Merge remote-tracking branch 'origin/litellm_internal_staging' into shadow-eval-pre-adoption

# Conflicts:
#	ui/litellm-dashboard/tsconfig.tsbuildinfo

.github/actions/cache-prisma-binaries/action.yml

@@ -0,0 +1,40 @@
+name: "Cache Prisma binaries"
+description: >-
+  Cache the Prisma CLI and engine binaries that `prisma generate` downloads, so
+  only the first job on a given prisma-client-py version pays for the download.
+
+  prisma-client-py shells out to `npm install prisma@<version>` whenever its
+  binary cache directory has no CLI entrypoint, which pulls ~85 MB of query and
+  schema engines over the network. That normally takes a few seconds, but it is
+  unbounded: one shard of a proxy-db run took 5m18s on that single step versus
+  3.8s on its eleven siblings, which pushed the job past its timeout and got a
+  fully passing test run cancelled.
+
+  Callers must not set PRISMA_BINARY_CACHE_DIR. The prisma-client-py default
+  (~/.cache/prisma-python/binaries/<prisma-version>/<engine-version>) is already
+  keyed by both versions, so a cache entry can never be served to a run that
+  expects different binaries.
+
+runs:
+  using: composite
+  steps:
+    - name: Resolve prisma-client-py version
+      id: version
+      shell: bash
+      run: |
+        version="$(grep -A1 '^name = "prisma"$' uv.lock | sed -n 's/^version = "\(.*\)"$/\1/p' | head -1)"
+        if [ -z "${version}" ]; then
+          echo "could not resolve the prisma package version from uv.lock" >&2
+          exit 1
+        fi
+        echo "version=${version}" >> "$GITHUB_OUTPUT"
+
+    - name: Restore Prisma binaries
+      uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
+      with:
+        # ~/.cache/prisma-python holds the npm install tree prisma-client-py
+        # drives; ~/.cache/prisma is where @prisma/engines stages its downloads.
+        path: |
+          ~/.cache/prisma-python
+          ~/.cache/prisma
+        key: ${{ runner.os }}-prisma-binaries-${{ steps.version.outputs.version }}

.github/pull_request_template.md

@@ -83,7 +83,11 @@ If you're seeing a delay in your PR being merged, ping the LiteLLM Team on [Slac
 🚄 Infrastructure
 ✅ Test
 
-## Changes
+## Caveats (if any)
+
+<!-- Short bullet points, just like the TLDR: one line per bullet, roughly 10 words max
+     Call out known limitations, follow-up work, or anything a reviewer should watch out for
+     Leave this section empty if there are none -->
 
 ## QA runbook
 

.github/workflows/_test-unit-base.yml

@@ -18,10 +18,25 @@ on:
         type: number
         default: 2
       timeout-minutes:
-        description: "Job timeout in minutes"
+        description: >-
+          Timeout for the test step alone. Setup (checkout, dependency install,
+          Prisma client generation) gets its own allowance on top, so a slow
+          runner or a cold binary download can never cancel passing tests.
         required: false
         type: number
         default: 20
+      job-timeout-minutes:
+        description: >-
+          Backstop for the whole job. Keep it >= `timeout-minutes` plus 35: 30 for
+          the per-step ceilings on the setup steps below, and 5 for the runner
+          overhead the job clock charges but no step owns (job init, step
+          transitions, post-job cleanup). That headroom is what makes the test
+          budget a floor rather than a hope, since setup cannot overrun into it
+          without failing its own step first. GitHub expressions have no
+          arithmetic, so the sum is passed in rather than computed.
+        required: false
+        type: number
+        default: 55
       max-failures:
         description: "Stop after this many failures"
         required: false
@@ -44,30 +59,35 @@ jobs:
   run:
     name: Run tests
     runs-on: ubuntu-latest
-    timeout-minutes: ${{ inputs.timeout-minutes }}
+    timeout-minutes: ${{ inputs.job-timeout-minutes }}
     outputs:
       decision: ${{ steps.changes.outputs.decision }}
 
     steps:
       - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        timeout-minutes: 3
         with:
           persist-credentials: false
 
       - name: Detect backend-relevant changes
         id: changes
+        timeout-minutes: 2
         uses: ./.github/actions/detect-backend-changes
 
       - name: Set up Python
+        timeout-minutes: 3
         uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
           python-version: "3.12"
 
       - name: Set up uv
+        timeout-minutes: 3
         uses: ./.github/actions/setup-uv-with-retries
         with:
           version: "0.10.9"
 
       - name: Cache uv dependencies
+        timeout-minutes: 5
         uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: |
@@ -79,18 +99,24 @@ jobs:
 
       - name: Install dependencies
         if: steps.changes.outputs.decision != 'skip'
+        timeout-minutes: 8
         run: |
           .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml
 
+      - name: Cache Prisma binaries
+        if: steps.changes.outputs.decision != 'skip'
+        timeout-minutes: 3
+        uses: ./.github/actions/cache-prisma-binaries
+
       - name: Generate Prisma client
         if: steps.changes.outputs.decision != 'skip'
-        env:
-          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
+        timeout-minutes: 3
         run: |
           uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
 
       - name: Run tests
         if: steps.changes.outputs.decision != 'skip'
+        timeout-minutes: ${{ inputs.timeout-minutes }}
         env:
           TEST_PATH: ${{ inputs.test-path }}
           MAX_FAILURES: ${{ inputs.max-failures }}

.github/workflows/check-ui-api-types.yml

@@ -71,10 +71,12 @@ jobs:
         if: steps.changes.outputs.relevant == 'true'
         run: .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router
 
+      - name: Cache Prisma binaries
+        if: steps.changes.outputs.relevant == 'true'
+        uses: ./.github/actions/cache-prisma-binaries
+
       - name: Generate Prisma client
         if: steps.changes.outputs.relevant == 'true'
-        env:
-          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
         run: uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
 
       - name: Set up Node.js

.github/workflows/mutation-test.yml

@@ -57,9 +57,10 @@ jobs:
         run: |
           .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml
 
+      - name: Cache Prisma binaries
+        uses: ./.github/actions/cache-prisma-binaries
+
       - name: Generate Prisma client
-        env:
-          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
         run: |
           uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
 

.github/workflows/publish-basedpyright-base-counts.yml

@@ -43,12 +43,13 @@ jobs:
         with:
           version: "0.10.9"
 
+      - name: Cache Prisma binaries
+        uses: ./.github/actions/cache-prisma-binaries
+
       # The gate provisions its own measurement env (.venv-typecheck: a frozen
       # uv sync of its canonical dependency groups plus a generated Prisma
       # client), so no install step here can drift from what local runs measure.
       - name: Emit basedpyright counts for HEAD
-        env:
-          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
         run: |
           python scripts/type_check_gate.py --emit-counts-dir "$RUNNER_TEMP/basedpyright-counts"
           counts_file=$(ls "$RUNNER_TEMP"/basedpyright-counts/basedpyright-counts-*.json)

.github/workflows/test-code-quality.yml

@@ -65,6 +65,12 @@ jobs:
       - name: check_provider_folders_documented
         run: uv run --no-sync python ./tests/code_coverage_tests/check_provider_folders_documented.py
 
+      - name: check_prisma_binary_cache
+        run: uv run --no-sync python ./tests/code_coverage_tests/check_prisma_binary_cache.py
+
+      - name: check_workflow_startup_safety
+        run: uv run --no-sync python ./tests/code_coverage_tests/check_workflow_startup_safety.py
+
       - name: router_code_coverage
         run: uv run --no-sync python ./tests/code_coverage_tests/router_code_coverage.py
 

.github/workflows/test-linting.yml

@@ -71,12 +71,13 @@ jobs:
         run: |
           uv sync --frozen --group proxy-dev --group e2e-dev
 
+      - name: Cache Prisma binaries
+        uses: ./.github/actions/cache-prisma-binaries
+
       # basedpyright resolves Prisma's generated client (litellm/proxy/schema.prisma)
       # only after `prisma generate` writes prisma/client.py et al. Without this the
       # DB wrappers typed against the generated client would degrade to Unknown.
       - name: Generate Prisma client
-        env:
-          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
         run: |
           uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
 
@@ -119,7 +120,6 @@ jobs:
       - name: Check basedpyright budget (delta vs base)
         env:
           GH_TOKEN: ${{ github.token }}
-          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
         run: |
           uv run --no-sync python scripts/type_check_gate.py --base "$GATE_BASE_SHA"
 

.github/workflows/test-litellm-ui-unit.yml

@@ -42,6 +42,11 @@ jobs:
       - name: Install dependencies
         run: npm ci
 
+      - name: Run UI type tests (Vitest)
+        env:
+          CI: "true"
+        run: npm run test:types
+
       - name: Run UI unit tests (Vitest)
         env:
           CI: "true"

.github/workflows/test-terraform-provider.yml

@@ -92,9 +92,10 @@ jobs:
         run: |
           .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router
 
+      - name: Cache Prisma binaries
+        uses: ./.github/actions/cache-prisma-binaries
+
       - name: Generate Prisma client
-        env:
-          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
         run: |
           uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
 

.github/workflows/test-unit-documentation.yml

@@ -65,10 +65,12 @@ jobs:
         run: |
           .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router
 
+      - name: Cache Prisma binaries
+        if: steps.changes.outputs.decision != 'skip'
+        uses: ./.github/actions/cache-prisma-binaries
+
       - name: Generate Prisma client
         if: steps.changes.outputs.decision != 'skip'
-        env:
-          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
         run: |
           uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
 

.github/workflows/test-unit-proxy-db.yml

@@ -28,6 +28,10 @@ concurrency:
 #     Most of a shard's time is pytest plugin load + xdist worker imports +
 #     pytest-cov instrumentation, not the tests themselves. Keeping per-shard
 #     work low and matching worker count to runner cores is what controls it.
+#   * `timeout` bounds the pytest step only. Checkout, dependency install, and
+#     Prisma client generation draw on a separate allowance in the base
+#     workflow, so slow setup shows up as a slow job rather than as a
+#     cancelled shard whose tests were passing.
 #   * workers: 4 matches the 4-core ubuntu-latest runner. -n 8 on 4 cores
 #     oversubscribes 2x and workers fight for CPU during their cold-start
 #     imports (measured ~441% CPU for -n 8 locally, i.e. ~55% effective).

.github/workflows/test-unit-proxy-endpoints.yml

@@ -76,4 +76,5 @@ jobs:
       workers: 4
       reruns: 2
       timeout-minutes: 60
+      job-timeout-minutes: 95
       artifact-name: proxy-server

.github/workflows/test-unit-proxy-legacy.yml

@@ -82,10 +82,12 @@ jobs:
         run: |
           .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router
 
+      - name: Cache Prisma binaries
+        if: steps.changes.outputs.decision != 'skip'
+        uses: ./.github/actions/cache-prisma-binaries
+
       - name: Generate Prisma client
         if: steps.changes.outputs.decision != 'skip'
-        env:
-          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
         run: |
           uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
 

.github/workflows/weekly_load_anomaly.yml

@@ -51,9 +51,10 @@ jobs:
         run: |
           .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra proxy
 
+      - name: Cache Prisma binaries
+        uses: ./.github/actions/cache-prisma-binaries
+
       - name: Generate Prisma client
-        env:
-          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
         run: |
           uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
 

CLAUDE.md

@@ -1,4 +1,12 @@
-Do not write any comments (existing comments can stay) unless explicitly asked to in a user (not system) prompt
+Do not write comments unless they are any of:
+- absolutely necessary to explain some very complex business logic (in which case, keep it concise and clear)
+- used as an input for tools to read and act on. For example:
+  - entries in `.git-blame-ignore-revs` saying which commit is excluded from git blame
+  - a lint or type checker suppression like `# mutable-ok` or `# pyright: ignore[reportArgumentType]  # <reason>` when introducing a truly unavoidable violation
+- a TODO or FIXME
+  - Not great to have those, but if it's unavoidable, make sure to include a strong, concise reason for why it's there or, better yet, link to a GitHub issue for the follow-up work
+
+Explanation: The point of this rule is to keep out AI slop comments. AI writes way too many and way too verbose comments. Code comments are, in a way, a violation of DRY code. You must update logic in two locations to change the code, and "hard to change" is literally the definition of tech debt. We should instead aim to write code that is intuitive and clear, even at a glance, to the reader, being both easy to maintain and high performance
 
 Don't assume that the existing code is correct or the right way of doing things / good coding patterns. In fact, there are a lot of bad coding practices, overly complex code, code smells, etc. If something doesn't look right, speak up. Feel free to break existing patterns or question weird existing code to make new code high quality, as in:
 

basedpyright-code-budget.json

@@ -1,18 +1,18 @@
 {
   "reportAny": {
-    "limit": 27731
+    "limit": 26391
   },
   "reportArgumentType": {
-    "limit": 2626
+    "limit": 2614
   },
   "reportAssignmentType": {
-    "limit": 329
+    "limit": 327
   },
   "reportAttributeAccessIssue": {
     "limit": 514
   },
   "reportCallIssue": {
-    "limit": 116
+    "limit": 114
   },
   "reportConstantRedefinition": {
     "limit": 40
@@ -24,7 +24,7 @@
     "limit": 19
   },
   "reportExplicitAny": {
-    "limit": 8807
+    "limit": 8319
   },
   "reportFunctionMemberAccess": {
     "limit": 7
@@ -54,10 +54,10 @@
     "limit": 0
   },
   "reportMissingParameterType": {
-    "limit": 5835
+    "limit": 5825
   },
   "reportMissingTypeArgument": {
-    "limit": 15790
+    "limit": 15695
   },
   "reportMissingTypeStubs": {
     "limit": 40
@@ -90,7 +90,7 @@
     "limit": 8
   },
   "reportReturnType": {
-    "limit": 217
+    "limit": 213
   },
   "reportTypedDictNotRequiredAccess": {
     "limit": 26
@@ -99,22 +99,22 @@
     "limit": 0
   },
   "reportUnknownArgumentType": {
-    "limit": 45063
+    "limit": 44996
   },
   "reportUnknownLambdaType": {
     "limit": 113
   },
   "reportUnknownMemberType": {
-    "limit": 39773
+    "limit": 39643
   },
   "reportUnknownParameterType": {
-    "limit": 20207
+    "limit": 20132
   },
   "reportUnknownVariableType": {
-    "limit": 31281
+    "limit": 31153
   },
   "reportUnnecessaryCast": {
-    "limit": 122
+    "limit": 118
   },
   "reportUnnecessaryComparison": {
     "limit": 701
@@ -123,7 +123,7 @@
     "limit": 5
   },
   "reportUnnecessaryIsInstance": {
-    "limit": 862
+    "limit": 857
   },
   "reportUntypedBaseClass": {
     "limit": 0

enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py

@@ -3,7 +3,7 @@ Polls LiteLLM_ManagedObjectTable to check if the batch job is complete, and if t
 """
 
 from datetime import datetime, timedelta, timezone
-from typing import TYPE_CHECKING, List, Optional, Tuple
+from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple
 
 from litellm._logging import verbose_proxy_logger
 from litellm._uuid import uuid
@@ -43,11 +43,15 @@ class CheckBatchCost:
         # the guaranteed-failing primary query on every subsequent cycle.
         self._has_batch_processed_column: bool = True
 
-    async def _get_user_info(self, batch_id, user_id) -> dict:
+    async def _get_user_info(self, batch_id: str, user_id: Optional[str]) -> Dict[str, Any]:
         """
         Look up user email and key alias by user_id for enriching the S3 callback metadata.
         Returns a dict with user_api_key_user_email and user_api_key_alias (both may be None).
+        Returns an empty dict when user_id is None: batches created by a team or service
+        account key carry no user id, and find_unique(where={"user_id": None}) raises.
         """
+        if not user_id:
+            return {}
         try:
             user_row = await self.prisma_client.db.litellm_usertable.find_unique(
                 where={"user_id": user_id}
@@ -62,6 +66,66 @@ class CheckBatchCost:
             verbose_proxy_logger.error(f"CheckBatchCost: could not look up user {user_id} for batch {batch_id}: {e}")
             return {}
 
+    async def _get_key_alias(self, batch_id: str, api_key: str | None) -> str | None:
+        """Resolve the creating virtual key's alias from its hashed token."""
+        if not api_key:
+            return None
+        try:
+            key_row = await self.prisma_client.db.litellm_verificationtoken.find_unique(
+                where={"token": api_key}
+            )
+            return getattr(key_row, "key_alias", None) if key_row is not None else None
+        except Exception as e:
+            verbose_proxy_logger.error(f"CheckBatchCost: could not look up key alias for batch {batch_id}: {e}")
+            return None
+
+    async def _get_team_alias(self, team_id: str | None) -> str | None:
+        """Resolve a team's alias from its id."""
+        if not team_id:
+            return None
+        try:
+            team_row = await self.prisma_client.db.litellm_teamtable.find_unique(
+                where={"team_id": team_id}
+            )
+            return getattr(team_row, "team_alias", None) if team_row is not None else None
+        except Exception as e:
+            verbose_proxy_logger.error(f"CheckBatchCost: could not look up team alias for team {team_id}: {e}")
+            return None
+
+    async def _build_creator_attribution_metadata(
+        self, job: "LiteLLM_ManagedObjectTable", batch_id: str
+    ) -> Dict[str, Any]:
+        """
+        Rebuild the spend-tracking metadata for the key, team, and tags that created the
+        batch so the batch-cost spend log is attributed the same way a non-batch request
+        is. Rows created before api_key and request_tags were persisted carry only
+        created_by and team_id, and fall back to those. A named creating key owns
+        user_api_key_alias; when it has no alias, or the key has since been rotated or
+        deleted, the field keeps the creating user's alias that _get_user_info filled in,
+        because a resolvable name is more useful on the spend row than a null.
+        """
+        api_key = getattr(job, "api_key", None)
+        team_id = getattr(job, "team_id", None)
+        request_tags = getattr(job, "request_tags", None)
+
+        metadata: Dict[str, Any] = {
+            "user_api_key_user_id": job.created_by,
+            "user_api_key": api_key,
+            "user_api_key_team_id": team_id,
+            **(await self._get_user_info(batch_id, job.created_by)),
+        }
+
+        key_alias = await self._get_key_alias(batch_id, api_key)
+        if key_alias is not None:
+            metadata["user_api_key_alias"] = key_alias
+        team_alias = await self._get_team_alias(team_id)
+        if team_alias is not None:
+            metadata["user_api_key_team_alias"] = team_alias
+        if isinstance(request_tags, list) and request_tags:
+            metadata["tags"] = [tag for tag in request_tags if isinstance(tag, str)]
+
+        return metadata
+
     async def _cleanup_stale_managed_objects(self) -> None:
         """
         Mark managed objects older than MANAGED_OBJECT_STALENESS_CUTOFF_DAYS days
@@ -485,9 +549,6 @@ class CheckBatchCost:
             function_id=str(uuid.uuid4()),
         )
 
-        creator_user_id = job.created_by
-        user_info = await self._get_user_info(batch_id, job.created_by)
-
         logging_obj.update_environment_variables(
             litellm_params={
                 # set the user-agent header so that S3 callback consumers can easily identify CheckBatchCost callbacks
@@ -496,11 +557,7 @@ class CheckBatchCost:
                         "user-agent": CHECK_BATCH_COST_USER_AGENT,
                     }
                 },
-                "metadata": {
-                    "user_api_key_user_id": creator_user_id,
-                    "user_api_key_team_id": getattr(job, "team_id", None),
-                    **user_info,
-                },
+                "metadata": await self._build_creator_attribution_metadata(job, batch_id),
             },
             optional_params={},
         )

enterprise/litellm_enterprise/proxy/hooks/managed_files.py

@@ -163,6 +163,8 @@ class _ManagedObjectTableActions(Protocol):
         self, where: Mapping[str, str], data: Mapping[str, Mapping[str, object]]
     ) -> "PrismaManagedObjectRow": ...
 
