chore: move ui and vscode-extension under litellm and delete docs (#50992)

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

.gitguardian.yaml

@@ -22,7 +22,7 @@ secret:
     
     # Build outputs and static assets
     - "litellm/proxy/_experimental/out/**"
-    - "ui/litellm-dashboard/public/**"
+    - "litellm/ui/litellm-dashboard/public/**"
     - "**/swagger/*.js"
     - "**/*.woff"
     - "**/*.woff2"
@@ -34,7 +34,6 @@ secret:
     - "tests/**/*.txt"
     
     # Documentation and other non-code files
-    - "docs/**"
     - "**/*.md"
     - "**/*.lock"
     - "uv.lock"

.github/CONTRIBUTING.md

@@ -278,14 +278,12 @@ Provider work (a new provider, a new parameter, a new usage or cost field) is th
 
 **Preserve zero prices.** In [`model_prices_and_context_window.json`](../model_prices_and_context_window.json), an explicit `0.0` means that the priced operation is free. A missing field or `null` means no rate is specified, so the relevant calculator may use a fallback. For example, when no batch input rate is configured, batch cache writes use `cache_creation_input_token_cost` if set, otherwise the regular input rate, then apply the batch discount. A zero ordinary input rate does not make separately priced cache reads or writes free. Test `rate is None` before substituting a fallback, since `row.get("cache_creation_input_token_cost") or fallback` would discard a valid zero. Speech keeps character pricing ahead of token pricing even when the character rate is zero. If neither rate is configured, speech cost calculation raises an error. Its model lookup preserves unset rates instead of treating compatibility defaults as explicit zero prices. Perplexity keeps a configured legacy search rate ahead of the current search rate, including zero. When registering custom prices, `None` leaves an existing rate unchanged and `0.0` overrides it
 
-**Find the existing machinery before you add plumbing.** LiteLLM already has generic paths that move data between the endpoints, the provider transformations, and cost tracking. A second, hand-rolled path for the same data is a common reason a provider PR gets rewritten before merge. [`ARCHITECTURE.md`](../docs/ARCHITECTURE.md) shows where the layers live, and the decision records in [`docs/adrs/`](../docs/adrs/AGENTS.md) explain why they are shaped that way. For example, [the ADR on provider usage fields](../docs/adrs/adr_001_provider_usage_fields_ride_as_usage_extras.md) covers how provider-specific usage fields reach cost tracking. If you cannot find a mechanism for what you need, say so in the PR or ask in [#pr-review on Slack](https://join.slack.com/t/litellmossslack/shared_invite/zt-3o7nkuyfr-p_kbNJj8taRfXGgQI1~YyA) before you build one
+**Find the existing machinery before you add plumbing.** LiteLLM already has generic paths that move data between the endpoints, the provider transformations, and cost tracking. A second, hand-rolled path for the same data is a common reason a provider PR gets rewritten before merge. If you cannot find a mechanism for what you need, say so in the PR or ask in [#pr-review on Slack](https://join.slack.com/t/litellmossslack/shared_invite/zt-3o7nkuyfr-p_kbNJj8taRfXGgQI1~YyA) before you build one
 
 **Bill a new provider usage field from the usage object.** Leave the field on the usage object as an extra and read it in that provider's `cost_calculator.py`. A provider without one gets a new `cost_calculator.py` and an arm for it in `cost_per_token` (`litellm/cost_calculator.py`), which picks the calculator by provider. If the provider's transform builds `Usage` from named fields, as the Anthropic, Gemini, and Bedrock Converse ones do, pass the new field there too. Streamed requests rebuild usage in `ChunkProcessor.calculate_usage` (`litellm/litellm_core_utils/streaming_chunk_builder_utils.py`), which does not copy extras yet the way the Responses-to-chat bridge does (minus a short exclusion list), so until it does, bill the field on streams by naming it there, as Anthropic's `inference_geo` is. A provider that reports its own charge for the request, as OpenRouter does in `usage.cost`, is billed at that charge from `_hidden_params` before any calculator runs, unless the deployment sets its own prices. When the field counts a built-in tool such as web search, add the provider to `get_cost_for_web_search_request` in `litellm/llms/__init__.py`, and add a gate to `litellm/litellm_core_utils/llm_cost_calc/tool_call_cost_tracking.py` only when no existing gate fires. Then show the field's cost in your proof on every endpoint it reaches, streaming included
 
 **Do not change what a caller sees to make internals easier.** Each endpoint keeps the schema of the API it emulates. A `/v1/responses` caller gets `input_tokens` and a `/v1/chat/completions` caller gets `prompt_tokens`, whatever the provider sent and whatever cost tracking needs. A provider usage field that shows up as an extra key is fine, since it only adds a key, but renaming, removing, or reshaping a key the endpoint defines is not. Reshaping a public response to feed an internal consumer breaks every user of that endpoint
 
-If your change makes an architecture decision, such as a new cross-cutting mechanism or a deliberate difference from a provider's API shape, add an ADR to [`docs/adrs/`](../docs/adrs/AGENTS.md) in the same PR
-
 ## Building and Running Locally
 
 ### LiteLLM Proxy Server
@@ -330,7 +328,7 @@ git clone https://github.com/YOUR_USERNAME/litellm.git
 cd litellm
 
 # Navigate to the UI dashboard directory
-cd ui/litellm-dashboard
+cd litellm/ui/litellm-dashboard
 
 # Install dependencies
 npm install

.github/actions/detect-changes/action.yml

@@ -1,7 +1,7 @@
 name: "Detect relevant changes"
 description: >-
   Classify the pull request's changed files with .github/scripts/ci/classify_changes.sh
-  and expose decision=run|skip for one category. backend means anything outside ui/,
+  and expose decision=run|skip for one category. backend means anything outside litellm/ui/,
   docs/ and markdown; ui means the dashboard sources alone. decision=skip lets callers
   short-circuit expensive steps while the job still completes successfully and satisfies
   its required status check, which a paths: filter cannot do because a workflow that

.github/scripts/ci/classify_changes.sh

@@ -27,8 +27,8 @@ while IFS= read -r file || [ -n "$file" ]; do
       has_windows_release=true ;;
   esac
   case "$file" in
-    ui/* | tests/e2e/ui/*) has_client=true ;;
-    docs/* | *.md | *.mdx) : ;;
+    litellm/ui/* | tests/e2e/ui/*) has_client=true ;;
+    *.md | *.mdx) : ;;
     .github/*) has_ci=true; has_backend=true ;;
     *) has_backend=true ;;
   esac

.github/scripts/ci/run_integration.sh

@@ -81,7 +81,7 @@ export INTEGRATION_UPSTREAM_URL=http://127.0.0.1:8190
 export INTEGRATION_MASTER_KEY="$LITELLM_MASTER_KEY"
 export LITELLM_UI_PATH="$PWD/litellm/proxy/_experimental/out"
 if [ "$suite" = browser ]; then
-  export LITELLM_UI_PATH="$PWD/ui/litellm-dashboard/out"
+  export LITELLM_UI_PATH="$PWD/litellm/ui/litellm-dashboard/out"
   test -f "$LITELLM_UI_PATH/index.html"
 fi
 export INTEGRATION_SEED="$(.venv/bin/python -c 'import hashlib,os; print(int(hashlib.sha256(((os.environ.get("GITHUB_SHA") or "local") + (os.environ.get("GITHUB_RUN_ID") or "local")).encode()).hexdigest()[:8],16))')"

