8 @@
        "supports_response_schema": true,
        "supports_system_messages": true,
        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": true
    },
    "azure/global/gpt-5.1-chat": {
        "cache_read_input_token_cost": 1.25e-07,
@ -2443,7 +2446,8 @@
        "supports_response_schema": true,
        "supports_system_messages": true,
        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": true
    },
    "azure/global/gpt-5.1-codex": {
        "cache_read_input_token_cost": 1.25e-07,
@ -3456,7 +3460,8 @@
        "supports_system_messages": true,
        "supports_tool_choice": true,
        "supports_service_tier": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": true
    },
    "azure/gpt-5.1-chat-2025-11-13": {
        "cache_read_input_token_cost": 1.25e-07,
@ -3491,7 +3496,8 @@
        "supports_response_schema": true,
        "supports_system_messages": true,
        "supports_tool_choice": false,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": true
    },
    "azure/gpt-5.1-codex-2025-11-13": {
        "cache_read_input_token_cost": 1.25e-07,
@ -3906,7 +3912,8 @@
        "supports_response_schema": true,
        "supports_system_messages": true,
        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": true
    },
    "azure/gpt-5.1-chat": {
        "cache_read_input_token_cost": 1.25e-07,
@ -3939,7 +3946,8 @@
        "supports_response_schema": true,
        "supports_system_messages": true,
        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": true
    },
    "azure/gpt-5.1-codex": {
        "cache_read_input_token_cost": 1.25e-07,
@ -5273,7 +5281,8 @@
        "supports_response_schema": true,
        "supports_system_messages": true,
        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": true
    },
    "azure/us/gpt-5.1-chat": {
        "cache_read_input_token_cost": 1.4e-07,
@ -5306,7 +5315,8 @@
        "supports_response_schema": true,
        "supports_system_messages": true,
        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": true
    },
    "azure/us/gpt-5.1-codex": {
        "cache_read_input_token_cost": 1.4e-07,
@ -6100,6 +6110,35 @@
        "supports_tool_choice": true,
        "supports_web_search": true
    },
+    "azure_ai/grok-4-1-fast-non-reasoning": {
+        "input_cost_per_token": 2e-07,
+        "output_cost_per_token": 5e-07,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_web_search": true
+    },
+    "azure_ai/grok-4-1-fast-reasoning": {
+        "input_cost_per_token": 2e-07,
+        "output_cost_per_token": 5e-07,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_web_search": true
+    },
    "azure_ai/grok-code-fast-1": {
        "input_cost_per_token": 2e-07,
        "litellm_provider": "azure_ai",
@ -18437,6 +18476,93 @@
        "max_tokens": 8191,
        "mode": "embedding"
    },
+    "chatgpt/gpt-5.4": {
+        "litellm_provider": "chatgpt",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "chatgpt/gpt-5.4-pro": {
+        "litellm_provider": "chatgpt",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "chatgpt/gpt-5.3-codex": {
+        "litellm_provider": "chatgpt",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "chatgpt/gpt-5.3-codex-spark": {
+        "litellm_provider": "chatgpt",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "chatgpt/gpt-5.3-instant": {
+        "litellm_provider": "chatgpt",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "chatgpt/gpt-5.3-chat-latest": {
+        "litellm_provider": "chatgpt",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
    "chatgpt/gpt-5.2-codex": {
        "litellm_provider": "chatgpt",
        "max_input_tokens": 128000,
@ -20506,7 +20632,9 @@
        "supports_system_messages": true,
        "supports_tool_choice": true,
        "supports_service_tier": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-5.1": {
        "cache_read_input_token_cost": 1.25e-07,
@ -20542,7 +20670,10 @@
        "supports_system_messages": true,
        "supports_tool_choice": true,
        "supports_service_tier": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-5.1-2025-11-13": {
        "cache_read_input_token_cost": 1.25e-07,
@ -20578,7 +20709,10 @@
        "supports_system_messages": true,
        "supports_tool_choice": true,
        "supports_service_tier": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-5.1-chat-latest": {
        "cache_read_input_token_cost": 1.25e-07,
@ -20613,7 +20747,10 @@
        "supports_response_schema": true,
        "supports_system_messages": true,
        "supports_tool_choice": false,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-5.2": {
        "cache_read_input_token_cost": 1.75e-07,
@ -20650,7 +20787,10 @@
        "supports_system_messages": true,
        "supports_tool_choice": true,
        "supports_service_tier": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true
    },
    "gpt-5.2-2025-12-11": {
        "cache_read_input_token_cost": 1.75e-07,
@ -20687,7 +20827,10 @@
        "supports_system_messages": true,
        "supports_tool_choice": true,
        "supports_service_tier": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true
    },
    "gpt-5.2-chat-latest": {
        "cache_read_input_token_cost": 1.75e-07,
@ -20721,7 +20864,10 @@
        "supports_response_schema": true,
        "supports_system_messages": true,
        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-5.3-chat-latest": {
        "cache_read_input_token_cost": 1.75e-07,
@ -20755,7 +20901,10 @@
        "supports_response_schema": true,
        "supports_system_messages": true,
        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-5.2-pro": {
        "input_cost_per_token": 2.1e-05,
@ -20786,7 +20935,9 @@
        "supports_system_messages": true,
        "supports_tool_choice": true,
        "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": true
    },
    "gpt-5.2-pro-2025-12-11": {
        "input_cost_per_token": 2.1e-05,
@ -20817,20 +20968,82 @@
        "supports_system_messages": true,
        "supports_tool_choice": true,
        "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": true
    },
    "gpt-5.4": {
        "cache_read_input_token_cost": 2.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 5e-07,
+        "cache_read_input_token_cost_flex": 1.3e-07,
        "cache_read_input_token_cost_priority": 5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06,
        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token_above_272k_tokens": 5e-06,
+        "input_cost_per_token_flex": 1.25e-06,
+        "input_cost_per_token_batches": 1.25e-06,
        "input_cost_per_token_priority": 5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 1e-05,
        "litellm_provider": "openai",
        "max_input_tokens": 1050000,
        "max_output_tokens": 128000,
        "max_tokens": 128000,
-        "mode": "responses",
+        "mode": "chat",
        "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_above_272k_tokens": 2.25e-05,
+        "output_cost_per_token_flex": 7.5e-06,
+        "output_cost_per_token_batches": 7.5e-06,
        "output_cost_per_token_priority": 2.25e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 3.375e-05,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "gpt-5.4-2026-03-05": {
+        "cache_read_input_token_cost": 2.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 5e-07,
+        "cache_read_input_token_cost_flex": 1.3e-07,
+        "cache_read_input_token_cost_priority": 5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06,
+        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token_above_272k_tokens": 5e-06,
+        "input_cost_per_token_flex": 1.25e-06,
+        "input_cost_per_token_batches": 1.25e-06,
+        "input_cost_per_token_priority": 5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 1e-05,
+        "litellm_provider": "openai",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_above_272k_tokens": 2.25e-05,
+        "output_cost_per_token_flex": 7.5e-06,
+        "output_cost_per_token_batches": 7.5e-06,
+        "output_cost_per_token_priority": 2.25e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 3.375e-05,
        "supported_endpoints": [
            "/v1/chat/completions",