+    async def update_many(self, where: Mapping[str, object], data: Mapping[str, object]) -> int: ...
+
 
 class _CursorPageArgs(TypedDict, total=False):
     cursor: Mapping[str, str]
@@ -263,7 +265,24 @@ class _PROXY_LiteLLMManagedFiles(CustomLogger, BaseFileEndpoints):
         model_object_id: str,
         file_purpose: Literal["batch", "fine-tune", "response"],
         user_api_key_dict: UserAPIKeyAuth,
+        request_tags: Sequence[str] | None = None,
+        persist_attribution: bool = False,
+        create_if_missing: bool = True,
     ) -> None:
+        """Persist a managed object row, caching it and upserting it in the DB.
+
+        persist_attribution is set only by the batch create, which is the one caller
+        that can speak for the creator; it gates the api_key and request_tags columns
+        that CheckBatchCost bills against, so a later poll or retrieve of the same
+        batch cannot record itself as the paying key. Like created_by and team_id,
+        both are written only in the upsert create branch, never on update.
+
+        create_if_missing is cleared by callers that observe a batch they did not
+        create, such as a poll. They still refresh status and file_object, but a
+        row absent from the table is left absent rather than created with the
+        observer as its creator, because created_by and team_id are written from
+        whoever calls the create branch.
+        """
         verbose_logger.info(f"Storing LiteLLM Managed {file_purpose} object with id={unified_object_id} in cache")
         litellm_managed_object = LiteLLM_ManagedObjectTable(
             unified_object_id=unified_object_id,
@@ -277,6 +296,29 @@ class _PROXY_LiteLLMManagedFiles(CustomLogger, BaseFileEndpoints):
             litellm_parent_otel_span=litellm_parent_otel_span,
         )
 
+        from prisma import Json
+
+        api_key = user_api_key_dict.api_key or None
+        attribution_columns = (
+            {
+                **({"api_key": api_key} if api_key is not None else {}),
+                **({"request_tags": Json(list(request_tags))} if request_tags else {}),
+            }
+            if persist_attribution
+            else {}
+        )
+        # FIX: Update status and file_object on every operation to keep state in sync
+        update_columns: Final = {
+            "file_object": file_object.model_dump_json(),
+            "status": file_object.status,
+            "updated_by": user_api_key_dict.user_id,
+        }
+        if not create_if_missing:
+            await _managed_object_table(self.prisma_client).update_many(
+                where={"unified_object_id": unified_object_id},
+                data=update_columns,
+            )
+            return
         await _managed_object_table(self.prisma_client).upsert(
             where={"unified_object_id": unified_object_id},
             data={
@@ -289,12 +331,9 @@ class _PROXY_LiteLLMManagedFiles(CustomLogger, BaseFileEndpoints):
                     "team_id": user_api_key_dict.team_id,
                     "updated_by": user_api_key_dict.user_id,
                     "status": file_object.status,
+                    **attribution_columns,
                 },
-                "update": {
-                    "file_object": file_object.model_dump_json(),
-                    "status": file_object.status,
-                    "updated_by": user_api_key_dict.user_id,
-                },  # FIX: Update status and file_object on every operation to keep state in sync
+                "update": update_columns,
             },
         )
 
@@ -1248,10 +1287,27 @@ class _PROXY_LiteLLMManagedFiles(CustomLogger, BaseFileEndpoints):
                     user_created_file_ids = await self.get_user_created_file_ids(user_api_key_dict, file_ids)
                     ## Filter the response to only include the files created by the user
                     response.data = user_created_file_ids  # type: ignore
+                    self._scope_list_page_cursors(response, user_created_file_ids)
                     return response
             return response
         return response
 
+    @staticmethod
+    def _scope_list_page_cursors(response: AsyncCursorPage, data: List[OpenAIFileObject]) -> None:
+        """Rebuild ``first_id`` / ``last_id`` from the caller-scoped page.
+
+        The upstream cursors point at rows that were just filtered out, so
+        leaving them in place discloses other callers' file ids. ``has_more``
+        is always cleared because ``after`` is never forwarded upstream, so
+        no further page is reachable through the proxy.
+        """
+        if hasattr(response, "first_id"):
+            response.first_id = data[0].id if data else None
+        if hasattr(response, "last_id"):
+            response.last_id = data[-1].id if data else None
+        if hasattr(response, "has_more"):
+            response.has_more = False
+
     async def afile_retrieve(
         self, file_id: str, litellm_parent_otel_span: Optional[Span], llm_router: Optional[Router] = None
     ) -> OpenAIFileObject:

litellm-proxy-extras/litellm_proxy_extras/migrations/20260713010000_add_ptu_columns_to_daily_team_spend/migration.sql

@@ -0,0 +1,2 @@
+-- AlterTable
+ALTER TABLE "LiteLLM_DailyTeamSpend" ADD COLUMN IF NOT EXISTS "ptu_flat_cost" DOUBLE PRECISION NOT NULL DEFAULT 0.0;

litellm-proxy-extras/litellm_proxy_extras/migrations/20260730000000_add_api_key_and_request_tags_to_managed_object_table/migration.sql

@@ -0,0 +1,5 @@
+-- Add api_key and request_tags columns to LiteLLM_ManagedObjectTable
+-- Captured at batch-create time so CheckBatchCost can attribute batch-cost spend
+-- back to the creating virtual key (and its tags) even when created_by is null.
+ALTER TABLE "LiteLLM_ManagedObjectTable" ADD COLUMN IF NOT EXISTS "api_key" TEXT;
+ALTER TABLE "LiteLLM_ManagedObjectTable" ADD COLUMN IF NOT EXISTS "request_tags" JSONB DEFAULT '[]';

litellm-proxy-extras/litellm_proxy_extras/schema.prisma

@@ -30,7 +30,7 @@ model LiteLLM_BudgetTable {
   end_users LiteLLM_EndUserTable[] // multiple end-users can have the same budget
   tags LiteLLM_TagTable[] // multiple tags can have the same budget
   team_membership LiteLLM_TeamMembership[] // budgets of Users within a Team 
-  organization_membership LiteLLM_OrganizationMembership[] // budgets of Users within a Organization 
+  organization_membership LiteLLM_OrganizationMembership[] // budgets of Users within a Organization
 }
 
 // Models on proxy
@@ -893,6 +893,7 @@ model LiteLLM_DailyTeamSpend {
   api_requests        BigInt      @default(0)
   successful_requests BigInt      @default(0)
   failed_requests     BigInt      @default(0)
+  ptu_flat_cost       Float    @default(0.0)
   created_at          DateTime @default(now())
   updated_at          DateTime @updatedAt
 
@@ -985,6 +986,8 @@ model LiteLLM_ManagedObjectTable { // for batches or finetuning jobs which use t
   created_at DateTime @default(now())
   created_by String?
   team_id String?
+  api_key String?
+  request_tags Json? @default("[]")
   updated_at DateTime @updatedAt
   updated_by String?
 

litellm/__init__.py

@@ -197,6 +197,7 @@ standard_logging_payload_excluded_fields: Optional[List[str]] = (
     None  # Fields to exclude from StandardLoggingPayload before callbacks receive it
 )
 log_raw_request_response: bool = False
+request_correlation_in_logs: bool = False
 redact_messages_in_exceptions: Optional[bool] = False
 redact_user_api_key_info: Optional[bool] = False
 # When True (default — preserves historical behavior), the Router appends

litellm/_logging.py

@@ -1,4 +1,5 @@
 import ast
+import contextvars
 import logging
 import os
 import sys
@@ -6,12 +7,44 @@ from datetime import datetime
 from logging import Formatter
 from typing import Any, Final
 
+import litellm
 from litellm.litellm_core_utils.safe_json_dumps import safe_dumps
 from litellm.litellm_core_utils.safe_json_loads import safe_json_loads
 from litellm.litellm_core_utils.secret_redaction import redact_string
 
 set_verbose = False
 
+session_id_var: Final[contextvars.ContextVar[str]] = contextvars.ContextVar("session_id", default="")
+trace_id_var: Final[contextvars.ContextVar[str]] = contextvars.ContextVar("trace_id", default="")
+
+_MAX_CORRELATION_ID_LENGTH: Final = 256
+
+
+def _sanitize_correlation_id(value: str) -> str:
+    """Strip control characters, bound length, and redact credential-shaped
+    content before a caller-controlled trace_id/session_id (e.g.
+    litellm_session_id, x-litellm-trace-id) is stamped into log lines.
+
+    Without the first two, a caller could embed \\r/\\n or terminal escape
+    sequences to forge fake log entries, or submit an oversized value repeated
+    across every log line for the request. Without the redaction, a caller
+    could smuggle a real credential (e.g. an sk-... key) through this field:
+    CorrelationContextFilter stamps trace_id/session_id onto the record after
+    SecretRedactionFilter has already run, so those two fields never otherwise
+    pass through credential redaction.
+    """
+    stripped: Final = "".join(ch for ch in value if ch.isprintable())
+    return _redact_string(stripped[:_MAX_CORRELATION_ID_LENGTH])
+
+
+def set_session_id(session_id: str) -> "contextvars.Token[str]":
+    return session_id_var.set(_sanitize_correlation_id(session_id))
+
+
+def set_trace_id(trace_id: str) -> "contextvars.Token[str]":
+    return trace_id_var.set(_sanitize_correlation_id(trace_id))
+
+
 if set_verbose is True:
     logging.warning(
         "`litellm.set_verbose` is deprecated. Please set `os.environ['LITELLM_LOG'] = 'DEBUG'` for debug logs."
@@ -77,6 +110,28 @@ class SecretRedactionFilter(logging.Filter):
 _secret_filter: Final = SecretRedactionFilter()
 
 
+class CorrelationContextFilter(logging.Filter):
+    """Stamps each log record with the current request's trace_id and session_id from contextvars.
+
+    Works in tandem with JsonFormatter: the formatter's record.__dict__ loop picks up these
+    attributes as first-class JSON fields without any formatter-level code.
+    """
+
+    def filter(self, record: logging.LogRecord) -> bool:
+        if not litellm.request_correlation_in_logs:
+            return True
+        trace_id: Final = trace_id_var.get()
+        if trace_id:
+            record.trace_id = trace_id  # rebind-ok: stamping the LogRecord is the Filter interface's contract
+        session_id: Final = session_id_var.get()
+        if session_id:
+            record.session_id = session_id  # rebind-ok: stamping the LogRecord is the Filter interface's contract
+        return True
+
+
+_correlation_filter: Final = CorrelationContextFilter()
+
+
 json_logs = bool(os.getenv("JSON_LOGS", False))
 # Create a handler for the logger (you may need to adapt this based on your needs)
 log_level: Final = os.getenv("LITELLM_LOG", "DEBUG")
@@ -84,6 +139,7 @@ numeric_level: Final[str] = getattr(logging, log_level.upper())
 handler: Final = logging.StreamHandler()
 handler.setLevel(numeric_level)
 handler.addFilter(_secret_filter)
+handler.addFilter(_correlation_filter)
 
 
 def _try_parse_json_message(message: str) -> dict[str, Any] | None:
@@ -146,6 +202,11 @@ def _get_standard_record_attrs() -> frozenset:
 
 _STANDARD_RECORD_ATTRS: Final = _get_standard_record_attrs()
 
+# CorrelationContextFilter is the only legitimate source for these two JSON fields;
+# see JsonFormatter.format() for why they're excluded from the generic message-content
+# and extra-attribute promotion paths.
+_RESERVED_CORRELATION_FIELDS: Final = frozenset(("trace_id", "session_id"))
+
 
 class JsonFormatter(Formatter):
     def __init__(self):
@@ -164,13 +225,18 @@ class JsonFormatter(Formatter):
             "timestamp": self.formatTime(record),
         }
 
-        # Parse embedded JSON or Python dict repr in message so sub-fields become first-class properties
+        # Parse embedded JSON or Python dict repr in message so sub-fields become first-class properties.
+        # trace_id/session_id are excluded here unconditionally (not just "if not already
+        # set") - CorrelationContextFilter is the only legitimate source for these two
+        # fields, and a message that merely happens to parse as JSON/dict (e.g. a proxy
+        # log line dumping raw request headers) must never be able to claim them, even on
+        # a record the filter hasn't stamped yet (no correlation context active for it).
         parsed = _try_parse_json_message(message_str)
         if parsed is None:
             parsed = _try_parse_embedded_python_dict(message_str)
         if parsed is not None:
             for key, value in parsed.items():
-                if key not in json_record:
+                if key not in json_record and key not in _RESERVED_CORRELATION_FIELDS:
                     json_record[key] = value
 
         # Include extra attributes passed via logger.debug("msg", extra={...})
@@ -178,6 +244,18 @@ class JsonFormatter(Formatter):
             if key not in _STANDARD_RECORD_ATTRS and key not in json_record:
                 json_record[key] = value
 
+        # trace_id/session_id are reserved: CorrelationContextFilter is the only
+        # legitimate source for these two fields. Without this, a message string
+        # that happens to parse as JSON/dict (e.g. a proxy log line dumping raw
+        # request headers) with a "trace_id"/"session_id" key would have already
+        # claimed the key at the parsed-message step above, and the extra-attributes
+        # loop's "key not in json_record" guard would then skip the real value -
+        # letting a caller-supplied header spoof another request's correlation ids.
+        for reserved_key in _RESERVED_CORRELATION_FIELDS:
+            value = getattr(record, reserved_key, None)
+            if value:
+                json_record[reserved_key] = value
+
         # Set component/logger only if not already supplied via extra={...}
         if "component" not in json_record:
             json_record["component"] = record.name
@@ -190,12 +268,34 @@ class JsonFormatter(Formatter):
         return safe_dumps(json_record)
 
 
+class CorrelationPlainFormatter(logging.Formatter):
+    """Appends trace_id/session_id to plain-text log lines stamped by CorrelationContextFilter.
+
+    Mirrors JsonFormatter's handling of these two fields so request_correlation_in_logs
+    behaves the same whether or not json_logs is enabled.
+    """
+
+    def format(self, record: logging.LogRecord) -> str:
+        formatted: Final = super().format(record)
+        trace_id: Final = getattr(record, "trace_id", None)
+        session_id: Final = getattr(record, "session_id", None)
+        if not trace_id and not session_id:
+            return formatted
+        parts: Final = tuple(
+            p
+            for p in (f"trace_id={trace_id}" if trace_id else None, f"session_id={session_id}" if session_id else None)
+            if p
+        )
+        return f"{formatted} [{' '.join(parts)}]"
+
+
 # Function to set up exception handlers for JSON logging
 def _setup_json_exception_handlers(formatter):
     # Create a handler with JSON formatting for exceptions
     error_handler: Final = logging.StreamHandler()
     error_handler.setFormatter(formatter)
     error_handler.addFilter(_secret_filter)
+    error_handler.addFilter(_correlation_filter)
 