.github/scripts/verify_linux_native_wheel.py

@@ -128,7 +128,7 @@ def main(
             member.filename
             for member in wheel_members
             if member.filename.endswith((".pdb", ".dwp", ".rlib", ".rmeta", "Cargo.toml", "Cargo.lock"))
-            or member.filename.startswith("litellm/deploy/")
+            or member.filename.startswith(("litellm/deploy/", "litellm/ui/", "litellm/vscode-extension/"))
             or any(part.endswith(".dSYM") for part in PurePosixPath(member.filename).parts)
         )
         native_member: Final = native_members[0]

.github/workflows/image-scan.yml

@@ -26,8 +26,8 @@ on:
       - litellm-proxy-extras/**
       - tests/integration/database/image/**
       - uv.lock
-      - ui/litellm-dashboard/package-lock.json
-      - ui/nginx.conf
+      - litellm/ui/litellm-dashboard/package-lock.json
+      - litellm/ui/nginx.conf
       - .github/workflows/image-scan.yml
       - .github/grype.yaml
   schedule:

.github/workflows/osv-scan.yml

@@ -42,5 +42,5 @@ jobs:
           "$RUNNER_TEMP/osv-scanner" scan source \
             --config .github/osv-scanner.toml \
             -L uv.lock \
-            -L ui/litellm-dashboard/package-lock.json \
-            -L vscode-extension/package-lock.json
+            -L litellm/ui/litellm-dashboard/package-lock.json \
+            -L litellm/vscode-extension/package-lock.json

.github/workflows/test-integration.yml

@@ -150,22 +150,22 @@ jobs:
         timeout-minutes: 5
         uses: actions/setup-node@a0853c24544627f65ddf259abe73b1d18a591444 # v5.0.0
         with:
-          node-version-file: ui/litellm-dashboard/.nvmrc
+          node-version-file: litellm/ui/litellm-dashboard/.nvmrc
           cache: "npm"
           cache-dependency-path: |
-            ui/litellm-dashboard/package-lock.json
+            litellm/ui/litellm-dashboard/package-lock.json
             tests/e2e/ui/package-lock.json
 
       - name: Install browser dependencies and build the dashboard
         if: matrix.suite == 'browser'
         timeout-minutes: 20
         run: |
-          (cd ui/litellm-dashboard && npm ci)
+          (cd litellm/ui/litellm-dashboard && npm ci)
           (cd tests/e2e/ui && npm ci)
           sudo env PATH="$PATH" DEBIAN_FRONTEND=noninteractive \
             node tests/e2e/ui/node_modules/@playwright/test/cli.js install-deps chromium
           node tests/e2e/ui/node_modules/@playwright/test/cli.js install chromium
-          (cd ui/litellm-dashboard && NEXT_TELEMETRY_DISABLED=1 npm run build)
+          (cd litellm/ui/litellm-dashboard && NEXT_TELEMETRY_DISABLED=1 npm run build)
 
       - name: Run integration contracts
         timeout-minutes: 45

.github/workflows/test-linting.yml

@@ -114,7 +114,7 @@ jobs:
       - name: Check ruff format
         if: steps.changes.outputs.decision != 'skip'
         run: |
-          git diff --name-only --diff-filter=ACMR "$GATE_BASE_SHA" HEAD -- ':(glob)litellm/**/*.py' | grep -v '^litellm/enterprise/' > "$RUNNER_TEMP/ruff_format_files.txt" || true
+          git diff --name-only --diff-filter=ACMR "$GATE_BASE_SHA" HEAD -- ':(glob)litellm/**/*.py' | grep -Ev '^litellm/(enterprise|ui|vscode-extension)/' > "$RUNNER_TEMP/ruff_format_files.txt" || true
           if [ ! -s "$RUNNER_TEMP/ruff_format_files.txt" ]; then
             echo "No changed litellm Python files to check with ruff format."
             exit 0
@@ -271,7 +271,7 @@ jobs:
     timeout-minutes: 8
     defaults:
       run:
-        working-directory: ui/litellm-dashboard
+        working-directory: litellm/ui/litellm-dashboard
 
     steps:
       - name: Checkout repository
@@ -315,9 +315,9 @@ jobs:
         if: steps.changed.outputs.has_files == 'true'
         uses: actions/setup-node@a0853c24544627f65ddf259abe73b1d18a591444 # v5.0.0
         with:
-          node-version-file: ui/litellm-dashboard/.nvmrc
+          node-version-file: litellm/ui/litellm-dashboard/.nvmrc
           cache: "npm"
-          cache-dependency-path: ui/litellm-dashboard/package-lock.json
+          cache-dependency-path: litellm/ui/litellm-dashboard/package-lock.json
 
       - name: Install dependencies
         if: steps.changed.outputs.has_files == 'true'
@@ -333,12 +333,12 @@ jobs:
           status=0
           if [ ${#prettier_files[@]} -gt 0 ]; then
             echo "::group::Prettier (${#prettier_files[@]} files)"
-            npx prettier --check "${prettier_files[@]}" || { status=1; echo "::error::Unformatted files. Fix with: npm run format"; }
+            node_modules/.bin/prettier --check "${prettier_files[@]}" || { status=1; echo "::error::Unformatted files. Fix with: npm run format"; }
             echo "::endgroup::"
           fi
           if [ ${#eslint_files[@]} -gt 0 ]; then
             echo "::group::ESLint (${#eslint_files[@]} files)"
-            npx eslint --no-warn-ignored --pass-on-unpruned-suppressions "${eslint_files[@]}" || status=1
+            node_modules/.bin/eslint --no-warn-ignored --pass-on-unpruned-suppressions "${eslint_files[@]}" || status=1
             echo "::endgroup::"
           fi
           exit $status
@@ -375,7 +375,7 @@ jobs:
             exit 0
           fi
           files="$(git diff --name-only "$base" HEAD)"
-          if grep -Eq '^(litellm/|enterprise/|(pyproject\.toml|uv\.lock)$|ui/litellm-dashboard/(src/lib/http/schema\.d\.ts|scripts/gen-api-types\.mjs|package(-lock)?\.json)$|\.github/workflows/test-linting\.yml$)' <<< "$files"; then
+          if grep -Ev '^litellm/(ui|vscode-extension)/' <<< "$files" | grep -E '^(litellm/|enterprise/|(pyproject\.toml|uv\.lock)$|\.github/workflows/test-linting\.yml$)' >/dev/null || grep -Eq '^litellm/ui/litellm-dashboard/(src/lib/http/schema\.d\.ts|scripts/gen-api-types\.mjs|package(-lock)?\.json)$' <<< "$files"; then
             echo "relevant=true" >> "$GITHUB_OUTPUT"
           else
             echo "No litellm, enterprise, dependency or generator changes in this pull request, nothing to verify."
@@ -434,7 +434,7 @@ jobs:
             echo "A lazily loaded route or model changed without regenerating the snapshot that /openapi.json serves for unloaded features."
             echo "To fix, run from the repo root:"
             echo "  uv run python -m litellm.proxy._lazy_openapi_snapshot"
-            echo "then run npm run gen:api from ui/litellm-dashboard and commit both files."
+            echo "then run npm run gen:api from litellm/ui/litellm-dashboard and commit both files."
             exit 1
           fi
           echo "_lazy_openapi_snapshot.json is in sync with the lazily loaded routes."
@@ -443,18 +443,18 @@ jobs:
         if: steps.changes.outputs.relevant == 'true'
         uses: actions/setup-node@a0853c24544627f65ddf259abe73b1d18a591444 # v5.0.0
         with:
-          node-version-file: ui/litellm-dashboard/.nvmrc
+          node-version-file: litellm/ui/litellm-dashboard/.nvmrc
           cache: "npm"
-          cache-dependency-path: ui/litellm-dashboard/package-lock.json
+          cache-dependency-path: litellm/ui/litellm-dashboard/package-lock.json
 
