scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-16 23:41:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

merge origin/main, resolve conflict in vertex gemini schema transform

Browse source 
Made-with: Cursor
This commit is contained in:
pradyyadav 2026-03-13 00:48:49 +05:30
commit bd0e92926a
668 changed files with 20099 additions and 4937 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
.circleci/config.yml
View file

@ -4337,7 +4337,8 @@ jobs:
name: Check for expected error
command: |
if grep -q "Error: P1001: Can't reach database server at" docker_output.log && \
grep -q "ERROR: Application startup failed. Exiting." docker_output.log; then
(grep -q "Database setup failed after multiple retries" docker_output.log || \
grep -q "ERROR: Application startup failed. Exiting." docker_output.log); then
echo "Expected error found. Test passed."
else
echo "Expected error not found. Test failed."

16
CLAUDE.md
View file

@ -102,6 +102,22 @@ LiteLLM is a unified interface for 100+ LLM providers with two main components:
### UI / Backend Consistency
- When wiring a new UI entity type to an existing backend endpoint, verify the backend API contract (single value vs. array, required vs. optional params) and ensure the UI controls match — e.g., use a single-select dropdown when the backend accepts a single value, not a multi-select
### MCP OAuth / OpenAPI Transport Mapping
- `TRANSPORT.OPENAPI` is a UI-only concept. The backend only accepts `"http"`, `"sse"`, or `"stdio"`. Always map it to `"http"` before any API call (including pre-OAuth temp-session calls).
- FastAPI validation errors return `detail` as an array of `{loc, msg, type}` objects. Error extractors must handle: array (map `.msg`), string, nested `{error: string}`, and fallback.
- When an MCP server already has `authorization_url` stored, skip OAuth discovery (`_discovery_metadata`) — the server URL for OpenAPI MCPs is the spec file, not the API base, and fetching it causes timeouts.
- `client_id` should be optional in the `/authorize` endpoint — if the server has a stored `client_id` in credentials, use that. Never require callers to re-supply it.
### MCP Credential Storage
- OAuth credentials and BYOK credentials share the `litellm_mcpusercredentials` table, distinguished by a `"type"` field in the JSON payload (`"oauth2"` vs plain string).
- When deleting OAuth credentials, check type before deleting to avoid accidentally deleting a BYOK credential for the same `(user_id, server_id)` pair.
- Always pass the raw `expires_at` timestamp to the client — never set it to `None` for expired credentials. Let the frontend compute the "Expired" display state from the timestamp.
- Use `RecordNotFoundError` (not bare `except Exception`) when catching "already deleted" in credential delete endpoints.
### Browser Storage Safety (UI)
- Never write LiteLLM access tokens or API keys to `localStorage` — use `sessionStorage` only. `localStorage` survives browser close and is readable by any injected script (XSS).
- Shared utility functions (e.g. `extractErrorMessage`) belong in `src/utils/` — never define them inline in hooks or duplicate them across files.
### Database Migrations
- Prisma handles schema migrations
- Migration files auto-generated with `prisma migrate dev`

119
docs/my-website/blog/realtime_webrtc_http_endpoints/index.md Normal file
View file

@ -0,0 +1,119 @@
---
slug: realtime_webrtc_http_endpoints
title: "Realtime WebRTC HTTP Endpoints"
date: 2026-03-12T10:00:00
authors:
- name: Sameer Kankute
title: SWE @ LiteLLM (LLM Translation)
url: https://www.linkedin.com/in/sameer-kankute/
image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
- name: Krrish Dholakia
title: "CEO, LiteLLM"
url: https://www.linkedin.com/in/krish-d/
image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
- name: Ishaan Jaff
title: "CTO, LiteLLM"
url: https://www.linkedin.com/in/reffajnaahsi/
image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
description: "Use the LiteLLM proxy to route OpenAI-style WebRTC realtime via HTTP: client_secrets and SDP exchange."
tags: [realtime, webrtc, proxy, openai]
hide_table_of_contents: false
---
import WebRTCTester from '@site/src/components/WebRTCTester';
Connect to the Realtime API via WebRTC from browser/mobile clients. LiteLLM handles auth and key management.
## How it works
![WebRTC flow: Browser, LiteLLM Proxy, and OpenAI/Azure](../../img/webrtc_flow.png)
**Flow of generating ephemeral token**
![Ephemeral token flow: Browser requests token, LiteLLM gets real token from OpenAI, returns encrypted token](../../img/ephemeral_token.png)
## Proxy Setup
```yaml
model_list:
- model_name: gpt-4o-realtime
litellm_params:
model: openai/gpt-4o-realtime-preview-2024-12-17
api_key: os.environ/OPENAI_API_KEY
model_info:
mode: realtime
```
**Azure:** use `model: azure/gpt-4o-realtime-preview`, `api_key`, `api_base`.
```bash
litellm --config /path/to/config.yaml
```
## Try it live
<WebRTCTester />
## Client Usage
**1. Get token** - `POST /v1/realtime/client_secrets` with LiteLLM API key and `{ model }`.
**2. WebRTC handshake** - Create `RTCPeerConnection`, add mic track, create data channel `oai-events`, send SDP offer to `POST /v1/realtime/calls` with `Authorization: Bearer <encrypted_token>` and `Content-Type: application/sdp`.
**3. Events** - Use the data channel for `session.update` and other events.
<details>
<summary>Full code example</summary>
```javascript
// 1. Token
const r = await fetch("http://proxy:4000/v1/realtime/client_secrets", {
method: "POST",
headers: { "Authorization": "Bearer sk-litellm-key", "Content-Type": "application/json" },
body: JSON.stringify({ model: "gpt-4o-realtime" }),
});
const { client_secret } = await r.json();
const token = client_secret.value;
// 2. WebRTC
const pc = new RTCPeerConnection();
const audio = document.createElement("audio");
audio.autoplay = true;
pc.ontrack = (e) => (audio.srcObject = e.streams[0]);
const ms = await navigator.mediaDevices.getUserMedia({ audio: true });
pc.addTrack(ms.getTracks()[0]);
const dc = pc.createDataChannel("oai-events");
const offer = await pc.createOffer();
await pc.setLocalDescription(offer);
const sdpRes = await fetch("http://proxy:4000/v1/realtime/calls", {
method: "POST",
headers: { "Authorization": `Bearer ${token}`, "Content-Type": "application/sdp" },
body: offer.sdp,
});
await pc.setRemoteDescription({ type: "answer", sdp: await sdpRes.text() });
// 3. Events
dc.send(JSON.stringify({ type: "session.update", session: { instructions: "..." } }));
```
</details>
## FAQ
**Q: What do I do if I get a 401 Token expired error?**
A: Tokens are short-lived. Get a fresh token right before creating the WebRTC offer.
**Q: Which key should I use for `/v1/realtime/calls`?**
A: Use the **encrypted token** from `client_secrets`, not your raw API key.
**Q: Should I pass the `model` parameter when making the call?**
A: No, the encrypted token already encodes all routing information including model.
**Q: How do I resolve Azure `api-version` errors?**
A: Set the correct `api_version` in `litellm_params` (or via the `AZURE_API_VERSION` environment variable), along with the right `api_base` and deployment values.
**Q: What if I get no audio?**
A: Make sure you grant microphone permission, ensure `pc.ontrack` assigns the audio element with `autoplay` enabled, check your network/firewall for WebRTC traffic, and inspect the browser console for ICE or SDP errors.

2
docs/my-website/docs/proxy/config_settings.md
View file

@ -944,7 +944,7 @@ 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_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

6
docs/my-website/docs/proxy/guardrails/guardrail_policies.md
View file

@ -309,6 +309,10 @@ Response:
</TabItem>
</Tabs>
## Policy Flow Builder
For conditional execution (e.g., run a second guardrail only if the first fails), use the [Policy Flow Builder](./policy_flow_builder) to define pipelines with per-step pass/fail actions.
## Config Reference
### `policies`
@ -323,6 +327,7 @@ policies:
remove: [...]
condition:
model: ...
pipeline: ... # optional; see Policy Flow Builder
```
| Field | Type | Description |
@ -332,6 +337,7 @@ policies:
| `guardrails.add` | `list[string]` | Guardrails to enable. |
| `guardrails.remove` | `list[string]` | Guardrails to disable (useful with inheritance). |
| `condition.model` | `string` or `list[string]` | Optional. Only apply when model matches. Supports regex. |
| `pipeline` | `object` | Optional. Ordered guardrail execution with per-step actions. See [Policy Flow Builder](./policy_flow_builder). |
### `policy_attachments`

219
docs/my-website/docs/proxy/guardrails/policy_flow_builder.md Normal file
View file

@ -0,0 +1,219 @@
# Policy Flow Builder
The Policy Flow Builder lets you design guardrail pipelines with **conditional execution**. Instead of running guardrails independently, you chain them into ordered steps and control what happens when each guardrail passes or fails.
Two powerful patterns it enables: **guardrail fallbacks** (try a different guardrail when one fails) and **retrying the same guardrail** (run the same guardrail again if it fails, e.g. to handle transient errors).
## When to use the Flow Builder
| Approach | Use case |
|----------|----------|
| **Simple policy** (`guardrails.add`) | All guardrails run in parallel; any failure blocks the request. |
| **Flow Builder** (pipeline) | Guardrails run in sequence; you choose actions per step (next, block, allow, custom response). |
Use the Flow Builder when you need:
- **Guardrail fallbacks** — use `on_fail: next` to try a different guardrail when one fails (e.g., fast filter → stricter filter)
- **Retrying the same guardrail** — add the same guardrail as multiple steps; if it fails, `on_fail: next` moves to the next step, which can be the same guardrail again (useful for transient API errors or rate limits)
- **Conditional routing** — e.g., if a fast guardrail fails, run a more advanced one instead of blocking immediately
- **Custom responses** — return a specific message when a guardrail fails instead of a generic block
- **Data chaining** — pass modified data (e.g., PII-masked content) from one step to the next
- **Fine-grained control** — different actions on pass vs. fail per step
## Concepts
### Pipeline
A pipeline has:
- **Mode**: `pre_call` (before the LLM) or `post_call` (after the LLM)
- **Steps**: Ordered list of guardrail steps
### Step actions
Each step defines what happens when the guardrail **passes** and when it **fails**:
| Action | Description |
|--------|-------------|
| **Next Step** | Continue to the next guardrail in the pipeline |
| **Allow** | Stop the pipeline and allow the request to proceed |
| **Block** | Stop the pipeline and block the request |
| **Custom Response** | Return a custom message instead of the default block |
### Step options
| Field | Type | Description |
|-------|------|--------------|
| `guardrail` | `string` | Name of the guardrail to run |
| `on_pass` | `string` | Action when guardrail passes: `next`, `allow`, `block`, `modify_response` |
| `on_fail` | `string` | Action when guardrail fails: `next`, `allow`, `block`, `modify_response` |
| `pass_data` | `boolean` | Forward modified request data (e.g., PII-masked) to the next step |
| `modify_response_message` | `string` | Custom message when using `modify_response` action |
## Using the Flow Builder (UI)
1. Go to **Policies** in the LiteLLM Admin UI
2. Click **+ Create New Policy** or **Edit** on an existing policy
3. Select **Flow Builder** (instead of the simple form)
4. Design your flow:
- **Trigger** — Incoming LLM request (runs when the policy matches)
- **Steps** — Add guardrails, set ON PASS and ON FAIL actions per step
- **End** — Request proceeds to the LLM
5. Use the **+** between steps to insert new steps
6. Use the **Test** panel to run sample messages through the pipeline before saving
7. Click **Save** to create or update the policy
## Config (YAML)
Define a pipeline in your policy config:
```yaml showLineNumbers title="config.yaml"
guardrails:
- guardrail_name: pii_masking
litellm_params:
guardrail: presidio
mode: pre_call
- guardrail_name: prompt_injection
litellm_params:
guardrail: lakera
mode: pre_call
policies:
my-pipeline-policy:
description: "PII mask first, then check for prompt injection"
guardrails:
add:
- pii_masking
- prompt_injection
pipeline:
mode: pre_call
steps:
- guardrail: pii_masking
on_pass: next
on_fail: block
pass_data: true
- guardrail: prompt_injection
on_pass: allow
on_fail: block
policy_attachments:
- policy: my-pipeline-policy
scope: "*"
```
## Fallbacks and retries
### Guardrail fallbacks
Use `on_fail: next` to fall back to another guardrail when one fails. Run a lightweight guardrail first; if it fails, escalate to a stricter or different provider:
```yaml
policies:
fallback-policy:
guardrails:
add:
- fast_content_filter
- strict_content_filter
pipeline:
mode: pre_call
steps:
- guardrail: fast_content_filter
on_pass: allow
on_fail: next
- guardrail: strict_content_filter
on_pass: allow
on_fail: block
```
If `fast_content_filter` passes → allow. If it fails → run `strict_content_filter`; pass → allow, fail → block.
### Retrying the same guardrail
Add the same guardrail as multiple steps to retry on failure. Useful for transient errors (API timeouts, rate limits):
```yaml
policies:
retry-policy:
guardrails:
add:
- lakera_prompt_injection
pipeline:
mode: pre_call
steps:
- guardrail: lakera_prompt_injection
on_pass: allow
on_fail: next
- guardrail: lakera_prompt_injection
on_pass: allow
on_fail: block
```
First attempt passes → allow. First attempt fails → retry the same guardrail; second pass → allow, second fail → block.
## Example: Custom response on fail
Return a branded message instead of a generic block:
```yaml
policies:
branded-block-policy:
guardrails:
add:
- pii_detector
pipeline:
mode: pre_call
steps:
- guardrail: pii_detector
on_pass: allow
on_fail: modify_response
modify_response_message: "Your message contains sensitive information. Please remove PII and try again."
```
## Test a pipeline (API)
Test a pipeline with sample messages before attaching it:
```bash
curl -X POST "http://localhost:4000/policies/test-pipeline" \
-H "Authorization: Bearer <your_api_key>" \
-H "Content-Type: application/json" \
-d '{
"pipeline": {
"mode": "pre_call",
"steps": [
{
"guardrail": "pii_masking",
"on_pass": "next",
"on_fail": "block",
"pass_data": true
},
{
"guardrail": "prompt_injection",
"on_pass": "allow",
"on_fail": "block"
}
]
},
"test_messages": [
{"role": "user", "content": "What is 2+2?"},
{"role": "user", "content": "My SSN is 123-45-6789"}
]
}'
```
Response includes per-step outcomes (pass/fail/error), actions taken, and timing.
## Pipeline vs simple policy
When a policy has a `pipeline`, the pipeline defines execution order and actions. The `guardrails.add` list must include all guardrails used in the pipeline steps.
| Policy type | Execution |
|-------------|-----------|
| Simple (`guardrails.add` only) | All guardrails run; any failure blocks |
| Pipeline (`pipeline` present) | Steps run in order; actions control flow |
## Related docs
- [Guardrail Policies](./guardrail_policies) — Policy basics, attachments, inheritance
- [Policy Templates](./policy_templates) — Pre-built policy templates

84
docs/my-website/docs/proxy/realtime_webrtc.md Normal file
View file

@ -0,0 +1,84 @@
# /realtime - WebRTC Support
Connect to the Realtime API via WebRTC from browser/mobile clients. LiteLLM handles auth; audio streams directly to OpenAI/Azure.
**Providers:** OpenAI · Azure
:::info **WebRTC vs WebSocket**
- **WebSocket** (`/v1/realtime`) — server-to-server
- **WebRTC** (`/v1/realtime/client_secrets` + `/v1/realtime/calls`) — browser/mobile, lower latency
:::
## How it works
LiteLLM issues tokens and relays SDP; audio never passes through the proxy.
```
Browser LiteLLM Proxy OpenAI/Azure
| | |
|-- POST client_secrets --->|-- POST sessions -------->|
|<-- encrypted_token -------|<-- ek_... ---------------|
|-- POST calls [SDP+token] ->|-- POST calls ----------->|
|<-- SDP answer ------------|<-- SDP answer -----------|
|===== audio P2P direct ===============================>|
```
## Proxy Setup
```yaml
model_list:
- model_name: gpt-4o-realtime
litellm_params:
model: openai/gpt-4o-realtime-preview-2024-12-17
api_key: os.environ/OPENAI_API_KEY
model_info:
mode: realtime
```
**Azure:** `model: azure/gpt-4o-realtime-preview`, `api_key`, `api_base`.
```bash
litellm --config /path/to/config.yaml
```
## Client Usage
1. **Token** — `POST /v1/realtime/client_secrets` with LiteLLM key and `{ model }`.
2. **WebRTC** — Create `RTCPeerConnection`, add mic, data channel `oai-events`, send SDP offer to `POST /v1/realtime/calls` with `Authorization: Bearer <token>`, `Content-Type: application/sdp`.
3. **Events** — Use data channel for `session.update` and other events.
```javascript
const r = await fetch("http://proxy:4000/v1/realtime/client_secrets", {
method: "POST",
headers: { "Authorization": "Bearer sk-litellm-key", "Content-Type": "application/json" },
body: JSON.stringify({ model: "gpt-4o-realtime" }),
});
const token = (await r.json()).client_secret.value;
const pc = new RTCPeerConnection();
const audio = document.createElement("audio");
audio.autoplay = true;
pc.ontrack = (e) => (audio.srcObject = e.streams[0]);
const ms = await navigator.mediaDevices.getUserMedia({ audio: true });
pc.addTrack(ms.getTracks()[0]);
const dc = pc.createDataChannel("oai-events");
const offer = await pc.createOffer();
await pc.setLocalDescription(offer);
const sdpRes = await fetch("http://proxy:4000/v1/realtime/calls", {
method: "POST",
headers: { "Authorization": `Bearer ${token}`, "Content-Type": "application/sdp" },
body: offer.sdp,
});
await pc.setRemoteDescription({ type: "answer", sdp: await sdpRes.text() });
dc.send(JSON.stringify({ type: "session.update", session: { instructions: "..." } }));
```
## FAQ
- **401 Token expired** — Get a fresh token right before creating the WebRTC offer.
- **Which key for `/calls`?** — Encrypted token from `client_secrets`, not raw key.
- **Pass `model`?** — No. Token encodes routing.
- **Azure `api-version`** — Set `api_version` in `litellm_params` and correct `api_base`.
- **No audio** — Grant mic; ensure `pc.ontrack` sets autoplay audio; check firewall/WebRTC; inspect console.

BIN
docs/my-website/img/ephemeral_token.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 290 KiB

BIN
docs/my-website/img/webrtc_flow.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 238 KiB

4
docs/my-website/release_notes/v1.82.0.md
View file

@ -1,5 +1,5 @@
---
title: "[Preview] v1.82.0 - Realtime Guardrails, Projects Management, and 10+ Performance Optimizations"
title: "v1.82.0 - Realtime Guardrails, Projects Management, and 10+ Performance Optimizations"
slug: "v1-82-0"
date: 2026-02-28T00:00:00
authors:
@ -26,7 +26,7 @@ import TabItem from '@theme/TabItem';
docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-1.82.0
ghcr.io/berriai/litellm:main-1.82.0-stable
```
</TabItem>