     # Setup excepthook for uncaught exceptions
     def json_excepthook(exc_type, exc_value, exc_traceback):
@@ -243,7 +343,7 @@ if json_logs:
     handler.setFormatter(JsonFormatter())
     _setup_json_exception_handlers(JsonFormatter())
 else:
-    formatter: Final = logging.Formatter(
+    formatter: Final = CorrelationPlainFormatter(
         "\033[92m%(asctime)s - %(name)s:%(levelname)s\033[0m: %(filename)s:%(lineno)s - %(message)s",
         datefmt="%H:%M:%S",
     )
@@ -346,6 +446,7 @@ def _initialize_loggers_with_handler(handler: logging.Handler):
     - Prevents bubbling to parent/root (critical to prevent duplicate JSON logs)
     """
     handler.addFilter(_secret_filter)
+    handler.addFilter(_correlation_filter)
     for lg in _get_loggers_to_initialize():
         lg.handlers.clear()  # remove any existing handlers
         lg.addHandler(handler)  # add JSON formatter handler

litellm/constants.py

@@ -1493,6 +1493,8 @@ SPEND_LOG_QUEUE_POLL_INTERVAL: Final = float(os.getenv("SPEND_LOG_QUEUE_POLL_INT
 SPEND_COUNTER_RESEED_LOCKS_MAX_SIZE: Final = int(os.getenv("SPEND_COUNTER_RESEED_LOCKS_MAX_SIZE", 10000))
 DEFAULT_CRON_JOB_LOCK_TTL_SECONDS: Final = int(os.getenv("DEFAULT_CRON_JOB_LOCK_TTL_SECONDS", 60))  # 1 minute
 PROXY_BUDGET_RESCHEDULER_MIN_TIME: Final = int(os.getenv("PROXY_BUDGET_RESCHEDULER_MIN_TIME", 597))
+RESET_BUDGET_JOB_BATCH_SIZE: Final = max(1, int(os.getenv("RESET_BUDGET_JOB_BATCH_SIZE", "500")))
+RESET_BUDGET_JOB_MAX_CHUNKS_PER_RUN: Final = max(1, int(os.getenv("RESET_BUDGET_JOB_MAX_CHUNKS_PER_RUN", "100")))
 PROXY_BATCH_POLLING_INTERVAL: Final = int(os.getenv("PROXY_BATCH_POLLING_INTERVAL", 3600))
 MAX_OBJECTS_PER_POLL_CYCLE: Final = max(1, int(os.getenv("MAX_OBJECTS_PER_POLL_CYCLE", 50)))
 MANAGED_OBJECT_STALENESS_CUTOFF_DAYS: Final = max(1, int(os.getenv("MANAGED_OBJECT_STALENESS_CUTOFF_DAYS", 7)))
@@ -1719,3 +1721,18 @@ BROWSER_SECURITY_HEADERS: Final[frozenset[str]] = frozenset(
 )
 
 UNSAFE_PROXY_RESPONSE_HEADERS: Final[frozenset[str]] = HTTP_FRAMING_HEADERS | BROWSER_SECURITY_HEADERS
+
+# PTU reservation rollup writes rows to LiteLLM_DailyTeamSpend with this
+# sentinel api_key so PTU flat cost stays distinguishable from real per-request
+# spend under the table's composite unique constraint.
+PTU_SENTINEL_API_KEY: Final[str] = "__ptu_flat_cost__"
+PTU_ROLLUP_JOB_ID: Final[str] = "ptu_flat_cost_rollup_job"
+PTU_ROLLUP_LOCK_TTL_SECONDS: Final[int] = 900
+# Furthest back the catch-up pass looks for unpriced PTU days when a deployment
+# declares no ptu_effective_from, bounding the scan for an open-ended window.
+PTU_ROLLUP_MAX_BACKFILL_DAYS: Final[int] = 90
+# Slack allowed when deciding a sentinel row is stale. The row's updated_at and the
+# run's cutoff are stamped by different hosts, so clock skew between them must not let
+# one run delete a charge another just wrote. A stale row is hours old and a concurrent
+# one is seconds old, so a few minutes separates them.
+PTU_PRUNE_SKEW_GRACE_SECONDS: Final[int] = 300

litellm/evals/main.py

@@ -7,7 +7,7 @@ import asyncio
 import contextvars
 from collections.abc import Coroutine
 from functools import partial
-from typing import Any, Final
+from typing import Final
 
 import httpx
 
@@ -21,8 +21,10 @@ from litellm.types.llms.openai_evals import (
     CancelRunResponse,
     CreateEvalRequest,
     CreateRunRequest,
+    DataSourceConfig,
     DeleteEvalResponse,
     Eval,
+    GraderConfig,
     ListEvalsParams,
     ListEvalsResponse,
     ListRunsParams,
@@ -41,13 +43,13 @@ DEFAULT_OPENAI_API_BASE: Final = "https://api.openai.com"
 
 @client
 async def acreate_eval(
-    data_source_config: dict[str, Any],
-    testing_criteria: list[dict[str, Any]],
+    data_source_config: DataSourceConfig,
+    testing_criteria: list[GraderConfig],
     name: str | None = None,
-    metadata: dict[str, Any] | None = None,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
-    extra_body: dict[str, Any] | None = None,
+    metadata: dict[str, object] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
+    extra_body: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
@@ -110,17 +112,17 @@ async def acreate_eval(
 
 @client
 def create_eval(
-    data_source_config: dict[str, Any],
-    testing_criteria: list[dict[str, Any]],
+    data_source_config: DataSourceConfig,
+    testing_criteria: list[GraderConfig],
     name: str | None = None,
-    metadata: dict[str, Any] | None = None,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
-    extra_body: dict[str, Any] | None = None,
+    metadata: dict[str, object] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
+    extra_body: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
-) -> Eval | Coroutine[Any, Any, Eval]:
+) -> Eval | Coroutine[object, object, Eval]:
     """
     Create a new evaluation
 
@@ -231,8 +233,8 @@ async def alist_evals(
     before: str | None = None,
     order: str | None = None,
     order_by: str | None = None,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
@@ -300,12 +302,12 @@ def list_evals(
     before: str | None = None,
     order: str | None = None,
     order_by: str | None = None,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
-) -> ListEvalsResponse | Coroutine[Any, Any, ListEvalsResponse]:
+) -> ListEvalsResponse | Coroutine[object, object, ListEvalsResponse]:
     """
     List all evaluations
 
@@ -413,8 +415,8 @@ def list_evals(
 @client
 async def aget_eval(
     eval_id: str,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
@@ -470,12 +472,12 @@ async def aget_eval(
 @client
 def get_eval(
     eval_id: str,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
-) -> Eval | Coroutine[Any, Any, Eval]:
+) -> Eval | Coroutine[object, object, Eval]:
     """
     Get an evaluation by ID
 
@@ -564,10 +566,10 @@ def get_eval(
 async def aupdate_eval(
     eval_id: str,
     name: str | None = None,
-    metadata: dict[str, Any] | None = None,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
-    extra_body: dict[str, Any] | None = None,
+    metadata: dict[str, object] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
+    extra_body: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
@@ -630,14 +632,14 @@ async def aupdate_eval(
 def update_eval(
     eval_id: str,
     name: str | None = None,
-    metadata: dict[str, Any] | None = None,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
-    extra_body: dict[str, Any] | None = None,
+    metadata: dict[str, object] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
+    extra_body: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
-) -> Eval | Coroutine[Any, Any, Eval]:
+) -> Eval | Coroutine[object, object, Eval]:
     """
     Update an evaluation
 
@@ -783,8 +785,8 @@ def update_eval(
 @client
 async def adelete_eval(
     eval_id: str,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
@@ -840,12 +842,12 @@ async def adelete_eval(
 @client
 def delete_eval(
     eval_id: str,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
-) -> DeleteEvalResponse | Coroutine[Any, Any, DeleteEvalResponse]:
+) -> DeleteEvalResponse | Coroutine[object, object, DeleteEvalResponse]:
     """
     Delete an evaluation
 
@@ -933,8 +935,8 @@ def delete_eval(
 @client
 async def acancel_eval(
     eval_id: str,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
@@ -990,12 +992,12 @@ async def acancel_eval(
 @client
 def cancel_eval(
     eval_id: str,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
-) -> CancelEvalResponse | Coroutine[Any, Any, CancelEvalResponse]:
+) -> CancelEvalResponse | Coroutine[object, object, CancelEvalResponse]:
     """
     Cancel a running evaluation
 
@@ -1092,12 +1094,12 @@ def cancel_eval(
 @client
 async def acreate_run(
     eval_id: str,
-    data_source: dict[str, Any],
+    data_source: dict[str, object],
     name: str | None = None,
-    metadata: dict[str, Any] | None = None,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
-    extra_body: dict[str, Any] | None = None,
+    metadata: dict[str, object] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
+    extra_body: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
@@ -1161,16 +1163,16 @@ async def acreate_run(
 @client
 def create_run(
     eval_id: str,
-    data_source: dict[str, Any],
+    data_source: dict[str, object],
     name: str | None = None,
-    metadata: dict[str, Any] | None = None,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
-    extra_body: dict[str, Any] | None = None,
+    metadata: dict[str, object] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
+    extra_body: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
-) -> Run | Coroutine[Any, Any, Run]:
+) -> Run | Coroutine[object, object, Run]:
     """
     Create a new run for an evaluation
 
@@ -1280,8 +1282,8 @@ async def alist_runs(
     after: str | None = None,
     before: str | None = None,
     order: str | None = None,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
@@ -1349,12 +1351,12 @@ def list_runs(
     after: str | None = None,
     before: str | None = None,
     order: str | None = None,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
-) -> ListRunsResponse | Coroutine[Any, Any, ListRunsResponse]:
+) -> ListRunsResponse | Coroutine[object, object, ListRunsResponse]:
     """
     List all runs for an evaluation
 
@@ -1462,8 +1464,8 @@ def list_runs(
 async def aget_run(
     eval_id: str,
     run_id: str,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
@@ -1522,12 +1524,12 @@ async def aget_run(
 def get_run(
     eval_id: str,
     run_id: str,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
-) -> Run | Coroutine[Any, Any, Run]:
+) -> Run | Coroutine[object, object, Run]:
     """
     Get a specific run
 
@@ -1618,8 +1620,8 @@ def get_run(
 async def acancel_run(
     eval_id: str,
     run_id: str,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
@@ -1678,12 +1680,12 @@ async def acancel_run(
 def cancel_run(
     eval_id: str,
     run_id: str,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
-) -> CancelRunResponse | Coroutine[Any, Any, CancelRunResponse]:
+) -> CancelRunResponse | Coroutine[object, object, CancelRunResponse]:
     """
     Cancel a running run
 
@@ -1783,8 +1785,8 @@ def cancel_run(
 async def adelete_run(
     eval_id: str,
     run_id: str,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
@@ -1843,12 +1845,12 @@ async def adelete_run(
 def delete_run(
     eval_id: str,
     run_id: str,
-    extra_headers: dict[str, Any] | None = None,
-    extra_query: dict[str, Any] | None = None,
+    extra_headers: dict[str, object] | None = None,
+    extra_query: dict[str, object] | None = None,
     timeout: float | httpx.Timeout | None = None,
     custom_llm_provider: str | None = None,
     **kwargs,
-) -> RunDeleteResponse | Coroutine[Any, Any, RunDeleteResponse]:
+) -> RunDeleteResponse | Coroutine[object, object, RunDeleteResponse]:
     """
     Delete a run
 

litellm/integrations/arize/_utils.py

@@ -1,4 +1,5 @@
 import json
+from collections.abc import Mapping
 from typing import TYPE_CHECKING, Any, Final
 
 from typing_extensions import override
@@ -12,7 +13,7 @@ from litellm.litellm_core_utils.redact_messages import (
     should_redact_message_logging,
 )
 from litellm.litellm_core_utils.safe_json_dumps import safe_dumps
-from litellm.types.utils import StandardLoggingPayload
+from litellm.types.utils import CallTypes, StandardLoggingMCPToolCall, StandardLoggingPayload
 
 if TYPE_CHECKING:
     from opentelemetry.trace import Span
@@ -22,6 +23,7 @@ from litellm.integrations._types.open_inference import (
     ImageAttributes,
     MessageAttributes,
     MessageContentAttributes,
+    OpenInferenceMimeTypeValues,
     OpenInferenceSpanKindValues,
     SpanAttributes,
     ToolCallAttributes,
@@ -480,6 +482,7 @@ def set_attributes(span: "Span", kwargs, response_obj, attributes: type[BaseLLMO
         response_obj_for_attrs,
         slp,
     )
+    _safe_emit("mcp tool attrs", _maybe_set_mcp_tool_attrs, span, kwargs, slp, response_obj_for_attrs)
 
 
 def _sanitize_optional_params(optional_params: dict | None) -> dict:
@@ -538,9 +541,12 @@ def _set_request_attributes(
     if optional_params.get("user"):
         safe_set_attribute(span, "llm.user", optional_params.get("user"))
 
-    if response_obj and response_obj.get("id"):
+    if not hasattr(response_obj, "get"):
+        return
+
+    if response_obj.get("id"):
         safe_set_attribute(span, "llm.response.id", response_obj.get("id"))
-    if response_obj and response_obj.get("model"):
+    if response_obj.get("model"):
         safe_set_attribute(span, "llm.response.model", response_obj.get("model"))
 
 
@@ -588,6 +594,8 @@ def _coerce_response_obj_for_attrs(response_obj):
     - dicts and Pydantic models that already expose `.get` are returned
       unchanged (preserves all current behavior, including the Responses API
       flow which relies on Pydantic attribute access).
+    - Pydantic models without `.get` (e.g. the MCP SDK's `CallToolResult`,
+      logged for `call_mcp_tool` spans) are dumped to a dict.
     - `httpx.Response` and other text-only responses (passthrough routes)
       are JSON-decoded so the standard extraction paths can read fields like
       `id`, `model`, and `usage`. On failure the original object is returned
@@ -595,6 +603,9 @@ def _coerce_response_obj_for_attrs(response_obj):
     """
     if response_obj is None or hasattr(response_obj, "get"):
         return response_obj
+    dumped: Final = _to_plain_dict(response_obj)
+    if isinstance(dumped, dict):
+        return dumped
     text: Final = getattr(response_obj, "text", None)
     if isinstance(text, str) and text:
         try:
@@ -1058,3 +1069,65 @@ def _parse_passthrough_response(raw_response_obj, coerced_response_obj, kwargs):
         except Exception:
             return None
     return None
+
+
+def _maybe_set_mcp_tool_attrs(
+    span: "Span",
+    kwargs: Mapping[str, object],
+    standard_logging_payload: StandardLoggingPayload | None,
+    coerced_response_obj: object,
+) -> None:
+    """Render `call_mcp_tool` spans as OpenInference TOOL spans.
+
+    MCP tool calls carry neither `messages` nor `choices`, so the generic
+    extraction paths leave Input/Output blank. The tool name and arguments live
+    in `metadata.mcp_tool_call_metadata`; the result is an MCP `CallToolResult`
+    whose `content` is a list of typed parts.
+    """
+    if standard_logging_payload is None:
+        return
+    if standard_logging_payload.get("call_type") != CallTypes.call_mcp_tool.value:
+        return
+
+    metadata: Final = standard_logging_payload.get("metadata")
+    mcp_meta: Final[StandardLoggingMCPToolCall | None] = metadata.get("mcp_tool_call_metadata") if metadata else None
+    if mcp_meta is None:
+        return
+
+    tool_name: Final = mcp_meta.get("name") or mcp_meta.get("namespaced_tool_name")
+    if tool_name:
+        safe_set_attribute(span, SpanAttributes.TOOL_NAME, tool_name)
+
+    if should_redact_message_logging(kwargs):  # pyright: ignore[reportArgumentType]  # reads, never mutates
+        return
+
+    arguments: Final[object] = mcp_meta.get("arguments")
+    if arguments is not None:
+        safe_set_attribute(span, SpanAttributes.INPUT_VALUE, safe_dumps(arguments))
+        safe_set_attribute(span, SpanAttributes.INPUT_MIME_TYPE, OpenInferenceMimeTypeValues.JSON.value)
+
+    _set_mcp_tool_output(span, coerced_response_obj)
+
+
+def _has_only_text_parts(content: object) -> bool:
+    return not isinstance(content, list) or all(_coerce_text([part]) is not None for part in content)
+
+
+def _set_mcp_tool_output(span: "Span", coerced_response_obj: object) -> None:
+    if not isinstance(coerced_response_obj, Mapping):
+        return
+
+    content: Final[object] = coerced_response_obj.get("content")
+    text: Final[str | None] = _coerce_text(content)
+    if text and _has_only_text_parts(content):
+        safe_set_attribute(span, SpanAttributes.OUTPUT_VALUE, text)
+        safe_set_attribute(span, SpanAttributes.OUTPUT_MIME_TYPE, OpenInferenceMimeTypeValues.TEXT.value)
+        return
+
+    structured: Final[object] = coerced_response_obj.get("structuredContent")
+    payload: Final[object] = content if content else structured if structured is not None else content
+    if payload is None:
+        return
+
+    safe_set_attribute(span, SpanAttributes.OUTPUT_VALUE, safe_dumps(payload))
+    safe_set_attribute(span, SpanAttributes.OUTPUT_MIME_TYPE, OpenInferenceMimeTypeValues.JSON.value)

litellm/integrations/websearch_interception/handler.py

@@ -10,7 +10,7 @@ import asyncio
 import math
 import uuid
 from collections.abc import AsyncIterator, Mapping, Sequence
-from typing import TYPE_CHECKING, Any, Final, cast
+from typing import TYPE_CHECKING, Any, Final, TypedDict, cast
 
 import litellm
 from litellm._logging import verbose_logger
@@ -73,6 +73,18 @@ WEBSEARCH_EMIT_NATIVE_BLOCKS_KEY: Final = "_websearch_interception_emit_native_b
 WEBSEARCH_NATIVE_BLOCKS_METADATA_KEY: Final = "websearch_native_blocks"
 
 
+class _PlanMetadataView(TypedDict):
+    websearch_native_blocks: Sequence[Mapping[str, object]] | None
+
+
+class _AgenticLoopParamsView(TypedDict):
+    agentic_loop_params: AgenticLoopParams
+
+
+class _WebSearchSettingsView(TypedDict):
+    websearch_interception_params: WebSearchInterceptionConfig
+
+
 class WebSearchInterceptionLogger(CustomLogger):
     """
     CustomLogger that intercepts WebSearch tool calls for models that don't
@@ -394,7 +406,7 @@ class WebSearchInterceptionLogger(CustomLogger):
         return tool.get("name")
 
     @classmethod
-    def _sync_forced_tool_choice(cls, tool_choice: Any, converted_tools: list[dict[str, object]]) -> object:
+    def _sync_forced_tool_choice(cls, tool_choice: object, converted_tools: Sequence[Mapping[str, object]]) -> object:
         """Repoint a forced ``tool_choice`` at ``litellm_web_search`` when it
         names a web-search tool that was just converted away.
 