       - name: Install dashboard dependencies
         if: steps.changes.outputs.relevant == 'true'
-        working-directory: ui/litellm-dashboard
+        working-directory: litellm/ui/litellm-dashboard
         run: npm ci
 
       - name: Regenerate types from the live spec
         if: steps.changes.outputs.relevant == 'true'
-        working-directory: ui/litellm-dashboard
+        working-directory: litellm/ui/litellm-dashboard
         env:
           LITELLM_PYTHON: "uv run --no-sync python"
         run: npm run gen:api
@@ -462,11 +462,11 @@ jobs:
       - name: Fail if types are stale
         if: steps.changes.outputs.relevant == 'true'
         run: |
-          if ! git diff --exit-code -- ui/litellm-dashboard/src/lib/http/schema.d.ts; then
-            echo "::error file=ui/litellm-dashboard/src/lib/http/schema.d.ts::Generated API types are out of sync with the proxy OpenAPI spec."
+          if ! git diff --exit-code -- litellm/ui/litellm-dashboard/src/lib/http/schema.d.ts; then
+            echo "::error file=litellm/ui/litellm-dashboard/src/lib/http/schema.d.ts::Generated API types are out of sync with the proxy OpenAPI spec."
             echo ""
             echo "A backend route or model changed without regenerating the dashboard types."
-            echo "To fix, run from ui/litellm-dashboard:"
+            echo "To fix, run from litellm/ui/litellm-dashboard:"
             echo "  npm run gen:api"
             echo "then commit the updated src/lib/http/schema.d.ts."
             exit 1

.github/workflows/test-unit.yml

@@ -1188,7 +1188,7 @@ jobs:
     timeout-minutes: 20
     defaults:
       run:
-        working-directory: ui/litellm-dashboard
+        working-directory: litellm/ui/litellm-dashboard
 
     steps:
       - name: Checkout repository
@@ -1207,9 +1207,9 @@ jobs:
         if: steps.changes.outputs.decision != 'skip'
         uses: actions/setup-node@a0853c24544627f65ddf259abe73b1d18a591444 # v5.0.0
         with:
-          node-version-file: ui/litellm-dashboard/.nvmrc
+          node-version-file: litellm/ui/litellm-dashboard/.nvmrc
           cache: "npm"
-          cache-dependency-path: ui/litellm-dashboard/package-lock.json
+          cache-dependency-path: litellm/ui/litellm-dashboard/package-lock.json
 
       - name: Install dependencies
         if: steps.changes.outputs.decision != 'skip'

.github/workflows/test-vscode-extension.yml

@@ -8,13 +8,13 @@ on:
       - main
       - "litellm_**"
     paths:
-      - "vscode-extension/**"
+      - "litellm/vscode-extension/**"
       - ".github/workflows/test-vscode-extension.yml"
   push:
     branches:
       - main
     paths:
-      - "vscode-extension/**"
+      - "litellm/vscode-extension/**"
       - ".github/workflows/test-vscode-extension.yml"
 
 concurrency:
@@ -27,7 +27,7 @@ jobs:
     timeout-minutes: 10
     defaults:
       run:
-        working-directory: vscode-extension
+        working-directory: litellm/vscode-extension
 
     steps:
       - name: Checkout repository
@@ -41,7 +41,7 @@ jobs:
         with:
           node-version: "24"
           cache: npm
-          cache-dependency-path: vscode-extension/package-lock.json
+          cache-dependency-path: litellm/vscode-extension/package-lock.json
 
       - name: Install dependencies
         run: npm ci
@@ -59,5 +59,5 @@ jobs:
         uses: actions/upload-artifact@4cec3d8aa04e39d1a68397de0c4cd6fb9dce8ec1 # v4.6.1
         with:
           name: litellm-vscode
-          path: vscode-extension/*.vsix
+          path: litellm/vscode-extension/*.vsix
           if-no-files-found: error

.gitignore

@@ -55,12 +55,12 @@ hosted_config.yaml
 litellm/proxy/tests/node_modules
 litellm/proxy/tests/package.json
 litellm/proxy/tests/package-lock.json
-ui/litellm-dashboard/.next
-ui/litellm-dashboard/node_modules
-ui/litellm-dashboard/next-env.d.ts
+litellm/ui/litellm-dashboard/.next
+litellm/ui/litellm-dashboard/node_modules
+litellm/ui/litellm-dashboard/next-env.d.ts
 *.tsbuildinfo
-ui/litellm-dashboard/package.json
-ui/litellm-dashboard/package-lock.json
+litellm/ui/litellm-dashboard/package.json
+litellm/ui/litellm-dashboard/package-lock.json
 litellm/deploy/helm/litellm/charts/*.tgz
 litellm/deploy/helm/*.tgz
 litellm/proxy/vertex_key.json
@@ -146,7 +146,7 @@ crash.*.log
 # pytest coverage data
 .coverage
 
-ui/litellm-dashboard/out/
+litellm/ui/litellm-dashboard/out/
 litellm.log
 
 .coverage-rust

AGENTS.md

@@ -30,8 +30,6 @@ A test must only fail when litellm code changes. Never pin facts we don't own (a
 
 End-to-end tests belong in `tests/e2e/`. A rule about one directory's files, like its harness or which CI runs it, goes in that directory's `AGENTS.md`, never only in a README or here. Read a directory's `AGENTS.md` before editing files in it
 
-Before you build a new way to move data between the endpoints, the provider transformations, and cost tracking or logging, read the architecture decision records in `docs/adrs/`, which say why those layers are shaped the way they are
-
 When creating PRs, target the repository's current default branch for both internal and external / OSS contributions. Check it with `python3 scripts/default_branch.py --branch` instead of assuming a branch name or relying on cached `origin/HEAD`
 
 When writing a PR body, treat the comments and imperative instructions inside .github/PULL_REQUEST_TEMPLATE/general.md as rules to follow, not just layout. Agent harnesses may strip HTML comments from copies of that file injected into context, so read .github/PULL_REQUEST_TEMPLATE/general.md from disk before writing a PR body to make sure you see every comment rule. A section you have nothing to put in (Relevant issues, Affected release, Linear ticket, Caveats, QA runbook, and so on) is removed entirely, heading included, never left as an empty title