            "/v1/batch",
@ -20855,18 +21068,28 @@
        "supports_service_tier": true,
        "supports_vision": true
    },
-    "gpt-5.4-2026-03-05": {
-        "cache_read_input_token_cost": 2.5e-07,
-        "cache_read_input_token_cost_priority": 5e-07,
-        "input_cost_per_token": 2.5e-06,
-        "input_cost_per_token_priority": 5e-06,
+    "gpt-5.4-pro": {
+        "cache_read_input_token_cost": 3e-06,
+        "cache_read_input_token_cost_above_272k_tokens": 6e-06,
+        "cache_read_input_token_cost_priority": 6e-06,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05,
+        "input_cost_per_token": 3e-05,
+        "input_cost_per_token_above_272k_tokens": 6e-05,
+        "input_cost_per_token_flex": 1.5e-05,
+        "input_cost_per_token_batches": 1.5e-05,
+        "input_cost_per_token_priority": 6e-05,
+        "input_cost_per_token_above_272k_tokens_priority": 0.00012,
        "litellm_provider": "openai",
        "max_input_tokens": 1050000,
        "max_output_tokens": 128000,
        "max_tokens": 128000,
-        "mode": "responses",
-        "output_cost_per_token": 1.5e-05,
-        "output_cost_per_token_priority": 2.25e-05,
+        "mode": "chat",
+        "output_cost_per_token": 0.00018,
+        "output_cost_per_token_above_272k_tokens": 0.00027,
+        "output_cost_per_token_flex": 9e-05,
+        "output_cost_per_token_batches": 9e-05,
+        "output_cost_per_token_priority": 0.00027,
+        "output_cost_per_token_above_272k_tokens_priority": 0.000405,
        "supported_endpoints": [
            "/v1/chat/completions",
            "/v1/batch",
@ -20885,11 +21108,63 @@
        "supports_pdf_input": true,
        "supports_prompt_caching": true,
        "supports_reasoning": true,
-        "supports_response_schema": true,
+        "supports_response_schema": false,
        "supports_system_messages": true,
        "supports_tool_choice": true,
        "supports_service_tier": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": true
+    },
+    "gpt-5.4-pro-2026-03-05": {
+        "cache_read_input_token_cost": 3e-06,
+        "cache_read_input_token_cost_above_272k_tokens": 6e-06,
+        "cache_read_input_token_cost_priority": 6e-06,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05,
+        "input_cost_per_token": 3e-05,
+        "input_cost_per_token_above_272k_tokens": 6e-05,
+        "input_cost_per_token_flex": 1.5e-05,
+        "input_cost_per_token_batches": 1.5e-05,
+        "input_cost_per_token_priority": 6e-05,
+        "input_cost_per_token_above_272k_tokens_priority": 0.00012,
+        "litellm_provider": "openai",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 0.00018,
+        "output_cost_per_token_above_272k_tokens": 0.00027,
+        "output_cost_per_token_flex": 9e-05,
+        "output_cost_per_token_batches": 9e-05,
+        "output_cost_per_token_priority": 0.00027,
+        "output_cost_per_token_above_272k_tokens_priority": 0.000405,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": true
    },
    "gpt-5-pro": {
        "input_cost_per_token": 1.5e-05,
@ -20922,7 +21197,9 @@
        "supports_system_messages": true,
        "supports_tool_choice": true,
        "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-5-pro-2025-10-06": {
        "input_cost_per_token": 1.5e-05,
@ -20955,7 +21232,9 @@
        "supports_system_messages": true,
        "supports_tool_choice": true,
        "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-5-2025-08-07": {
        "cache_read_input_token_cost": 1.25e-07,
@ -20994,7 +21273,9 @@
        "supports_system_messages": true,
        "supports_tool_choice": true,
        "supports_service_tier": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-5-chat": {
        "cache_read_input_token_cost": 1.25e-07,
@ -21026,7 +21307,9 @@
        "supports_response_schema": true,
        "supports_system_messages": true,
        "supports_tool_choice": false,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-5-chat-latest": {
        "cache_read_input_token_cost": 1.25e-07,
@ -21058,7 +21341,9 @@
        "supports_response_schema": true,
        "supports_system_messages": true,
        "supports_tool_choice": false,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-5-codex": {
        "cache_read_input_token_cost": 1.25e-07,
@ -21088,7 +21373,9 @@
        "supports_response_schema": true,
        "supports_system_messages": false,
        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-5.1-codex": {
        "cache_read_input_token_cost": 1.25e-07,
@ -21121,7 +21408,9 @@
        "supports_response_schema": true,
        "supports_system_messages": false,
        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-5.1-codex-max": {
        "cache_read_input_token_cost": 1.25e-07,
@ -21151,7 +21440,9 @@
        "supports_response_schema": true,
        "supports_system_messages": false,
        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": true
    },
    "gpt-5.1-codex-mini": {
        "cache_read_input_token_cost": 2.5e-08,
@ -21184,7 +21475,9 @@
        "supports_response_schema": true,
        "supports_system_messages": false,
        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-5.2-codex": {
        "cache_read_input_token_cost": 1.75e-07,
@ -21217,7 +21510,9 @@
        "supports_response_schema": true,
        "supports_system_messages": false,
        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": true
    },
    "gpt-5.3-codex": {
        "cache_read_input_token_cost": 1.75e-07,
@ -21250,7 +21545,9 @@
        "supports_response_schema": true,
        "supports_system_messages": false,
        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-5-mini": {
        "cache_read_input_token_cost": 2.5e-08,
@ -21289,7 +21586,9 @@
        "supports_system_messages": true,
        "supports_tool_choice": true,
        "supports_service_tier": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-5-mini-2025-08-07": {
        "cache_read_input_token_cost": 2.5e-08,
@ -21328,7 +21627,9 @@
        "supports_system_messages": true,
        "supports_tool_choice": true,
        "supports_service_tier": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-5-nano": {
        "cache_read_input_token_cost": 5e-09,
@ -21364,7 +21665,9 @@
        "supports_response_schema": true,
        "supports_system_messages": true,
        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-5-nano-2025-08-07": {
        "cache_read_input_token_cost": 5e-09,
@ -21399,7 +21702,9 @@
        "supports_response_schema": true,
        "supports_system_messages": true,
        "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-image-1": {
        "cache_read_input_image_token_cost": 2.5e-06,
@ -38559,7 +38864,9 @@
        "supports_system_messages": true,
        "supports_tool_choice": true,
        "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-5-search-api-2025-10-14": {
        "cache_read_input_token_cost": 1.25e-07,
@ -38578,7 +38885,9 @@
        "supports_system_messages": true,
        "supports_tool_choice": true,
        "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": false
    },
    "gpt-realtime-mini-2025-10-06": {
        "cache_creation_input_audio_token_cost": 3e-07,
--- a/litellm/proxy/_experimental/mcp_server/mcp_server_manager.py
+++ b/litellm/proxy/_experimental/mcp_server/mcp_server_manager.py
@ -385,6 +385,7 @@ class MCPServerManager:
        )
        from litellm.proxy._experimental.mcp_server.openapi_to_mcp_generator import (
            load_openapi_spec_async,
+            resolve_operation_params,
        )
        from litellm.proxy._experimental.mcp_server.tool_registry import (
            global_mcp_tool_registry,
@ -438,6 +439,7 @@ class MCPServerManager:

            # Extract and register tools from OpenAPI paths
            paths = spec.get("paths", {})
+            components = spec.get("components", {})
            registered_count = 0

            verbose_logger.debug(f"Processing {len(paths)} paths from OpenAPI spec")
@ -449,6 +451,11 @@ class MCPServerManager:

                    operation = path_item[method]

+                    # Resolve $ref params and merge path-level params into the operation.