2
docs/my-website/sidebars.js
View file

@ -100,6 +100,7 @@ const sidebars = {
label: "Policies",
items: [
"proxy/guardrails/guardrail_policies",
"proxy/guardrails/policy_flow_builder",
"proxy/guardrails/policy_templates",
"proxy/guardrails/policy_tags",
],
@ -668,6 +669,7 @@ const sidebars = {
"rag_ingest",
"rag_query",
"realtime",
"proxy/realtime_webrtc",
"rerank",
"response_api",
"response_api_compact",

83
docs/my-website/src/components/WebRTCTester.jsx Normal file
View file

@ -0,0 +1,83 @@
import DashboardWebRTCTester from "../../../../ui/litellm-dashboard/src/components/WebRTCTester.jsx";
const LIGHT_MODE_OVERRIDES = `
.wrt-wrap {
background: #1f2937;
border: 1px solid #334155;
}
.wrt-toggle,
.wrt-toggle:hover {
background: #111827;
}
.wrt-toggle-title,
.we-msg {
color: #e2e8f0;
}
.wrt-toggle-sub,
.wrt-label,
.wrt-field label,
.wrt-flow-box,
.wrt-flow-arrow,
.wrt-meta-row span:first-child,
.wrt-header-title,
.wrt-tab,
.we-time {
color: #94a3b8;
}
.wrt-body,
.wrt-sidebar,
.wrt-main,
.wrt-header,
.wrt-tabs,
.wrt-sdp-box,
.wrt-sdp-hdr,
.wrt-divider {
border-color: #334155;
}
.wrt-header {
background: #111827;
}
.wrt-field input,
.wrt-mic-btn,
.wrt-status-pill {
background: #0b1220;
border-color: #334155;
color: #e2e8f0;
}
.wrt-field input:focus,
.wrt-btn-ghost:hover {
border-color: #60a5fa;
}
.wrt-btn-ghost {
background: #0b1220;
border-color: #334155;
color: #e2e8f0;
}
.wrt-log::-webkit-scrollbar-thumb {
background: #475569;
}
.wrt-tab.active {
color: #93c5fd;
border-bottom-color: #93c5fd;
}
.wrt-empty,
.wrt-audio-status,
.wrt-meta-row span:last-child {
color: #cbd5e1;
}
.wrt-sdp-dot {
background: #475569;
}
.wrt-sdp-pane textarea {
color: #e2e8f0;
}
`;
export default function WebRTCTester() {
return (
<>
<DashboardWebRTCTester />
<style>{LIGHT_MODE_OVERRIDES}</style>
</>
);
}

BIN
litellm-proxy-extras/dist/litellm_proxy_extras-0.4.54-py3-none-any.whl vendored Normal file
View file

Binary file not shown.

BIN
litellm-proxy-extras/dist/litellm_proxy_extras-0.4.54.tar.gz vendored Normal file
View file

Binary file not shown.

13
litellm-proxy-extras/litellm_proxy_extras/migrations/20260309115809_add_missing_indexes/migration.sql
View file

@ -1,13 +0,0 @@
-- SkipTransactionBlock
-- Drop invalid indexes left behind by failed CONCURRENTLY builds
DROP INDEX CONCURRENTLY IF EXISTS "LiteLLM_VerificationToken_key_alias_idx";
-- CreateIndex
CREATE INDEX CONCURRENTLY "LiteLLM_VerificationToken_key_alias_idx" ON "LiteLLM_VerificationToken"("key_alias");
-- Drop invalid indexes left behind by failed CONCURRENTLY builds
DROP INDEX CONCURRENTLY IF EXISTS "LiteLLM_SpendLogs_user_startTime_idx";
-- CreateIndex
CREATE INDEX CONCURRENTLY "LiteLLM_SpendLogs_user_startTime_idx" ON "LiteLLM_SpendLogs"("user", "startTime");

11
litellm-proxy-extras/litellm_proxy_extras/migrations/20260311180521_schema_sync/migration.sql Normal file
View file

@ -0,0 +1,11 @@
-- DropIndex
DROP INDEX "LiteLLM_MCPServerTable_approval_status_idx";
-- AlterTable
ALTER TABLE "LiteLLM_MCPServerTable" DROP COLUMN "approval_status",
DROP COLUMN "review_notes",
DROP COLUMN "reviewed_at",
DROP COLUMN "source_url",
DROP COLUMN "submitted_at",
DROP COLUMN "submitted_by";

12
litellm-proxy-extras/litellm_proxy_extras/schema.prisma
View file

@ -267,6 +267,7 @@ model LiteLLM_ObjectPermissionTable {
vector_stores String[] @default([])
agents String[] @default([])
agent_access_groups String[] @default([])
models String[] @default([])
blocked_tools String[] @default([]) // Tool names blocked for any key/team/user with this permission
teams LiteLLM_TeamTable[]
projects LiteLLM_ProjectTable[]
@ -315,6 +316,11 @@ model LiteLLM_MCPServerTable {
is_byok Boolean @default(false)
byok_description String[] @default([])
byok_api_key_help_url String?
approval_status String @default("approved")
submitted_by String?
submitted_at DateTime?
reviewed_at DateTime?
review_notes String?
}
// Per-user BYOK credentials for MCP servers
@ -388,9 +394,6 @@ model LiteLLM_VerificationToken {
// SELECT ... FROM "public"."LiteLLM_VerificationToken" WHERE (("public"."LiteLLM_VerificationToken"."expires" IS NULL OR "public"."LiteLLM_VerificationToken"."expires" > $1) AND "public"."LiteLLM_VerificationToken"."budget_reset_at" < $2) OFFSET $3
@@index([budget_reset_at, expires])
// SELECT ... FROM "public"."LiteLLM_VerificationToken" WHERE (...) ORDER BY "public"."LiteLLM_VerificationToken"."key_alias" ASC
@@index([key_alias])
}
model LiteLLM_JWTKeyMapping {
@ -556,9 +559,6 @@ model LiteLLM_SpendLogs {
@@index([startTime, request_id])
@@index([end_user])
@@index([session_id])
// SELECT ... FROM "LiteLLM_SpendLogs" WHERE ("startTime" >= $1 AND "startTime" <= $2 AND "user" = $3) GROUP BY ...
@@index([user, startTime])
}
// View spend, model, api_key per request

4
litellm-proxy-extras/pyproject.toml
View file

@ -1,6 +1,6 @@
[tool.poetry]
name = "litellm-proxy-extras"
version = "0.4.53"
version = "0.4.54"
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 = "0.4.53"
version = "0.4.54"
version_files = [
"pyproject.toml:version",
"../requirements.txt:litellm-proxy-extras==",

2
litellm/__init__.py
View file

@ -1258,7 +1258,7 @@ from .containers.main import *
from .ocr.main import *
from .rag.main import *
from .search.main import *
from .realtime_api.main import _arealtime
from .realtime_api.main import _arealtime, acreate_realtime_client_secret, arealtime_calls
from .responses.main import _aresponses_websocket
from .fine_tuning.main import *
from .files.main import *

6
litellm/integrations/custom_logger.py
View file

@ -377,6 +377,7 @@ class CustomLogger: # https://docs.litellm.ai/docs/observability/custom_callbac
user_api_key_dict: UserAPIKeyAuth,
response: Any,
request_headers: Optional[Dict[str, str]] = None,
litellm_call_info: Optional[Dict[str, Any]] = None,
) -> Optional[Dict[str, str]]:
"""
Called after an LLM API call (success or failure) to allow injecting custom HTTP response headers.
@ -386,6 +387,11 @@ class CustomLogger: # https://docs.litellm.ai/docs/observability/custom_callbac
- user_api_key_dict: UserAPIKeyAuth - The user API key dictionary.
- response: Any - The response object (None for failure cases).
- request_headers: Optional[Dict[str, str]] - The original request headers.
- litellm_call_info: Optional[Dict[str, Any]] - Normalized routing metadata:
- custom_llm_provider: str - The LLM provider (e.g. "openai", "azure")
- model_info: dict - The model_info from router config
- api_base: str - The API base URL used
- model_id: str - The deployment model ID
Returns:
- Optional[Dict[str, str]]: A dictionary of headers to inject into the HTTP response.