Makefile

@@ -91,7 +91,7 @@ install-dev:
 bootstrap:
 	$(UV) sync --inexact --frozen --extra proxy --group proxy-dev --group e2e-dev
 	$(UV_RUN) python scripts/prisma_generate_if_needed.py
-	cd ui/litellm-dashboard && ../../scripts/with_dashboard_node.sh npm install --no-audit --no-fund
+	cd litellm/ui/litellm-dashboard && ../../../scripts/with_dashboard_node.sh npm install --no-audit --no-fund
 	@main_root=$$(git worktree list --porcelain | head -1 | sed 's/^worktree //'); \
 	if [ "$$main_root" != "$$(git rev-parse --show-toplevel)" ] && [ -f "$$main_root/.env" ] && [ ! -f .env ]; then \
 		cp "$$main_root/.env" .env && echo "bootstrap: copied .env from $$main_root"; \

README.md

@@ -660,7 +660,7 @@ The Terraform modules live at [`litellm/deploy/terraform/litellm/aws/`](./litell
 2. Start proxy backend: `uv run python litellm/proxy/proxy_cli.py`
 
 #### Frontend
-1. Navigate to `ui/litellm-dashboard` (dependencies were already installed w/ `make bootstrap`)
+1. Navigate to `litellm/ui/litellm-dashboard` (dependencies were already installed w/ `make bootstrap`)
 2. Start dashboard: `npm run dev`
 