+                    resolved_operation = resolve_operation_params(
+                        operation, path_item, components
+                    )
+
                    # Generate tool name (without prefix initially)
                    operation_id = operation.get(
                        "operationId", f"{method}_{path.replace('/', '_')}"
@ -467,11 +474,11 @@ class MCPServerManager:
                    )

                    # Build input schema using imported function
-                    input_schema = build_input_schema(operation)
+                    input_schema = build_input_schema(resolved_operation)

                    # Create tool function with headers using imported function
                    tool_func = create_tool_function(
-                        path, method, operation, base_url, headers=headers
+                        path, method, resolved_operation, base_url, headers=headers
                    )
                    tool_func.__name__ = prefixed_tool_name
                    tool_func.__doc__ = description
--- a/litellm/proxy/_experimental/mcp_server/openapi_to_mcp_generator.py
+++ b/litellm/proxy/_experimental/mcp_server/openapi_to_mcp_generator.py
@ -7,7 +7,7 @@ import contextvars
 import json
 import os
 from pathlib import PurePosixPath
-from typing import Any, Dict, Optional
+from typing import Any, Dict, List, Optional
 from urllib.parse import quote

 from litellm._logging import verbose_logger
@ -115,6 +115,62 @@ def get_base_url(spec: Dict[str, Any], spec_path: Optional[str] = None) -> str:
    return ""


+def _resolve_ref(
+    param: Dict[str, Any], component_params: Dict[str, Any]
+) -> Optional[Dict[str, Any]]:
+    """Resolve a single parameter, following a $ref if present.
+
+    Returns the resolved param dict, or None if the $ref target is absent from
+    components (so callers can skip/filter it rather than propagating a stub
+    with name=None that would corrupt deduplication).
+    """
+    ref = param.get("$ref", "")
+    if not ref.startswith("#/components/parameters/"):
+        return param
+    return component_params.get(ref.split("/")[-1])
+
+
+def _resolve_param_list(
+    raw: List[Dict[str, Any]], component_params: Dict[str, Any]
+) -> List[Dict[str, Any]]:
+    """Resolve $refs in a parameter list, dropping any unresolvable entries."""
+    result = []
+    for p in raw:
+        resolved = _resolve_ref(p, component_params)
+        if resolved is not None and resolved.get("name"):
+            result.append(resolved)
+    return result
+
+
+def resolve_operation_params(
+    operation: Dict[str, Any],
+    path_item: Dict[str, Any],
+    components: Dict[str, Any],
+) -> Dict[str, Any]:
+    """Return a copy of *operation* with fully-resolved, merged parameters.
+
+    Handles two common patterns in real-world OpenAPI specs:
+
+    1. **$ref parameters** — ``{"$ref": "#/components/parameters/per-page"}``
+       instead of inline objects.  Each ref is resolved against
+       ``components["parameters"]``; unresolvable refs are silently dropped so
+       they cannot corrupt the deduplication set with ``(None, None)`` keys.
+
+    2. **Path-level parameters** — params defined on the path item that apply
+       to every HTTP method on that path (e.g. ``owner``, ``repo``).  They are
+       merged with the operation-level params; operation-level wins when the
+       same ``name`` + ``in`` combination appears in both.
+    """
+    component_params = components.get("parameters", {})
+    path_level = _resolve_param_list(path_item.get("parameters", []), component_params)
+    op_level = _resolve_param_list(operation.get("parameters", []), component_params)
+    op_keys = {(p["name"], p.get("in")) for p in op_level}
+    merged = [p for p in path_level if (p["name"], p.get("in")) not in op_keys] + op_level
+    result = dict(operation)
+    result["parameters"] = merged
+    return result
+
+
 def extract_parameters(operation: Dict[str, Any]) -> tuple:
    """Extract parameter names from OpenAPI operation."""
    path_params = []
@ -124,6 +180,8 @@ def extract_parameters(operation: Dict[str, Any]) -> tuple:
    # OpenAPI 3.x and 2.x parameters
    if "parameters" in operation:
        for param in operation["parameters"]:
+            if "name" not in param:
+                continue
            param_name = param["name"]
            if param.get("in") == "path":
                path_params.append(param_name)
@ -147,6 +205,8 @@ def build_input_schema(operation: Dict[str, Any]) -> Dict[str, Any]:
    # Process parameters
    if "parameters" in operation:
        for param in operation["parameters"]:
+            if "name" not in param:
+                continue
            param_name = param["name"]
            param_schema = param.get("schema", {})
            param_type = param_schema.get("type", "string")
--- a/litellm/proxy/_experimental/mcp_server/rest_endpoints.py
+++ b/litellm/proxy/_experimental/mcp_server/rest_endpoints.py
@ -666,21 +666,26 @@ if MCP_AVAILABLE:
        from litellm.proxy._experimental.mcp_server.openapi_to_mcp_generator import (
            build_input_schema,
            load_openapi_spec_async,
+            resolve_operation_params,
        )

        try:
            spec = await load_openapi_spec_async(spec_path)
            paths = spec.get("paths", {})
+            components = spec.get("components", {})
            tools: List[dict] = []
            for path, path_item in paths.items():
                for method in ("get", "post", "put", "patch", "delete"):
                    operation = path_item.get(method)
                    if operation is None:
                        continue
+
+                    resolved_op = resolve_operation_params(operation, path_item, components)
+
                    op_id = operation.get("operationId", f"{method}_{path}")
                    summary = operation.get("summary", "")
                    description = operation.get("description", summary)
-                    input_schema = build_input_schema(operation)