14
litellm/litellm_core_utils/litellm_logging.py
View file

@ -5346,6 +5346,20 @@ def get_standard_logging_object_payload(
model_name = reconstruct_model_name(
kwargs.get("model", "") or "", custom_llm_provider, metadata
)
response_model_name: Optional[str] = None
if isinstance(final_response_obj, dict):
response_model_name = final_response_obj.get("model")
# For Azure Model Router, preserve the actual model in the top-level standard
# logging payload only when the user has opted in.
requested_model = kwargs.get("model")
if (
isinstance(requested_model, str)
and ("model_router" in requested_model.lower() or "model-router" in requested_model.lower())
and isinstance(response_model_name, str)
and response_model_name
):
model_name = response_model_name
payload: StandardLoggingPayload = StandardLoggingPayload(
id=str(id),

307
litellm/llms/anthropic/files/transformation.py Normal file
View file

@ -0,0 +1,307 @@
"""
Anthropic Files API transformation config.
Implements BaseFilesConfig for Anthropic's Files API (beta).
Reference: https://docs.anthropic.com/en/docs/build-with-claude/files
Anthropic Files API endpoints:
- POST /v1/files - Upload a file
- GET /v1/files - List files
- GET /v1/files/{file_id} - Retrieve file metadata
- DELETE /v1/files/{file_id} - Delete a file
- GET /v1/files/{file_id}/content - Download file content
"""
import calendar
import time
from typing import Any, Dict, List, Optional, Union
import httpx
from openai.types.file_deleted import FileDeleted
from litellm.litellm_core_utils.prompt_templates.common_utils import extract_file_data
from litellm.llms.base_llm.chat.transformation import BaseLLMException
from litellm.llms.base_llm.files.transformation import (
BaseFilesConfig,
LiteLLMLoggingObj,
)
from litellm.types.llms.openai import (
CreateFileRequest,
FileContentRequest,
HttpxBinaryResponseContent,
OpenAICreateFileRequestOptionalParams,
OpenAIFileObject,
)
from litellm.types.utils import LlmProviders
from ..common_utils import AnthropicError, AnthropicModelInfo
ANTHROPIC_FILES_API_BASE = "https://api.anthropic.com"
ANTHROPIC_FILES_BETA_HEADER = "files-api-2025-04-14"
class AnthropicFilesConfig(BaseFilesConfig):
"""
Transformation config for Anthropic Files API.
Anthropic uses:
- x-api-key header for authentication
- anthropic-beta: files-api-2025-04-14 header
- multipart/form-data for file uploads
- purpose="messages" (Anthropic-specific, not for batches/fine-tuning)
"""
def __init__(self):
pass
@property
def custom_llm_provider(self) -> LlmProviders:
return LlmProviders.ANTHROPIC
def get_complete_url(
self,
api_base: Optional[str],
api_key: Optional[str],
model: str,
optional_params: dict,
litellm_params: dict,
stream: Optional[bool] = None,
) -> str:
api_base = AnthropicModelInfo.get_api_base(api_base) or ANTHROPIC_FILES_API_BASE
return f"{api_base.rstrip('/')}/v1/files"
def get_error_class(
self,
error_message: str,
status_code: int,
headers: Union[dict, httpx.Headers],
) -> BaseLLMException:
return AnthropicError(
status_code=status_code,
message=error_message,
headers=headers,
)
def validate_environment(
self,
headers: dict,
model: str,
messages: list,
optional_params: dict,
litellm_params: dict,
api_key: Optional[str] = None,
api_base: Optional[str] = None,
) -> dict:
api_key = AnthropicModelInfo.get_api_key(api_key)
if not api_key:
raise ValueError(
"Anthropic API key is required. Set ANTHROPIC_API_KEY environment variable or pass api_key parameter."
)
headers.update(
{
"x-api-key": api_key,
"anthropic-version": "2023-06-01",
"anthropic-beta": ANTHROPIC_FILES_BETA_HEADER,
}
)
return headers
def get_supported_openai_params(
self, model: str
) -> List[OpenAICreateFileRequestOptionalParams]:
return ["purpose"]
def map_openai_params(
self,
non_default_params: dict,
optional_params: dict,
model: str,
drop_params: bool,
) -> dict:
return optional_params
def transform_create_file_request(
self,
model: str,
create_file_data: CreateFileRequest,
optional_params: dict,
litellm_params: dict,
) -> dict:
"""
Transform to multipart form data for Anthropic file upload.
Anthropic expects: POST /v1/files with multipart form-data
- file: the file content
- purpose: "messages" (defaults to "messages" if not provided)
"""
file_data = create_file_data.get("file")
if file_data is None:
raise ValueError("File data is required")
extracted = extract_file_data(file_data)
filename = extracted["filename"] or f"file_{int(time.time())}"
content = extracted["content"]
content_type = extracted.get("content_type", "application/octet-stream")
purpose = create_file_data.get("purpose", "messages")
return {
"file": (filename, content, content_type),
"purpose": (None, purpose),
}
def transform_create_file_response(
self,
model: Optional[str],
raw_response: httpx.Response,
logging_obj: LiteLLMLoggingObj,
litellm_params: dict,
) -> OpenAIFileObject:
"""
Transform Anthropic file response to OpenAI format.
Anthropic response:
{
"id": "file-xxx",
"type": "file",
"filename": "document.pdf",
"mime_type": "application/pdf",
"size_bytes": 12345,
"created_at": "2025-01-01T00:00:00Z"
}
"""
response_json = raw_response.json()
return self._parse_anthropic_file(response_json)
def transform_retrieve_file_request(
self,
file_id: str,
optional_params: dict,
litellm_params: dict,
) -> tuple[str, dict]:
api_base = (
AnthropicModelInfo.get_api_base(litellm_params.get("api_base"))
or ANTHROPIC_FILES_API_BASE
)
return f"{api_base.rstrip('/')}/v1/files/{file_id}", {}
def transform_retrieve_file_response(
self,
raw_response: httpx.Response,
logging_obj: LiteLLMLoggingObj,
litellm_params: dict,
) -> OpenAIFileObject:
response_json = raw_response.json()
return self._parse_anthropic_file(response_json)
def transform_delete_file_request(
self,
file_id: str,
optional_params: dict,
litellm_params: dict,
) -> tuple[str, dict]:
api_base = (
AnthropicModelInfo.get_api_base(litellm_params.get("api_base"))
or ANTHROPIC_FILES_API_BASE
)
return f"{api_base.rstrip('/')}/v1/files/{file_id}", {}
def transform_delete_file_response(
self,
raw_response: httpx.Response,
logging_obj: LiteLLMLoggingObj,
litellm_params: dict,
) -> FileDeleted:
response_json = raw_response.json()
file_id = response_json.get("id", "")
return FileDeleted(
id=file_id,
deleted=True,
object="file",
)
def transform_list_files_request(
self,
purpose: Optional[str],
optional_params: dict,
litellm_params: dict,
) -> tuple[str, dict]:
api_base = (
AnthropicModelInfo.get_api_base(litellm_params.get("api_base"))
or ANTHROPIC_FILES_API_BASE
)
url = f"{api_base.rstrip('/')}/v1/files"
params: Dict[str, Any] = {}
if purpose:
params["purpose"] = purpose
return url, params
def transform_list_files_response(
self,
raw_response: httpx.Response,
logging_obj: LiteLLMLoggingObj,
litellm_params: dict,
) -> List[OpenAIFileObject]:
"""
Anthropic list response:
{
"data": [...],
"has_more": false,
"first_id": "...",
"last_id": "..."
}
"""
response_json = raw_response.json()
files_data = response_json.get("data", [])
return [self._parse_anthropic_file(f) for f in files_data]
def transform_file_content_request(
self,
file_content_request: FileContentRequest,
optional_params: dict,
litellm_params: dict,
) -> tuple[str, dict]:
file_id = file_content_request.get("file_id")
api_base = (
AnthropicModelInfo.get_api_base(litellm_params.get("api_base"))
or ANTHROPIC_FILES_API_BASE
)
return f"{api_base.rstrip('/')}/v1/files/{file_id}/content", {}
def transform_file_content_response(
self,
raw_response: httpx.Response,
logging_obj: LiteLLMLoggingObj,
litellm_params: dict,
) -> HttpxBinaryResponseContent:
return HttpxBinaryResponseContent(response=raw_response)
@staticmethod
def _parse_anthropic_file(file_data: dict) -> OpenAIFileObject:
"""Parse Anthropic file object into OpenAI format."""
created_at_str = file_data.get("created_at", "")
if created_at_str:
try:
created_at = int(
calendar.timegm(
time.strptime(
created_at_str.replace("Z", "+00:00")[:19],
"%Y-%m-%dT%H:%M:%S",
)
)
)
except (ValueError, TypeError):
created_at = int(time.time())
else:
created_at = int(time.time())
return OpenAIFileObject(
id=file_data.get("id", ""),
bytes=file_data.get("size_bytes", file_data.get("bytes", 0)),
created_at=created_at,
filename=file_data.get("filename", ""),
object="file",
purpose=file_data.get("purpose", "messages"),
status="uploaded",
status_details=None,
)

52
litellm/llms/azure/realtime/http_transformation.py Normal file
View file

@ -0,0 +1,52 @@
"""Azure OpenAI realtime HTTP transformation config (client_secrets + realtime_calls)."""
from typing import Optional
import litellm
from litellm.llms.base_llm.realtime.http_transformation import BaseRealtimeHTTPConfig
from litellm.secret_managers.main import get_secret_str
class AzureRealtimeHTTPConfig(BaseRealtimeHTTPConfig):
def get_api_base(self, api_base: Optional[str], **kwargs) -> str:
return (
api_base
or litellm.api_base
or get_secret_str("AZURE_API_BASE")
or ""
)
def get_api_key(self, api_key: Optional[str], **kwargs) -> str:
return (
api_key
or litellm.api_key
or get_secret_str("AZURE_API_KEY")
or ""
)
def get_complete_url(self, api_base: Optional[str], model: str, api_version: Optional[str] = None) -> str:
base = self.get_api_base(api_base).rstrip("/")
version = api_version or get_secret_str("AZURE_API_VERSION") or "2024-12-17"
return f"{base}/openai/realtime/client_secrets?api-version={version}"
def validate_environment(
self,
headers: dict,
model: str,
api_key: Optional[str] = None,
) -> dict:
return {
**headers,
"api-key": api_key or "",
"Content-Type": "application/json",
}
def get_realtime_calls_url(self, api_base: Optional[str], model: str, api_version: Optional[str] = None) -> str:
base = self.get_api_base(api_base).rstrip("/")
version = api_version or get_secret_str("AZURE_API_VERSION") or "2024-12-17"
return f"{base}/openai/realtime/calls?api-version={version}"
def get_realtime_calls_headers(self, ephemeral_key: str) -> dict:
return {
"api-key": ephemeral_key,
}

18
litellm/llms/azure_ai/azure_model_router/transformation.py
View file

@ -64,24 +64,17 @@ class AzureModelRouterConfig(AzureAIStudioConfig):
"""
Transform response for Model Router.
Preserves the original model path (including model_router/ prefix) in the response
for proper cost tracking and logging.
Extracts the actual model used from the Azure response (e.g., gpt-5-nano-2025-08-07)
and returns it with the azure_ai/ prefix for proper display and cost tracking.
"""
from litellm.llms.azure_ai.common_utils import AzureFoundryModelInfo
# Preserve the original model from litellm_params (includes routing prefixes like model_router/)
# This ensures cost tracking and logging use the full model path
original_model: str = litellm_params.get("model") or model
if not original_model.startswith("azure_ai/"):
# Add provider prefix if not already present
model_response.model = f"azure_ai/{original_model}"
else:
model_response.model = original_model
# Get base model for the parent call (strips routing prefixes for API compatibility)
base_model: str = AzureFoundryModelInfo.get_base_model(model)
return super().transform_response(
# Call parent transform_response first - this will extract the actual model
# from the raw response (e.g., "gpt-5-nano-2025-08-07")
model_response = super().transform_response(
model=base_model,
raw_response=raw_response,
model_response=model_response,
@ -94,6 +87,7 @@ class AzureModelRouterConfig(AzureAIStudioConfig):
api_key=api_key,
json_mode=json_mode,
)
return model_response
def calculate_additional_costs(
self, model: str, prompt_tokens: int, completion_tokens: int