 ### Verify Docker Image Signatures

docs/ARCHITECTURE.md

@@ -1,419 +0,0 @@
-# LiteLLM Architecture - LiteLLM SDK + AI Gateway
-
-This document helps contributors understand where to make changes in LiteLLM.
-
-For why a layer is shaped the way it is, read the architecture decision records in [`docs/adrs/`](adrs/AGENTS.md) (Python SDK and proxy) and [`litellm-rust/docs/adrs/`](../litellm-rust/docs/adrs/AGENTS.md) (Rust core)
-
----
-
-## How It Works
-
-The LiteLLM AI Gateway (Proxy) uses the LiteLLM SDK internally for all LLM calls:
-
-```
-OpenAI SDK (client)    ──▶  LiteLLM AI Gateway (proxy/)  ──▶  LiteLLM SDK (litellm/)  ──▶  LLM API
-Anthropic SDK (client) ──▶  LiteLLMAI Gateway (proxy/)  ──▶  LiteLLM SDK (litellm/)  ──▶  LLM API
-Any HTTP client        ──▶  LiteLLMAI Gateway (proxy/)  ──▶  LiteLLM SDK (litellm/)  ──▶  LLM API
-```
-
-The **AI Gateway** adds authentication, rate limiting, budgets, and routing on top of the SDK.
-The **SDK** handles the actual LLM provider calls, request/response transformations, and streaming.
-
----
-
-## 1. AI Gateway (Proxy) Request Flow
-
-The AI Gateway (`litellm/proxy/`) wraps the SDK with authentication, rate limiting, and management features.
-
-```mermaid
-sequenceDiagram
-    participant Client
-    participant ProxyServer as proxy/proxy_server.py
-    participant Auth as proxy/auth/user_api_key_auth.py
-    participant Redis as Redis Cache
-    participant Hooks as proxy/hooks/
-    participant Router as router.py
-    participant Main as main.py + utils.py
-    participant Handler as llms/custom_httpx/llm_http_handler.py
-    participant Transform as llms/{provider}/chat/transformation.py
-    participant Provider as LLM Provider API
-    participant CostCalc as cost_calculator.py
-    participant LoggingObj as litellm_logging.py
-    participant DBWriter as db/db_spend_update_writer.py
-    participant Postgres as PostgreSQL
-
-    %% Request Flow
-    Client->>ProxyServer: POST /v1/chat/completions
-    ProxyServer->>Auth: user_api_key_auth()
-    Auth->>Redis: Check API key cache
-    Redis-->>Auth: Key info + spend limits
-    ProxyServer->>Hooks: parallel_request_limiter, cache_control_check
-    Hooks->>Redis: Check/increment rate limit counters
-    ProxyServer->>Router: route_request()
-    Router->>Main: litellm.acompletion()
-    Main->>Handler: BaseLLMHTTPHandler.completion()
-    Handler->>Transform: ProviderConfig.transform_request()
-    Handler->>Provider: HTTP Request
-    Provider-->>Handler: Response
-    Handler->>Transform: ProviderConfig.transform_response()
-    Transform-->>Handler: ModelResponse
-    Handler-->>Main: ModelResponse
-    
-    %% Cost Attribution (in utils.py wrapper)
-    Main->>LoggingObj: update_response_metadata()
-    LoggingObj->>CostCalc: _response_cost_calculator()
-    CostCalc->>CostCalc: completion_cost(tokens × price)
-    CostCalc-->>LoggingObj: response_cost
-    LoggingObj-->>Main: Set response._hidden_params["response_cost"]
-    Main-->>ProxyServer: ModelResponse (with cost in _hidden_params)
-    
-    %% Response Headers + Async Logging
-    ProxyServer->>ProxyServer: Extract cost from hidden_params
-    ProxyServer->>LoggingObj: async_success_handler()
-    LoggingObj->>Hooks: async_log_success_event()
-    Hooks->>DBWriter: update_database(response_cost)
-    DBWriter->>Redis: Queue spend increment
-    DBWriter->>Postgres: Batch write spend logs (async)
-    ProxyServer-->>Client: ModelResponse + x-litellm-response-cost header
-```
-
-### Proxy Components
-
-```mermaid
-graph TD
-    subgraph "Incoming Request"
-        Client["POST /v1/chat/completions"]
-    end
-
-    subgraph "proxy/proxy_server.py"
-        Endpoint["chat_completion()"]
-    end
-
-    subgraph "proxy/auth/"
-        Auth["user_api_key_auth()"]
-    end
-
-    subgraph "proxy/"
-        PreCall["litellm_pre_call_utils.py"]
-        RouteRequest["route_llm_request.py"]
-    end
-
-    subgraph "litellm/"
-        Router["router.py"]
-        Main["main.py"]
-    end
-
-    subgraph "Infrastructure"
-        DualCache["DualCache<br/>(in-memory + Redis)"]
-        Postgres["PostgreSQL<br/>(keys, teams, spend logs)"]
-    end
-
-    Client --> Endpoint
-    Endpoint --> Auth
-    Auth --> DualCache
-    DualCache -.->|cache miss| Postgres
-    Auth --> PreCall
-    PreCall --> RouteRequest
-    RouteRequest --> Router
-    Router --> DualCache
-    Router --> Main
-    Main --> Client
-```
-
-**Key proxy files:**
-- `proxy/proxy_server.py` - Main API endpoints
-- `proxy/auth/` - Authentication (API keys, JWT, OAuth2)
-- `proxy/hooks/` - Proxy-level callbacks
-- `router.py` - Load balancing, fallbacks
-- `router_strategy/` - Routing algorithms (`lowest_latency.py`, `simple_shuffle.py`, etc.)
-
-**LLM-specific proxy endpoints:**
-
-| Endpoint | Directory | Purpose |
-|----------|-----------|---------|
-| `/v1/messages` | `proxy/anthropic_endpoints/` | Anthropic Messages API |
-| `/vertex-ai/*` | `proxy/vertex_ai_endpoints/` | Vertex AI passthrough |
-| `/gemini/*` | `proxy/google_endpoints/` | Google AI Studio passthrough |
-| `/v1/images/*` | `proxy/image_endpoints/` | Image generation |
-| `/v1/batches` | `proxy/batches_endpoints/` | Batch processing |
-| `/v1/files` | `proxy/openai_files_endpoints/` | File uploads |
-| `/v1/fine_tuning` | `proxy/fine_tuning_endpoints/` | Fine-tuning jobs |
-| `/v1/rerank` | `proxy/rerank_endpoints/` | Reranking |
-| `/v1/responses` | `proxy/response_api_endpoints/` | OpenAI Responses API |
-| `/v1/vector_stores` | `proxy/vector_store_endpoints/` | Vector stores |
-| `/*` (passthrough) | `proxy/pass_through_endpoints/` | Direct provider passthrough |
-
-**Proxy Hooks** (`proxy/hooks/__init__.py`):
-
-| Hook | File | Purpose |
-|------|------|---------|
-| `parallel_request_limiter` | `proxy/hooks/parallel_request_limiter_v3.py` | Rate limiting per key/user |
-| `cache_control_check` | `proxy/hooks/cache_control_check.py` | Cache validation |
-| `responses_id_security` | `proxy/hooks/responses_id_security.py` | Response ID validation |
-| `litellm_skills` | `proxy/hooks/litellm_skills/main.py` | Skills injection |
-
-To add a new proxy hook, implement `CustomLogger` and register in `PROXY_HOOKS`.
-
-### Infrastructure Components
-
-The AI Gateway uses external infrastructure for persistence and caching:
-
-```mermaid
-graph LR
-    subgraph "AI Gateway (proxy/)"
-        Proxy["proxy_server.py"]
-        Auth["auth/user_api_key_auth.py"]
-        DBWriter["db/db_spend_update_writer.py<br/>DBSpendUpdateWriter"]
-        InternalCache["utils.py<br/>InternalUsageCache"]
-        CostCallback["hooks/proxy_track_cost_callback.py<br/>_ProxyDBLogger"]
-        Scheduler["APScheduler<br/>ProxyStartupEvent"]
-    end
-
-    subgraph "SDK (litellm/)"
-        Router["router.py<br/>Router.cache (DualCache)"]
-        LLMCache["caching/caching_handler.py<br/>LLMCachingHandler"]
-        CacheClass["caching/caching.py<br/>Cache"]
-    end
-
-    subgraph "Redis (caching/redis_cache.py)"
-        RateLimit["Rate Limit Counters"]
-        SpendQueue["Spend Increment Queue"]
-        KeyCache["API Key Cache"]
-        TPM_RPM["TPM/RPM Tracking"]
-        Cooldowns["Deployment Cooldowns"]
-        LLMResponseCache["LLM Response Cache"]
-    end
-
-    subgraph "PostgreSQL (proxy/schema.prisma)"
-        Keys["LiteLLM_VerificationToken"]
-        Teams["LiteLLM_TeamTable"]
-        SpendLogs["LiteLLM_SpendLogs"]
-        Users["LiteLLM_UserTable"]
-    end
-
-    Auth --> InternalCache
-    InternalCache --> KeyCache
-    InternalCache -.->|cache miss| Keys
-    InternalCache --> RateLimit
-    Router --> TPM_RPM
-    Router --> Cooldowns
-    LLMCache --> CacheClass
-    CacheClass --> LLMResponseCache
-    CostCallback --> DBWriter
-    DBWriter --> SpendQueue
-    DBWriter --> SpendLogs
-    Scheduler --> SpendLogs
-    Scheduler --> Keys
-```
-
-| Component | Purpose | Key Files/Classes |
-|-----------|---------|-------------------|
-| **Redis** | Rate limiting, API key caching, TPM/RPM tracking, cooldowns, LLM response caching, spend queuing | `caching/redis_cache.py` (`RedisCache`), `caching/dual_cache.py` (`DualCache`) |
-| **PostgreSQL** | API keys, teams, users, spend logs | `proxy/utils.py` (`PrismaClient`), `proxy/schema.prisma` |
-| **InternalUsageCache** | Proxy-level cache for rate limits + API keys (in-memory + Redis) | `proxy/utils.py` (`InternalUsageCache`) |
-| **Router.cache** | TPM/RPM tracking, deployment cooldowns, client caching (in-memory + Redis) | `router.py` (`Router.cache: DualCache`) |
-| **LLMCachingHandler** | SDK-level LLM response/embedding caching | `caching/caching_handler.py` (`LLMCachingHandler`), `caching/caching.py` (`Cache`) |
-| **DBSpendUpdateWriter** | Batches spend updates to reduce DB writes | `proxy/db/db_spend_update_writer.py` (`DBSpendUpdateWriter`) |
-| **Cost Tracking** | Calculates and logs response costs | `proxy/hooks/proxy_track_cost_callback.py` (`_ProxyDBLogger`) |
-
-**Background Jobs** (APScheduler, initialized in `proxy/proxy_server.py` → `ProxyStartupEvent.initialize_scheduled_background_jobs()`):
-
-| Job | Interval | Purpose | Key Files |
-|-----|----------|---------|-----------|
-| `update_spend` | 60s | Batch write spend logs to PostgreSQL | `proxy/db/db_spend_update_writer.py` |
-| `reset_budget` | 10-12min | Reset budgets for keys/users/teams | `proxy/common_utils/reset_budget_job.py` |
-| `add_deployment` | 10s | Sync new model deployments from DB | `proxy/proxy_server.py` (`ProxyConfig`) |
-| `cleanup_old_spend_logs` | cron/interval | Delete old spend logs | `proxy/db/db_transaction_queue/spend_log_cleanup.py` |
-| `check_batch_cost` | 30min | Calculate costs for batch jobs | `enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py` |
