diff --git a/.github/workflows/publish-basedpyright-base-counts.yml b/.github/workflows/publish-basedpyright-base-counts.yml index d9b034684a4..c85d30df0ce 100644 --- a/.github/workflows/publish-basedpyright-base-counts.yml +++ b/.github/workflows/publish-basedpyright-base-counts.yml @@ -43,22 +43,14 @@ jobs: with: version: "0.10.9" - - name: Install dependencies - run: | - uv sync --frozen --group proxy-dev --group e2e-dev - - # Mirrors test-linting.yml's lint job: basedpyright resolves Prisma's - # generated client only after `prisma generate`, and the published counts - # must match what that job would measure for the same tree. - - name: Generate Prisma client + # 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: ${{ runner.temp }}/prisma-cache run: | - uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma - - - name: Emit basedpyright counts for HEAD - run: | - uv run --no-sync python scripts/type_check_gate.py --emit-counts-dir "$RUNNER_TEMP/basedpyright-counts" + python scripts/type_check_gate.py --emit-counts-dir "$RUNNER_TEMP/basedpyright-counts" counts_file=$(ls "$RUNNER_TEMP"/basedpyright-counts/basedpyright-counts-*.json) echo "COUNTS_ARTIFACT_NAME=$(basename "$counts_file" .json)" >> "$GITHUB_ENV" diff --git a/.github/workflows/test-linting.yml b/.github/workflows/test-linting.yml index 5125dd0a354..5e333f2a3ca 100644 --- a/.github/workflows/test-linting.yml +++ b/.github/workflows/test-linting.yml @@ -115,6 +115,7 @@ 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" diff --git a/.gitignore b/.gitignore index 13f2202305d..3329f39ca10 100644 --- a/.gitignore +++ b/.gitignore @@ -1,5 +1,6 @@ .python-version .venv +.venv-typecheck .venv_policy_test .env .claude diff --git a/CLAUDE.md b/CLAUDE.md index 1bc4d108da7..59929143c46 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -29,7 +29,7 @@ Never use `pytest` commands or the like as "Screenshots / Proof of Fix". We pref If you ever make public-facing PR descriptions, comments, issues, commit messages, etc., always follow these guidelines to sound less AI-y: - don't use emojis -- don't use "—". Instead, reach for ",", ".", conjunction words, ":", ";", etc. in descending order of preference: vary among them, weighted toward the front of the list, and skip "," where it would cause a comma splice or the sentence is getting long. Overusing any one of them, ";" especially, also feels AI-y +- don't use "—". Instead, reach for ",", ".", conjunction words, ":", ";", etc. in descending order of preference: vary among them, weighted toward the front of the list, and skip "," where it would cause a comma splice or the sentence is getting long. Overusing any one of them, ";" especially, also feels AI-y. A word cap does not penalize you for adding more sentences: when writing under tight word budgets, prefer a period split or a conjunction over ";", and keep to at most one ";" per message - don't use the pattern "It's not X, it's Y", "You're not X, you're Y", etc. - don't use bulleted or numbered lists unless it would be nonsensical not to. Instead, prefer prose - don't add a trailing "." at the end of paragraphs (just like this file). That means every paragraph, not just the last one (of the markdown file, PR description, GitHub comment, etc.). Rule of thumb: if you're adding new line(s) before the next sentence, don't add a "." @@ -41,11 +41,11 @@ Python max line length is 120, not 88 When you fix violations gated by `ruff-strict-budget.json`, `type-discipline-budget.json`, or `basedpyright-code-budget.json`, run `make lint-budget-update` and commit the lowered limits so the ceilings ratchet down instead of leaving stale headroom. It measures the working tree, so it must contain exactly the fixes you're committing -`make pre-commit` always saves its complete output to a per-worktree log file and prints that path as its first and last output lines. To inspect a run, read or grep that log instead of re-running the multi-minute checks just to see a different slice, and re-run only after the working tree actually changed +`make pre-commit` saves its complete output to a log file in .git (overwriting previous pre-commit logs) and prints that path as its first and last output lines. To inspect a run, read or grep that log instead of re-running the multi-minute checks just to see a different slice If you're trying to create a new function that relies on untyped stuff, instead of adding more Any's and pushing `reportAny` / `reportExplicitAny` closer to their basedpyright ceilings, just validate it in the caller with Pydantic (a model or `TypeAdapter` that returns the typed thing or raises will do) and then pass the now typed variable in -If you get an LIT001 or LIT002 fail, refactor the code to follow functional programming best practices rather than introducing mutable data structures. For example, build values in one shot with comprehensions or generators wrapped in `tuple()` / `frozenset()` instead of seeding an empty `list`/`dict`/`set` and mutating it over time. Ideally, `# mutable-ok` is never used; reach for it only as a genuine last resort when an immutable rewrite is truly impossible, and always pair it with a real reason +If you get an LIT001 or LIT002 fail, refactor the code to follow functional programming best practices rather than introducing mutable data structures. For example, build values in one shot with comprehensions or generators wrapped in `tuple()` / `MappingProxyType()` / `frozenset()` instead of seeding an empty `list`/`dict`/`set` and mutating it over time. Ideally, `# mutable-ok` is never used; reach for it only as a genuine last resort when an immutable rewrite is truly impossible, and always pair it with a real reason Every lint or type suppression must name the exact rule inside brackets and carry a reason comment, e.g. `# pyright: ignore[reportArgumentType] # stubs lack async overload` or `# noqa: TID251 # `. `# type: ignore` is banned (LIT009): pyrightconfig.json sets `enableTypeIgnoreComments` to false, so it silently does nothing @@ -59,7 +59,7 @@ Do not add `Co-Authored-By: Claude` or any Claude attribution to commit messages When working on a PR, keep the PR description in sync with new commits being made -Replies/rebuttals to AI PR review bots must be 15-25 word human-readable replies +All GitHub comments must be human-readable and 15-25 words max Monkeypatching attributes of a class to do testing is an anti-pattern. Prefer dependency-injecting things into classes. That way, at unit test time, you can pass a mocked dependency in @@ -72,7 +72,7 @@ Follow these coding conventions for new/updated code (a three-line fix in a lega - Composition over inheritance - Never-nester: early returns over deep nesting - Don't throw; model failures as values (One function (e.g., raise_public) maps error union to existing public exception contracts via exhaustive match + assert_never) -- No mutation; don't reassign variables, global or local. Instead of mutable lists and dicts, prefer tuples, frozen dataclasses (with slots=True), etc. +- No mutation; don't reassign variables, global or local. Instead of mutable lists and dicts, prefer tuples, frozen dataclasses (with slots=True), `MappingProxyType`, etc. - Annotate every variable with `: Final` (LIT010). Unpacking and walrus targets cannot carry the annotation, so they are implicitly final. Don't rebind them. Never rebind or mutate function parameters (LIT011); `self`/`cls` attribute stores are the exception. If rebinding or in-place mutation is truly unavoidable, suppress with `# rebind-ok: ` explaining why - Use dependency injection - Fully typed; no `Any` or coarse types like `dict[str, Any]` or just `dict`. Every function parameter must be strongly typed diff --git a/Makefile b/Makefile index 3e82e141c77..493828571b7 100644 --- a/Makefile +++ b/Makefile @@ -124,10 +124,10 @@ lint-fetch-base: git fetch origin litellm_internal_staging # Mirror test-linting.yml's lint job environment: the proxy-dev group plus a generated -# Prisma client, so basedpyright resolves the same modules CI does (without the generated -# client the DB wrappers typed against it degrade to Unknown, drifting the budget from -# CI's). --inexact tops up the venv instead of pruning the proxy extras gen:api and the -# running proxy need. +# Prisma client, so `basedpyright tests/e2e` resolves the same modules CI does. The +# budget gate itself no longer measures here (scripts/type_check_gate.py provisions its +# own .venv-typecheck). --inexact tops up the venv instead of pruning the proxy extras +# gen:api and the running proxy need. lint-install: $(UV) sync --inexact --frozen --group proxy-dev --group e2e-dev $(UV_RUN) python scripts/prisma_generate_if_needed.py diff --git a/basedpyright-code-budget.json b/basedpyright-code-budget.json index 27d96e415fd..632743236c4 100644 --- a/basedpyright-code-budget.json +++ b/basedpyright-code-budget.json @@ -1,18 +1,18 @@ { "reportAny": { - "limit": 29204 + "limit": 28842 }, "reportArgumentType": { - "limit": 2635 + "limit": 2634 }, "reportAssignmentType": { "limit": 329 }, "reportAttributeAccessIssue": { - "limit": 516 + "limit": 514 }, "reportCallIssue": { - "limit": 123 + "limit": 117 }, "reportConstantRedefinition": { "limit": 40 @@ -24,7 +24,7 @@ "limit": 19 }, "reportExplicitAny": { - "limit": 9227 + "limit": 9103 }, "reportFunctionMemberAccess": { "limit": 7 @@ -54,10 +54,10 @@ "limit": 0 }, "reportMissingParameterType": { - "limit": 5850 + "limit": 5843 }, "reportMissingTypeArgument": { - "limit": 15833 + "limit": 15816 }, "reportMissingTypeStubs": { "limit": 40 @@ -99,34 +99,34 @@ "limit": 0 }, "reportUnknownArgumentType": { - "limit": 45242 + "limit": 45110 }, "reportUnknownLambdaType": { "limit": 113 }, "reportUnknownMemberType": { - "limit": 40340 + "limit": 39838 }, "reportUnknownParameterType": { - "limit": 20293 + "limit": 20237 }, "reportUnknownVariableType": { - "limit": 31796 + "limit": 31383 }, "reportUnnecessaryCast": { "limit": 122 }, "reportUnnecessaryComparison": { - "limit": 703 + "limit": 701 }, "reportUnnecessaryContains": { "limit": 5 }, "reportUnnecessaryIsInstance": { - "limit": 865 + "limit": 864 }, "reportUntypedBaseClass": { - "limit": 72 + "limit": 0 }, "reportUntypedFunctionDecorator": { "limit": 33 diff --git a/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py b/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py index 3ed63b0d9ee..7acdd5dbdaf 100644 --- a/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py +++ b/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py @@ -498,6 +498,7 @@ class CheckBatchCost: }, "metadata": { "user_api_key_user_id": creator_user_id, + "user_api_key_team_id": getattr(job, "team_id", None), **user_info, }, }, @@ -656,6 +657,20 @@ class CheckBatchCost: elif response.status in ("failed", "expired", "cancelled"): try: + from litellm.proxy.openai_files_endpoints.common_utils import ( + _is_base64_encoded_unified_file_id, + ensure_batch_response_managed_file_ids, + ) + + response.id = job.unified_object_id + await ensure_batch_response_managed_file_ids( + response=response, + managed_files_obj=self.proxy_logging_obj.get_proxy_hook("managed_files"), + prisma_client=self.prisma_client, + verbose_proxy_logger=verbose_proxy_logger, + db_batch_object=job, + unified_batch_id=_is_base64_encoded_unified_file_id(job.unified_object_id), + ) update_data = { "status": response.status, "file_object": response.model_dump_json(), diff --git a/enterprise/litellm_enterprise/proxy/common_utils/check_responses_cost.py b/enterprise/litellm_enterprise/proxy/common_utils/check_responses_cost.py index dc0168683c8..27837b0b5e4 100644 --- a/enterprise/litellm_enterprise/proxy/common_utils/check_responses_cost.py +++ b/enterprise/litellm_enterprise/proxy/common_utils/check_responses_cost.py @@ -1,10 +1,10 @@ """ Polls LiteLLM_ManagedObjectTable to check if the response is complete. -Cost tracking is handled automatically by litellm.aget_responses(). +Cost tracking is handled automatically by the get-responses call. """ from datetime import datetime, timedelta, timezone -from typing import TYPE_CHECKING +from typing import TYPE_CHECKING, Dict, Optional, cast import litellm from litellm._logging import verbose_proxy_logger @@ -13,11 +13,15 @@ from litellm.constants import ( MAX_OBJECTS_PER_POLL_CYCLE, STALE_OBJECT_CLEANUP_BATCH_SIZE, ) +from litellm.responses.utils import ResponsesAPIRequestUtils +from litellm.types.llms.openai import ResponsesAPIResponse if TYPE_CHECKING: from litellm.proxy.utils import PrismaClient, ProxyLogging from litellm.router import Router +TERMINAL_RESPONSE_STATUSES = frozenset({"completed", "failed", "cancelled", "incomplete"}) + class CheckResponsesCost: def __init__( @@ -33,6 +37,28 @@ class CheckResponsesCost: self.prisma_client: PrismaClient = prisma_client self.llm_router: Router = llm_router + async def _get_response( + self, + response_id: str, + litellm_metadata: Dict[str, str], + ) -> ResponsesAPIResponse: + """Fetch the upstream response, using deployment credentials when available. + + LiteLLM-encoded response IDs carry the ``model_id`` of the deployment that + served the original request, so routing through ``llm_router`` applies that + deployment's ``api_base`` / ``api_key`` / ``api_version``, exactly like + ``GET /v1/responses/{id}`` does. ``litellm.aget_responses`` on its own only + sees provider env vars, so it fails for every deployment whose credentials + live in the config; the row then never leaves ``queued``. + """ + model_id: Optional[str] = ResponsesAPIRequestUtils.get_model_id_from_response_id(response_id) + if model_id is None or self.llm_router.get_deployment(model_id=model_id) is None: + return await litellm.aget_responses(response_id=response_id, litellm_metadata=litellm_metadata) + router_response = await self.llm_router.aget_responses( + response_id=response_id, litellm_metadata=litellm_metadata + ) + return cast(ResponsesAPIResponse, router_response) + async def _expire_stale_rows( self, cutoff: datetime, batch_size: int ) -> int: @@ -87,8 +113,8 @@ class CheckResponsesCost: Check if background responses are complete and track their cost. - Get all status="queued" or "in_progress" and file_purpose="response" jobs - Query the provider to check if response is complete - - Cost is automatically tracked by litellm.aget_responses() - - Mark completed/failed/cancelled responses as complete in the database + - Cost is automatically tracked by the get-responses call + - Mark responses in a terminal state as complete in the database """ try: await self._cleanup_stale_managed_objects() @@ -134,7 +160,7 @@ class CheckResponsesCost: litellm_metadata["model"] = model_name litellm_metadata["model_group"] = model_name # Use same value for model_group - response = await litellm.aget_responses( + response = await self._get_response( response_id=responses_id_security, litellm_metadata=litellm_metadata, ) @@ -144,21 +170,14 @@ class CheckResponsesCost: ) except Exception as e: - verbose_proxy_logger.info( + verbose_proxy_logger.warning( f"Skipping job {unified_object_id} due to error: {e}" ) continue - # Check if response is in a terminal state - if response.status == "completed": + if response.status in TERMINAL_RESPONSE_STATUSES: verbose_proxy_logger.info( - f"Response {unified_object_id} is complete. Cost automatically tracked by aget_responses." - ) - completed_jobs.append(job) - - elif response.status in ["failed", "cancelled"]: - verbose_proxy_logger.info( - f"Response {unified_object_id} has status {response.status}, marking as complete" + f"Response {unified_object_id} has terminal status {response.status}, marking as complete" ) completed_jobs.append(job) diff --git a/litellm/caching/redis_semantic_cache.py b/litellm/caching/redis_semantic_cache.py index b1d298b79bb..604d6395ea1 100644 --- a/litellm/caching/redis_semantic_cache.py +++ b/litellm/caching/redis_semantic_cache.py @@ -13,6 +13,7 @@ import ast import asyncio import json import os +from collections.abc import Callable, Mapping from typing import Any, Final, cast import litellm @@ -47,7 +48,7 @@ class RedisSemanticCache(BaseCache): similarity_threshold: float | None = None, embedding_model: str = "text-embedding-ada-002", index_name: str | None = None, - **kwargs, + **kwargs: object, ): """ Initialize the Redis Semantic Cache. @@ -150,11 +151,11 @@ class RedisSemanticCache(BaseCache): def _init_semantic_cache( self, - semantic_cache_cls: Any, + semantic_cache_cls: Callable[..., object], index_name: str, redis_url: str, - cache_vectorizer: Any, - ) -> Any: + cache_vectorizer: object, + ) -> object: def _is_schema_mismatch(exc: ValueError) -> bool: error_message: Final = str(exc).lower() return any(phrase in error_message for phrase in ("schema does not match", "index schema")) @@ -206,12 +207,12 @@ class RedisSemanticCache(BaseCache): def _get_cache_filters(self, key: str) -> dict[str, str]: return {self.CACHE_KEY_FIELD_NAME: str(key)} - def _get_cache_key_filter_expression(self, key: str) -> Any: + def _get_cache_key_filter_expression(self, key: str) -> object: from redisvl.query.filter import Tag return Tag(self.CACHE_KEY_FIELD_NAME) == str(key) - def _cache_hit_matches_key(self, cache_hit: dict[str, Any], key: str) -> bool: + def _cache_hit_matches_key(self, cache_hit: Mapping[str, object], key: str) -> bool: # Pre-isolation entries with no ``litellm_cache_key`` field cannot be # safely reassigned to a caller's scope and are treated as misses. cached_key = cache_hit.get(self.CACHE_KEY_FIELD_NAME) @@ -297,7 +298,7 @@ class RedisSemanticCache(BaseCache): return @staticmethod - def _coerce_response_input_value(value: Any) -> Any: + def _coerce_response_input_value(value: object) -> object: model_dump: Final = getattr(value, "model_dump", None) if callable(model_dump): return model_dump() @@ -340,7 +341,7 @@ class RedisSemanticCache(BaseCache): ) return embedding_response["data"][0]["embedding"] - def _get_cache_logic(self, cached_response: Any) -> Any: + def _get_cache_logic(self, cached_response: Any) -> object: """ Process the cached response to prepare it for use. @@ -369,7 +370,7 @@ class RedisSemanticCache(BaseCache): return cached_response - def set_cache(self, key: str, value: Any, **kwargs) -> None: + def set_cache(self, key: str, value: object, **kwargs) -> None: """ Store a value in the semantic cache. @@ -405,7 +406,7 @@ class RedisSemanticCache(BaseCache): except Exception as e: print_verbose(f"Error setting {value_str or value} in the Redis semantic cache: {e}") - def get_cache(self, key: str, **kwargs) -> Any: + def get_cache(self, key: str, **kwargs) -> object: """ Retrieve a semantically similar cached response. @@ -428,7 +429,7 @@ class RedisSemanticCache(BaseCache): # Check the cache for semantically similar prompts in this exact # LiteLLM cache-key scope. prompt_embedding: Final = self._get_embedding(prompt, metadata=kwargs.get("metadata")) - check_kwargs: Final[dict[str, Any]] = { + check_kwargs: Final[Mapping[str, object]] = { "prompt": prompt, "vector": prompt_embedding, "filter_expression": self._get_cache_key_filter_expression(key), @@ -508,7 +509,7 @@ class RedisSemanticCache(BaseCache): print_verbose(f"Error generating async embedding: {e}") raise ValueError(f"Failed to generate embedding: {e}") from e - async def async_set_cache(self, key: str, value: Any, **kwargs) -> None: + async def async_set_cache(self, key: str, value: object, **kwargs) -> None: """ Asynchronously store a value in the semantic cache. @@ -548,7 +549,7 @@ class RedisSemanticCache(BaseCache): except Exception as e: print_verbose(f"Error in async_set_cache: {e}") - async def async_get_cache(self, key: str, **kwargs) -> Any: + async def async_get_cache(self, key: str, **kwargs) -> object: """ Asynchronously retrieve a semantically similar cached response. @@ -573,7 +574,7 @@ class RedisSemanticCache(BaseCache): # Check the cache for semantically similar prompts in this exact # LiteLLM cache-key scope. - check_kwargs: Final[dict[str, Any]] = { + check_kwargs: Final[Mapping[str, object]] = { "prompt": prompt, "vector": prompt_embedding, "filter_expression": self._get_cache_key_filter_expression(key), @@ -615,7 +616,7 @@ class RedisSemanticCache(BaseCache): print_verbose(f"Error in async_get_cache: {e}") kwargs.setdefault("metadata", {})["semantic-similarity"] = 0.0 - async def _index_info(self) -> dict[str, Any]: + async def _index_info(self) -> Mapping[str, object]: """ Get information about the Redis index. @@ -625,7 +626,7 @@ class RedisSemanticCache(BaseCache): aindex: Final = await self.llmcache._get_async_index() return await aindex.info() - async def async_set_cache_pipeline(self, cache_list: list[tuple[str, Any]], **kwargs) -> None: + async def async_set_cache_pipeline(self, cache_list: list[tuple[str, Any]], **kwargs: object) -> None: """ Asynchronously store multiple values in the semantic cache. diff --git a/litellm/integrations/custom_guardrail.py b/litellm/integrations/custom_guardrail.py index 20f3aa430e9..2e91e082bd4 100644 --- a/litellm/integrations/custom_guardrail.py +++ b/litellm/integrations/custom_guardrail.py @@ -714,6 +714,29 @@ class CustomGuardrail(CustomLogger): return result + def supports_scan_only_tool_results(self) -> bool: + """Whether this guardrail can scan tool-result content. + + Guardrails whose own role filtering only ever scans human-authored + messages override this to return False, so configuring them with + ``scan_only_tool_results`` is rejected at initialization instead of + silently scanning nothing on every request. + """ + return True + + def structured_messages_cover_full_request(self) -> bool: + """Whether returned ``structured_messages`` span the whole request. + + Translation handlers hand guardrails only the in-scope subset of the + conversation and merge a returned ``structured_messages`` list back + into the full request. A guardrail that already rebuilds the complete + conversation itself (like CrowdStrike AIDR with its skip filters + active) overrides this to return True so the handler installs the + returned list as-is instead of merging it a second time, which would + duplicate the out-of-scope messages. + """ + return False + def should_run_guardrail( self, data, diff --git a/litellm/integrations/galileo.py b/litellm/integrations/galileo.py index 12c2ac8a53f..2c9ac63941c 100644 --- a/litellm/integrations/galileo.py +++ b/litellm/integrations/galileo.py @@ -4,8 +4,9 @@ import json import os import re import uuid -from datetime import datetime, timezone -from typing import Any, Final, cast +from collections.abc import Mapping, Sequence +from datetime import datetime, timezone, tzinfo +from typing import Any, Final, TypedDict, cast import httpx from pydantic import BaseModel, Field @@ -34,6 +35,17 @@ GALILEO_CLOUD_API_BASE_URL: Final = "https://api.galileo.ai" GALILEO_MAX_IN_MEMORY_RECORDS: Final = 1000 +class GalileoStandardLoggingFields(TypedDict, total=False): + call_type: str + model: str + prompt_tokens: int + completion_tokens: int + total_tokens: int + response_cost: float + startTime: float + endTime: float + + class LLMResponse(BaseModel): latency_ms: int status_code: int @@ -59,7 +71,7 @@ class LLMResponse(BaseModel): class GalileoObserve(CustomLogger): def __init__(self) -> None: - self.in_memory_records: list[dict] = [] + self.in_memory_records: list[Mapping[str, object]] = [] self.batch_size = 1 self.api_key = os.getenv("GALILEO_API_KEY") self.project_id = os.getenv("GALILEO_PROJECT_ID") @@ -176,7 +188,7 @@ class GalileoObserve(CustomLogger): return False @staticmethod - def _galileo_input_messages(messages: Any | None, input_text: str) -> list[dict[str, str]]: + def _galileo_input_messages(messages: object, input_text: str) -> list[dict[str, str]]: if isinstance(messages, dict): messages = messages.get("messages") if not messages: @@ -203,11 +215,11 @@ class GalileoObserve(CustomLogger): return [{"role": "user", "content": input_text}] @staticmethod - def _local_timezone(): + def _local_timezone() -> tzinfo: return datetime.now().astimezone().tzinfo or timezone.utc @staticmethod - def _format_created_at(dt: datetime | Any) -> str: + def _format_created_at(dt: object) -> str: """Serialize timestamps as UTC ISO-8601 for Galileo.""" if not isinstance(dt, datetime): return str(dt) @@ -226,7 +238,7 @@ class GalileoObserve(CustomLogger): return created_at @staticmethod - def _token_metrics_from_record(record: dict[str, Any]) -> dict[str, Any]: + def _token_metrics_from_record(record: Mapping[str, Any]) -> dict[str, Any]: num_input_tokens: Final = int(record.get("num_input_tokens") or 0) num_output_tokens: Final = int(record.get("num_output_tokens") or 0) num_total_tokens = int(record.get("num_total_tokens") or 0) @@ -244,7 +256,7 @@ class GalileoObserve(CustomLogger): @staticmethod def _record_to_v2_span( - record: dict[str, Any], + record: Mapping[str, Any], *, trace_id: str, span_id: str, @@ -275,7 +287,7 @@ class GalileoObserve(CustomLogger): return span @staticmethod - def _record_to_v2_trace(record: dict[str, Any]) -> dict[str, Any]: + def _record_to_v2_trace(record: Mapping[str, Any]) -> dict[str, Any]: trace_id: Final = str(uuid.uuid4()) span_id: Final = str(uuid.uuid4()) created_at: Final = GalileoObserve._normalize_created_at(record.get("created_at", "")) @@ -295,7 +307,7 @@ class GalileoObserve(CustomLogger): "spans": [GalileoObserve._record_to_v2_span(record, trace_id=trace_id, span_id=span_id)], } - def _build_traces_payload(self, records: list[dict]) -> dict[str, Any]: + def _build_traces_payload(self, records: Sequence[Mapping[str, Any]]) -> dict[str, Any]: payload: Final[dict[str, Any]] = { "traces": [self._record_to_v2_trace(record) for record in records], "logging_method": "api_direct", @@ -357,7 +369,7 @@ class GalileoObserve(CustomLogger): @staticmethod def _log_v2_payload_validation(payload: dict[str, Any]) -> None: missing_fields: Final[list[str]] = [] - traces: Final = payload.get("traces", []) + traces: Final[Sequence[object]] = payload.get("traces", []) if not traces: missing_fields.append("traces") @@ -385,7 +397,7 @@ class GalileoObserve(CustomLogger): ) def _log_flush_payload(self, url: str, payload: dict[str, Any]) -> None: - traces: Final = payload.get("traces", []) + traces: Final[Sequence[object]] = payload.get("traces", []) verbose_logger.debug( "Galileo Logger flush URL: %s trace_count=%s", url, @@ -415,8 +427,8 @@ class GalileoObserve(CustomLogger): pass @staticmethod - def _build_prompt(kwargs: dict[str, Any]) -> dict[str, Any]: - optional_params: Final = kwargs.get("optional_params", {}) or {} + def _build_prompt(kwargs: Mapping[str, Any]) -> dict[str, Any]: + optional_params: Final[Mapping[str, object]] = kwargs.get("optional_params", {}) or {} prompt: Final[dict[str, Any]] = {"messages": kwargs.get("messages")} if optional_params.get("functions") is not None: prompt["functions"] = optional_params["functions"] @@ -425,13 +437,13 @@ class GalileoObserve(CustomLogger): return prompt @staticmethod - def _serialize_galileo_output(value: Any) -> str: + def _serialize_galileo_output(value: object) -> str: if value is None: return "" if isinstance(value, str): return value - def _json_default(obj: Any) -> Any: + def _json_default(obj: Any) -> object: if hasattr(obj, "model_dump"): return obj.model_dump() return str(obj) @@ -439,8 +451,8 @@ class GalileoObserve(CustomLogger): return json.dumps(value, default=_json_default) @staticmethod - def _prompt_to_input_text(prompt: dict[str, Any]) -> str: - messages: Final = prompt.get("messages") + def _prompt_to_input_text(prompt: Mapping[str, Any]) -> str: + messages: Final[object] = prompt.get("messages") if messages is not None: text: Final = GalileoObserve._input_text_from_messages(messages) if text: @@ -448,7 +460,7 @@ class GalileoObserve(CustomLogger): return json.dumps(prompt, default=str) @staticmethod - def _get_chat_content_for_galileo(response_obj: litellm.ModelResponse) -> Any: + def _get_chat_content_for_galileo(response_obj: litellm.ModelResponse) -> object: if response_obj.choices and len(response_obj.choices) > 0: message: Final = response_obj["choices"][0]["message"] if hasattr(message, "json"): @@ -470,23 +482,23 @@ class GalileoObserve(CustomLogger): @staticmethod def _get_responses_api_content_for_galileo( response_obj: ResponsesAPIResponse, - ) -> Any: + ) -> object: if hasattr(response_obj, "output") and response_obj.output: return response_obj.output return None @staticmethod - def _langfuse_style_rerank_prompt(kwargs: dict[str, Any]) -> dict[str, Any]: + def _langfuse_style_rerank_prompt(kwargs: Mapping[str, object]) -> dict[str, Any]: """Match Langfuse rerank input: prompt = {"messages": kwargs.get("messages")}.""" return {"messages": kwargs.get("messages")} def _get_galileo_input_output_content( self, - kwargs: dict[str, Any], - response_obj: Any, + kwargs: Mapping[str, object], + response_obj: object, level: str = "DEFAULT", status_message: str | None = None, - ) -> tuple[str, str, Any]: + ) -> tuple[str, str, object]: """ Mirror Langfuse _get_langfuse_input_output_content for Galileo ingest. @@ -582,12 +594,12 @@ class GalileoObserve(CustomLogger): return self._prompt_to_input_text(prompt), "", kwargs.get("messages") or [] - def get_output_str_from_response(self, response_obj: Any, kwargs: dict[str, Any]) -> str: + def get_output_str_from_response(self, response_obj: object, kwargs: Mapping[str, object]) -> str: _, output_text, _ = self._get_galileo_input_output_content(kwargs=kwargs, response_obj=response_obj) return output_text @staticmethod - def _input_text_from_messages(messages: Any) -> str: + def _input_text_from_messages(messages: object) -> str: """Return a plain-string summary of the input suitable for the trace-level input field.""" if isinstance(messages, str): return messages @@ -613,7 +625,13 @@ class GalileoObserve(CustomLogger): return str(content) return "" - async def async_log_success_event(self, kwargs: Any, response_obj: Any, start_time: Any, end_time: Any): + async def async_log_success_event( + self, + kwargs: Mapping[str, object], + response_obj: object, + start_time: object, + end_time: object, + ) -> None: verbose_logger.debug("On Async Success") try: await self._async_log_success_event_impl( @@ -625,7 +643,13 @@ class GalileoObserve(CustomLogger): except Exception: verbose_logger.exception("Galileo Logger: unexpected error in async_log_success_event") - async def _async_log_success_event_impl(self, kwargs: Any, response_obj: Any, start_time: Any, end_time: Any): + async def _async_log_success_event_impl( + self, + kwargs: Mapping[str, Any], + response_obj: object, + start_time: object, + end_time: object, + ) -> None: if not self._is_configured(): verbose_logger.debug( "Galileo Logger: skipping — GALILEO_PROJECT_ID=%s GALILEO_API_KEY=%s GALILEO_BASE_URL=%s", @@ -635,7 +659,7 @@ class GalileoObserve(CustomLogger): ) return - slo: Final[dict[str, Any] | None] = kwargs.get("standard_logging_object") + slo: Final[GalileoStandardLoggingFields | None] = kwargs.get("standard_logging_object") if slo is None: verbose_logger.debug("Galileo Logger: no standard_logging_object in kwargs, skipping") return @@ -646,8 +670,8 @@ class GalileoObserve(CustomLogger): kwargs=kwargs, response_obj=response_obj ) - raw_start: Final = slo.get("startTime") - raw_end: Final = slo.get("endTime") + raw_start: Final[float | None] = slo.get("startTime") + raw_end: Final[float | None] = slo.get("endTime") if raw_start is None or raw_end is None: verbose_logger.debug( "Galileo Logger: standard_logging_object missing startTime/endTime, " @@ -710,7 +734,7 @@ class GalileoObserve(CustomLogger): if len(self.in_memory_records) >= self.batch_size: await self.flush_in_memory_records() - async def flush_in_memory_records(self): + async def flush_in_memory_records(self) -> None: if not self.in_memory_records: return @@ -774,5 +798,11 @@ class GalileoObserve(CustomLogger): if not self.use_v2_api and response.status_code in (401, 403): self.headers = None - async def async_log_failure_event(self, kwargs, response_obj, start_time, end_time): + async def async_log_failure_event( + self, + kwargs: Mapping[str, object], + response_obj: object, + start_time: object, + end_time: object, + ) -> None: verbose_logger.debug("On Async Failure") diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py index 6ba06919e00..9475441e214 100644 --- a/litellm/litellm_core_utils/litellm_logging.py +++ b/litellm/litellm_core_utils/litellm_logging.py @@ -1399,10 +1399,7 @@ class Logging(LiteLLMLoggingBaseClass): litellm_params=(self.litellm_params if hasattr(self, "litellm_params") else None) ) - prompt = "" # use for tts cost calc - _input: Final = self.model_call_details.get("input", None) - if _input is not None and isinstance(_input, str): - prompt = _input + prompt = self._prompt_for_cost_calculation() if cache_hit is None: cache_hit = self.model_call_details.get("cache_hit", False) @@ -1461,6 +1458,19 @@ class Logging(LiteLLMLoggingBaseClass): return None + def _prompt_for_cost_calculation(self) -> str: + """ + The raw input string is only priced directly for text-to-speech, which bills per character. + Every other call type gets its billable units from the response usage object, and call types + that carry no usage at all (file content retrieval, and anything else `function_setup` cannot + build messages for) only have the ``"default-message-value"`` placeholder here, so passing the + input along would token-price that placeholder. + """ + if self.call_type not in (CallTypes.speech.value, CallTypes.aspeech.value): + return "" + _input = self.model_call_details.get("input", None) + return _input if isinstance(_input, str) else "" + def _generate_content_result_as_model_response(self, result: object) -> ModelResponse | None: """ Native Google :generateContent bodies report token usage under diff --git a/litellm/llms/anthropic/chat/guardrail_translation/handler.py b/litellm/llms/anthropic/chat/guardrail_translation/handler.py index 3662389900b..88db9fae912 100644 --- a/litellm/llms/anthropic/chat/guardrail_translation/handler.py +++ b/litellm/llms/anthropic/chat/guardrail_translation/handler.py @@ -26,10 +26,13 @@ from litellm.llms.anthropic.experimental_pass_through.adapters.transformation im ) from litellm.llms.base_llm.guardrail_translation.base_translation import BaseTranslation from litellm.llms.base_llm.guardrail_translation.utils import ( + anthropic_tool_name, + effective_scan_only_tool_results_for_guardrail, effective_skip_system_message_for_guardrail, effective_skip_tool_message_for_guardrail, - openai_messages_without_system, - openai_messages_without_tool, + merge_guardrailed_scoped_messages, + merge_returned_tools_into_request_tools, + scoped_structured_message_indices, ) from litellm.proxy.pass_through_endpoints.llm_provider_handlers.anthropic_passthrough_logging_handler import ( AnthropicPassthroughLoggingHandler, @@ -326,19 +329,25 @@ class AnthropicMessagesHandler(BaseTranslation): skip_system: Final = effective_skip_system_message_for_guardrail(guardrail_to_apply) skip_tool: Final = effective_skip_tool_message_for_guardrail(guardrail_to_apply) + scan_only_tool_results: Final = effective_scan_only_tool_results_for_guardrail(guardrail_to_apply) chat_completion_compatible_request: Final = self._translate_to_openai(data) - structured_messages = cast( + full_structured_messages: Final = cast( list[AllMessageValues], chat_completion_compatible_request.get("messages", []), ) - if skip_system: - structured_messages = openai_messages_without_system(structured_messages) - if skip_tool: - structured_messages = openai_messages_without_tool(structured_messages) + scoped_message_indices: Final = scoped_structured_message_indices( + full_structured_messages, + scan_only_tool_results=scan_only_tool_results, + skip_system=skip_system, + skip_tool=skip_tool, + ) + structured_messages: Final = [full_structured_messages[index] for index in scoped_message_indices] - tools_to_check: Final[list[ChatCompletionToolParam]] = chat_completion_compatible_request.get("tools", []) + tools_to_check: Final[list[ChatCompletionToolParam]] = ( + [] if scan_only_tool_results else chat_completion_compatible_request.get("tools", []) + ) # Step 1: Extract all text content and images extracted: Final = tuple( @@ -347,6 +356,7 @@ class AnthropicMessagesHandler(BaseTranslation): msg_idx=msg_idx, skip_system_message=skip_system, skip_tool_message=skip_tool, + scan_only_tool_results=scan_only_tool_results, ) for msg_idx, message in enumerate(messages) ) @@ -388,14 +398,31 @@ class AnthropicMessagesHandler(BaseTranslation): if converted_tool is not None: anthropic_tools.append(converted_tool) # Note: MCP servers are handled separately in the main transformation - data["tools"] = anthropic_tools + data["tools"] = ( + merge_returned_tools_into_request_tools( + request_tools=data.get("tools"), + returned_tools=anthropic_tools, + tool_name=anthropic_tool_name, + ) + if scan_only_tool_results + else anthropic_tools + ) guardrailed_structured_messages: Final = guardrailed_inputs.get("structured_messages") if ( guardrailed_structured_messages is not None and guardrailed_structured_messages is not original_structured_messages ): - self._write_back_structured_messages(data, guardrailed_structured_messages) + self._write_back_structured_messages( + data, + guardrailed_structured_messages + if guardrail_to_apply.structured_messages_cover_full_request() + else merge_guardrailed_scoped_messages( + full_messages=full_structured_messages, + scoped_indices=scoped_message_indices, + guardrailed_scoped=guardrailed_structured_messages, + ), + ) else: # Step 3: Map guardrail responses back to original message structure await self._apply_guardrail_responses_to_input( @@ -461,6 +488,7 @@ class AnthropicMessagesHandler(BaseTranslation): msg_idx: int, skip_system_message: bool = False, skip_tool_message: bool = False, + scan_only_tool_results: bool = False, ) -> ExtractedInput: """ Extract text content and images from a message. @@ -471,6 +499,8 @@ class AnthropicMessagesHandler(BaseTranslation): content: Final = message.get("content", None) if isinstance(content, str): + if scan_only_tool_results: + return EMPTY_EXTRACTED_INPUT return ExtractedInput(scanned=(ScannedText(content, MessageContentTarget(msg_idx)),), images=()) if not isinstance(content, list): return EMPTY_EXTRACTED_INPUT @@ -481,6 +511,7 @@ class AnthropicMessagesHandler(BaseTranslation): msg_idx=msg_idx, content_idx=content_idx, skip_tool_message=skip_tool_message, + scan_only_tool_results=scan_only_tool_results, ) for content_idx, content_item in enumerate(content) if isinstance(content_item, dict) @@ -497,12 +528,16 @@ class AnthropicMessagesHandler(BaseTranslation): msg_idx: int, content_idx: int, skip_tool_message: bool, + scan_only_tool_results: bool = False, ) -> ExtractedInput: if content_item.get("type") == "tool_result": if skip_tool_message: return EMPTY_EXTRACTED_INPUT return cls._extract_tool_result(content_item=content_item, msg_idx=msg_idx, content_idx=content_idx) + if scan_only_tool_results: + return EMPTY_EXTRACTED_INPUT + text_str: Final = content_item.get("text", None) return ExtractedInput( scanned=( @@ -551,22 +586,6 @@ class AnthropicMessagesHandler(BaseTranslation): data: Final = source.get("data") return (data,) if data else () - def _extract_input_tools( - self, - tools: list[dict[str, Any]], - tools_to_check: list[ChatCompletionToolParam], - ) -> None: - """ - Extract tools from a message. - """ - ## CHECK FOR TOOLS - if tools is not None and isinstance(tools, list): - # TRANSFORM ANTHROPIC TOOLS TO OPENAI TOOLS - openai_tools: Final = self.adapter.translate_anthropic_tools_to_openai( - tools=cast(list[AllAnthropicToolsValues], tools) - ) - tools_to_check.extend(openai_tools) - async def _apply_guardrail_responses_to_input( self, messages: list[dict[str, Any]], diff --git a/litellm/llms/anthropic/chat/transformation.py b/litellm/llms/anthropic/chat/transformation.py index 7bbdb9a43fd..1161c92232a 100644 --- a/litellm/llms/anthropic/chat/transformation.py +++ b/litellm/llms/anthropic/chat/transformation.py @@ -592,7 +592,7 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig): # Anthropic requires additionalProperties=false for object schemas # See: https://docs.anthropic.com/en/docs/build-with-claude/structured-outputs - if result.get("type") == "object" and "additionalProperties" not in result: + if result.get("type") == "object": result["additionalProperties"] = False return result diff --git a/litellm/llms/base_llm/guardrail_translation/utils.py b/litellm/llms/base_llm/guardrail_translation/utils.py index 17cc0f118d6..f1ddf21cd3c 100644 --- a/litellm/llms/base_llm/guardrail_translation/utils.py +++ b/litellm/llms/base_llm/guardrail_translation/utils.py @@ -1,7 +1,8 @@ from __future__ import annotations import json -from typing import Any, Final +from collections.abc import Callable, Iterator, Sequence +from typing import Any, Final, TypeVar from litellm.types.llms.anthropic_messages.anthropic_response import AnthropicUsage from litellm.types.llms.openai import AllMessageValues @@ -113,13 +114,131 @@ def effective_skip_tool_message_for_guardrail(guardrail_to_apply: Any) -> bool: return bool(getattr(litellm, "skip_tool_message_in_guardrail", False)) +def _message_role(message: AllMessageValues) -> str: + return str((message or {}).get("role") or "").lower() + + def openai_messages_without_system( - messages: list[AllMessageValues], -) -> list[AllMessageValues]: - return [m for m in messages if str((m or {}).get("role") or "").lower() != "system"] + messages: Sequence[AllMessageValues], +) -> tuple[AllMessageValues, ...]: + return tuple(m for m in messages if _message_role(m) != "system") def openai_messages_without_tool( - messages: list[AllMessageValues], + messages: Sequence[AllMessageValues], +) -> tuple[AllMessageValues, ...]: + return tuple(m for m in messages if _message_role(m) != "tool") + + +def effective_scan_only_tool_results_for_guardrail(guardrail_to_apply: object) -> bool: + return getattr(guardrail_to_apply, "scan_only_tool_results", None) is True + + +def role_out_of_guardrail_scope( + role: str, + *, + skip_system_message: bool, + skip_tool_message: bool, + scan_only_tool_results: bool = False, +) -> bool: + if skip_system_message and role == "system": + return True + if skip_tool_message and role == "tool": + return True + return scan_only_tool_results and role not in ("tool", "function") + + +def scoped_structured_message_indices( + messages: Sequence[AllMessageValues], + *, + scan_only_tool_results: bool, + skip_system: bool, + skip_tool: bool, +) -> tuple[int, ...]: + return tuple( + index + for index, message in enumerate(messages) + if not role_out_of_guardrail_scope( + _message_role(message), + skip_system_message=skip_system, + skip_tool_message=skip_tool, + scan_only_tool_results=scan_only_tool_results, + ) + ) + + +ToolT = TypeVar("ToolT") + + +def openai_tool_name(tool: object) -> str | None: + if not isinstance(tool, dict): + return None + function: Final = tool.get("function") + if isinstance(function, dict): + function_name: Final = function.get("name") + return function_name if isinstance(function_name, str) else None + flat_name: Final = tool.get("name") + return flat_name if isinstance(flat_name, str) else None + + +def anthropic_tool_name(tool: object) -> str | None: + name: Final = tool.get("name") if isinstance(tool, dict) else None + return name if isinstance(name, str) else None + + +def merge_returned_tools_into_request_tools( + request_tools: Sequence[ToolT] | None, + returned_tools: Sequence[ToolT], + tool_name: Callable[[ToolT], str | None], +) -> list[ToolT]: + """Union of the request's tools and guardrail-returned tools, keyed by name. + + Under ``scan_only_tool_results`` the guardrail never saw the request's + tools, so a returned list can neither replace them (it would drop every + user-defined function) nor be discarded (it may carry a tool the guardrail + synthesized and told the model to call, like Compresr's retrieve tool). + Keep every request tool and append only returned tools whose names aren't + already taken by a request tool or an earlier returned tool. + """ + originals: Final = tuple(request_tools or ()) + taken_names: Final = frozenset(name for tool in originals if (name := tool_name(tool)) is not None) + additions: Final = tuple( + tool + for index, tool in enumerate(returned_tools) + if (name := tool_name(tool)) not in taken_names + and (name is None or all(tool_name(earlier) != name for earlier in returned_tools[:index])) + ) + return [*originals, *additions] + + +def merge_guardrailed_scoped_messages( + full_messages: Sequence[AllMessageValues], + scoped_indices: Sequence[int], + guardrailed_scoped: Sequence[AllMessageValues], ) -> list[AllMessageValues]: - return [m for m in messages if str((m or {}).get("role") or "").lower() != "tool"] + """Substitute guardrail-returned messages back into the full conversation. + + Guardrails only ever see the scoped subset of messages, so a replacement + list they hand back describes that subset, not the whole request. Writing + it over ``data["messages"]`` wholesale would silently drop every + out-of-scope message (system prompt, prior turns). Instead, swap each + returned message into the position its scoped original came from; extra + returned messages land after the last scoped position, and scoped + originals without a counterpart are treated as removed by the guardrail. + When nothing was filtered out this degenerates to the returned list + itself, preserving wholesale-replacement behavior for unscoped guardrails. + """ + replacements: Final = dict(zip(scoped_indices, guardrailed_scoped)) + removed: Final = frozenset(scoped_indices[len(guardrailed_scoped) :]) + appended: Final = tuple(guardrailed_scoped[len(scoped_indices) :]) + last_scoped_index: Final = scoped_indices[-1] if scoped_indices else None + + def _merged() -> Iterator[AllMessageValues]: + for index, message in enumerate(full_messages): + if index in removed: + continue + yield replacements.get(index, message) + if index == last_scoped_index: + yield from appended + + return list(_merged()) diff --git a/litellm/llms/openai/chat/guardrail_translation/handler.py b/litellm/llms/openai/chat/guardrail_translation/handler.py index 3988326f2c2..e411dc497fc 100644 --- a/litellm/llms/openai/chat/guardrail_translation/handler.py +++ b/litellm/llms/openai/chat/guardrail_translation/handler.py @@ -23,10 +23,14 @@ from litellm.llms.base_llm.guardrail_translation.base_translation import ( StreamTransformSink, ) from litellm.llms.base_llm.guardrail_translation.utils import ( + effective_scan_only_tool_results_for_guardrail, effective_skip_system_message_for_guardrail, effective_skip_tool_message_for_guardrail, - openai_messages_without_system, - openai_messages_without_tool, + merge_guardrailed_scoped_messages, + merge_returned_tools_into_request_tools, + openai_tool_name, + role_out_of_guardrail_scope, + scoped_structured_message_indices, ) from litellm.main import stream_chunk_builder from litellm.types.llms.openai import AllMessageValues, ChatCompletionToolParam @@ -82,6 +86,7 @@ class OpenAIChatCompletionsHandler(BaseTranslation): skip_system: Final = effective_skip_system_message_for_guardrail(guardrail_to_apply) skip_tool: Final = effective_skip_tool_message_for_guardrail(guardrail_to_apply) + scan_only_tool_results: Final = effective_scan_only_tool_results_for_guardrail(guardrail_to_apply) texts_to_check: Final[list[str]] = [] images_to_check: Final[list[str]] = [] @@ -101,6 +106,7 @@ class OpenAIChatCompletionsHandler(BaseTranslation): tool_call_task_mappings=tool_call_task_mappings, skip_system_message=skip_system, skip_tool_message=skip_tool, + scan_only_tool_results=scan_only_tool_results, ) # Step 2: Apply guardrail to all texts and tool calls in batch @@ -110,16 +116,18 @@ class OpenAIChatCompletionsHandler(BaseTranslation): inputs["images"] = images_to_check if tool_calls_to_check: inputs["tool_calls"] = tool_calls_to_check - structured_messages = self.get_structured_messages(data) + structured_messages: Final = self.get_structured_messages(data) + scoped_message_indices: Final = scoped_structured_message_indices( + structured_messages or [], + scan_only_tool_results=scan_only_tool_results, + skip_system=skip_system, + skip_tool=skip_tool, + ) if structured_messages: - if skip_system: - structured_messages = openai_messages_without_system(structured_messages) - if skip_tool: - structured_messages = openai_messages_without_tool(structured_messages) - inputs["structured_messages"] = structured_messages + inputs["structured_messages"] = [structured_messages[index] for index in scoped_message_indices] # Pass tools (function definitions) to the guardrail tools: Final = data.get("tools") - if tools: + if tools and not scan_only_tool_results: inputs["tools"] = tools # Include model information if available model: Final = data.get("model") @@ -138,14 +146,30 @@ class OpenAIChatCompletionsHandler(BaseTranslation): guardrailed_tool_calls: Final = guardrailed_inputs.get("tool_calls", []) guardrailed_tools: Final = guardrailed_inputs.get("tools") if guardrailed_tools is not None: - data["tools"] = guardrailed_tools + data["tools"] = ( + merge_returned_tools_into_request_tools( + request_tools=tools, + returned_tools=guardrailed_tools, + tool_name=openai_tool_name, + ) + if scan_only_tool_results + else guardrailed_tools + ) guardrailed_structured_messages: Final = guardrailed_inputs.get("structured_messages") if ( guardrailed_structured_messages is not None and guardrailed_structured_messages is not original_structured_messages ): - data["messages"] = guardrailed_structured_messages + data["messages"] = ( + guardrailed_structured_messages + if guardrail_to_apply.structured_messages_cover_full_request() + else merge_guardrailed_scoped_messages( + full_messages=structured_messages or [], + scoped_indices=scoped_message_indices, + guardrailed_scoped=guardrailed_structured_messages, + ) + ) else: # Step 3: Map guardrail responses back to original message structure if guardrailed_texts and texts_to_check: @@ -194,16 +218,19 @@ class OpenAIChatCompletionsHandler(BaseTranslation): tool_call_task_mappings: list[tuple[int, int]], skip_system_message: bool = False, skip_tool_message: bool = False, + scan_only_tool_results: bool = False, ) -> None: """ Extract text content, images, and tool calls from a message. Override this method to customize text/image/tool call extraction logic. """ - role: Final = str(message.get("role") or "").lower() - if skip_system_message and role == "system": - return - if skip_tool_message and role == "tool": + if role_out_of_guardrail_scope( + str(message.get("role") or "").lower(), + skip_system_message=skip_system_message, + skip_tool_message=skip_tool_message, + scan_only_tool_results=scan_only_tool_results, + ): return content: Final = message.get("content", None) diff --git a/litellm/proxy/_experimental/mcp_server/openapi_to_mcp_generator.py b/litellm/proxy/_experimental/mcp_server/openapi_to_mcp_generator.py index 1794a1b66b8..2cc761f99ed 100644 --- a/litellm/proxy/_experimental/mcp_server/openapi_to_mcp_generator.py +++ b/litellm/proxy/_experimental/mcp_server/openapi_to_mcp_generator.py @@ -7,10 +7,13 @@ import contextvars import json import os import re +from collections.abc import Mapping, Sequence from pathlib import PurePosixPath -from typing import Any, Final +from typing import Any, Final, TypeAlias, TypedDict from urllib.parse import quote +import httpx + # Tool names emitted from OpenAPI specs must work across all major LLM providers. # OpenAI/Anthropic/Bedrock all enforce a character class roughly equivalent to # ^[a-zA-Z0-9_-]+$ on tool names. Many specs (notably GitHub's REST API) use @@ -44,6 +47,41 @@ from litellm.proxy._experimental.mcp_server.tool_registry import ( global_mcp_tool_registry, ) +_OpenAPIParameter: TypeAlias = Mapping[str, Any] + + +class _OpenAPIJSONSchema(TypedDict, total=False): + properties: Mapping[str, object] + + +class _OpenAPIMediaType(TypedDict, total=False): + schema: _OpenAPIJSONSchema + + +class _OpenAPIRequestBody(TypedDict, total=False): + description: str + required: bool + content: Mapping[str, _OpenAPIMediaType] + + +class _OpenAPIOperation(TypedDict, total=False): + operationId: str + summary: str + description: str + parameters: Sequence[_OpenAPIParameter] + requestBody: _OpenAPIRequestBody + + +class _OpenAPIPathItem(TypedDict, total=False): + summary: str + description: str + parameters: Sequence[_OpenAPIParameter] + + +class _OpenAPIComponents(TypedDict, total=False): + parameters: Mapping[str, _OpenAPIParameter] + + # Store the base URL and headers globally BASE_URL: Final = "" HEADERS: Final[dict[str, str]] = {} @@ -69,7 +107,7 @@ _request_resolved_auth_headers: Final[contextvars.ContextVar[dict[str, str] | No ) -def _sanitize_path_parameter_value(param_value: Any, param_name: str) -> str: +def _sanitize_path_parameter_value(param_value: object, param_name: str) -> str: """Ensure path params cannot introduce directory traversal.""" if param_value is None: return "" @@ -109,7 +147,7 @@ def load_openapi_spec(filepath: str) -> dict[str, Any]: async def load_openapi_spec_async(filepath: str) -> dict[str, Any]: if filepath.startswith("http://") or filepath.startswith("https://"): client: Final = get_async_httpx_client(llm_provider=httpxSpecialProvider.MCP) - r: Final = await async_safe_get(client, filepath) + r: Final[httpx.Response] = await async_safe_get(client, filepath) r.raise_for_status() return r.json() @@ -121,11 +159,11 @@ async def load_openapi_spec_async(filepath: str) -> dict[str, Any]: return json.load(f) -def get_base_url(spec: dict[str, Any], spec_path: str | None = None) -> str: +def get_base_url(spec: Mapping[str, Any], spec_path: str | None = None) -> str: """Extract base URL from OpenAPI spec.""" # OpenAPI 3.x if "servers" in spec and spec["servers"]: - server_url: Final = spec["servers"][0]["url"] + server_url: Final[str] = spec["servers"][0]["url"] # If the server URL is relative (starts with /), derive base from spec_path if server_url.startswith("/") and spec_path: @@ -147,8 +185,8 @@ def get_base_url(spec: dict[str, Any], spec_path: str | None = None) -> str: return server_url # OpenAPI 2.x (Swagger) elif "host" in spec: - scheme: Final = spec.get("schemes", ["https"])[0] - base_path: Final = spec.get("basePath", "") + scheme: Final[str] = spec.get("schemes", ["https"])[0] + base_path: Final[str] = spec.get("basePath", "") return f"{scheme}://{spec['host']}{base_path}" # Fallback: derive base URL from spec_path if it's a URL @@ -172,20 +210,24 @@ def get_base_url(spec: dict[str, Any], spec_path: str | None = None) -> str: return "" -def _resolve_ref(param: dict[str, Any], component_params: dict[str, Any]) -> dict[str, Any] | None: +def _resolve_ref( + param: _OpenAPIParameter, component_params: Mapping[str, _OpenAPIParameter] +) -> _OpenAPIParameter | None: """Resolve a single parameter, following a $ref if present. Returns the resolved param dict, or None if the $ref target is absent from components (so callers can skip/filter it rather than propagating a stub with name=None that would corrupt deduplication). """ - ref: Final = param.get("$ref", "") + ref: Final[str] = param.get("$ref", "") if not ref.startswith("#/components/parameters/"): return param return component_params.get(ref.split("/")[-1]) -def _resolve_param_list(raw: list[dict[str, Any]], component_params: dict[str, Any]) -> list[dict[str, Any]]: +def _resolve_param_list( + raw: Sequence[_OpenAPIParameter], component_params: Mapping[str, _OpenAPIParameter] +) -> list[_OpenAPIParameter]: """Resolve $refs in a parameter list, dropping any unresolvable entries.""" result: Final = [] for p in raw: @@ -196,9 +238,9 @@ def _resolve_param_list(raw: list[dict[str, Any]], component_params: dict[str, A def resolve_operation_params( - operation: dict[str, Any], - path_item: dict[str, Any], - components: dict[str, Any], + operation: _OpenAPIOperation, + path_item: _OpenAPIPathItem, + components: _OpenAPIComponents, ) -> dict[str, Any]: """Return a copy of *operation* with fully-resolved, merged parameters. @@ -214,7 +256,7 @@ def resolve_operation_params( merged with the operation-level params; operation-level wins when the same ``name`` + ``in`` combination appears in both. """ - component_params: Final = components.get("parameters", {}) + component_params: Final[Mapping[str, _OpenAPIParameter]] = components.get("parameters", {}) path_level: Final = _resolve_param_list(path_item.get("parameters", []), component_params) op_level: Final = _resolve_param_list(operation.get("parameters", []), component_params) op_keys: Final = {(p["name"], p.get("in")) for p in op_level} @@ -224,7 +266,7 @@ def resolve_operation_params( return result -def extract_parameters(operation: dict[str, Any]) -> tuple: +def extract_parameters(operation: Mapping[str, Any]) -> tuple[Sequence[str], Sequence[str], Sequence[str]]: """Extract parameter names from OpenAPI operation.""" path_params: Final = [] query_params: Final = [] @@ -250,7 +292,7 @@ def extract_parameters(operation: dict[str, Any]) -> tuple: return path_params, query_params, body_params -def build_input_schema(operation: dict[str, Any]) -> dict[str, Any]: +def build_input_schema(operation: Mapping[str, Any]) -> dict[str, Any]: """Build MCP input schema from OpenAPI operation.""" properties: Final = {} required: Final = [] @@ -274,12 +316,12 @@ def build_input_schema(operation: dict[str, Any]) -> dict[str, Any]: # Process requestBody (OpenAPI 3.x) if "requestBody" in operation: - request_body: Final = operation["requestBody"] - content: Final = request_body.get("content", {}) + request_body: Final[_OpenAPIRequestBody] = operation["requestBody"] + content: Final[Mapping[str, _OpenAPIMediaType]] = request_body.get("content", {}) # Try to get JSON schema if "application/json" in content: - schema: Final = content["application/json"].get("schema", {}) + schema: Final[_OpenAPIJSONSchema] = content["application/json"].get("schema", {}) properties["body"] = { "type": "object", "description": request_body.get("description", "Request body"), @@ -347,7 +389,7 @@ def _merge_openapi_tool_request_headers( def create_tool_function( path: str, method: str, - operation: dict[str, Any], + operation: Mapping[str, Any], base_url: str, headers: dict[str, str] | None = None, ): @@ -373,7 +415,7 @@ def create_tool_function( path_params, query_params, body_params = extract_parameters(operation) original_method: Final = method.lower() - async def tool_function(**kwargs: Any) -> str: + async def tool_function(**kwargs: object) -> str: """ Dynamically generated tool function. @@ -448,10 +490,10 @@ def create_tool_function( return tool_function -def register_tools_from_openapi(spec: dict[str, Any], base_url: str): +def register_tools_from_openapi(spec: Mapping[str, Any], base_url: str) -> None: """Register MCP tools from OpenAPI specification.""" - paths: Final = spec.get("paths", {}) - used_names: Final[set] = set() + paths: Final[Mapping[str, Mapping[str, Any]]] = spec.get("paths", {}) + used_names: Final = set() for path, path_item in paths.items(): for method in ["get", "post", "put", "delete", "patch"]: diff --git a/litellm/proxy/_types.py b/litellm/proxy/_types.py index 7bc8ed59a6a..5b1134650f2 100644 --- a/litellm/proxy/_types.py +++ b/litellm/proxy/_types.py @@ -781,6 +781,7 @@ class LiteLLMRoutes(enum.Enum): "/model/update", "/model/delete", "/user/daily/activity", + "/user/daily/activity/aggregated", "/user/available_roles", # read-only role metadata; any authenticated user may read "/user/list", # org admins checked in endpoint; non-admins get 403 "/model/{model_id}/update", diff --git a/litellm/proxy/anthropic_endpoints/claude_code_endpoints/claude_code_marketplace.py b/litellm/proxy/anthropic_endpoints/claude_code_endpoints/claude_code_marketplace.py index 579c735b180..46ee9b0911d 100644 --- a/litellm/proxy/anthropic_endpoints/claude_code_endpoints/claude_code_marketplace.py +++ b/litellm/proxy/anthropic_endpoints/claude_code_endpoints/claude_code_marketplace.py @@ -18,8 +18,9 @@ Endpoints: import json import re +from collections.abc import Mapping, Sequence from datetime import datetime, timezone -from typing import Any, Final +from typing import Final, Protocol, TypedDict from fastapi import APIRouter, Depends, HTTPException from fastapi.responses import JSONResponse @@ -41,7 +42,30 @@ from litellm.types.proxy.claude_code_endpoints import ( router: Final = APIRouter() -async def _get_prisma_client(): +class _PluginRecord(Protocol): + id: str + name: str + version: str | None + description: str | None + manifest_json: str | None + enabled: bool + created_at: datetime | None + updated_at: datetime | None + created_by: str | None + + +class _MarketplaceEntry(TypedDict, total=False): + name: str + source: object + version: str + description: str + author: object + homepage: object + keywords: object + category: object + + +async def _get_prisma_client() -> object: """Get the prisma client from proxy_server.""" from litellm.proxy.proxy_server import prisma_client @@ -77,12 +101,14 @@ async def get_marketplace(): try: prisma_client: Final = await _get_prisma_client() - plugins: Final = await ClaudeCodePluginRepository(prisma_client).table.find_many(where={"enabled": True}) + plugins: Final[Sequence[_PluginRecord]] = await ClaudeCodePluginRepository(prisma_client).table.find_many( + where={"enabled": True} + ) plugin_list: Final = [] for plugin in plugins: try: - manifest = json.loads(plugin.manifest_json) + manifest: Mapping[str, object] = json.loads(plugin.manifest_json or "{}") except json.JSONDecodeError: verbose_proxy_logger.warning("Plugin %s has invalid manifest JSON, skipping", plugin.name) continue @@ -92,7 +118,7 @@ async def get_marketplace(): verbose_proxy_logger.warning("Plugin %s has no source field, skipping", plugin.name) continue - entry: dict[str, Any] = { + entry: _MarketplaceEntry = { "name": plugin.name, "source": manifest["source"], } @@ -137,7 +163,7 @@ async def get_marketplace(): _VALID_GIT_SUBDIR_PATH_RE: Final = re.compile(r"^[a-zA-Z0-9][a-zA-Z0-9._-]*(/[a-zA-Z0-9][a-zA-Z0-9._-]*)*$") -def _validate_plugin_source(source: dict[str, Any]) -> None: +def _validate_plugin_source(source: Mapping[str, str]) -> None: """Validate plugin source format, raising HTTPException on invalid input.""" source_type: Final = source.get("source") if source_type == "github": @@ -179,9 +205,9 @@ def _validate_plugin_source(source: dict[str, Any]) -> None: ) -def _build_plugin_manifest(name: str, spec: PluginSpec) -> dict[str, Any]: +def _build_plugin_manifest(name: str, spec: PluginSpec) -> Mapping[str, object]: """Build the stored manifest dict shared by plugin create and update.""" - dumped = spec.model_dump(exclude_none=True) + dumped: Final[Mapping[str, object]] = spec.model_dump(exclude_none=True) return {"name": name, **{key: value for key, value in dumped.items() if value and key != "name"}} @@ -255,14 +281,16 @@ async def register_plugin( _validate_plugin_source(request.source) - existing = await ClaudeCodePluginRepository(prisma_client).table.find_unique(where={"name": request.name}) + existing: Final[_PluginRecord | None] = await ClaudeCodePluginRepository(prisma_client).table.find_unique( + where={"name": request.name} + ) if existing: raise _name_conflict_error(request.name) - manifest = _build_plugin_manifest(request.name, request) + manifest: Final[Mapping[str, object]] = _build_plugin_manifest(request.name, request) try: - plugin = await ClaudeCodePluginRepository(prisma_client).table.create( + plugin: Final[_PluginRecord] = await ClaudeCodePluginRepository(prisma_client).table.create( data={ "name": request.name, "version": request.version, @@ -326,7 +354,9 @@ async def list_plugins( prisma_client: Final = await _get_prisma_client() where: Final = {"enabled": True} if enabled_only else {} - plugins: Final = await ClaudeCodePluginRepository(prisma_client).table.find_many(where=where) + plugins: Final[Sequence[_PluginRecord]] = await ClaudeCodePluginRepository(prisma_client).table.find_many( + where=where + ) plugin_list: Final = [] for p in plugins: @@ -391,7 +421,9 @@ async def get_plugin( try: prisma_client: Final = await _get_prisma_client() - plugin: Final = await ClaudeCodePluginRepository(prisma_client).table.find_unique(where={"name": plugin_name}) + plugin: Final[_PluginRecord | None] = await ClaudeCodePluginRepository(prisma_client).table.find_unique( + where={"name": plugin_name} + ) if not plugin: raise HTTPException( @@ -399,7 +431,7 @@ async def get_plugin( detail={"error": f"Plugin '{plugin_name}' not found"}, ) - manifest: Final = json.loads(plugin.manifest_json) if plugin.manifest_json else {} + manifest: Final[Mapping[str, object]] = json.loads(plugin.manifest_json or "{}") if plugin.manifest_json else {} return { "id": plugin.id, @@ -477,19 +509,19 @@ async def update_plugin( from prisma.errors import PrismaError try: - prisma_client = await _get_prisma_client() + prisma_client: Final = await _get_prisma_client() _validate_plugin_source(request.source) - existing = await ClaudeCodePluginRepository(prisma_client).table.find_unique( + existing: Final[_PluginRecord | None] = await ClaudeCodePluginRepository(prisma_client).table.find_unique( where={"name": plugin_name} # mutable-ok: prisma query arguments must be plain dicts ) if not existing: raise _error_response(404, f"Plugin '{plugin_name}' not found") - manifest = _build_plugin_manifest(plugin_name, request) + manifest: Final[Mapping[str, object]] = _build_plugin_manifest(plugin_name, request) - plugin = await ClaudeCodePluginRepository(prisma_client).table.update( + plugin: Final[_PluginRecord] = await ClaudeCodePluginRepository(prisma_client).table.update( where={"name": plugin_name}, # mutable-ok: prisma query arguments must be plain dicts data={ # mutable-ok: prisma query arguments must be plain dicts "version": request.version, @@ -540,7 +572,9 @@ async def enable_plugin( try: prisma_client: Final = await _get_prisma_client() - plugin: Final = await ClaudeCodePluginRepository(prisma_client).table.find_unique(where={"name": plugin_name}) + plugin: Final[_PluginRecord | None] = await ClaudeCodePluginRepository(prisma_client).table.find_unique( + where={"name": plugin_name} + ) if not plugin: raise HTTPException( status_code=404, @@ -583,7 +617,9 @@ async def disable_plugin( try: prisma_client: Final = await _get_prisma_client() - plugin: Final = await ClaudeCodePluginRepository(prisma_client).table.find_unique(where={"name": plugin_name}) + plugin: Final[_PluginRecord | None] = await ClaudeCodePluginRepository(prisma_client).table.find_unique( + where={"name": plugin_name} + ) if not plugin: raise HTTPException( status_code=404, @@ -626,7 +662,9 @@ async def delete_plugin( try: prisma_client: Final = await _get_prisma_client() - plugin: Final = await ClaudeCodePluginRepository(prisma_client).table.find_unique(where={"name": plugin_name}) + plugin: Final[_PluginRecord | None] = await ClaudeCodePluginRepository(prisma_client).table.find_unique( + where={"name": plugin_name} + ) if not plugin: raise HTTPException( status_code=404, diff --git a/litellm/proxy/batches_endpoints/endpoints.py b/litellm/proxy/batches_endpoints/endpoints.py index deed665d3f2..f7c332f2849 100644 --- a/litellm/proxy/batches_endpoints/endpoints.py +++ b/litellm/proxy/batches_endpoints/endpoints.py @@ -264,6 +264,7 @@ async def create_batch( detail={"error": "LLM Router not initialized. Ensure models added to proxy."}, ) + _create_batch_data.update(disable_fallbacks=True) # pyright: ignore[reportCallIssue] # router flag response = await llm_router.acreate_batch(**_create_batch_data) response.input_file_id = input_file_id response._hidden_params["unified_file_id"] = unified_file_id @@ -961,6 +962,7 @@ async def cancel_batch( prisma_client=prisma_client, verbose_proxy_logger=verbose_proxy_logger, operation="cancel", + user_api_key_dict=user_api_key_dict, ) ### CALL HOOKS ### - modify outgoing data diff --git a/litellm/proxy/common_utils/custom_openapi_spec.py b/litellm/proxy/common_utils/custom_openapi_spec.py index cb91805aafc..bc7b80801fe 100644 --- a/litellm/proxy/common_utils/custom_openapi_spec.py +++ b/litellm/proxy/common_utils/custom_openapi_spec.py @@ -1,3 +1,4 @@ +from collections.abc import Mapping, Sequence from typing import Any, Final from litellm._logging import verbose_proxy_logger @@ -26,7 +27,7 @@ class CustomOpenAPISpec: RESPONSES_API_PATHS = ["/v1/responses", "/responses"] @staticmethod - def get_pydantic_schema(model_class) -> dict[str, Any] | None: + def get_pydantic_schema(model_class) -> Mapping[str, object] | None: """ Get JSON schema from a Pydantic model, handling both v1 and v2 APIs. @@ -53,7 +54,9 @@ class CustomOpenAPISpec: return None @staticmethod - def add_schema_to_components(openapi_schema: dict[str, Any], schema_name: str, schema_def: dict[str, Any]) -> None: + def add_schema_to_components( + openapi_schema: dict[str, Any], schema_name: str, schema_def: Mapping[str, object] + ) -> None: """ Add a schema definition to the OpenAPI components/schemas section. @@ -72,7 +75,7 @@ class CustomOpenAPISpec: CustomOpenAPISpec._move_defs_to_components(openapi_schema, {schema_name: schema_def}) @staticmethod - def add_request_body_to_paths(openapi_schema: dict[str, Any], paths: list[str], schema_ref: str) -> None: + def add_request_body_to_paths(openapi_schema: dict[str, Any], paths: Sequence[str], schema_ref: str) -> None: """ Add request body with expanded form fields for better Swagger UI display. This keeps the request body but expands it to show individual fields in the UI. @@ -130,7 +133,7 @@ class CustomOpenAPISpec: openapi_schema["paths"][path]["post"]["parameters"] = filtered_params @staticmethod - def _move_defs_to_components(openapi_schema: dict[str, Any], defs: dict[str, Any]) -> None: + def _move_defs_to_components(openapi_schema: dict[str, Any], defs: Mapping[str, Mapping[str, Any]]) -> None: """ Move $defs from Pydantic v2 schema to OpenAPI components/schemas. This makes the definitions resolvable in Swagger/OpenAPI viewers. @@ -218,7 +221,7 @@ class CustomOpenAPISpec: return {"type": "string"} @staticmethod - def _expand_field_definition(field_def: dict[str, Any]) -> dict[str, Any]: + def _expand_field_definition(field_def: dict[str, object]) -> dict[str, object]: """ Expand a Pydantic field definition for inline use in OpenAPI schema. This creates a full field definition that Swagger UI can render as individual form fields. @@ -234,12 +237,12 @@ class CustomOpenAPISpec: @staticmethod def add_request_schema( - openapi_schema: dict[str, Any], + openapi_schema: dict[str, object], model_class: type, schema_name: str, - paths: list[str], + paths: Sequence[str], operation_name: str, - ) -> dict[str, Any]: + ) -> dict[str, object]: """ Generic method to add a request schema to OpenAPI specification. @@ -279,8 +282,8 @@ class CustomOpenAPISpec: @staticmethod def add_chat_completion_request_schema( - openapi_schema: dict[str, Any], - ) -> dict[str, Any]: + openapi_schema: dict[str, object], + ) -> dict[str, object]: """ Add ProxyChatCompletionRequest schema to chat completion endpoints for documentation. This shows the request body in Swagger without runtime validation. @@ -306,7 +309,7 @@ class CustomOpenAPISpec: return openapi_schema @staticmethod - def add_embedding_request_schema(openapi_schema: dict[str, Any]) -> dict[str, Any]: + def add_embedding_request_schema(openapi_schema: dict[str, object]) -> dict[str, object]: """ Add EmbeddingRequest schema to embedding endpoints for documentation. This shows the request body in Swagger without runtime validation. @@ -333,8 +336,8 @@ class CustomOpenAPISpec: @staticmethod def add_responses_api_request_schema( - openapi_schema: dict[str, Any], - ) -> dict[str, Any]: + openapi_schema: dict[str, object], + ) -> dict[str, object]: """ Add ResponsesAPIRequestParams schema to responses API endpoints for documentation. This shows the request body in Swagger without runtime validation. @@ -361,8 +364,8 @@ class CustomOpenAPISpec: @staticmethod def add_llm_api_request_schema_body( - openapi_schema: dict[str, Any], - ) -> dict[str, Any]: + openapi_schema: dict[str, object], + ) -> dict[str, object]: """ Add LLM API request schema bodies to OpenAPI specification for documentation. diff --git a/litellm/proxy/container_endpoints/ownership.py b/litellm/proxy/container_endpoints/ownership.py index e582ddb36c7..a559ab49cfa 100644 --- a/litellm/proxy/container_endpoints/ownership.py +++ b/litellm/proxy/container_endpoints/ownership.py @@ -1,5 +1,7 @@ import json -from typing import Any, Final +from collections.abc import Mapping, Sequence +from collections.abc import Set as AbstractSet +from typing import TYPE_CHECKING, Any, Final, Protocol from fastapi import HTTPException @@ -15,6 +17,29 @@ from litellm.proxy.common_utils.resource_ownership import ( from litellm.repositories.table_repositories import ManagedObjectRepository from litellm.responses.utils import ResponsesAPIRequestUtils +if TYPE_CHECKING: + from litellm.proxy.utils import PrismaClient + + +class _ManagedObjectRow(Protocol): + model_object_id: str + unified_object_id: str | None + file_purpose: str | None + created_by: str | None + + +class _ManagedObjectTable(Protocol): + async def find_unique(self, *, where: Mapping[str, str]) -> _ManagedObjectRow | None: ... + + async def find_first(self, *, where: Mapping[str, str]) -> _ManagedObjectRow | None: ... + + async def find_many(self, *, where: Mapping[str, object]) -> Sequence[_ManagedObjectRow]: ... + + async def create(self, *, data: Mapping[str, str]) -> _ManagedObjectRow: ... + + async def update(self, *, where: Mapping[str, str], data: Mapping[str, str]) -> _ManagedObjectRow | None: ... + + CONTAINER_OBJECT_PURPOSE: Final = "container" # 60s LRU/TTL cache absorbs every container access check before it reaches @@ -39,7 +64,7 @@ _CONTAINER_STORED_ID_CACHE: Final = InMemoryCache(max_size_in_memory=10000, defa _ALLOWED_CONTAINER_IDS_CACHE: Final = InMemoryCache(max_size_in_memory=2048, default_ttl=60) -def _allowed_container_ids_cache_key(owner_scopes: list[str]) -> str: +def _allowed_container_ids_cache_key(owner_scopes: Sequence[str]) -> str: """JSON-encode the sorted scope list — using a separator like ``|`` would collide for any tenant whose user_id / team_id / org_id / api_key happens to contain the separator. JSON quoting escapes @@ -86,7 +111,7 @@ async def get_container_forwarding_params( return params -def _get_response_id(response: Any) -> str | None: +def _get_response_id(response: object) -> str | None: if response is None: return None if isinstance(response, dict): @@ -96,7 +121,7 @@ def _get_response_id(response: Any) -> str | None: return value if isinstance(value, str) else None -def _dump_response(response: Any) -> dict[str, Any]: +def _dump_response(response: Any) -> dict[str, object]: if isinstance(response, dict): return dict(response) if hasattr(response, "model_dump"): @@ -106,17 +131,17 @@ def _dump_response(response: Any) -> dict[str, Any]: return {"id": _get_response_id(response)} -async def _get_prisma_client(): +async def _get_prisma_client() -> "PrismaClient | None": from litellm.proxy.proxy_server import prisma_client return prisma_client def _custom_llm_provider_from_responses_response( - response: Any, + response: object, default: str = "openai", ) -> str: - hidden_params: dict[str, Any] = {} + hidden_params: Mapping[str, object] = {} if isinstance(response, dict): hidden_params = response.get("_hidden_params") or {} else: @@ -129,7 +154,7 @@ def _custom_llm_provider_from_responses_response( async def record_container_owners_from_responses_response( - response: Any, + response: object, user_api_key_dict: UserAPIKeyAuth, custom_llm_provider: str | None = None, ) -> None: @@ -160,10 +185,10 @@ async def record_container_owners_from_responses_response( async def record_container_owner( - response: Any, + response: object, user_api_key_dict: UserAPIKeyAuth, custom_llm_provider: str, -) -> Any: +) -> object: container_id: Final = _get_response_id(response) if container_id is None: verbose_proxy_logger.warning("Skipping container ownership tracking because provider response has no id") @@ -195,7 +220,7 @@ async def record_container_owner( verbose_proxy_logger.warning("Skipping container ownership tracking because prisma_client is None") return response - table: Final = ManagedObjectRepository(prisma_client).table + table: Final[_ManagedObjectTable] = ManagedObjectRepository(prisma_client).table existing: Final = await table.find_unique(where={"model_object_id": model_object_id}) if existing is not None: if getattr(existing, "file_purpose", None) != CONTAINER_OBJECT_PURPOSE: @@ -247,15 +272,16 @@ async def _get_container_owner(original_container_id: str, custom_llm_provider: if prisma_client is None: return None - row: Final = await ManagedObjectRepository(prisma_client).table.find_first( + table: Final[_ManagedObjectTable] = ManagedObjectRepository(prisma_client).table + row: Final[_ManagedObjectRow | None] = await table.find_first( where={ "model_object_id": model_object_id, "file_purpose": CONTAINER_OBJECT_PURPOSE, } ) - owner: Final = getattr(row, "created_by", None) if row is not None else None + owner: Final[str | None] = getattr(row, "created_by", None) if row is not None else None _CONTAINER_OWNER_CACHE.set_cache(model_object_id, owner if owner is not None else _NEGATIVE_OWNER_SENTINEL) - stored_id: Final = getattr(row, "unified_object_id", None) if row is not None else None + stored_id: Final[str | None] = getattr(row, "unified_object_id", None) if row is not None else None _CONTAINER_STORED_ID_CACHE.set_cache( model_object_id, (stored_id if isinstance(stored_id, str) and stored_id else _NEGATIVE_STORED_ID_SENTINEL), @@ -283,13 +309,14 @@ async def _get_stored_container_id(original_container_id: str, custom_llm_provid if prisma_client is None: return None - row: Final = await ManagedObjectRepository(prisma_client).table.find_first( + table: Final[_ManagedObjectTable] = ManagedObjectRepository(prisma_client).table + row: Final[_ManagedObjectRow | None] = await table.find_first( where={ "model_object_id": model_object_id, "file_purpose": CONTAINER_OBJECT_PURPOSE, } ) - stored_id: Final = getattr(row, "unified_object_id", None) if row is not None else None + stored_id: Final[str | None] = getattr(row, "unified_object_id", None) if row is not None else None _CONTAINER_STORED_ID_CACHE.set_cache( model_object_id, (stored_id if isinstance(stored_id, str) and stored_id else _NEGATIVE_STORED_ID_SENTINEL), @@ -317,7 +344,7 @@ async def assert_user_can_access_container( return original_container_id, resolved_provider -def _get_container_list_data(response: Any) -> list[Any] | None: +def _get_container_list_data(response: object) -> Sequence[object] | None: if response is None: return None if isinstance(response, dict): @@ -327,7 +354,7 @@ def _get_container_list_data(response: Any) -> list[Any] | None: return data if isinstance(data, list) else None -def _set_container_list_data(response: Any, data: list[Any], removed_filtered_items: bool = False) -> Any: +def _set_container_list_data(response: Any, data: list[object], removed_filtered_items: bool = False) -> object: if isinstance(response, dict): response["data"] = data if data: @@ -353,7 +380,7 @@ def _set_container_list_data(response: Any, data: list[Any], removed_filtered_it async def _get_allowed_container_ids( user_api_key_dict: UserAPIKeyAuth, -) -> set[str]: +) -> AbstractSet[str]: owner_scopes: Final = get_resource_owner_scopes(user_api_key_dict) if not owner_scopes: return set() @@ -367,7 +394,8 @@ async def _get_allowed_container_ids( if prisma_client is None: return set() - rows: Final = await ManagedObjectRepository(prisma_client).table.find_many( + table: Final[_ManagedObjectTable] = ManagedObjectRepository(prisma_client).table + rows: Final[Sequence[_ManagedObjectRow]] = await table.find_many( where={ "file_purpose": CONTAINER_OBJECT_PURPOSE, "created_by": {"in": owner_scopes}, @@ -382,10 +410,10 @@ async def _get_allowed_container_ids( async def filter_container_list_response( - response: Any, + response: object, user_api_key_dict: UserAPIKeyAuth, custom_llm_provider: str, -) -> Any: +) -> object: if is_proxy_admin(user_api_key_dict): return response @@ -394,7 +422,7 @@ async def filter_container_list_response( return response allowed_container_ids: Final = await _get_allowed_container_ids(user_api_key_dict) - filtered: Final[list[Any]] = [] + filtered: Final[list[object]] = [] for item in data: container_id = _get_response_id(item) if container_id is None: diff --git a/litellm/proxy/guardrails/guardrail_hooks/bedrock_guardrails.py b/litellm/proxy/guardrails/guardrail_hooks/bedrock_guardrails.py index f7a5c7559b1..e9e729fb118 100644 --- a/litellm/proxy/guardrails/guardrail_hooks/bedrock_guardrails.py +++ b/litellm/proxy/guardrails/guardrail_hooks/bedrock_guardrails.py @@ -26,6 +26,9 @@ from litellm.caching import DualCache from litellm.exceptions import ModifyResponseException from litellm.integrations.custom_guardrail import CustomGuardrail from litellm.litellm_core_utils.core_helpers import redact_nested_match_and_regex_keys +from litellm.llms.base_llm.guardrail_translation.utils import ( + effective_scan_only_tool_results_for_guardrail, +) from litellm.llms.bedrock.base_aws_llm import BaseAWSLLM from litellm.llms.custom_httpx.http_handler import ( get_async_httpx_client, @@ -402,6 +405,9 @@ class BedrockGuardrail(CustomGuardrail, BaseAWSLLM): grounding.append(block) return grounding + def supports_scan_only_tool_results(self) -> bool: + return self.experimental_use_latest_role_message_only is not True + def _prepare_guardrail_messages_for_role( self, messages: list[AllMessageValues] | None, @@ -523,6 +529,11 @@ class BedrockGuardrail(CustomGuardrail, BaseAWSLLM): latest_user_index: Final = self._find_latest_message_index(structured_messages, target_role="user") if latest_user_index is None: + if effective_scan_only_tool_results_for_guardrail(self): + verbose_proxy_logger.warning( + "Bedrock Guardrail: experimental_use_latest_role_message_only scans only the latest " + "user message, so scan_only_tool_results leaves nothing to scan for this request" + ) verbose_proxy_logger.debug("Bedrock Guardrail: no user-role message in request, skipping INPUT scan") return ApplyGuardrailMessageSelection(None, None, True, skip_scan=True) diff --git a/litellm/proxy/guardrails/guardrail_hooks/cato_networks/cato_networks.py b/litellm/proxy/guardrails/guardrail_hooks/cato_networks/cato_networks.py index c5481c9ce63..958f84e18de 100644 --- a/litellm/proxy/guardrails/guardrail_hooks/cato_networks/cato_networks.py +++ b/litellm/proxy/guardrails/guardrail_hooks/cato_networks/cato_networks.py @@ -9,11 +9,13 @@ import contextlib import json import os import ssl -from collections.abc import AsyncGenerator +from collections.abc import AsyncGenerator, AsyncIterable, Mapping, Sequence +from ssl import SSLContext from typing import TYPE_CHECKING, Any, Final from fastapi import HTTPException from pydantic import BaseModel +from typing_extensions import NotRequired, TypedDict from websockets.asyncio.client import ClientConnection, connect from websockets.exceptions import ConnectionClosed @@ -35,8 +37,8 @@ from litellm.types.guardrails import GuardrailEventHooks from litellm.types.utils import ( CallTypesLiteral, Choices, - EmbeddingResponse, - ImageResponse, + LLMResponseTypes, + Message, ModelResponse, ModelResponseStream, ResponsesAPIResponse, @@ -50,6 +52,44 @@ class CatoNetworksGuardrailMissingSecrets(Exception): pass +class _WsSslKwargs(TypedDict, total=False): + ssl: bool | str | SSLContext + + +class _CatoRequiredAction(TypedDict, total=False): + action_type: str + detection_message: str + + +class _CatoRedactedMessage(TypedDict): + role: NotRequired[str] + content: str | None + + +class _CatoRedactedChat(TypedDict, total=False): + all_redacted_messages: Sequence[_CatoRedactedMessage] + + +class _CatoAnalysisResult(TypedDict, total=False): + policy_drill_down: Mapping[str, object] + + +class _CatoAnalyzeResponse(TypedDict): + required_action: NotRequired[_CatoRequiredAction | None] + analysis_result: NotRequired[_CatoAnalysisResult] + redacted_chat: NotRequired[_CatoRedactedChat] + + +class _CatoOutputRedaction(TypedDict): + redacted_output: str + + +class _CatoStreamMessage(TypedDict, total=False): + verified_chunk: Mapping[str, object] + done: bool + blocking_message: str + + class CatoNetworksGuardrail(CustomGuardrail): @classmethod def get_supported_event_hooks(cls) -> list[GuardrailEventHooks]: @@ -80,7 +120,7 @@ class CatoNetworksGuardrail(CustomGuardrail): super().__init__(**kwargs) @staticmethod - def _build_ws_ssl_kwargs(ssl_verify: bool | str | None, ws_api_base: str) -> dict: + def _build_ws_ssl_kwargs(ssl_verify: bool | str | None, ws_api_base: str) -> _WsSslKwargs: """Resolve the ``ssl`` argument for ``websockets.connect``. Mirrors the ``ssl_verify`` handling applied to the HTTP handler so a custom Cato instance behind TLS honours the same verification settings for streaming.""" @@ -156,7 +196,7 @@ class CatoNetworksGuardrail(CustomGuardrail): return flattened @staticmethod - def _prompt_inspection_messages(prompt: Any) -> list: + def _prompt_inspection_messages(prompt: object) -> Sequence[Mapping[str, str]]: """Synthetic user messages for a legacy completion ``prompt`` (a string or a list of string prompts).""" if isinstance(prompt, str): @@ -166,7 +206,7 @@ class CatoNetworksGuardrail(CustomGuardrail): return [] @staticmethod - def _iter_schema_string_refs(data: dict): + def _iter_schema_string_refs(data: Mapping[str, Any]): """Yield ``(container, key)`` for every non-empty schema string the proxy forwards to the model inside tool/function and structured-output schemas: each ``tools[].function`` and legacy ``functions[]`` entry plus the @@ -208,7 +248,7 @@ class CatoNetworksGuardrail(CustomGuardrail): stack.extend(reversed(node)) @classmethod - def _extra_inspection_sources(cls, data: dict) -> list: + def _extra_inspection_sources(cls, data: Mapping[str, Any]) -> Sequence[tuple[str, Sequence[Mapping[str, str]]]]: """Text the proxy forwards to the model outside chat ``messages``: Responses-API ``input`` and ``instructions``, legacy completion ``prompt`` and tool/function/``response_format`` schema strings. Returned @@ -251,7 +291,7 @@ class CatoNetworksGuardrail(CustomGuardrail): json={"messages": self._inspection_messages(data)}, ) response.raise_for_status() - res: Final = response.json() + res: Final[_CatoAnalyzeResponse] = response.json() required_action: Final = res.get("required_action") action_type: Final = required_action and required_action.get("action_type", None) if action_type is None: @@ -267,7 +307,11 @@ class CatoNetworksGuardrail(CustomGuardrail): verbose_proxy_logger.error("Cato: %s action", action_type) return data - def _handle_block_action(self, analysis_result: Any, required_action: Any) -> None: + def _handle_block_action( + self, + analysis_result: _CatoAnalysisResult, + required_action: Any, + ) -> None: detection_message: Final = required_action.get("detection_message", None) verbose_proxy_logger.info( "Cato: Violation detected enabled policies: {policies}".format( @@ -348,7 +392,7 @@ class CatoNetworksGuardrail(CustomGuardrail): hook: str, key_alias: str | None, user_email: str | None = None, - ) -> dict | None: + ) -> _CatoOutputRedaction | None: call_id: Final = request_data.get("litellm_call_id") inspection_messages: Final = self._inspection_messages(request_data) assistant_index: Final = len(inspection_messages) @@ -363,7 +407,7 @@ class CatoNetworksGuardrail(CustomGuardrail): json={"messages": inspection_messages + [{"role": "assistant", "content": output}]}, ) response.raise_for_status() - res: Final = response.json() + res: Final[_CatoAnalyzeResponse] = response.json() required_action: Final = res.get("required_action") action_type: Final = required_action and required_action.get("action_type", None) if action_type and action_type == "block_action": @@ -378,7 +422,11 @@ class CatoNetworksGuardrail(CustomGuardrail): return {"redacted_output": redacted_output} return None - def _handle_block_action_on_output(self, analysis_result: Any, required_action: Any) -> None: + def _handle_block_action_on_output( + self, + analysis_result: _CatoAnalysisResult, + required_action: Any, + ) -> None: detection_message: Final = required_action.get("detection_message", None) verbose_proxy_logger.info( "Cato: detected: {detected}, enabled policies: {policies}".format( @@ -422,7 +470,7 @@ class CatoNetworksGuardrail(CustomGuardrail): ) @staticmethod - def _output_fragments(message: Any) -> list: + def _output_fragments(message: Message) -> Sequence[tuple[tuple[str, int | None], str]]: """Assistant text the proxy returns to the caller: ``content`` plus every ``tool_calls[].function.arguments`` string, each tagged with where a redaction must be written back. ``content`` is only included when present @@ -439,7 +487,7 @@ class CatoNetworksGuardrail(CustomGuardrail): return fragments @staticmethod - def _apply_output_fragment(message: Any, target: tuple, redacted: str) -> None: + def _apply_output_fragment(message: Any, target: tuple[str, int | None], redacted: str) -> None: kind, idx = target if kind == "content": message.content = redacted @@ -447,11 +495,11 @@ class CatoNetworksGuardrail(CustomGuardrail): message.tool_calls[idx].function.arguments = redacted @staticmethod - def _responses_output_field(item: Any, key: str) -> Any: + def _responses_output_field(item: object, key: str) -> str | Sequence[object] | None: return item.get(key) if isinstance(item, dict) else getattr(item, key, None) @classmethod - def _responses_output_fragments(cls, response: ResponsesAPIResponse) -> list: + def _responses_output_fragments(cls, response: ResponsesAPIResponse) -> Sequence[tuple[object, str, str]]: """Assistant text the Responses API returns to the caller: every ``output_text`` content block plus every function-call ``arguments`` string, each paired with the ``(container, key)`` a Cato redaction is @@ -474,7 +522,7 @@ class CatoNetworksGuardrail(CustomGuardrail): return fragments @staticmethod - def _apply_responses_output_fragment(container: Any, key: str, redacted: str) -> None: + def _apply_responses_output_fragment(container: object, key: str, redacted: str) -> None: if isinstance(container, dict): container[key] = redacted else: @@ -505,8 +553,8 @@ class CatoNetworksGuardrail(CustomGuardrail): self, data: dict, user_api_key_dict: UserAPIKeyAuth, - response: Any | ModelResponse | EmbeddingResponse | ImageResponse, - ) -> Any: + response: LLMResponseTypes, + ) -> LLMResponseTypes: user_email: Final = self._resolve_cato_user_email(user_api_key_dict) if isinstance(response, ModelResponse) and response.choices: for choice in response.choices: @@ -526,7 +574,7 @@ class CatoNetworksGuardrail(CustomGuardrail): async def async_post_call_streaming_iterator_hook( self, user_api_key_dict: UserAPIKeyAuth, - response, + response: AsyncIterable[object], request_data: dict, ) -> AsyncGenerator[ModelResponseStream, None]: from litellm.proxy.proxy_server import StreamingCallbackError @@ -547,7 +595,7 @@ class CatoNetworksGuardrail(CustomGuardrail): try: while True: raw_message = await self._await_cato_message(websocket, sender) - result = json.loads(raw_message) + result: _CatoStreamMessage = json.loads(raw_message) if verified_chunk := result.get("verified_chunk"): yield ModelResponseStream.model_validate(verified_chunk) continue @@ -560,7 +608,7 @@ class CatoNetworksGuardrail(CustomGuardrail): finally: await self._cancel_background_task(sender) - async def _await_cato_message(self, websocket: ClientConnection, sender: asyncio.Task) -> Any: + async def _await_cato_message(self, websocket: ClientConnection, sender: asyncio.Task[None]) -> str | bytes: """Wait for the next Cato message, surfacing a dead forwarding task instead of blocking.""" from litellm.proxy.proxy_server import StreamingCallbackError @@ -578,7 +626,7 @@ class CatoNetworksGuardrail(CustomGuardrail): async def forward_the_stream_to_cato( self, websocket: ClientConnection, - response_iter: AsyncGenerator[Any, None], + response_iter: AsyncIterable[object], ) -> None: async for chunk in response_iter: if isinstance(chunk, BaseModel): diff --git a/litellm/proxy/guardrails/guardrail_hooks/crowdstrike_aidr/crowdstrike_aidr.py b/litellm/proxy/guardrails/guardrail_hooks/crowdstrike_aidr/crowdstrike_aidr.py index 15ddd5e3458..b1bf9159607 100644 --- a/litellm/proxy/guardrails/guardrail_hooks/crowdstrike_aidr/crowdstrike_aidr.py +++ b/litellm/proxy/guardrails/guardrail_hooks/crowdstrike_aidr/crowdstrike_aidr.py @@ -362,6 +362,10 @@ class CrowdStrikeAIDRHandler(CustomGuardrail): tail: Final = guard_output.messages[-num_assistant_messages:] if num_assistant_messages > 0 else [] return [_extract_text_from_message(msg) for msg in tail] + @override + def structured_messages_cover_full_request(self) -> bool: + return effective_skip_system_message_for_guardrail(self) or effective_skip_tool_message_for_guardrail(self) + def _writeback_messages( self, structured_messages: list[AllMessageValues], diff --git a/litellm/proxy/guardrails/guardrail_hooks/hiddenlayer/hiddenlayer.py b/litellm/proxy/guardrails/guardrail_hooks/hiddenlayer/hiddenlayer.py index 131ce5f9392..ca84ff47884 100644 --- a/litellm/proxy/guardrails/guardrail_hooks/hiddenlayer/hiddenlayer.py +++ b/litellm/proxy/guardrails/guardrail_hooks/hiddenlayer/hiddenlayer.py @@ -1,7 +1,8 @@ from __future__ import annotations import os -from typing import TYPE_CHECKING, Any, Final, Literal +from collections.abc import Mapping, Sequence +from typing import TYPE_CHECKING, Any, Final, Literal, TypedDict from urllib.parse import urlparse from uuid import uuid4 @@ -29,9 +30,31 @@ from litellm.types.proxy.guardrails.guardrail_hooks.hiddenlayer import ( from litellm.types.utils import GenericGuardrailAPIInputs if TYPE_CHECKING: + from pydantic import BaseModel + from litellm.types.proxy.guardrails.guardrail_hooks.base import GuardrailConfigModel +class _HiddenlayerEvaluation(TypedDict, total=False): + action: str + threat_level: str + + +class _HiddenlayerAnalysisEntry(TypedDict, total=False): + name: str + detected: bool + + +class _HiddenlayerModifiedSide(TypedDict): + messages: Any + + +class _HiddenlayerResponse(TypedDict, total=False): + evaluation: _HiddenlayerEvaluation + analysis: Sequence[_HiddenlayerAnalysisEntry] + modified_data: Mapping[str, _HiddenlayerModifiedSide] + + def is_saas(host: str) -> bool: """Checks whether the connection is to the SaaS platform""" @@ -43,7 +66,7 @@ def is_saas(host: str) -> bool: return False -def _get_jwt(auth_url, api_id, api_key): +def _get_jwt(auth_url, api_id, api_key) -> str: token_url: Final = f"{auth_url}/oauth2/token?grant_type=client_credentials" resp: Final = requests.post(token_url, auth=HTTPBasicAuth(api_id, api_key)) @@ -139,7 +162,7 @@ class HiddenlayerGuardrail(CustomGuardrail): if scan_params := inputs.get("structured_messages"): last_msg: Final = scan_params[-1] - result = await self._call_hiddenlayer( + result: _HiddenlayerResponse = await self._call_hiddenlayer( project_id, hl_request_metadata, { @@ -205,11 +228,11 @@ class HiddenlayerGuardrail(CustomGuardrail): async def _call_hiddenlayer( self, project_id: str | None, - metadata: dict[str, str], - payload: dict[str, Any], + metadata: Mapping[str, str], + payload: Mapping[str, Sequence[Mapping[str, str]]], input_type: Literal["request", "response"], - ) -> dict[str, Any]: - data: Final[dict[str, Any]] = {"metadata": metadata} + ) -> _HiddenlayerResponse: + data: Final[dict[str, object]] = {"metadata": metadata} if input_type == "request": data["input"] = payload @@ -235,7 +258,7 @@ class HiddenlayerGuardrail(CustomGuardrail): headers=headers, ) response.raise_for_status() - result = response.json() + result: _HiddenlayerResponse = response.json() verbose_proxy_logger.debug("Hiddenlayer reponse: %s", result) @@ -265,7 +288,7 @@ class HiddenlayerGuardrail(CustomGuardrail): return result @staticmethod - def get_config_model() -> type[GuardrailConfigModel] | None: + def get_config_model() -> type[GuardrailConfigModel[BaseModel]] | None: from litellm.types.proxy.guardrails.guardrail_hooks.hiddenlayer import ( HiddenlayerGuardrailConfigModel, ) @@ -343,7 +366,7 @@ class HiddenlayerGuardrailV2(CustomGuardrail): if "hl-requester-id" not in hl_headers: hl_headers["hl-requester-id"] = "LiteLLM" - payload: Any + payload: object if input_type == "request": payload = { "messages": inputs.get("structured_messages"), @@ -461,7 +484,7 @@ class HiddenlayerGuardrailV2(CustomGuardrail): return response @staticmethod - def get_config_model() -> type[GuardrailConfigModel] | None: + def get_config_model() -> type[GuardrailConfigModel[BaseModel]] | None: from litellm.types.proxy.guardrails.guardrail_hooks.hiddenlayer import ( HiddenlayerGuardrailConfigModel, ) diff --git a/litellm/proxy/guardrails/guardrail_hooks/microsoft_purview/base.py b/litellm/proxy/guardrails/guardrail_hooks/microsoft_purview/base.py index 4ae29ade0d7..3f666178970 100644 --- a/litellm/proxy/guardrails/guardrail_hooks/microsoft_purview/base.py +++ b/litellm/proxy/guardrails/guardrail_hooks/microsoft_purview/base.py @@ -2,8 +2,11 @@ import threading import time import uuid from collections import OrderedDict +from collections.abc import Mapping, Sequence from typing import TYPE_CHECKING, Any, Final +from typing_extensions import NotRequired, TypedDict + from litellm._logging import verbose_proxy_logger from litellm.litellm_core_utils.prompt_templates.common_utils import ( convert_content_list_to_str, @@ -15,6 +18,7 @@ from litellm.llms.custom_httpx.http_handler import ( ) if TYPE_CHECKING: + from litellm.proxy._types import UserAPIKeyAuth from litellm.types.llms.openai import AllMessageValues GRAPH_API_BASE: Final = "https://graph.microsoft.com/v1.0" @@ -25,6 +29,11 @@ GRAPH_SCOPE: Final = "https://graph.microsoft.com/.default" SCOPE_CACHE_TTL_SECONDS: Final = 3600.0 +class GraphTokenResponse(TypedDict): + access_token: str + expires_in: NotRequired[int] + + class PurviewGuardrailBase: """ Base class for Microsoft Purview guardrails. @@ -41,8 +50,8 @@ class PurviewGuardrailBase: client_secret: str, purview_app_name: str = "LiteLLM", user_id_field: str = "user_id", - **kwargs: Any, - ): + **kwargs: object, + ) -> None: # Forward remaining kwargs to the next class in the MRO # (typically CustomGuardrail). super().