+                    input_schema = build_input_schema(resolved_op)
                    tools.append(
                        {
                            "name": op_id,
--- a/litellm/proxy/_experimental/mcp_server/server.py
+++ b/litellm/proxy/_experimental/mcp_server/server.py
@ -1644,7 +1644,7 @@ if MCP_AVAILABLE:
                },
            )

-    async def execute_mcp_tool(
+    async def execute_mcp_tool(  # noqa: PLR0915
        name: str,
        arguments: Dict[str, Any],
        allowed_mcp_servers: List[MCPServer],
--- a/litellm/proxy/_experimental/out/404.html
+++ b/litellm/proxy/_experimental/out/404.html
--- a/litellm/proxy/_experimental/out/404/index.html
+++ b/litellm/proxy/_experimental/out/404/index.html
--- a/litellm/proxy/_experimental/out/next.PAGE__.txt
+++ b/litellm/proxy/_experimental/out/next.PAGE__.txt
@ -1,32 +1,30 @@
 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/61f59596bf7f0628.js","/litellm-asset-prefix/_next/static/chunks/9f5ccd929375c1d6.js","/litellm-asset-prefix/_next/static/chunks/30539b80ac15aad2.js","/litellm-asset-prefix/_next/static/chunks/142704439974f6b3.js","/litellm-asset-prefix/_next/static/chunks/8b4fd43197a5dfc8.js","/litellm-asset-prefix/_next/static/chunks/1fe0596a309ad6cf.js","/litellm-asset-prefix/_next/static/chunks/7b788dd93ad868b3.js","/litellm-asset-prefix/_next/static/chunks/c979f252fa5ee77c.js","/litellm-asset-prefix/_next/static/chunks/50febaabfb896c46.js","/litellm-asset-prefix/_next/static/chunks/c4cc89d1b0a147d5.js","/litellm-asset-prefix/_next/static/chunks/fe5201571c777f09.js","/litellm-asset-prefix/_next/static/chunks/c748f222de4766db.js","/litellm-asset-prefix/_next/static/chunks/5f9c3b92a016f382.js","/litellm-asset-prefix/_next/static/chunks/fe750aa0bf04912c.js","/litellm-asset-prefix/_next/static/chunks/7d4cded1a1238581.js","/litellm-asset-prefix/_next/static/chunks/d64d74932cb225a3.js","/litellm-asset-prefix/_next/static/chunks/9ffb8ddd0c9a7c31.js","/litellm-asset-prefix/_next/static/chunks/c4fe728e74b52958.js","/litellm-asset-prefix/_next/static/chunks/1532edb438ed84bb.js","/litellm-asset-prefix/_next/static/chunks/d0d828f9a0668699.js","/litellm-asset-prefix/_next/static/chunks/88c74f8b4b20d25a.js","/litellm-asset-prefix/_next/static/chunks/25c5a08661ac2ec3.js","/litellm-asset-prefix/_next/static/chunks/134f728fa7099e3e.js","/litellm-asset-prefix/_next/static/chunks/9d6e5aad99b19216.js","/litellm-asset-prefix/_next/static/chunks/e8718f949e42598e.js","/litellm-asset-prefix/_next/static/chunks/6a51328383335d1e.js","/litellm-asset-prefix/_next/static/chunks/3b30ab8eaa03bc21.js","/litellm-asset-prefix/_next/static/chunks/99cf9cf99df5ccfc.js","/litellm-asset-prefix/_next/static/chunks/6a4eede876bb5c8f.js","/litellm-asset-prefix/_next/static/chunks/7e417dd24c8becd0.js","/litellm-asset-prefix/_next/static/chunks/c7b74067c01ee971.js","/litellm-asset-prefix/_next/static/chunks/a85adee4198d5478.js","/litellm-asset-prefix/_next/static/chunks/bff4459534c52f16.js","/litellm-asset-prefix/_next/static/chunks/39eb5927f56ccc0e.js","/litellm-asset-prefix/_next/static/chunks/ebb2b2d8175d3d2f.js","/litellm-asset-prefix/_next/static/chunks/5a5488ab3db0c3de.js","/litellm-asset-prefix/_next/static/chunks/0a65da2cd24e2ab6.js","/litellm-asset-prefix/_next/static/chunks/82dbdb17d57c6737.js","/litellm-asset-prefix/_next/static/chunks/b31a08272a82b84e.js","/litellm-asset-prefix/_next/static/chunks/496b84010c33cf69.js","/litellm-asset-prefix/_next/static/chunks/eba9ac65320061b1.js","/litellm-asset-prefix/_next/static/chunks/0eda6dc5d5f35d92.js","/litellm-asset-prefix/_next/static/chunks/96aed36e606e8582.js","/litellm-asset-prefix/_next/static/chunks/ad426ab08aee6c64.js","/litellm-asset-prefix/_next/static/chunks/2971c4658f1bcd7d.js","/litellm-asset-prefix/_next/static/chunks/06ebe9b0e9cdf241.js","/litellm-asset-prefix/_next/static/chunks/6c4c97f1ea6e7d77.js","/litellm-asset-prefix/_next/static/chunks/165d00848f04c4c9.js","/litellm-asset-prefix/_next/static/chunks/bb0a6e4a3a18721a.js","/litellm-asset-prefix/_next/static/chunks/4980372eaa37b78b.js","/litellm-asset-prefix/_next/static/chunks/8ab6e2ca95000c8e.js","/litellm-asset-prefix/_next/static/chunks/06cdd9bb80c63794.js","/litellm-asset-prefix/_next/static/chunks/66a190706fc6c35a.js","/litellm-asset-prefix/_next/static/chunks/54e29148cb2f2582.js","/litellm-asset-prefix/_next/static/chunks/fd9de419c8c0222e.js"],"default"]
-1c:I[897367,["/litellm-asset-prefix/_next/static/chunks/d96012bcfc98706a.js","/litellm-asset-prefix/_next/static/chunks/dbca964212122d58.js"],"OutletBoundary"]
-1d:"$Sreact.suspense"
+3:I[952683,["/litellm-asset-prefix/_next/static/chunks/a7f104aa2cc7f3f0.js","/litellm-asset-prefix/_next/static/chunks/e8ed72789c2b42ff.js","/litellm-asset-prefix/_next/static/chunks/bb64f18ed439db51.js","/litellm-asset-prefix/_next/static/chunks/9de031ba49f226b2.js","/litellm-asset-prefix/_next/static/chunks/30539b80ac15aad2.js","/litellm-asset-prefix/_next/static/chunks/142704439974f6b3.js","/litellm-asset-prefix/_next/static/chunks/f0a13680e53afb88.js","/litellm-asset-prefix/_next/static/chunks/1fe0596a309ad6cf.js","/litellm-asset-prefix/_next/static/chunks/5f9c3b92a016f382.js","/litellm-asset-prefix/_next/static/chunks/403c4d96324c23a6.js","/litellm-asset-prefix/_next/static/chunks/edc62b8625528255.js","/litellm-asset-prefix/_next/static/chunks/e34ebe113303fbb2.js","/litellm-asset-prefix/_next/static/chunks/2d471965761a22ff.js","/litellm-asset-prefix/_next/static/chunks/e8718f949e42598e.js","/litellm-asset-prefix/_next/static/chunks/3b30ab8eaa03bc21.js","/litellm-asset-prefix/_next/static/chunks/0bd654557fbb50e9.js","/litellm-asset-prefix/_next/static/chunks/124fefccff39e221.js","/litellm-asset-prefix/_next/static/chunks/bb0a6e4a3a18721a.js","/litellm-asset-prefix/_next/static/chunks/d0d828f9a0668699.js","/litellm-asset-prefix/_next/static/chunks/4d3d997560b322ca.js","/litellm-asset-prefix/_next/static/chunks/4e4d0f466b5c1780.js","/litellm-asset-prefix/_next/static/chunks/88c74f8b4b20d25a.js","/litellm-asset-prefix/_next/static/chunks/821f45f615724874.js","/litellm-asset-prefix/_next/static/