-| `check_responses_cost` | 30min | Calculate costs for responses API | `enterprise/litellm_enterprise/proxy/common_utils/check_responses_cost.py` |
-| `process_rotations` | 1hr | Auto-rotate API keys | `proxy/common_utils/key_rotation_manager.py` |
-| `_run_background_health_check` | continuous | Health check model deployments | `proxy/proxy_server.py` |
-| `send_weekly_spend_report` | weekly | Slack spend alerts | `proxy/utils.py` (`SlackAlerting`) |
-| `send_monthly_spend_report` | monthly | Slack spend alerts | `proxy/utils.py` (`SlackAlerting`) |
-
-**Cost Attribution Flow:**
-1. LLM response returns to `utils.py` wrapper after `litellm.acompletion()` completes
-2. `update_response_metadata()` (`litellm_core_utils/llm_response_utils/response_metadata.py`) is called
-3. `logging_obj._response_cost_calculator()` (`litellm_core_utils/litellm_logging.py`) calculates cost via `litellm.completion_cost()` (`cost_calculator.py`)
-4. Cost is stored in `response._hidden_params["response_cost"]`
-5. `proxy/common_request_processing.py` extracts cost from `hidden_params` and adds to response headers (`x-litellm-response-cost`)
-6. `logging_obj.async_success_handler()` triggers callbacks including `_ProxyDBLogger.async_log_success_event()`
-7. `DBSpendUpdateWriter.update_database()` queues spend increments to Redis
-8. Background job `update_spend` flushes queued spend to PostgreSQL every 60s
-
-Cost lookup falls back to the response model when the provider-reported name cannot be priced. Explicitly registered zero rates remain zero, and custom deployment pricing or an explicit `base_model` retain precedence
-
-### Data Access Layer (Models & Repositories)
-
-Database entities and the operations on them live in two packages at the root of `litellm/` so both the gateway (`proxy/`) and the SDK can use them without importing proxy internals:
-
-- `litellm/models/` holds the canonical Pydantic definitions for every persisted entity (`LiteLLM_VerificationToken`, `LiteLLM_TeamTable`, `LiteLLM_UserTable`, etc.). `proxy/_types.py` re-exports these for backwards compatibility, so existing imports keep working.
-- `litellm/repositories/` holds the data-access layer. `BaseRepository[T]` provides the generic CRUD (`find_by_id`, `find_many`, `create`, `update`, `delete`, `count`, `exists`); entity repositories such as `VerificationTokenRepository`, `TeamRepository`, and `UserRepository` add domain-specific queries and writes on top of it.
-
-Conventions to follow when touching this layer:
-
-| Concern | How it's handled |
-|---------|------------------|
-| JSON columns | Prisma `Json` columns are stored as JSON strings. Repositories `json.dumps()` on write and `json.loads()` on read (see `_to_model` and the `_build_*_data` helpers). |
-| Archive-then-delete | `delete_team` / `delete_token` copy the row into the `LiteLLM_Deleted*` table and delete the original inside a single `prisma_client.db.tx()` transaction. Archive payloads are built explicitly so only columns that exist on the archive table are written. |
-| Column vs. field names | Where a model field differs from its DB column (for example `org_id` maps to the `organization_id` column), the repository translates in both directions rather than relying on Pydantic to guess. |
-| Array mutations | Adds use Prisma's atomic `push` (`add_member`, `add_admin`, `add_models`) to avoid read-modify-write races. Removals fall back to read-modify-write because Prisma has no atomic array remove. |
-
-To add a new entity, define the model under `litellm/models/`, re-export it from `proxy/_types.py` if existing code imports it from there, and add a repository under `litellm/repositories/` (subclass `BaseRepository` for plain CRUD, or add bespoke methods when the entity needs encryption, archiving, or atomic array updates). Mirror the tests in `tests/unit/repositories/`.
-
----
-
-## 2. SDK Request Flow
-
-The SDK (`litellm/`) provides the core LLM calling functionality used by both direct SDK users and the AI Gateway.
-
-```mermaid
-graph TD
-    subgraph "SDK Entry Points"
-        Completion["litellm.completion()"]
-        Messages["litellm.messages()"]
-    end
-
-    subgraph "main.py"
-        Main["completion()<br/>acompletion()"]
-    end
-
-    subgraph "utils.py"
-        GetProvider["get_llm_provider()"]
-    end
-
-    subgraph "llms/custom_httpx/"
-        Handler["llm_http_handler.py<br/>BaseLLMHTTPHandler"]
-        HTTP["http_handler.py<br/>HTTPHandler / AsyncHTTPHandler"]
-    end
-
-    subgraph "llms/{provider}/chat/"
-        TransformReq["transform_request()"]
-        TransformResp["transform_response()"]
-    end
-
-    subgraph "litellm_core_utils/"
-        Streaming["streaming_handler.py"]
-    end
-
-    subgraph "integrations/ (async, off main thread)"
-        Callbacks["custom_logger.py<br/>Langfuse, Datadog, etc."]
-    end
-
-    Completion --> Main
-    Messages --> Main
-    Main --> GetProvider
-    GetProvider --> Handler
-    Handler --> TransformReq
-    TransformReq --> HTTP
-    HTTP --> Provider["LLM Provider API"]
-    Provider --> HTTP
-    HTTP --> TransformResp
-    TransformResp --> Streaming
-    Streaming --> Response["ModelResponse"]
-    Response -.->|async| Callbacks
-```
-
-**Key SDK files:**
-- `main.py` - Entry points: `completion()`, `acompletion()`, `embedding()`
-- `utils.py` - `get_llm_provider()` resolves model → provider
-- `llms/custom_httpx/llm_http_handler.py` - Central HTTP orchestrator
-- `llms/custom_httpx/http_handler.py` - Low-level HTTP client
-- `llms/{provider}/chat/transformation.py` - Provider-specific transformations
-- `litellm_core_utils/streaming_handler.py` - Streaming response handling
-- `integrations/` - Async callbacks (Langfuse, Datadog, etc.)
-
----
-
-## 3. Translation Layer
-
-When a request comes in, it goes through a **translation layer** that converts between API formats.
-Each translation is isolated in its own file, making it easy to test and modify independently.
-
-### Where to find translations
-
-| Incoming API | Provider | Translation File |
-|--------------|----------|------------------|
-| `/v1/chat/completions` | Anthropic | `llms/anthropic/chat/transformation.py` |
-| `/v1/chat/completions` | Bedrock Converse | `llms/bedrock/chat/converse_transformation.py` |
-| `/v1/chat/completions` | Bedrock Invoke | `llms/bedrock/chat/invoke_transformations/anthropic_claude_transformation.py` |
-| `/v1/chat/completions` | Gemini | `llms/gemini/chat/transformation.py` |
-| `/v1/chat/completions` | Vertex AI | `llms/vertex_ai/gemini/transformation.py` |
-| `/v1/chat/completions` | OpenAI | `llms/openai/chat/gpt_transformation.py` |
-| `/v1/messages` (passthrough) | Anthropic | `llms/anthropic/messages/native/transformation.py` |
-| `/v1/messages` (passthrough) | Bedrock | `llms/bedrock/messages/invoke_transformations/anthropic_claude_transformation.py` |
-| `/v1/messages` (passthrough) | Vertex AI | `llms/vertex_ai/vertex_ai_partner_models/anthropic/messages/transformation.py` |
-| Passthrough endpoints | All | `proxy/pass_through_endpoints/llm_provider_handlers/` |
-
-### Example: Debugging prompt caching
-
-If `/v1/messages` → Bedrock Converse prompt caching isn't working but Bedrock Invoke works:
-
-1. **Bedrock Converse translation**: `llms/bedrock/chat/converse_transformation.py`
-2. **Bedrock Invoke translation**: `llms/bedrock/chat/invoke_transformations/anthropic_claude_transformation.py`
-3. Compare how each handles `cache_control` in `transform_request()`
-
-### How translations work
-
-Each provider has a `Config` class that inherits from `BaseConfig` (`llms/base_llm/chat/transformation.py`):
-
-```python
-class ProviderConfig(BaseConfig):
-    def transform_request(self, model, messages, optional_params, litellm_params, headers):
-        # Convert OpenAI format → Provider format
-        return {"messages": transformed_messages, ...}
-    
-    def transform_response(self, model, raw_response, model_response, logging_obj, ...):
-        # Convert Provider format → OpenAI format
-        return ModelResponse(choices=[...], usage=Usage(...))
-```
-
-The `BaseLLMHTTPHandler` (`llms/custom_httpx/llm_http_handler.py`) calls these methods - you never need to modify the handler itself.
-
----
-
-## 4. Adding/Modifying Providers
-
-### To add a new provider:
-
-1. Create `llms/{provider}/chat/transformation.py`
-2. Implement `Config` class with `transform_request()` and `transform_response()`
-3. Add tests in `tests/llm_translation/test_{provider}.py`
-
-### To add a feature (e.g., prompt caching):
-
-1. Find the translation file from the table above
-2. Modify `transform_request()` to handle the new parameter
-3. Add unit tests that verify the transformation
-
-### Testing checklist
-
-When adding a feature, verify it works across all paths:
-
-| Test | File Pattern |
-|------|--------------|
-| OpenAI passthrough | `tests/llm_translation/test_openai*.py` |
-| Anthropic direct | `tests/llm_translation/test_anthropic*.py` |
-| Bedrock Invoke | `tests/llm_translation/test_bedrock*.py` |
-| Bedrock Converse | `tests/llm_translation/test_bedrock*converse*.py` |
-| Vertex AI | `tests/llm_translation/test_vertex*.py` |
-| Gemini | `tests/llm_translation/test_gemini*.py` |
-
-### Unit testing translations
-
-Translations are designed to be unit testable without making API calls:
-
-```python
-from litellm.llms.bedrock.chat.converse_transformation import BedrockConverseConfig
-
-def test_prompt_caching_transform():
-    config = BedrockConverseConfig()
-    result = config.transform_request(
-        model="anthropic.claude-3-opus",
-        messages=[{"role": "user", "content": "test", "cache_control": {"type": "ephemeral"}}],
-        optional_params={},
-        litellm_params={},
-        headers={}
-    )
-    assert "cachePoint" in str(result)  # Verify cache_control was translated
-```