__init__(**kwargs) @@ -59,7 +68,7 @@ class PurviewGuardrailBase: # Protection scope cache: user_id -> (etag, scope_response, fetched_at) # Capped at 1000 entries (LRU eviction) to avoid unbounded growth. - self._scope_cache: OrderedDict[str, tuple[str, dict[str, Any], float]] = OrderedDict() + self._scope_cache: OrderedDict[str, tuple[str, Mapping[str, object], float]] = OrderedDict() self._scope_cache_maxsize = 1000 # Use a threading.Lock (not asyncio.Lock) because this lock is acquired # from both the proxy's main asyncio event loop and from short-lived @@ -100,7 +109,7 @@ class PurviewGuardrailBase: headers={"Content-Type": "application/x-www-form-urlencoded"}, ) response.raise_for_status() - token_data: Final = response.json() + token_data: Final[GraphTokenResponse] = response.json() access_token: Final = token_data["access_token"] expires_in: Final = int(token_data.get("expires_in", 3599)) # Recompute ``now`` after the await so the expiry reflects when the @@ -117,9 +126,9 @@ class PurviewGuardrailBase: async def _graph_post( self, url: str, - json_body: dict[str, Any], - extra_headers: dict[str, str] | None = None, - ) -> tuple[dict[str, Any], dict[str, str]]: + json_body: dict[str, object], + extra_headers: Mapping[str, str] | None = None, + ) -> tuple[dict[str, object], dict[str, str]]: """POST to Graph API with bearer auth. Returns: @@ -136,7 +145,7 @@ class PurviewGuardrailBase: verbose_proxy_logger.debug("Purview Graph POST %s", url) response: Final = await self.async_handler.post(url=url, headers=headers, json=json_body) response.raise_for_status() - response_json: Final[dict[str, Any]] = response.json() + response_json: Final[dict[str, object]] = response.json() response_headers: Final = dict(response.headers) verbose_proxy_logger.debug("Purview Graph response: %s", response_json) return response_json, response_headers @@ -145,7 +154,7 @@ class PurviewGuardrailBase: # Protection scopes # ------------------------------------------------------------------ - async def _compute_protection_scopes(self, user_id: str) -> tuple[str, dict[str, Any]]: + async def _compute_protection_scopes(self, user_id: str) -> tuple[str, Mapping[str, object]]: """Call protectionScopes/compute and cache with ETag. Returns: @@ -161,7 +170,7 @@ class PurviewGuardrailBase: return cached[0], cached[1] url: Final = f"{GRAPH_API_BASE}/users/{encoded_user_id}/dataSecurityAndGovernance/protectionScopes/compute" - body: Final[dict[str, Any]] = { + body: Final[dict[str, object]] = { "activities": "uploadText,downloadText", "locations": [ { @@ -199,7 +208,7 @@ class PurviewGuardrailBase: activity: str, etag: str, correlation_id: str | None = None, - ) -> dict[str, Any]: + ) -> dict[str, object]: """Call processContent for DLP policy evaluation. Args: @@ -211,7 +220,7 @@ class PurviewGuardrailBase: """ encoded_user_id: Final = self._encode_graph_user_id(user_id) url: Final = f"{GRAPH_API_BASE}/users/{encoded_user_id}/dataSecurityAndGovernance/processContent" - body: Final[dict[str, Any]] = { + body: Final[dict[str, object]] = { "contentToProcess": { "contentEntries": [ { @@ -261,7 +270,7 @@ class PurviewGuardrailBase: # User ID resolution # ------------------------------------------------------------------ - def _resolve_user_id(self, data: dict[str, Any], user_api_key_dict: Any) -> str | None: + def _resolve_user_id(self, data: Mapping[str, object], user_api_key_dict: "UserAPIKeyAuth") -> str | None: """Resolve the Entra user object ID from request data or auth context. Returns the strongest available identity walking down four sources, in @@ -284,7 +293,10 @@ class PurviewGuardrailBase: if hasattr(user_api_key_dict, "end_user_id") and user_api_key_dict.end_user_id: return str(user_api_key_dict.end_user_id) - metadata: Final = data.get("metadata") or data.get("litellm_metadata") or {} + metadata_value: Final[object] = data.get("metadata") or data.get("litellm_metadata") or {} + if not isinstance(metadata_value, Mapping): + return None + metadata: Final[Mapping[str, object]] = metadata_value uid = metadata.get("user_api_key_user_id") if uid: return str(uid) @@ -296,15 +308,15 @@ class PurviewGuardrailBase: return None @staticmethod - def _logging_kwargs_metadata(kwargs: dict[str, Any]) -> dict[str, Any]: + def _logging_kwargs_metadata(kwargs: Mapping[str, object]) -> Mapping[str, object]: """Metadata dict from ``model_call_details`` / logging kwargs.""" - litellm_params: Final = kwargs.get("litellm_params") or {} + litellm_params: Final[object] = kwargs.get("litellm_params") or {} if not isinstance(litellm_params, dict): return {} md: Final = litellm_params.get("metadata") return md if isinstance(md, dict) else {} - def _resolve_trusted_user_id(self, data: dict[str, Any], user_api_key_dict: Any) -> str | None: + def _resolve_trusted_user_id(self, data: Mapping[str, object], user_api_key_dict: "UserAPIKeyAuth") -> str | None: """Resolve user ID from API-key/JWT-bound identity for blocking DLP. Uses only ``UserAPIKeyAuth.user_id`` (bound on the LiteLLM key or JWT). @@ -325,7 +337,7 @@ class PurviewGuardrailBase: return None - def _resolve_user_id_from_logging_kwargs(self, kwargs: dict[str, Any]) -> str | None: + def _resolve_user_id_from_logging_kwargs(self, kwargs: Mapping[str, object]) -> str | None: """Trusted-identity-only resolver for logging-only hooks. Uses only the proxy-injected ``user_api_key_user_id`` (populated from @@ -365,7 +377,7 @@ class PurviewGuardrailBase: # ------------------------------------------------------------------ @staticmethod - def is_token_id_prompt(prompt: Any) -> bool: + def is_token_id_prompt(prompt: str | Sequence[object] | None) -> bool: """Return True if ``prompt`` carries OpenAI completions token ids. Covers every list shape that ``completion_prompt_to_str`` cannot decode @@ -383,7 +395,7 @@ class PurviewGuardrailBase: return False @staticmethod - def completion_prompt_to_str(prompt: Any) -> str | None: + def completion_prompt_to_str(prompt: str | Sequence[object] | None) -> str | None: """Normalize OpenAI ``/v1/completions`` ``prompt`` for text DLP. Supports string prompts and list-of-string prompts. List-of-token-id prompts @@ -408,7 +420,7 @@ class PurviewGuardrailBase: return None @staticmethod - def _extract_tool_call_args_from_message(message: Any) -> list[str]: + def _extract_tool_call_args_from_message(message: object) -> list[str]: """Return plaintext arguments strings from tool_calls and function_call fields. Covers both the request path (assistant messages in chat histories that @@ -419,7 +431,9 @@ class PurviewGuardrailBase: args: Final[list[str]] = [] # tool_calls: [{"function": {"arguments": "..."}}] - tool_calls = message.get("tool_calls") if isinstance(message, dict) else getattr(message, "tool_calls", None) + tool_calls: Final[Sequence[object] | None] = ( + message.get("tool_calls") if isinstance(message, dict) else getattr(message, "tool_calls", None) + ) if tool_calls: for tc in tool_calls: fn = tc.get("function") if isinstance(tc, dict) else getattr(tc, "function", None) diff --git a/litellm/proxy/guardrails/guardrail_hooks/panw_prisma_airs/panw_prisma_airs.py b/litellm/proxy/guardrails/guardrail_hooks/panw_prisma_airs/panw_prisma_airs.py index ae1478a9210..13ced0ac06c 100644 --- a/litellm/proxy/guardrails/guardrail_hooks/panw_prisma_airs/panw_prisma_airs.py +++ b/litellm/proxy/guardrails/guardrail_hooks/panw_prisma_airs/panw_prisma_airs.py @@ -22,6 +22,9 @@ from litellm.integrations.custom_guardrail import ( CustomGuardrail, log_guardrail_information, ) +from litellm.llms.base_llm.guardrail_translation.utils import ( + effective_scan_only_tool_results_for_guardrail, +) from litellm.llms.custom_httpx.http_handler import ( get_async_httpx_client, httpxSpecialProvider, @@ -1561,6 +1564,9 @@ class PanwPrismaAirsHandler(CustomGuardrail): return scannable + def supports_scan_only_tool_results(self) -> bool: + return False + @staticmethod def _get_scannable_text_indices( texts: list[str], @@ -1716,6 +1722,15 @@ class PanwPrismaAirsHandler(CustomGuardrail): # - latest-user extraction returned None (no user / count mismatch) if scannable_indices is None: scannable_indices = self._get_scannable_text_indices(texts, structured_messages) + if ( + scannable_indices is not None + and not scannable_indices + and effective_scan_only_tool_results_for_guardrail(self) + ): + verbose_proxy_logger.warning( + "PANW Prisma AIRS scans only user, system, and developer messages, " + "so scan_only_tool_results leaves nothing to scan for this request" + ) for i, text in enumerate(texts): if not text or not text.strip(): diff --git a/litellm/proxy/guardrails/guardrail_hooks/prompt_security/prompt_security.py b/litellm/proxy/guardrails/guardrail_hooks/prompt_security/prompt_security.py index 743ad888949..1a2c46f306c 100644 --- a/litellm/proxy/guardrails/guardrail_hooks/prompt_security/prompt_security.py +++ b/litellm/proxy/guardrails/guardrail_hooks/prompt_security/prompt_security.py @@ -74,6 +74,9 @@ class PromptSecurityGuardrail(CustomGuardrail): super().__init__(**kwargs) + def supports_scan_only_tool_results(self) -> bool: + return self.check_tool_results + @log_guardrail_information async def apply_guardrail( self, diff --git a/litellm/proxy/guardrails/guardrail_registry.py b/litellm/proxy/guardrails/guardrail_registry.py index f77588cf087..9f70ed63dcb 100644 --- a/litellm/proxy/guardrails/guardrail_registry.py +++ b/litellm/proxy/guardrails/guardrail_registry.py @@ -14,6 +14,10 @@ from litellm._logging import verbose_proxy_logger from litellm._uuid import uuid from litellm.integrations.custom_guardrail import CustomGuardrail from litellm.litellm_core_utils.safe_json_dumps import safe_dumps +from litellm.llms.base_llm.guardrail_translation.utils import ( + effective_scan_only_tool_results_for_guardrail, + effective_skip_tool_message_for_guardrail, +) from litellm.proxy.guardrails.guardrail_hooks.bedrock_guardrails import ( BedrockGuardrail, ) @@ -487,16 +491,27 @@ class InMemoryGuardrailHandler: raise ValueError(f"Unsupported guardrail: {guardrail_type}") if custom_guardrail_callback is not None: - setattr( - custom_guardrail_callback, + for scoping_param in ( "skip_system_message_in_guardrail", - getattr(litellm_params, "skip_system_message_in_guardrail", None), - ) - setattr( - custom_guardrail_callback, "skip_tool_message_in_guardrail", - getattr(litellm_params, "skip_tool_message_in_guardrail", None), + "scan_only_tool_results", + ): + setattr(custom_guardrail_callback, scoping_param, getattr(litellm_params, scoping_param, None)) + scan_only_tool_results_enabled: Final = effective_scan_only_tool_results_for_guardrail( + custom_guardrail_callback ) + if scan_only_tool_results_enabled and not custom_guardrail_callback.supports_scan_only_tool_results(): + raise ValueError( + f"Guardrail {guardrail['guardrail_name']}: scan_only_tool_results is enabled, but this " + "guardrail's role filtering never scans tool results, so no request content would ever " + "be scanned. Remove scan_only_tool_results or the guardrail's role-filtering option." + ) + if scan_only_tool_results_enabled and effective_skip_tool_message_for_guardrail(custom_guardrail_callback): + raise ValueError( + f"Guardrail {guardrail['guardrail_name']}: scan_only_tool_results and " + "skip_tool_message_in_guardrail are enabled together, which excludes every message from " + "scanning, so no request content would ever be scanned. Remove one of the two." + ) configured_run_in_parallel: Final = getattr(litellm_params, "run_in_parallel", None) if configured_run_in_parallel is not None: custom_guardrail_callback.run_in_parallel = bool(configured_run_in_parallel) diff --git a/litellm/proxy/hooks/proxy_track_cost_callback.py b/litellm/proxy/hooks/proxy_track_cost_callback.py index 01e18b00024..3346f9d7e3b 100644 --- a/litellm/proxy/hooks/proxy_track_cost_callback.py +++ b/litellm/proxy/hooks/proxy_track_cost_callback.py @@ -34,11 +34,17 @@ from litellm.types.utils import ( ) from litellm.utils import get_end_user_id_for_cost_tracking -_PASS_THROUGH_CALL_TYPES: Final[frozenset[str]] = frozenset( +_UNATTRIBUTED_TRACKABLE_CALL_TYPES: Final[frozenset[str]] = frozenset( { CallTypes.pass_through.value, CallTypes.llm_passthrough_route.value, CallTypes.allm_passthrough_route.value, + # CheckBatchCost's synthetic logging_obj for a completed managed batch only ever + # carries user_api_key_user_id (from LiteLLM_ManagedObjectTable.created_by) and + # user_api_key_team_id (from .team_id) -- both are None for batches created with + # the master key or a team-less key, since the table never stores the raw key + # hash. The batch already incurred real provider cost, so track it regardless. + CallTypes.aretrieve_batch.value, } ) @@ -440,6 +446,8 @@ def _should_track_cost_callback( the request with no key/user/team/end-user to attribute spend to. Those requests still forward real provider traffic that operators expect to see in request/usage logs, so they are tracked even when unauthenticated. + The same reasoning applies to a completed managed batch's cost event + (see _UNATTRIBUTED_TRACKABLE_CALL_TYPES). """ # don't run track cost callback if user opted into disabling spend @@ -448,7 +456,7 @@ def _should_track_cost_callback( if user_api_key is not None or user_id is not None or team_id is not None or end_user_id is not None: return True - return call_type in _PASS_THROUGH_CALL_TYPES + return call_type in _UNATTRIBUTED_TRACKABLE_CALL_TYPES def _get_budget_reservation_from_metadata(metadata: dict) -> dict | None: diff --git a/litellm/proxy/management_endpoints/workflow_management_endpoints.py b/litellm/proxy/management_endpoints/workflow_management_endpoints.py index 70a6cc507f5..eeb64ab2773 100644 --- a/litellm/proxy/management_endpoints/workflow_management_endpoints.py +++ b/litellm/proxy/management_endpoints/workflow_management_endpoints.py @@ -14,7 +14,8 @@ GET /v1/workflows/runs/{run_id}/messages - Fetch conversation history """ import json -from typing import Any, Final, Literal +from collections.abc import Mapping, Sequence +from typing import Final, Literal, Protocol, TypedDict from fastapi import APIRouter, Depends, HTTPException, Query @@ -43,7 +44,7 @@ router: Final = APIRouter() _MAX_SEQUENCE_RETRIES: Final = 5 -def _json(value: Any) -> str: +def _json(value: object) -> str: """Serialize a Python value for prisma-client-py Json fields (must be a string).""" return json.dumps(value) @@ -62,7 +63,7 @@ def _caller_key(user_api_key_dict: UserAPIKeyAuth) -> str | None: # Status transitions driven by event_type -_EVENT_STATUS_MAP: Final[dict[str, str]] = { +_EVENT_STATUS_MAP: Final[Mapping[str, str]] = { "step.started": "running", "step.failed": "failed", "hook.waiting": "paused", @@ -77,8 +78,8 @@ _EVENT_STATUS_MAP: Final[dict[str, str]] = { class WorkflowRunCreateRequest(BaseModel): workflow_type: str - input: dict[str, Any] | None = None - metadata: dict[str, Any] | None = None + input: Mapping[str, object] | None = None + metadata: Mapping[str, object] | None = None WorkflowRunStatus = Literal["pending", "running", "paused", "completed", "failed"] @@ -86,14 +87,14 @@ WorkflowRunStatus = Literal["pending", "running", "paused", "completed", "failed class WorkflowRunUpdateRequest(BaseModel): status: WorkflowRunStatus | None = None - output: dict[str, Any] | None = None - metadata: dict[str, Any] | None = None + output: Mapping[str, object] | None = None + metadata: Mapping[str, object] | None = None class WorkflowEventCreateRequest(BaseModel): event_type: str step_name: str - data: dict[str, Any] | None = None + data: Mapping[str, object] | None = None class WorkflowMessageCreateRequest(BaseModel): @@ -102,15 +103,60 @@ class WorkflowMessageCreateRequest(BaseModel): session_id: str | None = None +class _RunRow(Protocol): + @property + def created_by(self) -> str | None: ... + + +class _SeqRow(Protocol): + @property + def sequence_number(self) -> int: ... + + +class _RunCreateData(TypedDict, total=False): + workflow_type: str + created_by: str | None + input: str + metadata: str + + +class _RunWhere(TypedDict, total=False): + workflow_type: str + status: str | Mapping[str, Sequence[str]] + created_by: str + + +class _RunUpdateData(TypedDict, total=False): + status: WorkflowRunStatus + output: str + metadata: str + + +class _EventCreateData(TypedDict, total=False): + run_id: str + event_type: str + step_name: str + sequence_number: int + data: str + + +class _MessageCreateData(TypedDict, total=False): + run_id: str + role: str + content: str + sequence_number: int + session_id: str + + # --------------------------------------------------------------------------- # Helpers # --------------------------------------------------------------------------- -async def _get_next_sequence_number(prisma_client: Any, run_id: str, table: str) -> int: +async def _get_next_sequence_number(prisma_client: object, run_id: str, table: str) -> int: """Return MAX(sequence_number) + 1 for the given run, for either events or messages.""" if table == "events": - rows = await WorkflowEventRepository(prisma_client).table.find_many( + rows: Sequence[_SeqRow] = await WorkflowEventRepository(prisma_client).table.find_many( where={"run_id": run_id}, order={"sequence_number": "desc"}, take=1, @@ -125,12 +171,12 @@ async def _get_next_sequence_number(prisma_client: Any, run_id: str, table: str) async def _require_run( - prisma_client: Any, + prisma_client: object, run_id: str, user_api_key_dict: UserAPIKeyAuth | None = None, -) -> Any: +) -> _RunRow: """Return the run or raise 404. For non-admin callers, also enforce key ownership.""" - run: Final = await WorkflowRunRepository(prisma_client).table.find_unique(where={"run_id": run_id}) + run: Final[_RunRow | None] = await WorkflowRunRepository(prisma_client).table.find_unique(where={"run_id": run_id}) if run is None: raise HTTPException(status_code=404, detail=f"Run '{run_id}' not found") if user_api_key_dict is not None and not _is_admin(user_api_key_dict): @@ -165,7 +211,7 @@ async def create_workflow_run( raise HTTPException(status_code=500, detail=CommonProxyErrors.db_not_connected_error.value) try: - create_data: Final[dict[str, Any]] = { + create_data: Final[_RunCreateData] = { "workflow_type": data.workflow_type, "created_by": _caller_key(user_api_key_dict), } @@ -173,7 +219,7 @@ async def create_workflow_run( create_data["input"] = _json(data.input) if data.metadata is not None: create_data["metadata"] = _json(data.metadata) - run: Final = await WorkflowRunRepository(prisma_client).table.create(data=create_data) + run: Final[_RunRow] = await WorkflowRunRepository(prisma_client).table.create(data=create_data) return run except Exception as e: verbose_proxy_logger.exception("Error creating workflow run: %s", e) @@ -200,7 +246,7 @@ async def list_workflow_runs( if prisma_client is None: raise HTTPException(status_code=500, detail=CommonProxyErrors.db_not_connected_error.value) - where: Final[dict[str, Any]] = {} + where: Final[_RunWhere] = {} if workflow_type: where["workflow_type"] = workflow_type if status: @@ -214,7 +260,7 @@ async def list_workflow_runs( where["created_by"] = caller try: - runs: Final = await WorkflowRunRepository(prisma_client).table.find_many( + runs: Final[Sequence[object]] = await WorkflowRunRepository(prisma_client).table.find_many( where=where, order={"created_at": "desc"}, take=limit, @@ -241,7 +287,7 @@ async def get_workflow_run( raise HTTPException(status_code=500, detail=CommonProxyErrors.db_not_connected_error.value) try: - run: Final = await WorkflowRunRepository(prisma_client).table.find_unique( + run: Final[_RunRow | None] = await WorkflowRunRepository(prisma_client).table.find_unique( where={"run_id": run_id}, include={"events": {"order_by": {"sequence_number": "desc"}, "take": 1}}, ) @@ -275,7 +321,7 @@ async def update_workflow_run( if prisma_client is None: raise HTTPException(status_code=500, detail=CommonProxyErrors.db_not_connected_error.value) - update: Final[dict[str, Any]] = {} + update: Final[_RunUpdateData] = {} if data.status is not None: update["status"] = data.status if data.output is not None: @@ -290,7 +336,7 @@ async def update_workflow_run( await _require_run(prisma_client, run_id, user_api_key_dict) try: - run: Final = await WorkflowRunRepository(prisma_client).table.update( + run: Final[_RunRow | None] = await WorkflowRunRepository(prisma_client).table.update( where={"run_id": run_id}, data=update, ) @@ -332,7 +378,7 @@ async def append_workflow_event( for attempt in range(_MAX_SEQUENCE_RETRIES): try: seq = await _get_next_sequence_number(prisma_client, run_id, "events") - event_data: dict[str, Any] = { + event_data: _EventCreateData = { "run_id": run_id, "event_type": data.event_type, "step_name": data.step_name, @@ -342,7 +388,7 @@ async def append_workflow_event( event_data["data"] = _json(data.data) async with prisma_client.db.tx() as tx: - event = await tx.litellm_workflowevent.create(data=event_data) + event: object = await tx.litellm_workflowevent.create(data=event_data) if new_status: await tx.litellm_workflowrun.update( where={"run_id": run_id}, @@ -389,7 +435,7 @@ async def list_workflow_events( await _require_run(prisma_client, run_id, _read_scope_caller(user_api_key_dict)) try: - events: Final = await WorkflowEventRepository(prisma_client).table.find_many( + events: Final[Sequence[object]] = await WorkflowEventRepository(prisma_client).table.find_many( where={"run_id": run_id}, order={"sequence_number": "asc"}, take=limit, @@ -424,7 +470,7 @@ async def append_workflow_message( for attempt in range(_MAX_SEQUENCE_RETRIES): try: seq = await _get_next_sequence_number(prisma_client, run_id, "messages") - msg_data: dict[str, Any] = { + msg_data: _MessageCreateData = { "run_id": run_id, "role": data.role, "content": data.content, @@ -432,7 +478,7 @@ async def append_workflow_message( } if data.session_id is not None: msg_data["session_id"] = data.session_id - msg = await WorkflowMessageRepository(prisma_client).table.create(data=msg_data) + msg: object = await WorkflowMessageRepository(prisma_client).table.create(data=msg_data) return msg except Exception as e: @@ -473,7 +519,7 @@ async def list_workflow_messages( await _require_run(prisma_client, run_id, _read_scope_caller(user_api_key_dict)) try: - messages: Final = await WorkflowMessageRepository(prisma_client).table.find_many( + messages: Final[Sequence[object]] = await WorkflowMessageRepository(prisma_client).table.find_many( where={"run_id": run_id}, order={"sequence_number": "asc"}, take=limit, diff --git a/litellm/proxy/openai_files_endpoints/common_utils.py b/litellm/proxy/openai_files_endpoints/common_utils.py index 0f6494051cf..fce57e514c1 100644 --- a/litellm/proxy/openai_files_endpoints/common_utils.py +++ b/litellm/proxy/openai_files_endpoints/common_utils.py @@ -1148,7 +1148,7 @@ async def update_batch_in_database( managed_files_obj: The managed_files proxy hook object prisma_client: Prisma database client verbose_proxy_logger: Logger instance - db_batch_object: Optional existing database object (for comparison) + db_batch_object: Optional existing database object; fetched by unified_object_id when omitted operation: Description of operation ("update", "cancel", etc.) user_api_key_dict: Optional auth context for creating managed file IDs """ @@ -1161,6 +1161,12 @@ async def update_batch_in_database( if not prisma_client: return + effective_db_batch_object: Final = ( + db_batch_object + if db_batch_object is not None + else await ManagedObjectRepository(prisma_client).table.find_first(where={"unified_object_id": batch_id}) + ) + # Always normalize the response's file IDs to unified managed IDs # (mutates in place) so the caller returns unified IDs to the user # even when we skip the DB update below for an unchanged status. @@ -1170,16 +1176,17 @@ async def update_batch_in_database( prisma_client=prisma_client, verbose_proxy_logger=verbose_proxy_logger, user_api_key_dict=user_api_key_dict, - db_batch_object=db_batch_object, + db_batch_object=effective_db_batch_object, + unified_batch_id=unified_batch_id, ) # Only update if status has changed (when db_batch_object is provided) - if db_batch_object and response.status == db_batch_object.status: + if effective_db_batch_object and response.status == effective_db_batch_object.status: return - if db_batch_object: + if effective_db_batch_object: verbose_proxy_logger.info( - "Updating batch %s status from %s to %s", batch_id, db_batch_object.status, response.status + "Updating batch %s status from %s to %s", batch_id, effective_db_batch_object.status, response.status ) else: verbose_proxy_logger.info("Updating batch %s status to %s after %s", batch_id, response.status, operation) diff --git a/litellm/proxy/policy_engine/attachment_registry.py b/litellm/proxy/policy_engine/attachment_registry.py index 8ee1dd268e6..05df44242aa 100644 --- a/litellm/proxy/policy_engine/attachment_registry.py +++ b/litellm/proxy/policy_engine/attachment_registry.py @@ -6,7 +6,7 @@ This allows the same policy to be attached to multiple scopes. """ from datetime import datetime, timezone -from typing import TYPE_CHECKING, Any, Final +from typing import TYPE_CHECKING, Any, Final, TypedDict from litellm._logging import verbose_proxy_logger from litellm.repositories.table_repositories import PolicyAttachmentRepository @@ -18,9 +18,18 @@ from litellm.types.proxy.policy_engine import ( ) if TYPE_CHECKING: + from collections.abc import Sequence + + from prisma.models import LiteLLM_PolicyAttachmentTable + from litellm.proxy.utils import PrismaClient +class PolicyAttachmentMatch(TypedDict): + policy_name: str + matched_via: str + + class AttachmentRegistry: """ In-memory registry for storing and managing policy attachments. @@ -40,7 +49,7 @@ class AttachmentRegistry: ``` """ - def __init__(self): + def __init__(self) -> None: self._attachments: list[PolicyAttachment] = [] self._config_attachments: tuple[PolicyAttachment, ...] = () self._initialized: bool = False @@ -98,7 +107,7 @@ class AttachmentRegistry: """ return [r["policy_name"] for r in self.get_attached_policies_with_reasons(context)] - def get_attached_policies_with_reasons(self, context: PolicyMatchContext) -> list[dict[str, Any]]: + def get_attached_policies_with_reasons(self, context: PolicyMatchContext) -> list[PolicyAttachmentMatch]: """ Get list of policy names and match reasons for the given context. @@ -107,8 +116,8 @@ class AttachmentRegistry: """ from litellm.proxy.policy_engine.policy_matcher import PolicyMatcher - results: Final[list[dict[str, Any]]] = [] - seen_policies: Final[set] = set() + results: Final[list[PolicyAttachmentMatch]] = [] + seen_policies: Final[set[str]] = set() for attachment in self._attachments: scope = attachment.to_policy_scope() @@ -280,7 +289,9 @@ class AttachmentRegistry: PolicyAttachmentDBResponse with the created attachment """ try: - created_attachment: Final = await PolicyAttachmentRepository(prisma_client).table.create( + created_attachment: Final[LiteLLM_PolicyAttachmentTable] = await PolicyAttachmentRepository( + prisma_client + ).table.create( data={ "policy_name": attachment_request.policy_name, "scope": attachment_request.scope, @@ -340,9 +351,9 @@ class AttachmentRegistry: """ try: # Get attachment before deleting - attachment: Final = await PolicyAttachmentRepository(prisma_client).table.find_unique( - where={"attachment_id": attachment_id} - ) + attachment: Final[LiteLLM_PolicyAttachmentTable | None] = await PolicyAttachmentRepository( + prisma_client + ).table.find_unique(where={"attachment_id": attachment_id}) if attachment is None: raise Exception(f"Attachment with ID {attachment_id} not found") @@ -375,9 +386,9 @@ class AttachmentRegistry: PolicyAttachmentDBResponse if found, None otherwise """ try: - attachment: Final = await PolicyAttachmentRepository(prisma_client).table.find_unique( - where={"attachment_id": attachment_id} - ) + attachment: Final[LiteLLM_PolicyAttachmentTable | None] = await PolicyAttachmentRepository( + prisma_client + ).table.find_unique(where={"attachment_id": attachment_id}) if attachment is None: return None @@ -413,7 +424,9 @@ class AttachmentRegistry: List of PolicyAttachmentDBResponse objects """ try: - attachments: Final = await PolicyAttachmentRepository(prisma_client).table.find_many( + attachments: Final[Sequence[LiteLLM_PolicyAttachmentTable]] = await PolicyAttachmentRepository( + prisma_client + ).table.find_many( order={"created_at": "desc"}, ) diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py index 539b68c1aee..07eaed9fe45 100644 --- a/litellm/proxy/proxy_server.py +++ b/litellm/proxy/proxy_server.py @@ -3909,6 +3909,10 @@ class ProxyConfig: # whether an existing request predates the prices it just fetched, and re-serving one # costs a single fetch where skipping one leaves it priced wrong indefinitely self.model_cost_map_applied_revision: int = 0 + # Keys explicitly set in the YAML config file. Used to give YAML + # precedence over stale DB-cached values for these specific keys + # during periodic config reloads (_update_general_settings). + self._yaml_general_settings_keys: set[str] = set() # mutable-ok: populated once at startup, read-only thereafter # fmt: skip def is_yaml(self, config_file_path: str) -> bool: if not os.path.isfile(config_file_path): @@ -4839,6 +4843,11 @@ class ProxyConfig: _hc_staleness = None _hc_ignore_transient = False if general_settings: + # Record which keys were explicitly set in the YAML config file. + # These keys take precedence over DB-cached values during periodic + # reloads (see _update_general_settings). + self._yaml_general_settings_keys = set(general_settings.keys()) # mutable-ok: snapshot of YAML keys at load time # fmt: skip + ### LOAD KEY MANAGEMENT SETTINGS FIRST (needed for custom secret manager) ### key_management_settings: Final = general_settings.get("key_management_settings", None) if key_management_settings is not None: @@ -6049,7 +6058,15 @@ class ProxyConfig: ## STORE PROMPTS IN SPEND LOGS ## if "store_prompts_in_spend_logs" in _general_settings: - value = _general_settings["store_prompts_in_spend_logs"] + # If the YAML config explicitly set this key, prefer the YAML value + # over the DB-cached value. This ensures config changes deployed via + # CI/CD take effect without requiring a manual /config/update call. + # When YAML does not set this key, the DB value is used (preserving + # admin UI runtime changes). + if "store_prompts_in_spend_logs" in self._yaml_general_settings_keys: + value = general_settings.get("store_prompts_in_spend_logs") + else: + value = _general_settings["store_prompts_in_spend_logs"] # Normalize case: handle True/true/TRUE, False/false/FALSE, None/null if value is None: general_settings["store_prompts_in_spend_logs"] = None diff --git a/litellm/proxy/search_endpoints/search_tool_management.py b/litellm/proxy/search_endpoints/search_tool_management.py index 381a5e14ca2..69edf681e4d 100644 --- a/litellm/proxy/search_endpoints/search_tool_management.py +++ b/litellm/proxy/search_endpoints/search_tool_management.py @@ -2,13 +2,15 @@ CRUD ENDPOINTS FOR SEARCH TOOLS """ +from collections.abc import Awaitable, Callable from datetime import datetime -from typing import Any, Final +from typing import Any, Final, TypeAlias from fastapi import APIRouter, Depends, HTTPException from pydantic import BaseModel from litellm._logging import verbose_proxy_logger +from litellm.constants import UI_SESSION_TOKEN_TEAM_ID from litellm.proxy._types import ( LiteLLM_TeamTable, LitellmUserRoles, @@ -46,9 +48,46 @@ def _convert_datetime_to_str(value: datetime | str | None) -> str | None: return value +TeamObjectLookup: TypeAlias = Callable[[str, UserAPIKeyAuth], Awaitable[LiteLLM_TeamTable]] + + +async def _team_object_from_db(team_id: str, user_api_key_dict: UserAPIKeyAuth) -> LiteLLM_TeamTable: + from litellm.proxy.auth.auth_checks import get_team_object + from litellm.proxy.proxy_server import ( + prisma_client, + proxy_logging_obj, + user_api_key_cache, + ) + + return await get_team_object( + team_id=team_id, + prisma_client=prisma_client, + user_api_key_cache=user_api_key_cache, + parent_otel_span=user_api_key_dict.parent_otel_span, + proxy_logging_obj=proxy_logging_obj, + ) + + +def _allowlist_team_id(user_api_key_dict: UserAPIKeyAuth) -> str | None: + """ + The team whose object_permission allowlist scopes this caller, or None when there is none. + + Every Admin UI session key is stamped with UI_SESSION_TOKEN_TEAM_ID, a reserved sentinel that + never has a row in LiteLLM_TeamTable (`/team/new` rejects it as a real team id), so looking it + up would raise 404 instead of resolving a team. It carries no allowlist of its own, so the + caller is scoped by its key-level allowlist alone. Any other team id is looked up for real and + a failed lookup still surfaces. + """ + team_id: Final = user_api_key_dict.team_id + if not team_id or team_id == UI_SESSION_TOKEN_TEAM_ID: + return None + return team_id + + async def _filter_visible_search_tools( search_tools: list[SearchToolInfoResponse], user_api_key_dict: UserAPIKeyAuth, + lookup_team_object: TeamObjectLookup = _team_object_from_db, ) -> list[SearchToolInfoResponse]: """ Drop search tools the caller is not authorized to invoke, applying the same @@ -60,25 +99,12 @@ async def _filter_visible_search_tools( ): return search_tools - from litellm.proxy.auth.auth_checks import ( - can_user_view_search_tool, - get_team_object, - ) - from litellm.proxy.proxy_server import ( - prisma_client, - proxy_logging_obj, - user_api_key_cache, - ) + from litellm.proxy.auth.auth_checks import can_user_view_search_tool - team_object: LiteLLM_TeamTable | None = None - if user_api_key_dict.team_id: - team_object = await get_team_object( - team_id=user_api_key_dict.team_id, - prisma_client=prisma_client, - user_api_key_cache=user_api_key_cache, - parent_otel_span=user_api_key_dict.parent_otel_span, - proxy_logging_obj=proxy_logging_obj, - ) + allowlist_team_id: Final = _allowlist_team_id(user_api_key_dict) + team_object: Final[LiteLLM_TeamTable | None] = ( + await lookup_team_object(allowlist_team_id, user_api_key_dict) if allowlist_team_id else None + ) visible: Final[list[SearchToolInfoResponse]] = [] for tool in search_tools: @@ -213,6 +239,8 @@ async def list_search_tools( visible_search_tools: Final = await _filter_visible_search_tools(search_tool_configs, user_api_key_dict) return ListSearchToolsResponse(search_tools=visible_search_tools) + except HTTPException: + raise except Exception as e: verbose_proxy_logger.exception("Error getting search tools: %s", e) raise HTTPException(status_code=500, detail=str(e)) diff --git a/litellm/types/guardrails.py b/litellm/types/guardrails.py index 60c3830fbef..6b354a39101 100644 --- a/litellm/types/guardrails.py +++ b/litellm/types/guardrails.py @@ -753,6 +753,16 @@ class BaseLitellmParams(ContentFilterConfigModel): # works for new and patch up ), ) + scan_only_tool_results: bool | None = Field( + default=None, + description=( + "When True, unified guardrails only evaluate tool results, the untrusted data an " + "agent feeds back into the model, and skip system, user, and assistant content. " + "Intended for agent harnesses whose own prompt scaffolding is trusted but often " + "trips prompt-attack detectors." + ), + ) + # Lakera specific params category_thresholds: LakeraCategoryThresholds | None = Field( default=None, diff --git a/ruff-strict-budget.json b/ruff-strict-budget.json index 421b424757b..60356eda05b 100644 --- a/ruff-strict-budget.json +++ b/ruff-strict-budget.json @@ -1,30 +1,30 @@ { "ANN001": { - "limit": 3126 + "limit": 3121 }, "ANN002": { "limit": 71 }, "ANN003": { - "limit": 836 + "limit": 834 }, "ANN201": { - "limit": 2037 + "limit": 2033 }, "ANN202": { - "limit": 869 + "limit": 865 }, "ANN204": { - "limit": 715 + "limit": 713 }, "ANN205": { - "limit": 115 + "limit": 114 }, "ANN206": { "limit": 133 }, "ANN401": { - "limit": 1689 + "limit": 1630 }, "ASYNC230": { "limit": 11 @@ -42,7 +42,7 @@ "limit": 81 }, "B010": { - "limit": 194 + "limit": 190 }, "B018": { "limit": 2 @@ -222,7 +222,7 @@ "limit": 0 }, "RET504": { - "limit": 178 + "limit": 177 }, "RUF010": { "limit": 0 @@ -306,7 +306,7 @@ "limit": 0 }, "TID251": { - "limit": 1242 + "limit": 1240 }, "TRY002": { "limit": 528 diff --git a/ruff-strict.toml b/ruff-strict.toml index d58885fe848..01faf04805f 100644 --- a/ruff-strict.toml +++ b/ruff-strict.toml @@ -15,7 +15,7 @@ max-args = 5 "typing.Any".msg = "Use a concrete type. Frozen slots=True dataclass (preferred) / NamedTuple / ReadOnly TypedDict for payloads." "typing_extensions.Any".msg = "Same as typing.Any." "typing.List".msg = "tuple[X, ...] for state, Sequence[X] for params." -"typing.Dict".msg = "Frozen dataclass / NamedTuple / ReadOnly TypedDict; create a Mapping alias with concrete value types if truly dynamic." +"typing.Dict".msg = "Frozen dataclass / NamedTuple / ReadOnly TypedDict; if truly dynamic, use MappingProxyType." "typing.Set".msg = "frozenset[X] or AbstractSet[X]." "typing.MutableSequence".msg = "Sequence[X]." "typing.MutableMapping".msg = "See typing.Dict." diff --git a/scripts/check_type_discipline.py b/scripts/check_type_discipline.py index c303fbaffce..65d0424fb5a 100644 --- a/scripts/check_type_discipline.py +++ b/scripts/check_type_discipline.py @@ -17,13 +17,14 @@ LIT002 Mutable-collection *construction*: a list/dict/set literal or comprehens a call to a mutable constructor (list/dict/set/deque/defaultdict/Counter/...). Catches the unannotated seed-then-mutate pattern LIT001 cannot see (`acc = []`). Build the value in one shot and freeze it: a `tuple`/`frozenset` wrapping a - generator (`tuple(f(x) for x in xs)`), a tuple literal, or a frozen dataclass / - NamedTuple / ReadOnly TypedDict. Generator expressions and `tuple`/`frozenset` - calls are not construction and pass. Annotation-internal lists (`Callable[[int], - str]`) are exempt, as is a value passed directly to a freezing wrapper - (`tuple(...)`, `frozenset(...)`, `MappingProxyType(...)`): it is frozen before - it can escape, though anything mutable nested inside it still counts. - Suppress with `# mutable-ok: `. + generator (`tuple(f(x) for x in xs)`), a tuple literal, a frozen dataclass / + NamedTuple / ReadOnly TypedDict, or (if it really must be dynamic) a + MappingProxyType wrapping a dict literal or comprehension. Generator expressions + and freezing-wrapper calls (`tuple(...)`, `frozenset(...)`, + `MappingProxyType(...)`) are not construction and pass, as does the value passed + directly to a wrapper: it is frozen before it can escape, though anything + mutable nested inside it still counts. Annotation-internal lists + (`Callable[[int], str]`) are exempt. Suppress with `# mutable-ok: `. LIT003 noqa suppression without rule codes or without a reason. Required shape: `# noqa: TID251 # ` LIT004 pyright/mypy ignore without bracketed codes or without a reason. @@ -488,8 +489,9 @@ def iter_construction_violations(path: Path, tree: ast.AST, comments: Comments) path, node.lineno, "LIT002", f"mutable {kind}: this builds a collection that can be grown or rewritten. " f"Build it in one shot and freeze it -- a tuple/frozenset wrapping a generator " - f"(`tuple(f(x) for x in xs)`), a tuple literal, or a frozen dataclass / NamedTuple " - f"/ ReadOnly TypedDict (suppress: `# mutable-ok: `)", + f"(`tuple(f(x) for x in xs)`), a tuple literal, a frozen dataclass / NamedTuple " + f"/ ReadOnly TypedDict, or (if it really must be dynamic) a MappingProxyType " + f"wrapping a dict literal or comprehension (suppress: `# mutable-ok: `)", ) diff --git a/scripts/prisma_generate_if_needed.py b/scripts/prisma_generate_if_needed.py index d2c40adf820..f2d2232b23f 100644 --- a/scripts/prisma_generate_if_needed.py +++ b/scripts/prisma_generate_if_needed.py @@ -9,13 +9,21 @@ client (a fresh or reinstalled prisma package) forces a regenerate even when the stamp matches. The prisma package itself is never imported here: once generated it re-exports the whole client on import, which costs more than the generate this script exists to skip. + +prisma resolves its generator command (``prisma-client-py``) through a plain +PATH lookup, never through the interpreter that invoked ``prisma generate``, +so the generate runs with this interpreter's own bin directory pinned to the +front of PATH; without that pin the client lands in whichever venv the caller +happened to have on PATH (or the generate fails outright when none is). """ import hashlib import importlib.metadata import importlib.util +import os import subprocess import sys +from collections.abc import Callable, Mapping from pathlib import Path REPO_ROOT = Path(__file__).resolve().parent.parent @@ -46,6 +54,25 @@ def client_is_generated() -> bool: ) +def env_with_own_bin_first(base_env: Mapping[str, str]) -> dict[str, str]: + bin_dir = str(Path(sys.executable).parent) + inherited = base_env.get("PATH") + path = os.pathsep.join((bin_dir, inherited)) if inherited else bin_dir + return {**base_env, "PATH": path} + + +def _run_command(cmd: list[str], cwd: Path, env: dict[str, str]) -> int: + return subprocess.run(cmd, cwd=cwd, env=env).returncode + + +def run_generate(run: Callable[[list[str], Path, dict[str, str]], int] = _run_command) -> int: + return run( + [sys.executable, "-m", "prisma", "generate", "--schema", str(SCHEMA)], + REPO_ROOT, + env_with_own_bin_first(os.environ), + ) + + def main() -> int: version = importlib.metadata.version("prisma") expected = stamp_value(SCHEMA.read_bytes(), version) @@ -55,12 +82,9 @@ def main() -> int: f"(prisma {version}); skipping prisma generate" ) return 0 - result = subprocess.run( - [sys.executable, "-m", "prisma", "generate", "--schema", str(SCHEMA)], - cwd=REPO_ROOT, - ) - if result.returncode != 0: - return result.returncode + returncode = run_generate() + if returncode != 0: + return returncode STAMP.write_text(expected) return 0 diff --git a/scripts/type_check_gate.py b/scripts/type_check_gate.py index b8c6cb29a4e..c9f774c6113 100644 --- a/scripts/type_check_gate.py +++ b/scripts/type_check_gate.py @@ -12,6 +12,18 @@ a red once two PRs each land near the limit and their sum crosses it: the bystander's count equals its base, so it is spared, while any PR that actually grows the rule past its limit still fails. +Installed packages are part of the measurement: a typed dependency that is +present changes what basedpyright can prove (and therefore which diagnostics +fire) versus when it is absent, so counts from two differently provisioned +venvs are not comparable and their comparison produces phantom breaches no +diff hunk explains. The gate therefore provisions its own environment at +``.venv-typecheck`` (a frozen ``uv sync`` of one canonical dependency-group +set, plus a generated Prisma client) and runs every basedpyright pass from it, +so pre-commit, the CI lint job, and the artifact publisher measure one package +set by construction; re-syncs of an up-to-date env are a near-instant no-op. +The group set is folded into the cache and artifact fingerprint, so counts +recorded under a different set are never matched, only recomputed. + The gate runs basedpyright itself, for both the head and the base pass, with ``NODE_OPTIONS`` raised to the heap this repo needs: basedpyright's node process OOMs at the ~4 GB default, and when callers had to remember the flag, @@ -21,9 +33,9 @@ matters once some rule is over its limit, so when none is the base pass is skipped outright. When it is needed, it is a second basedpyright pass over a detached worktree at the merge-base, run under the same environment so import resolution matches, and its per-rule counts are cached under the repo's git -common dir keyed by merge-base commit, -``pyrightconfig.json``, and ``uv.lock``, so re-runs against the same branch -point pay for it once. A CI workflow publishes every staging commit's counts as +common dir keyed by merge-base commit, ``pyrightconfig.json``, ``uv.lock``, +the Prisma schema, and the dependency-group set, so re-runs against the same +branch point pay for it once. A CI workflow publishes every staging commit's counts as an artifact (``--emit-counts-dir`` is its entry point), and on a disk-cache miss the gate first tries to download the merge-base's artifact through the ``gh`` CLI; any fetch failure falls back silently to the local base pass, so the gate @@ -51,7 +63,7 @@ import sys import tempfile import zipfile from collections import Counter -from collections.abc import Callable, Iterator, Mapping +from collections.abc import Callable, Iterator, Mapping, Sequence from pathlib import Path from typing import Final, NamedTuple @@ -61,13 +73,23 @@ PYRIGHT_CONFIG = REPO_ROOT / "pyrightconfig.json" UV_LOCK = REPO_ROOT / "uv.lock" DEFAULT_BASE = "origin/litellm_internal_staging" CACHE_FILE_PREFIX = "basedpyright-base-" +CACHE_KEEP_ENTRIES = 8 ARTIFACT_NAME_PREFIX = "basedpyright-counts-" GH_TIMEOUT_SECONDS = 10 +# The one environment every basedpyright pass measures in. The group set is +# the slim one the CI publisher has always installed (not bootstrap's fatter +# --extra proxy env), so the committed budgets stay valid; changing it re-keys +# every cache and artifact fingerprint, so stale counts can never be matched. +TYPECHECK_ENV_DIR = REPO_ROOT / ".venv-typecheck" +TYPECHECK_DEP_GROUPS = ("proxy-dev", "e2e-dev") +PRISMA_GENERATE_SCRIPT = REPO_ROOT / "scripts" / "prisma_generate_if_needed.py" +PRISMA_SCHEMA = REPO_ROOT / "litellm" / "proxy" / "schema.prisma" + # basedpyright's node process needs more than the ~4 GB default heap on this # repo; appended last so it wins node's last-flag-wins resolution over any # caller-set value while preserving the caller's other NODE_OPTIONS flags. -NODE_HEAP_OPTION = "--max-old-space-size=12288" +NODE_HEAP_OPTION = "--max-old-space-size=8192" # Bucket for a basedpyright diagnostic with no `rule`. Counted so it's gated. UNCODED = "" @@ -129,14 +151,83 @@ def node_options_with_heap(base_env: Mapping[str, str]) -> str: return f"{base_env.get('NODE_OPTIONS', '')} {NODE_HEAP_OPTION}".strip() -def run_basedpyright(cwd: Path = REPO_ROOT) -> str: - """One basedpyright pass over `cwd` with the raised node heap exported. +def typecheck_python_version() -> str | None: + """The interpreter version to build the owned env with, read from + pyrightconfig's `pythonVersion` so the packages installed for basedpyright + to see always come from the same version it type-checks against.""" + try: + config = json.loads(PYRIGHT_CONFIG.read_text()) + except (OSError, ValueError): + return None + version: Final = config.get("pythonVersion") if isinstance(config, dict) else None + return version if isinstance(version, str) else None - Exit 0 (clean) and 1 (errors found) are both output-bearing runs; anything - else is a crash and fails loudly instead of reading as zero errors.""" - exe = shutil.which("basedpyright") or "basedpyright" + +def typecheck_env_commands(env_dir: Path = TYPECHECK_ENV_DIR) -> tuple[tuple[str, ...], ...]: + python_pin: Final = typecheck_python_version() + sync: Final = ( + "uv", + "sync", + "--frozen", + *(("--python", python_pin) if python_pin else ()), + *(flag for group in TYPECHECK_DEP_GROUPS for flag in ("--group", group)), + ) + generate: Final = (str(env_dir / "bin" / "python"), str(PRISMA_GENERATE_SCRIPT)) + return (sync, generate) + + +def _run_provision_step(cmd: tuple[str, ...], env: Mapping[str, str]) -> int: proc = subprocess.run( - [exe, "--outputjson"], + list(cmd), cwd=REPO_ROOT, env=dict(env), capture_output=True, text=True + ) + if proc.returncode != 0: + sys.stderr.write(proc.stdout) + sys.stderr.write(proc.stderr) + return proc.returncode + + +def ensure_typecheck_env( + env_dir: Path = TYPECHECK_ENV_DIR, + run: Callable[[tuple[str, ...], Mapping[str, str]], int] = _run_provision_step, +) -> Path: + """Sync the gate-owned venv (and its generated Prisma client) before a + measurement pass. Unconditional on purpose: an up-to-date env makes both + steps near-instant no-ops, and skipping them on a heuristic is how the + measured environment and the fingerprinted one drift apart.""" + if not env_dir.exists(): + sys.stderr.write( + f"provisioning {env_dir.name} (first run installs packages and " + "generates the Prisma client; re-runs are near-instant no-ops)\n" + ) + env: Final = {**os.environ, "UV_PROJECT_ENVIRONMENT": str(env_dir)} + for cmd in typecheck_env_commands(env_dir): + if run(cmd, env) != 0: + raise SystemExit( + f"could not provision the type-check environment at {env_dir}: " + f"`{' '.join(cmd)}` failed" + ) + return env_dir + + +def run_basedpyright(cwd: Path = REPO_ROOT, env_dir: Path = TYPECHECK_ENV_DIR) -> str: + """One basedpyright pass over `cwd` from the gate-owned venv, with the + raised node heap exported. + + `--pythonpath` pins import resolution to the owned env's interpreter; it is + the only pin that works, because basedpyright auto-detects a `.venv` in the + project root and that beats both PATH order and VIRTUAL_ENV, silently + measuring the caller's fatter venv (whose extra typed packages flip + diagnostics) whenever the repo has one. Exit 0 (clean) and 1 (errors + found) are both output-bearing runs; anything else is a crash and fails + loudly instead of reading as zero errors.""" + bin_dir: Final = env_dir / "bin" + proc = subprocess.run( + [ + str(bin_dir / "basedpyright"), + "--outputjson", + "--pythonpath", + str(bin_dir / "python"), + ], cwd=cwd, capture_output=True, text=True, @@ -208,11 +299,16 @@ def over_ceiling( ) -def environment_fingerprints() -> tuple[str, ...]: - return tuple( - hashlib.sha256(path.read_bytes()).hexdigest() - for path in (PYRIGHT_CONFIG, UV_LOCK) - if path.exists() +def environment_fingerprints( + dep_groups: tuple[str, ...] = TYPECHECK_DEP_GROUPS, +) -> tuple[str, ...]: + return ( + *( + hashlib.sha256(path.read_bytes()).hexdigest() + for path in (PYRIGHT_CONFIG, UV_LOCK, PRISMA_SCHEMA) + if path.exists() + ), + "groups:" + ",".join(dep_groups), ) @@ -272,16 +368,30 @@ def counts_payload(base_point: str, counts: Mapping[str, int]) -> str: ) +def entry_recency(path: Path) -> float: + try: + return path.stat().st_mtime + except OSError: + return 0.0 + + +def evicted_beyond_cap(entries: Sequence[Path], keep: int) -> tuple[Path, ...]: + newest_first: Final = sorted(entries, key=entry_recency, reverse=True) + return tuple(newest_first[keep:]) + + def store_counts( directory: Path, path: Path, base_point: str, counts: Mapping[str, int] ) -> None: directory.mkdir(parents=True, exist_ok=True) - for stale in directory.glob(f"{CACHE_FILE_PREFIX}*.json"): - if stale != path: - stale.unlink(missing_ok=True) scratch = scratch_path(path) scratch.write_text(counts_payload(base_point, counts)) scratch.replace(path) + siblings: Final = tuple( + entry for entry in directory.glob(f"{CACHE_FILE_PREFIX}*.json") if entry != path + ) + for stale in evicted_beyond_cap(siblings, CACHE_KEEP_ENTRIES - 1): + stale.unlink(missing_ok=True) def parse_origin_slug(url: str) -> str | None: @@ -560,6 +670,7 @@ def main() -> None: parser.add_argument("--update", action="store_true") parser.add_argument("--emit-counts-dir", type=Path) args = parser.parse_args() + ensure_typecheck_env() head = count_basedpyright(run_basedpyright()) if args.emit_counts_dir is not None: cmd_emit_counts( diff --git a/tests/litellm/llms/anthropic/test_anthropic_schema_filter.py b/tests/litellm/llms/anthropic/test_anthropic_schema_filter.py index c10ac5532a0..71c9cfe8f41 100644 --- a/tests/litellm/llms/anthropic/test_anthropic_schema_filter.py +++ b/tests/litellm/llms/anthropic/test_anthropic_schema_filter.py @@ -281,7 +281,10 @@ class TestFilterAnthropicOutputSchema: "unevaluatedProperties", ): assert field not in result - assert 'properties whose names match each pattern must satisfy: {"^x": {"type": "string"}}' in result["description"] + assert ( + 'properties whose names match each pattern must satisfy: {"^x": {"type": "string"}}' + in result["description"] + ) assert 'property names must satisfy: {"pattern": "^[a-z]+$"}' in result["description"] assert 'dependent required properties: {"first": ["last"]}' in result["description"] assert 'dependent schemas: {"first": {"required": ["last"]}}' in result["description"] @@ -347,3 +350,70 @@ class TestFilterAnthropicOutputSchema: "all array items must be unique, minimum number of matching items: 2, " "maximum number of matching items: 3." ) + + def test_coerces_explicit_additional_properties_true(self): + """An explicit ``additionalProperties: true`` must be coerced to false. + + Anthropic rejects anything other than false with: + "output_format.schema: For 'object' type, 'additionalProperties: true' is + not supported". + """ + schema = { + "type": "object", + "additionalProperties": True, + "properties": {"a": {"type": "string"}}, + } + + result = AnthropicConfig.filter_anthropic_output_schema(schema) + + assert result["additionalProperties"] is False + + def test_coerces_additional_properties_true_when_nested(self): + """Nested object schemas are coerced too, at every recursion site.""" + schema = { + "type": "object", + "properties": { + "obj": { + "type": "object", + "additionalProperties": True, + "properties": {"a": {"type": "string"}}, + }, + "rows": { + "type": "array", + "items": { + "type": "object", + "additionalProperties": True, + "properties": {"b": {"type": "string"}}, + }, + }, + }, + } + + result = AnthropicConfig.filter_anthropic_output_schema(schema) + + assert result["properties"]["obj"]["additionalProperties"] is False + assert result["properties"]["rows"]["items"]["additionalProperties"] is False + + def test_coerces_additional_properties_sub_schema(self): + """A sub-schema value (free-form map) is also rejected by Anthropic.""" + schema = { + "type": "object", + "additionalProperties": {"type": "string"}, + "properties": {"a": {"type": "string"}}, + } + + result = AnthropicConfig.filter_anthropic_output_schema(schema) + + assert result["additionalProperties"] is False + + def test_explicit_additional_properties_false_is_preserved(self): + """The already-correct value must survive untouched.""" + schema = { + "type": "object", + "additionalProperties": False, + "properties": {"a": {"type": "string"}}, + } + + result = AnthropicConfig.filter_anthropic_output_schema(schema) + + assert result["additionalProperties"] is False diff --git a/tests/openai_endpoints_tests/test_openai_batches_endpoint.py b/tests/openai_endpoints_tests/test_openai_batches_endpoint.py index c6f4128f2c5..db8f75cf640 100644 --- a/tests/openai_endpoints_tests/test_openai_batches_endpoint.py +++ b/tests/openai_endpoints_tests/test_openai_batches_endpoint.py @@ -414,7 +414,7 @@ async def test_batch_status_sync_from_provider_to_database(): # Verify logger was called with status change message mock_logger.info.assert_called() - log_message = mock_logger.info.call_args[0][0] + log_message = mock_logger.info.call_args[0][0] % mock_logger.info.call_args[0][1:] assert "validating" in log_message assert "completed" in log_message @@ -450,6 +450,9 @@ async def test_batch_cancel_updates_database(): # Mock prisma client mock_prisma_client = MagicMock() + mock_prisma_client.db.litellm_managedobjecttable.find_first = AsyncMock( + return_value=None + ) mock_prisma_client.db.litellm_managedobjecttable.update = AsyncMock() # Mock managed_files_obj @@ -482,7 +485,7 @@ async def test_batch_cancel_updates_database(): # Verify logger was called mock_logger.info.assert_called() - log_message = mock_logger.info.call_args[0][0] + log_message = mock_logger.info.call_args[0][0] % mock_logger.info.call_args[0][1:] assert "cancel" in log_message.lower() assert "cancelled" in log_message diff --git a/tests/proxy_unit_tests/test_check_batch_cost.py b/tests/proxy_unit_tests/test_check_batch_cost.py index a15abd023d8..800c97d7ba1 100644 --- a/tests/proxy_unit_tests/test_check_batch_cost.py +++ b/tests/proxy_unit_tests/test_check_batch_cost.py @@ -420,6 +420,134 @@ class TestCheckBatchCost: ), "update() must include batch_processed=True when column is present" assert update_data["status"] == "complete" + @pytest.mark.asyncio + async def test_completed_batch_with_no_attributable_owner_still_writes_spend_log( + self, check_batch_cost_instance, mock_prisma_client, mock_llm_router + ): + """Regression: a batch created with the master key or a team-less key has + created_by=None and team_id=None on LiteLLM_ManagedObjectTable (the table + never stores the raw key hash). CheckBatchCost's synthetic logging_obj for + such a batch then carries no attributable key/user/team/end-user, and + before the fix _should_track_cost_callback silently skipped the DB write + with no error or warning: batch_processed still became True, but no + LiteLLM_SpendLogs row was ever written. + + Unlike the other tests in this file, this one does NOT mock + litellm_logging.Logging or async_success_handler -- it runs the real + logging pipeline through to _ProxyDBLogger, which is the exact gap that + let the original bug ship undetected. + """ + import litellm + from litellm.proxy.hooks.proxy_track_cost_callback import _ProxyDBLogger + + mock_prisma_client.db.litellm_managedobjecttable.update_many = AsyncMock(return_value=0) + mock_prisma_client.db.litellm_managedobjecttable.update = AsyncMock() + mock_prisma_client.db.litellm_usertable.find_unique = AsyncMock(return_value=None) + + mock_job = MagicMock() + mock_job.id = "job-unattributed-1" + mock_job.unified_object_id = "dW5pZmllZF9iYXRjaF9pZA==" + mock_job.created_by = None + mock_job.team_id = None + + mock_prisma_client.db.litellm_managedobjecttable.find_many = AsyncMock(return_value=[mock_job]) + + # A real LiteLLMBatch (not a bare MagicMock): this test runs the real + # litellm_logging.Logging pipeline, which type-checks the result via + # isinstance(..., LiteLLMBatch) before it will compute/attach a cost. + from litellm.types.utils import LiteLLMBatch + + mock_response = LiteLLMBatch( + id="batch-1", + completion_window="24h", + created_at=1, + endpoint="/v1/chat/completions", + input_file_id="file-input-123", + object="batch", + status="completed", + output_file_id="file-output-123", + ) + + mock_llm_router.aretrieve_batch = AsyncMock(return_value=mock_response) + mock_llm_router.get_deployment_credentials_with_provider = MagicMock(return_value={"api_key": "sk-test"}) + + mock_deployment = MagicMock() + mock_deployment.litellm_params.custom_llm_provider = "openai" + mock_deployment.litellm_params.model = "gpt-4" + mock_deployment.model_info.model_dump.return_value = {} + mock_llm_router.get_deployment = MagicMock(return_value=mock_deployment) + + mock_file_content = MagicMock() + mock_file_content.content = b'{"id":"req-1"}' + + decoded_id = "llm_model_id,model-123;llm_batch_id,batch-456;" + + db_logger = _ProxyDBLogger() + mock_update_database = AsyncMock() + + # Unlike the other tests in this file, this one runs the real + # litellm_logging.Logging pipeline, which calls + # _is_base64_encoded_unified_file_id an extra time (checking result.id + # after it's reset to job.unified_object_id). Key off the argument + # instead of a fixed-length side_effect list so the exact call count + # doesn't matter. + def _fake_is_base64_encoded(file_id): + return decoded_id if file_id == mock_job.unified_object_id else None + + with ( + patch( + "litellm.proxy.openai_files_endpoints.common_utils._is_base64_encoded_unified_file_id", + side_effect=_fake_is_base64_encoded, + ), + patch( + "litellm.proxy.openai_files_endpoints.common_utils.get_model_id_from_unified_batch_id", + return_value="model-123", + ), + patch( + "litellm.proxy.openai_files_endpoints.common_utils.get_batch_id_from_unified_batch_id", + return_value="batch-456", + ), + patch( + "litellm.files.main.afile_content", + new_callable=AsyncMock, + return_value=mock_file_content, + ), + patch( + "litellm.batches.batch_utils._get_file_content_as_dictionary", + return_value=[{"id": "req-1"}], + ), + patch( + "litellm.batches.batch_utils.calculate_batch_cost_and_usage", + new_callable=AsyncMock, + return_value=( + 0.01, + {"prompt_tokens": 10, "completion_tokens": 5}, + ["gpt-4"], + ), + ), + patch( + "litellm.litellm_core_utils.get_llm_provider_logic.get_llm_provider", + return_value=("gpt-4", "openai", None, None), + ), + patch.object(litellm, "_async_success_callback", [db_logger]), + patch( + "litellm.proxy.proxy_server.proxy_logging_obj", + MagicMock( + db_spend_update_writer=MagicMock(update_database=mock_update_database), + slack_alerting_instance=MagicMock(customer_spend_alert=AsyncMock()), + ), + ), + patch("litellm.proxy.proxy_server.increment_spend_counters", AsyncMock()), + patch("litellm.proxy.proxy_server.update_cache", AsyncMock()), + ): + await check_batch_cost_instance.check_batch_cost() + + mock_update_database.assert_awaited_once() + assert mock_update_database.call_args.kwargs["response_cost"] == 0.01 + assert mock_prisma_client.db.litellm_managedobjecttable.update.call_count == 1, ( + "the job must still be marked processed once cost tracking succeeds" + ) + @pytest.mark.asyncio async def test_cost_tracking_failure_leaves_job_unprocessed( self, check_batch_cost_instance, mock_prisma_client, mock_llm_router @@ -499,7 +627,7 @@ class TestCheckBatchCost: must be written back with that status and batch_processed=True so it stops being polled forever. """ - from unittest.mock import patch + import base64 mock_prisma_client.db.litellm_managedobjecttable.update_many = AsyncMock( return_value=0 @@ -511,7 +639,9 @@ class TestCheckBatchCost: mock_job = MagicMock() mock_job.id = "job-terminal-1" - mock_job.unified_object_id = "dW5pZmllZF9iYXRjaF9pZA==" + mock_job.unified_object_id = base64.urlsafe_b64encode( + b"litellm_proxy;model_id:model-123;llm_batch_id:batch-456" + ).decode() mock_job.created_by = "user-1" assert check_batch_cost_instance._has_batch_processed_column is True @@ -527,23 +657,7 @@ class TestCheckBatchCost: mock_llm_router.aretrieve_batch = AsyncMock(return_value=mock_response) - decoded_id = "llm_model_id,model-123;llm_batch_id,batch-456;" - - with ( - patch( - "litellm.proxy.openai_files_endpoints.common_utils._is_base64_encoded_unified_file_id", - side_effect=[decoded_id, None], - ), - patch( - "litellm.proxy.openai_files_endpoints.common_utils.get_model_id_from_unified_batch_id", - return_value="model-123", - ), - patch( - "litellm.proxy.openai_files_endpoints.common_utils.get_batch_id_from_unified_batch_id", - return_value="batch-456", - ), - ): - await check_batch_cost_instance.check_batch_cost() + await check_batch_cost_instance.check_batch_cost() assert ( mock_prisma_client.db.litellm_managedobjecttable.update.call_count == 1 @@ -556,6 +670,133 @@ class TestCheckBatchCost: update_data["batch_processed"] is True ), "terminal-status update() must set batch_processed=True so polling stops" + @pytest.mark.asyncio + @pytest.mark.parametrize("terminal_status", ["failed", "expired", "cancelled"]) + async def test_terminal_status_persists_managed_output_file_ids( + self, + check_batch_cost_instance, + mock_prisma_client, + mock_llm_router, + terminal_status, + ): + """A cancelled/failed/expired batch with provider output files must be persisted + with unified managed file IDs, never raw provider IDs. Raw IDs written here leak + to every later GET /batches/{id} and GET /batches because the terminal row is + final (batch_processed=True) and read paths only resolve, never mint. + """ + import base64 + import json + + from litellm.types.utils import LiteLLMBatch + + unified_batch_uid = base64.urlsafe_b64encode( + b"litellm_proxy;model_id:model-123;llm_batch_id:batch-456" + ).decode() + raw_output_file_id = "file-terminal-out-abc" + raw_error_file_id = "file-terminal-err-xyz" + raw_input_file_id = "file-terminal-in-123" + unified_input_file_id = base64.urlsafe_b64encode( + b"litellm_proxy:application/octet-stream;unified_id,in-1;target_model_names,gpt-5-batch" + ).decode() + unified_output_file_id = base64.urlsafe_b64encode( + f"litellm_proxy:application/octet-stream;unified_id,u-1;llm_output_file_id,{raw_output_file_id}".encode() + ).decode() + unified_error_file_id = base64.urlsafe_b64encode( + f"litellm_proxy:application/octet-stream;unified_id,u-2;llm_output_file_id,{raw_error_file_id}".encode() + ).decode() + + mock_prisma_client.db.litellm_managedobjecttable.update_many = AsyncMock( + return_value=0 + ) + mock_prisma_client.db.litellm_managedobjecttable.update = AsyncMock() + mock_prisma_client.db.litellm_usertable.find_unique = AsyncMock( + return_value=None + ) + + input_file_row = MagicMock() + input_file_row.unified_file_id = unified_input_file_id + + def find_managed_file(where): + if where["flat_model_file_ids"]["has"] == raw_input_file_id: + return input_file_row + return None + + mock_prisma_client.db.litellm_managedfiletable.find_first = AsyncMock( + side_effect=find_managed_file + ) + + mock_job = MagicMock() + mock_job.id = "job-terminal-mint-1" + mock_job.unified_object_id = unified_batch_uid + mock_job.created_by = "user-1" + mock_job.team_id = "team-1" + + check_batch_cost_instance._has_batch_processed_column = True + mock_prisma_client.db.litellm_managedobjecttable.find_many = AsyncMock( + return_value=[mock_job] + ) + + response = LiteLLMBatch( + id="batch-456", + completion_window="24h", + created_at=1, + endpoint="/v1/chat/completions", + input_file_id=raw_input_file_id, + object="batch", + status=terminal_status, + output_file_id=raw_output_file_id, + error_file_id=raw_error_file_id, + ) + mock_llm_router.aretrieve_batch = AsyncMock(return_value=response) + + mock_hook = MagicMock() + mock_hook.get_unified_output_file_id.side_effect = [ + unified_output_file_id, + unified_error_file_id, + ] + mock_hook.store_unified_file_id = AsyncMock() + check_batch_cost_instance.proxy_logging_obj.get_proxy_hook.return_value = ( + mock_hook + ) + + await check_batch_cost_instance.check_batch_cost() + + mock_hook.get_unified_output_file_id.assert_any_call( + output_file_id=raw_output_file_id, + model_id="model-123", + model_name="gpt-5-batch", + ) + mock_hook.get_unified_output_file_id.assert_any_call( + output_file_id=raw_error_file_id, + model_id="model-123", + model_name="gpt-5-batch", + ) + stored = { + next(iter(c.kwargs["model_mappings"].values())): c.kwargs["file_id"] + for c in mock_hook.store_unified_file_id.call_args_list + } + assert stored == { + raw_output_file_id: unified_output_file_id, + raw_error_file_id: unified_error_file_id, + } + for store_call in mock_hook.store_unified_file_id.call_args_list: + assert store_call.kwargs["user_api_key_dict"].user_id == "user-1" + assert store_call.kwargs["user_api_key_dict"].team_id == "team-1" + + assert mock_prisma_client.db.litellm_managedobjecttable.update.call_count == 1 + update_call = mock_prisma_client.db.litellm_managedobjecttable.update.call_args + assert update_call.kwargs["where"] == {"id": "job-terminal-mint-1"} + update_data = update_call.kwargs["data"] + assert update_data["status"] == terminal_status + assert update_data["batch_processed"] is True + persisted = json.loads(update_data["file_object"]) + assert persisted["id"] == unified_batch_uid + assert persisted["input_file_id"] == unified_input_file_id + assert persisted["output_file_id"] == unified_output_file_id + assert persisted["error_file_id"] == unified_error_file_id + assert raw_output_file_id not in update_data["file_object"] + assert raw_error_file_id not in update_data["file_object"] + @pytest.mark.asyncio async def test_raw_output_file_id_converted_to_managed_id( self, check_batch_cost_instance, mock_prisma_client, mock_llm_router diff --git a/tests/proxy_unit_tests/test_check_responses_cost.py b/tests/proxy_unit_tests/test_check_responses_cost.py index 4c0ca94df48..1faf8692b46 100644 --- a/tests/proxy_unit_tests/test_check_responses_cost.py +++ b/tests/proxy_unit_tests/test_check_responses_cost.py @@ -449,6 +449,281 @@ class TestCheckResponsesCost: assert "job-3" in completion_call[1]["where"]["id"]["in"] assert "job-2" not in completion_call[1]["where"]["id"]["in"] + @pytest.mark.asyncio + async def test_encoded_response_id_is_fetched_through_router( + self, check_responses_cost_instance, mock_prisma_client, mock_llm_router + ): + """ + Regression test for https://github.com/BerriAI/litellm/issues/35131 + + A background response created against a deployment whose credentials only + exist in the config (e.g. Azure api_base/api_key) must be fetched through + the router so the deployment credentials are applied. Calling + litellm.aget_responses directly only sees provider env vars, fails, and + leaves the row in "queued" forever. + """ + from litellm.responses.utils import ResponsesAPIRequestUtils + + encoded_response_id = ResponsesAPIRequestUtils._build_responses_api_response_id( + custom_llm_provider="azure", + model_id="deployment-abc", + response_id="resp_upstream_123", + ) + + mock_job = MagicMock() + mock_job.unified_object_id = encoded_response_id + mock_job.created_by = "test-user" + mock_job.id = "job-router" + mock_job.file_object = {"model": "azure-gpt-5", "id": encoded_response_id} + + mock_prisma_client.db.litellm_managedobjecttable.find_many = AsyncMock( + return_value=[mock_job] + ) + mock_prisma_client.db.litellm_managedobjecttable.update_many = AsyncMock( + return_value=0 + ) + + mock_llm_router.aget_responses = AsyncMock( + return_value=ResponsesAPIResponse( + id=encoded_response_id, + object="response", + status="completed", + created_at=int(datetime.now().timestamp()), + output=[], + usage=ResponseAPIUsage( + input_tokens=100, output_tokens=50, total_tokens=150 + ), + ) + ) + + with patch( + "litellm.aget_responses", + new_callable=AsyncMock, + side_effect=AssertionError( + "must not bypass the router for a deployment-scoped response id" + ), + ) as mock_sdk_aget: + await check_responses_cost_instance.check_responses_cost() + + mock_sdk_aget.assert_not_called() + assert ( + mock_llm_router.aget_responses.call_args[1]["response_id"] + == encoded_response_id + ) + + calls = ( + mock_prisma_client.db.litellm_managedobjecttable.update_many.call_args_list + ) + assert len(calls) == 1 + assert calls[0][1]["data"]["status"] == "completed" + assert calls[0][1]["where"]["id"]["in"] == ["job-router"] + + @pytest.mark.asyncio + async def test_encrypted_response_id_is_fetched_through_router( + self, check_responses_cost_instance, mock_prisma_client, mock_llm_router, monkeypatch + ): + """ + Rows store the *encrypted* response id when responses id security is on. + After decryption the id still carries the deployment model_id, so the + fetch must go through the router (issue #35131). + """ + from litellm.proxy.common_utils.encrypt_decrypt_utils import encrypt_value_helper + from litellm.responses.utils import ResponsesAPIRequestUtils + from litellm.types.utils import SpecialEnums + + monkeypatch.setenv("LITELLM_SALT_KEY", "sk-test-salt-key-for-response-ids") + + encoded_response_id = ResponsesAPIRequestUtils._build_responses_api_response_id( + custom_llm_provider="openai", + model_id="deployment-xyz", + response_id="resp_upstream_456", + ) + encrypted_response_id = "resp_" + str( + encrypt_value_helper( + value=SpecialEnums.LITELLM_MANAGED_RESPONSE_API_RESPONSE_ID_COMPLETE_STR.value.format( + encoded_response_id, "test-user", "test-team" + ) + ) + ) + + mock_job = MagicMock() + mock_job.unified_object_id = encrypted_response_id + mock_job.created_by = "test-user" + mock_job.id = "job-encrypted" + mock_job.file_object = {"model": "gpt-5", "id": encrypted_response_id} + + mock_prisma_client.db.litellm_managedobjecttable.find_many = AsyncMock( + return_value=[mock_job] + ) + mock_prisma_client.db.litellm_managedobjecttable.update_many = AsyncMock( + return_value=0 + ) + + mock_llm_router.aget_responses = AsyncMock( + return_value=ResponsesAPIResponse( + id=encoded_response_id, + object="response", + status="completed", + created_at=int(datetime.now().timestamp()), + output=[], + usage=None, + ) + ) + + with patch( + "litellm.aget_responses", + new_callable=AsyncMock, + side_effect=AssertionError( + "must not bypass the router for a deployment-scoped response id" + ), + ) as mock_sdk_aget: + await check_responses_cost_instance.check_responses_cost() + + mock_sdk_aget.assert_not_called() + assert ( + mock_llm_router.aget_responses.call_args[1]["response_id"] + == encoded_response_id + ) + calls = ( + mock_prisma_client.db.litellm_managedobjecttable.update_many.call_args_list + ) + assert len(calls) == 1 + assert calls[0][1]["where"]["id"]["in"] == ["job-encrypted"] + + @pytest.mark.asyncio + async def test_response_id_without_model_id_uses_sdk( + self, check_responses_cost_instance, mock_prisma_client, mock_llm_router + ): + """Ids that carry no deployment info can't be routed, so fall back to the SDK.""" + mock_job = MagicMock() + mock_job.unified_object_id = "resp_plain_upstream_id" + mock_job.created_by = "test-user" + mock_job.id = "job-plain" + mock_job.file_object = {"model": "gpt-5", "id": "resp_plain_upstream_id"} + + mock_prisma_client.db.litellm_managedobjecttable.find_many = AsyncMock( + return_value=[mock_job] + ) + mock_prisma_client.db.litellm_managedobjecttable.update_many = AsyncMock( + return_value=0 + ) + mock_llm_router.aget_responses = AsyncMock( + side_effect=AssertionError("router cannot route an id without a model_id") + ) + + mock_response = ResponsesAPIResponse( + id="resp_plain_upstream_id", + object="response", + status="completed", + created_at=int(datetime.now().timestamp()), + output=[], + usage=None, + ) + + with patch("litellm.aget_responses", new_callable=AsyncMock) as mock_sdk_aget: + mock_sdk_aget.return_value = mock_response + await check_responses_cost_instance.check_responses_cost() + + mock_sdk_aget.assert_called_once() + mock_llm_router.aget_responses.assert_not_called() + + @pytest.mark.asyncio + async def test_missing_deployment_falls_back_to_sdk( + self, check_responses_cost_instance, mock_prisma_client, mock_llm_router + ): + """ + An encoded id whose deployment was removed from the router must fall back + to the SDK so provider env credentials can still retrieve it, instead of + failing every poll cycle until stale expiration. + """ + from litellm.responses.utils import ResponsesAPIRequestUtils + + encoded_response_id = ResponsesAPIRequestUtils._build_responses_api_response_id( + custom_llm_provider="openai", + model_id="deployment-deleted", + response_id="resp_upstream_789", + ) + + mock_job = MagicMock() + mock_job.unified_object_id = encoded_response_id + mock_job.created_by = "test-user" + mock_job.id = "job-missing-deployment" + mock_job.file_object = {"model": "gpt-5", "id": encoded_response_id} + + mock_prisma_client.db.litellm_managedobjecttable.find_many = AsyncMock( + return_value=[mock_job] + ) + mock_prisma_client.db.litellm_managedobjecttable.update_many = AsyncMock( + return_value=0 + ) + mock_llm_router.get_deployment = MagicMock(return_value=None) + mock_llm_router.aget_responses = AsyncMock( + side_effect=AssertionError("router has no deployment for this model_id") + ) + + mock_response = ResponsesAPIResponse( + id=encoded_response_id, + object="response", + status="completed", + created_at=int(datetime.now().timestamp()), + output=[], + usage=None, + ) + + with patch("litellm.aget_responses", new_callable=AsyncMock) as mock_sdk_aget: + mock_sdk_aget.return_value = mock_response + await check_responses_cost_instance.check_responses_cost() + + mock_llm_router.get_deployment.assert_called_once_with(model_id="deployment-deleted") + mock_llm_router.aget_responses.assert_not_called() + mock_sdk_aget.assert_called_once() + assert mock_sdk_aget.call_args[1]["response_id"] == encoded_response_id + + calls = ( + mock_prisma_client.db.litellm_managedobjecttable.update_many.call_args_list + ) + assert len(calls) == 1 + assert calls[0][1]["data"]["status"] == "completed" + assert calls[0][1]["where"]["id"]["in"] == ["job-missing-deployment"] + + @pytest.mark.asyncio + async def test_check_responses_cost_with_incomplete_response( + self, check_responses_cost_instance, mock_prisma_client + ): + """'incomplete' is terminal in the Responses API, so the row must not stay queued.""" + mock_job = MagicMock() + mock_job.unified_object_id = "resp_test_incomplete" + mock_job.created_by = "test-user" + mock_job.id = "job-incomplete" + mock_job.file_object = {"model": "gpt-5", "id": "resp_test_incomplete"} + + mock_prisma_client.db.litellm_managedobjecttable.find_many = AsyncMock( + return_value=[mock_job] + ) + mock_prisma_client.db.litellm_managedobjecttable.update_many = AsyncMock( + return_value=0 + ) + + mock_response = ResponsesAPIResponse( + id="resp_incomplete", + object="response", + status="incomplete", + created_at=int(datetime.now().timestamp()), + output=[], + usage=None, + ) + + with patch("litellm.aget_responses", new_callable=AsyncMock) as mock_aget: + mock_aget.return_value = mock_response + await check_responses_cost_instance.check_responses_cost() + + calls = ( + mock_prisma_client.db.litellm_managedobjecttable.update_many.call_args_list + ) + assert len(calls) == 1 + assert calls[0][1]["data"]["status"] == "completed" + assert calls[0][1]["where"]["id"]["in"] == ["job-incomplete"] + @pytest.mark.asyncio async def test_check_responses_cost_no_model_in_file_object( self, check_responses_cost_instance, mock_prisma_client diff --git a/tests/proxy_unit_tests/test_proxy_config_unit_test.py b/tests/proxy_unit_tests/test_proxy_config_unit_test.py index 36cd08fa5f5..e6b38f31b48 100644 --- a/tests/proxy_unit_tests/test_proxy_config_unit_test.py +++ b/tests/proxy_unit_tests/test_proxy_config_unit_test.py @@ -15,9 +15,7 @@ import os # this file is to test litellm/proxy -sys.path.insert( - 0, os.path.abspath("../..") -) # Adds the parent directory to the system path +sys.path.insert(0, os.path.abspath("../..")) # Adds the parent directory to the system path import asyncio import logging @@ -88,25 +86,14 @@ async def test_read_config_file_with_os_environ_vars(): # Read config proxy_config_instance = ProxyConfig() current_path = os.path.dirname(os.path.abspath(__file__)) - config_path = os.path.join( - current_path, "example_config_yaml", "config_with_env_vars.yaml" - ) + config_path = os.path.join(current_path, "example_config_yaml", "config_with_env_vars.yaml") config = await proxy_config_instance.get_config(config_file_path=config_path) print(config) # Add assertions - assert ( - config["litellm_settings"]["default_internal_user_params"]["user_role"] - == "admin" - ) - assert ( - config["litellm_settings"]["s3_callback_params"]["s3_aws_access_key_id"] - == "1234567890" - ) - assert ( - config["litellm_settings"]["s3_callback_params"]["s3_aws_secret_access_key"] - == "1234567890" - ) + assert config["litellm_settings"]["default_internal_user_params"]["user_role"] == "admin" + assert config["litellm_settings"]["s3_callback_params"]["s3_aws_access_key_id"] == "1234567890" + assert config["litellm_settings"]["s3_callback_params"]["s3_aws_secret_access_key"] == "1234567890" for model in config["model_list"]: if "azure" in model["litellm_params"]["model"]: @@ -129,17 +116,13 @@ async def test_basic_include_directive(): """ proxy_config_instance = ProxyConfig() current_path = os.path.dirname(os.path.abspath(__file__)) - config_path = os.path.join( - current_path, "example_config_yaml", "config_with_include.yaml" - ) + config_path = os.path.join(current_path, "example_config_yaml", "config_with_include.yaml") config = await proxy_config_instance.get_config(config_file_path=config_path) # Verify the included model list was merged assert len(config["model_list"]) > 0 - assert any( - model["model_name"] == "included-model" for model in config["model_list"] - ) + assert any(model["model_name"] == "included-model" for model in config["model_list"]) # Verify original config settings remain assert config["litellm_settings"]["callbacks"] == ["prometheus"] @@ -152,9 +135,7 @@ async def test_missing_include_file(): """ proxy_config_instance = ProxyConfig() current_path = os.path.dirname(os.path.abspath(__file__)) - config_path = os.path.join( - current_path, "example_config_yaml", "config_with_missing_include.yaml" - ) + config_path = os.path.join(current_path, "example_config_yaml", "config_with_missing_include.yaml") with pytest.raises(FileNotFoundError): await proxy_config_instance.get_config(config_file_path=config_path) @@ -167,20 +148,14 @@ async def test_multiple_includes(): """ proxy_config_instance = ProxyConfig() current_path = os.path.dirname(os.path.abspath(__file__)) - config_path = os.path.join( - current_path, "example_config_yaml", "config_with_multiple_includes.yaml" - ) + config_path = os.path.join(current_path, "example_config_yaml", "config_with_multiple_includes.yaml") config = await proxy_config_instance.get_config(config_file_path=config_path) # Verify models from both included files are present assert len(config["model_list"]) == 2 - assert any( - model["model_name"] == "included-model-1" for model in config["model_list"] - ) - assert any( - model["model_name"] == "included-model-2" for model in config["model_list"] - ) + assert any(model["model_name"] == "included-model-1" for model in config["model_list"]) + assert any(model["model_name"] == "included-model-2" for model in config["model_list"]) # Verify original config settings remain assert config["litellm_settings"]["callbacks"] == ["prometheus"] @@ -211,8 +186,7 @@ def test_add_callbacks_from_db_config(): # 1 instance of LangfusePromptManagement should exist in litellm.success_callback num_langfuse_instances = sum( - isinstance(callback, LangfusePromptManagement) - for callback in litellm.success_callback + isinstance(callback, LangfusePromptManagement) for callback in litellm.success_callback ) assert num_langfuse_instances == 1 assert len(litellm.success_callback) == 2 @@ -290,9 +264,7 @@ async def test_json_logs_calls_turn_on_json(): "litellm_settings": {"json_logs": True}, } - with tempfile.NamedTemporaryFile( - mode="w", suffix=".yaml", delete=False - ) as temp_file: + with tempfile.NamedTemporaryFile(mode="w", suffix=".yaml", delete=False) as temp_file: yaml.dump(config_content, temp_file) temp_file_path = temp_file.name @@ -316,3 +288,71 @@ async def test_json_logs_calls_turn_on_json(): # Cleanup os.unlink(temp_file_path) litellm.json_logs = False + + +class TestYamlStorePromptsDbOverride: + """ + Test that YAML store_prompts_in_spend_logs takes precedence over DB-cached value. + + When store_model_in_db=true, LiteLLM persists general_settings to the DB. + On periodic reloads, _update_general_settings() must NOT override + YAML-explicit values with stale DB values. + """ + + def _make_proxy_config_with_yaml_keys(self, yaml_keys: set) -> "ProxyConfig": + """Helper: create ProxyConfig with pre-populated _yaml_general_settings_keys.""" + proxy_config = ProxyConfig() + proxy_config._yaml_general_settings_keys = yaml_keys + return proxy_config + + @pytest.mark.asyncio + async def test_yaml_value_takes_precedence_over_db(self): + """When YAML sets store_prompts_in_spend_logs=false, DB value (true) should be ignored.""" + proxy_config = self._make_proxy_config_with_yaml_keys({"store_prompts_in_spend_logs"}) + + test_general_settings = {"store_prompts_in_spend_logs": False} + + with mock.patch("litellm.proxy.proxy_server.general_settings", test_general_settings): + await proxy_config._update_general_settings( + db_general_settings={"store_prompts_in_spend_logs": True}, + ) + + assert test_general_settings["store_prompts_in_spend_logs"] is False + + @pytest.mark.asyncio + async def test_db_value_used_when_yaml_does_not_set_key(self): + """When YAML does NOT set store_prompts_in_spend_logs, DB value should be used.""" + proxy_config = self._make_proxy_config_with_yaml_keys({"master_key", "database_url"}) + + test_general_settings = {"master_key": "sk-test"} + + with mock.patch("litellm.proxy.proxy_server.general_settings", test_general_settings): + await proxy_config._update_general_settings( + db_general_settings={"store_prompts_in_spend_logs": True}, + ) + + assert test_general_settings["store_prompts_in_spend_logs"] is True + + @pytest.mark.asyncio + async def test_admin_ui_change_works_when_yaml_omits_key(self): + """Admin UI change (DB update) should work when YAML doesn't set the key.""" + proxy_config = self._make_proxy_config_with_yaml_keys({"master_key"}) + + test_general_settings = {"master_key": "sk-test"} + + with mock.patch("litellm.proxy.proxy_server.general_settings", test_general_settings): + await proxy_config._update_general_settings( + db_general_settings={"store_prompts_in_spend_logs": True}, + ) + assert test_general_settings["store_prompts_in_spend_logs"] is True + + await proxy_config._update_general_settings( + db_general_settings={"store_prompts_in_spend_logs": False}, + ) + + assert test_general_settings["store_prompts_in_spend_logs"] is False + + def test_yaml_general_settings_keys_populated_on_load(self): + """_yaml_general_settings_keys should be empty on init.""" + proxy_config = ProxyConfig() + assert proxy_config._yaml_general_settings_keys == set() diff --git a/tests/test_litellm/conftest.py b/tests/test_litellm/conftest.py index f4aa1926d21..c0993051d33 100644 --- a/tests/test_litellm/conftest.py +++ b/tests/test_litellm/conftest.py @@ -19,6 +19,7 @@ sys.path.insert( import asyncio import litellm +from litellm import utils as litellm_utils_module from litellm._logging import ALL_LOGGERS from litellm.litellm_core_utils.prompt_templates import ( image_handling as image_handling_module, @@ -238,6 +239,11 @@ def isolate_litellm_state(): if hasattr(litellm, _attr): original_state[_attr] = getattr(litellm, _attr) + original_runtime_registered_model_cost = { + model_key: dict(model_value) + for model_key, model_value in litellm_utils_module._runtime_registered_model_cost.items() + } + # Store LiteLLM logger state. Some tests reconfigure handlers/propagation for # JSON logging and do not restore them, which breaks later caplog-based tests. logger_state = {} @@ -304,6 +310,9 @@ def isolate_litellm_state(): if hasattr(litellm, attr_name): setattr(litellm, attr_name, original_value) + litellm_utils_module._runtime_registered_model_cost.clear() + litellm_utils_module._runtime_registered_model_cost.update(original_runtime_registered_model_cost) + # Restore logger configuration mutated by logging-focused tests. for logger in ALL_LOGGERS: original_logger_state = logger_state.get(logger.name) diff --git a/tests/test_litellm/enterprise/proxy/test_batch_update_db_managed_output_file_id.py b/tests/test_litellm/enterprise/proxy/test_batch_update_db_managed_output_file_id.py index d8669960674..1b60c97b510 100644 --- a/tests/test_litellm/enterprise/proxy/test_batch_update_db_managed_output_file_id.py +++ b/tests/test_litellm/enterprise/proxy/test_batch_update_db_managed_output_file_id.py @@ -45,9 +45,10 @@ def _build_managed_files_mock(unified_id: str = "file-bWFuYWdlZF9vdXRwdXRfaWQ=") return mock -def _build_prisma_mock(): +def _build_prisma_mock(db_batch_object=None): mock = MagicMock() mock.db.litellm_managedfiletable.find_first = AsyncMock(return_value=None) + mock.db.litellm_managedobjecttable.find_first = AsyncMock(return_value=db_batch_object) mock.db.litellm_managedobjecttable.update = AsyncMock() return mock @@ -89,6 +90,103 @@ async def test_update_batch_in_database_stores_unified_output_file_id(): assert stored["output_file_id"] != raw_output_file_id +@pytest.mark.asyncio +async def test_cancel_path_registers_output_file_under_batch_owner(): + unified_id = "file-bWFuYWdlZF9vdXRwdXRfaWQ=" + db_batch_object = SimpleNamespace( + created_by="batch-owner", team_id="batch-team", status="in_progress" + ) + response = _build_batch_response( + status="cancelling", + output_file_id="file-raw-output", + hidden_params={"model_id": "my-model", "model_name": "openai/gpt-4o"}, + ) + mock_managed_files = _build_managed_files_mock(unified_id=unified_id) + mock_prisma = _build_prisma_mock(db_batch_object=db_batch_object) + + await update_batch_in_database( + batch_id="batch_managed_ids_test", + unified_batch_id="litellm_proxy;model_id:my-model;llm_batch_id:batch_managed_ids_test", + response=response, + managed_files_obj=mock_managed_files, + prisma_client=mock_prisma, + verbose_proxy_logger=MagicMock(), + operation="cancel", + ) + + forwarded_auth = mock_managed_files.store_unified_file_id.call_args.kwargs[ + "user_api_key_dict" + ] + assert forwarded_auth.user_id == "batch-owner" + assert forwarded_auth.team_id == "batch-team" + stored = json.loads( + mock_prisma.db.litellm_managedobjecttable.update.call_args.kwargs["data"][ + "file_object" + ] + ) + assert stored["output_file_id"] == unified_id + + +@pytest.mark.asyncio +async def test_update_batch_skips_lookup_when_db_batch_object_supplied(): + unified_id = "file-bWFuYWdlZF9vdXRwdXRfaWQ=" + caller_row = SimpleNamespace( + created_by="caller-owner", team_id="caller-team", status="in_progress" + ) + decoy_row = SimpleNamespace( + created_by="decoy-owner", team_id="decoy-team", status="in_progress" + ) + response = _build_batch_response( + status="cancelling", + output_file_id="file-raw-output", + hidden_params={"model_id": "my-model", "model_name": "openai/gpt-4o"}, + ) + mock_managed_files = _build_managed_files_mock(unified_id=unified_id) + mock_prisma = _build_prisma_mock(db_batch_object=decoy_row) + + await