chunks/2971c4658f1bcd7d.js","/litellm-asset-prefix/_next/static/chunks/134f728fa7099e3e.js","/litellm-asset-prefix/_next/static/chunks/9b539d4d807cee27.js","/litellm-asset-prefix/_next/static/chunks/fc83f709354547bd.js","/litellm-asset-prefix/_next/static/chunks/853e5f250e7a0af5.js","/litellm-asset-prefix/_next/static/chunks/348b31083769a7c4.js","/litellm-asset-prefix/_next/static/chunks/37c03dc421ba81f8.js","/litellm-asset-prefix/_next/static/chunks/c81bdad246412686.js","/litellm-asset-prefix/_next/static/chunks/496b84010c33cf69.js","/litellm-asset-prefix/_next/static/chunks/b6cdb9a433f054f3.js","/litellm-asset-prefix/_next/static/chunks/fcdf7322b0aa3e2e.js","/litellm-asset-prefix/_next/static/chunks/6146a0436556bd42.js","/litellm-asset-prefix/_next/static/chunks/4980372eaa37b78b.js","/litellm-asset-prefix/_next/static/chunks/90f0529c4408147d.js","/litellm-asset-prefix/_next/static/chunks/a85adee4198d5478.js","/litellm-asset-prefix/_next/static/chunks/0a65da2cd24e2ab6.js","/litellm-asset-prefix/_next/static/chunks/8604d59a86c051be.js","/litellm-asset-prefix/_next/static/chunks/d3ac82723ec9e30d.js","/litellm-asset-prefix/_next/static/chunks/664bbc28119f9cc1.js","/litellm-asset-prefix/_next/static/chunks/d64d74932cb225a3.js","/litellm-asset-prefix/_next/static/chunks/0adb91ab5f3140d5.js","/litellm-asset-prefix/_next/static/chunks/5c6d02376dbf0f55.js","/litellm-asset-prefix/_next/static/chunks/85238af541b170ca.js","/litellm-asset-prefix/_next/static/chunks/06ebe9b0e9cdf241.js","/litellm-asset-prefix/_next/static/chunks/6c4c97f1ea6e7d77.js","/litellm-asset-prefix/_next/static/chunks/9d6e5aad99b19216.js","/litellm-asset-prefix/_next/static/chunks/99cf9cf99df5ccfc.js","/litellm-asset-prefix/_next/static/chunks/fba776c260ae166c.js","/litellm-asset-prefix/_next/static/chunks/b13b0ddeb85b5333.js","/litellm-asset-prefix/_next/static/chunks/54e29148cb2f2582.js","/litellm-asset-prefix/_next/static/chunks/7e417dd24c8becd0.js","/litellm-asset-prefix/_next/static/chunks/09058c1c88c095d7.js"],"default"]
+1a:I[897367,["/litellm-asset-prefix/_next/static/chunks/d96012bcfc98706a.js","/litellm-asset-prefix/_next/static/chunks/dbca964212122d58.js"],"OutletBoundary"]
+1b:"$Sreact.suspense"
 :HL["/litellm-asset-prefix/_next/static/chunks/3f3fa56b5786d58c.css","style"]
-0:{"buildId":"U_YrOOnSehrpkdU42KJ-W","rsc":["$","$1","c",{"children":[["$","$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"}],["$","script","script-0",{"src":"/litellm-asset-prefix/_next/static/chunks/61f59596bf7f0628.js","async":true}],["$","script","script-1",{"src":"/litellm-asset-prefix/_next/static/chunks/9f5ccd929375c1d6.js","async":true}],["$","script","script-2",{"src":"/litellm-asset-prefix/_next/static/chunks/30539b80ac15aad2.js","async":true}],["$","script","script-3",{"src":"/litellm-asset-prefix/_next/static/chunks/142704439974f6b3.js","async":true}],["$","script","script-4",{"src":"/litellm-asset-prefix/_next/static/chunks/8b4fd43197a5dfc8.js","async":true}],["$","script","script-5",{"src":"/litellm-asset-prefix/_next/static/chunks/1fe0596a309ad6cf.js","async":true}],["$","script","script-6",{"src":"/litellm-asset-prefix/_next/static/chunks/7b788dd93ad868b3.js","async":true}],["$","script","script-7",{"src":"/litellm-asset-prefix/_next/static/chunks/c979f252fa5ee77c.js","async":true}],["$","script","script-8",{"src":"/litellm-asset-prefix/_next/static/chunks/50febaabfb896c46.js","async":true}],["$","script","script-9",{"src":"/litellm-asset-prefix/_next/static/chunks/c4cc89d1b0a147d5.js","async":true}],["$","script","script-10",{"src":"/litellm-asset-prefix/_next/static/chunks/fe5201571c777f09.js","async":true}],["$","script","script-11",{"src":"/litellm-asset-prefix/_next/static/chunks/c748f222de4766db.js","async":true}],["$","script","script-12",{"src":"/litellm-asset-prefix/_next/static/chunks/5f9c3b92a016f382.js","async":true}],["$","script","script-13",{"src":"/litellm-asset-prefix/_next/static/chunks/fe750aa0bf04912c.js","async":true}],["$","script","script-14",{"src":"/litellm-asset-prefix/_next/static/chunks/7d4cded1a1238581.js","async":true}],["$","script","script-15",{"src":"/litellm-asset-prefix/_next/static/chunks/d64d74932cb225a3.js","async":true}],["$","script","script-16",{"src":"/litellm-asset-prefix/_next/static/chunks/9ffb8ddd0c9a7c31.js","async":true}],["$","script","script-17",{"src":"/litellm-asset-prefix/_next/static/chunks/c4fe728e74b52958.js","async":true}],["$","script","script-18",{"src":"/litellm-asset-prefix/_next/static/chunks/1532edb438ed84bb.js","async":true}],["$","script","script-19",{"src":"/litellm-asset-prefix/_next/static/chunks/d0d828f9a0668699.js","async":true}],["$","script","script-20",{"src":"/litellm-asset-prefix/_next/static/chunks/88c74f8b4b20d25a.js","async":true}],["$","script","script-21",{"src":"/litellm-asset-prefix/_next/static/chunks/25c5a08661ac2ec3.js","async":true}],["$","script","script-22",{"src":"/litellm-asset-prefix/_next/static/chunks/134f728fa7099e3e.js","async":true}],["$","script","script-23",{"src":"/litellm-asset-prefix/_next/static/chunks/9d6e5aad99b19216.js","async":true}],["$","script","script-24",{"src":"/litellm-asset-prefix/_next/static/chunks/e8718f949e42598e.js","async":true}],["$","script","script-25",{"src":"/litellm-asset-prefix/_next/static/chunks/6a51328383335d1e.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}],["$","script","script-28",{"src":"/litellm-asset-prefix/_next/static/chunks/6a4eede876bb5c8f.js","async":true}],["$","script","script-29",{"src":"/litellm-asset-prefix/_next/static/chunks/7e417dd24c8becd0.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/a85adee4198d5478.js","async":true}],["$","script","script-32",{"src":"/litellm-asset-prefix/_next/static/chunks/bff4459534c52f16.js","async":true}],["$","script","script-33",{"src":"/litellm-asset-prefix/_next/static/chunks/39eb5927f56ccc0e.js","async":true}],"$L6","$L7","$L8","$L9","$La","$Lb","$Lc","$Ld","$Le","$Lf","$L10","$L11","$L12","$L13","$L14","$L15","$L16","$L17","$L18","$L19","$L1a"],"$L1b"]}],"loading":null,"isPartial":false}