115
litellm/llms/base_llm/realtime/http_transformation.py Normal file
View file

@ -0,0 +1,115 @@
"""
Base transformation class for realtime HTTP endpoints (client_secrets, realtime_calls).
These are HTTP (not WebSocket) endpoints used by the WebRTC flow:
POST /v1/realtime/client_secrets — obtains a short-lived ephemeral key
POST /v1/realtime/calls — exchanges an SDP offer using that key
"""
from abc import ABC, abstractmethod
from typing import Optional, Union
import httpx
class BaseRealtimeHTTPConfig(ABC):
"""
Abstract base for provider-specific realtime HTTP credential / URL logic.
Implement one subclass per provider (OpenAI, Azure, …).
"""
# ------------------------------------------------------------------ #
# Credential resolution #
# ------------------------------------------------------------------ #
@abstractmethod
def get_api_base(
self,
api_base: Optional[str],
**kwargs,
) -> str:
"""
Resolve the provider API base URL.
Resolution order (provider-specific):
explicit api_base → litellm.api_base → env var → hard-coded default
"""
@abstractmethod
def get_api_key(
self,
api_key: Optional[str],
**kwargs,
) -> str:
"""
Resolve the provider API key.
Resolution order (provider-specific):
explicit api_key → litellm.api_key → env var → ""
"""
# ------------------------------------------------------------------ #
# client_secrets endpoint #
# ------------------------------------------------------------------ #
@abstractmethod
def get_complete_url(self, api_base: Optional[str], model: str, api_version: Optional[str] = None) -> str:
"""Return the full URL for POST /realtime/client_secrets."""
@abstractmethod
def validate_environment(
self,
headers: dict,
model: str,
api_key: Optional[str] = None,
) -> dict:
"""
Build and return the request headers for the client_secrets call.
Merge `headers` (caller-supplied extras) with auth / content-type
headers required by this provider.
"""
# ------------------------------------------------------------------ #
# realtime_calls endpoint #
# ------------------------------------------------------------------ #
def get_realtime_calls_url(
self, api_base: Optional[str], model: str, api_version: Optional[str] = None
) -> str:
"""Return the full URL for POST /realtime/calls (SDP exchange)."""
base = (api_base or "").rstrip("/")
return f"{base}/v1/realtime/calls"
def get_realtime_calls_headers(self, ephemeral_key: str) -> dict:
"""
Build headers for the realtime_calls POST.
The Bearer token here is the ephemeral key obtained from
client_secrets, not the long-lived provider key.
"""
return {
"Authorization": f"Bearer {ephemeral_key}",
}
# ------------------------------------------------------------------ #
# Error handling #
# ------------------------------------------------------------------ #
def get_error_class(
self, error_message: str, status_code: int, headers: Union[dict, httpx.Headers]
):
"""
Map HTTP errors to LiteLLM exception types.
Default: generic exception. Override in subclasses for provider-specific
error mapping (e.g., Azure uses different error codes).
"""
from litellm.llms.base_llm.chat.transformation import BaseLLMException
return BaseLLMException(
status_code=status_code,
message=error_message,
headers=headers,
)

3
litellm/llms/bedrock/chat/converse_transformation.py
View file

@ -1199,6 +1199,9 @@ class AmazonConverseConfig(BaseConfig):
+ supported_config_params
)
inference_params.pop("json_mode", None) # used for handling json_schema
# Anthropic-only key. Bedrock expects `outputConfig` (camelCase) and
# will reject `output_config` if it leaks through pass-through routes.
inference_params.pop("output_config", None)
# Extract requestMetadata before processing other parameters
request_metadata = inference_params.pop("requestMetadata", None)

677
litellm/llms/custom_httpx/llm_http_handler.py
View file

@ -4735,6 +4735,153 @@ class BaseLLMHTTPHandler:
f"Unexpected error while closing WebSocket: {close_error}"
)
async def async_realtime_client_secret_handler(
self,
api_base: str,
api_key: str,
request_data: Dict[str, Any],
logging_obj: LiteLLMLoggingObj,
timeout: Union[float, httpx.Timeout],
provider_config: Optional[Any] = None,
model: Optional[str] = None,
extra_headers: Optional[Dict[str, Any]] = None,
client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
api_version: Optional[str] = None,
) -> httpx.Response:
"""
Forward POST /v1/realtime/client_secrets to upstream provider.
Uses provider_config (BaseRealtimeHTTPConfig) for URL construction and
header auth when available; falls back to the legacy OpenAI-style defaults.
"""
if client is None or not isinstance(client, AsyncHTTPHandler):
async_httpx_client = get_async_httpx_client(
llm_provider=litellm.LlmProviders.OPENAI,
)
else:
async_httpx_client = client
if provider_config is not None:
url = provider_config.get_complete_url(api_base=api_base, model=model or "", api_version=api_version)
headers: Dict[str, Any] = provider_config.validate_environment(
headers={}, model=model or "", api_key=api_key
)
else:
url = f"{api_base.rstrip('/')}/v1/realtime/client_secrets"
headers = {
"Authorization": f"Bearer {api_key}",
"Content-Type": "application/json",
"OpenAI-Beta": "realtime=v1",
}
if extra_headers:
headers.update(extra_headers)
logging_obj.pre_call(
input=request_data,
api_key="",
additional_args={
"complete_input_dict": request_data,
"api_base": url,
"headers": headers,
},
)
try:
return await async_httpx_client.post(
url=url,
headers=headers,
json=request_data,
timeout=timeout,
)
except Exception as e:
raise self._handle_error(
e=e,
provider_config=provider_config,
)
async def async_realtime_calls_handler(
self,
api_base: str,
openai_ephemeral_key: str,
sdp_body: bytes,
logging_obj: LiteLLMLoggingObj,
timeout: Union[float, httpx.Timeout],
provider_config: Optional[Any] = None,
model: Optional[str] = None,
session_config: Optional[Dict[str, Any]] = None,
extra_headers: Optional[Dict[str, Any]] = None,
client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
api_version: Optional[str] = None,
) -> httpx.Response:
"""
Forward POST /v1/realtime/calls (SDP exchange) to upstream provider.
Uses provider_config (BaseRealtimeHTTPConfig) for URL construction and
header auth when available; falls back to the legacy OpenAI-style defaults.
OpenAI's GA realtime API expects multipart/form-data with:
- sdp: the SDP offer (text)
- session: JSON string with {"type": "realtime", "model": "...", ...}
"""
if client is None or not isinstance(client, AsyncHTTPHandler):
async_httpx_client = get_async_httpx_client(
llm_provider=litellm.LlmProviders.OPENAI,
)
else:
async_httpx_client = client
if provider_config is not None:
url = provider_config.get_realtime_calls_url(api_base=api_base, model=model or "", api_version=api_version)
headers: Dict[str, Any] = provider_config.get_realtime_calls_headers(
ephemeral_key=openai_ephemeral_key
)
else:
url = f"{api_base.rstrip('/')}/v1/realtime/calls"
headers = {
"Authorization": f"Bearer {openai_ephemeral_key}",
}
if extra_headers:
headers.update(extra_headers)
# Build multipart form data: sdp + session JSON
session_data = session_config or {}
if "type" not in session_data:
session_data["type"] = "realtime"
if "model" not in session_data and model:
session_data["model"] = model
sdp_text = sdp_body.decode("utf-8") if isinstance(sdp_body, bytes) else sdp_body
files = {
"sdp": (None, sdp_text, "text/plain"),
"session": (None, json.dumps(session_data), "application/json"),
}
logging_obj.pre_call(
input="realtime_sdp_offer",
api_key="",
additional_args={
"api_base": url,
"headers": headers,
"session": session_data,
},
)
try:
return await async_httpx_client.post(
url=url,
headers=headers,
files=files,
timeout=timeout,
)
except Exception as e:
raise self._handle_error(
e=e,
provider_config=provider_config,
)
async def async_responses_websocket(
self,
model: str,
@ -7625,6 +7772,536 @@ class BaseLLMHTTPHandler:
response=response,
)
async def async_vector_store_retrieve_handler(
self,
vector_store_id: str,
vector_store_provider_config: BaseVectorStoreConfig,
custom_llm_provider: str,
litellm_params: GenericLiteLLMParams,
logging_obj: LiteLLMLoggingObj,
extra_headers: Optional[Dict[str, Any]] = None,
extra_body: Optional[Dict[str, Any]] = None,
timeout: Optional[Union[float, httpx.Timeout]] = None,
client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
) -> VectorStoreCreateResponse:
if client is None or not isinstance(client, AsyncHTTPHandler):
async_httpx_client = get_async_httpx_client(
llm_provider=litellm.LlmProviders(custom_llm_provider),
params={"ssl_verify": litellm_params.get("ssl_verify", None)},
)
else:
async_httpx_client = client
headers = vector_store_provider_config.validate_environment(
headers=extra_headers or {}, litellm_params=litellm_params
)
if extra_headers:
headers.update(extra_headers)
api_base = vector_store_provider_config.get_complete_url(
api_base=litellm_params.api_base,
litellm_params=dict(litellm_params),
)
url = f"{api_base}/{vector_store_id}"
logging_obj.pre_call(
input="",
api_key="",
additional_args={
"api_base": api_base,
"headers": headers,
},
)
try:
response = await async_httpx_client.get(
url=url, headers=headers
)
except Exception as e:
raise self._handle_error(e=e, provider_config=vector_store_provider_config)
return vector_store_provider_config.transform_create_vector_store_response(
response=response,
)
def vector_store_retrieve_handler(
self,
vector_store_id: str,
vector_store_provider_config: BaseVectorStoreConfig,
custom_llm_provider: str,
litellm_params: GenericLiteLLMParams,
logging_obj: LiteLLMLoggingObj,
extra_headers: Optional[Dict[str, Any]] = None,
extra_body: Optional[Dict[str, Any]] = None,
timeout: Optional[Union[float, httpx.Timeout]] = None,
client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
_is_async: bool = False,
) -> Union[
VectorStoreCreateResponse, Coroutine[Any, Any, VectorStoreCreateResponse]
]:
if _is_async:
return self.async_vector_store_retrieve_handler(
vector_store_id=vector_store_id,
vector_store_provider_config=vector_store_provider_config,
litellm_params=litellm_params,
logging_obj=logging_obj,
custom_llm_provider=custom_llm_provider,
extra_headers=extra_headers,
extra_body=extra_body,
timeout=timeout,
client=client,
)
if client is None or not isinstance(client, HTTPHandler):
sync_httpx_client = _get_httpx_client(
params={"ssl_verify": litellm_params.get("ssl_verify", None)}
)
else:
sync_httpx_client = client
headers = vector_store_provider_config.validate_environment(
headers=extra_headers or {}, litellm_params=litellm_params
)
if extra_headers:
headers.update(extra_headers)
api_base = vector_store_provider_config.get_complete_url(
api_base=litellm_params.api_base,
litellm_params=dict(litellm_params),
)
url = f"{api_base}/{vector_store_id}"
logging_obj.pre_call(
input="",
api_key="",
additional_args={
"api_base": api_base,
"headers": headers,
},
)
try:
response = sync_httpx_client.get(url=url, headers=headers)
except Exception as e:
raise self._handle_error(e=e, provider_config=vector_store_provider_config)
return vector_store_provider_config.transform_create_vector_store_response(
response=response,
)
async def async_vector_store_list_handler(
self,
after: Optional[str],
before: Optional[str],
limit: Optional[int],
order: Optional[str],
vector_store_provider_config: BaseVectorStoreConfig,
custom_llm_provider: str,
litellm_params: GenericLiteLLMParams,
logging_obj: LiteLLMLoggingObj,
extra_headers: Optional[Dict[str, Any]] = None,
extra_body: Optional[Dict[str, Any]] = None,
timeout: Optional[Union[float, httpx.Timeout]] = None,
client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
):
if client is None or not isinstance(client, AsyncHTTPHandler):
async_httpx_client = get_async_httpx_client(
llm_provider=litellm.LlmProviders(custom_llm_provider),
params={"ssl_verify": litellm_params.get("ssl_verify", None)},
)
else:
async_httpx_client = client
headers = vector_store_provider_config.validate_environment(
headers=extra_headers or {}, litellm_params=litellm_params
)
if extra_headers:
headers.update(extra_headers)
api_base = vector_store_provider_config.get_complete_url(
api_base=litellm_params.api_base,
litellm_params=dict(litellm_params),
)
url = api_base
params = {}
if after is not None:
params["after"] = after
if before is not None:
params["before"] = before
if limit is not None:
params["limit"] = limit
if order is not None:
params["order"] = order
logging_obj.pre_call(
input="",
api_key="",
additional_args={
"api_base": api_base,
"headers": headers,
"params": params,
},
)
try:
response = await async_httpx_client.get(
url=url, headers=headers, params=params
)
except Exception as e:
raise self._handle_error(e=e, provider_config=vector_store_provider_config)
return response.json()
def vector_store_list_handler(
self,
after: Optional[str],
before: Optional[str],
limit: Optional[int],
order: Optional[str],
vector_store_provider_config: BaseVectorStoreConfig,
custom_llm_provider: str,
litellm_params: GenericLiteLLMParams,
logging_obj: LiteLLMLoggingObj,
extra_headers: Optional[Dict[str, Any]] = None,
extra_body: Optional[Dict[str, Any]] = None,
timeout: Optional[Union[float, httpx.Timeout]] = None,
client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
_is_async: bool = False,
):
if _is_async:
return self.async_vector_store_list_handler(
after=after,
before=before,
limit=limit,
order=order,
vector_store_provider_config=vector_store_provider_config,
litellm_params=litellm_params,
logging_obj=logging_obj,
custom_llm_provider=custom_llm_provider,
extra_headers=extra_headers,
extra_body=extra_body,
timeout=timeout,
client=client,
)
if client is None or not isinstance(client, HTTPHandler):
sync_httpx_client = _get_httpx_client(
params={"ssl_verify": litellm_params.get("ssl_verify", None)}
)
else:
sync_httpx_client = client
headers = vector_store_provider_config.validate_environment(
headers=extra_headers or {}, litellm_params=litellm_params
)
if extra_headers:
headers.update(extra_headers)
api_base = vector_store_provider_config.get_complete_url(
api_base=litellm_params.api_base,
litellm_params=dict(litellm_params),
)
url = api_base
params = {}
if after is not None:
params["after"] = after
if before is not None:
params["before"] = before
if limit is not None:
params["limit"] = limit
if order is not None:
params["order"] = order
logging_obj.pre_call(
input="",
api_key="",
additional_args={
"api_base": api_base,
"headers": headers,
"params": params,
},
)
try:
response = sync_httpx_client.get(url=url, headers=headers, params=params)
except Exception as e:
raise self._handle_error(e=e, provider_config=vector_store_provider_config)
return response.json()
async def async_vector_store_update_handler(
self,
vector_store_id: str,
vector_store_update_optional_params: VectorStoreCreateOptionalRequestParams,
vector_store_provider_config: BaseVectorStoreConfig,
custom_llm_provider: str,
litellm_params: GenericLiteLLMParams,
logging_obj: LiteLLMLoggingObj,
extra_headers: Optional[Dict[str, Any]] = None,
extra_body: Optional[Dict[str, Any]] = None,
timeout: Optional[Union[float, httpx.Timeout]] = None,
client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
) -> VectorStoreCreateResponse:
if client is None or not isinstance(client, AsyncHTTPHandler):
async_httpx_client = get_async_httpx_client(
llm_provider=litellm.LlmProviders(custom_llm_provider),
params={"ssl_verify": litellm_params.get("ssl_verify", None)},
)
else:
async_httpx_client = client
headers = vector_store_provider_config.validate_environment(
headers=extra_headers or {}, litellm_params=litellm_params
)
if extra_headers:
headers.update(extra_headers)
api_base = vector_store_provider_config.get_complete_url(
api_base=litellm_params.api_base,
litellm_params=dict(litellm_params),
)
url = f"{api_base}/{vector_store_id}"
request_body = dict(vector_store_update_optional_params)
# Clean metadata to only include string values (OpenAI requirement)
if "metadata" in request_body and request_body["metadata"] is not None:
from litellm.utils import add_openai_metadata
request_body["metadata"] = add_openai_metadata(request_body["metadata"])
if extra_body:
request_body.update(extra_body)
logging_obj.pre_call(
input="",
api_key="",
additional_args={
"complete_input_dict": request_body,
"api_base": api_base,
"headers": headers,
},
)
try:
response = await async_httpx_client.post(
url=url, headers=headers, json=request_body, timeout=timeout
)
except Exception as e:
raise self._handle_error(e=e, provider_config=vector_store_provider_config)
return vector_store_provider_config.transform_create_vector_store_response(
response=response,
)
def vector_store_update_handler(
self,
vector_store_id: str,
vector_store_update_optional_params: VectorStoreCreateOptionalRequestParams,
vector_store_provider_config: BaseVectorStoreConfig,
custom_llm_provider: str,
litellm_params: GenericLiteLLMParams,
logging_obj: LiteLLMLoggingObj,
extra_headers: Optional[Dict[str, Any]] = None,
extra_body: Optional[Dict[str, Any]] = None,
timeout: Optional[Union[float, httpx.Timeout]] = None,
client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
_is_async: bool = False,
) -> Union[
VectorStoreCreateResponse, Coroutine[Any, Any, VectorStoreCreateResponse]
]:
if _is_async:
return self.async_vector_store_update_handler(
vector_store_id=vector_store_id,
vector_store_update_optional_params=vector_store_update_optional_params,
vector_store_provider_config=vector_store_provider_config,
litellm_params=litellm_params,
logging_obj=logging_obj,
custom_llm_provider=custom_llm_provider,
extra_headers=extra_headers,
extra_body=extra_body,
timeout=timeout,
client=client,
)
if client is None or not isinstance(client, HTTPHandler):
sync_httpx_client = _get_httpx_client(
params={"ssl_verify": litellm_params.get("ssl_verify", None)}
)
else:
sync_httpx_client = client
headers = vector_store_provider_config.validate_environment(
headers=extra_headers or {}, litellm_params=litellm_params
)
if extra_headers:
headers.update(extra_headers)
api_base = vector_store_provider_config.get_complete_url(
api_base=litellm_params.api_base,
litellm_params=dict(litellm_params),
)
url = f"{api_base}/{vector_store_id}"
request_body = dict(vector_store_update_optional_params)
# Clean metadata to only include string values (OpenAI requirement)
if "metadata" in request_body and request_body["metadata"] is not None:
from litellm.utils import add_openai_metadata
request_body["metadata"] = add_openai_metadata(request_body["metadata"])
if extra_body:
request_body.update(extra_body)
logging_obj.pre_call(
input="",
api_key="",
additional_args={
"complete_input_dict": request_body,
"api_base": api_base,
"headers": headers,
},
)
try:
response = sync_httpx_client.post(
url=url, headers=headers, json=request_body
)
except Exception as e:
raise self._handle_error(e=e, provider_config=vector_store_provider_config)
return vector_store_provider_config.transform_create_vector_store_response(
response=response,
)
async def async_vector_store_delete_handler(
self,
vector_store_id: str,
vector_store_provider_config: BaseVectorStoreConfig,
custom_llm_provider: str,
litellm_params: GenericLiteLLMParams,
logging_obj: LiteLLMLoggingObj,
extra_headers: Optional[Dict[str, Any]] = None,
extra_body: Optional[Dict[str, Any]] = None,
timeout: Optional[Union[float, httpx.Timeout]] = None,
client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
):
if client is None or not isinstance(client, AsyncHTTPHandler):
async_httpx_client = get_async_httpx_client(
llm_provider=litellm.LlmProviders(custom_llm_provider),
params={"ssl_verify": litellm_params.get("ssl_verify", None)},
)
else:
async_httpx_client = client
headers = vector_store_provider_config.validate_environment(
headers=extra_headers or {}, litellm_params=litellm_params
)
if extra_headers:
headers.update(extra_headers)
api_base = vector_store_provider_config.get_complete_url(
api_base=litellm_params.api_base,
litellm_params=dict(litellm_params),
)
url = f"{api_base}/{vector_store_id}"
logging_obj.pre_call(
input="",
api_key="",
additional_args={
"api_base": api_base,
"headers": headers,
},
)
try:
response = await async_httpx_client.delete(
url=url, headers=headers, timeout=timeout
)
except Exception as e:
raise self._handle_error(e=e, provider_config=vector_store_provider_config)
return response.json()
def vector_store_delete_handler(
self,
vector_store_id: str,
vector_store_provider_config: BaseVectorStoreConfig,
custom_llm_provider: str,
litellm_params: GenericLiteLLMParams,
logging_obj: LiteLLMLoggingObj,
extra_headers: Optional[Dict[str, Any]] = None,
extra_body: Optional[Dict[str, Any]] = None,
timeout: Optional[Union[float, httpx.Timeout]] = None,
client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
_is_async: bool = False,
):
if _is_async:
return self.async_vector_store_delete_handler(
vector_store_id=vector_store_id,
vector_store_provider_config=vector_store_provider_config,
litellm_params=litellm_params,
logging_obj=logging_obj,
custom_llm_provider=custom_llm_provider,
extra_headers=extra_headers,
extra_body=extra_body,
timeout=timeout,
client=client,
)
if client is None or not isinstance(client, HTTPHandler):
sync_httpx_client = _get_httpx_client(
params={"ssl_verify": litellm_params.get("ssl_verify", None)}
)
else:
sync_httpx_client = client
headers = vector_store_provider_config.validate_environment(
headers=extra_headers or {}, litellm_params=litellm_params
)
if extra_headers:
headers.update(extra_headers)
api_base = vector_store_provider_config.get_complete_url(
api_base=litellm_params.api_base,
litellm_params=dict(litellm_params),
)
url = f"{api_base}/{vector_store_id}"
logging_obj.pre_call(
input="",
api_key="",
additional_args={
"api_base": api_base,
"headers": headers,
},
)
try:
response = sync_httpx_client.delete(url=url, headers=headers)
except Exception as e:
raise self._handle_error(e=e, provider_config=vector_store_provider_config)
return response.json()
#####################################################################
################ Vector Store Files HANDLERS ########################
#####################################################################