update_batch_in_database( + batch_id="batch_managed_ids_test", + unified_batch_id="litellm_proxy;model_id:my-model;llm_batch_id:batch_managed_ids_test", + response=response, + managed_files_obj=mock_managed_files, + prisma_client=mock_prisma, + verbose_proxy_logger=MagicMock(), + db_batch_object=caller_row, + operation="retrieve", + ) + + mock_prisma.db.litellm_managedobjecttable.find_first.assert_not_called() + forwarded_auth = mock_managed_files.store_unified_file_id.call_args.kwargs[ + "user_api_key_dict" + ] + assert forwarded_auth.user_id == "caller-owner" + assert forwarded_auth.team_id == "caller-team" + + +@pytest.mark.asyncio +async def test_update_batch_derives_model_id_from_unified_batch_id(): + unified_id = "file-bWFuYWdlZF9vdXRwdXRfaWQ=" + response = _build_batch_response(output_file_id="file-raw-output", hidden_params={}) + mock_managed_files = _build_managed_files_mock(unified_id=unified_id) + mock_prisma = _build_prisma_mock() + + await update_batch_in_database( + batch_id="batch_managed_ids_test", + unified_batch_id="litellm_proxy;model_id:model-from-batch-id;llm_batch_id:batch_managed_ids_test", + response=response, + managed_files_obj=mock_managed_files, + prisma_client=mock_prisma, + verbose_proxy_logger=MagicMock(), + user_api_key_dict=UserAPIKeyAuth(user_id="user-abc"), + ) + + assert ( + mock_managed_files.get_unified_output_file_id.call_args.kwargs["model_id"] + == "model-from-batch-id" + ) + assert response.output_file_id == unified_id + + @pytest.mark.asyncio async def test_ensure_batch_response_normalizes_error_file_id(): """Both output_file_id and error_file_id must be normalized to managed IDs.""" diff --git a/tests/test_litellm/litellm_core_utils/test_litellm_logging.py b/tests/test_litellm/litellm_core_utils/test_litellm_logging.py index eaa4bd3e3fc..a09c45cb141 100644 --- a/tests/test_litellm/litellm_core_utils/test_litellm_logging.py +++ b/tests/test_litellm/litellm_core_utils/test_litellm_logging.py @@ -11,6 +11,9 @@ sys.path.insert( import time +import httpx +from openai._legacy_response import HttpxBinaryResponseContent + import litellm from litellm.constants import SENTRY_DENYLIST, SENTRY_PII_DENYLIST from litellm.integrations.custom_logger import CustomLogger @@ -1771,6 +1774,60 @@ def test_response_cost_calculator_does_not_transform_non_generate_content_dict() assert not cost +def _file_content_logging_obj(call_type: str) -> LitellmLogging: + logging_obj = LitellmLogging( + model="gemini-3-flash-preview", + messages="default-message-value", + stream=False, + call_type=call_type, + start_time=time.time(), + litellm_call_id=f"file-content-{call_type}", + function_id=f"file-content-{call_type}", + ) + logging_obj.model_call_details["custom_llm_provider"] = "vertex_ai" + logging_obj.model_call_details["input"] = "default-message-value" + logging_obj.optional_params = {} + return logging_obj + + +@pytest.mark.parametrize("call_type", ["afile_content", "file_content"]) +def test_file_content_call_is_not_billed(call_type): + """ + Regression for #35130: file content retrieval has no token usage, but ``function_setup`` + stores the ``"default-message-value"`` placeholder as the logged input, which the cost + calculator then token-priced, billing every call at exactly 3 * input_cost_per_token. + """ + result = HttpxBinaryResponseContent(httpx.Response(status_code=200, content=b"file contents")) + + cost = _file_content_logging_obj(call_type)._response_cost_calculator(result=result) + + assert cost == 0.0 + + +@pytest.mark.parametrize("call_type", ["aspeech", "speech"]) +def test_speech_call_is_still_priced_from_input_characters(call_type): + """tts bills per input character, so speech call types must keep passing the input along.""" + logging_obj = LitellmLogging( + model="tts-1", + messages="the quick brown fox jumped over the lazy dogs", + stream=False, + call_type=call_type, + start_time=time.time(), + litellm_call_id=f"speech-{call_type}", + function_id=f"speech-{call_type}", + ) + logging_obj.model_call_details["custom_llm_provider"] = "openai" + logging_obj.model_call_details["input"] = "the quick brown fox jumped over the lazy dogs" + logging_obj.optional_params = {} + + result = HttpxBinaryResponseContent(httpx.Response(status_code=200, content=b"audio bytes")) + + cost = logging_obj._response_cost_calculator(result=result) + + assert cost is not None + assert cost > 0 + + def test_sentry_event_scrubber_initialization(monkeypatch): # Step 1: Create a fake sentry_sdk.scrubber module mock_event_scrubber_instance = MagicMock() diff --git a/tests/test_litellm/llms/anthropic/chat/guardrail_translation/test_anthropic_guardrail_handler.py b/tests/test_litellm/llms/anthropic/chat/guardrail_translation/test_anthropic_guardrail_handler.py index dff3390af12..c7a30f7f954 100644 --- a/tests/test_litellm/llms/anthropic/chat/guardrail_translation/test_anthropic_guardrail_handler.py +++ b/tests/test_litellm/llms/anthropic/chat/guardrail_translation/test_anthropic_guardrail_handler.py @@ -5,6 +5,7 @@ Tests the handler's ability to process streaming output for Anthropic Messages A with guardrail transformations, specifically testing edge cases with empty choices. """ +import json import os import sys from typing import Any, Literal, Optional @@ -760,3 +761,205 @@ class TestAnthropicMessagesToolResultScanning: assert "skip me POISON" not in guardrail.seen_texts assert messages[1]["content"][0]["content"] == "skip me POISON" assert messages[0]["content"] == "keep me [BLOCKED]" + + +class InputsRecordingGuardrail(MockMaskingGuardrail): + def __init__(self): + super().__init__(guardrail_name="scan-only-capture") + self.captured_inputs: Optional[GenericGuardrailAPIInputs] = None + + async def apply_guardrail( + self, + inputs: GenericGuardrailAPIInputs, + request_data: dict, + input_type: Literal["request", "response"], + logging_obj: Optional[Any] = None, + ) -> GenericGuardrailAPIInputs: + self.captured_inputs = inputs + return await super().apply_guardrail(inputs, request_data, input_type, logging_obj) + + +class StructuredMessagesRewritingGuardrail(CustomGuardrail): + """Returns a new structured_messages list with a canary redacted, like redaction guardrails do.""" + + def __init__(self): + super().__init__(guardrail_name="structured-rewrite") + + async def apply_guardrail( + self, + inputs: GenericGuardrailAPIInputs, + request_data: dict, + input_type: Literal["request", "response"], + logging_obj: Optional[Any] = None, + ) -> GenericGuardrailAPIInputs: + structured = inputs.get("structured_messages") or [] + inputs["structured_messages"] = [ + json.loads(json.dumps(message).replace("POISON", "[BLOCKED]")) for message in structured + ] + return inputs + + +class TestAnthropicMessagesScanOnlyToolResults: + def _guardrail(self): + guardrail = InputsRecordingGuardrail() + guardrail.scan_only_tool_results = True + return guardrail + + @pytest.mark.asyncio + async def test_structured_write_back_merges_into_the_full_conversation(self): + handler = AnthropicMessagesHandler() + guardrail = StructuredMessagesRewritingGuardrail() + guardrail.scan_only_tool_results = True + data = { + "model": "claude-sonnet-4-5", + "system": "You are a careful agent harness.", + "messages": [ + {"role": "user", "content": "fetch the page"}, + { + "role": "assistant", + "content": [{"type": "tool_use", "id": "tu1", "name": "Bash", "input": {"cmd": "curl"}}], + }, + { + "role": "user", + "content": [{"type": "tool_result", "tool_use_id": "tu1", "content": "fetched POISON page"}], + }, + ], + } + + await handler.process_input_messages(data=data, guardrail_to_apply=guardrail) + + assert data["system"] == "You are a careful agent harness." + assert [m["role"] for m in data["messages"]] == ["user", "assistant", "user"], ( + "a redacting guardrail must not strip out-of-scope turns from the request" + ) + serialized = json.dumps(data["messages"]) + assert "fetch the page" in serialized + assert "tool_use" in serialized + assert "fetched [BLOCKED] page" in serialized + assert "POISON" not in serialized + + @pytest.mark.asyncio + async def test_scan_narrows_to_tool_results_and_write_back_stays_aligned(self): + handler = AnthropicMessagesHandler() + guardrail = self._guardrail() + data = { + "model": "claude-sonnet-4-5", + "system": "You are a trusted agent harness with POISON heuristics.", + "tools": [ + { + "name": "Bash", + "description": "run a command", + "input_schema": {"type": "object", "properties": {}}, + } + ], + "messages": [ + {"role": "user", "content": "scaffolding POISON prompt"}, + { + "role": "assistant", + "content": [{"type": "tool_use", "id": "tu1", "name": "Bash", "input": {"cmd": "curl"}}], + }, + { + "role": "user", + "content": [ + {"type": "text", "text": "sibling POISON text"}, + {"type": "tool_result", "tool_use_id": "tu1", "content": "fetched POISON page"}, + ], + }, + ], + } + + await handler.process_input_messages(data=data, guardrail_to_apply=guardrail) + + assert guardrail.seen_texts == ["fetched POISON page"], ( + "only the tool_result payload may reach the guardrail" + ) + assert guardrail.captured_inputs is not None + assert guardrail.captured_inputs.get("tools") is None + assert [m["role"] for m in guardrail.captured_inputs["structured_messages"]] == ["tool"] + assert data["messages"][2]["content"][1]["content"] == "fetched [BLOCKED] page" + assert data["messages"][0]["content"] == "scaffolding POISON prompt", ( + "out-of-scope content must come back untouched, not masked or dropped" + ) + assert data["messages"][2]["content"][0]["text"] == "sibling POISON text" + + @pytest.mark.asyncio + async def test_guardrail_synthesized_tools_are_appended_without_replacing_request_tools(self): + handler = AnthropicMessagesHandler() + guardrail = ToolAppendingGuardrail(guardrail_name="tool-appending") + guardrail.scan_only_tool_results = True + original_tools = [ + { + "name": "get_weather", + "description": "Get the weather at a specific location", + "input_schema": {"type": "object", "properties": {"location": {"type": "string"}}}, + } + ] + data = { + "model": "claude-sonnet-4-5", + "tools": original_tools, + "messages": [ + {"role": "user", "content": "what's the weather?"}, + { + "role": "assistant", + "content": [{"type": "tool_use", "id": "tu1", "name": "get_weather", "input": {}}], + }, + { + "role": "user", + "content": [{"type": "tool_result", "tool_use_id": "tu1", "content": "sunny"}], + }, + ], + } + + await handler.process_input_messages(data=data, guardrail_to_apply=guardrail) + + assert [t["name"] for t in data["tools"]] == ["get_weather", "injected_tool"], ( + "a tool the guardrail synthesized must reach the model, converted to Anthropic format, " + "without the request's own tools being replaced or dropped" + ) + assert data["tools"][0] == original_tools[0] + + @pytest.mark.asyncio + async def test_guardrail_is_not_called_when_the_request_has_no_tool_results(self): + handler = AnthropicMessagesHandler() + guardrail = self._guardrail() + data = { + "model": "claude-sonnet-4-5", + "messages": [{"role": "user", "content": "What is 2 plus 2?"}], + } + + await handler.process_input_messages(data=data, guardrail_to_apply=guardrail) + + assert guardrail.captured_inputs is None + assert guardrail.seen_texts == [] + + @pytest.mark.asyncio + async def test_images_are_scoped_the_same_way_as_texts(self): + handler = AnthropicMessagesHandler() + guardrail = self._guardrail() + data = { + "model": "claude-sonnet-4-5", + "messages": [ + { + "role": "user", + "content": [{"type": "image", "source": {"type": "base64", "data": "USER_IMG"}}], + }, + { + "role": "user", + "content": [ + { + "type": "tool_result", + "tool_use_id": "tu1", + "content": [ + {"type": "text", "text": "screenshot POISON"}, + {"type": "image", "source": {"type": "base64", "data": "TOOL_IMG"}}, + ], + } + ], + }, + ], + } + + await handler.process_input_messages(data=data, guardrail_to_apply=guardrail) + + assert guardrail.captured_inputs is not None + assert guardrail.captured_inputs.get("images") == ["TOOL_IMG"] diff --git a/tests/test_litellm/llms/openai/chat/guardrail_translation/test_openai_guardrail_handler.py b/tests/test_litellm/llms/openai/chat/guardrail_translation/test_openai_guardrail_handler.py index 7730b664c5e..2e75f29b1c5 100644 --- a/tests/test_litellm/llms/openai/chat/guardrail_translation/test_openai_guardrail_handler.py +++ b/tests/test_litellm/llms/openai/chat/guardrail_translation/test_openai_guardrail_handler.py @@ -1229,3 +1229,338 @@ class TestIncrementalScanRespectsSkipFlags: assert mock_api.call_count == 1 scanned = [m["content"] for m in mock_api.call_args.kwargs["messages"]] assert scanned == ["It is sunny in Paris.", "And tomorrow?"] + + +class StructuredRedactionGuardrail(CustomGuardrail): + """Captures inputs and returns a new structured_messages list with a canary redacted.""" + + def __init__(self): + super().__init__(guardrail_name="structured-redaction") + self.captured_inputs: Optional[GenericGuardrailAPIInputs] = None + + async def apply_guardrail( + self, + inputs: GenericGuardrailAPIInputs, + request_data: dict, + input_type: Literal["request", "response"], + logging_obj: Optional[Any] = None, + ) -> GenericGuardrailAPIInputs: + self.captured_inputs = inputs + structured = inputs.get("structured_messages") or [] + inputs["structured_messages"] = [ + {**m, "content": str(m.get("content", "")).replace("POISON", "[BLOCKED]")} for m in structured + ] + return inputs + + +class ToolSynthesizingGuardrail(CustomGuardrail): + """Appends its own function tool to whatever tools it was given, like a + retrieval/recovery guardrail that injects a tool the model can later call.""" + + def __init__(self): + super().__init__(guardrail_name="tool-synthesizing") + + async def apply_guardrail( + self, + inputs: GenericGuardrailAPIInputs, + request_data: dict, + input_type: Literal["request", "response"], + logging_obj: Optional[Any] = None, + ) -> GenericGuardrailAPIInputs: + tools = list(inputs.get("tools") or []) + tools.append( + { + "type": "function", + "function": {"name": "injected_retrieve", "parameters": {"type": "object", "properties": {}}}, + } + ) + inputs["tools"] = tools + return inputs + + +class ToolNameCollidingGuardrail(CustomGuardrail): + """Returns a tool reusing a request tool's name plus a genuinely new tool.""" + + def __init__(self): + super().__init__(guardrail_name="tool-name-colliding") + + async def apply_guardrail( + self, + inputs: GenericGuardrailAPIInputs, + request_data: dict, + input_type: Literal["request", "response"], + logging_obj: Optional[Any] = None, + ) -> GenericGuardrailAPIInputs: + inputs["tools"] = [ + { + "type": "function", + "function": { + "name": "read_file", + "parameters": {"type": "object", "properties": {"hijacked": {"type": "string"}}}, + }, + }, + { + "type": "function", + "function": {"name": "injected_retrieve", "parameters": {"type": "object", "properties": {}}}, + }, + ] + return inputs + + +class DuplicateToolReturningGuardrail(CustomGuardrail): + """Returns the same synthesized tool name twice, second copy with a different schema.""" + + def __init__(self): + super().__init__(guardrail_name="duplicate-tool-returning") + + async def apply_guardrail( + self, + inputs: GenericGuardrailAPIInputs, + request_data: dict, + input_type: Literal["request", "response"], + logging_obj: Optional[Any] = None, + ) -> GenericGuardrailAPIInputs: + inputs["tools"] = [ + { + "type": "function", + "function": { + "name": "injected_retrieve", + "parameters": {"type": "object", "properties": {"first": {"type": "string"}}}, + }, + }, + { + "type": "function", + "function": { + "name": "injected_retrieve", + "parameters": {"type": "object", "properties": {"second": {"type": "string"}}}, + }, + }, + ] + return inputs + + +class TestScanOnlyToolResults: + def _bedrock_guardrail(self): + from litellm.proxy.guardrails.guardrail_hooks.bedrock_guardrails import BedrockGuardrail + + guardrail = BedrockGuardrail( + guardrail_name="bedrock-scan-only-tool-results", + guardrailIdentifier="test-guardrail", + guardrailVersion="DRAFT", + default_on=True, + ) + guardrail.scan_only_tool_results = True + return guardrail + + @pytest.mark.asyncio + async def test_only_tool_role_content_is_scanned(self): + from unittest.mock import AsyncMock, patch + + handler = OpenAIChatCompletionsHandler() + guardrail = self._bedrock_guardrail() + data = { + "messages": [ + {"role": "system", "content": "SYSTEM-PROMPT-not-scanned"}, + {"role": "user", "content": "USER-PROMPT-not-scanned"}, + { + "role": "assistant", + "content": "ASSISTANT-not-scanned", + "tool_calls": [ + { + "id": "call_1", + "type": "function", + "function": {"name": "read_file", "arguments": '{"path": "report.html"}'}, + } + ], + }, + {"role": "tool", "tool_call_id": "call_1", "content": "TOOL-RESULT-scanned"}, + ] + } + with patch.object(guardrail, "make_bedrock_api_request", new_callable=AsyncMock) as mock_api: + mock_api.return_value = {"action": "NONE", "output": [], "outputs": []} + await handler.process_input_messages(data=data, guardrail_to_apply=guardrail) + assert mock_api.call_count == 1 + scanned = [m["content"] for m in mock_api.call_args.kwargs["messages"]] + assert scanned == ["TOOL-RESULT-scanned"] + + @pytest.mark.asyncio + async def test_legacy_function_role_results_are_scanned(self): + from unittest.mock import AsyncMock, patch + + handler = OpenAIChatCompletionsHandler() + guardrail = self._bedrock_guardrail() + data = { + "messages": [ + {"role": "user", "content": "USER-PROMPT-not-scanned"}, + {"role": "function", "name": "read_file", "content": "FUNCTION-RESULT-scanned"}, + {"role": "tool", "tool_call_id": "call_1", "content": "TOOL-RESULT-scanned"}, + ] + } + with patch.object(guardrail, "make_bedrock_api_request", new_callable=AsyncMock) as mock_api: + mock_api.return_value = {"action": "NONE", "output": [], "outputs": []} + await handler.process_input_messages(data=data, guardrail_to_apply=guardrail) + assert mock_api.call_count == 1 + scanned = [m["content"] for m in mock_api.call_args.kwargs["messages"]] + assert scanned == ["FUNCTION-RESULT-scanned", "TOOL-RESULT-scanned"], ( + "a tool result sent with the legacy function role must not bypass the scoped scan" + ) + + @pytest.mark.parametrize("flag_value", [None, "false", 0, object()]) + @pytest.mark.asyncio + async def test_scope_narrows_only_when_the_flag_is_actually_true(self, flag_value): + from unittest.mock import AsyncMock, patch + + handler = OpenAIChatCompletionsHandler() + guardrail = self._bedrock_guardrail() + guardrail.scan_only_tool_results = flag_value + data = { + "messages": [ + {"role": "user", "content": "USER-PROMPT"}, + {"role": "tool", "tool_call_id": "call_1", "content": "TOOL-RESULT"}, + ] + } + with patch.object(guardrail, "make_bedrock_api_request", new_callable=AsyncMock) as mock_api: + mock_api.return_value = {"action": "NONE", "output": [], "outputs": []} + await handler.process_input_messages(data=data, guardrail_to_apply=guardrail) + assert mock_api.call_count == 1 + scanned = [m["content"] for m in mock_api.call_args.kwargs["messages"]] + assert scanned == ["USER-PROMPT", "TOOL-RESULT"], ( + "anything but an explicit True must leave the whole request in scope" + ) + + @pytest.mark.parametrize("scan_only_tool_results", [True, False]) + @pytest.mark.asyncio + async def test_function_definitions_are_scoped_out_with_the_tool_results_flag(self, scan_only_tool_results): + handler = OpenAIChatCompletionsHandler() + guardrail = StructuredRedactionGuardrail() + guardrail.scan_only_tool_results = scan_only_tool_results + tools = [ + { + "type": "function", + "function": {"name": "read_file", "parameters": {"type": "object", "properties": {}}}, + } + ] + data = { + "messages": [ + {"role": "user", "content": "read the report"}, + {"role": "tool", "tool_call_id": "call_1", "content": "TOOL-RESULT"}, + ], + "tools": tools, + } + + await handler.process_input_messages(data=data, guardrail_to_apply=guardrail) + + assert guardrail.captured_inputs is not None + expected_tools = None if scan_only_tool_results else tools + assert guardrail.captured_inputs.get("tools") == expected_tools, ( + "function definitions must stay out of a tool-results-only scan" + ) + + @pytest.mark.parametrize("scan_only_tool_results", [True, False]) + @pytest.mark.asyncio + async def test_guardrail_synthesized_tools_are_appended_without_replacing_request_tools( + self, scan_only_tool_results + ): + handler = OpenAIChatCompletionsHandler() + guardrail = ToolSynthesizingGuardrail() + guardrail.scan_only_tool_results = scan_only_tool_results + original_tools = [ + { + "type": "function", + "function": {"name": "read_file", "parameters": {"type": "object", "properties": {}}}, + } + ] + data = { + "messages": [ + {"role": "user", "content": "read the report"}, + {"role": "tool", "tool_call_id": "call_1", "content": "TOOL-RESULT"}, + ], + "tools": original_tools, + } + + await handler.process_input_messages(data=data, guardrail_to_apply=guardrail) + + assert [t["function"]["name"] for t in data["tools"]] == ["read_file", "injected_retrieve"], ( + "a tool the guardrail synthesized (like a recovery/retrieve tool) must reach the model " + "without the request's own tools being replaced or dropped" + ) + assert data["tools"][0] == original_tools[0] + + @pytest.mark.asyncio + async def test_returned_tool_name_collisions_keep_the_request_schema(self): + handler = OpenAIChatCompletionsHandler() + guardrail = ToolNameCollidingGuardrail() + guardrail.scan_only_tool_results = True + original_read_file = { + "type": "function", + "function": {"name": "read_file", "parameters": {"type": "object", "properties": {}}}, + } + data = { + "messages": [ + {"role": "user", "content": "read the report"}, + {"role": "tool", "tool_call_id": "call_1", "content": "TOOL-RESULT"}, + ], + "tools": [original_read_file], + } + + await handler.process_input_messages(data=data, guardrail_to_apply=guardrail) + + assert [t["function"]["name"] for t in data["tools"]] == ["read_file", "injected_retrieve"] + assert data["tools"][0] == original_read_file, ( + "a returned tool reusing a request tool's name must not replace the request's schema" + ) + + @pytest.mark.asyncio + async def test_duplicate_returned_tool_names_keep_only_the_first(self): + handler = OpenAIChatCompletionsHandler() + guardrail = DuplicateToolReturningGuardrail() + guardrail.scan_only_tool_results = True + original_read_file = { + "type": "function", + "function": {"name": "read_file", "parameters": {"type": "object", "properties": {}}}, + } + data = { + "messages": [ + {"role": "user", "content": "read the report"}, + {"role": "tool", "tool_call_id": "call_1", "content": "TOOL-RESULT"}, + ], + "tools": [original_read_file], + } + + await handler.process_input_messages(data=data, guardrail_to_apply=guardrail) + + assert [t["function"]["name"] for t in data["tools"]] == ["read_file", "injected_retrieve"], ( + "two returned tools sharing a name must not both be forwarded to the provider" + ) + assert data["tools"][1]["function"]["parameters"]["properties"] == {"first": {"type": "string"}} + + @pytest.mark.asyncio + async def test_structured_write_back_keeps_out_of_scope_messages(self): + handler = OpenAIChatCompletionsHandler() + guardrail = StructuredRedactionGuardrail() + guardrail.scan_only_tool_results = True + data = { + "messages": [ + {"role": "system", "content": "SYSTEM-PROMPT"}, + {"role": "user", "content": "fetch the page"}, + { + "role": "assistant", + "content": "fetching", + "tool_calls": [ + {"id": "call_1", "type": "function", "function": {"name": "fetch", "arguments": "{}"}} + ], + }, + {"role": "tool", "tool_call_id": "call_1", "content": "page says POISON here"}, + {"role": "user", "content": "and then?"}, + ] + } + + await handler.process_input_messages(data=data, guardrail_to_apply=guardrail) + + assert [m["role"] for m in data["messages"]] == ["system", "user", "assistant", "tool", "user"], ( + "a redacting guardrail must not strip out-of-scope messages from the request" + ) + assert data["messages"][0]["content"] == "SYSTEM-PROMPT" + assert data["messages"][3]["content"] == "page says [BLOCKED] here" + assert data["messages"][3]["tool_call_id"] == "call_1" + assert data["messages"][4]["content"] == "and then?" diff --git a/tests/test_litellm/proxy/anthropic_endpoints/test_claude_code_marketplace.py b/tests/test_litellm/proxy/anthropic_endpoints/test_claude_code_marketplace.py index f94cd471a01..18e0f2cb559 100644 --- a/tests/test_litellm/proxy/anthropic_endpoints/test_claude_code_marketplace.py +++ b/tests/test_litellm/proxy/anthropic_endpoints/test_claude_code_marketplace.py @@ -18,13 +18,14 @@ from litellm.types.proxy.claude_code_endpoints import ( UpdatePluginRequest, ) from litellm.proxy.anthropic_endpoints.claude_code_endpoints.claude_code_marketplace import ( + get_marketplace, register_plugin, update_plugin, ) def _make_mock_prisma(): - """Stateful prisma mock that supports find_unique, create, and update.""" + """Stateful prisma mock that supports find_unique, find_many, create, and update.""" store: dict = {} mock_client = MagicMock() @@ -34,6 +35,12 @@ def _make_mock_prisma(): async def _find_unique(where): return store.get(where.get("name")) + async def _find_many(where=None): + records = list(store.values()) + if where and "enabled" in where: + return [r for r in records if r.enabled == where["enabled"]] + return records + async def _create(data): record = MagicMock() record.id = "test-id" @@ -52,6 +59,7 @@ def _make_mock_prisma(): return record mock_table.find_unique = AsyncMock(side_effect=_find_unique) + mock_table.find_many = AsyncMock(side_effect=_find_many) mock_table.create = AsyncMock(side_effect=_create) mock_table.update = AsyncMock(side_effect=_update) mock_client.db.litellm_claudecodeplugintable = mock_table @@ -211,6 +219,23 @@ async def test_update_plugin_db_error_maps_to_structured_500(): assert "connection lost" in exc_info.value.detail["error"] +@pytest.mark.asyncio +async def test_get_marketplace_skips_plugin_with_null_manifest(): + await register_plugin( + request=RegisterPluginRequest(name="good-plugin", source=_GIT_SUBDIR_SOURCE, version="1.0.0"), + user_api_key_dict=_USER, + ) + + table = litellm.proxy.proxy_server.prisma_client.db.litellm_claudecodeplugintable + await table.create(data={"name": "null-manifest-plugin", "manifest_json": None, "enabled": True}) + + response = await get_marketplace() + + assert response.status_code == 200 + body = json.loads(response.body) + assert [plugin["name"] for plugin in body["plugins"]] == ["good-plugin"] + + @pytest.mark.asyncio async def test_register_plugin_git_subdir_missing_url(): """git-subdir without url field raises HTTP 400.""" diff --git a/tests/test_litellm/proxy/auth/test_route_checks.py b/tests/test_litellm/proxy/auth/test_route_checks.py index 9285b997efc..0bfb10320f7 100644 --- a/tests/test_litellm/proxy/auth/test_route_checks.py +++ b/tests/test_litellm/proxy/auth/test_route_checks.py @@ -3246,3 +3246,55 @@ def test_internal_user_still_blocked_from_another_users_info(): assert exc_info.value.status_code == 403 assert "key not allowed to access this user's info" in str(exc_info.value.detail) + + +@pytest.mark.parametrize( + "route", + [ + "/user/daily/activity", + "/user/daily/activity/aggregated", + ], +) +@pytest.mark.parametrize( + "user_role", + [ + LitellmUserRoles.INTERNAL_USER.value, + LitellmUserRoles.INTERNAL_USER_VIEW_ONLY.value, + ], +) +def test_user_daily_activity_routes_reachable_by_non_admin(route, user_role): + """Both /user/daily/activity and its /aggregated sibling power the default + "Your Usage" dashboard view, and both handlers self-scope to the caller + (_user_has_admin_view -> require_caller_user_id_for_non_admin -> 403 on a + user_id mismatch). self_managed_routes is the ONLY list that grants either + route to a non-admin, so dropping one from it 401s every internal user's + main Usage page before the handler ever runs. + """ + user_obj = LiteLLM_UserTable( + user_id="test_user", + user_email="test@example.com", + user_role=user_role, + ) + valid_token = UserAPIKeyAuth(user_id="test_user", user_role=user_role) + request = MagicMock(spec=Request) + request.query_params = {} + + RouteChecks.non_proxy_admin_allowed_routes_check( + user_obj=user_obj, + _user_role=user_role, + route=route, + request=request, + valid_token=valid_token, + request_data={}, + ) + + +def test_user_daily_activity_aggregated_not_covered_by_prefix_match(): + """check_route_access is exact-match plus explicit wildcards, so listing the + parent /user/daily/activity does not implicitly cover the /aggregated + sub-path. Pins the reason the sibling needs its own entry. + """ + assert not RouteChecks.check_route_access( + route="/user/daily/activity/aggregated", + allowed_routes=["/user/daily/activity"], + ) diff --git a/tests/test_litellm/proxy/batches_endpoints/test_endpoints.py b/tests/test_litellm/proxy/batches_endpoints/test_endpoints.py index f2d37fbe842..e758aa5ca7f 100644 --- a/tests/test_litellm/proxy/batches_endpoints/test_endpoints.py +++ b/tests/test_litellm/proxy/batches_endpoints/test_endpoints.py @@ -469,13 +469,14 @@ async def test_create__fallback_body_custom_llm_provider(harness): @pytest.mark.asyncio -async def test_create__unified_file_id_single_model(harness): +async def test_create__unified_file_id_single_model_disables_cross_model_fallbacks(harness): set_body( harness, { "input_file_id": "litellm_proxy_unified_id", "endpoint": "/v1/chat/completions", "completion_window": "24h", + "disable_fallbacks": False, }, ) with ( @@ -489,6 +490,7 @@ async def test_create__unified_file_id_single_model(harness): harness.litellm_acreate.assert_not_called() # model injected from the unified id, input_file_id restored, hidden param set assert harness.router_kwargs()["model"] == "gpt-4o-mini" + assert harness.router_kwargs()["disable_fallbacks"] is True assert resp.input_file_id == "litellm_proxy_unified_id" assert resp._hidden_params["unified_file_id"] == "unified-xyz" @@ -1896,6 +1898,17 @@ async def test_cancel__unified_batch_id_routes_to_router(cancel_harness): assert cancel_harness.update_batch_in_db.call_args.kwargs["operation"] == "cancel" +@pytest.mark.asyncio +async def test_cancel__db_write_receives_caller_auth(cancel_harness): + """update_batch_in_database can only mint managed IDs for a cancelled batch's + output files when it has an auth context, so cancel must forward the caller's.""" + caller = UserAPIKeyAuth(api_key="sk-test", user_id="user-cancel-1") + with patch.object(endpoints, "_is_base64_encoded_unified_file_id", return_value=UNIFIED_BATCH_ID): + await call_cancel(cancel_harness, "batch-unified-blob", user=caller) + + assert cancel_harness.update_batch_in_db.call_args.kwargs["user_api_key_dict"] is caller + + @pytest.mark.asyncio async def test_cancel__unified_missing_model_id_400(cancel_harness): # unified id with no model_id segment -> get_model_id returns None -> 400. diff --git a/tests/test_litellm/proxy/guardrails/guardrail_hooks/test_bedrock_guardrails.py b/tests/test_litellm/proxy/guardrails/guardrail_hooks/test_bedrock_guardrails.py index 65d6e33588f..76a695ce3fd 100644 --- a/tests/test_litellm/proxy/guardrails/guardrail_hooks/test_bedrock_guardrails.py +++ b/tests/test_litellm/proxy/guardrails/guardrail_hooks/test_bedrock_guardrails.py @@ -3670,3 +3670,40 @@ async def test_moderation_hook_honors_the_mcp_event_type(mode, call_type, should "the scan must be logged under the event it actually ran for, so guardrail logs, " "OTel