+0:{"buildId":"WhBGJTAPhDM3j-59ST728","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"}],["$","script","script-0",{"src":"/litellm-asset-prefix/_next/static/chunks/bb64f18ed439db51.js","async":true}],["$","script","script-1",{"src":"/litellm-asset-prefix/_next/static/chunks/9de031ba49f226b2.js","async":true}],["$","script","script-2",{"src":"/litellm-asset-prefix/_next/static/chunks/30539b80ac15aad2.js","async":true}],["$","script","script-3",{"src":"/litellm-asset-prefix/_next/static/chunks/142704439974f6b3.js","async":true}],["$","script","script-4",{"src":"/litellm-asset-prefix/_next/static/chunks/f0a13680e53afb88.js","async":true}],["$","script","script-5",{"src":"/litellm-asset-prefix/_next/static/chunks/1fe0596a309ad6cf.js","async":true}],["$","script","script-6",{"src":"/litellm-asset-prefix/_next/static/chunks/5f9c3b92a016f382.js","async":true}],["$","script","script-7",{"src":"/litellm-asset-prefix/_next/static/chunks/403c4d96324c23a6.js","async":true}],["$","script","script-8",{"src":"/litellm-asset-prefix/_next/static/chunks/edc62b8625528255.js","async":true}],["$","script","script-9",{"src":"/litellm-asset-prefix/_next/static/chunks/e34ebe113303fbb2.js","async":true}],["$","script","script-10",{"src":"/litellm-asset-prefix/_next/static/chunks/2d471965761a22ff.js","async":true}],["$","script","script-11",{"src":"/litellm-asset-prefix/_next/static/chunks/e8718f949e42598e.js","async":true}],["$","script","script-12",{"src":"/litellm-asset-prefix/_next/static/chunks/3b30ab8eaa03bc21.js","async":true}],["$","script","script-13",{"src":"/litellm-asset-prefix/_next/static/chunks/0bd654557fbb50e9.js","async":true}],["$","script","script-14",{"src":"/litellm-asset-prefix/_next/static/chunks/124fefccff39e221.js","async":true}],["$","script","script-15",{"src":"/litellm-asset-prefix/_next/static/chunks/bb0a6e4a3a18721a.js","async":true}],["$","script","script-16",{"src":"/litellm-asset-prefix/_next/static/chunks/d0d828f9a0668699.js","async":true}],["$","script","script-17",{"src":"/litellm-asset-prefix/_next/static/chunks/4d3d997560b322ca.js","async":true}],["$","script","script-18",{"src":"/litellm-asset-prefix/_next/static/chunks/4e4d0f466b5c1780.js","async":true}],["$","script","script-19",{"src":"/litellm-asset-prefix/_next/static/chunks/88c74f8b4b20d25a.js","async":true}],["$","script","script-20",{"src":"/litellm-asset-prefix/_next/static/chunks/821f45f615724874.js","async":true}],["$","script","script-21",{"src":"/litellm-asset-prefix/_next/static/chunks/2971c4658f1bcd7d.js","async":true}],["$","script","script-22",{"src":"/litellm-asset-prefix/_next/static/chunks/134f728fa7099e3e.js","async":true}],["$","script","script-23",{"src":"/litellm-asset-prefix/_next/static/chunks/9b539d4d807cee27.js","async":true}],["$","script","script-24",{"src":"/litellm-asset-prefix/_next/static/chunks/fc83f709354547bd.js","async":true}],["$","script","script-25",{"src":"/litellm-asset-prefix/_next/static/chunks/853e5f250e7a0af5.js","async":true}],["$","script","script-26",{"src":"/litellm-asset-prefix/_next/static/chunks/348b31083769a7c4.js","async":true}],["$","script","script-27",{"src":"/litellm-asset-prefix/_next/static/chunks/37c03dc421ba81f8.js","async":true}],["$","script","script-28",{"src":"/litellm-asset-prefix/_next/static/chunks/c81bdad246412686.js","async":true}],["$","script","script-29",{"src":"/litellm-asset-prefix/_next/static/chunks/496b84010c33cf69.js","async":true}],["$","script","script-30",{"src":"/litellm-asset-prefix/_next/static/chunks/b6cdb9a433f054f3.js","async":true}],["$","script","script-31",{"src":"/litellm-asset-prefix/_next/static/chunks/fcdf7322b0aa3e2e.js","async":true}],["$","script","script-32",{"src":"/litellm-asset-prefix/_next/static/chunks/6146a0436556bd42.js","async":true}],["$","script","script-33",{"src":"/litellm-asset-prefix/_next/static/chunks/4980372eaa37b78b.js","async":true}],"$L6","$L7","$L8","$L9","$La","$Lb","$Lc","$Ld","$Le","$Lf","$L10","$L11","$L12","$L13","$L14","$L15","$L16","$L17","$L18"],"$L19"]}],"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/ebb2b2d8175d3d2f.js","async":true}]
-7:["$","script","script-35",{"src":"/litellm-asset-prefix/_next/static/chunks/5a5488ab3db0c3de.js","async":true}]
+6:["$","script","script-34",{"src":"/litellm-asset-prefix/_next/static/chunks/90f0529c4408147d.js","async":true}]
+7:["$","script","script-35",{"src":"/litellm-asset-prefix/_next/static/chunks/a85adee4198d5478.js","async":true}]
 8:["$","script","script-36",{"src":"/litellm-asset-prefix/_next/static/chunks/0a65da2cd24e2ab6.js","async":true}]
-9:["$","script","script-37",{"src":"/litellm-asset-prefix/_next/static/chunks/82dbdb17d57c6737.js","async":true}]
-a:["$","script","script-38",{"src":"/litellm-asset-prefix/_next/static/chunks/b31a08272a82b84e.js","async":true}]
-b:["$","script","script-39",{"src":"/litellm-asset-prefix/_next/static/chunks/496b84010c33cf69.js","async":true}]
-c:["$","script","script-40",{"src":"/litellm-asset-prefix/_next/static/chunks/eba9ac65320061b1.js","async":true}]
-d:["$","script","script-41",{"src":"/litellm-asset-prefix/_next/static/chunks/0eda6dc5d5f35d92.js","async":true}]
-e:["$","script","script-42",{"src":"/litellm-asset-prefix/_next/static/chunks/96aed36e606e8582.js","async":true}]
-f:["$","script","script-43",{"src":"/litellm-asset-prefix/_next/static/chunks/ad426ab08aee6c64.js","async":true}]
-10:["$","script","script-44",{"src":"/litellm-asset-prefix/_next/static/chunks/2971c4658f1bcd7d.js","async":true}]
-11:["$","script","script-45",{"src":"/litellm-asset-prefix/_next/static/chunks/06ebe9b0e9cdf241.js","async":true}]
-12:["$","script","script-46",{"src":"/litellm-asset-prefix/_next/static/chunks/6c4c97f1ea6e7d77.js","async":true}]
-13:["$","script","script-47",{"src":"/litellm-asset-prefix/_next/static/chunks/165d00848f04c4c9.js","async":true}]
-14:["$","script","script-48",{"src":"/litellm-asset-prefix/_next/static/chunks/bb0a6e4a3a18721a.js","async":true}]
-15:["$","script","script-49",{"src":"/litellm-asset-prefix/_next/static/chunks/4980372eaa37b78b.js","async":true}]