2
litellm/llms/openai/chat/gpt_5_transformation.py
View file

@ -194,7 +194,7 @@ class OpenAIGPT5Config(OpenAIGPTConfig):
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
reasoning_effort = None # noqa: F841
# 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")

50
litellm/llms/openai/realtime/http_transformation.py Normal file
View file

@ -0,0 +1,50 @@
"""OpenAI realtime HTTP transformation config (client_secrets + realtime_calls)."""
from typing import Optional
import litellm
from litellm.llms.base_llm.realtime.http_transformation import BaseRealtimeHTTPConfig
from litellm.secret_managers.main import get_secret_str
class OpenAIRealtimeHTTPConfig(BaseRealtimeHTTPConfig):
def get_api_base(self, api_base: Optional[str], **kwargs) -> str:
return (
api_base
or litellm.api_base
or get_secret_str("OPENAI_API_BASE")
or "https://api.openai.com"
)
def get_api_key(self, api_key: Optional[str], **kwargs) -> str:
return (
api_key
or litellm.api_key
or litellm.openai_key
or get_secret_str("OPENAI_API_KEY")
or ""
)
def get_complete_url(self, api_base: Optional[str], model: str, api_version: Optional[str] = None) -> str:
base = self.get_api_base(api_base).rstrip("/")
if base.endswith("/v1"):
base = base[:-3]
return f"{base}/v1/realtime/client_secrets"
def get_realtime_calls_url(self, api_base: Optional[str], model: str, api_version: Optional[str] = None) -> str:
base = self.get_api_base(api_base).rstrip("/")
if base.endswith("/v1"):
base = base[:-3]
return f"{base}/v1/realtime/calls"
def validate_environment(
self,
headers: dict,
model: str,
api_key: Optional[str] = None,
) -> dict:
return {
**headers,
"Authorization": f"Bearer {api_key or ''}",
"Content-Type": "application/json",
}

29
litellm/llms/snowflake/chat/transformation.py
View file

@ -219,17 +219,32 @@ class SnowflakeConfig(SnowflakeBaseConfig, OpenAIGPTConfig):
tool_choice: Tool choice in OpenAI format (str or dict)
Returns:
Tool choice in Snowflake format (always an object)
Tool choice in Snowflake format (always an object, never a string)
OpenAI format (string): "auto", "required", "none"
OpenAI format (object): {"type": "function", "function": {"name": "get_weather"}}
OpenAI format (string):
"auto", "required", "none"
Snowflake format (string values become objects): {"type": "auto"}
Snowflake format (specific tool): {"type": "tool", "name": ["get_weather"]}
OpenAI format (dict):
{"type": "function", "function": {"name": "get_weather"}}
Snowflake format:
{"type": "auto"} / {"type": "any"} / {"type": "none"}
{"type": "tool", "name": ["get_weather"]}
Snowflake's API (like Anthropic) requires tool_choice as an object
with a "type" field, not as a bare string.
"""
if isinstance(tool_choice, str):
# Snowflake requires object format: {"type": "auto"} not string "auto"
return {"type": tool_choice}
# Snowflake requires object format, not string.
# Map OpenAI string values to Snowflake object format.
# "required" maps to "any" (Snowflake/Anthropic convention).
_type_map = {
"auto": "auto",
"required": "any",
"none": "none",
}
mapped_type = _type_map.get(tool_choice, tool_choice)
return {"type": mapped_type}
if isinstance(tool_choice, dict):
if tool_choice.get("type") == "function":

23
litellm/llms/vertex_ai/common_utils.py
View file

@ -520,29 +520,6 @@ def _build_vertex_schema(parameters: dict, add_property_ordering: bool = False):
return parameters
def _build_vertex_schema_for_gemini_2(parameters: dict) -> dict:
"""
Minimal schema builder for Gemini 2.0+ tool parameters.
Gemini 2.0+ accepts standard JSON Schema natively in tool parameters,
including lowercase types, anyOf with null, and bare {} (TYPE_UNSPECIFIED).
The only transformation needed is resolving $ref/$defs, which Gemini does
NOT support in tool parameters (returns 400).
This avoids the harmful transforms in _build_vertex_schema that break
JsonValue/Any semantics by coercing {} to {"type": "object"}.
"""
valid_schema_fields = set(get_type_hints(Schema).keys())
parameters = dict(parameters) # shallow copy to avoid mutating caller's dict
defs = parameters.pop("$defs", {})
unpack_defs(parameters, defs)
parameters = filter_schema_fields(parameters, valid_schema_fields)
return parameters
def _build_json_schema(parameters: dict) -> dict:
"""
Build a JSON Schema for use with Gemini's responseJsonSchema parameter.