spans, and Langfuse metadata do not misclassify MCP enforcement as an LLM call" ) + + +class TestScanOnlyToolResultsWithLatestRoleFilter: + @pytest.mark.asyncio + async def test_warns_and_skips_when_scoped_payload_has_no_user_message(self): + """scan_only_tool_results hands Bedrock a tool-role-only payload, but + experimental_use_latest_role_message_only scans only the latest user + message: the silent no-op must warn.""" + guardrail = BedrockGuardrail( + guardrail_name="bedrock-latest-role-scoped", + guardrailIdentifier="test-guardrail", + guardrailVersion="DRAFT", + default_on=True, + experimental_use_latest_role_message_only=True, + ) + guardrail.scan_only_tool_results = True + inputs = { + "texts": ["TOOL-RESULT"], + "structured_messages": [{"role": "tool", "tool_call_id": "call_1", "content": "TOOL-RESULT"}], + } + + with ( + patch.object(guardrail, "make_bedrock_api_request", new_callable=AsyncMock) as mock_api, + patch( + "litellm.proxy.guardrails.guardrail_hooks.bedrock_guardrails.verbose_proxy_logger.warning" + ) as mock_warning, + ): + result = await guardrail.apply_guardrail( + inputs=inputs, + request_data={"litellm_call_id": "test-call-id"}, + input_type="request", + ) + + mock_api.assert_not_called() + assert result["texts"] == ["TOOL-RESULT"] + warning_text = " ".join(str(arg) for c in mock_warning.call_args_list for arg in c.args) + assert "scan_only_tool_results" in warning_text diff --git a/tests/test_litellm/proxy/guardrails/guardrail_hooks/test_panw_prisma_airs.py b/tests/test_litellm/proxy/guardrails/guardrail_hooks/test_panw_prisma_airs.py index 431a7aa6f02..2f0fd51539d 100644 --- a/tests/test_litellm/proxy/guardrails/guardrail_hooks/test_panw_prisma_airs.py +++ b/tests/test_litellm/proxy/guardrails/guardrail_hooks/test_panw_prisma_airs.py @@ -1696,6 +1696,34 @@ class TestPanwAirsApplyGuardrail: request_data=request_data, guardrail_name=handler.guardrail_name ) + @pytest.mark.asyncio + async def test_apply_guardrail_warns_when_tool_results_scope_leaves_nothing_scannable(self, handler): + """scan_only_tool_results hands PANW a tool-role-only payload, but PANW's role + filter only scans user/system/developer rows: the silent no-op must warn.""" + handler.scan_only_tool_results = True + inputs: GenericGuardrailAPIInputs = { + "texts": ["TOOL-RESULT"], + "structured_messages": [{"role": "tool", "tool_call_id": "call_1", "content": "TOOL-RESULT"}], + } + request_data = {"litellm_call_id": "test-call-id", "model": "gpt-4"} + + with ( + patch.object(handler, "_call_panw_api", new_callable=AsyncMock) as mock_api, + patch( + "litellm.proxy.guardrails.guardrail_hooks.panw_prisma_airs.panw_prisma_airs.verbose_proxy_logger.warning" + ) as mock_warning, + ): + result = await handler.apply_guardrail( + inputs=inputs, + request_data=request_data, + input_type="request", + ) + + mock_api.assert_not_called() + assert result["texts"] == ["TOOL-RESULT"] + warning_text = " ".join(str(arg) for c in mock_warning.call_args_list for arg in c.args) + assert "scan_only_tool_results" in warning_text + @pytest.mark.asyncio async def test_apply_guardrail_block(self, handler): """Test block action raises HTTPException(400).""" diff --git a/tests/test_litellm/proxy/guardrails/test_guardrail_registry.py b/tests/test_litellm/proxy/guardrails/test_guardrail_registry.py index 6bd109f0f95..729dbce6b9a 100644 --- a/tests/test_litellm/proxy/guardrails/test_guardrail_registry.py +++ b/tests/test_litellm/proxy/guardrails/test_guardrail_registry.py @@ -558,3 +558,102 @@ def test_reinitialized_judge_guardrail_uses_lazy_router_provider(): finally: for cb_list, snapshot in zip(lists, snapshots): cb_list[:] = snapshot + + +class TestScanOnlyToolResultsInitRefusal: + """A guardrail whose role filtering never scans tool results must be rejected at + initialization when configured with scan_only_tool_results, instead of booting a + proxy that silently scans nothing on every request.""" + + def _initialize(self, name: str, params: dict): + lists = _all_callback_lists() + snapshots = [list(cb_list) for cb_list in lists] + try: + return InMemoryGuardrailHandler().initialize_guardrail( + guardrail={"guardrail_name": name, "litellm_params": params}, + ) + finally: + for cb_list, snapshot in zip(lists, snapshots): + cb_list[:] = snapshot + + def test_panw_prisma_airs_with_scan_only_tool_results_is_rejected(self): + with pytest.raises(ValueError, match="never scans tool results"): + self._initialize( + "panw-scan-only-combo", + { + "guardrail": "panw_prisma_airs", + "mode": "pre_call", + "api_key": "test-key", + "profile_name": "test-profile", + "scan_only_tool_results": True, + }, + ) + + def test_bedrock_latest_role_with_scan_only_tool_results_is_rejected(self): + with pytest.raises(ValueError, match="never scans tool results"): + self._initialize( + "bedrock-latest-role-scan-only-combo", + { + "guardrail": "bedrock", + "mode": "pre_call", + "guardrailIdentifier": "gr-1", + "guardrailVersion": "1", + "experimental_use_latest_role_message_only": True, + "scan_only_tool_results": True, + }, + ) + + def test_bedrock_without_latest_role_accepts_scan_only_tool_results(self): + result = self._initialize( + "bedrock-scan-only-ok", + { + "guardrail": "bedrock", + "mode": "pre_call", + "guardrailIdentifier": "gr-1", + "guardrailVersion": "1", + "scan_only_tool_results": True, + }, + ) + assert result is not None + + def test_prompt_security_default_tool_filtering_rejects_scan_only_tool_results(self, monkeypatch): + monkeypatch.delenv("PROMPT_SECURITY_CHECK_TOOL_RESULTS", raising=False) + with pytest.raises(ValueError, match="never scans tool results"): + self._initialize( + "prompt-security-scan-only-combo", + { + "guardrail": "prompt_security", + "mode": "pre_call", + "api_key": "test-key", + "api_base": "https://ps.example.com", + "scan_only_tool_results": True, + }, + ) + + def test_prompt_security_check_tool_results_accepts_scan_only_tool_results(self, monkeypatch): + monkeypatch.setenv("PROMPT_SECURITY_CHECK_TOOL_RESULTS", "true") + result = self._initialize( + "prompt-security-scan-only-ok", + { + "guardrail": "prompt_security", + "mode": "pre_call", + "api_key": "test-key", + "api_base": "https://ps.example.com", + "scan_only_tool_results": True, + }, + ) + assert result is not None + + def test_skip_tool_message_with_scan_only_tool_results_is_rejected(self): + with pytest.raises(ValueError, match="skip_tool_message_in_guardrail are enabled together"): + self._initialize( + "bedrock-skip-tool-scan-only-combo", + { + "guardrail": "bedrock", + "mode": "pre_call", + "guardrailIdentifier": "gr-1", + "guardrailVersion": "1", + "skip_tool_message_in_guardrail": True, + "scan_only_tool_results": True, + }, + ) diff --git a/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py b/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py index f289148101a..69f04ce2bbe 100644 --- a/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py +++ b/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py @@ -1186,6 +1186,7 @@ async def test_track_cost_callback_enriches_user_id_for_mcp_style_metadata(): ("pass_through_endpoint", True), ("llm_passthrough_route", True), ("allm_passthrough_route", True), + ("aretrieve_batch", True), ("acompletion", False), ("call_mcp_tool", False), (None, False), @@ -1194,7 +1195,14 @@ async def test_track_cost_callback_enriches_user_id_for_mcp_style_metadata(): def test_should_track_cost_callback_pass_through_without_owner(call_type, expected): """Regression for LIT-3782: unauthenticated pass-through requests (auth=false) carry no key/user/team/end-user, yet must still be tracked so they land in - LiteLLM_SpendLogs. Other call types with no owner stay untracked.""" + LiteLLM_SpendLogs. Other call types with no owner stay untracked. + + aretrieve_batch is included for the same reason: CheckBatchCost's synthetic + logging_obj for a completed managed batch only ever carries + user_api_key_user_id/user_api_key_team_id from LiteLLM_ManagedObjectTable, + both of which are None for a batch created with the master key or a + team-less key (the table never stores the raw key hash). Before this fix, + such a batch's cost silently never reached LiteLLM_SpendLogs.""" assert ( _should_track_cost_callback( user_api_key=None, @@ -1211,6 +1219,7 @@ def test_should_track_cost_callback_pass_through_without_owner(call_type, expect "call_type, expect_spend_log", [ ("pass_through_endpoint", True), + ("aretrieve_batch", True), ("acompletion", False), (None, False), ], @@ -1223,7 +1232,11 @@ async def test_track_cost_callback_logs_unauthenticated_pass_through_request( cost callback with no key/user/team/end-user. Before the fix the spend-log write was skipped and the request never appeared in request/usage logs. It must now be written for pass-through call types while other unauthenticated - calls remain skipped.""" + calls remain skipped. + + aretrieve_batch is included because CheckBatchCost's completed-batch cost + event reaches this same callback with no attributable key/user/team when + the batch was created with the master key or a team-less key.""" logger = _ProxyDBLogger() kwargs = { diff --git a/tests/test_litellm/proxy/management_endpoints/search_endpoints/test_search_tool_management.py b/tests/test_litellm/proxy/management_endpoints/search_endpoints/test_search_tool_management.py index f2ccfcd0155..a64397d9818 100644 --- a/tests/test_litellm/proxy/management_endpoints/search_endpoints/test_search_tool_management.py +++ b/tests/test_litellm/proxy/management_endpoints/search_endpoints/test_search_tool_management.py @@ -5,6 +5,7 @@ from datetime import datetime from unittest.mock import AsyncMock, MagicMock, patch import pytest +from fastapi import HTTPException from fastapi.testclient import TestClient sys.path.insert( @@ -23,6 +24,7 @@ import litellm.proxy.proxy_server as ps # Now we can safely import app from litellm.proxy.proxy_server import app +from litellm.types.search import SearchToolInfoResponse client = TestClient(app) @@ -815,3 +817,183 @@ async def test_list_search_tools_admin_with_restricted_key_still_sees_all(): assert response.status_code == 200 names = {t["search_tool_name"] for t in response.json()["search_tools"]} assert names == {"db-tool-1", "db-tool-2", "db-tool-3"} + + +def _search_tool_responses(*names: str) -> list[SearchToolInfoResponse]: + return [ + SearchToolInfoResponse( + search_tool_id=f"id-{name}", + search_tool_name=name, + litellm_params={"search_provider": "perplexity"}, + search_tool_info=None, + created_at=None, + updated_at=None, + is_from_config=False, + ) + for name in names + ] + + +def _team_ids_looked_up(lookup: AsyncMock) -> list[str]: + return [awaited.args[0] for awaited in lookup.await_args_list] + + +@pytest.mark.asyncio +async def test_list_search_tools_dashboard_session_key_does_not_look_up_the_ui_team(): + """ + Regression: the Admin UI session key is stamped with the reserved team id + ``litellm-dashboard``, which has no row in LiteLLM_TeamTable. Resolving it as a real team + raised 404, which the endpoint reported as a 500, so the Search Tools page was broken for + every non-admin browsing the dashboard. + """ + from litellm.constants import UI_SESSION_TOKEN_TEAM_ID + + dashboard_session_user = UserAPIKeyAuth( + user_role=LitellmUserRoles.INTERNAL_USER, + user_id="internal_user", + team_id=UI_SESSION_TOKEN_TEAM_ID, + ) + ui_team_is_not_a_real_team = AsyncMock( + side_effect=HTTPException( + status_code=404, + detail={"error": f"Team doesn't exist in db. Team={UI_SESSION_TOKEN_TEAM_ID}."}, + ) + ) + + with ( + _mock_search_tool_backend(_scoping_db_tools()), + patch( + "litellm.proxy.auth.auth_checks.get_team_object", + ui_team_is_not_a_real_team, + ), + _override_auth(dashboard_session_user), + ): + response = TestClient(app).get("/search_tools/list") + + assert response.status_code == 200 + names = {t["search_tool_name"] for t in response.json()["search_tools"]} + assert names == {"db-tool-1", "db-tool-2", "db-tool-3"} + ui_team_is_not_a_real_team.assert_not_awaited() + + +@pytest.mark.asyncio +async def test_filter_visible_search_tools_dashboard_session_still_honors_key_allowlist(): + """ + Skipping the synthetic team must not widen visibility: a dashboard session whose key + carries a search_tools allowlist stays scoped to it. + """ + from litellm.constants import UI_SESSION_TOKEN_TEAM_ID + from litellm.proxy.search_endpoints.search_tool_management import ( + _filter_visible_search_tools, + ) + + restricted_dashboard_session = UserAPIKeyAuth( + user_role=LitellmUserRoles.INTERNAL_USER, + user_id="internal_user", + team_id=UI_SESSION_TOKEN_TEAM_ID, + object_permission=LiteLLM_ObjectPermissionTable( + object_permission_id="op-key", + search_tools=["db-tool-3"], + ), + ) + lookup = AsyncMock() + + visible = await _filter_visible_search_tools( + _search_tool_responses("db-tool-1", "db-tool-2", "db-tool-3"), + restricted_dashboard_session, + lookup, + ) + + assert [t["search_tool_name"] for t in visible] == ["db-tool-3"] + lookup.assert_not_awaited() + + +@pytest.mark.asyncio +async def test_filter_visible_search_tools_still_applies_a_real_team_allowlist(): + """A caller with a real team is still resolved and scoped by that team's allowlist.""" + from litellm.proxy.search_endpoints.search_tool_management import ( + _filter_visible_search_tools, + ) + + team_member = UserAPIKeyAuth( + user_role=LitellmUserRoles.INTERNAL_USER, + user_id="internal_user", + team_id="team-1", + ) + lookup = AsyncMock( + return_value=LiteLLM_TeamTable( + team_id="team-1", + object_permission=LiteLLM_ObjectPermissionTable( + object_permission_id="op-team", + search_tools=["db-tool-2"], + ), + ) + ) + + visible = await _filter_visible_search_tools( + _search_tool_responses("db-tool-1", "db-tool-2", "db-tool-3"), + team_member, + lookup, + ) + + assert [t["search_tool_name"] for t in visible] == ["db-tool-2"] + assert _team_ids_looked_up(lookup) == ["team-1"] + + +@pytest.mark.asyncio +async def test_filter_visible_search_tools_propagates_a_real_team_lookup_failure(): + """ + A caller whose real team cannot be resolved must not fall through to "no team", which + would drop that team's allowlist and show tools the caller may not call. + """ + from litellm.proxy.search_endpoints.search_tool_management import ( + _filter_visible_search_tools, + ) + + team_member = UserAPIKeyAuth( + user_role=LitellmUserRoles.INTERNAL_USER, + user_id="internal_user", + team_id="deleted-team", + ) + lookup = AsyncMock(side_effect=HTTPException(status_code=404, detail={"error": "Team doesn't exist in db."})) + + with pytest.raises(HTTPException) as exc_info: + await _filter_visible_search_tools( + _search_tool_responses("db-tool-1", "db-tool-2"), + team_member, + lookup, + ) + + assert exc_info.value.status_code == 404 + assert _team_ids_looked_up(lookup) == ["deleted-team"] + + +@pytest.mark.asyncio +async def test_list_search_tools_reports_a_missing_real_team_as_404(): + """ + The endpoint surfaces a genuine team lookup failure with its own status instead of + masking it as a 500 or quietly returning an unscoped list. + """ + team_member = UserAPIKeyAuth( + user_role=LitellmUserRoles.INTERNAL_USER, + user_id="internal_user", + team_id="deleted-team", + ) + + with ( + _mock_search_tool_backend(_scoping_db_tools()), + patch( + "litellm.proxy.auth.auth_checks.get_team_object", + AsyncMock( + side_effect=HTTPException( + status_code=404, + detail={"error": "Team doesn't exist in db. Team=deleted-team."}, + ) + ), + ), + _override_auth(team_member), + ): + response = TestClient(app).get("/search_tools/list") + + assert response.status_code == 404 + assert "search_tools" not in response.json() diff --git a/tests/test_litellm/proxy/management_endpoints/test_internal_user_endpoints.py b/tests/test_litellm/proxy/management_endpoints/test_internal_user_endpoints.py index aab9a0b4fd0..056c2d3657a 100644 --- a/tests/test_litellm/proxy/management_endpoints/test_internal_user_endpoints.py +++ b/tests/test_litellm/proxy/management_endpoints/test_internal_user_endpoints.py @@ -2294,6 +2294,75 @@ async def test_get_user_daily_activity_aggregated_admin_global_view(monkeypatch) ) +@pytest.mark.asyncio +async def test_get_user_daily_activity_aggregated_non_admin_cannot_view_other_users( + monkeypatch, +): + """ + Same scoping contract as + test_get_user_daily_activity_non_admin_cannot_view_other_users, on the + aggregated route. Non-admins reach this handler now that the route is in + self_managed_routes, so the 403-on-mismatch and default-to-self behaviour + has to hold here too: opening the route must not widen access. + """ + from unittest.mock import AsyncMock, MagicMock, patch + + from fastapi import HTTPException + + from litellm.proxy.management_endpoints.internal_user_endpoints import ( + get_user_daily_activity_aggregated, + ) + + mock_prisma_client = MagicMock() + monkeypatch.setattr("litellm.proxy.proxy_server.prisma_client", mock_prisma_client) + + non_admin_key_dict = UserAPIKeyAuth( + user_id="regular-user-123", + user_role=LitellmUserRoles.INTERNAL_USER, + ) + + # Case 1: Non-admin targets another user's data — 403, helper never reached + with patch( + "litellm.proxy.management_endpoints.internal_user_endpoints.get_daily_activity_aggregated", + new_callable=AsyncMock, + ) as mock_get_daily_agg: + with pytest.raises(HTTPException) as exc_info: + await get_user_daily_activity_aggregated( + start_date="2025-01-01", + end_date="2025-01-31", + model=None, + api_key=None, + user_id="other-user-456", + timezone=None, + user_api_key_dict=non_admin_key_dict, + ) + + assert exc_info.value.status_code == 403 + assert "Non-admin users can only view their own spend data" in str(exc_info.value.detail) + mock_get_daily_agg.assert_not_called() + + # Case 2: Non-admin omits user_id — scoped to their own user_id, not global + mock_response = MagicMock() + with patch( + "litellm.proxy.management_endpoints.internal_user_endpoints.get_daily_activity_aggregated", + new_callable=AsyncMock, + return_value=mock_response, + ) as mock_get_daily_agg: + result = await get_user_daily_activity_aggregated( + start_date="2025-01-01", + end_date="2025-01-31", + model=None, + api_key=None, + user_id=None, + timezone=None, + user_api_key_dict=non_admin_key_dict, + ) + + assert result is mock_response + mock_get_daily_agg.assert_called_once() + assert mock_get_daily_agg.call_args.kwargs["entity_id"] == "regular-user-123" + + @pytest.mark.asyncio async def test_delete_user_cleans_up_created_by_invitation_links(mocker): """ diff --git a/tests/test_litellm/test_check_type_discipline.py b/tests/test_litellm/test_check_type_discipline.py index f2bfc637095..4b8533df604 100644 --- a/tests/test_litellm/test_check_type_discipline.py +++ b/tests/test_litellm/test_check_type_discipline.py @@ -175,6 +175,13 @@ def test_unfrozen_literal_still_counts(tmp_path): assert "LIT002" in _codes(tmp_path, "from types import MappingProxyType\nd = {'a': 1}\nm = MappingProxyType(d)\n") +def test_lit002_fix_message_names_mappingproxytype(tmp_path): + f = tmp_path / "snippet.py" + f.write_text("x = {'a': 1}\n", encoding="utf-8") + messages = [v.message for v in checker.check_file(f) if v.code == "LIT002"] + assert "MappingProxyType" in messages[0] + + def test_mutable_ok_with_reason_suppresses_both_rules(tmp_path): codes = _codes(tmp_path, "x: dict[str, int] = {} # mutable-ok: in-place buffer mutated hot path\n") assert "LIT001" not in codes diff --git a/tests/test_litellm/test_conftest_isolation.py b/tests/test_litellm/test_conftest_isolation.py new file mode 100644 index 00000000000..88889ad7740 --- /dev/null +++ b/tests/test_litellm/test_conftest_isolation.py @@ -0,0 +1,13 @@ +import litellm +from litellm import utils as litellm_utils_module + +CANARY_MODEL = "conftest-isolation-canary-model" + + +def test_register_model_ledger_entry_is_scoped_to_this_test(): + litellm.register_model({CANARY_MODEL: {"litellm_provider": "openai", "input_cost_per_token": 0.001}}) + assert CANARY_MODEL in litellm_utils_module._runtime_registered_model_cost + + +def test_register_model_ledger_entry_was_rolled_back(): + assert CANARY_MODEL not in litellm_utils_module._runtime_registered_model_cost diff --git a/tests/test_litellm/test_prisma_generate_if_needed.py b/tests/test_litellm/test_prisma_generate_if_needed.py index 39b9fcc4202..c36f580e24f 100644 --- a/tests/test_litellm/test_prisma_generate_if_needed.py +++ b/tests/test_litellm/test_prisma_generate_if_needed.py @@ -1,4 +1,6 @@ import importlib.util +import os +import sys from pathlib import Path _MODULE_PATH = ( @@ -33,3 +35,30 @@ def test_skip_requires_a_generated_client_even_with_a_matching_stamp(tmp_path): expected = mod.stamp_value(b"schema", "0.11.0") stamp.write_text(expected) assert mod.should_skip(stamp, expected, client_generated=False) is False + + +def test_env_puts_this_interpreters_bin_dir_first_on_path(): + env = mod.env_with_own_bin_first({"PATH": "/usr/bin", "HOME": "/home"}) + bin_dir = str(Path(sys.executable).parent) + assert env["PATH"].split(os.pathsep) == [bin_dir, "/usr/bin"] + assert env["HOME"] == "/home" + + +def test_env_without_an_inherited_path_is_just_the_bin_dir(): + env = mod.env_with_own_bin_first({}) + assert env["PATH"] == str(Path(sys.executable).parent) + + +def test_generate_runs_prisma_with_its_own_bin_dir_leading_the_childs_path(): + seen = {} + + def recorder(cmd, cwd, env): + seen["cmd"] = cmd + seen["cwd"] = cwd + seen["env"] = env + return 0 + + assert mod.run_generate(run=recorder) == 0 + assert seen["cmd"][:4] == [sys.executable, "-m", "prisma", "generate"] + assert seen["cwd"] == mod.REPO_ROOT + assert seen["env"]["PATH"].split(os.pathsep)[0] == str(Path(sys.executable).parent) diff --git a/tests/test_litellm/test_router.py b/tests/test_litellm/test_router.py index b910cc3c5fc..4a3395a7d3f 100644 --- a/tests/test_litellm/test_router.py +++ b/tests/test_litellm/test_router.py @@ -6710,6 +6710,51 @@ def test_get_configured_token_limits_coerces_numeric_strings(): assert router.get_configured_token_limits("quoted-limits-model") == (32000, 8000) +@pytest.mark.asyncio +async def test_acreate_batch_disable_fallbacks_surfaces_owning_provider_error(): + router = litellm.Router( + model_list=[ + { + "model_name": "owning-model", + "litellm_params": { + "model": "openai/gpt-4o-mini", + "api_key": "sk-owning", + }, + }, + { + "model_name": "fallback-model", + "litellm_params": { + "model": "azure/gpt-4o-mini", + "api_key": "sk-fallback", + "api_base": "https://fallback.openai.azure.com", + "api_version": "2024-08-01-preview", + }, + }, + ], + fallbacks=[{"owning-model": ["fallback-model"]}], + num_retries=0, + ) + owning_provider_error = litellm.BadRequestError( + message="completion_window must be one of: 24h", + model="openai/gpt-4o-mini", + llm_provider="openai", + ) + mock_create = AsyncMock(side_effect=owning_provider_error) + + with patch.object(router, "_acreate_batch", mock_create): + with pytest.raises(litellm.BadRequestError, match="24h"): + await router.acreate_batch( + model="owning-model", + input_file_id="file-owned-by-openai", + endpoint="/v1/chat/completions", + completion_window="5m", + disable_fallbacks=True, + ) + + mock_create.assert_awaited_once() + assert mock_create.call_args.kwargs["model"] == "owning-model" + + @pytest.mark.asyncio async def test_acreate_batch_request_bedrock_tags_override_deployment_tags(): import httpx diff --git a/tests/test_litellm/test_type_check_gate.py b/tests/test_litellm/test_type_check_gate.py index e381f787d78..d104e4ca0c8 100644 --- a/tests/test_litellm/test_type_check_gate.py +++ b/tests/test_litellm/test_type_check_gate.py @@ -1,3 +1,4 @@ +import hashlib import importlib.util import json import os @@ -84,33 +85,51 @@ def test_node_options_with_heap_appends_after_caller_flags_so_it_wins(): assert merged == f"--max-old-space-size=4096 --no-warnings {gate.NODE_HEAP_OPTION}" -def _stub_basedpyright(tmp_path, monkeypatch, script_body): - stub = tmp_path / "basedpyright" +def _stub_env(tmp_path, script_body): + bin_dir = tmp_path / "bin" + bin_dir.mkdir(exist_ok=True) + stub = bin_dir / "basedpyright" stub.write_text(f"#!/bin/sh\n{script_body}\n") stub.chmod(0o755) - monkeypatch.setenv("PATH", str(tmp_path), prepend=os.pathsep) + return tmp_path def test_run_basedpyright_exports_the_raised_heap_to_the_child(tmp_path, monkeypatch): captured = tmp_path / "node_options.txt" - _stub_basedpyright( + env_dir = _stub_env( tmp_path, - monkeypatch, f'echo "$NODE_OPTIONS" > "{captured}"\necho \'{{"generalDiagnostics": []}}\'', ) monkeypatch.delenv("NODE_OPTIONS", raising=False) - assert json.loads(gate.run_basedpyright(cwd=tmp_path)) == {"generalDiagnostics": []} + assert json.loads(gate.run_basedpyright(cwd=tmp_path, env_dir=env_dir)) == { + "generalDiagnostics": [] + } assert captured.read_text().strip() == gate.NODE_HEAP_OPTION -def test_run_basedpyright_fails_loudly_on_a_crash_exit_code(tmp_path, monkeypatch): +def test_run_basedpyright_pins_import_resolution_to_the_owned_env(tmp_path): + # basedpyright auto-detects a `.venv` in the project root, and that beats + # PATH order and VIRTUAL_ENV; only an explicit --pythonpath keeps the + # caller's fatter venv (whose extra typed packages flip diagnostics vs CI) + # out of the measurement. + captured = tmp_path / "argv.txt" + env_dir = _stub_env( + tmp_path, + f'echo "$@" > "{captured}"\necho \'{{"generalDiagnostics": []}}\'', + ) + gate.run_basedpyright(cwd=tmp_path, env_dir=env_dir) + argv = captured.read_text().split() + assert argv[argv.index("--pythonpath") + 1] == str(env_dir / "bin" / "python") + + +def test_run_basedpyright_fails_loudly_on_a_crash_exit_code(tmp_path): import pytest # 134 is SIGABRT, what node dies with on a heap OOM; it must never read as a # clean zero-error run. - _stub_basedpyright(tmp_path, monkeypatch, "exit 134") + env_dir = _stub_env(tmp_path, "exit 134") with pytest.raises(SystemExit): - gate.run_basedpyright(cwd=tmp_path) + gate.run_basedpyright(cwd=tmp_path, env_dir=env_dir) def test_at_or_under_ceiling_passes(): @@ -248,6 +267,89 @@ def test_cache_key_changes_with_base_point_and_each_fingerprint(): assert gate.cache_key("abc", ("cfg", "lock2")) != key +def test_fingerprints_carry_the_dependency_group_set(): + # Counts measured under one group set must never be compared against + # another's: the fingerprint difference re-keys every cache entry and + # artifact name, so a changed canonical set falls back to recompute. + assert gate.environment_fingerprints() == gate.environment_fingerprints() + assert gate.environment_fingerprints( + dep_groups=("proxy-dev",) + ) != gate.environment_fingerprints(dep_groups=("proxy-dev", "e2e-dev")) + assert gate.environment_fingerprints()[-1] == "groups:" + ",".join( + gate.TYPECHECK_DEP_GROUPS + ) + + +def test_fingerprints_cover_the_prisma_schema(): + schema_hash = hashlib.sha256(gate.PRISMA_SCHEMA.read_bytes()).hexdigest() + assert schema_hash in gate.environment_fingerprints() + + +def test_env_commands_sync_the_canonical_groups_then_generate_prisma(): + sync, generate = gate.typecheck_env_commands(Path("/envdir")) + assert sync[:3] == ("uv", "sync", "--frozen") + adjacent = list(zip(sync, sync[1:])) + for group in gate.TYPECHECK_DEP_GROUPS: + assert ("--group", group) in adjacent + assert generate == ( + str(Path("/envdir") / "bin" / "python"), + str(gate.PRISMA_GENERATE_SCRIPT), + ) + + +def test_env_interpreter_pin_tracks_pyrightconfigs_python_version(): + configured = json.loads((ROOT / "pyrightconfig.json").read_text())[ + "pythonVersion" + ] + assert gate.typecheck_python_version() == configured + sync = gate.typecheck_env_commands()[0] + assert sync[sync.index("--python") + 1] == configured + + +def test_ensure_env_targets_the_owned_dir_and_runs_sync_then_generate(tmp_path): + calls = [] + + def runner(cmd, env): + calls.append((cmd[:2], env["UV_PROJECT_ENVIRONMENT"])) + return 0 + + assert gate.ensure_typecheck_env(env_dir=tmp_path, run=runner) == tmp_path + assert calls == [ + (("uv", "sync"), str(tmp_path)), + ((str(tmp_path / "bin" / "python"), str(gate.PRISMA_GENERATE_SCRIPT)), str(tmp_path)), + ] + + +def test_ensure_env_fails_loudly_and_stops_at_the_first_failed_step(tmp_path): + import pytest + + calls = [] + + def failing(cmd, env): + calls.append(cmd) + return 2 + + with pytest.raises(SystemExit): + gate.ensure_typecheck_env(env_dir=tmp_path, run=failing) + assert len(calls) == 1 + + +def test_ensure_env_announces_a_cold_provision(tmp_path, capsys): + def runner(cmd, env): + return 0 + + gate.ensure_typecheck_env(env_dir=tmp_path / "fresh", run=runner) + assert "provisioning" in capsys.readouterr().err + + +def test_ensure_env_is_silent_when_the_env_already_exists(tmp_path, capsys): + def runner(cmd, env): + return 0 + + gate.ensure_typecheck_env(env_dir=tmp_path, run=runner) + assert capsys.readouterr().err == "" + + def test_cached_counts_round_trip(tmp_path): path = gate.cache_path(tmp_path, "abc123", ("f1", "f2")) gate.store_counts(tmp_path, path, "abc123", {"reportAny": 3, "reportCall": 1}) @@ -286,15 +388,45 @@ def test_store_prune_spares_a_concurrent_runs_in_flight_scratch(tmp_path): assert gate.load_cached_counts(mine) == {"reportAny": 1} -def test_store_prunes_entries_for_other_branch_points(tmp_path): +def test_store_keeps_a_concurrent_worktrees_entry_for_another_branch_point(tmp_path): old = gate.cache_path(tmp_path, "old", ("f",)) gate.store_counts(tmp_path, old, "old", {"reportAny": 1}) new = gate.cache_path(tmp_path, "new", ("f",)) gate.store_counts(tmp_path, new, "new", {"reportAny": 2}) - assert not old.exists() + assert gate.load_cached_counts(old) == {"reportAny": 1} assert gate.load_cached_counts(new) == {"reportAny": 2} +def test_store_evicts_only_the_oldest_entries_beyond_the_cap(tmp_path): + aged = [ + gate.cache_path(tmp_path, f"base{i}", ("f",)) + for i in range(gate.CACHE_KEEP_ENTRIES) + ] + for age, path in enumerate(aged): + gate.store_counts(tmp_path, path, f"base{age}", {"reportAny": age}) + os.utime(path, (age, age)) + newest = gate.cache_path(tmp_path, "newest", ("f",)) + gate.store_counts(tmp_path, newest, "newest", {"reportAny": 99}) + assert not aged[0].exists() + assert all(path.exists() for path in aged[1:]) + assert gate.load_cached_counts(newest) == {"reportAny": 99} + + +def test_store_never_evicts_the_entry_it_just_wrote_even_on_mtime_ties(tmp_path): + others = [ + gate.cache_path(tmp_path, f"base{i}", ("f",)) + for i in range(gate.CACHE_KEEP_ENTRIES + 2) + ] + for path in others: + gate.store_counts(tmp_path, path, path.name, {"reportAny": 1}) + os.utime(path, (9_999_999_999, 9_999_999_999)) + mine = gate.cache_path(tmp_path, "mine", ("f",)) + gate.store_counts(tmp_path, mine, "mine", {"reportAny": 2}) + assert gate.load_cached_counts(mine) == {"reportAny": 2} + survivors = list(tmp_path.glob(f"{gate.CACHE_FILE_PREFIX}*.json")) + assert len(survivors) == gate.CACHE_KEEP_ENTRIES + + def _no_fetch(ref): return None diff --git a/type-discipline-budget.json b/type-discipline-budget.json index e26ce54ede7..ab8198304bb 100644 --- a/type-discipline-budget.json +++ b/type-discipline-budget.json @@ -1,6 +1,6 @@ { "LIT001": { - "limit": 23343 + "limit": 23256 }, "LIT002": { "limit": 27213 @@ -15,7 +15,7 @@ "limit": 0 }, "LIT006": { - "limit": 1093 + "limit": 1091 }, "LIT007": { "limit": 0 @@ -27,7 +27,7 @@ "limit": 0 }, "LIT010": { - "limit": 16802 + "limit": 16783 }, "LIT011": { "limit": 5602