-16:["$","script","script-50",{"src":"/litellm-asset-prefix/_next/static/chunks/8ab6e2ca95000c8e.js","async":true}]
-17:["$","script","script-51",{"src":"/litellm-asset-prefix/_next/static/chunks/06cdd9bb80c63794.js","async":true}]
-18:["$","script","script-52",{"src":"/litellm-asset-prefix/_next/static/chunks/66a190706fc6c35a.js","async":true}]
-19:["$","script","script-53",{"src":"/litellm-asset-prefix/_next/static/chunks/54e29148cb2f2582.js","async":true}]
-1a:["$","script","script-54",{"src":"/litellm-asset-prefix/_next/static/chunks/fd9de419c8c0222e.js","async":true}]
-1b:["$","$L1c",null,{"children":["$","$1d",null,{"name":"Next.MetadataOutlet","children":"$@1e"}]}]
-1e:null
+9:["$","script","script-37",{"src":"/litellm-asset-prefix/_next/static/chunks/8604d59a86c051be.js","async":true}]
+a:["$","script","script-38",{"src":"/litellm-asset-prefix/_next/static/chunks/d3ac82723ec9e30d.js","async":true}]
+b:["$","script","script-39",{"src":"/litellm-asset-prefix/_next/static/chunks/664bbc28119f9cc1.js","async":true}]
+c:["$","script","script-40",{"src":"/litellm-asset-prefix/_next/static/chunks/d64d74932cb225a3.js","async":true}]
+d:["$","script","script-41",{"src":"/litellm-asset-prefix/_next/static/chunks/0adb91ab5f3140d5.js","async":true}]
+e:["$","script","script-42",{"src":"/litellm-asset-prefix/_next/static/chunks/5c6d02376dbf0f55.js","async":true}]
+f:["$","script","script-43",{"src":"/litellm-asset-prefix/_next/static/chunks/85238af541b170ca.js","async":true}]
+10:["$","script","script-44",{"src":"/litellm-asset-prefix/_next/static/chunks/06ebe9b0e9cdf241.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/9d6e5aad99b19216.js","async":true}]
+13:["$","script","script-47",{"src":"/litellm-asset-prefix/_next/static/chunks/99cf9cf99df5ccfc.js","async":true}]
+14:["$","script","script-48",{"src":"/litellm-asset-prefix/_next/static/chunks/fba776c260ae166c.js","async":true}]
+15:["$","script","script-49",{"src":"/litellm-asset-prefix/_next/static/chunks/b13b0ddeb85b5333.js","async":true}]
+16:["$","script","script-50",{"src":"/litellm-asset-prefix/_next/static/chunks/54e29148cb2f2582.js","async":true}]
+17:["$","script","script-51",{"src":"/litellm-asset-prefix/_next/static/chunks/7e417dd24c8becd0.js","async":true}]
+18:["$","script","script-52",{"src":"/litellm-asset-prefix/_next/static/chunks/09058c1c88c095d7.js","async":true}]
+19:["$","$L1a",null,{"children":["$","$1b",null,{"name":"Next.MetadataOutlet","children":"$@1c"}]}]
+1c: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
@ -3,4 +3,4 @@
 3:I[897367,["/litellm-asset-prefix/_next/static/chunks/d96012bcfc98706a.js","/litellm-asset-prefix/_next/static/chunks/dbca964212122d58.js"],"MetadataBoundary"]
 4:"$Sreact.suspense"
 5:I[27201,["/litellm-asset-prefix/_next/static/chunks/d96012bcfc98706a.js","/litellm-asset-prefix/_next/static/chunks/dbca964212122d58.js"],"IconMark"]
-0:{"buildId":"U_YrOOnSehrpkdU42KJ-W","rsc":["$","$1","h",{"children":[null,["$","$L2",null,{"children":[["$","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}
+0:{"buildId":"WhBGJTAPhDM3j-59ST728","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
@ -1,7 +1,8 @@
 1:"$Sreact.fragment"
-2:I[71195,["/litellm-asset-prefix/_next/static/chunks/26adfa4e8ffc85c7.js","/litellm-asset-prefix/_next/static/chunks/e8ed72789c2b42ff.js"],"default"]
-3:I[339756,["/litellm-asset-prefix/_next/static/chunks/d96012bcfc98706a.js","/litellm-asset-prefix/_next/static/chunks/dbca964212122d58.js"],"default"]
-4:I[837457,["/litellm-asset-prefix/_next/static/chunks/d96012bcfc98706a.js","/litellm-asset-prefix/_next/static/chunks/dbca964212122d58.js"],"default"]
+2:I[867271,["/litellm-asset-prefix/_next/static/chunks/a7f104aa2cc7f3f0.js","/litellm-asset-prefix/_next/static/chunks/e8ed72789c2b42ff.js"],"default"]
+3:I[71195,["/litellm-asset-prefix/_next/static/chunks/a7f104aa2cc7f3f0.js","/litellm-asset-prefix/_next/static/chunks/e8ed72789c2b42ff.js"],"default"]
+4:I[339756,["/litellm-asset-prefix/_next/static/chunks/d96012bcfc98706a.js","/litellm-asset-prefix/_next/static/chunks/dbca964212122d58.js"],"default"]
+5:I[837457,["/litellm-asset-prefix/_next/static/chunks/d96012bcfc98706a.js","/litellm-asset-prefix/_next/static/chunks/dbca964212122d58.js"],"default"]
 :HL["/litellm-asset-prefix/_next/static/chunks/4e20891f2fd03463.css","style"]
-:HL["/litellm-asset-prefix/_next/static/chunks/6fabf2cec1bd2d6e.css","style"]
-0:{"buildId":"U_YrOOnSehrpkdU42KJ-W","rsc":["$","$1","c",{"children":[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/chunks/4e20891f2fd03463.css","precedence":"next"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/chunks/6fabf2cec1bd2d6e.css","precedence":"next"}],["$","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}
+:HL["/litellm-asset-prefix/_next/static/chunks/7936c9bd377ea4bf.css","style"]
+0:{"buildId":"WhBGJTAPhDM3j-59ST728","rsc":["$","$1","c",{"children":[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/chunks/4e20891f2fd03463.css","precedence":"next"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/chunks/7936c9bd377ea4bf.css","precedence":"next"}],["$","script","script-0",{"src":"/litellm-asset-prefix/_next/static/chunks/a7f104aa2cc7f3f0.js","async":true}],["$","script","script-1",{"src":"/litellm-asset-prefix/_next/static/chunks/e8ed72789c2b42ff.js","async":true}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"inter_5972bc34-module__OU16Qa__className","children":["$","$L2",null,{"children":["$","$L3",null,{"children":["$","$L4",null,{"parallelRouterKey":"children","template":["$","$L5",null,{}],"notFound":[[["$","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
@ -1,5 +1,5 @@
 :HL["/litellm-asset-prefix/_next/static/chunks/4e20891f2fd03463.css","style"]
-:HL["/litellm-asset-prefix/_next/static/chunks/6fabf2cec1bd2d6e.css","style"]
+:HL["/litellm-asset-prefix/_next/static/chunks/7936c9bd377ea4bf.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":"U_YrOOnSehrpkdU42KJ-W","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}
+0:{"buildId":"WhBGJTAPhDM3j-59ST728","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/WhBGJTAPhDM3j-59ST728/_buildManifest.js