5
litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py
View file

@ -97,7 +97,6 @@ from ..common_utils import (
VertexAIError,
_build_json_schema,
_build_vertex_schema,
_build_vertex_schema_for_gemini_2,
supports_response_json_schema,
)
from ..vertex_llm_base import VertexBase
@ -468,7 +467,7 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
return None
def _map_function( # noqa: PLR0915
self, value: List[dict], optional_params: dict, model: str = ""
self, value: List[dict], optional_params: dict
) -> List[Tools]:
"""
Map OpenAI-style tools/functions to Vertex AI format.
@ -1058,7 +1057,7 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
):
# Pass optional_params so _map_function can add toolConfig if needed
mapped_tools = self._map_function(
value=value, optional_params=optional_params, model=model
value=value, optional_params=optional_params
)
optional_params = self._add_tools_to_optional_params(
optional_params, mapped_tools

3200
litellm/model_prices_and_context_window_backup.json
View file

File diff suppressed because it is too large Load diff

138
litellm/proxy/_experimental/mcp_server/db.py
View file

@ -1,4 +1,6 @@
from datetime import datetime, timezone
import base64
import json
from datetime import datetime, timedelta, timezone
from typing import Any, Dict, Iterable, List, Optional, Set, Union, cast
from litellm._logging import verbose_proxy_logger
@ -495,7 +497,6 @@ async def store_user_credential(
credential: str,
) -> None:
"""Store a user credential for a BYOK MCP server."""
import base64
encoded = base64.urlsafe_b64encode(credential.encode()).decode()
await prisma_client.db.litellm_mcpusercredentials.upsert(
@ -517,7 +518,6 @@ async def get_user_credential(
server_id: str,
) -> Optional[str]:
"""Return credential for a user+server pair, or None."""
import base64
row = await prisma_client.db.litellm_mcpusercredentials.find_unique(
where={"user_id_server_id": {"user_id": user_id, "server_id": server_id}}
@ -559,6 +559,138 @@ async def delete_user_credential(
)
# ── OAuth2 user-credential helpers ────────────────────────────────────────────
async def store_user_oauth_credential(
prisma_client: PrismaClient,
user_id: str,
server_id: str,
access_token: str,
refresh_token: Optional[str] = None,
expires_in: Optional[int] = None,
scopes: Optional[List[str]] = None,
) -> None:
"""Persist an OAuth2 access token for a user+server pair.
The payload is JSON-serialised and stored base64-encoded in the same
``credential_b64`` column used by BYOK. A ``"type": "oauth2"`` key
differentiates it from plain BYOK API keys.
"""
expires_at: Optional[str] = None
if expires_in is not None:
expires_at = (
datetime.now(timezone.utc) + timedelta(seconds=expires_in)
).isoformat()
payload: Dict[str, Any] = {
"type": "oauth2",
"access_token": access_token,
"connected_at": datetime.now(timezone.utc).isoformat(),
}
if refresh_token:
payload["refresh_token"] = refresh_token
if expires_at:
payload["expires_at"] = expires_at
if scopes:
payload["scopes"] = scopes
# Guard against silently overwriting a BYOK credential with an OAuth token.
# BYOK credentials lack a "type" field (or use a non-"oauth2" type).
existing = await prisma_client.db.litellm_mcpusercredentials.find_unique(
where={"user_id_server_id": {"user_id": user_id, "server_id": server_id}}
)
if existing is not None:
_byok_error = ValueError(
f"A non-OAuth2 credential already exists for user {user_id} "
f"and server {server_id}. Refusing to overwrite."
)
try:
raw = json.loads(base64.urlsafe_b64decode(existing.credential_b64).decode())
except Exception:
# Credential is not base64+JSON — it's a plain-text BYOK key.
raise _byok_error
if raw.get("type") != "oauth2":
raise _byok_error
encoded = base64.urlsafe_b64encode(json.dumps(payload).encode()).decode()
await prisma_client.db.litellm_mcpusercredentials.upsert(
where={"user_id_server_id": {"user_id": user_id, "server_id": server_id}},
data={
"create": {
"user_id": user_id,
"server_id": server_id,
"credential_b64": encoded,
},
"update": {"credential_b64": encoded},
},
)
def is_oauth_credential_expired(cred: Dict[str, Any]) -> bool:
"""Return True if the OAuth2 credential's access_token has expired.
Checks the ``expires_at`` ISO-format string stored in the credential payload.
Returns False when ``expires_at`` is absent or unparseable (treat as non-expired).
"""
expires_at = cred.get("expires_at")
if not expires_at:
return False
try:
exp_dt = datetime.fromisoformat(expires_at)
if exp_dt.tzinfo is None:
exp_dt = exp_dt.replace(tzinfo=timezone.utc)
return datetime.now(timezone.utc) > exp_dt
except (ValueError, TypeError):
return False
async def get_user_oauth_credential(
prisma_client: PrismaClient,
user_id: str,
server_id: str,
) -> Optional[Dict[str, Any]]:
"""Return the decoded OAuth2 payload dict for a user+server pair, or None."""
row = await prisma_client.db.litellm_mcpusercredentials.find_unique(
where={"user_id_server_id": {"user_id": user_id, "server_id": server_id}}
)
if row is None:
return None
try:
decoded = base64.urlsafe_b64decode(row.credential_b64).decode()
parsed = json.loads(decoded)
if isinstance(parsed, dict) and parsed.get("type") == "oauth2":
return parsed
# Row exists but is a BYOK (plain string), not an OAuth token
return None
except Exception:
return None
async def list_user_oauth_credentials(
prisma_client: PrismaClient,
user_id: str,
) -> List[Dict[str, Any]]:
"""Return all OAuth2 credential payloads for a user, tagged with server_id."""
rows = await prisma_client.db.litellm_mcpusercredentials.find_many(
where={"user_id": user_id}
)
results: List[Dict[str, Any]] = []
for row in rows:
try:
decoded = base64.urlsafe_b64decode(row.credential_b64).decode()
parsed = json.loads(decoded)
if isinstance(parsed, dict) and parsed.get("type") == "oauth2":
parsed["server_id"] = row.server_id
results.append(parsed)
except Exception:
pass # Skip non-OAuth rows (BYOK plain strings)
return results
async def approve_mcp_server(
prisma_client: PrismaClient,
server_id: str,

25
litellm/proxy/_experimental/mcp_server/discoverable_endpoints.py
View file

@ -316,8 +316,8 @@ async def register_client_with_server(
@router.get("/authorize")
async def authorize(
request: Request,
client_id: str,
redirect_uri: str,
client_id: Optional[str] = None,
state: str = "",
mcp_server_name: Optional[str] = None,
code_challenge: Optional[str] = None,
@ -330,19 +330,34 @@ async def authorize(
global_mcp_server_manager,
)
lookup_name = mcp_server_name or client_id
lookup_name: Optional[str] = mcp_server_name or client_id
client_ip = IPAddressUtils.get_mcp_client_ip(request)
mcp_server = global_mcp_server_manager.get_mcp_server_by_name(
lookup_name, client_ip=client_ip
mcp_server = (
global_mcp_server_manager.get_mcp_server_by_name(lookup_name, client_ip=client_ip)
if lookup_name
else None
)
if mcp_server is None and mcp_server_name is None:
mcp_server = _resolve_oauth2_server_for_root_endpoints()
if mcp_server is None:
raise HTTPException(status_code=404, detail="MCP server not found")
# Use server's stored client_id when caller doesn't supply one.
# Raise a clear error instead of passing an empty string — an empty
# client_id would silently produce a broken authorization URL.
resolved_client_id: str = mcp_server.client_id or client_id or ""
if not resolved_client_id:
raise HTTPException(
status_code=400,
detail={
"error": "client_id is required but was not supplied and is not "
"stored on the MCP server record. Provide client_id as a query "
"parameter or configure it on the server."
},
)
return await authorize_with_server(
request=request,
mcp_server=mcp_server,
client_id=client_id,
client_id=resolved_client_id,
redirect_uri=redirect_uri,
state=state,
code_challenge=code_challenge,

176
litellm/proxy/_experimental/mcp_server/rest_endpoints.py
View file

@ -1,6 +1,6 @@
import importlib
from datetime import datetime
from typing import Any, Awaitable, Callable, Dict, List, Optional, Union
from datetime import datetime, timezone
from typing import Any, Awaitable, Callable, Dict, List, Optional, Set, Union
from fastapi import APIRouter, Depends, HTTPException, Query, Request
@ -69,6 +69,132 @@ if MCP_AVAILABLE:
return server_auth
return mcp_auth_header
def _get_oauth2_server_ids(allowed_server_ids: List[str]) -> Set[str]:
"""Return the subset of *allowed_server_ids* whose servers use OAuth2 auth.
Used as a cheap pre-flight check to skip bulk credential fetching when no
OAuth2 servers are involved in the current request.
"""
return {
sid
for sid in allowed_server_ids
if getattr(
global_mcp_server_manager.get_mcp_server_by_id(sid), "auth_type", None
)
== MCPAuth.oauth2
}
async def _get_user_oauth_extra_headers(
server,
user_api_key_dict: UserAPIKeyAuth,
prefetched_creds: Optional[Dict[str, Dict[str, Any]]] = None,
) -> Optional[Dict[str, str]]:
"""
For OAuth2 servers, look up the user's stored access token and return it
as extra_headers {"Authorization": "Bearer <token>"} so that it reaches
the MCP server the same way the admin "Add MCP / Authorize and Fetch" flow does.
Returns None for non-OAuth2 servers or when no credential is stored.
Args:
prefetched_creds: Optional dict keyed by server_id with credential payloads.
When provided, avoids a per-server DB round-trip.
"""
if getattr(server, "auth_type", None) != MCPAuth.oauth2:
return None
user_id = getattr(user_api_key_dict, "user_id", None)
server_id = getattr(server, "server_id", None)
if not user_id or not server_id:
return None
try:
from litellm.proxy._experimental.mcp_server.db import (
get_user_oauth_credential,
is_oauth_credential_expired,
)
if prefetched_creds is not None:
cred = prefetched_creds.get(server_id)
else:
from litellm.proxy.utils import get_prisma_client_or_throw
prisma_client = get_prisma_client_or_throw(
"Database not connected. Connect a database to use OAuth2 MCP tools."
)
cred = await get_user_oauth_credential(prisma_client, user_id, server_id)
if cred and cred.get("access_token"):
if is_oauth_credential_expired(cred):
verbose_logger.debug(
f"_get_user_oauth_extra_headers: token expired for "
f"user={user_id} server={server_id}"
)
return None
return {"Authorization": f"Bearer {cred['access_token']}"}
except Exception as e:
verbose_logger.warning(
f"_get_user_oauth_extra_headers: failed to retrieve credential for "
f"user={user_id} server={server_id}: {e}"
)
return None
async def _prefetch_user_oauth_creds(
user_api_key_dict: UserAPIKeyAuth,
) -> Dict[str, Dict[str, Any]]:
"""Fetch all OAuth2 credentials for the user in a single DB query.
Returns a dict keyed by server_id. Used to avoid N+1 DB queries when
iterating over multiple OAuth2 MCP servers.
"""
user_id = getattr(user_api_key_dict, "user_id", None)
if not user_id:
return {}
try:
from litellm.proxy._experimental.mcp_server.db import (
list_user_oauth_credentials,
)
from litellm.proxy.utils import get_prisma_client_or_throw
prisma_client = get_prisma_client_or_throw(
"Database not connected. Connect a database to use OAuth2 MCP tools."
)
creds = await list_user_oauth_credentials(prisma_client, user_id)
return {c["server_id"]: c for c in creds if "server_id" in c}
except Exception as e:
verbose_logger.warning(
f"_prefetch_user_oauth_creds: failed to prefetch for user={user_id}: {e}"
)
return {}
async def _get_bulk_user_oauth_headers(
user_api_key_dict: UserAPIKeyAuth,
) -> Dict[str, Dict[str, str]]:
"""
Fetch ALL OAuth2 credentials for the current user in a single DB query and
return a mapping of server_id → {"Authorization": "Bearer <token>"}.
This is the batch alternative to calling _get_user_oauth_extra_headers
per-server inside a loop (N+1 DB queries).
"""
user_id = getattr(user_api_key_dict, "user_id", None)
if not user_id:
return {}
try:
from litellm.proxy._experimental.mcp_server.db import (
list_user_oauth_credentials,
)
from litellm.proxy.utils import get_prisma_client_or_throw
prisma_client = get_prisma_client_or_throw(
"Database not connected. Connect a database to use OAuth2 MCP tools."
)
creds = await list_user_oauth_credentials(prisma_client, user_id)
return {
c["server_id"]: {"Authorization": f"Bearer {c['access_token']}"}
for c in creds
if c.get("access_token") and c.get("server_id")
}
except Exception:
verbose_logger.debug("Failed to bulk-fetch OAuth credentials", exc_info=True)
return {}
def _create_tool_response_objects(tools, server_mcp_info):
"""Helper function to create tool response objects."""
return [
@ -162,11 +288,13 @@ if MCP_AVAILABLE:
server_auth_header,
raw_headers: Optional[Dict[str, str]] = None,
user_api_key_auth: Optional[UserAPIKeyAuth] = None,
extra_headers: Optional[Dict[str, str]] = None,
):
"""Helper function to get tools for a single server."""
tools = await global_mcp_server_manager._get_tools_from_server(
server=server,
mcp_auth_header=server_auth_header,
extra_headers=extra_headers,
add_prefix=False,
raw_headers=raw_headers,
)
@ -294,8 +422,23 @@ if MCP_AVAILABLE:
# If server_id is specified, only query that specific server
if server_id:
# Resolve a server name to its UUID if needed (MCPConnectPicker passes
# server_name strings, but allowed_server_ids_set contains UUIDs).
# _name_resolved is kept so the second check can reuse it for accurate
# IP-filter error reporting if the resolved UUID is not in allowed_server_ids.
_name_resolved = None
if server_id not in allowed_server_ids:
_server = global_mcp_server_manager.get_mcp_server_by_id(server_id)
_name_resolved = global_mcp_server_manager.get_mcp_server_by_name(server_id)
if _name_resolved is not None and _name_resolved.server_id in set(allowed_server_ids):
server_id = _name_resolved.server_id
if server_id not in allowed_server_ids:
# Try UUID lookup first; fall back to the name-resolved server so that
# IP-filter reporting works correctly even when server_id is a name string.
_server = (
global_mcp_server_manager.get_mcp_server_by_id(server_id)
or _name_resolved
)
if (
_server is not None
and _rest_client_ip is not None
@ -333,6 +476,8 @@ if MCP_AVAILABLE:
server_auth_header = _get_server_auth_header(
server, mcp_server_auth_headers, mcp_auth_header
)
# Single-server request: targeted lookup is more efficient than a bulk fetch.
user_oauth_extra_headers = await _get_user_oauth_extra_headers(server, user_api_key_dict)
try:
list_tools_result = await _get_tools_for_single_server(
@ -340,6 +485,7 @@ if MCP_AVAILABLE:
server_auth_header,
raw_headers_from_request,
user_api_key_dict,
extra_headers=user_oauth_extra_headers,
)
except Exception as e:
verbose_logger.exception(
@ -373,6 +519,14 @@ if MCP_AVAILABLE:
},
)
# Pre-fetch OAuth credentials only when at least one allowed server uses OAuth2,
# to avoid an unnecessary DB round-trip on requests with no OAuth2 MCP servers.
prefetched_oauth_creds = (
await _prefetch_user_oauth_creds(user_api_key_dict)
if _get_oauth2_server_ids(allowed_server_ids)
else {}
)
# Query all servers the user has access to
errors = []
for allowed_server_id in allowed_server_ids:
@ -385,6 +539,9 @@ if MCP_AVAILABLE:
server_auth_header = _get_server_auth_header(
server, mcp_server_auth_headers, mcp_auth_header
)
user_oauth_extra_headers = await _get_user_oauth_extra_headers(
server, user_api_key_dict, prefetched_creds=prefetched_oauth_creds
)
try:
tools_result = await _get_tools_for_single_server(
@ -392,6 +549,7 @@ if MCP_AVAILABLE:
server_auth_header,
raw_headers_from_request,
user_api_key_dict,
extra_headers=user_oauth_extra_headers,
)
list_tools_result.extend(tools_result)
except Exception as e:
@ -505,6 +663,16 @@ if MCP_AVAILABLE:
request, user_api_key_dict, server_id
)
# Look up per-user OAuth headers for this server (mirrors list_tool_rest_api).
user_oauth_extra_headers: Optional[Dict[str, str]] = None
target_server = next(
(s for s in allowed_mcp_servers if s.server_id == server_id), None
)
if target_server is not None:
user_oauth_extra_headers = await _get_user_oauth_extra_headers(
target_server, user_api_key_dict
)
# Call execute_mcp_tool directly (permission checks already done)
result = await execute_mcp_tool(
name=tool_name,
@ -514,7 +682,7 @@ if MCP_AVAILABLE:
user_api_key_auth=data.get("user_api_key_auth"),
mcp_auth_header=data.get("mcp_auth_header"),
mcp_server_auth_headers=data.get("mcp_server_auth_headers"),
oauth2_headers=data.get("oauth2_headers"),
oauth2_headers=user_oauth_extra_headers or data.get("oauth2_headers"),
raw_headers=data.get("raw_headers"),
litellm_logging_obj=data.get("litellm_logging_obj"),
)