docs/adrs/AGENTS.md

@@ -1,5 +0,0 @@
-# Architecture decision records for the Python SDK and proxy
-
-This folder records decisions about the Python SDK and proxy the way [`litellm-rust/docs/adrs/`](../../litellm-rust/docs/adrs/AGENTS.md) records them for the Rust core, and that file's process applies here unchanged: one short `adr_NNN_short_title.md` per decision that is hard to reverse or that a new contributor would reasonably question, with Context, Decision, Alternatives Considered, and Consequences, superseded by a new ADR instead of edited once accepted. Each folder numbers its own ADRs, so a reference to an ADR in the other folder names its path
-
-Read the ADRs here before you build a new way to move data between the endpoints, the provider transformations, and cost tracking or logging. A PR that makes a decision of that kind adds its ADR in the same PR

docs/adrs/adr_001_provider_usage_fields_ride_as_usage_extras.md

@@ -1,39 +0,0 @@
-# ADR 001: Provider usage fields ride as extras on the normalized usage object
-
-Status: Accepted
-
-## Context
-
-Providers report usage fields that no other provider has, such as xAI's `usage.server_side_tool_usage_details.web_search_calls` or Anthropic's `usage.inference_geo`, and cost tracking has to read them or that spend never reaches `LiteLLM_SpendLogs`. One provider response can be served on `/v1/chat/completions`, `/v1/responses`, and `/v1/messages`, streaming or not, so a field that only one of those paths carries is billed wrong on the others
-
-[#30817](https://github.com/BerriAI/litellm/pull/30817) fixed unbilled xAI web searches. One draft did the copy in the xAI Responses transform to keep provider code out of shared files, and that swapped `/v1/responses` usage to the chat shape, so callers of that endpoint lost the Responses schema. The merged version keeps the schema, copies unknown usage fields in the shared Responses-to-chat bridge for every provider, and gates on the reported field without naming the provider
-
-In October 2026, `Usage` and `ResponseAPIUsage` kept unknown usage keys as pydantic extras, and that bridge copied them. Paths that build usage from named fields kept only the fields they name: the Anthropic, Gemini, and Bedrock Converse transforms, the stream builder, and the bridges from chat usage to `/v1/responses` and `/v1/messages`
-
-## Decision
-
-Provider-only usage fields stay on the usage object as pydantic extras, and cost tracking reads them there, in that provider's cost calculator or in a shared gate that checks the field instead of the provider. An extra reaches callers as an added usage key. No transform renames, removes, or reshapes a usage field the endpoint's schema defines to feed cost tracking, though it may fill one LiteLLM's usage object already defines, such as `server_tool_use`
-
-A shared path that rebuilds usage, such as the stream builder or a bridge between endpoint shapes, copies the extras instead of naming provider fields. A provider transform that builds usage from named fields names the new field. Neither is bypassed with a side channel. Older code that differs, such as the Azure branches in the shared tracker and the Gemini pricing tier read from `_hidden_params`, predates this ADR
-
-## Alternatives Considered
-
-**Reshape usage in the provider transform**, as a draft of #30817 did. It changes the schema that callers of that endpoint rely on, and every provider and endpoint needs its own copy
-
-**A typed field on `ResponseAPIUsage` and `Usage` for each provider's quirk**. The types grow without bound and every bridge needs an update for each one. A field several providers report, like `server_tool_use`, does get one
-
-**A side channel such as `_hidden_params`**. Cost calculators receive `Usage`, so a side channel makes a second source of truth for the same number
-
-**Provider branches or provider field names in shared code**. They put one provider's logic in a file every provider shares, which is why #30817 replaced its xAI-only gate with one that checks the reported field
-
-## Consequences
-
-Benefits:
-
-- Billing a new provider usage field touches that provider's calculator (plus a `cost_per_token` arm when the calculator is new), its transform when that names fields, and for a built-in tool at most one gate and one `get_cost_for_web_search_request` arm
-
-Costs:
-
-- Extras are untyped, so a reader validates them before use, as `_usage_reports_server_side_web_search_calls` does
-- The stream builder and the bridges from chat usage did not copy extras when this was written, so until they do, a field billed on those paths is named in them, and tests and proof runs cover each endpoint and `"stream": true`
-- This covers usage fields LiteLLM prices, not request-side params or a provider's own charge for the request, which OpenRouter and opencode Go report and `response_cost_calculator` reads from `_hidden_params` first

litellm/deploy/docker/Dockerfile

@@ -38,11 +38,11 @@ ENV NEXT_TELEMETRY_DISABLED=1 \
 
 WORKDIR /ui
 
-COPY ui/litellm-dashboard/package.json ui/litellm-dashboard/package-lock.json ./
-COPY ui/litellm-dashboard/vendor/ ./vendor/
+COPY litellm/ui/litellm-dashboard/package.json litellm/ui/litellm-dashboard/package-lock.json ./
+COPY litellm/ui/litellm-dashboard/vendor/ ./vendor/
 RUN --mount=type=cache,target=/root/.npm npm ci --prefer-offline
 
-COPY ui/litellm-dashboard/ ./
+COPY litellm/ui/litellm-dashboard/ ./
 RUN npm run build
 
 # Builder stage
@@ -191,8 +191,8 @@ COPY --from=builder /app/backend /app/backend
 COPY --from=builder /app/migrations /app/migrations
 COPY --from=builder /opt/prisma /opt/prisma
 COPY --from=builder /var/lib/litellm /var/lib/litellm
-COPY ui/nginx.conf /etc/nginx/nginx.conf
-COPY ui/docker-entrypoint.d/40-litellm-runtime-config.sh /app/ui/docker-entrypoint.d/40-litellm-runtime-config.sh
+COPY litellm/ui/nginx.conf /etc/nginx/nginx.conf
+COPY litellm/ui/docker-entrypoint.d/40-litellm-runtime-config.sh /app/ui/docker-entrypoint.d/40-litellm-runtime-config.sh
 