@@ -462,7 +474,7 @@ class WebSearchInterceptionLogger(CustomLogger):
             kwargs[WEBSEARCH_EMIT_NATIVE_BLOCKS_KEY] = True
 
         # Convert native web search tools to LiteLLM standard
-        converted_tools: Final = []
+        converted_tools: Final[list[dict[str, object]]] = []
         for tool in tools:
             if is_web_search_tool(tool):
                 standard_tool = get_litellm_web_search_tool()
@@ -833,7 +845,10 @@ class WebSearchInterceptionLogger(CustomLogger):
         Anthropic-native clients (Claude Desktop, the Anthropic SDK) can
         render citations / sources alongside the model's textual reply.
         """
-        native_blocks: Final = plan.metadata.get(WEBSEARCH_NATIVE_BLOCKS_METADATA_KEY)
+        metadata_view: Final[_PlanMetadataView] = {
+            "websearch_native_blocks": plan.metadata.get(WEBSEARCH_NATIVE_BLOCKS_METADATA_KEY)
+        }
+        native_blocks: Final = metadata_view["websearch_native_blocks"]
         if not native_blocks:
             return response
         return self._inject_native_blocks(response, native_blocks)
@@ -1278,8 +1293,10 @@ class WebSearchInterceptionLogger(CustomLogger):
         kwargs_for_followup: Final = self._prepare_followup_kwargs(kwargs)
 
         if logging_obj is not None:
-            agentic_params: Final[AgenticLoopParams] = logging_obj.model_call_details.get("agentic_loop_params", {})
-            full_model_name = agentic_params.get("model", model)
+            agentic_view: Final[_AgenticLoopParamsView] = {
+                "agentic_loop_params": logging_obj.model_call_details.get("agentic_loop_params", {})
+            }
+            full_model_name = agentic_view["agentic_loop_params"].get("model", model)
         verbose_logger.debug(
             "WebSearchInterception: Built anthropic request patch [call_id=%s model=%s messages=%d searches=%d]",
             _call_id,
@@ -1676,7 +1693,7 @@ class WebSearchInterceptionLogger(CustomLogger):
     @staticmethod
     def initialize_from_proxy_config(
         litellm_settings: dict[str, Any],
-        callback_specific_params: dict[str, Any],
+        callback_specific_params: Mapping[str, object],
     ) -> "WebSearchInterceptionLogger":
         """
         Static method to initialize WebSearchInterceptionLogger from proxy config.
@@ -1700,7 +1717,10 @@ class WebSearchInterceptionLogger(CustomLogger):
         # Get websearch_interception_params from litellm_settings or callback_specific_params
         websearch_params: WebSearchInterceptionConfig = {}
         if "websearch_interception_params" in litellm_settings:
-            websearch_params = litellm_settings["websearch_interception_params"]
+            settings_view: Final[_WebSearchSettingsView] = {
+                "websearch_interception_params": litellm_settings["websearch_interception_params"]
+            }
+            websearch_params = settings_view["websearch_interception_params"]
         elif "websearch_interception" in callback_specific_params and isinstance(
             callback_specific_params["websearch_interception"], dict
         ):

litellm/litellm_core_utils/cli_token_utils.py

@@ -8,6 +8,7 @@ This module has no dependencies on proxy code and can be safely imported at the
 import json
 import os
 import time
+from collections.abc import Mapping
 from pathlib import Path
 from typing import Final
 
@@ -71,7 +72,7 @@ def get_litellm_gateway_api_key(
     return token_data["key"]
 
 
-def is_cli_token_fresh(token_data: dict, buffer_hours: float = 0.1) -> bool:
+def is_cli_token_fresh(token_data: Mapping[str, object], buffer_hours: float = 0.1) -> bool:
     """Check whether a cached CLI token (as stored in token.json) is still
     within its expiration window. Used by `lite auth print-token` to fail
     fast, without a network round trip, once the cached token is past

litellm/litellm_core_utils/litellm_logging.py

@@ -10,7 +10,7 @@ import subprocess
 import sys
 import time
 import traceback
-from collections.abc import Callable
+from collections.abc import Callable, Mapping
 from datetime import datetime as dt_object
 from functools import lru_cache
 from typing import TYPE_CHECKING, Any, Final, Literal, Optional, Union, cast
@@ -25,7 +25,15 @@ from litellm import (
     log_raw_request_response,
     turn_off_message_logging,
 )
-from litellm._logging import _is_debugging_on, _redact_string, verbose_logger
+from litellm._logging import (
+    _is_debugging_on,
+    _redact_string,
+    session_id_var,
+    set_session_id,
+    set_trace_id,
+    trace_id_var,
+    verbose_logger,
+)
 from litellm._uuid import uuid
 from litellm.batches.batch_utils import _handle_completed_batch
 from litellm.caching.caching import DualCache, InMemoryCache
@@ -313,6 +321,7 @@ class Logging(LiteLLMLoggingBaseClass):
         applied_guardrails: list[str] | None = None,
         kwargs: dict | None = None,
         log_raw_request_response: bool = False,
+        supports_correlation_logging: bool = True,
     ):
         _input: Final[str | None] = messages  # save original value of messages
         if messages is not None:
@@ -338,6 +347,36 @@ class Logging(LiteLLMLoggingBaseClass):
         self.call_type = call_type
         self.litellm_call_id = litellm_call_id
         self.litellm_trace_id: str = litellm_trace_id if litellm_trace_id else str(uuid.uuid4())
+
+        # Capture the pre-call *value* (not a contextvars.Token) so restoration works
+        # even if this attempt's own logging ends up dispatched onto a different
+        # asyncio Task/context (e.g. via asyncio.create_task or the logging worker) -
+        # a Token can only be reset in the exact Context where it was created.
+        self._pre_call_trace_id: str = trace_id_var.get()
+        self._pre_call_session_id: str = session_id_var.get()
+        _sid: Final = kwargs.get("litellm_session_id") if kwargs else None
+        self.litellm_session_id: str = str(_sid) if _sid else ""
+        # supports_correlation_logging is False for calls originating from the
+        # sync client entry point (wrapper() in utils.py): a plain OS thread
+        # has no per-call context isolation the way an asyncio Task does, and
+        # a thread pool's worker threads are recycled across unrelated
+        # requests, so stamping trace_id/session_id there risks one request's
+        # ids leaking into a different, later request on the same thread. Sync
+        # support is deferred to a follow-up PR with its own safe-restore
+        # mechanism; async calls (the proxy's only call path) are unaffected.
+        if supports_correlation_logging:
+            set_trace_id(self.litellm_trace_id)
+            set_session_id(self.litellm_session_id)
+        # set_trace_id()/set_session_id() sanitize (strip control chars, bound
+        # length) before storing, so the contextvar's actual value can differ
+        # from self.litellm_trace_id/litellm_session_id. Capture what was
+        # really stored - _restore_correlation_context_if_unclaimed() must
+        # compare against this, not the raw ids, or a caller-supplied id
+        # containing control characters/oversized input would never match
+        # and cleanup would be skipped forever.
+        self._own_trace_id: str = trace_id_var.get()
+        self._own_session_id: str = session_id_var.get()
+
         self.function_id = function_id
         self.streaming_chunks: list[Any] = []  # for generating complete stream response
         self.sync_streaming_chunks: list[Any] = []  # for generating complete stream response
@@ -1992,7 +2031,67 @@ class Logging(LiteLLMLoggingBaseClass):
         if complete_streaming_response is not None:
             await self.async_success_handler(result=complete_streaming_response)
 
-    def success_handler(self, result=None, start_time=None, end_time=None, cache_hit=None, **kwargs):
+    def _restore_correlation_context(self) -> None:
+        """Restore trace_id/session_id contextvars to their pre-call value.
+
+        Without this, a nested LiteLLM call sharing the same asyncio Task as an
+        outer request (e.g. a guardrail's own LLM-as-judge call, an MCP sampling
+        call) would leave the outer request's subsequent log lines stamped with
+        the nested call's trace_id/session_id instead of its own.
+
+        Uses a plain set() of the captured pre-call value rather than
+        contextvars.Token-based reset(), since this can end up called from a
+        different asyncio Task/context than __init__ ran in (e.g. the request
+        task's own wrapper() finally block, plus async_success_handler
+        dispatched separately via asyncio.create_task/the logging worker) -
+        reset() only works in the exact Context a Token was created in and
+        raises otherwise. Deliberately NOT idempotent/guarded: each distinct
+        Task that calls this needs its own restore to actually take effect in
+        that Task's view of the contextvars, so calling it multiple times
+        (once per Task involved in this attempt) is required, not just safe.
+        """
+        set_trace_id(self._pre_call_trace_id)
+        set_session_id(self._pre_call_session_id)
+
+    def _restore_correlation_context_if_unclaimed(self) -> None:
+        """Guarded variant for __del__-triggered cleanup only.
+
+        __del__ can fire arbitrarily late (delayed by cyclic GC, possibly
+        after the consuming Task/thread has already moved on to a different,
+        still-active call). Unconditionally restoring in that case would
+        stomp the active call's trace_id/session_id with this abandoned
+        stream's stale pre-call snapshot. Only restore if the contextvars
+        still hold the ids *this* call set - i.e. nothing has claimed them
+        since - so an unrelated active call is never overwritten.
+        """
+        if trace_id_var.get() == self._own_trace_id and session_id_var.get() == self._own_session_id:
+            self._restore_correlation_context()
+
+    def success_handler(
+        self,
+        result: Any = None,  # heterogeneous response object; varies by call type (ANN401 ignored, see ruff-strict.toml)
+        start_time: datetime.datetime | None = None,
+        end_time: datetime.datetime | None = None,
+        cache_hit: bool | None = None,
+        **kwargs: Any,  # kwargs-ok: forwarded to _success_handler_body
+    ) -> None:
+        """Restores trace_id/session_id contextvars once this attempt's own success
+        logging (including any nested calls its callbacks trigger) is fully done."""
+        try:
+            return self._success_handler_body(
+                result=result, start_time=start_time, end_time=end_time, cache_hit=cache_hit, **kwargs
+            )
+        finally:
+            self._restore_correlation_context()
+
+    def _success_handler_body(
+        self,
+        result: Any = None,  # heterogeneous response object; varies by call type (ANN401 ignored, see ruff-strict.toml)
+        start_time: datetime.datetime | None = None,
+        end_time: datetime.datetime | None = None,
+        cache_hit: bool | None = None,
+        **kwargs: Any,  # kwargs-ok: forwarded from success_handler
+    ) -> None:
         verbose_logger.debug("Logging Details LiteLLM-Success Call: Cache_hit=%s", cache_hit)
         if not self.should_run_logging(event_type="sync_success"):  # prevent double logging
             return
@@ -2399,7 +2498,31 @@ class Logging(LiteLLMLoggingBaseClass):
                 e,
             )
 
-    async def async_success_handler(self, result=None, start_time=None, end_time=None, cache_hit=None, **kwargs):
+    async def async_success_handler(
+        self,
+        result: Any = None,  # heterogeneous response object; varies by call type (ANN401 ignored, see ruff-strict.toml)
+        start_time: datetime.datetime | None = None,
+        end_time: datetime.datetime | None = None,
+        cache_hit: bool | None = None,
+        **kwargs: Any,  # kwargs-ok: forwarded to _async_success_handler_body
+    ) -> None:
+        """Restores trace_id/session_id contextvars once this attempt's own success
+        logging (including any nested calls its callbacks trigger) is fully done."""
+        try:
+            return await self._async_success_handler_body(
+                result=result, start_time=start_time, end_time=end_time, cache_hit=cache_hit, **kwargs
+            )
+        finally:
+            self._restore_correlation_context()
+
+    async def _async_success_handler_body(
+        self,
+        result: Any = None,  # heterogeneous response object; varies by call type (ANN401 ignored, see ruff-strict.toml)
+        start_time: datetime.datetime | None = None,
+        end_time: datetime.datetime | None = None,
+        cache_hit: bool | None = None,
+        **kwargs: Any,  # kwargs-ok: forwarded from async_success_handler
+    ) -> None:
         """
         Implementing async callbacks, to handle asyncio event loop issues when custom integrations need to use async functions.
         """
@@ -2791,7 +2914,32 @@ class Logging(LiteLLMLoggingBaseClass):
                     kwargs=self.model_call_details,
                 )
 
-    def failure_handler(self, exception, traceback_exception, start_time=None, end_time=None):
+    def failure_handler(
+        self,
+        exception: Exception,
+        traceback_exception: str,
+        start_time: datetime.datetime | None = None,
+        end_time: datetime.datetime | None = None,
+    ) -> None:
+        """Restores trace_id/session_id contextvars once this attempt's own failure
+        logging (including any nested calls its callbacks trigger) is fully done."""
+        try:
+            return self._failure_handler_body(
+                exception=exception,
+                traceback_exception=traceback_exception,
+                start_time=start_time,
+                end_time=end_time,
+            )
+        finally:
+            self._restore_correlation_context()
+
+    def _failure_handler_body(
+        self,
+        exception: Exception,
+        traceback_exception: str,
+        start_time: datetime.datetime | None = None,
+        end_time: datetime.datetime | None = None,
+    ) -> None:
         verbose_logger.debug("Logging Details LiteLLM-Failure Call: %s", litellm.failure_callback)
         if not self.should_run_logging(event_type="sync_failure"):  # prevent double logging
             return
@@ -2960,7 +3108,32 @@ class Logging(LiteLLMLoggingBaseClass):
                 "LiteLLM.LoggingError: [Non-Blocking] Exception occurred while failure logging %s", e
             )
 
-    async def async_failure_handler(self, exception, traceback_exception, start_time=None, end_time=None):
+    async def async_failure_handler(
+        self,
+        exception: Exception,
+        traceback_exception: str,
+        start_time: datetime.datetime | None = None,
+        end_time: datetime.datetime | None = None,
+    ) -> None:
+        """Restores trace_id/session_id contextvars once this attempt's own failure
+        logging (including any nested calls its callbacks trigger) is fully done."""
+        try:
+            return await self._async_failure_handler_body(
+                exception=exception,
+                traceback_exception=traceback_exception,
+                start_time=start_time,
+                end_time=end_time,
+            )
+        finally:
+            self._restore_correlation_context()
+
+    async def _async_failure_handler_body(
+        self,
+        exception: Exception,
+        traceback_exception: str,
+        start_time: datetime.datetime | None = None,
+        end_time: datetime.datetime | None = None,
+    ) -> None:
         """
         Implementing async callbacks, to handle asyncio event loop issues when custom integrations need to use async functions.
         """
@@ -5061,33 +5234,61 @@ class StandardLoggingPayloadSetup:
             return end_time_float - start_time_float
 
     @staticmethod
-    def _get_standard_logging_payload_trace_id(
+    def get_standard_logging_payload_trace_id(
         logging_obj: Logging,
-        litellm_params: dict,
+        litellm_params: Mapping[str, Any],
     ) -> str:
         """
         Returns the `litellm_trace_id` for this request
 
         This helps link sessions when multiple requests are made in a single session
+
+        Gated behind `litellm.request_correlation_in_logs`:
+        - Off (default): legacy behavior, preserved for backward compatibility -
+          `litellm_session_id` takes priority over `litellm_trace_id` since historically
+          this field doubled as the session-grouping field.
+        - On: `litellm_trace_id` takes priority - trace_id and session_id are independent,
+          see `get_standard_logging_payload_session_id` for session tracking.
         """
         dynamic_litellm_session_id: Final = litellm_params.get("litellm_session_id")
         dynamic_litellm_trace_id: Final = litellm_params.get("litellm_trace_id")
+        metadata: Final = litellm_params.get("metadata")
+        metadata_session_id: Final = metadata.get("session_id") if metadata else None
+        metadata_trace_id: Final = metadata.get("trace_id") if metadata else None
 
-        # Note: we recommend using `litellm_session_id` for session tracking
-        # `litellm_trace_id` is an internal litellm param
+        ordered_candidates: Final[tuple[Any, Any, Any, Any]] = (
+            (dynamic_litellm_trace_id, dynamic_litellm_session_id, metadata_trace_id, metadata_session_id)
+            if litellm.request_correlation_in_logs
+            else (dynamic_litellm_session_id, dynamic_litellm_trace_id, metadata_session_id, metadata_trace_id)
+        )
+        for candidate in ordered_candidates:
+            if candidate:
+                return str(candidate)
+        return logging_obj.litellm_trace_id
+
+    @staticmethod
+    def get_standard_logging_payload_session_id(
+        logging_obj: Logging,
+        litellm_params: Mapping[str, Any],
+    ) -> str:
+        """
+        Returns the end-user/conversation `litellm_session_id` for this request, independent of trace_id.
+
+        Only populated when `litellm.request_correlation_in_logs` is enabled - off by default
+        to avoid changing existing StandardLoggingPayload shape for callers who haven't opted in.
+        Unlike `get_standard_logging_payload_trace_id`, this never falls back to a generated
+        per-call trace id: it's empty when the caller never supplied a session id.
+        """
+        if not litellm.request_correlation_in_logs:
+            return ""
+        dynamic_litellm_session_id: Final = litellm_params.get("litellm_session_id")
         if dynamic_litellm_session_id:
             return str(dynamic_litellm_session_id)
-        elif dynamic_litellm_trace_id:
-            return str(dynamic_litellm_trace_id)
-        # Fallback: use metadata.session_id or metadata.trace_id for call chaining
-        metadata: Final = litellm_params.get("metadata") or {}
-        metadata_session_id: Final = metadata.get("session_id")
-        metadata_trace_id: Final = metadata.get("trace_id")
+        metadata: Final = litellm_params.get("metadata")
+        metadata_session_id: Final = metadata.get("session_id") if metadata else None
         if metadata_session_id:
             return str(metadata_session_id)
-        if metadata_trace_id:
-            return str(metadata_trace_id)
-        return logging_obj.litellm_trace_id
+        return logging_obj.litellm_session_id
 
     @staticmethod
     def _get_user_agent_tags(proxy_server_request: dict) -> list[str] | None:
@@ -5392,7 +5593,11 @@ def get_standard_logging_object_payload(
         payload: Final[StandardLoggingPayload] = StandardLoggingPayload(
             id=str(id),
             litellm_call_id=kwargs.get("litellm_call_id") or litellm_params.get("litellm_call_id"),
-            trace_id=StandardLoggingPayloadSetup._get_standard_logging_payload_trace_id(
+            trace_id=StandardLoggingPayloadSetup.get_standard_logging_payload_trace_id(
+                logging_obj=logging_obj,
+                litellm_params=litellm_params,
+            ),
+            session_id=StandardLoggingPayloadSetup.get_standard_logging_payload_session_id(
                 logging_obj=logging_obj,
                 litellm_params=litellm_params,
             ),

litellm/litellm_core_utils/llm_cost_calc/utils.py

@@ -49,6 +49,12 @@ _SERVICE_TIER_TO_COST_KEY_SUFFIX: Final[Mapping[str, str]] = MappingProxyType(
     }
 )
 
+_INCLUSIVE_THRESHOLD_PROVIDERS: Final = frozenset({"xai"})
+
+
+def _uses_inclusive_token_thresholds(custom_llm_provider: str | None) -> bool:
+    return custom_llm_provider in _INCLUSIVE_THRESHOLD_PROVIDERS
+
 
 def _get_token_detail_value(details: object, key: str) -> int | None:
     if isinstance(details, dict):
@@ -202,7 +208,11 @@ def _parse_above_token_threshold(key: str) -> float:
 
 
 def _get_token_base_cost(
-    model_info: ModelInfo, usage: Usage, service_tier: str | None = None
+    model_info: ModelInfo,
+    usage: Usage,
+    service_tier: str | None = None,
+    *,
+    threshold_is_inclusive: bool = False,
 ) -> tuple[float, float, float, float, float]:
     """
     Return prompt cost, completion cost, and cache costs for a given model and usage.
@@ -210,6 +220,9 @@ def _get_token_base_cost(
     If input_tokens > threshold and `input_cost_per_token_above_[x]k_tokens` or `input_cost_per_token_above_[x]_tokens` is set,
     then we use the corresponding threshold cost for all token types.
 