98
litellm/proxy/_experimental/mcp_server/server.py
View file

@ -8,7 +8,7 @@ import contextlib
import time
import traceback
import uuid
from datetime import datetime
from datetime import datetime, timezone
from typing import (
Any,
AsyncIterator,
@ -871,6 +871,84 @@ if MCP_AVAILABLE:
return allowed_mcp_servers
async def _get_user_oauth_extra_headers_from_db(
server: MCPServer,
user_api_key_auth: Optional[UserAPIKeyAuth],
prefetched_creds: Optional[Dict[str, Dict[str, Any]]] = None,
) -> Optional[Dict[str, str]]:
"""Look up stored OAuth2 token for (user, server) from DB and return as extra_headers dict.
Args:
prefetched_creds: Optional dict keyed by server_id with credential payloads.
When provided, avoids a per-server DB round-trip.
"""
if server.auth_type != MCPAuth.oauth2:
return None
if user_api_key_auth is None:
return None
user_id = getattr(user_api_key_auth, "user_id", None)
server_id = getattr(server, "server_id", None)
if not user_id or not server_id:
return None
try:
from litellm.proxy._experimental.mcp_server.db import ( # noqa: PLC0415
get_user_oauth_credential,
is_oauth_credential_expired,
)
if prefetched_creds is not None:
cred = prefetched_creds.get(server_id)
else:
from litellm.proxy.utils import ( # noqa: PLC0415
get_prisma_client_or_throw,
)
prisma_client = get_prisma_client_or_throw(
"Database not connected. Connect a database to use OAuth2 MCP tools."
)
cred = await get_user_oauth_credential(prisma_client, user_id, server_id)
if cred and cred.get("access_token"):
if is_oauth_credential_expired(cred):
verbose_logger.debug(
f"_get_user_oauth_extra_headers_from_db: token expired for "
f"user={user_id} server={server_id}"
)
return None
return {"Authorization": f"Bearer {cred['access_token']}"}
except Exception as e:
verbose_logger.warning(
f"_get_user_oauth_extra_headers_from_db: failed to retrieve credential for "
f"user={user_id} server={server_id}: {e}"
)
return None
async def _prefetch_oauth_creds_for_user(
user_api_key_auth: Optional[UserAPIKeyAuth],
) -> Dict[str, Dict[str, Any]]:
"""Fetch all OAuth2 credentials for the user in one DB query.
Returns a dict keyed by server_id to avoid N+1 queries in asyncio.gather loops.
"""
user_id = getattr(user_api_key_auth, "user_id", None) if user_api_key_auth else None
if not user_id:
return {}
try:
from litellm.proxy._experimental.mcp_server.db import ( # noqa: PLC0415
list_user_oauth_credentials,
)
from litellm.proxy.utils import get_prisma_client_or_throw # noqa: PLC0415
prisma_client = get_prisma_client_or_throw(
"Database not connected. Connect a database to use OAuth2 MCP tools."
)
creds = await list_user_oauth_credentials(prisma_client, user_id)
return {c["server_id"]: c for c in creds if "server_id" in c}
except Exception as e:
verbose_logger.warning(
f"_prefetch_oauth_creds_for_user: failed to prefetch for user={user_id}: {e}"
)
return {}
def _prepare_mcp_server_headers(
server: MCPServer,
mcp_server_auth_headers: Optional[Dict[str, Dict[str, str]]],
@ -1015,6 +1093,18 @@ if MCP_AVAILABLE:
mcp_servers=mcp_servers,
)
# Pre-fetch OAuth credentials only when at least one server uses OAuth2,
# to avoid an unnecessary DB round-trip on requests with no OAuth2 MCP servers.
_has_oauth2_server = any(
getattr(s, "auth_type", None) == MCPAuth.oauth2
for s in allowed_mcp_servers
)
_prefetched_oauth_creds = (
await _prefetch_oauth_creds_for_user(user_api_key_auth)
if _has_oauth2_server
else {}
)
async def _fetch_and_filter_server_tools(
server: MCPServer,
) -> List[MCPTool]:
@ -1030,6 +1120,12 @@ if MCP_AVAILABLE:
raw_headers=raw_headers,
)
# If no OAuth2 token came from request headers, fall back to pre-fetched creds
if extra_headers is None and server.auth_type == MCPAuth.oauth2:
extra_headers = await _get_user_oauth_extra_headers_from_db(
server, user_api_key_auth, prefetched_creds=_prefetched_oauth_creds
)
try:
tools = await global_mcp_server_manager._get_tools_from_server(
server=server,

2
litellm/proxy/_experimental/out/404/index.html → litellm/proxy/_experimental/out/404.html
View file

File diff suppressed because one or more lines are too long

45
litellm/proxy/_experimental/out/__next.__PAGE__.txt
View file

@ -1,30 +1,27 @@
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/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"
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/e627c7aa5ead52b3.js","/litellm-asset-prefix/_next/static/chunks/142704439974f6b3.js","/litellm-asset-prefix/_next/static/chunks/30539b80ac15aad2.js","/litellm-asset-prefix/_next/static/chunks/7d82a1cebfdb679c.js","/litellm-asset-prefix/_next/static/chunks/2d471965761a22ff.js","/litellm-asset-prefix/_next/static/chunks/1fe0596a309ad6cf.js","/litellm-asset-prefix/_next/static/chunks/7b788dd93ad868b3.js","/litellm-asset-prefix/_next/static/chunks/c847ecdf8c790b0b.js","/litellm-asset-prefix/_next/static/chunks/403c4d96324c23a6.js","/litellm-asset-prefix/_next/static/chunks/88c74f8b4b20d25a.js","/litellm-asset-prefix/_next/static/chunks/d64d74932cb225a3.js","/litellm-asset-prefix/_next/static/chunks/8c13023d89b01566.js","/litellm-asset-prefix/_next/static/chunks/3b30ab8eaa03bc21.js","/litellm-asset-prefix/_next/static/chunks/74ce31aa0fb2adc9.js","/litellm-asset-prefix/_next/static/chunks/cdf98a03da656604.js","/litellm-asset-prefix/_next/static/chunks/cac89fc12fb6ef7e.js","/litellm-asset-prefix/_next/static/chunks/d0d828f9a0668699.js","/litellm-asset-prefix/_next/static/chunks/1a04d31843c96649.js","/litellm-asset-prefix/_next/static/chunks/ed90bf177ad61e18.js","/litellm-asset-prefix/_next/static/chunks/2971c4658f1bcd7d.js","/litellm-asset-prefix/_next/static/chunks/6c4c97f1ea6e7d77.js","/litellm-asset-prefix/_next/static/chunks/9d6e5aad99b19216.js","/litellm-asset-prefix/_next/static/chunks/134f728fa7099e3e.js","/litellm-asset-prefix/_next/static/chunks/acbeac1b0fde1fdf.js","/litellm-asset-prefix/_next/static/chunks/fa6fc6b79591df63.js","/litellm-asset-prefix/_next/static/chunks/7e417dd24c8becd0.js","/litellm-asset-prefix/_next/static/chunks/348b31083769a7c4.js","/litellm-asset-prefix/_next/static/chunks/a85adee4198d5478.js","/litellm-asset-prefix/_next/static/chunks/c8eee6971ca36303.js","/litellm-asset-prefix/_next/static/chunks/0adb91ab5f3140d5.js","/litellm-asset-prefix/_next/static/chunks/b6cdb9a433f054f3.js","/litellm-asset-prefix/_next/static/chunks/22970a12064ba16b.js","/litellm-asset-prefix/_next/static/chunks/aae16a3ce4812424.js","/litellm-asset-prefix/_next/static/chunks/4980372eaa37b78b.js","/litellm-asset-prefix/_next/static/chunks/d069df5baead6d90.js","/litellm-asset-prefix/_next/static/chunks/69365f493e1655a4.js","/litellm-asset-prefix/_next/static/chunks/0a65da2cd24e2ab6.js","/litellm-asset-prefix/_next/static/chunks/fc4d54eb6afe7984.js","/litellm-asset-prefix/_next/static/chunks/e99f98e7f34532c9.js","/litellm-asset-prefix/_next/static/chunks/496b84010c33cf69.js","/litellm-asset-prefix/_next/static/chunks/06ebe9b0e9cdf241.js","/litellm-asset-prefix/_next/static/chunks/df6546cd8a44d3b3.js","/litellm-asset-prefix/_next/static/chunks/d3ac82723ec9e30d.js","/litellm-asset-prefix/_next/static/chunks/99cf9cf99df5ccfc.js","/litellm-asset-prefix/_next/static/chunks/07fd9d7c5c879cb6.js","/litellm-asset-prefix/_next/static/chunks/8dda507c226082ca.js","/litellm-asset-prefix/_next/static/chunks/54e29148cb2f2582.js","/litellm-asset-prefix/_next/static/chunks/3675074b1d85e268.js","/litellm-asset-prefix/_next/static/chunks/fcdf7322b0aa3e2e.js","/litellm-asset-prefix/_next/static/chunks/bd94e2fe34d8a187.js"],"default"]
17:I[897367,["/litellm-asset-prefix/_next/static/chunks/d96012bcfc98706a.js","/litellm-asset-prefix/_next/static/chunks/dbca964212122d58.js"],"OutletBoundary"]
18:"$Sreact.suspense"
:HL["/litellm-asset-prefix/_next/static/chunks/3f3fa56b5786d58c.css","style"]
0:{"buildId":"WhBGJTAPhDM3j-59ST728","rsc":["$","$1","c",{"children":[["$","$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}
0:{"buildId":"Kalni9LnFJDBB7xvqCPNe","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"}],["$","script","script-0",{"src":"/litellm-asset-prefix/_next/static/chunks/e627c7aa5ead52b3.js","async":true}],["$","script","script-1",{"src":"/litellm-asset-prefix/_next/static/chunks/142704439974f6b3.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/7d82a1cebfdb679c.js","async":true}],["$","script","script-4",{"src":"/litellm-asset-prefix/_next/static/chunks/2d471965761a22ff.js","async":true}],["$","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/c847ecdf8c790b0b.js","async":true}],["$","script","script-8",{"src":"/litellm-asset-prefix/_next/static/chunks/403c4d96324c23a6.js","async":true}],["$","script","script-9",{"src":"/litellm-asset-prefix/_next/static/chunks/88c74f8b4b20d25a.js","async":true}],["$","script","script-10",{"src":"/litellm-asset-prefix/_next/static/chunks/d64d74932cb225a3.js","async":true}],["$","script","script-11",{"src":"/litellm-asset-prefix/_next/static/chunks/8c13023d89b01566.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/74ce31aa0fb2adc9.js","async":true}],["$","script","script-14",{"src":"/litellm-asset-prefix/_next/static/chunks/cdf98a03da656604.js","async":true}],["$","script","script-15",{"src":"/litellm-asset-prefix/_next/static/chunks/cac89fc12fb6ef7e.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/1a04d31843c96649.js","async":true}],["$","script","script-18",{"src":"/litellm-asset-prefix/_next/static/chunks/ed90bf177ad61e18.js","async":true}],["$","script","script-19",{"src":"/litellm-asset-prefix/_next/static/chunks/2971c4658f1bcd7d.js","async":true}],["$","script","script-20",{"src":"/litellm-asset-prefix/_next/static/chunks/6c4c97f1ea6e7d77.js","async":true}],["$","script","script-21",{"src":"/litellm-asset-prefix/_next/static/chunks/9d6e5aad99b19216.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/acbeac1b0fde1fdf.js","async":true}],["$","script","script-24",{"src":"/litellm-asset-prefix/_next/static/chunks/fa6fc6b79591df63.js","async":true}],["$","script","script-25",{"src":"/litellm-asset-prefix/_next/static/chunks/7e417dd24c8becd0.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/a85adee4198d5478.js","async":true}],["$","script","script-28",{"src":"/litellm-asset-prefix/_next/static/chunks/c8eee6971ca36303.js","async":true}],["$","script","script-29",{"src":"/litellm-asset-prefix/_next/static/chunks/0adb91ab5f3140d5.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/22970a12064ba16b.js","async":true}],["$","script","script-32",{"src":"/litellm-asset-prefix/_next/static/chunks/aae16a3ce4812424.js","async":true}],["$","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"]}],"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/90f0529c4408147d.js","async":true}]
7:["$","script","script-35",{"src":"/litellm-asset-prefix/_next/static/chunks/a85adee4198d5478.js","async":true}]
6:["$","script","script-34",{"src":"/litellm-asset-prefix/_next/static/chunks/d069df5baead6d90.js","async":true}]
7:["$","script","script-35",{"src":"/litellm-asset-prefix/_next/static/chunks/69365f493e1655a4.js","async":true}]
8:["$","script","script-36",{"src":"/litellm-asset-prefix/_next/static/chunks/0a65da2cd24e2ab6.js","async":true}]
9:["$","script","script-37",{"src":"/litellm-asset-prefix/_next/static/chunks/8604d59a86c051be.js","async":true}]
a:["$","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
9:["$","script","script-37",{"src":"/litellm-asset-prefix/_next/static/chunks/fc4d54eb6afe7984.js","async":true}]
a:["$","script","script-38",{"src":"/litellm-asset-prefix/_next/static/chunks/e99f98e7f34532c9.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/06ebe9b0e9cdf241.js","async":true}]
d:["$","script","script-41",{"src":"/litellm-asset-prefix/_next/static/chunks/df6546cd8a44d3b3.js","async":true}]
e:["$","script","script-42",{"src":"/litellm-asset-prefix/_next/static/chunks/d3ac82723ec9e30d.js","async":true}]
f:["$","script","script-43",{"src":"/litellm-asset-prefix/_next/static/chunks/99cf9cf99df5ccfc.js","async":true}]
10:["$","script","script-44",{"src":"/litellm-asset-prefix/_next/static/chunks/07fd9d7c5c879cb6.js","async":true}]
11:["$","script","script-45",{"src":"/litellm-asset-prefix/_next/static/chunks/8dda507c226082ca.js","async":true}]
12:["$","script","script-46",{"src":"/litellm-asset-prefix/_next/static/chunks/54e29148cb2f2582.js","async":true}]
13:["$","script","script-47",{"src":"/litellm-asset-prefix/_next/static/chunks/3675074b1d85e268.js","async":true}]
14:["$","script","script-48",{"src":"/litellm-asset-prefix/_next/static/chunks/fcdf7322b0aa3e2e.js","async":true}]
15:["$","script","script-49",{"src":"/litellm-asset-prefix/_next/static/chunks/bd94e2fe34d8a187.js","async":true}]
16:["$","$L17",null,{"children":["$","$18",null,{"name":"Next.MetadataOutlet","children":"$@19"}]}]
19:null