 RUN find /app/.venv -depth -type d -path "*/tornado/test" -exec rm -rf {} + && \
     mkdir -p /app/.cache /var/run/litellm && \

litellm/deploy/docker/Dockerfile.dockerignore

@@ -1,4 +1,4 @@
-docs
+litellm/vscode-extension
 litellm/proxy/discovery_endpoints/skill_scanner_adapter
 .github
 tests
@@ -47,8 +47,8 @@ build/
 *.egg-info/
 .DS_Store
 **/node_modules
-ui/litellm-dashboard/.next
-ui/litellm-dashboard/out
+litellm/ui/litellm-dashboard/.next
+litellm/ui/litellm-dashboard/out
 litellm-rust/target/
 litellm/rust_bridge/_native*.so
 *.log

litellm/deploy/docker/build_admin_ui.sh

@@ -54,13 +54,13 @@ else
 fi || { echo "nvm checksum verification failed"; exit 1; }
 bash "$NVM_SCRIPT"
 source ~/.nvm/nvm.sh
-NODE_VERSION="$(cat ui/litellm-dashboard/.nvmrc)"
+NODE_VERSION="$(cat litellm/ui/litellm-dashboard/.nvmrc)"
 nvm install "v${NODE_VERSION}"
 nvm use "v${NODE_VERSION}"
 
 
-# cd in to /ui/litellm-dashboard
-cd ui/litellm-dashboard
+# cd in to /litellm/ui/litellm-dashboard
+cd litellm/ui/litellm-dashboard
 
 # ensure have access to build_ui.sh
 chmod +x ./build_ui.sh
@@ -69,4 +69,4 @@ chmod +x ./build_ui.sh
 ./build_ui.sh
 
 # return to root directory
-cd ../..
+cd ../../..

litellm/deploy/docker/docker-entrypoint.sh

@@ -102,7 +102,7 @@ os.execvp("litellm", ["litellm", *sys.argv[1:]])' "$@"
     ui)
         ui_hook="$(dirname "$0")/ui/docker-entrypoint.d/40-litellm-runtime-config.sh"
         if [ ! -f "$ui_hook" ]; then
-            ui_hook="$(dirname "$0")/../../../ui/docker-entrypoint.d/40-litellm-runtime-config.sh"
+            ui_hook="$(dirname "$0")/../../ui/docker-entrypoint.d/40-litellm-runtime-config.sh"
         fi
         sh "$ui_hook"
         exec nginx -g 'daemon off;' "$@"

litellm/deploy/helm/litellm/templates/ingress.yaml

@@ -72,7 +72,7 @@
   irrelevant to path matching). They are not under /ui, /_next, or
   /litellm-asset-prefix, so without /*.txt they fall to the backend catch-all
   → 404 → client-side navigation never settles and the login flow spins in an
-  infinite redirect loop (/ ⇄ /ui/login). ui/nginx.conf already serves *.txt
+  infinite redirect loop (/ ⇄ /ui/login). litellm/ui/nginx.conf already serves *.txt
   from the export; the rule only routes the request to it. It needs an
   ingress controller whose ImplementationSpecific path is a wildcard pattern
   (AWS ALB: `*` = 0+ chars), so it is rendered for ingress.controller=alb

litellm/integrations/email_templates/model_deprecation_email.py

@@ -14,7 +14,7 @@ from litellm.types.integrations.model_deprecation_email import (
 from litellm.types.proxy.model_deprecation import SuccessorModelSource
 
 _LOGO_BASE_URL: Final = (
-    "https://raw.githubusercontent.com/BerriAI/litellm/main/ui/litellm-dashboard/public/assets/logos"
+    "https://raw.githubusercontent.com/BerriAI/litellm/main/litellm/ui/litellm-dashboard/public/assets/logos"
 )
 _EMAIL_LOGO_URL: Final = f"{_LOGO_BASE_URL}/litellm_logo.png"
 # Reuse dashboard brand assets; PNGs also render in email clients that block SVG.

litellm/proxy/_lazy_openapi_snapshot.py

@@ -7,7 +7,7 @@ features without importing them. test-linting.yml (mirrored locally by
 `make check`) regenerates this file and fails when the committed copy differs,
 then rebuilds schema.d.ts from app.openapi() with the snapshot injected. After
 changing any lazily loaded route or this generator, rerun the module and commit
-the JSON, then run `npm run gen:api` in ui/litellm-dashboard and commit schema.d.ts.
+the JSON, then run `npm run gen:api` in litellm/ui/litellm-dashboard and commit schema.d.ts.
 """
 
 import json

litellm/proxy/management_endpoints/ui_sso.py

@@ -3176,7 +3176,7 @@ def set_session_token_cookie(response: Response, request: Request, jwt_token: st
 
     Not HttpOnly: the dashboard reads this cookie via ``document.cookie`` to
     populate its own Authorization headers (see
-    ``ui/litellm-dashboard/src/utils/cookieUtils.ts``), so marking it
+    ``litellm/ui/litellm-dashboard/src/utils/cookieUtils.ts``), so marking it
     HttpOnly would break login. Secure is still required whenever the public
     origin is HTTPS, resolved the same trust-aware way as every other
     litellm cookie."""

litellm/proxy/mcp_server/utils.py

@@ -176,7 +176,7 @@ def sanitize_mcp_alias_for_header(alias: str) -> str:
     """
     Sanitize an MCP server alias for x-mcp-{alias}-{header} HTTP headers.
 
-    Must stay in sync with ui/litellm-dashboard/src/utils/mcpHeaderUtils.ts.
+    Must stay in sync with litellm/ui/litellm-dashboard/src/utils/mcpHeaderUtils.ts.
     """
     sanitized = _MCP_ALIAS_HEADER_INVALID_RE.sub("_", alias.lower().strip())
     sanitized = re.sub(r"_+", "_", sanitized)

litellm/types/mcp.py

@@ -410,7 +410,7 @@ def credential_redirect_hook(
 
 MCP_ADMIN_CONFIG_CREDENTIAL_KEYS: Final[tuple[str, ...]] = ("upstream_resource", "upstream_token_header")
 """Non-secret credential keys returned on read so the admin form can show and clear them. Mirrors
-``ADMIN_CONFIG_CREDENTIAL_KEYS`` in ``ui/litellm-dashboard/src/components/mcp_tools/types.tsx``."""
+``ADMIN_CONFIG_CREDENTIAL_KEYS`` in ``litellm/ui/litellm-dashboard/src/components/mcp_tools/types.tsx``."""
 
 
 class MCPServerCostInfo(TypedDict, total=False):

litellm/ui/litellm-dashboard/build_release_ui.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 set -e
 
-destination_dir="../../litellm/proxy/_experimental/out"
+destination_dir="../../proxy/_experimental/out"
 
 chmod +x ./build_ui.sh
 ./build_ui.sh

litellm/ui/litellm-dashboard/build_ui.sh

@@ -45,7 +45,7 @@ if [ $? -eq 0 ]; then
   pwd
 
   # Specify the destination directory
-  destination_dir="../../litellm/proxy/_experimental/out"
+  destination_dir="../../proxy/_experimental/out"
 
   # Remove existing files in the destination directory
   rm -rf "$destination_dir"/*

litellm/ui/litellm-dashboard/build_ui_custom_path.sh

@@ -54,7 +54,7 @@ if [ $? -eq 0 ]; then
     pwd
 
     # Specify the destination directory
-    destination_dir="../../litellm/proxy/_experimental/out"
+    destination_dir="../../proxy/_experimental/out"
 
     # Remove existing files in the destination directory
     rm -rf "$destination_dir"/*