+    `threshold_is_inclusive` switches that comparison to >=, for providers such as xAI
+    that bill the higher tier once the prompt reaches the threshold.
+
     Returns:
         Tuple[float, float, float, float] - (prompt_cost, completion_cost, cache_creation_cost, cache_read_cost)
     """
@@ -262,7 +275,7 @@ def _get_token_base_cost(
                 # Handle both formats: _above_128k_tokens and _above_128_tokens
                 threshold_str = key.split("_above_")[1].split("_tokens")[0]
                 threshold = _parse_above_token_threshold(key)
-                if usage.prompt_tokens > threshold:
+                if usage.prompt_tokens > threshold or (threshold_is_inclusive and usage.prompt_tokens == threshold):
                     # Prefer a service_tier-specific above-threshold key when available,
                     # e.g. input_cost_per_token_priority_above_200k_tokens for Gemini
                     # ON_DEMAND_PRIORITY.  Falls back to the standard key automatically
@@ -777,7 +790,12 @@ def generic_cost_per_token(
         cache_creation_cost,
         cache_creation_cost_above_1hr,
         cache_read_cost,
-    ) = _get_token_base_cost(model_info=model_info, usage=usage, service_tier=service_tier)
+    ) = _get_token_base_cost(
+        model_info=model_info,
+        usage=usage,
+        service_tier=service_tier,
+        threshold_is_inclusive=_uses_inclusive_token_thresholds(custom_llm_provider),
+    )
 
     prompt_cost = _calculate_input_cost(
         prompt_tokens_details=prompt_tokens_details,
@@ -909,7 +927,12 @@ def get_token_type_cost_breakdown(
         cache_creation_cost_rate,
         cache_creation_cost_above_1hr_rate,
         cache_read_cost_rate,
-    ) = _get_token_base_cost(model_info=model_info, usage=usage, service_tier=service_tier)
+    ) = _get_token_base_cost(
+        model_info=model_info,
+        usage=usage,
+        service_tier=service_tier,
+        threshold_is_inclusive=_uses_inclusive_token_thresholds(custom_llm_provider),
+    )
 
     reasoning_tokens = (
         _parse_completion_tokens_details(usage)["reasoning_tokens"]
@@ -996,9 +1019,13 @@ def calculate_image_response_cost_from_usage(
     input_tokens_details: Final = getattr(usage, "input_tokens_details", None)
     prompt_tokens_details: PromptTokensDetailsWrapper | None = None
     if input_tokens_details is not None:
+        # input_tokens_details may be a dict (e.g. OpenAI image edit responses)
+        # or an object; read it tolerantly like the output side below, so image
+        # input tokens are priced at input_cost_per_image_token instead of
+        # silently falling back to the text rate.
         prompt_tokens_details = PromptTokensDetailsWrapper(
-            text_tokens=getattr(input_tokens_details, "text_tokens", None),
-            image_tokens=getattr(input_tokens_details, "image_tokens", None),
+            text_tokens=_get_token_detail_value(input_tokens_details, "text_tokens"),
+            image_tokens=_get_token_detail_value(input_tokens_details, "image_tokens"),
             cached_tokens=0,
         )
 

litellm/litellm_core_utils/streaming_handler.py

@@ -213,7 +213,75 @@ class CustomStreamWrapper:
     def __aiter__(self) -> AsyncIterator["ModelResponseStream"]:
         return self
 
+    def _restore_consumer_correlation_context(self, *, guarded: bool = False) -> None:
+        """Restore trace_id/session_id in the *consuming* thread/task/context.
+
+        wrapper_async() deliberately skips restoring correlation context when
+        it returns a stream, so log lines emitted while the caller iterates it
+        still carry this call's ids (see request_correlation_in_logs).
+        wrapper() (the sync path) never stamps anything in the first place -
+        see Logging.__init__'s supports_correlation_logging - so this method
+        is an inert no-op for sync-created streams, harmless to call anyway
+        since the class is shared between __next__ and __anext__.
+        But the terminal success/failure handlers this stream dispatches to
+        finish the job run on a *different* Task/thread (asyncio.create_task,
+        threading.Thread, or the shared executor) - restoring there fixes up
+        that detached context, not the one actually running the caller's
+        `for`/`async for` loop. Call this at every point control genuinely
+        returns to that consuming context: natural exhaustion (StopIteration/
+        StopAsyncIteration), a raised failure, or explicit aclose(). Never let
+        this raise - it must not break the caller's actual stream handling.
+
+        guarded=True (only __del__ uses this) skips the restore unless the
+        contextvars still hold the ids this stream's own call set, so a
+        delayed finalizer never overwrites a different, still-active call
+        that has since taken over the same Task/thread's context.
+        """
+        try:
+            logging_obj: Final = getattr(self, "logging_obj", None)
+            if logging_obj is None:
+                return
+            method_name: Final = (
+                "_restore_correlation_context_if_unclaimed" if guarded else "_restore_correlation_context"
+            )
+            restore: Final = getattr(logging_obj, method_name, None)
+            if restore is not None:
+                restore()
+        except Exception as restore_error:  # noqa: BLE001  # best-effort cleanup; must not raise into the caller
+            verbose_logger.debug("could not restore correlation context: %s", restore_error)
+
+    def __del__(self) -> None:
+        """Best-effort correlation-context cleanup for an abandoned async stream.
+
+        Only meaningfully applies to streams created by wrapper_async(): it
+        leaves contextvars "open" across the caller's iteration, so if the
+        caller never fully consumes the stream - stops early, drops the
+        reference, cancels it - none of the exit points
+        _restore_consumer_correlation_context() is called from ever run. For a
+        sync stream (wrapper()), this is a no-op in practice: wrapper() never
+        stamps trace_id/session_id for sync calls in the first place (see
+        Logging.__init__'s supports_correlation_logging), so there is nothing
+        for this to clean up.
+
+        This is a best-effort fallback, not a guarantee: __del__ timing is
+        unpredictable (delayed by cyclic GC, not guaranteed at interpreter
+        shutdown, and may run on a different thread), so this can only reduce
+        how long the leak persists, not eliminate it. That's an acceptable
+        trade specifically because its blast radius is bounded to the one
+        asyncio Task this stream's own call ran in - each async call has its
+        own copy of the contextvars, and Tasks (unlike a thread pool's worker
+        threads) are never recycled across requests, so a delayed or missed
+        cleanup here can never misattribute a *different* request's logs.
+        guarded=True additionally ensures it never clobbers a different,
+        still-active call's context within that same Task if this fires late.
+        """
+        self._restore_consumer_correlation_context(guarded=True)
+
     async def aclose(self):
+        # Restore the consumer's outer context only after the underlying
+        # provider stream's own close (and its diagnostic logging below, if
+        # closing fails) completes - not before - so those log lines still
+        # carry this closing stream's own trace_id/session_id.
         if self.completion_stream is not None:
             stream_to_close: Final = self.completion_stream
             self.completion_stream = None
@@ -233,6 +301,7 @@ class CustomStreamWrapper:
                         "CustomStreamWrapper.aclose: error closing completion_stream: %s",
                         e,
                     )
+        self._restore_consumer_correlation_context()
 
     def check_send_stream_usage(self, stream_options: dict | None):
         return stream_options is not None and stream_options.get("include_usage", False) is True
@@ -1839,6 +1908,7 @@ class CustomStreamWrapper:
                 if self.sent_stream_usage is False and self.send_stream_usage is True:
                     self.sent_stream_usage = True
                     return response
+                self._restore_consumer_correlation_context()
                 raise  # Re-raise StopIteration
             else:
                 self.sent_last_chunk = True
@@ -1852,6 +1922,19 @@ class CustomStreamWrapper:
                     processed_chunk,
                     cache_hit,
                 )  # log response
+                # Deliberately do NOT restore context here even though
+                # completion_stream is already exhausted: this chunk is still
+                # real data belonging to this call, and the caller's own
+                # (application-level) log statements processing it run
+                # immediately after this return, in this same synchronous
+                # frame - restoring first would make those lines carry the
+                # wrong ids, which is exactly what leaving context open during
+                # iteration is meant to prevent (see
+                # _restore_consumer_correlation_context's docstring). A caller
+                # that keeps iterating gets cleaned up on its next __next__()
+                # call (immediate StopIteration, handled above); one that
+                # stops right here relies on aclose() or the best-effort
+                # __del__ guard instead.
                 return processed_chunk
         except Exception as e:
             traceback_exception: Final = traceback.format_exc()
@@ -1879,8 +1962,12 @@ class CustomStreamWrapper:
         cache_hit = False
         if self.custom_llm_provider is not None and self.custom_llm_provider == "cached_response":
             cache_hit = True
-        self._check_max_streaming_duration()
         try:
+            # Inside the try (not before it) so a raised litellm.Timeout flows
+            # through the same except Exception -> _handle_stream_fallback_error
+            # path as every other failure, restoring the consumer's correlation
+            # context - a check before the try would bypass that entirely.
+            self._check_max_streaming_duration()
             if self.completion_stream is None:
                 await self.fetch_stream()
 
@@ -2083,10 +2170,17 @@ class CustomStreamWrapper:
                     )
                 )
 
+            self._restore_consumer_correlation_context()
             raise StopAsyncIteration  # Re-raise StopIteration
         else:
             self.sent_last_chunk = True
             processed_chunk: Final = self.finish_reason_handler()
+            # see sync __next__'s sibling branch: deliberately do NOT restore
+            # here - this chunk is still this call's own data, and restoring
+            # before returning it would corrupt the caller's own log
+            # statements processing it. A caller that keeps iterating gets
+            # cleaned up on the next __anext__() call; one that stops here
+            # relies on aclose() or the best-effort __del__ guard.
             return processed_chunk
 
     def _log_stream_failure_and_raise(self, e: Exception) -> NoReturn:
@@ -2138,7 +2232,12 @@ class CustomStreamWrapper:
         """
         from litellm.exceptions import MidStreamFallbackError
 
-        # Map to OpenAI exception format
+        # Map to OpenAI exception format. Some providers' mappers (e.g.
+        # _map_anthropic_exception, _map_aleph_alpha_exception) synchronously
+        # log a debug diagnostic (the raw status code) as part of mapping -
+        # restore the consumer's outer context only after this completes, so
+        # that diagnostic log line still carries the failing stream's own
+        # trace_id/session_id instead of the consumer's (or an empty one).
         if isinstance(e, OpenAIError):
             mapped_exception: Exception = e
         else:
@@ -2152,6 +2251,7 @@ class CustomStreamWrapper:
                 )
             except Exception as mapping_error:
                 mapped_exception = mapping_error
+        self._restore_consumer_correlation_context()
 
         def _normalize_status_code(exc: Exception) -> int | None:
             """Best-effort status_code extraction."""

litellm/llms/anthropic/experimental_pass_through/adapters/handler.py

@@ -1,12 +1,13 @@
 from collections.abc import AsyncIterator, Coroutine, Iterator, Mapping
 from typing import (
     TYPE_CHECKING,
-    Any,
     Final,
     TypeAlias,
     cast,
 )
 
+from typing_extensions import TypedDict
+
 import litellm
 from litellm._logging import verbose_logger
 from litellm.litellm_core_utils.asyncify import run_async_function
@@ -39,6 +40,11 @@ _AnthropicSystem: TypeAlias = "str | list[dict[str, object]] | None"
 _ContextManagementSpec: TypeAlias = "dict[str, object] | list[dict[str, object]] | None"
 
 
+class _CompletionKwargs(TypedDict, total=False, extra_items=object):
+    model: str
+    custom_llm_provider: str
+
+
 def _messages_have_compaction_block(messages: _AnthropicMessages) -> bool:
     """Return True when any message carries a ``compaction`` content block."""
     for msg in messages:
@@ -312,7 +318,7 @@ ANTHROPIC_ADAPTER: Final = AnthropicAdapter()
 class LiteLLMMessagesToCompletionTransformationHandler:
     @staticmethod
     def _route_openai_thinking_to_responses_api_if_needed(
-        completion_kwargs: dict[str, Any],
+        completion_kwargs: _CompletionKwargs,
         *,
         thinking: Mapping[str, object] | None,
     ) -> None:
@@ -377,7 +383,7 @@ class LiteLLMMessagesToCompletionTransformationHandler:
 
     @staticmethod
     def _normalize_reasoning_effort(
-        completion_kwargs: dict[str, Any],
+        completion_kwargs: _CompletionKwargs,
     ) -> None:
         """
         Normalize reasoning_effort values based on target model capabilities.
@@ -393,7 +399,7 @@ class LiteLLMMessagesToCompletionTransformationHandler:
         if reasoning_effort is None:
             return
 
-        model: Final = cast(str, completion_kwargs.get("model", ""))
+        model: Final = completion_kwargs.get("model", "")
         custom_llm_provider: Final = completion_kwargs.get("custom_llm_provider")
 
         if isinstance(reasoning_effort, str):
@@ -417,19 +423,19 @@ class LiteLLMMessagesToCompletionTransformationHandler:
         max_tokens: int,
         messages: _AnthropicMessages,
         model: str,
-        metadata: dict | None = None,
+        metadata: dict[str, object] | None = None,
         stop_sequences: list[str] | None = None,
         stream: bool | None = False,
         system: _AnthropicSystem = None,
         temperature: float | None = None,
-        thinking: dict | None = None,
-        tool_choice: dict | None = None,
-        tools: list[dict] | None = None,
+        thinking: dict[str, object] | None = None,
+        tool_choice: dict[str, object] | None = None,
+        tools: list[dict[str, object]] | None = None,
         top_k: int | None = None,
         top_p: float | None = None,
-        output_format: dict | None = None,
+        output_format: dict[str, object] | None = None,
         extra_kwargs: Mapping[str, object] | None = None,
-    ) -> tuple[dict[str, Any], dict[str, str]]:
+    ) -> tuple[_CompletionKwargs, dict[str, str]]:
         """Prepare kwargs for litellm.completion/acompletion.
 