87
litellm/proxy/_experimental/out/__next._full.txt
View file

File diff suppressed because one or more lines are too long

2
litellm/proxy/_experimental/out/__next._head.txt
View file

@ -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:"$Sreact.suspense"
5:I[27201,["/litellm-asset-prefix/_next/static/chunks/d96012bcfc98706a.js","/litellm-asset-prefix/_next/static/chunks/dbca964212122d58.js"],"IconMark"]
0:{"buildId":"WhBGJTAPhDM3j-59ST728","rsc":["$","$1","h",{"children":[null,["$","$L2",null,{"children":[["$","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}
0:{"buildId":"Kalni9LnFJDBB7xvqCPNe","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}

4
litellm/proxy/_experimental/out/__next._index.txt
View file

@ -4,5 +4,5 @@
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/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}
:HL["/litellm-asset-prefix/_next/static/chunks/8dc3b559a2e76f88.css","style"]
0:{"buildId":"Kalni9LnFJDBB7xvqCPNe","rsc":["$","$1","c",{"children":[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/chunks/4e20891f2fd03463.css","precedence":"next"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/chunks/8dc3b559a2e76f88.css","precedence":"next"}],["$","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}

4
litellm/proxy/_experimental/out/__next._tree.txt
View file

@ -1,5 +1,5 @@
:HL["/litellm-asset-prefix/_next/static/chunks/4e20891f2fd03463.css","style"]
:HL["/litellm-asset-prefix/_next/static/chunks/7936c9bd377ea4bf.css","style"]
:HL["/litellm-asset-prefix/_next/static/chunks/8dc3b559a2e76f88.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":"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}
0:{"buildId":"Kalni9LnFJDBB7xvqCPNe","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
litellm/proxy/_experimental/out/_next/static/WhBGJTAPhDM3j-59ST728/_buildManifest.js → litellm/proxy/_experimental/out/_next/static/Kalni9LnFJDBB7xvqCPNe/_buildManifest.js
View file

0
litellm/proxy/_experimental/out/_next/static/WhBGJTAPhDM3j-59ST728/_clientMiddlewareManifest.json → litellm/proxy/_experimental/out/_next/static/Kalni9LnFJDBB7xvqCPNe/_clientMiddlewareManifest.json
View file

0
litellm/proxy/_experimental/out/_next/static/WhBGJTAPhDM3j-59ST728/_ssgManifest.js → litellm/proxy/_experimental/out/_next/static/Kalni9LnFJDBB7xvqCPNe/_ssgManifest.js
View file

1
litellm/proxy/_experimental/out/_next/static/chunks/0184f3b07b67e571.js
View file

File diff suppressed because one or more lines are too long

29
litellm/proxy/_experimental/out/_next/static/chunks/02765645e0bbd8f7.js
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/0289c4377358ae4f.js
View file

File diff suppressed because one or more lines are too long

2
litellm/proxy/_experimental/out/_next/static/chunks/e8718f949e42598e.js → litellm/proxy/_experimental/out/_next/static/chunks/07fd9d7c5c879cb6.js
View file

File diff suppressed because one or more lines are too long

420
litellm/proxy/_experimental/out/_next/static/chunks/0a55aff89c1ec2e4.js
View file

File diff suppressed because one or more lines are too long

7
litellm/proxy/_experimental/out/_next/static/chunks/0b06d056425a991f.js Normal file
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/0bd654557fbb50e9.js
View file

File diff suppressed because one or more lines are too long

8
litellm/proxy/_experimental/out/_next/static/chunks/0bffe854234d50c4.js Normal file
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/0ea9112947894f26.js Normal file
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/0ed98235bd6bf63a.js
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/10b2c4546ee6aca1.js Normal file
View file

File diff suppressed because one or more lines are too long

420
litellm/proxy/_experimental/out/_next/static/chunks/11362340846735c3.js Normal file
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/117fd0772eee5df6.js Normal file
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/124fefccff39e221.js
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/125e23733670afea.js
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/12a00fb6ae67dbdf.js
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/12b229c40945c2e9.js
View file

File diff suppressed because one or more lines are too long

7
litellm/proxy/_experimental/out/_next/static/chunks/16d77647b44247de.js Normal file
View file

File diff suppressed because one or more lines are too long

8
litellm/proxy/_experimental/out/_next/static/chunks/16ee7f92da0b1f99.js
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/17741b7a77c20f1b.js Normal file
View file

File diff suppressed because one or more lines are too long

9
litellm/proxy/_experimental/out/_next/static/chunks/179f4b987bc9083f.js Normal file
View file

File diff suppressed because one or more lines are too long

598
litellm/proxy/_experimental/out/_next/static/chunks/1a04d31843c96649.js Normal file
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/1a87dd202db8e85d.js
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/1b424ce64213980f.js Normal file
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/1eccde2dab0b3311.js Normal file
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/1f58814a2409d571.js Normal file
View file

File diff suppressed because one or more lines are too long

2
litellm/proxy/_experimental/out/_next/static/chunks/3330260a2a6da847.js → litellm/proxy/_experimental/out/_next/static/chunks/1f6df7977860dc7b.js
View file

File diff suppressed because one or more lines are too long

7
litellm/proxy/_experimental/out/_next/static/chunks/1fcff413509b2e1f.js Normal file
View file

File diff suppressed because one or more lines are too long

231
litellm/proxy/_experimental/out/_next/static/chunks/22970a12064ba16b.js Normal file
View file

File diff suppressed because one or more lines are too long

8
litellm/proxy/_experimental/out/_next/static/chunks/22e715061d511345.js Normal file
View file

File diff suppressed because one or more lines are too long

23
litellm/proxy/_experimental/out/_next/static/chunks/23887804eaacee0d.js
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/26fda1c4c6936e38.js Normal file
View file

File diff suppressed because one or more lines are too long

8
litellm/proxy/_experimental/out/_next/static/chunks/2ac51d4e6cc8e420.js
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/2f9ed92e7b7cd792.js Normal file
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/31ad6450b9c696ec.js Normal file
View file

File diff suppressed because one or more lines are too long

8
litellm/proxy/_experimental/out/_next/static/chunks/31e02a31dea7d5d2.js Normal file
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/3413b6a1ede03f29.js Normal file
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/34775f0167305a22.js
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/3569f12d1e9d5e0d.js Normal file
View file

File diff suppressed because one or more lines are too long

10
litellm/proxy/_experimental/out/_next/static/chunks/3675074b1d85e268.js Normal file
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/39768ec0eebd2554.js Normal file
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/3b2ec401925509b1.js
View file

File diff suppressed because one or more lines are too long

179
litellm/proxy/_experimental/out/_next/static/chunks/3e16ca85d4f4e974.js
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/3e395bb55b8572f7.js
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/4242033bd0f32638.js Normal file
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/442ccb8d620e1fa6.js Normal file
View file

File diff suppressed because one or more lines are too long

8
litellm/proxy/_experimental/out/_next/static/chunks/4472ece1be7379b3.js Normal file
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/_next/static/chunks/46a2cc6389ea6525.js
View file

@ -1 +0,0 @@
(globalThis.TURBOPACK||(globalThis.TURBOPACK=[])).push(["object"==typeof document?document.currentScript:void 0,618566,(e,t,s)=>{t.exports=e.r(976562)},346328,e=>{"use strict";var t=e.i(843476),s=e.i(271645),l=e.i(618566);let i="litellm-mcp-oauth-result",a="litellm-mcp-oauth-return-url",n=()=>{let e=(0,l.useSearchParams)(),n=(0,s.useMemo)(()=>e?{type:"litellm-mcp-oauth",code:e.get("code"),state:e.get("state")}:null,[e]);return(0,s.useEffect)(()=>{if(!n)return;try{window.sessionStorage.setItem(i,JSON.stringify(n)),window.localStorage.setItem(i,JSON.stringify(n))}catch(e){}let e=window.sessionStorage.getItem(a)||window.localStorage.getItem(a)||(()=>{let e=window.location.pathname||"",t=e.indexOf("/ui");if(t>=0){let s=e.slice(0,t+3);return s.endsWith("/")?s:`${s}`}return"/"})();window.location.replace(e)},[n]),(0,t.jsx)("div",{className:"min-h-screen flex items-center justify-center bg-slate-50 p-6",children:(0,t.jsxs)("div",{className:"max-w-lg w-full rounded-lg bg-white shadow-md p-8 text-center space-y-4",children:[(0,t.jsx)("h1",{className:"text-xl font-semibold text-slate-900",children:"LiteLLM MCP OAuth"}),(0,t.jsx)("p",{className:"text-sm text-slate-700",children:"Authorization complete. You may close this window and return to the LiteLLM dashboard."}),(0,t.jsx)("p",{className:"text-xs text-slate-500",children:"If the window does not close automatically, everything is still saved—you can close it manually."})]})})};e.s(["default",0,()=>(0,t.jsx)(s.Suspense,{fallback:(0,t.jsx)("div",{className:"min-h-screen flex items-center justify-center",children:"Loading..."}),children:(0,t.jsx)(n,{})})])}]);

1
litellm/proxy/_experimental/out/_next/static/chunks/476e3c64fbdd0295.js
View file

@ -1 +0,0 @@
(globalThis.TURBOPACK||(globalThis.TURBOPACK=[])).push(["object"==typeof document?document.currentScript:void 0,21548,e=>{"use strict";var t=e.i(616303);e.s(["Empty",()=>t.default])},601236,e=>{e.v(e=>Promise.resolve().then(()=>e(764205)))}]);

1
litellm/proxy/_experimental/out/_next/static/chunks/4c4469911e2f315e.js Normal file
View file

File diff suppressed because one or more lines are too long

13
litellm/proxy/_experimental/out/_next/static/chunks/4d3d997560b322ca.js
View file

File diff suppressed because one or more lines are too long

598
litellm/proxy/_experimental/out/_next/static/chunks/4e4d0f466b5c1780.js
View file

File diff suppressed because one or more lines are too long

7
litellm/proxy/_experimental/out/_next/static/chunks/503ca4764960a7c8.js Normal file
View file

File diff suppressed because one or more lines are too long

8
litellm/proxy/_experimental/out/_next/static/chunks/531dc633eecbb64f.js Normal file
View file

File diff suppressed because one or more lines are too long

Some files were not shown because too many files have changed in this diff Show more