+++ b/litellm/proxy/_experimental/out/_next/static/WhBGJTAPhDM3j-59ST728/_buildManifest.js
--- a/litellm/proxy/_experimental/out/_next/static/WhBGJTAPhDM3j-59ST728/_clientMiddlewareManifest.json
+++ b/litellm/proxy/_experimental/out/_next/static/WhBGJTAPhDM3j-59ST728/_clientMiddlewareManifest.json
--- a/litellm/proxy/_experimental/out/_next/static/WhBGJTAPhDM3j-59ST728/_ssgManifest.js
+++ b/litellm/proxy/_experimental/out/_next/static/WhBGJTAPhDM3j-59ST728/_ssgManifest.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/0184f3b07b67e571.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/0184f3b07b67e571.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/02765645e0bbd8f7.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/02765645e0bbd8f7.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/0289c4377358ae4f.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/0289c4377358ae4f.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/02b4612136350b79.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/02b4612136350b79.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/02b5f26d5e34d4ec.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/02b5f26d5e34d4ec.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/04a69f0d1ec0d10f.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/04a69f0d1ec0d10f.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/052676b05389fa51.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/052676b05389fa51.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/056b4991f668b494.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/056b4991f668b494.js
@ -0,0 +1 @@
+(globalThis.TURBOPACK||(globalThis.TURBOPACK=[])).push(["object"==typeof document?document.currentScript:void 0,233525,(e,c,u)=>{"use strict";Object.defineProperty(u,"__esModule",{value:!0}),Object.defineProperty(u,"warnOnce",{enumerable:!0,get:function(){return r}});let r=e=>{}},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"})},928685,e=>{"use strict";var c=e.i(38953);e.s(["SearchOutlined",()=>c.default])},86408,e=>{"use strict";var c=e.i(843476),u=e.i(271645),r=e.i(618566),t=e.i(934879);function a(){let e=(0,r.useSearchParams)().get("key"),[a,i]=(0,u.useState)(null);return console.log("PublicModelHubTable accessToken:",a),(0,u.useEffect)(()=>{e&&i(e)},[e]),(0,c.jsx)(t.default,{accessToken:a,publicPage:!0,premiumUser:!1,userRole:null})}function i(){return(0,c.jsx)(u.Suspense,{fallback:(0,c.jsx)("div",{className:"flex items-center justify-center min-h-screen",children:"Loading..."}),children:(0,c.jsx)(a,{})})}e.s(["default",()=>i])}]);
--- a/litellm/proxy/_experimental/out/_next/static/chunks/066f513556b1bb0b.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/066f513556b1bb0b.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/0691430f3293d02d.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/0691430f3293d02d.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/06cdd9bb80c63794.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/06cdd9bb80c63794.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/06fcc87de3bb3ff8.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/06fcc87de3bb3ff8.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/082f482bd4c6ecfb.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/082f482bd4c6ecfb.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/09058c1c88c095d7.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/09058c1c88c095d7.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/0a55aff89c1ec2e4.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/0a55aff89c1ec2e4.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/0adb91ab5f3140d5.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/0adb91ab5f3140d5.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/0bd654557fbb50e9.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/0bd654557fbb50e9.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/0ed98235bd6bf63a.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/0ed98235bd6bf63a.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/0eda6dc5d5f35d92.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/0eda6dc5d5f35d92.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/10a902acb31b2e0d.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/10a902acb31b2e0d.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/1153e633ed18e0bd.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/1153e633ed18e0bd.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/124fefccff39e221.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/124fefccff39e221.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/125e23733670afea.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/125e23733670afea.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/12a00fb6ae67dbdf.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/12a00fb6ae67dbdf.js
--- a/litellm/proxy/_experimental/out/_next/static/chunks/12b229c40945c2e9.js
+++ b/litellm/proxy/_experimental/out/_next/static/chunks/12b229c40945c2e9.js
--- a/Show more
+++ b/Show more
				`@ -0,0 +1 @@`
				(globalThis.TURBOPACK\|\|(globalThis.TURBOPACK=[])).push(["object"==typeof document?document.currentScript:void 0,233525,(e,c,u)=>{"use strict";Object.defineProperty(u,"__esModule",{value:!0}),Object.defineProperty(u,"warnOnce",{enumerable:!0,get:function(){return r}});let r=e=>{}},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"})},928685,e=>{"use strict";var c=e.i(38953);e.s(["SearchOutlined",()=>c.default])},86408,e=>{"use strict";var c=e.i(843476),u=e.i(271645),r=e.i(618566),t=e.i(934879);function a(){let e=(0,r.useSearchParams)().get("key"),[a,i]=(0,u.useState)(null);return console.log("PublicModelHubTable accessToken:",a),(0,u.useEffect)(()=>{e&&i(e)},[e]),(0,c.jsx)(t.default,{accessToken:a,publicPage:!0,premiumUser:!1,userRole:null})}function i(){return(0,c.jsx)(u.Suspense,{fallback:(0,c.jsx)("div",{className:"flex items-center justify-center min-h-screen",children:"Loading..."}),children:(0,c.jsx)(a,{})})}e.s(["default",()=>i])}]);