         Returns:
@@ -486,7 +492,7 @@ class LiteLLMMessagesToCompletionTransformationHandler:
         if openai_request is None:
             raise ValueError("Failed to translate request to OpenAI format")
 
-        completion_kwargs: Final[dict[str, Any]] = dict(openai_request)
+        completion_kwargs: Final[_CompletionKwargs] = {**openai_request}
 
         if stream:
             completion_kwargs["stream"] = stream
@@ -538,17 +544,17 @@ class LiteLLMMessagesToCompletionTransformationHandler:
         max_tokens: int,
         messages: _AnthropicMessages,
         model: str,
-        metadata: dict | None = None,
+        metadata: dict[str, object] | None = None,
         stop_sequences: list[str] | None = None,
         stream: bool | None = False,
         system: str | None = None,
         temperature: float | None = None,
-        thinking: dict | None = None,
-        tool_choice: dict | None = None,
+        thinking: dict[str, object] | None = None,
+        tool_choice: dict[str, object] | None = None,
         tools: list[dict[str, object]] | None = None,
         top_k: int | None = None,
         top_p: float | None = None,
-        output_format: dict | None = None,
+        output_format: dict[str, object] | None = None,
         **kwargs,
     ) -> AnthropicMessagesResponse | AsyncIterator[bytes] | Iterator[bytes]:
         """Handle non-Anthropic models asynchronously using the adapter"""
@@ -625,17 +631,17 @@ class LiteLLMMessagesToCompletionTransformationHandler:
         max_tokens: int,
         messages: _AnthropicMessages,
         model: str,
-        metadata: dict | None = None,
+        metadata: dict[str, object] | None = None,
         stop_sequences: list[str] | None = None,
         stream: bool | None = False,
         system: str | None = None,
         temperature: float | None = None,
-        thinking: dict | None = None,
-        tool_choice: dict | None = None,
+        thinking: dict[str, object] | None = None,
+        tool_choice: dict[str, object] | None = None,
         tools: list[dict[str, object]] | None = None,
         top_k: int | None = None,
         top_p: float | None = None,
-        output_format: dict | None = None,
+        output_format: dict[str, object] | None = None,
         _is_async: bool = False,
         **kwargs,
     ) -> (

litellm/llms/anthropic/experimental_pass_through/messages/mcp_handler.py

@@ -7,8 +7,8 @@ tool through a ``tool_use`` content block, and results are fed back as
 ``tool_result`` blocks in a user message.
 """
 
-from collections.abc import AsyncIterator, Mapping, Sequence
-from typing import Any, Final
+from collections.abc import AsyncIterator, Awaitable, Callable, Iterator, Mapping, Sequence
+from typing import Any, Final, NamedTuple
 
 from litellm._logging import verbose_logger
 from litellm.responses.mcp.request_context import MCPRequestContext
@@ -24,14 +24,18 @@ from litellm.types.llms.anthropic_messages.anthropic_response import (
 MAX_MCP_TOOL_USE_ITERATIONS: Final = 10
 
 
-def _get_response_content(response: AnthropicMessagesResponse) -> Sequence[Mapping[str, Any]]:
+class _AnthropicMessagesCall(NamedTuple):
+    fn: Callable[..., Awaitable[AnthropicMessagesResponse | Iterator[bytes] | AsyncIterator[object]]]
+
+
+def _get_response_content(response: AnthropicMessagesResponse) -> Sequence[Mapping[str, object]]:
     content: Final = response.get("content")
     if not isinstance(content, list):
         return ()
     return tuple(block for block in content if isinstance(block, dict))
 
 
-def _extract_tool_use_blocks(response: AnthropicMessagesResponse) -> Sequence[Mapping[str, Any]]:
+def _extract_tool_use_blocks(response: AnthropicMessagesResponse) -> Sequence[Mapping[str, object]]:
     """Return the ``tool_use`` content blocks the model emitted."""
     return tuple(block for block in _get_response_content(response) if block.get("type") == "tool_use")
 
@@ -41,7 +45,7 @@ def _get_stop_reason(response: AnthropicMessagesResponse) -> str | None:
     return stop_reason if isinstance(stop_reason, str) else None
 
 
-def _build_tool_result_message(tool_results: Sequence[Mapping[str, Any]]) -> AnthropicMessagesUserMessageParam:
+def _build_tool_result_message(tool_results: Sequence[Mapping[str, object]]) -> AnthropicMessagesUserMessageParam:
     """Turn executed tool results into the user message Anthropic expects."""
     return AnthropicMessagesUserMessageParam(
         role="user",
@@ -58,11 +62,11 @@ def _build_tool_result_message(tool_results: Sequence[Mapping[str, Any]]) -> Ant
 
 async def anthropic_messages_with_mcp(
     max_tokens: int,
-    messages: Sequence[Mapping[str, Any]],
+    messages: Sequence[Mapping[str, object]],
     model: str,
-    tools: Sequence[Mapping[str, Any]] | None = None,
+    tools: Sequence[Mapping[str, object]] | None = None,
     **kwargs: Any,  # kwargs-ok: forwarded verbatim to litellm.anthropic_messages, which owns the param contract
-) -> AnthropicMessagesResponse | AsyncIterator[Any]:
+) -> AnthropicMessagesResponse | Iterator[bytes] | AsyncIterator[object]:
     """
     Expand litellm_proxy MCP references for `/v1/messages` and run the tool loop.
 
@@ -81,7 +85,7 @@ async def anthropic_messages_with_mcp(
     mcp_references, other_tools = LiteLLM_Proxy_MCP_Handler._parse_mcp_tools(tools)
 
     if not mcp_references:
-        return await litellm.anthropic_messages(
+        return await _AnthropicMessagesCall(fn=litellm.anthropic_messages).fn(
             max_tokens=max_tokens,
             messages=list(messages),
             model=model,
@@ -114,7 +118,7 @@ async def anthropic_messages_with_mcp(
     )
     stream: Final = bool(kwargs.pop("stream", False))
 
-    base_call_args: Final[Mapping[str, Any]] = {
+    base_call_args: Final[Mapping[str, object]] = {
         "max_tokens": max_tokens,
         "model": model,
         "tools": all_tools or None,
@@ -123,10 +127,12 @@ async def anthropic_messages_with_mcp(
     }
 
     if not should_auto_execute:
-        return await litellm.anthropic_messages(messages=list(messages), stream=stream, **base_call_args)
+        return await _AnthropicMessagesCall(fn=litellm.anthropic_messages).fn(
+            messages=list(messages), stream=stream, **base_call_args
+        )
 
-    working_messages: Sequence[Mapping[str, Any]] = tuple(messages)
-    response: AnthropicMessagesResponse = await litellm.anthropic_messages(
+    working_messages: Sequence[Mapping[str, object]] = tuple(messages)
+    response: AnthropicMessagesResponse = await _AnthropicMessagesCall(fn=litellm.anthropic_messages).fn(
         messages=list(working_messages), stream=False, **base_call_args
     )
 
@@ -161,7 +167,9 @@ async def anthropic_messages_with_mcp(
             {"role": "assistant", "content": list(_get_response_content(response))},
             _build_tool_result_message(tool_results),
         )
-        response = await litellm.anthropic_messages(messages=list(working_messages), stream=False, **base_call_args)
+        response = await _AnthropicMessagesCall(fn=litellm.anthropic_messages).fn(
+            messages=list(working_messages), stream=False, **base_call_args
+        )
     else:
         verbose_logger.warning(
             "MCP tool loop hit its %s iteration cap for model %s; returning the last response",

litellm/llms/anthropic/experimental_pass_through/responses_adapters/handler.py

@@ -8,7 +8,12 @@ from collections.abc import AsyncIterator, Coroutine
 from typing import Any, Final
 
 import litellm
-from litellm.types.llms.anthropic import AnthropicMessagesRequest
+from litellm.types.llms.anthropic import (
+    AllAnthropicToolsValues,
+    AnthropicMessagesRequest,
+    AnthropicOutputConfig,
+    AnthropicOutputSchema,
+)
 from litellm.types.llms.anthropic_messages.anthropic_response import (
     AnthropicMessagesResponse,
 )
@@ -27,24 +32,24 @@ def _build_responses_kwargs(
     model: str,
     context_management: dict | None = None,
     metadata: dict | None = None,
-    output_config: dict | None = None,
+    output_config: AnthropicOutputConfig | None = None,
     stop_sequences: list[str] | None = None,
     stream: bool | None = False,
     system: str | None = None,
     temperature: float | None = None,
     thinking: dict | None = None,
     tool_choice: dict | None = None,
-    tools: list[dict] | None = None,
+    tools: list[AllAnthropicToolsValues | dict] | None = None,
     top_k: int | None = None,
     top_p: float | None = None,
-    output_format: dict | None = None,
+    output_format: AnthropicOutputSchema | None = None,
     extra_kwargs: dict[str, Any] | None = None,
 ) -> dict[str, Any]:
     """
     Build the kwargs dict to pass directly to litellm.responses() / litellm.aresponses().
     """
     # Build a typed AnthropicMessagesRequest for the adapter
-    request_data: Final[dict[str, Any]] = {
+    request_data: Final[AnthropicMessagesRequest] = {
         "model": model,
         "messages": messages,
         "max_tokens": max_tokens,
@@ -128,19 +133,19 @@ class LiteLLMMessagesToResponsesAPIHandler:
         model: str,
         context_management: dict | None = None,
         metadata: dict | None = None,
-        output_config: dict | None = None,
+        output_config: AnthropicOutputConfig | None = None,
         stop_sequences: list[str] | None = None,
         stream: bool | None = False,
         system: str | None = None,
         temperature: float | None = None,
         thinking: dict | None = None,
         tool_choice: dict | None = None,
-        tools: list[dict] | None = None,
+        tools: list[AllAnthropicToolsValues | dict] | None = None,
         top_k: int | None = None,
         top_p: float | None = None,
-        output_format: dict | None = None,
+        output_format: AnthropicOutputSchema | None = None,
         **kwargs,
-    ) -> AnthropicMessagesResponse | AsyncIterator:
+    ) -> AnthropicMessagesResponse | AsyncIterator[bytes]:
         responses_kwargs: Final = _build_responses_kwargs(
             max_tokens=max_tokens,
             messages=messages,
@@ -179,23 +184,23 @@ class LiteLLMMessagesToResponsesAPIHandler:
         model: str,
         context_management: dict | None = None,
         metadata: dict | None = None,
-        output_config: dict | None = None,
+        output_config: AnthropicOutputConfig | None = None,
         stop_sequences: list[str] | None = None,
         stream: bool | None = False,
         system: str | None = None,
         temperature: float | None = None,
         thinking: dict | None = None,
         tool_choice: dict | None = None,
-        tools: list[dict] | None = None,
+        tools: list[AllAnthropicToolsValues | dict] | None = None,
         top_k: int | None = None,
         top_p: float | None = None,
-        output_format: dict | None = None,
+        output_format: AnthropicOutputSchema | None = None,
         _is_async: bool = False,
         **kwargs,
     ) -> (
         AnthropicMessagesResponse
-        | AsyncIterator[Any]
-        | Coroutine[Any, Any, AnthropicMessagesResponse | AsyncIterator[Any]]
+        | AsyncIterator[bytes]
+        | Coroutine[None, None, AnthropicMessagesResponse | AsyncIterator[bytes]]
     ):
         if _is_async:
             return LiteLLMMessagesToResponsesAPIHandler.async_anthropic_messages_handler(

litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py

@@ -67,6 +67,8 @@ class AmazonAnthropicClaudeMessagesConfig(
 
     DEFAULT_BEDROCK_ANTHROPIC_API_VERSION = "bedrock-2023-05-31"
 
+    WEBSEARCH_INTERCEPTION_DOCS_URL = "https://docs.litellm.ai/docs/integrations/websearch_interception"
+
     @property
     def custom_llm_provider(self) -> str | None:
         return "bedrock"
@@ -572,6 +574,45 @@ class AmazonAnthropicClaudeMessagesConfig(
 
         return filtered_betas
 
+    @staticmethod
+    def _reject_unsupported_web_search_tools(anthropic_messages_request: dict[str, object], model: str) -> None:
+        """
+        Bedrock's Anthropic endpoints cannot execute Anthropic's server-side
+        ``web_search_*`` tool; forwarding it returns an opaque
+        "The provided request is not valid" 400 from Bedrock. Fail fast with an
+        error that names the problem and the fix instead.
+
+        When web search interception is enabled
+        (``litellm_settings.callbacks: ["websearch_interception"]``), the tool
+        is converted to a regular function tool before this transform runs, so
+        this guard never fires.
+        """
+        from litellm.integrations.websearch_interception.tools import (
+            is_anthropic_native_web_search_tool,
+        )
+
+        tools: Final = anthropic_messages_request.get("tools")
+        if not isinstance(tools, list):
+            return
+        web_search_tool: Final = next(
+            (t for t in tools if isinstance(t, dict) and is_anthropic_native_web_search_tool(t)),
+            None,
+        )
+        if web_search_tool is None:
+            return
+        raise litellm.BadRequestError(
+            message=(
+                f"Bedrock does not support Anthropic's server-side web search tool "
+                f"(tool type '{web_search_tool.get('type')}', model '{model}'). "
+                "To use web search with this model, enable LiteLLM's web search interception "
+                "so the proxy executes the search instead: "
+                f"{AmazonAnthropicClaudeMessagesConfig.WEBSEARCH_INTERCEPTION_DOCS_URL}. "
+                "Alternatively, remove the web_search tool from the request."
+            ),
+            model=model,
+            llm_provider="bedrock",
+        )
+
     def _strip_unsupported_bedrock_invoke_fields(
         self,
         anthropic_messages_request: dict,
@@ -630,6 +671,8 @@ class AmazonAnthropicClaudeMessagesConfig(
         ############## BEDROCK Invoke SPECIFIC TRANSFORMATION ###
         #########################################################
 
+        self._reject_unsupported_web_search_tools(anthropic_messages_request=anthropic_messages_request, model=model)
+
         # 1. anthropic_version is required for all claude models
         if "anthropic_version" not in anthropic_messages_request:
             anthropic_messages_request["anthropic_version"] = self.DEFAULT_BEDROCK_ANTHROPIC_API_VERSION

litellm/proxy/_experimental/mcp_server/sampling_handler.py

@@ -15,6 +15,8 @@ from collections.abc import Mapping, Sequence
 from typing import Any, Final, NamedTuple, Optional, Protocol, Union, runtime_checkable
 
 if typing.TYPE_CHECKING:
+    from collections.abc import Awaitable, Callable
+
     from fastapi import Request
     from mcp.client.session import ClientSession
     from mcp.shared.context import RequestContext
@@ -28,8 +30,9 @@ if typing.TYPE_CHECKING:
         ToolUseContent,
     )
 
+    from litellm.litellm_core_utils.streaming_handler import CustomStreamWrapper
     from litellm.proxy._types import UserAPIKeyAuth
-    from litellm.proxy.utils import ProxyLogging
+    from litellm.types.utils import ModelResponse
 
 from fastapi import HTTPException
 from pydantic import TypeAdapter
@@ -1016,7 +1019,7 @@ async def _run_budget_checks(
             general_settings=general_settings or {},
             route="/chat/completions",
             llm_router=_llm_router,
-            proxy_logging_obj=typing.cast("ProxyLogging", _proxy_logging_obj),
+            proxy_logging_obj=_proxy_logging_obj,
             valid_token=user_api_key_auth,
             request=dummy_request,
         )
@@ -1176,15 +1179,19 @@ async def _build_completion_kwargs(
     )
 
 
+class _AcompletionCall(NamedTuple):
+    fn: "Callable[..., Awaitable[ModelResponse | CustomStreamWrapper]]"
+
+
 async def _run_guardrails_and_call_llm(
-    completion_kwargs: dict[str, Any],
+    completion_kwargs: dict[str, object],
     user_api_key_auth: "UserAPIKeyAuth",
 ) -> Any:
     try:
         from litellm.proxy.proxy_server import proxy_logging_obj as _plo
 
         if _plo is not None:
-            completion_kwargs = await typing.cast("ProxyLogging", _plo).pre_call_hook(
+            completion_kwargs = await _plo.pre_call_hook(
                 user_api_key_dict=user_api_key_auth,
                 data=completion_kwargs,
                 call_type="acompletion",
@@ -1204,10 +1211,10 @@ async def _run_guardrails_and_call_llm(
         from litellm.proxy.proxy_server import llm_router
 
         if llm_router is not None:
-            return await llm_router.acompletion(**completion_kwargs)
-        return await litellm.acompletion(**completion_kwargs)
+            return await _AcompletionCall(fn=llm_router.acompletion).fn(**completion_kwargs)
+        return await _AcompletionCall(fn=litellm.acompletion).fn(**completion_kwargs)
     except ImportError:
-        return await litellm.acompletion(**completion_kwargs)
+        return await _AcompletionCall(fn=litellm.acompletion).fn(**completion_kwargs)
 
 
 async def handle_sampling_create_message(

litellm/proxy/_experimental/out/__next.!KGRhc2hib2FyZCk.__PAGE__.txt

@@ -1,9 +1,9 @@
 1:"$Sreact.fragment"
-2:I[347257,["/litellm-asset-prefix/_next/static/chunks/0vggytdohwe7o.js","/litellm-asset-prefix/_next/static/chunks/32_ulchi2_aad.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js"],"ClientPageRoot"]
-3:I[871135,["/litellm-asset-prefix/_next/static/chunks/0vggytdohwe7o.js","/litellm-asset-prefix/_next/static/chunks/32_ulchi2_aad.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js","/litellm-asset-prefix/_next/static/chunks/28md7sjkucknx.js","/litellm-asset-prefix/_next/static/chunks/2x96scis66zmk.js","/litellm-asset-prefix/_next/static/chunks/2cngn5bal3278.js","/litellm-asset-prefix/_next/static/chunks/1azbeyb626rh5.js","/litellm-asset-prefix/_next/static/chunks/3_3dj4vdy-3xy.js","/litellm-asset-prefix/_next/static/chunks/0vvnul8uez9kj.js","/litellm-asset-prefix/_next/static/chunks/0g8wwba6umbim.js","/litellm-asset-prefix/_next/static/chunks/2up3bks93iqds.js","/litellm-asset-prefix/_next/static/chunks/0g_w4tf2inv3i.js","/litellm-asset-prefix/_next/static/chunks/17-6zku8f68gf.js","/litellm-asset-prefix/_next/static/chunks/0dbvgsc7ha049.js","/litellm-asset-prefix/_next/static/chunks/1iakmimqrlpn0.js","/litellm-asset-prefix/_next/static/chunks/0fk0i3e2aixp7.js","/litellm-asset-prefix/_next/static/chunks/0f5fel02jwglw.js","/litellm-asset-prefix/_next/static/chunks/17gy9d71tfqhd.js","/litellm-asset-prefix/_next/static/chunks/1vquuz09jxl5_.js","/litellm-asset-prefix/_next/static/chunks/0kx52ovlpa34x.js","/litellm-asset-prefix/_next/static/chunks/3drq2_k-jeio2.js","/litellm-asset-prefix/_next/static/chunks/2vnpyhxoamx0f.js","/litellm-asset-prefix/_next/static/chunks/323l6h8s7ahat.js","/litellm-asset-prefix/_next/static/chunks/3ib18qm2ox61z.js","/litellm-asset-prefix/_next/static/chunks/111jj26rg98nb.js","/litellm-asset-prefix/_next/static/chunks/2hu1vyy-5pv13.js","/litellm-asset-prefix/_next/static/chunks/1cea03gg5a_c7.js","/litellm-asset-prefix/_next/static/chunks/1abwfud5uqxxq.js","/litellm-asset-prefix/_next/static/chunks/199uwr871eene.js","/litellm-asset-prefix/_next/static/chunks/1uz3jt-tj9lkf.js","/litellm-asset-prefix/_next/static/chunks/2c90xukbd3il6.js","/litellm-asset-prefix/_next/static/chunks/3bhv2o_oast51.js","/litellm-asset-prefix/_next/static/chunks/105643dvf00hu.js","/litellm-asset-prefix/_next/static/chunks/12wsfsljxg4xv.js","/litellm-asset-prefix/_next/static/chunks/09l_m9l1emin2.js","/litellm-asset-prefix/_next/static/chunks/31cwj7vkk3gfz.js","/litellm-asset-prefix/_next/static/chunks/112n0hv3cc2rg.js","/litellm-asset-prefix/_next/static/chunks/3pu9plov1btip.js","/litellm-asset-prefix/_next/static/chunks/1lndy6n7cwvrq.js","/litellm-asset-prefix/_next/static/chunks/2kt_m68ln2fyr.js","/litellm-asset-prefix/_next/static/chunks/23-g73xaw3kap.js","/litellm-asset-prefix/_next/static/chunks/08eaumdx0krrt.js"],"default"]
-6:I[897367,["/litellm-asset-prefix/_next/static/chunks/0vggytdohwe7o.js","/litellm-asset-prefix/_next/static/chunks/32_ulchi2_aad.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js"],"OutletBoundary"]
+2:I[347257,["/litellm-asset-prefix/_next/static/chunks/19frz_r2jewoi.js","/litellm-asset-prefix/_next/static/chunks/20mvgyvrlrdla.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js","/litellm-asset-prefix/_next/static/chunks/3fzya67r1y1fl.js"],"ClientPageRoot"]
+3:I[871135,["/litellm-asset-prefix/_next/static/chunks/19frz_r2jewoi.js","/litellm-asset-prefix/_next/static/chunks/20mvgyvrlrdla.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js","/litellm-asset-prefix/_next/static/chunks/3fzya67r1y1fl.js","/litellm-asset-prefix/_next/static/chunks/0catil7su1yp5.js","/litellm-asset-prefix/_next/static/chunks/2cngn5bal3278.js","/litellm-asset-prefix/_next/static/chunks/34canl9e2fj8w.js","/litellm-asset-prefix/_next/static/chunks/0vvnul8uez9kj.js","/litellm-asset-prefix/_next/static/chunks/3vu26x-a1_slz.js","/litellm-asset-prefix/_next/static/chunks/1vquuz09jxl5_.js","/litellm-asset-prefix/_next/static/chunks/3_3dj4vdy-3xy.js","/litellm-asset-prefix/_next/static/chunks/0ex44ljfg9dp9.js","/litellm-asset-prefix/_next/static/chunks/0xcneptpo0s76.js","/litellm-asset-prefix/_next/static/chunks/08uoywqkfbbbt.js","/litellm-asset-prefix/_next/static/chunks/0g_w4tf2inv3i.js","/litellm-asset-prefix/_next/static/chunks/1iakmimqrlpn0.js","/litellm-asset-prefix/_next/static/chunks/17-6zku8f68gf.js","/litellm-asset-prefix/_next/static/chunks/0f5fel02jwglw.js","/litellm-asset-prefix/_next/static/chunks/0fk0i3e2aixp7.js","/litellm-asset-prefix/_next/static/chunks/3ytz29phknzsy.js","/litellm-asset-prefix/_next/static/chunks/0dbvgsc7ha049.js","/litellm-asset-prefix/_next/static/chunks/0aoel7yrv88fp.js","/litellm-asset-prefix/_next/static/chunks/2v54hze4wuham.js","/litellm-asset-prefix/_next/static/chunks/1axupaiywv5s2.js","/litellm-asset-prefix/_next/static/chunks/0zy8o1br4cxj_.js","/litellm-asset-prefix/_next/static/chunks/1uz3jt-tj9lkf.js","/litellm-asset-prefix/_next/static/chunks/2bwy4wke9jrlh.js","/litellm-asset-prefix/_next/static/chunks/2cz4e0-p1l3hf.js","/litellm-asset-prefix/_next/static/chunks/2tkpj7d49kuht.js","/litellm-asset-prefix/_next/static/chunks/323l6h8s7ahat.js","/litellm-asset-prefix/_next/static/chunks/1cea03gg5a_c7.js","/litellm-asset-prefix/_next/static/chunks/2hu1vyy-5pv13.js","/litellm-asset-prefix/_next/static/chunks/199uwr871eene.js","/litellm-asset-prefix/_next/static/chunks/105643dvf00hu.js","/litellm-asset-prefix/_next/static/chunks/29l3pao1xfkc3.js","/litellm-asset-prefix/_next/static/chunks/111jj26rg98nb.js","/litellm-asset-prefix/_next/static/chunks/12wsfsljxg4xv.js","/litellm-asset-prefix/_next/static/chunks/112n0hv3cc2rg.js","/litellm-asset-prefix/_next/static/chunks/31azy9hywrzm7.js","/litellm-asset-prefix/_next/static/chunks/3pu9plov1btip.js","/litellm-asset-prefix/_next/static/chunks/3mz07lvvrbciz.js","/litellm-asset-prefix/_next/static/chunks/1lndy6n7cwvrq.js","/litellm-asset-prefix/_next/static/chunks/09l_m9l1emin2.js","/litellm-asset-prefix/_next/static/chunks/2c90xukbd3il6.js","/litellm-asset-prefix/_next/static/chunks/0ikhgrs0xvkyu.js","/litellm-asset-prefix/_next/static/chunks/23-g73xaw3kap.js"],"default"]
+6:I[897367,["/litellm-asset-prefix/_next/static/chunks/19frz_r2jewoi.js","/litellm-asset-prefix/_next/static/chunks/20mvgyvrlrdla.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js","/litellm-asset-prefix/_next/static/chunks/3fzya67r1y1fl.js"],"OutletBoundary"]
 7:"$Sreact.suspense"
-0:{"rsc":["$","$1","c",{"children":[["$","$L2",null,{"Component":"$3","serverProvidedParams":{"searchParams":{},"params":{},"promises":["$@4","$@5"]}}],[["$","script","script-0",{"src":"/litellm-asset-prefix/_next/static/chunks/0kx52ovlpa34x.js","async":true}],["$","script","script-1",{"src":"/litellm-asset-prefix/_next/static/chunks/3drq2_k-jeio2.js","async":true}],["$","script","script-2",{"src":"/litellm-asset-prefix/_next/static/chunks/2vnpyhxoamx0f.js","async":true}],["$","script","script-3",{"src":"/litellm-asset-prefix/_next/static/chunks/323l6h8s7ahat.js","async":true}],["$","script","script-4",{"src":"/litellm-asset-prefix/_next/static/chunks/3ib18qm2ox61z.js","async":true}],["$","script","script-5",{"src":"/litellm-asset-prefix/_next/static/chunks/111jj26rg98nb.js","async":true}],["$","script","script-6",{"src":"/litellm-asset-prefix/_next/static/chunks/2hu1vyy-5pv13.js","async":true}],["$","script","script-7",{"src":"/litellm-asset-prefix/_next/static/chunks/1cea03gg5a_c7.js","async":true}],["$","script","script-8",{"src":"/litellm-asset-prefix/_next/static/chunks/1abwfud5uqxxq.js","async":true}],["$","script","script-9",{"src":"/litellm-asset-prefix/_next/static/chunks/199uwr871eene.js","async":true}],["$","script","script-10",{"src":"/litellm-asset-prefix/_next/static/chunks/1uz3jt-tj9lkf.js","async":true}],["$","script","script-11",{"src":"/litellm-asset-prefix/_next/static/chunks/2c90xukbd3il6.js","async":true}],["$","script","script-12",{"src":"/litellm-asset-prefix/_next/static/chunks/3bhv2o_oast51.js","async":true}],["$","script","script-13",{"src":"/litellm-asset-prefix/_next/static/chunks/105643dvf00hu.js","async":true}],["$","script","script-14",{"src":"/litellm-asset-prefix/_next/static/chunks/12wsfsljxg4xv.js","async":true}],["$","script","script-15",{"src":"/litellm-asset-prefix/_next/static/chunks/09l_m9l1emin2.js","async":true}],["$","script","script-16",{"src":"/litellm-asset-prefix/_next/static/chunks/31cwj7vkk3gfz.js","async":true}],["$","script","script-17",{"src":"/litellm-asset-prefix/_next/static/chunks/112n0hv3cc2rg.js","async":true}],["$","script","script-18",{"src":"/litellm-asset-prefix/_next/static/chunks/3pu9plov1btip.js","async":true}],["$","script","script-19",{"src":"/litellm-asset-prefix/_next/static/chunks/1lndy6n7cwvrq.js","async":true}],["$","script","script-20",{"src":"/litellm-asset-prefix/_next/static/chunks/2kt_m68ln2fyr.js","async":true}],["$","script","script-21",{"src":"/litellm-asset-prefix/_next/static/chunks/23-g73xaw3kap.js","async":true}],["$","script","script-22",{"src":"/litellm-asset-prefix/_next/static/chunks/08eaumdx0krrt.js","async":true}]],["$","$L6",null,{"children":["$","$7",null,{"name":"Next.MetadataOutlet","children":"$@8"}]}]]}],"isPartial":false,"staleTime":300,"varyParams":null,"buildId":"VCvPhLLOUp92Yx-E-CVlV"}
+0:{"rsc":["$","$1","c",{"children":[["$","$L2",null,{"Component":"$3","serverProvidedParams":{"searchParams":{},"params":{},"promises":["$@4","$@5"]}}],[["$","script","script-0",{"src":"/litellm-asset-prefix/_next/static/chunks/2v54hze4wuham.js","async":true}],["$","script","script-1",{"src":"/litellm-asset-prefix/_next/static/chunks/1axupaiywv5s2.js","async":true}],["$","script","script-2",{"src":"/litellm-asset-prefix/_next/static/chunks/0zy8o1br4cxj_.js","async":true}],["$","script","script-3",{"src":"/litellm-asset-prefix/_next/static/chunks/1uz3jt-tj9lkf.js","async":true}],["$","script","script-4",{"src":"/litellm-asset-prefix/_next/static/chunks/2bwy4wke9jrlh.js","async":true}],["$","script","script-5",{"src":"/litellm-asset-prefix/_next/static/chunks/2cz4e0-p1l3hf.js","async":true}],["$","script","script-6",{"src":"/litellm-asset-prefix/_next/static/chunks/2tkpj7d49kuht.js","async":true}],["$","script","script-7",{"src":"/litellm-asset-prefix/_next/static/chunks/323l6h8s7ahat.js","async":true}],["$","script","script-8",{"src":"/litellm-asset-prefix/_next/static/chunks/1cea03gg5a_c7.js","async":true}],["$","script","script-9",{"src":"/litellm-asset-prefix/_next/static/chunks/2hu1vyy-5pv13.js","async":true}],["$","script","script-10",{"src":"/litellm-asset-prefix/_next/static/chunks/199uwr871eene.js","async":true}],["$","script","script-11",{"src":"/litellm-asset-prefix/_next/static/chunks/105643dvf00hu.js","async":true}],["$","script","script-12",{"src":"/litellm-asset-prefix/_next/static/chunks/29l3pao1xfkc3.js","async":true}],["$","script","script-13",{"src":"/litellm-asset-prefix/_next/static/chunks/111jj26rg98nb.js","async":true}],["$","script","script-14",{"src":"/litellm-asset-prefix/_next/static/chunks/12wsfsljxg4xv.js","async":true}],["$","script","script-15",{"src":"/litellm-asset-prefix/_next/static/chunks/112n0hv3cc2rg.js","async":true}],["$","script","script-16",{"src":"/litellm-asset-prefix/_next/static/chunks/31azy9hywrzm7.js","async":true}],["$","script","script-17",{"src":"/litellm-asset-prefix/_next/static/chunks/3pu9plov1btip.js","async":true}],["$","script","script-18",{"src":"/litellm-asset-prefix/_next/static/chunks/3mz07lvvrbciz.js","async":true}],["$","script","script-19",{"src":"/litellm-asset-prefix/_next/static/chunks/1lndy6n7cwvrq.js","async":true}],["$","script","script-20",{"src":"/litellm-asset-prefix/_next/static/chunks/09l_m9l1emin2.js","async":true}],["$","script","script-21",{"src":"/litellm-asset-prefix/_next/static/chunks/2c90xukbd3il6.js","async":true}],["$","script","script-22",{"src":"/litellm-asset-prefix/_next/static/chunks/0ikhgrs0xvkyu.js","async":true}],["$","script","script-23",{"src":"/litellm-asset-prefix/_next/static/chunks/23-g73xaw3kap.js","async":true}]],["$","$L6",null,{"children":["$","$7",null,{"name":"Next.MetadataOutlet","children":"$@8"}]}]]}],"isPartial":false,"staleTime":300,"varyParams":null,"buildId":"HynDchE8aLeEewsZVNDO8"}
 4:{}
 5:"$0:rsc:props:children:0:props:serverProvidedParams:params"
 8:null

litellm/proxy/_experimental/out/__next.!KGRhc2hib2FyZCk.txt

@@ -1,7 +1,7 @@
 1:"$Sreact.fragment"
-2:I[92825,["/litellm-asset-prefix/_next/static/chunks/0vggytdohwe7o.js","/litellm-asset-prefix/_next/static/chunks/32_ulchi2_aad.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js"],"ClientSegmentRoot"]
-3:I[216370,["/litellm-asset-prefix/_next/static/chunks/0vggytdohwe7o.js","/litellm-asset-prefix/_next/static/chunks/32_ulchi2_aad.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js","/litellm-asset-prefix/_next/static/chunks/28md7sjkucknx.js","/litellm-asset-prefix/_next/static/chunks/2x96scis66zmk.js","/litellm-asset-prefix/_next/static/chunks/2cngn5bal3278.js","/litellm-asset-prefix/_next/static/chunks/1azbeyb626rh5.js","/litellm-asset-prefix/_next/static/chunks/3_3dj4vdy-3xy.js","/litellm-asset-prefix/_next/static/chunks/0vvnul8uez9kj.js","/litellm-asset-prefix/_next/static/chunks/0g8wwba6umbim.js","/litellm-asset-prefix/_next/static/chunks/2up3bks93iqds.js","/litellm-asset-prefix/_next/static/chunks/0g_w4tf2inv3i.js","/litellm-asset-prefix/_next/static/chunks/17-6zku8f68gf.js","/litellm-asset-prefix/_next/static/chunks/0dbvgsc7ha049.js","/litellm-asset-prefix/_next/static/chunks/1iakmimqrlpn0.js","/litellm-asset-prefix/_next/static/chunks/0fk0i3e2aixp7.js","/litellm-asset-prefix/_next/static/chunks/0f5fel02jwglw.js","/litellm-asset-prefix/_next/static/chunks/17gy9d71tfqhd.js","/litellm-asset-prefix/_next/static/chunks/1vquuz09jxl5_.js"],"default"]
-4:I[339756,["/litellm-asset-prefix/_next/static/chunks/0vggytdohwe7o.js","/litellm-asset-prefix/_next/static/chunks/32_ulchi2_aad.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js"],"default"]
-5:I[837457,["/litellm-asset-prefix/_next/static/chunks/0vggytdohwe7o.js","/litellm-asset-prefix/_next/static/chunks/32_ulchi2_aad.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js"],"default"]
-0:{"rsc":["$","$1","c",{"children":[[["$","script","script-0",{"src":"/litellm-asset-prefix/_next/static/chunks/28md7sjkucknx.js","async":true}],["$","script","script-1",{"src":"/litellm-asset-prefix/_next/static/chunks/2x96scis66zmk.js","async":true}],["$","script","script-2",{"src":"/litellm-asset-prefix/_next/static/chunks/2cngn5bal3278.js","async":true}],["$","script","script-3",{"src":"/litellm-asset-prefix/_next/static/chunks/1azbeyb626rh5.js","async":true}],["$","script","script-4",{"src":"/litellm-asset-prefix/_next/static/chunks/3_3dj4vdy-3xy.js","async":true}],["$","script","script-5",{"src":"/litellm-asset-prefix/_next/static/chunks/0vvnul8uez9kj.js","async":true}],["$","script","script-6",{"src":"/litellm-asset-prefix/_next/static/chunks/0g8wwba6umbim.js","async":true}],["$","script","script-7",{"src":"/litellm-asset-prefix/_next/static/chunks/2up3bks93iqds.js","async":true}],["$","script","script-8",{"src":"/litellm-asset-prefix/_next/static/chunks/0g_w4tf2inv3i.js","async":true}],["$","script","script-9",{"src":"/litellm-asset-prefix/_next/static/chunks/17-6zku8f68gf.js","async":true}],["$","script","script-10",{"src":"/litellm-asset-prefix/_next/static/chunks/0dbvgsc7ha049.js","async":true}],["$","script","script-11",{"src":"/litellm-asset-prefix/_next/static/chunks/1iakmimqrlpn0.js","async":true}],["$","script","script-12",{"src":"/litellm-asset-prefix/_next/static/chunks/0fk0i3e2aixp7.js","async":true}],["$","script","script-13",{"src":"/litellm-asset-prefix/_next/static/chunks/0f5fel02jwglw.js","async":true}],["$","script","script-14",{"src":"/litellm-asset-prefix/_next/static/chunks/17gy9d71tfqhd.js","async":true}],["$","script","script-15",{"src":"/litellm-asset-prefix/_next/static/chunks/1vquuz09jxl5_.js","async":true}]],["$","$L2",null,{"Component":"$3","slots":{"children":["$","$L4",null,{"parallelRouterKey":"children","template":["$","$L5",null,{}],"notFound":[[["$","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."}]}]]}]}]],[]]}]},"serverProvidedParams":{"params":{},"promises":["$@6"]}}]]}],"isPartial":false,"staleTime":300,"varyParams":null,"buildId":"VCvPhLLOUp92Yx-E-CVlV"}
+2:I[92825,["/litellm-asset-prefix/_next/static/chunks/19frz_r2jewoi.js","/litellm-asset-prefix/_next/static/chunks/20mvgyvrlrdla.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js","/litellm-asset-prefix/_next/static/chunks/3fzya67r1y1fl.js"],"ClientSegmentRoot"]
+3:I[216370,["/litellm-asset-prefix/_next/static/chunks/19frz_r2jewoi.js","/litellm-asset-prefix/_next/static/chunks/20mvgyvrlrdla.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js","/litellm-asset-prefix/_next/static/chunks/3fzya67r1y1fl.js","/litellm-asset-prefix/_next/static/chunks/0catil7su1yp5.js","/litellm-asset-prefix/_next/static/chunks/2cngn5bal3278.js","/litellm-asset-prefix/_next/static/chunks/34canl9e2fj8w.js","/litellm-asset-prefix/_next/static/chunks/0vvnul8uez9kj.js","/litellm-asset-prefix/_next/static/chunks/3vu26x-a1_slz.js","/litellm-asset-prefix/_next/static/chunks/1vquuz09jxl5_.js","/litellm-asset-prefix/_next/static/chunks/3_3dj4vdy-3xy.js","/litellm-asset-prefix/_next/static/chunks/0ex44ljfg9dp9.js","/litellm-asset-prefix/_next/static/chunks/0xcneptpo0s76.js","/litellm-asset-prefix/_next/static/chunks/08uoywqkfbbbt.js","/litellm-asset-prefix/_next/static/chunks/0g_w4tf2inv3i.js","/litellm-asset-prefix/_next/static/chunks/1iakmimqrlpn0.js","/litellm-asset-prefix/_next/static/chunks/17-6zku8f68gf.js","/litellm-asset-prefix/_next/static/chunks/0f5fel02jwglw.js","/litellm-asset-prefix/_next/static/chunks/0fk0i3e2aixp7.js","/litellm-asset-prefix/_next/static/chunks/3ytz29phknzsy.js","/litellm-asset-prefix/_next/static/chunks/0dbvgsc7ha049.js","/litellm-asset-prefix/_next/static/chunks/0aoel7yrv88fp.js"],"default"]
+4:I[339756,["/litellm-asset-prefix/_next/static/chunks/19frz_r2jewoi.js","/litellm-asset-prefix/_next/static/chunks/20mvgyvrlrdla.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js","/litellm-asset-prefix/_next/static/chunks/3fzya67r1y1fl.js"],"default"]
+5:I[837457,["/litellm-asset-prefix/_next/static/chunks/19frz_r2jewoi.js","/litellm-asset-prefix/_next/static/chunks/20mvgyvrlrdla.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js","/litellm-asset-prefix/_next/static/chunks/3fzya67r1y1fl.js"],"default"]
+0:{"rsc":["$","$1","c",{"children":[[["$","script","script-0",{"src":"/litellm-asset-prefix/_next/static/chunks/0catil7su1yp5.js","async":true}],["$","script","script-1",{"src":"/litellm-asset-prefix/_next/static/chunks/2cngn5bal3278.js","async":true}],["$","script","script-2",{"src":"/litellm-asset-prefix/_next/static/chunks/34canl9e2fj8w.js","async":true}],["$","script","script-3",{"src":"/litellm-asset-prefix/_next/static/chunks/0vvnul8uez9kj.js","async":true}],["$","script","script-4",{"src":"/litellm-asset-prefix/_next/static/chunks/3vu26x-a1_slz.js","async":true}],["$","script","script-5",{"src":"/litellm-asset-prefix/_next/static/chunks/1vquuz09jxl5_.js","async":true}],["$","script","script-6",{"src":"/litellm-asset-prefix/_next/static/chunks/3_3dj4vdy-3xy.js","async":true}],["$","script","script-7",{"src":"/litellm-asset-prefix/_next/static/chunks/0ex44ljfg9dp9.js","async":true}],["$","script","script-8",{"src":"/litellm-asset-prefix/_next/static/chunks/0xcneptpo0s76.js","async":true}],["$","script","script-9",{"src":"/litellm-asset-prefix/_next/static/chunks/08uoywqkfbbbt.js","async":true}],["$","script","script-10",{"src":"/litellm-asset-prefix/_next/static/chunks/0g_w4tf2inv3i.js","async":true}],["$","script","script-11",{"src":"/litellm-asset-prefix/_next/static/chunks/1iakmimqrlpn0.js","async":true}],["$","script","script-12",{"src":"/litellm-asset-prefix/_next/static/chunks/17-6zku8f68gf.js","async":true}],["$","script","script-13",{"src":"/litellm-asset-prefix/_next/static/chunks/0f5fel02jwglw.js","async":true}],["$","script","script-14",{"src":"/litellm-asset-prefix/_next/static/chunks/0fk0i3e2aixp7.js","async":true}],["$","script","script-15",{"src":"/litellm-asset-prefix/_next/static/chunks/3ytz29phknzsy.js","async":true}],["$","script","script-16",{"src":"/litellm-asset-prefix/_next/static/chunks/0dbvgsc7ha049.js","async":true}],["$","script","script-17",{"src":"/litellm-asset-prefix/_next/static/chunks/0aoel7yrv88fp.js","async":true}]],["$","$L2",null,{"Component":"$3","slots":{"children":["$","$L4",null,{"parallelRouterKey":"children","template":["$","$L5",null,{}],"notFound":[[["$","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."}]}]]}]}]],[]]}]},"serverProvidedParams":{"params":{},"promises":["$@6"]}}]]}],"isPartial":false,"staleTime":300,"varyParams":null,"buildId":"HynDchE8aLeEewsZVNDO8"}
 6:"$0:rsc:props:children:1:props:serverProvidedParams:params"

litellm/proxy/_experimental/out/__next._head.txt

@@ -1,6 +1,6 @@
 1:"$Sreact.fragment"
-2:I[897367,["/litellm-asset-prefix/_next/static/chunks/0vggytdohwe7o.js","/litellm-asset-prefix/_next/static/chunks/32_ulchi2_aad.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js"],"ViewportBoundary"]
-3:I[897367,["/litellm-asset-prefix/_next/static/chunks/0vggytdohwe7o.js","/litellm-asset-prefix/_next/static/chunks/32_ulchi2_aad.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js"],"MetadataBoundary"]
+2:I[897367,["/litellm-asset-prefix/_next/static/chunks/19frz_r2jewoi.js","/litellm-asset-prefix/_next/static/chunks/20mvgyvrlrdla.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js","/litellm-asset-prefix/_next/static/chunks/3fzya67r1y1fl.js"],"ViewportBoundary"]
+3:I[897367,["/litellm-asset-prefix/_next/static/chunks/19frz_r2jewoi.js","/litellm-asset-prefix/_next/static/chunks/20mvgyvrlrdla.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js","/litellm-asset-prefix/_next/static/chunks/3fzya67r1y1fl.js"],"MetadataBoundary"]
 4:"$Sreact.suspense"
-5:I[27201,["/litellm-asset-prefix/_next/static/chunks/0vggytdohwe7o.js","/litellm-asset-prefix/_next/static/chunks/32_ulchi2_aad.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js"],"IconMark"]
-0:{"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.3arlap5n8tyzg.ico","sizes":"48x48","type":"image/x-icon"}],["$","link","3",{"rel":"icon","href":"/get_favicon"}],["$","$L5","4",{}]]}]}]}],["$","meta",null,{"name":"next-size-adjust","content":""}]]}],"isPartial":false,"staleTime":300,"varyParams":null,"buildId":"VCvPhLLOUp92Yx-E-CVlV"}
+5:I[27201,["/litellm-asset-prefix/_next/static/chunks/19frz_r2jewoi.js","/litellm-asset-prefix/_next/static/chunks/20mvgyvrlrdla.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js","/litellm-asset-prefix/_next/static/chunks/3fzya67r1y1fl.js"],"IconMark"]
+0:{"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.3arlap5n8tyzg.ico","sizes":"48x48","type":"image/x-icon"}],["$","link","3",{"rel":"icon","href":"/get_favicon"}],["$","$L5","4",{}]]}]}]}],["$","meta",null,{"name":"next-size-adjust","content":""}]]}],"isPartial":false,"staleTime":300,"varyParams":null,"buildId":"HynDchE8aLeEewsZVNDO8"}

litellm/proxy/_experimental/out/__next._index.txt

@@ -1,9 +1,10 @@
 1:"$Sreact.fragment"
-2:I[867271,["/litellm-asset-prefix/_next/static/chunks/0vggytdohwe7o.js","/litellm-asset-prefix/_next/static/chunks/32_ulchi2_aad.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js"],"default"]
-3:I[71195,["/litellm-asset-prefix/_next/static/chunks/0vggytdohwe7o.js","/litellm-asset-prefix/_next/static/chunks/32_ulchi2_aad.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js"],"default"]
-4:I[557951,["/litellm-asset-prefix/_next/static/chunks/0vggytdohwe7o.js","/litellm-asset-prefix/_next/static/chunks/32_ulchi2_aad.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js"],"AuthProvider"]
-5:I[339756,["/litellm-asset-prefix/_next/static/chunks/0vggytdohwe7o.js","/litellm-asset-prefix/_next/static/chunks/32_ulchi2_aad.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js"],"default"]
-6:I[837457,["/litellm-asset-prefix/_next/static/chunks/0vggytdohwe7o.js","/litellm-asset-prefix/_next/static/chunks/32_ulchi2_aad.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js"],"default"]
+2:I[12985,["/litellm-asset-prefix/_next/static/chunks/19frz_r2jewoi.js","/litellm-asset-prefix/_next/static/chunks/20mvgyvrlrdla.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js","/litellm-asset-prefix/_next/static/chunks/3fzya67r1y1fl.js"],"NuqsAdapter"]
+3:I[867271,["/litellm-asset-prefix/_next/static/chunks/19frz_r2jewoi.js","/litellm-asset-prefix/_next/static/chunks/20mvgyvrlrdla.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js","/litellm-asset-prefix/_next/static/chunks/3fzya67r1y1fl.js"],"default"]
+4:I[71195,["/litellm-asset-prefix/_next/static/chunks/19frz_r2jewoi.js","/litellm-asset-prefix/_next/static/chunks/20mvgyvrlrdla.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js","/litellm-asset-prefix/_next/static/chunks/3fzya67r1y1fl.js"],"default"]
+5:I[557951,["/litellm-asset-prefix/_next/static/chunks/19frz_r2jewoi.js","/litellm-asset-prefix/_next/static/chunks/20mvgyvrlrdla.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js","/litellm-asset-prefix/_next/static/chunks/3fzya67r1y1fl.js"],"AuthProvider"]
+6:I[339756,["/litellm-asset-prefix/_next/static/chunks/19frz_r2jewoi.js","/litellm-asset-prefix/_next/static/chunks/20mvgyvrlrdla.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js","/litellm-asset-prefix/_next/static/chunks/3fzya67r1y1fl.js"],"default"]
+7:I[837457,["/litellm-asset-prefix/_next/static/chunks/19frz_r2jewoi.js","/litellm-asset-prefix/_next/static/chunks/20mvgyvrlrdla.js","/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js","/litellm-asset-prefix/_next/static/chunks/3fzya67r1y1fl.js"],"default"]
 :HL["/litellm-asset-prefix/_next/static/chunks/1kid9zr1--h6y.css","style"]
-:HL["/litellm-asset-prefix/_next/static/chunks/169bqf_mz3j8m.css","style"]
-0:{"rsc":["$","$1","c",{"children":[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/chunks/1kid9zr1--h6y.css","precedence":"next"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/chunks/169bqf_mz3j8m.css","precedence":"next"}],["$","script","script-0",{"src":"/litellm-asset-prefix/_next/static/chunks/0vggytdohwe7o.js","async":true}],["$","script","script-1",{"src":"/litellm-asset-prefix/_next/static/chunks/32_ulchi2_aad.js","async":true}],["$","script","script-2",{"src":"/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.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,{"children":["$","$L5",null,{"parallelRouterKey":"children","template":["$","$L6",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":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],[]]}]}]}]}]}]}]]}],"isPartial":false,"staleTime":300,"varyParams":null,"buildId":"VCvPhLLOUp92Yx-E-CVlV"}
+:HL["/litellm-asset-prefix/_next/static/chunks/1u9cxkx771jnb.css","style"]
+0:{"rsc":["$","$1","c",{"children":[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/chunks/1kid9zr1--h6y.css","precedence":"next"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/chunks/1u9cxkx771jnb.css","precedence":"next"}],["$","script","script-0",{"src":"/litellm-asset-prefix/_next/static/chunks/19frz_r2jewoi.js","async":true}],["$","script","script-1",{"src":"/litellm-asset-prefix/_next/static/chunks/20mvgyvrlrdla.js","async":true}],["$","script","script-2",{"src":"/litellm-asset-prefix/_next/static/chunks/1jfookxfajkeo.js","async":true}],["$","script","script-3",{"src":"/litellm-asset-prefix/_next/static/chunks/3fzya67r1y1fl.js","async":true}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"inter_5972bc34-module__OU16Qa__className","children":["$","$L2",null,{"children":["$","$L3",null,{"children":["$","$L4",null,{"children":["$","$L5",null,{"children":["$","$L6",null,{"parallelRouterKey":"children","template":["$","$L7",null,{}],"notFound":[[["$","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."}]}]]}]}]],[]]}]}]}]}]}]}]}]]}],"isPartial":false,"staleTime":300,"varyParams":null,"buildId":"HynDchE8aLeEewsZVNDO8"}

litellm/proxy/_experimental/out/__next._tree.txt

@@ -1,4 +1,4 @@
 :HL["/litellm-asset-prefix/_next/static/chunks/1kid9zr1--h6y.css","style"]
-:HL["/litellm-asset-prefix/_next/static/chunks/169bqf_mz3j8m.css","style"]
+:HL["/litellm-asset-prefix/_next/static/chunks/1u9cxkx771jnb.css","style"]
 :HL["/litellm-asset-prefix/_next/static/media/83afe278b6a6bb3c-s.p.2bn3s6zvc0dyp.woff2","font",{"crossOrigin":"","type":"font/woff2"}]
-0:{"tree":{"name":"","param":null,"prefetchHints":16,"slots":{"children":{"name":"(dashboard)","param":null,"prefetchHints":0,"slots":{"children":{"name":"__PAGE__","param":null,"prefetchHints":0,"slots":null}}}}},"staleTime":300,"buildId":"VCvPhLLOUp92Yx-E-CVlV"}
+0:{"tree":{"name":"","param":null,"prefetchHints":16,"slots":{"children":{"name":"(dashboard)","param":null,"prefetchHints":0,"slots":{"children":{"name":"__PAGE__","param":null,"prefetchHints":0,"slots":null}}}}},"staleTime":300,"buildId":"HynDchE8aLeEewsZVNDO8"}

litellm/proxy/_experimental/out/_next/static/chunks/0_8sguvytg2x1.js

@@ -1 +0,0 @@
-(globalThis.TURBOPACK||(globalThis.TURBOPACK=[])).push(["object"==typeof document?document.currentScript:void 0,618566,(e,t,r)=>{t.exports=e.r(976562)},434166,e=>{"use strict";e.s(["getSecureItem",0,function(e){try{let t=window.sessionStorage.getItem(e);if(null===t)return null;return decodeURIComponent(atob(t).split("").map(e=>"%"+e.charCodeAt(0).toString(16).padStart(2,"0")).join(""))}catch{return null}},"setSecureItem",0,function(e,t){window.sessionStorage.setItem(e,btoa(encodeURIComponent(t).replace(/%([0-9A-F]{2})/g,(e,t)=>String.fromCharCode(parseInt(t,16)))))}])},346328,e=>{"use strict";var t=e.i(843476),r=e.i(271645),l=e.i(618566),s=e.i(434166);let i=()=>{let e=(0,l.useSearchParams)(),i=(0,r.useMemo)(()=>e?{type:"litellm-mcp-oauth",code:e.get("code"),state:e.get("state"),error:e.get("error"),error_description:e.get("error_description")}:null,[e]);return(0,r.useEffect)(()=>{if(!i)return;try{let e=JSON.stringify(i);(0,s.setSecureItem)("litellm-mcp-oauth-result",e),(0,s.setSecureItem)("litellm-user-mcp-oauth-result",e),(0,s.setSecureItem)("litellm-tools-mcp-oauth-result",e)}catch(e){}let e=(0,s.getSecureItem)("litellm-mcp-oauth-return-url"),t=(()=>{let e=window.location.pathname||"",t=e.indexOf("/ui");if(t>=0){let r=e.slice(0,t+3);return r.endsWith("/")?r:`${r}`}return"/"})();if(e)try{let r=new URL(e,window.location.origin);r.origin===window.location.origin&&(t=r.href)}catch{}window.location.replace(t)},[i]),(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)(r.Suspense,{fallback:(0,t.jsx)("div",{className:"min-h-screen flex items-center justify-center",children:"Loading..."}),children:(0,t.jsx)(i,{})})])}]);